An Approach of Steel Plates Fault Diagnosis in Multiple Classes Decision Making

Simić, Dragan; Svirăević, Vasa; Simić, Svetlana

doi:10.1007/978-3-319-07617-1_8

Cited by 5 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While it is straightforward for human to perform classification, machines require complex algorithms to perform the same task. In [46], several ML methods, such as random forest and support vector machine, were used to form an intelligent fault diagnosis system for inferring fault status in steel plate manufacturing industry. The goal of the system is to improve manufacturing production line by reducing faulty plates.…”

Section: Supervised Machine Learningmentioning

confidence: 99%

See 1 more Smart Citation

Supporting Decision Making With an Ariz-Based Model for Smart Manufacturing

Koay

Tan

Teh

et al. 2023

MJCS

View full text Add to dashboard Cite

Smart manufacturing has transformed the way decisions are made. By accelerating the delivery of data to the various decision points, more rapid decision-making processes can be realized. A generic Decision Support System (DSS) utilizes an efficient technique, which integrates the algorithm for inventive problem solving (ARIZ) and supervised machine learning into a model for supporting various automated decision making processes. The proposed model is to examine the theoretical framework of ARIZ by devising an ARIZ-based DSS model. It incorporates supervised ML algorithms to assist decision making processes. Three case studies from the manufacturing sector are evaluated. The results indicate the capability of the proposed DSS in achieving a high accuracy rate and, at the same time reducing the time and resources required for decision making. Our study has simplified the data processing and extraction processes through an automated ARIZ-based DSS model; therefore enabling a non-technical user the opportunity to harvest the vast knowledge from the collected data for efficient decision making.

show abstract

Section: Supervised Machine Learningmentioning

confidence: 99%

“…In the first case study, we examine the manufacturing process of steel plates. Defective products impose a high cost for the steel product manufacturers [46], and a DSS model to help decision-makers in running an efficient manufacturing line is useful. 2).…”

Section: Benchmark Steel Plates Faults (Spf)mentioning

confidence: 99%

Supporting Decision Making With an Ariz-Based Model for Smart Manufacturing

Koay

Tan

Teh

et al. 2023

MJCS

View full text Add to dashboard Cite

show abstract

“…It was indicated that the decision tree was superior to other models with reaching an accuracy score of 95.66 in both training and test. Simić et al, (2014) utilized a remarkable approach by hybridizing random forest and bagging algorithms, called as Treebagger, and compare this novel algorithm against support vector machine, logistic regression, and multi perception neural network classification algorithms. The dataset was divided into training and test by the ratio of 70:30 in percentage, respectively.…”

Section: Related Studies On the Steel Plate Fault Datasetmentioning

confidence: 99%

“…Moreover, hyperparameter optimisation, which is one of the steps of the model development stage, is an important part of achieving a more accurate and updatable model. Regarding the studies using the steel plate fault dataset, the following ML models, namely: logistic regression (LR) (Fakhr and Elsayad, 2012;Simić et al, 2014;Kharal, 2020;Gamal et al, 2021), support vector machine (SVM) (Simić et al, 2014;Tian et al, 2015;Nkonyana et al, 2019;Srivastava, 2019;Gamal et al, 2021;Tasar, 2022), k-nearest neighbour (kNN) (Srivastava, 2019;Gamal et al, 2021;Tasar, 2022), naive Bayes (NB) (Kazemi et al, 2018;Gamal et al, 2021), decision tree (DT) (Fakhr and Elsayad, 2012;Chen, 2018;Kazemi et al, 2018;Srivastava, 2019;Gamal et al, 2021;Tasar, 2022), random forest (RF) (Chen, 2018;Nkonyana et al, 2019;Srivastava, 2019;Kharal, 2020;Gamal et al, 2021;Tasar, 2022), neural network (NN) (Fakhr and Elsayad, 2012;Simić et al, 2014;Zhao et al, 2015;Kazemi et al, 2018;Nkonyana et al, 2019;Gamal et al, 2021;Tasar, 2022) have developed to address the fault classification problem. However, among all these ML models, studies involving hyperparameter optimization are rarely addressed (Tian et al, 2015;Zhao et al, 2015;Nkonyana et al, 2019;…”

Section: Introductionmentioning

confidence: 99%

A Method to Classify Steel Plate Faults Based on Ensemble Learning

Özkat

2022

Journal of Materials and Mechatronics: A

View full text Add to dashboard Cite

With the industrial revolution 4.0, machine learning methods are widely used in all aspects of manufacturing to perform quality prediction, fault diagnosis or maintenance. In the steel industry, it is important to precisely detect faults/defects in order to produce high quality steel plates. However, determining the exact first-principal model between process parameters and mechanical properties is a challenging process. In addition, steel plate defects are detected through manual, costly and less productive offline inspection in the traditional manufacturing process of steel. Therefore, it is a great necessity to enable automatic detection of steel plate faults. To this end, this study explores the capabilities of the following three machine learning models Adaboost, Bagging and Random Forest in detecting steel plate faults. The well-known steel plate failure dataset provided by Communication Sciences Research Center Semeion was used in this study. The aim of many studies using this dataset is to correctly classify defects in steel plates using traditional machine learning models, ignoring the applicability of the developed models to real-world problems. Manufacturing is a dynamic process with constant adjustments and improvements. For this reason, it is necessary to establish learning process that determine the best model based on the arrival of new information. Contrary to previous studies on the steel plate failure dataset, this article presents a systematic modelling approach that includes the normalization step in the data preparation stage to reduce the effects of outliers, the feature selection step in the dimension reduction stage to develop a machine learning model with less inputs, and hyperparameter optimization step in the model development stage to increase the accuracy of the machine learning model. The performances of the developed machine learning models were compared according to statistical metrics in terms of precision, recall, sensitivity and accuracy. The results revealed that AdaBoost performed well on this dataset, achieving accuracy scores of 93.15% and 91.90% for the training and test datasets, respectively.

show abstract

“…It is still uncertain what kind of defects such samples are, which may cause some minor troubles in actual production. Some scholars even apply more methods to defect classi ication to analyze which methods have better ef iciency and accuracy [23]. Despite there may be problems in practice, these machine learning methods must be more ef icient than manual methods.…”

Section: B Advantages and Disadvantagesmentioning

confidence: 99%

The Application of tree-based ML algorithm in steel plates Ffaults identification

2018

J. appl. phys. sci.

View full text Add to dashboard Cite

In the production of steel plates, it is essential to detect the surface quality effectively in real time. If the faults are not identi ied quickly and correctly, and the production technology is not corrected in time, the production of such faulty steel plates will cause huge economic losses to the company. In the traditional manufacturing process, the manual detection methods are often used to identify these faults, which is inef icient, inaccurate and timeconsuming. Steel plate fault classi ication can be regarded as a typical classi ication problem in machine learning ields, which can be conducted more ef iciently, quickly and accurately with the help of ef icient algorithm. Rapid classi ication of faults allows operators to ind issues more easily and improve the production processes. We apply a series of classical machine learning algorithms based on decision trees (Decision Tree, Adaboosting, Bagging, Random Forest) to verify the ten fold cross-validation of the steel plate fault data. It is found that Bagging algorithm outperforms the other methods and achieves 96.30% and 90% accuracy on the training and testing set, respectively. This will allow us to ind abnormalities on the surface of the steel plate timely and reduce losses. Based on these algorithms, we can cooperate with iron and steel practitioners to design more appropriate algorithms to achieve higher recognition accuracy in the future.

show abstract

An Approach of Steel Plates Fault Diagnosis in Multiple Classes Decision Making

Cited by 5 publications

References 15 publications

Supporting Decision Making With an Ariz-Based Model for Smart Manufacturing

Supporting Decision Making With an Ariz-Based Model for Smart Manufacturing

A Method to Classify Steel Plate Faults Based on Ensemble Learning

The Application of tree-based ML algorithm in steel plates Ffaults identification

Contact Info

Product

Resources

About