Multi-Objective Optimization of CNC Turning Process Parameters Considering Transient-Steady State Energy Consumption

Energy-saving and emission reduction are recognized as the primary measure to tackle the problems associated with climate change, which is one of the major challenges for humanity for the forthcoming decades. Energy modeling and process parameters optimization of machining are effective and powerful ways to realize energy saving in the manufacturing industry. In order to realize high quality and low energy consumption machining of computer numerical control (CNC) lathe, a multi-objective optimization of CNC turning process parameters considering transient-steady state energy consumption is proposed. By analyzing the energy consumption characteristics in the process of machining and introducing practical constraints, such as machine tool equipment performance and tool life, a multi-objective optimization model with turning process parameters as optimization variables and high quality and low energy consumption as optimization objectives is established. The model is solved by non-dominated sorting genetic algorithm-II (NSGA-II), and the pareto optimal solution set of the model is obtained. Finally, the machining process of shaft parts is studied by CK6153i CNC lathe. The results show that 38.3% energy consumption is saved, and the surface roughness of workpiece is reduced by 47.0%, which verifies the effectiveness of the optimization method.

Prediction of Surface Roughness in CNC Turning Process using Adaptive Neural Fuzzy Inference System

This paper presents the methodology of surface roughness inspection in the CNC Turning process. Adaptive Neural Fuzzy Inference System classifier can predict the high accuracy roughness value by insisting on surface roughness image. The vision system captures the image and determines the mean value by using the ANFIS algorithm. Training sets variables speed, depth of cut, feed rate, and mean value are feed as the input, and manual stylus probe surface roughness value is feed as the output. After the simulation process, the testing input was performed, and finally getting the vision measurement value. This higher accuracy (above 95%) and low error rate (below 4%) can be achieved by using the ANFIS classifier, which is predominantly helpful for the industry to measure surface roughness. Assign the quality of the product by evaluating the manual stylus probe and vision measurement value.

Application of XGBoost Algorithm as a Predictive Tool in a CNC Turning Process

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.