A Hybrid Predictive Approach for Chromium Layer Thickness in the Hard Chromium Plating Process Based on the Differential Evolution/Gradient Boosted Regression Tree Methodology
The purpose of the industrial process of chromium plating is the creation of a hard and wear-resistant layer of chromium over a metallic surface. One of the main properties of chromium plating is its resistance to both wear and corrosion. This research presents an innovative nonparametric machine le...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-06-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/8/6/959 |
| _version_ | 1797565543372292096 |
|---|---|
| author | Paulino José Garcia Nieto Esperanza García Gonzalo Fernando Sanchez Lasheras Antonio Bernardo Sánchez |
| author_facet | Paulino José Garcia Nieto Esperanza García Gonzalo Fernando Sanchez Lasheras Antonio Bernardo Sánchez |
| author_sort | Paulino José Garcia Nieto |
| collection | DOAJ |
| description | The purpose of the industrial process of chromium plating is the creation of a hard and wear-resistant layer of chromium over a metallic surface. One of the main properties of chromium plating is its resistance to both wear and corrosion. This research presents an innovative nonparametric machine learning approach that makes use of a hybrid gradient boosted regression tree (GBRT) methodology for hard chromium layer thickness prediction. GBRT is a non-parametric statistical learning technique that produces a prediction model in the form of an ensemble of weak prediction models. The motivation for boosting is a procedure that combines the output of many weak classifiers to produce a powerful committee. In this study, the GBRT hyperparameters were optimized with the help of differential evolution (DE). DE is an optimization technique within evolutionary computing. The results found that this model was able to predict the thickness of the chromium layer formed in this industrial process with a determination coefficient equal to 0.9842 and a root-mean-square error value of 0.01590. The two most important variables of the model were the time of the hard-chromium process and the thickness of the layer removed by electropolishing. Thus, these results provide a foundation for an accurate predictive model of hard chromium layer thickness. The derived model also allowed the ranking of the importance of the independent input variables that were examined. Finally, the high performance and simplicity of the model make the DE/GBRT method attractive compared to conventional forecasting techniques. |
| first_indexed | 2024-03-10T19:13:42Z |
| format | Article |
| id | doaj.art-17dd546da767499ca4063abf505b0030 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-10T19:13:42Z |
| publishDate | 2020-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-17dd546da767499ca4063abf505b00302023-11-20T03:31:45ZengMDPI AGMathematics2227-73902020-06-018695910.3390/math8060959A Hybrid Predictive Approach for Chromium Layer Thickness in the Hard Chromium Plating Process Based on the Differential Evolution/Gradient Boosted Regression Tree MethodologyPaulino José Garcia Nieto0Esperanza García Gonzalo1Fernando Sanchez Lasheras2Antonio Bernardo Sánchez3Department of Mathematics, Faculty of Sciences, University of Oviedo, c/Federico García Lorca 18, 33007 Oviedo, SpainDepartment of Mathematics, Faculty of Sciences, University of Oviedo, c/Federico García Lorca 18, 33007 Oviedo, SpainDepartment of Mathematics, Faculty of Sciences, University of Oviedo, c/Federico García Lorca 18, 33007 Oviedo, SpainDepartment of Mining Technology, Topography and Structures, University of León, 24071 León, SpainThe purpose of the industrial process of chromium plating is the creation of a hard and wear-resistant layer of chromium over a metallic surface. One of the main properties of chromium plating is its resistance to both wear and corrosion. This research presents an innovative nonparametric machine learning approach that makes use of a hybrid gradient boosted regression tree (GBRT) methodology for hard chromium layer thickness prediction. GBRT is a non-parametric statistical learning technique that produces a prediction model in the form of an ensemble of weak prediction models. The motivation for boosting is a procedure that combines the output of many weak classifiers to produce a powerful committee. In this study, the GBRT hyperparameters were optimized with the help of differential evolution (DE). DE is an optimization technique within evolutionary computing. The results found that this model was able to predict the thickness of the chromium layer formed in this industrial process with a determination coefficient equal to 0.9842 and a root-mean-square error value of 0.01590. The two most important variables of the model were the time of the hard-chromium process and the thickness of the layer removed by electropolishing. Thus, these results provide a foundation for an accurate predictive model of hard chromium layer thickness. The derived model also allowed the ranking of the importance of the independent input variables that were examined. Finally, the high performance and simplicity of the model make the DE/GBRT method attractive compared to conventional forecasting techniques.https://www.mdpi.com/2227-7390/8/6/959gradient boosted regression tree (GBRT)differential evolution (DE)machine learningstatistical regressionhard chromium plating process |
| spellingShingle | Paulino José Garcia Nieto Esperanza García Gonzalo Fernando Sanchez Lasheras Antonio Bernardo Sánchez A Hybrid Predictive Approach for Chromium Layer Thickness in the Hard Chromium Plating Process Based on the Differential Evolution/Gradient Boosted Regression Tree Methodology Mathematics gradient boosted regression tree (GBRT) differential evolution (DE) machine learning statistical regression hard chromium plating process |
| title | A Hybrid Predictive Approach for Chromium Layer Thickness in the Hard Chromium Plating Process Based on the Differential Evolution/Gradient Boosted Regression Tree Methodology |
| title_full | A Hybrid Predictive Approach for Chromium Layer Thickness in the Hard Chromium Plating Process Based on the Differential Evolution/Gradient Boosted Regression Tree Methodology |
| title_fullStr | A Hybrid Predictive Approach for Chromium Layer Thickness in the Hard Chromium Plating Process Based on the Differential Evolution/Gradient Boosted Regression Tree Methodology |
| title_full_unstemmed | A Hybrid Predictive Approach for Chromium Layer Thickness in the Hard Chromium Plating Process Based on the Differential Evolution/Gradient Boosted Regression Tree Methodology |
| title_short | A Hybrid Predictive Approach for Chromium Layer Thickness in the Hard Chromium Plating Process Based on the Differential Evolution/Gradient Boosted Regression Tree Methodology |
| title_sort | hybrid predictive approach for chromium layer thickness in the hard chromium plating process based on the differential evolution gradient boosted regression tree methodology |
| topic | gradient boosted regression tree (GBRT) differential evolution (DE) machine learning statistical regression hard chromium plating process |
| url | https://www.mdpi.com/2227-7390/8/6/959 |
| work_keys_str_mv | AT paulinojosegarcianieto ahybridpredictiveapproachforchromiumlayerthicknessinthehardchromiumplatingprocessbasedonthedifferentialevolutiongradientboostedregressiontreemethodology AT esperanzagarciagonzalo ahybridpredictiveapproachforchromiumlayerthicknessinthehardchromiumplatingprocessbasedonthedifferentialevolutiongradientboostedregressiontreemethodology AT fernandosanchezlasheras ahybridpredictiveapproachforchromiumlayerthicknessinthehardchromiumplatingprocessbasedonthedifferentialevolutiongradientboostedregressiontreemethodology AT antoniobernardosanchez ahybridpredictiveapproachforchromiumlayerthicknessinthehardchromiumplatingprocessbasedonthedifferentialevolutiongradientboostedregressiontreemethodology AT paulinojosegarcianieto hybridpredictiveapproachforchromiumlayerthicknessinthehardchromiumplatingprocessbasedonthedifferentialevolutiongradientboostedregressiontreemethodology AT esperanzagarciagonzalo hybridpredictiveapproachforchromiumlayerthicknessinthehardchromiumplatingprocessbasedonthedifferentialevolutiongradientboostedregressiontreemethodology AT fernandosanchezlasheras hybridpredictiveapproachforchromiumlayerthicknessinthehardchromiumplatingprocessbasedonthedifferentialevolutiongradientboostedregressiontreemethodology AT antoniobernardosanchez hybridpredictiveapproachforchromiumlayerthicknessinthehardchromiumplatingprocessbasedonthedifferentialevolutiongradientboostedregressiontreemethodology |