A comparison of machine learning methods for cutting parameters prediction in high speed turning process
| Autor: | Zoran Jurković, Goran Cukor, Tomislav Brajkovic, Miran Brezocnik |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Polynomial regression
0209 industrial biotechnology Polynomial Engineering Artificial neural network business.industry 02 engineering and technology 021001 nanoscience & nanotechnology Machine learning computer.software_genre Industrial and Manufacturing Engineering Support vector machine 020901 industrial engineering & automation Machining Artificial Intelligence Polynomial kernel Turning Roughness Cutting force Tool life ANN SVR Kernel (statistics) Radial basis function kernel Artificial intelligence 0210 nano-technology business computer Software |
| Zdroj: | Journal of Intelligent Manufacturing. 29:1683-1693 |
| ISSN: | 1572-8145 0956-5515 |
| Popis: | Support vector machines are arguably one of the most successful methods for data classification, but when using them in regression problems, literature suggests that their performance is no longer state-of-the-art. This paper compares performances of three machine learning methods for the prediction of independent output cutting parameters in a high speed turning process. Observed parameters were the surface roughness (Ra), cutting force $$(F_{c})$$(Fc), and tool lifetime (T). For the modelling, support vector regression (SVR), polynomial (quadratic) regression, and artificial neural network (ANN) were used. In this research, polynomial regression has outperformed SVR and ANN in the case of $$F_{c}$$Fc and Ra prediction, while ANN had the best performance in the case of T, but also the worst performance in the case of $$F_{c}$$Fc and Ra. The study has also shown that in SVR, the polynomial kernel has outperformed linear kernel and RBF kernel. In addition, there was no significant difference in performance between SVR and polynomial regression for prediction of all three output machining parameters. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink