A regression-tree multilayer-perceptron hybrid strategy for the prediction of ore crushing-plate lifetimes

Đăng ngày 11/29/2019 6:30:35 AM | Thể loại: | Lần tải: 0 | Lần xem: 2 | Page: 12 | FileSize: 2.03 M | File type: PDF
A regression-tree multilayer-perceptron hybrid strategy for the prediction of ore crushing-plate lifetimes. Highly tensile manganese steel is in great demand owing to its high tensile strength under shock loads. All workpieces are produced through casting, because it is highly difficult to machine. The probabilistic aspects of its casting, its variable composition, and the different casting techniques must all be considered for the optimisation of its mechanical properties. A hybrid strategy is therefore proposed which combines decision trees and artificial neural networks (ANNs) for accurate and reliable prediction models for ore crushing plate lifetimes. The strategic blend of these two high-accuracy prediction models is used to generate simple decision trees which can reveal the main dataset features, thereby facilitating decisionmaking. Following a complexity analysis of a dataset with 450 different plates, the best model consisted of 9 different multilayer perceptrons, the inputs of which were only the Fe and Mn plate compositions. The model recorded a low root mean square error (RMSE) of only 0.0614 h for the lifetime of the plate: a very accurate result considering their varied lifetimes of between 746 and 6902 h in the dataset. Finally, the use of these models under real industrial conditions is presented in a heat map, namely a 2D representation of the main manufacturing process inputs with a colour scale which shows the predicted output, i.e. the expected lifetime of the manufactured plates. Thus, the hybrid strategy extracts core training dataset information in high-accuracy prediction models. This novel strategy merges the different capabilities of two families of machine-learning algorithms.
´
Contents lists available at ScienceDirect
Journal of Advanced Research
Original article
A regression-tree multilayer-perceptron hybrid strategy for the
prediction of ore crushing-plate lifetimes
Mario Juez-Gila, Ivan Nikolaevich Erdakovb, Andres Bustilloa, Danil Yurievich Pimenovc,
a Department of Civil Engineering, Universidad de Burgos, Avda Cantabria s/n, Burgos 09006, Spain
b Foundry Department, South Ural State University, Lenin Prosp. 76, Chelyabinsk 454080, Russia
c Department of Automated Mechanical Engineering, South Ural State University, Lenin Prosp. 76, Chelyabinsk 454080, Russia
h i g h l i g h t s
g r a p h i c a l
a b s t r a c t
 Dataset of plates lifetime were
obtained by 3 casting methods and
chemical composition.
 A two-steps model for prediction of
the full lifetime of plates of Hadfield
steel was proposed.
 The prediction model combines
regression trees with multilayer
perceptron (MLP)
 MLP provides accurate wears models
considering the chemical
composition.
 Regression trees provide visual
information about dataset structure
to build MLP.
a r t i c l e
i n f o
a b s t r a c t
Article history:
Highly tensile manganese steel is in great demand owing to its high tensile strength under shock loads.
Received 15 December 2018
Revised 21 March 2019
Accepted 21 March 2019
Available online 23 March 2019
All workpieces are produced through casting, because it is highly difficult to machine. The probabilistic
aspects of its casting, its variable composition, and the different casting techniques must all be considered
for the optimisation of its mechanical properties. A hybrid strategy is therefore proposed which combines
decision trees and artificial neural networks (ANNs) for accurate and reliable prediction models for ore
Keywords:
Hadfield steel
Resource savings
Lifetime prediction
Regression trees
crushing plate lifetimes. The strategic blend of these two high-accuracy prediction models is used to gen-
erate simple decision trees which can reveal the main dataset features, thereby facilitating decision-
making. Following a complexity analysis of a dataset with 450 different plates, the best model consisted
of 9 different multilayer perceptrons, the inputs of which were only the Fe and Mn plate compositions.
The model recorded a low root mean square error (RMSE) of only 0.0614 h for the lifetime of the plate:
Multi-layer perceptrons
a very accurate result considering their varied lifetimes of between 746 and 6902 h in the dataset. Finally,
Artificial intelligence
the use of these models under real industrial conditions is presented in a heat map, namely a 2D repre-
sentation of the main manufacturing process inputs with a colour scale which shows the predicted out-
put, i.e. the expected lifetime of the manufactured plates. Thus, the hybrid strategy extracts core training
Peer review under responsibility of Cairo University.
Corresponding author.
E-mail address: danil_u@rambler.ru (D.Y. Pimenov).
2090-1232/ 2019 The Authors. Published by Elsevier B.V. on behalf of Cairo University.
This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
174
M. Juez-Gil et al./Journal of Advanced Research 18 (2019) 173–184
dataset information in high-accuracy prediction models. This novel strategy merges the different capabil-
ities of two families of machine-learning algorithms. It provides a high-accuracy industrial tool for the
prediction of the full lifetime of highly tensile manganese steel plates. The results yielded a precision pre-
diction of (RMSE of 0.061 h) for the full lifetime of (light, medium, and heavy) crusher plates manufac-
tured with the three (experimental, classic, and highly efficient (new)) casting methods.
 2019 The Authors. Published by Elsevier B.V. on behalf of Cairo University. This is an open access article
Introduction
mum parameters, the new technology requires neither heavy
heads nor labour-intensive operations with the casting form both
Highly tensile manganese steel, also known as Hadfield steel,
before and after pouring to achieve the optimum angle; thereby
named after its first manufacturer, consisting of 11.5–15.0% of
decreasesing the cost of producing plates and leading to consider-
Mn and 0.9–1.4% of C demonstrates high tensile strength under
able savings on metal in the gating system and machine heads (15–
shock loads, such as in tank track operation, tractors and other
20%).
soil-removal
machines, bucket tooth
bars for
limestone, ore
As we approach the fourth technological revolution in the set-
crusher jaws, and railroad track switches on wheel sets. The afore-
ting of global competition, the analysis of all existing data from
mentioned properties are due to the interaction of steel with a
the casting process becomes increasingly relevant in terms of iden-
softer material and the absence of scuffing on the impact surface
tifying the best strategies which will optimise the mechanical
of the steel workpiece, thus causing fatigue-induced rather than
characteristics, particularly the wear resistance of components
abrasive wear. As a consequence of the difficulties associated with
which are cast using this steel type, thus creating a competitive
cutting this alloy, highly tensile manganese-steel workpieces are
advantage. Previously unknown and hidden trends can be useful,
typically produced via casting.
and comprehensible patterns found at the intersection of data-
Extensive research on improvements in this type of steel
bases, statistics, and machine-learning techniques. The size of the
reflects the active industrial interest in its mechanical properties.
database (big data or data of a specific experiment) is not essential;
Siafakas et al. [1] conducted a quantitative analysis of the amount,
the importance lies in the identification of hidden patterns, which
size, and number of particles which precipitate in situ in titanium-
would be impossible to establish with direct visual analysis or by
and aluminium-treated Hadfield steel during casting. In certain
calculating simple statistical features.
research works, heat treatment has been suggested as a means of
Casting is an inherently probabilistic process; the quality of a
increasing the micro-hardness of the cast Hadfield steel matrix
cast is primarily attributed to the chemical composition of the
[2–4]. Moreover, in several studies [5–7], the factors which can
alloy and the nature of its solidification. The objective of finding
affect the increased wear resistance of high-manganese steel have
hidden patterns in the array of technological data from the produc-
been examined.
tion and operation of steel plates used at crushing stations appears
Wear resistance appears to be the focus of most research efforts
relevant to the investigation of the reasons which cause their wear.
owing to the fact that it can extend the workpiece lifetime. There
Therefore, the objective of this study is to extend the total lifetime
are works dedicated to the study of wear resistance in high-
of (light, medium, and heavy) Hadfield steel plates for ore process-
speed pounding (HSP) of Hadfield steel to produce a thick
ing equipment by revealing new trends using machine-learning
nanocrystalline surface layer with gradient nanostructure [8].
techniques to model their wear limits.
Abbasi et al. [9] studied the abrasive wear behaviour of Al-
The solutions of complex industrial manufacturing processes, as
alloyed Hadfield steel under both high- and low-stress wear condi-
presented in this study, typically follow two separate strategies. In
tions in comparison with that of non-Al alloyed Hadfield steel.
the first one, the use of analytical models is proposed based on
Kolokoltsev et al. [10] studied the resistance of Hadfield steel
experimental data; in certain cases, this strategy is supported by
cooled at different rates. El-Fawkhry et al. and Kalandyk et al.
physical models or simulations of the manufacturing process and
[11,12] both discussed the results of austenitic matrix modification
is fine-tuned with the experimental data acquired under labora-
in high-manganese steel castings. Smith et al. [13] studied the
tory conditions. This approach has already been discussed in the
materials produced through the addition of minor amounts of
introduction for the prediction of the lifetime of ore crushing
other carbide-forming and solid-solution strengthening elements
plates. In the second approach, machine-learning techniques are
and through the heat treatment of the as-cast components under
employed to build prediction models from massive datasets; this
pressure. Te˛cza and Głownia and Głownia et al. [14,15] studied
approach could become a suitable tool for decision making.
the composite structure of high-manganese steel using vanadium
Each approach has its advantages and disadvantages. The ana-
carbides following melting and solidification. Najafabadi et al.
lytical models are typically based on homogeneous and simplified
[16] studied the wear resistance of cast Hadfield steel after adding
manufacturing processes, first, because they use data for fine-
Ti elements. Zhong et al. [17] studied the effect of the composite
tuning collected under restricted laboratory conditions (to reduce
structure of (Fe, Cr)7C3-Fe on its wear resistance and concluded
experimental costs); second, because they are meant to consider
that it was 1.34 times higher than that of the Hadfield steel. Finally,
only variables of the same nature in the manufacturing process,
Zhang et al. [18] examined a composite coating of WC/Hadfield
e.g. cutting conditions and chemical composition. However, they
steel produced via centrifugal casting to improve its impact wear
rarely mix variables of distinctly different natures, because the
resistance.
analytical and physics-based models are not designed for such
However, all aforementioned methods complicate the technol-
tasks. The most common machine-learning approaches, such as
ogy of manufacturing workpieces using Hadfield steel and cause
artificial neural networks, belong to the black-box category of
it to be more expensive. Moreover, insufficient attention has been
these techniques, i.e. they provide no equation which shows the
paid to the issue of resource conservation, with the exception of
relationship between inputs and outputs. The only manner in
the studies by Erdakov et al. [19–22], who proposed a new highly
which the information contained in those models can be extracted
efficient gating and feeding system and defined its optimum
is to query the predicted output for a certain combination of inputs
parameters for casting using green sand moulds. With the opti-
and the prediction model will provide an estimated value. Hence, if
M. Juez-Gil et al./Journal of Advanced Research 18 (2019) 173–184
175
useful information would be extracted from these models, they
Research material and methods
would require either a 2D or a 3D representation of their predic-
tions [23–25]. This approach has been successfully validated for
Before developing a model for the prediction of the lifetime of
several industrial tasks, for example, in predicting surface rough-
crushing plates and prior to conducting an experiment, it is neces-
ness [26–28], surface quality [29], and cutting-tool wear [30,31],
sary to determine the properties of the materials that are used, the
among others. Furthermore, the datasets required to train these
parameters of the cast products, as well as the casting and investi-
models should be as big and diverse as possible. However, indus-
gation methods.
trial data are limited to real-life scenarios, given the reluctance of
the industry to finance tests which go beyond the specification of
manufacturing conditions. Nevertheless, such tests are essential
in the training process of machine-learning techniques. Moreover,
Plate manufacturing and casting methods
part of the information in the datasets, rather than relating to the
manufacturing problem, is related to the experimental design
method itself (e.g. if in a certain cutting process we test a range
of cutting tools, each having an additional tooth and an extra
5 mm diameter in addition to those of the preceding one, as per
the specifications of the manufacturer, then the machine-learning
model will conclude that the number of teeth and the diameter
of the tool are two completely correlated inputs, playing the same
role in the cutting process).
Although the most common machine-learning techniques
belong to the black-box category, there are certain machine-
learning techniques, such as decision trees, that provide visual
information on the process. However, these techniques are often
simpler than artificial neural networks (ANNs) and might not per-
form equally well in very complex processes, although they are free
from the complexity and tediousness of fine-tuning the ANN model
parameters.In thisstudy, we proposea hybridstrategyto overcome
this limitation, which combines decision trees for extraction of the
main information included in the training dataset with ANNs for
high-accuracy prediction models. This strategy combines the great-
est advantagesof both machine-learning techniques: to understand
the main features of the dataset, it generates rapid, visual, and sim-
ple decision trees, thereby facilitating decision-making on inputs
for simple, yet accurate, ANN models.
Themodellingprocesswasdividedintothreestages.First,avisual
pre-analysis wasperformed usingreducederror pruning(REP)trees,
whichadvisedsplittingthedatasetintoninesubsetsandconsidering
only eight chemical components as inputs for the prediction model.
Then, the 9 independent prediction models (one for each subset)
for 13 different multilayer perceptron (MLP) structures (the most
promising combinations of chemical components) were trained
and the most accurate models were identified. The test of only some
of the possible combinations of chemical composition of the ore
plates in the MLPs is an industrial requirement (to reduce the mod-
elling effort). Meanwhile, the efficient selection of the features used
in the training stage of the MLPs is an interesting challenge owing
to the high number of possible combinations. Then, the complexity
of the MLP structure was considered to select the best prediction
model from an industrial perspective. Finally, the identification of a
high-accuracypredictionmodel may beinsufficientforitssuccessful
implementation under real industrial conclusions. Therefore, the
bestofalltheproposedmodelswasusedtobuildaheatmapofdirect
industrial use, namely a 2D representation of the main inputs of the
manufacturing process with a colour scale showing the predicted
output, i.e. the wear limit of the manufactured plates.
This strategy is able to deal with data of different natures, the
chemical composition of the plates, and the manufacturing process
of the plates in our case study. Moreover, the strategy produces
models which are optimised in terms of accuracy, with a reduced
In this research, the following materials and research methods
were used. The chemical composition (%) of Hadfield steel is listed
in Table 1. Hadfield steel contains 84.3–87.3% iron (Fe), 11.5–15.0%
magnesium (Mn), 0.9–1.4% carbon (C), 0.3–1.0% silicon (Si), and 0–
3% impurities. The physical and mechanical properties of Hadfield
steel in its austenite form are the following: a density (q) of
7890 kg/m3, a Brinell hardness HB of 186–229, and a strength, r,
of 654–830 MPa; mechanical properties: ductile alloy. The physical
and the mechanical properties of ferro-chromium industrial-type
ores with high-melt impurities are the following: a density (q) of
2235 kg/m3, a Brinell hardness (HB) of 438–662, and a strength,
r, of 307–522 MPa. mechanical properties: fragile ore mineral.
The gating and feeding system parameter variation methods are
categorised into classic, experimental, and high-efficiency (new)
(Fig. 1).
The classic method involved a massive head for the supply of
molten metal through the gating system. After pouring the molten
metal into the mould, the form was horizontally rotated at 25
(Fig. 1a). In the experimental method, a significantly reduced head
was used in the corner of the plate. The supply of molten metal was
not through the gating system to the head; molten metal entered
from the end of the plate and there was no rotation of the form
after pouring (Fig. 1b). The new, highly efficient method permitted
the molten metal to enter from the end and the side of the plate.
The supply of molten metal through the gating system was
switched to both the end and the side of the plate. Moreover, the
form was not turned after pouring (Fig. 1b).
The tests were conducted on cast plates with the following
designs (Fig. 2a–c): a – ‘light’, b – a ‘medium’, and c – a ‘heavy’
design.
Each plate has a matching one with negligible variation in
weight, average wall thickness, and design. These plates are widely
used in ferroalloy crushing stations, have a relatively simple
design, and their production is fraught with several thermal stress,
shrinkage, and drop defects.
The plates are conventionally classified into ‘light’, ‘medium’,
and ‘heavy’; this categorisation identifies the effect of the plate
geometrics (primarily that of the average wall thickness) on the
severity of production-related defects.
To determine the chemical composition of the alloy, spectral
analysis was performed on a modern ISKROLINE 300 static-
emission spectrometer with a concentration measuring range of
0.0001–0.1%.
The measurement of the steel temperature as it crystallised in
the mould was performed by applying tungsten-rhenium thermo-
couples (VR 5/20) which were connected to EPR-08mz, an auto-
matic electronic potentiometer. The melt temperature was
measured in degrees Celsius.
number of inputs; the reduction of the number of inputs is an addi-
tional industrial requirement in order for such models to be imple-
mented in factories, because they will reduce the costs of analysis
Table 1
Chemical composition (%) of Hadfield steel.
(i.e. if a percentage of only 2 rather than 16 chemical components
Fe
Mn
C
Si
Impurities
should be evaluated in a workpiece, then the analytical process
will cost less).
84.3–87.3
11.5–15.0
0.9–1.4
0.3–1.0
0–3
HƯỚNG DẪN DOWNLOAD TÀI LIỆU

Bước 1:Tại trang tài liệu slideshare.vn bạn muốn tải, click vào nút Download màu xanh lá cây ở phía trên.
Bước 2: Tại liên kết tải về, bạn chọn liên kết để tải File về máy tính. Tại đây sẽ có lựa chọn tải File được lưu trên slideshare.vn
Bước 3: Một thông báo xuất hiện ở phía cuối trình duyệt, hỏi bạn muốn lưu . - Nếu click vào Save, file sẽ được lưu về máy (Quá trình tải file nhanh hay chậm phụ thuộc vào đường truyền internet, dung lượng file bạn muốn tải)
Có nhiều phần mềm hỗ trợ việc download file về máy tính với tốc độ tải file nhanh như: Internet Download Manager (IDM), Free Download Manager, ... Tùy vào sở thích của từng người mà người dùng chọn lựa phần mềm hỗ trợ download cho máy tính của mình  
2 lần xem

A regression-tree multilayer-perceptron hybrid strategy for the prediction of ore crushing-plate lifetimes. Highly tensile manganese steel is in great demand owing to its high tensile strength under shock loads. All workpieces are produced through casting, because it is highly difficult to machine. The probabilistic aspects of its casting, its variable composition, and the different casting techniques must all be considered for the optimisation of its mechanical properties. A hybrid strategy is therefore proposed which combines decision trees and artificial neural networks (ANNs) for accurate and reliable prediction models for ore crushing plate lifetimes. The strategic blend of these two high-accuracy prediction models is used to generate simple decision trees which can reveal the main dataset features, thereby facilitating decisionmaking. Following a complexity analysis of a dataset with 450 different plates, the best model consisted of 9 different multilayer perceptrons, the inputs of which were only the Fe and Mn plate compositions. The model recorded a low root mean square error (RMSE) of only 0.0614 h for the lifetime of the plate: a very accurate result considering their varied lifetimes of between 746 and 6902 h in the dataset. Finally, the use of these models under real industrial conditions is presented in a heat map, namely a 2D representation of the main manufacturing process inputs with a colour scale which shows the predicted output, i.e. the expected lifetime of the manufactured plates. Thus, the hybrid strategy extracts core training dataset information in high-accuracy prediction models. This novel strategy merges the different capabilities

Nội dung

Journal of Advanced Research 18 (2019) 173–184 Contents lists available at ScienceDirect Journal of Advanced Research journal homepage: www.elsevier.com/locate/jare Original article A regression-tree multilayer-perceptron hybrid strategy for the prediction of ore crushing-plate lifetimes Mario Juez-Gila, Ivan Nikolaevich Erdakovb, Andres Bustilloa, Danil Yurievich Pimenovc,⇑ a Department of Civil Engineering, Universidad de Burgos, Avda Cantabria s/n, Burgos 09006, Spain b Foundry Department, South Ural State University, Lenin Prosp. 76, Chelyabinsk 454080, Russia c Department of Automated Mechanical Engineering, South Ural State University, Lenin Prosp. 76, Chelyabinsk 454080, Russia h i g h l i g h t s g r a p h i c a l a b s t r a c t Dataset of plates lifetime were obtained by 3 casting methods and chemical composition. A two-steps model for prediction of the full lifetime of plates of Hadfield steel was proposed. The prediction model combines regression trees with multilayer perceptron (MLP) MLP provides accurate wears models considering the chemical composition. Regression trees provide visual information about dataset structure to build MLP. a r t i c l e i n f o a b s t r a c t Article history: Received 15 December 2018 Revised 21 March 2019 Accepted 21 March 2019 Available online 23 March 2019 Keywords: Hadfield steel Resource savings Lifetime prediction Regression trees Multi-layer perceptrons Artificial intelligence Highly tensile manganese steel is in great demand owing to its high tensile strength under shock loads. All workpieces are produced through casting, because it is highly difficult to machine. The probabilistic aspects of its casting, its variable composition, and the different casting techniques must all be considered for the optimisation of its mechanical properties. A hybrid strategy is therefore proposed which combines decision trees and artificial neural networks (ANNs) for accurate and reliable prediction models for ore crushing plate lifetimes. The strategic blend of these two high-accuracy prediction models is used to gen-erate simple decision trees which can reveal the main dataset features, thereby facilitating decision-making. Following a complexity analysis of a dataset with 450 different plates, the best model consisted of 9 different multilayer perceptrons, the inputs of which were only the Fe and Mn plate compositions. The model recorded a low root mean square error (RMSE) of only 0.0614 h for the lifetime of the plate: a very accurate result considering their varied lifetimes of between 746 and 6902 h in the dataset. Finally, the use of these models under real industrial conditions is presented in a heat map, namely a 2D repre-sentation of the main manufacturing process inputs with a colour scale which shows the predicted out- put, i.e. the expected lifetime of the manufactured plates. Thus, the hybrid strategy extracts core training Peer review under responsibility of Cairo University. ⇑ Corresponding author. E-mail address: danil_u@rambler.ru (D.Y. Pimenov). https://doi.org/10.1016/j.jare.2019.03.008 2090-1232/ 2019 The Authors. Published by Elsevier B.V. on behalf of Cairo University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). 174 M. Juez-Gil et al./Journal of Advanced Research 18 (2019) 173–184 dataset information in high-accuracy prediction models. This novel strategy merges the different capabil-ities of two families of machine-learning algorithms. It provides a high-accuracy industrial tool for the prediction of the full lifetime of highly tensile manganese steel plates. The results yielded a precision pre-diction of (RMSE of 0.061 h) for the full lifetime of (light, medium, and heavy) crusher plates manufac-tured with the three (experimental, classic, and highly efficient (new)) casting methods. 2019 The Authors. Published by Elsevier B.V. on behalf of Cairo University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). Introduction Highly tensile manganese steel, also known as Hadfield steel, named after its first manufacturer, consisting of 11.5–15.0% of Mn and 0.9–1.4% of C demonstrates high tensile strength under shock loads, such as in tank track operation, tractors and other soil-removal machines, bucket tooth bars for limestone, ore crusher jaws, and railroad track switches on wheel sets. The afore-mentioned properties are due to the interaction of steel with a softer material and the absence of scuffing on the impact surface of the steel workpiece, thus causing fatigue-induced rather than abrasive wear. As a consequence of the difficulties associated with cutting this alloy, highly tensile manganese-steel workpieces are typically produced via casting. Extensive research on improvements in this type of steel reflects the active industrial interest in its mechanical properties. Siafakas et al. [1] conducted a quantitative analysis of the amount, size, and number of particles which precipitate in situ in titanium-and aluminium-treated Hadfield steel during casting. In certain research works, heat treatment has been suggested as a means of increasing the micro-hardness of the cast Hadfield steel matrix [2–4]. Moreover, in several studies [5–7], the factors which can affect the increased wear resistance of high-manganese steel have been examined. Wear resistance appears to be the focus of most research efforts owing to the fact that it can extend the workpiece lifetime. There are works dedicated to the study of wear resistance in high-speed pounding (HSP) of Hadfield steel to produce a thick nanocrystalline surface layer with gradient nanostructure [8]. Abbasi et al. [9] studied the abrasive wear behaviour of Al-alloyed Hadfield steel under both high- and low-stress wear condi-tions in comparison with that of non-Al alloyed Hadfield steel. Kolokoltsev et al. [10] studied the resistance of Hadfield steel cooled at different rates. El-Fawkhry et al. and Kalandyk et al. [11,12] both discussed the results of austenitic matrix modification in high-manganese steel castings. Smith et al. [13] studied the materials produced through the addition of minor amounts of other carbide-forming and solid-solution strengthening elements and through the heat treatment of the as-cast components under pressure. Te˛cza and Głownia and Głownia et al. [14,15] studied the composite structure of high-manganese steel using vanadium carbides following melting and solidification. Najafabadi et al. [16] studied the wear resistance of cast Hadfield steel after adding Ti elements. Zhong et al. [17] studied the effect of the composite structure of (Fe, Cr)7C3-Fe on its wear resistance and concluded that it was 1.34 times higher than that of the Hadfield steel. Finally, Zhang et al. [18] examined a composite coating of WC/Hadfield steel produced via centrifugal casting to improve its impact wear resistance. However, all aforementioned methods complicate the technol-ogy of manufacturing workpieces using Hadfield steel and cause it to be more expensive. Moreover, insufficient attention has been paid to the issue of resource conservation, with the exception of the studies by Erdakov et al. [19–22], who proposed a new highly efficient gating and feeding system and defined its optimum parameters for casting using green sand moulds. With the opti- mum parameters, the new technology requires neither heavy heads nor labour-intensive operations with the casting form both before and after pouring to achieve the optimum angle; thereby decreasesing the cost of producing plates and leading to consider-able savings on metal in the gating system and machine heads (15– 20%). As we approach the fourth technological revolution in the set-ting of global competition, the analysis of all existing data from the casting process becomes increasingly relevant in terms of iden-tifying the best strategies which will optimise the mechanical characteristics, particularly the wear resistance of components which are cast using this steel type, thus creating a competitive advantage. Previously unknown and hidden trends can be useful, and comprehensible patterns found at the intersection of data-bases, statistics, and machine-learning techniques. The size of the database (big data or data of a specific experiment) is not essential; the importance lies in the identification of hidden patterns, which would be impossible to establish with direct visual analysis or by calculating simple statistical features. Casting is an inherently probabilistic process; the quality of a cast is primarily attributed to the chemical composition of the alloy and the nature of its solidification. The objective of finding hidden patterns in the array of technological data from the produc-tion and operation of steel plates used at crushing stations appears relevant to the investigation of the reasons which cause their wear. Therefore, the objective of this study is to extend the total lifetime of (light, medium, and heavy) Hadfield steel plates for ore process-ing equipment by revealing new trends using machine-learning techniques to model their wear limits. The solutions of complex industrial manufacturing processes, as presented in this study, typically follow two separate strategies. In the first one, the use of analytical models is proposed based on experimental data; in certain cases, this strategy is supported by physical models or simulations of the manufacturing process and is fine-tuned with the experimental data acquired under labora-tory conditions. This approach has already been discussed in the introduction for the prediction of the lifetime of ore crushing plates. In the second approach, machine-learning techniques are employed to build prediction models from massive datasets; this approach could become a suitable tool for decision making. Each approach has its advantages and disadvantages. The ana-lytical models are typically based on homogeneous and simplified manufacturing processes, first, because they use data for fine-tuning collected under restricted laboratory conditions (to reduce experimental costs); second, because they are meant to consider only variables of the same nature in the manufacturing process, e.g. cutting conditions and chemical composition. However, they rarely mix variables of distinctly different natures, because the analytical and physics-based models are not designed for such tasks. The most common machine-learning approaches, such as artificial neural networks, belong to the black-box category of these techniques, i.e. they provide no equation which shows the relationship between inputs and outputs. The only manner in which the information contained in those models can be extracted is to query the predicted output for a certain combination of inputs and the prediction model will provide an estimated value. Hence, if M. Juez-Gil et al./Journal of Advanced Research 18 (2019) 173–184 175 useful information would be extracted from these models, they would require either a 2D or a 3D representation of their predic-tions [23–25]. This approach has been successfully validated for several industrial tasks, for example, in predicting surface rough-ness [26–28], surface quality [29], and cutting-tool wear [30,31], among others. Furthermore, the datasets required to train these models should be as big and diverse as possible. However, indus-trial data are limited to real-life scenarios, given the reluctance of the industry to finance tests which go beyond the specification of manufacturing conditions. Nevertheless, such tests are essential in the training process of machine-learning techniques. Moreover, part of the information in the datasets, rather than relating to the manufacturing problem, is related to the experimental design method itself (e.g. if in a certain cutting process we test a range of cutting tools, each having an additional tooth and an extra 5 mm diameter in addition to those of the preceding one, as per the specifications of the manufacturer, then the machine-learning model will conclude that the number of teeth and the diameter of the tool are two completely correlated inputs, playing the same role in the cutting process). Although the most common machine-learning techniques belong to the black-box category, there are certain machine-learning techniques, such as decision trees, that provide visual information on the process. However, these techniques are often simpler than artificial neural networks (ANNs) and might not per-form equally well in very complex processes, although they are free from the complexity and tediousness of fine-tuning the ANN model parameters.In thisstudy, we proposea hybridstrategyto overcome this limitation, which combines decision trees for extraction of the main information included in the training dataset with ANNs for high-accuracy prediction models. This strategy combines the great-est advantagesof both machine-learning techniques: to understand the main features of the dataset, it generates rapid, visual, and sim-ple decision trees, thereby facilitating decision-making on inputs for simple, yet accurate, ANN models. Themodellingprocesswasdividedintothreestages.First,avisual pre-analysis wasperformed usingreducederror pruning(REP)trees, whichadvisedsplittingthedatasetintoninesubsetsandconsidering only eight chemical components as inputs for the prediction model. Then, the 9 independent prediction models (one for each subset) for 13 different multilayer perceptron (MLP) structures (the most promising combinations of chemical components) were trained and the most accurate models were identified. The test of only some of the possible combinations of chemical composition of the ore plates in the MLPs is an industrial requirement (to reduce the mod-elling effort). Meanwhile, the efficient selection of the features used in the training stage of the MLPs is an interesting challenge owing to the high number of possible combinations. Then, the complexity of the MLP structure was considered to select the best prediction model from an industrial perspective. Finally, the identification of a high-accuracypredictionmodel may beinsufficientforitssuccessful implementation under real industrial conclusions. Therefore, the bestofalltheproposedmodelswasusedtobuildaheatmapofdirect industrial use, namely a 2D representation of the main inputs of the manufacturing process with a colour scale showing the predicted output, i.e. the wear limit of the manufactured plates. This strategy is able to deal with data of different natures, the chemical composition of the plates, and the manufacturing process of the plates in our case study. Moreover, the strategy produces models which are optimised in terms of accuracy, with a reduced number of inputs; the reduction of the number of inputs is an addi-tional industrial requirement in order for such models to be imple- mented in factories, because they will reduce the costs of analysis Research material and methods Before developing a model for the prediction of the lifetime of crushing plates and prior to conducting an experiment, it is neces-sary to determine the properties of the materials that are used, the parameters of the cast products, as well as the casting and investi-gation methods. Plate manufacturing and casting methods In this research, the following materials and research methods were used. The chemical composition (%) of Hadfield steel is listed in Table 1. Hadfield steel contains 84.3–87.3% iron (Fe), 11.5–15.0% magnesium (Mn), 0.9–1.4% carbon (C), 0.3–1.0% silicon (Si), and 0– 3% impurities. The physical and mechanical properties of Hadfield steel in its austenite form are the following: a density (q) of 7890 kg/m3, a Brinell hardness HB of 186–229, and a strength, r, of 654–830 MPa; mechanical properties: ductile alloy. The physical and the mechanical properties of ferro-chromium industrial-type ores with high-melt impurities are the following: a density (q) of 2235 kg/m3, a Brinell hardness (HB) of 438–662, and a strength, r, of 307–522 MPa. mechanical properties: fragile ore mineral. The gating and feeding system parameter variation methods are categorised into classic, experimental, and high-efficiency (new) (Fig. 1). The classic method involved a massive head for the supply of molten metal through the gating system. After pouring the molten metal into the mould, the form was horizontally rotated at 25 (Fig. 1a). In the experimental method, a significantly reduced head was used in the corner of the plate. The supply of molten metal was not through the gating system to the head; molten metal entered from the end of the plate and there was no rotation of the form after pouring (Fig. 1b). The new, highly efficient method permitted the molten metal to enter from the end and the side of the plate. The supply of molten metal through the gating system was switched to both the end and the side of the plate. Moreover, the form was not turned after pouring (Fig. 1b). The tests were conducted on cast plates with the following designs (Fig. 2a–c): a – ‘light’, b – a ‘medium’, and c – a ‘heavy’ design. Each plate has a matching one with negligible variation in weight, average wall thickness, and design. These plates are widely used in ferroalloy crushing stations, have a relatively simple design, and their production is fraught with several thermal stress, shrinkage, and drop defects. The plates are conventionally classified into ‘light’, ‘medium’, and ‘heavy’; this categorisation identifies the effect of the plate geometrics (primarily that of the average wall thickness) on the severity of production-related defects. To determine the chemical composition of the alloy, spectral analysis was performed on a modern ISKROLINE 300 static-emission spectrometer with a concentration measuring range of 0.0001–0.1%. The measurement of the steel temperature as it crystallised in the mould was performed by applying tungsten-rhenium thermo-couples (VR 5/20) which were connected to EPR-08mz, an auto-matic electronic potentiometer. The melt temperature was measured in degrees Celsius. Table 1 Chemical composition (%) of Hadfield steel. (i.e. if a percentage of only 2 rather than 16 chemical components should be evaluated in a workpiece, then the analytical process will cost less). Fe 84.3–87.3 Mn 11.5–15.0 C 0.9–1.4 Si 0.3–1.0 Impurities 0–3 176 M. Juez-Gil et al./Journal of Advanced Research 18 (2019) 173–184 Fig. 1. Designs of a feeding and gating system (head locations shown as dotted lines): a–classic horizontal form at 25 after pouring, b–experimental, and c–high-efficiency (new). Fig. 2. Mechanical 3D drawing of stationary plate: a – a ‘light’ design, length: 1165 m, width: 950 mm, and height: 106 mm; b – a ‘medium’ design, length: 1500 m, width: 950 mm, and height: 149 mm; and c – a ‘heavy’ design, length: 1080 m, width: 1045 mm, and height: 249 mm. Experimental The experimental investigations were conducted from February 2013, to December 2016, in an operational foundry shop of the Katav–Ivanovsk Foundry, which is part of the Chelyabinsk Elec-trometallurgical Integrated Plant (ChEMK, Russia). During the experimental investigations, approximately 50 meltings of Had-field steel were conducted and 450 crusher plates, 150 of each type (light, medium, and heavy), were obtained using the three different methods (classic, experimental, and high-efficiency). Each melting produced nine forms, in which cavities existed for three types of plates with three variants of gating and feeding sys- tems. An additional sample was produced with each cast plate for the chemical analysis of the alloy. All samples and plates were labelled by melt number. Before installation in the crushing station, the plates were weighed. Then, the ore grinding time was recorded with a stop-watch throughout the three crushing divisions (SMD-109A, SMD-110A, and B9-2H) in parallel mode. The complete abrasion of the plate edges was determined by visual inspection; after weighing the worn plate, if its weight loss had reached a limit value (mar-ginal mass loss: light plate = 90 kg, medium plate = 170 kg, and heavy plate = 240 kg), the time on the stopwatch was considered to be the total plate lifetime. One-off forms of the plates were made via the cold-box-amine process. The average wall thickness of the plates was: 50 mm for M. Juez-Gil et al./Journal of Advanced Research 18 (2019) 173–184 177 the light plate, 70 mm for the medium plate, and 85 mm for the heavy plate. Mould filling was performed in 7, 8, and 9 min for the light, medium, and heavy plates, respectively. The area of the narrow sections of the gating systems was as follows: 23.00 cm2 for the light plate, 28.00 cm2 for the medium, and 33 cm2 for the massive plate. The temperature of the molten steel poured into the mould was 1570 C for the light plate, 1540 C for the medium plate, and 1520 C for the heavy plate. The volume economy achieved for the experimental and high-efficiency casting methods was as follows: 7500 cm3 for the light plate, 15,000 cm3 for the medium plate, and 41,000 cm3 for the massive plate. The volume was three times greater using the classic casting method. The control of the chemical composition of the marked steel samples was carried out on sixteen elements: Fe, C, Si, Mn, P, S, Mo, Ni, Al, Co, Cu, Nb, Ti, V, and W. The pouring temperature of the steel lied within 1520–1570 C. The hardness coefficients of the chrome ore and the prill shape were determined to be f = 0.1 317 = 30.1 and SC = (193 240)/29 = 1597, respectively. Modelling Dataset description From an industrial perspective, there is a clear output for the wear-limit experiments which should be considered in the dataset, namely the total time during which the plates remain in the crush-ing station before they pass a limit (time). The dataset included up to 11 inputs of two clearly different natures: the first group of inputs described the chemical composition of the plates in mass percentages, whereas the second group had two characteristics which described the casting process of the plates. In the first group, the percentages of iron (Fe), carbon (C), silicon (Si), manganese (Mn), phosphorus (P), sulphur (S), chromium (Cr), molybdenum (Mo), nickel (Ni), aluminium (Al), cobalt (Co), copper (Cu), neody-mium (Nb), titanium (Ti), vanadium (V), and tungsten (W) were all recorded. In the second group, the casting method (Method) and the type of cast plate (Type) which have been previously described in Section 2 were recorded. All inputs of the first group are continuous variables, whereas the inputs of the second group are nominal and can each take three different values. As outlined in the introduction, these inputs were selected because they are the main indicators available to the process engineer regarding the quality and source of the plate, as well as the different casting Table 2 Dataset variables and their variation range. methods through which it was formed. The dataset included 450 different plate compositions cast in a balanced proportion with the nine different casting conditions. Table 2 summarises the inputs and the output, their units, and the range of values in the dataset; the output variable, time, is shown in bold. The dataset is included as supplementary material for further research. Because the total time during which the plates remain in the crushing station before they reach their breakage limit is a contin-uous output, its prediction is a regression problem. Machine-learning techniques One of the main purposes of machine-learning techniques is to solve classification and regression problems. If the output can only receive a discrete number of values or classes, the task is referred to as classification; however, if the output is a continuous value, the problem must be solved with a regression. Regression trees [32] are a popular and effective machine-learning approach for the solution of regression problems. In our research, Reduced Error Prunning (REP) trees were used; more specifically, their implementation is referred to as REPTree [33]. A regression tree is a decision tree, the predicted outcome of which is a continuous value. This type of predictive model consists of a set of three different types of nodes: one root node, the internal nodes or branches, and the terminal nodes or leaves. Root and internal nodes serve to make decisions depending on one of the input attri-butes. Alternatively, each terminal node provides a prediction by means of a linear model of the inputs. To summarise, regression trees consist of a series of decisions made from the top of the tree to the bottom, where a leaf node is reached [34]; then, a continu-ous outcome is predicted. ANNs, known for their capabilities as universal approximators [36], are a powerful non-linear family of techniques which draw their inspiration from neuroscience [35]. A neural network is a col-lection of nodes, also referred to as neurons [37], which perform simple operations, i.e. typically, a sum of the weighted inputs fol-lowed by the application of an activation function to that sum. The neurons are distributed in multiple layers, where, with the exception of the input and the output layers of the network, the neuronal outputs of one layer will be the inputs for the neurons in the following layer. Each neuron input is associated with a weight which has to be fitted during the network training process, typically through back-propagation algorithms [38], such as the stochastic gradient descent [39]. The use of ANNs to solve regression problems could even be described as a trend in machine learning [40]. ANNs have the capa- bility of outperforming other techniques, such as, for example, the Variable Iron Carbon Silicon Manganese Phosphorus Sulfur Chromium Molybdenum Nickel Aluminium Cobalt Copper Neodymium Titanium Vanadium Tungsten Casting method Type of cast plate Total lifetime Abbreviation Fe C Si Mn P S Cr Mo Ni Al Co Cu Nb Ti V W Method Type time Range Units 85.357–87.172 % 0.818–1.032 % 0.410–0.636 % 11.098–12.832 % 0.028–0.056 % 0.012–0.032 % 0.029–0.262 % 0.008–0.016 % 0.075–0.125 % 0.007–0.011 % 0.015–0.021 % 0.085–0.099 % 0.004–0.007 % 0.001–0.004 % 0.016–0.023 % 0.043–0.063 % High-efficiency, experimental, None classic Light, medium, heavy None 746.368–6902.709 h aforementioned regression trees. There are several types of ANNs, e.g. feedforward, radial basis functions (RBFs), and recurrent neural networks (RNN). Each type addresses a very specific type of prob-lem. In this study, an MLP, which is part of the family of feedfor-ward networks, was applied to predict the lifetime of steel plates. MLPs had a large impact within the research community [41]. A perceptron [42] is a linear classifier, i.e. a straight line can be used to divide input data into two categories (e.g. true and false). Through the combination of several perceptrons in an MLP architecture, non-linear classification, or regression problems can be addressed by distinguishing data which are not linearly separa-ble [43]. Methodology The Waikato Environment for Knowledge Analysis (WEKA) soft-ware tool [44] was used to build the machine-learning models and to conduct the experiments. Its implementation of the algorithms 178 M. Juez-Gil et al./Journal of Advanced Research 18 (2019) 173–184 will be described in Section 3.2. All attributes of the data set, except for the target value, were normalised in a pre-processing step which improved the training process for experimentation with the models. A k-fold cross-validation technique was selected for the evalua- tion step. In cross-validation, the data were randomly split into k Visual pre-analysis using REPTrees Typically, data from industrial sources include certain major features which can be linked to the nature of the industrial prob-lem, as well as the experimental design; however, these features will not necessarily be apparent to the programmer who is respon- sible for building the prediction model. If these features are not subsets or folds. When using this technique, the under- taken into account, the models can be very inaccurate. Therefore, evaluation predictive model was trained k times; at each training stage, one fold was used as the test data and the remaining k 1 folds as training data. Each fold can only be used once for testing because the data used during validation will not have been used in the training stage, thus providing a better generalisation of the model [45]. A well-generalised model is capable of predicting tar-get values from new input data [34]. The repetition of cross-validation in several operations can ensure that statistical value is attached to the average error of the prediction models. In this research, a 10-fold cross-validation technique repeated 10 times (10 10 cross-validation) was employed; therefore, each result was an average of 100 runs [46]. The performance of a machine-learning model was assessed through the use of evaluation metrics. Two of the best overall mea-sures in regression are the root-mean-square error (RMSE) and the mean absolute error (MAE) [47]. In this study, both were selected for the evaluation of the effectiveness of the models; although cer-tain authors have stated that the RMSE is not a good choice for determining the average model performance [48], others have pos-tulated that the RMSE is more appropriate than the MAE in some specific cases [49]. In our case, the hourly units of both RMSE and MAE were the same as the predicted target attribute. Obvi-ously, the lower the value of the RMSE and MAE is, the better the model is. The following expressions were used to determine the RMSE and MAE: sffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffi RMSE ¼ i¼1 yi yi 2; MAE ¼ Pi¼1yi yi; where, n represents the number of instances of the test subset, i refers to the instance when it is used for the current prediction, yi is the predicted value, and yi is the actual value of the output variable. Results and discussion The results of the prediction models generated from the exper-imental dataset will be presented in this section. First, the mod-elling results following different analyses will be discussed in detail. Then, the industrial implementations of the best model will be outlined. Modelling results The modelling process, as presented in the Introduction, was divided into three stages. First a visual pre-analysis was performed using REPTrees. Then, the conclusion of the pre-analysis was used to split the dataset into nine subsets and to build nine independent prediction models, one for each subset; different MLP configura- tions were trained and the results of their performance were dis- in this research, a regression model using a REPTree was first trained to take this possibility into account. The REPTree parameter values were the default options in WEKA. The most useful informa-tion which can be obtained from the resulting model is the tree structure that it generates, as shown in Fig. 3, where only two out of eighteen features were used by the tree. These features coin-cide with the group which describes the casting process of the plates. Therefore, we can intuitively expect that the influence of the chemical composition on the wear-limit resistance of the steel plates will be different for the nine leaves: one for each pair of Type of Cast Plate–Casting Method. Therefore, the dataset can be split into nine subsets with different behaviours. If we analyse the model accuracy, the model achieved an RMSE value of 1.81 h and a MAE value of 1.51 h. These errors, although apparently very good considering the standard deviation of 2125.52 h of the full data set, are quite the opposite: if we look closely at the data which corre-spond to each subset of each leaf of the tree, their standard devia-tions were between 1.13 and 2.24; hence, the obtained error value was not acceptable. Upon completion of this pre-analysis, an ANN model was built with the aim of improving the accuracy of the REPTree model. The reason for this strategy is attributed to the fact that regression trees are one of the simplest machine-learning approaches, whereas ANNs are typically more precise at predicting complex processes, such as the plate wear limit. Therefore, the most well-known ANN structure, the MLP, was selected for this task. After performing a parameter tuning process, the best performance was achieved with the WEKA default options with the exceptions of the following. The number of neurons in the hidden layer: the same as the number of attributes (18). The learning rate: 0.5. The momentum: 0.1. The training time (number of epochs): 10,000. The RMSE of the model, considering the full dataset, was 0.874 h and its MAE was 0.657 h, which clearly outperformed the REPTree model. Additionally, the training time of this model (25.03 s) was significantly higher than that of the REPTree (0.0011 s). Both training times were obtained with a workstation equipped with an Intel Core i7 6700 3.4-GHz processor, 16 GB RAM, and an NVIDIA Titan Xp GPU. Subset modelling The analysis of the REPTree allowed us to conclude that nine different subsets were present in the dataset and that two of the inputs were sufficient to define them: casting method and type of cast plate. Thus, having divided the dataset into nine subsets, a REPTree for each subset with a WEKA default parameter config-uration was built. Table 3 lists the performance of the REPTree models for each subset in terms of the RMSE and the MAE, as well as the chemical elements which were selected by the REPTree algo-rithm to build each regression tree. According to the MAE value (within the range of 0.165–0.442 h), in all nine cases, the generated cussed. Finally, the complexity of the MLP structure was models outperformed the REPTree considering the full dataset (a considered to select the best prediction model from an industrial perspective. MAE value of 1.51 h); the best MLP model (with a MAE value of 0.657 h) was built using the full dataset (Section 4.1.1). M. Juez-Gil et al./Journal of Advanced Research 18 (2019) 173–184 179 Fig. 3. Reduced-error pruning tree (REPTree) obtained for a period of the plates (in hours) prediction using the full dataset. Table 3 Types of cast plate and casting method tree models, indicating the chemical elements selected by each regression tree and their performance indicators (RMSE and MAE). Cast Plate Type Casting Method Alloy elements chosen by regression tree RMSE (h) MAE (h) Light Experimental Classic High-efficiency Medium Experimental Classic High-efficiency Heavy Experimental Classic

Tài liệu liên quan