| CHI Yu-lun,FAN Zhi-hui,GE Ai-li,LI Yi-lin.Multi-objective Parameter Optimization of Hard Turning Process for Green High Surface Quality Manufacturing[J],52(9):278-293 |
| Multi-objective Parameter Optimization of Hard Turning Process for Green High Surface Quality Manufacturing |
| Received:November 06, 2022 Revised:March 13, 2023 |
| View Full Text View/Add Comment Download reader |
| DOI：10.16490/j.cnki.issn.1001-3660.2023.09.024 |
| KeyWord:hard turning green manufacturing surface roughness carbon emission model generalized regression neural network multi-objective parameter optimization experimental study |
| Author | Institution |
| CHI Yu-lun |
University of Shanghai for Science and Technology, Shanghai , China |
| FAN Zhi-hui |
University of Shanghai for Science and Technology, Shanghai , China |
| GE Ai-li |
University of Shanghai for Science and Technology, Shanghai , China |
| LI Yi-lin |
University of Shanghai for Science and Technology, Shanghai , China |
|
| Hits: |
| Download times: |
| Abstract: |
| In the production of manufacturing industry, the manufacturing process of workpiece produces a large amount of energy consumption and material consumption, which has a serious impact on the environment. With continuous emphasis of the government on energy conservation and emission reduction, enterprises have increasingly attached importance to the green optimization of product processing. Hard turning is a widely used processing technology in the bearing processing process at present. How to optimize the cutting parameters to improve product quality and control carbon emissions is a hot issue to be solved in the manufacturing industry. In order to study the collaborative optimization of hard turning green manufacturing and process performance, a multi-objective optimization model considering both carbon emissions and surface roughness is proposed in this paper. This model can provide an effective solution for improving product surface quality and controlling carbon emission. Firstly, the carbon emission target function was established by analyzing the influence of cutting parameters, workpiece materials, tool materials and other factors on the cutting power during hard turning. In view of the fact that the surface roughness of the workpiece was affected by many factors such as cutting conditions, workpiece materials, tool materials, etc., the objective function of bearing hard turning surface roughness was established by using orthogonal experiments and generalized regression neural network. The model could well deal with the nonlinear relationship between cutting parameters and surface roughness. The genetic algorithm was used to optimize the structural parameters of the generalized regression neural network surface roughness prediction model. The accuracy of the prediction model was improved. Then, considering the constraint conditions such as the characteristics of the machine tool and the actual working conditions of the hard turning during the machining process, a multi-objective optimization model with cutting parameters as the optimization variables and carbon emissions and surface roughness as the optimization objectives was established. The weight coefficient was introduced to convert it into a single-objective optimization model. Finally, the genetic algorithm was used to optimize the optimization model, and the influence of cutting parameters on the optimization objectives was analyzed in depth. The effectiveness of the optimization model was verified in the hard turning test of the actual bearing products in the factory. The results showed that when the cutting speed was 225 m/min, the feed rate was 0.08 mm/r, and the cutting depth was 0.10 mm, the comprehensive optimization index of carbon emissions and surface roughness was the lowest. Compared with the previous optimization, although the carbon emission was increased by 13.05%, the surface quality was improved by 34.44%. The bearing surface quality was improved and the increase of carbon emission during processing was controlled. Through the single factor influence analysis method, it was found that the impact of each cutting parameter on the comprehensive optimization index was from highness to lowness:feed rate, cutting speed, cutting depth. The conclusion of this paper is that the research results are of great significance for improving the surface quality of hard turning bearing and optimizing the process parameters of green manufacturing. |
| Close |
|
|
|