Prediction of Laser Formed Shaped Surface Characteristics Using Computational Intelligence Techniques
Апстракт
The main purpose of this study was to establish a prediction model for parameters of shaped surface based on laser forming process. Shape modelling from a flat sheet by lasers forming process needs numerous irradiations along surface paths with different heating parameters. Since the prediction of the parameters of shape modelling could be very complex task, computational intelligence techniques could be used for the prediction process. In this article support vector regression (SVR) was applied for the shaped surface parameters prediction. The SVR model was compared with other computational intelligence models like artificial neural network (ANN) and genetic programming (GP) techniques as benchmark models. Laser power, laser scan speed and spot diameter were used as inputs. The crucial aim of the study was to predict favourable and unfavourable shape forms according to the machining parameters. By the way one should make optimal machining conditions in order to avoid unfavourable shap...e forms. Based on the results, SVR model outperformed ANN and GP models for the shaped surface parameters prediction.
Кључне речи:
surface modelling / support vector regression (SVR) / stainless steel / prediction / laser forming / genetic programming (GP) / Fibre laser / artificial neural network (ANN) / analytical modelИзвор:
Lasers in Engineering, 2018, 40, 4-6, 239-251Издавач:
- Old City Publishing
Колекције
Институција/група
Mašinski fakultetTY - JOUR AU - Jović, Srdjan AU - Lazarević, Mihailo AU - Šarkoćević, Živče AU - Lazarević, D. PY - 2018 UR - https://machinery.mas.bg.ac.rs/handle/123456789/2964 AB - The main purpose of this study was to establish a prediction model for parameters of shaped surface based on laser forming process. Shape modelling from a flat sheet by lasers forming process needs numerous irradiations along surface paths with different heating parameters. Since the prediction of the parameters of shape modelling could be very complex task, computational intelligence techniques could be used for the prediction process. In this article support vector regression (SVR) was applied for the shaped surface parameters prediction. The SVR model was compared with other computational intelligence models like artificial neural network (ANN) and genetic programming (GP) techniques as benchmark models. Laser power, laser scan speed and spot diameter were used as inputs. The crucial aim of the study was to predict favourable and unfavourable shape forms according to the machining parameters. By the way one should make optimal machining conditions in order to avoid unfavourable shape forms. Based on the results, SVR model outperformed ANN and GP models for the shaped surface parameters prediction. PB - Old City Publishing T2 - Lasers in Engineering T1 - Prediction of Laser Formed Shaped Surface Characteristics Using Computational Intelligence Techniques EP - 251 IS - 4-6 SP - 239 VL - 40 UR - https://hdl.handle.net/21.15107/rcub_machinery_2964 ER -
@article{ author = "Jović, Srdjan and Lazarević, Mihailo and Šarkoćević, Živče and Lazarević, D.", year = "2018", abstract = "The main purpose of this study was to establish a prediction model for parameters of shaped surface based on laser forming process. Shape modelling from a flat sheet by lasers forming process needs numerous irradiations along surface paths with different heating parameters. Since the prediction of the parameters of shape modelling could be very complex task, computational intelligence techniques could be used for the prediction process. In this article support vector regression (SVR) was applied for the shaped surface parameters prediction. The SVR model was compared with other computational intelligence models like artificial neural network (ANN) and genetic programming (GP) techniques as benchmark models. Laser power, laser scan speed and spot diameter were used as inputs. The crucial aim of the study was to predict favourable and unfavourable shape forms according to the machining parameters. By the way one should make optimal machining conditions in order to avoid unfavourable shape forms. Based on the results, SVR model outperformed ANN and GP models for the shaped surface parameters prediction.", publisher = "Old City Publishing", journal = "Lasers in Engineering", title = "Prediction of Laser Formed Shaped Surface Characteristics Using Computational Intelligence Techniques", pages = "251-239", number = "4-6", volume = "40", url = "https://hdl.handle.net/21.15107/rcub_machinery_2964" }
Jović, S., Lazarević, M., Šarkoćević, Ž.,& Lazarević, D.. (2018). Prediction of Laser Formed Shaped Surface Characteristics Using Computational Intelligence Techniques. in Lasers in Engineering Old City Publishing., 40(4-6), 239-251. https://hdl.handle.net/21.15107/rcub_machinery_2964
Jović S, Lazarević M, Šarkoćević Ž, Lazarević D. Prediction of Laser Formed Shaped Surface Characteristics Using Computational Intelligence Techniques. in Lasers in Engineering. 2018;40(4-6):239-251. https://hdl.handle.net/21.15107/rcub_machinery_2964 .
Jović, Srdjan, Lazarević, Mihailo, Šarkoćević, Živče, Lazarević, D., "Prediction of Laser Formed Shaped Surface Characteristics Using Computational Intelligence Techniques" in Lasers in Engineering, 40, no. 4-6 (2018):239-251, https://hdl.handle.net/21.15107/rcub_machinery_2964 .