Abstract
In this paper, an ensemble learning method, in the form of extreme gradient boosting (XGBoost) algorithm is adopted as an effective predictive tool for envisaging values of average surface roughness and material removal rate during CNC turning operation of high strength steel grade-H material. In order to develop the related models, a grid with 24600 combinations of different hyperparameters is created and tested for all the possible hyperparametric combinations of the model. The configurations having the optimal values of the considered hyperparameters and yielding the lowest training error are finally employed for predicting the response values in the CNC turning process. The performance of the developed models is finally validated with the help of five statistical error estimators, i.e. mean absolute percentage error, root mean squared percentage error, root mean squared logarithmic error, correlation coefficient and root relative squared error. Based on the favorable values of all the statistical metrics, it can be observed that XGBoost can be efficiently applied as a predictive tool with excellent accuracy in machining processes.
Highlights
In the field of manufacturing, machining is the process of removing unwanted material from a given workpiece to provide it the required shape and geometry, while meeting the requirements for better surface quality and close dimensional tolerance
Taking into consideration Vc, t and f as the input parameters, and material removal rate (MRR) and Ra as the responses, Abbas et al (2017) conducted 53 (125) experiments using an EMCO Concept Turn computer numerical control (CNC) lathe equipped with Sinumeric 840-D controller on high strength grade-H steel materials
Among 125 experimental observations, group numbers 3, 10, 14, 16 and 22 are randomly chosen for testing the prediction performance of XGBoost algorithm, whereas, the remaining 20 groups are utilized for training of this algorithm
Summary
In the field of manufacturing, machining is the process of removing unwanted material from a given workpiece to provide it the required shape and geometry, while meeting the requirements for better surface quality and close dimensional tolerance. It is usually a customary practice to evaluate the quality of a final product based on these responses For this reason, the concerned process designer/machine operator must closely control and better understand the effects and interactions of different turning parameters on the responses. The relationship between steel properties, their compositions and manufacturing parameters is extremely difficult to comprehend For this purpose, Song et al (2020) adopted linear regression, support vector machine and XGBoost to determine the mapping functions between tensile strength, plasticity and other influencing factors for steel. While predicting tool wear during a drilling operation, Alajmi et al (2020) proved the effectiveness of XGBoost algorithm against support vector machine and multilayer perception artificial neural network This algorithm has been successfully employed in different discrete domains of manufacturing, its application as an efficient predictive tool based on real-time machining data is really scarce. This paper presents the application of XGBoost algorithm to envisage values of MRR (in mm3/min) and Ra (in μm) during CNC turning operation of high strength grade-H steel material
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
