2024 Vol.7 Jun.N03

• Title: Machine Learning Algorithm Based Process Monitoring and Quality Prediction in Mechanical Manufacturing
• Name: Shan Li
• Company: School of Information and Mechatronic Engineering, Zhengzhou Business University ZhengZhou 451200,China
• Abstract:

  Influenced by the generalization ability of the model, the poor prediction effect usually occurs in the process of monitoring and quality prediction of the machinery manufacturing process, in this regard, the monitoring and quality prediction of the machinery manufacturing process based on machine learning algorithms is proposed. Firstly, the peak factor, waveform factor and skewness coefficient of power are used as the power signal feature indexes to extract the time-domain features of the power signal of the mechanical manufacturing process. Then combined with the machine learning algorithm, the distance between the input data and the distribution space of the in-control data is used to determine whether the mechanical manufacturing process is out of control, and the process monitoring model is constructed. Finally, taking the process parameters as the independent variables and the quality objective as the dependent variable, the XGBoost algorithm is used to construct the quality objective function to realize the quality prediction of mechanical manufacturing. The practical effectiveness of the proposed practical method for quality prediction in the mechanical manufacturing process is verified by building an experimental session. By visualizing and analyzing the results, it is demonstrated that the method has a high recall and a more desirable prediction accuracy when using this paper's method for the prediction of the mechanical manufacturing process.

  
  

• Keyword: machine learning algorithms; machine manufacturing; process monitoring; quality prediction;
• DOI: 10.12250/jpciams2024090611
• Citation form: Shan Li.Machine Learning Algorithm Based Process Monitoring and Quality Prediction in Mechanical Manufacturing[J]. Computer Informatization and Mechanical System,2024,Vol.7,pp.47-51

[1] Sun Z , Duan B , Zhang Y ,et al. Influence and experiment of cable-net manufacturing errors on surface accuracy of mesh reflector antennas[J]. Journal of Aeronautics, 2023(2):363-376.

[2] Rong G , Mi T , Ye S ,et al. Modelling and intelligent prediction of sound quality for high-voltage fans on fuel cell vehicles:[J].Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, 2022, 236(6):1246-1258.

[3] Hu G , Ahmed M ,M. L'Abbé.Natural language processing and machine learning approaches for food categorization and nutrition quality prediction compared with traditional methods.[J].The American journal of clinical nutrition, 2022, 117 3:553-563.  

[4] Wu Y .Control Force Compensation and Wear Monitoring of Variable Stiffness Joints in Drive Machining Process[J].Mathematical Problems in Engineering, 2021, 2021:1-11.

[5] Yin Y , Xu J , Ji M L L C M .A critical review on sintering and mechanical processing of 3Y-TZP ceramics[J].CERAMICS INTERNATIONAL, 2023, 49(2):1549- 1571.

[6] Li J , Zhang S , Fan Y ,et al. Effect of phenyltrimethoxysilane coupling agent (A153) on simultaneously improving mechanical, electrical, and processing properties of ultra-high-filled polypropylene composites[J].e-Polymers, 2022, 22:585 - 594.

[7]F. Rivera-López,M. Hernández-molina, Bravo A D M ,et al.Effect of Process Parameters and Postprocessing on Mechanical Properties of Additive Manufacturing Polylactic Acid Obtained by Fused Deposition Modeling.[J].3D printing and additive manufacturing, 2023, 10 1:, 60-69.  

[8] Wang S , Gao Z , Wu G ,et al. Titanium microalloying of steel: a review of its effects on processing,microstructure and mechanical properties[J]. International Journal of Minerals, Metallurgy and Materials, 2022, 29(4):645-661.

[9] Chaari R , Kharrat F , Khlif M ,et al. Effect of processing conditions on the rheological and mechanical properties of composites based on a PBS matrix and enzymatically treated date palm fibers[J].International Polymer Processing, 2022, 38:19 - 29.

[10] Tiwari D , Farnsworth M , Zhang Z ,et al. In-process monitoring in electrical machine manufacturing: a review of state of the art and future directions :[J].Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture, 2021, 235(13):2035-2051.

[11] Nithin S K, Hemanth K, Shamanth V, et al. Importance of condition monitoring in mechanical domain[J]. Materials Today: proceedings, 2022, 54: 234-239.

[12] Lee W J, **a K, Denton N L, et al. Development of a speed invariant deep learning model with application to condition monitoring of rotating machinery [ J]. Journal of Intelligent Manufacturing, 2021, 32: 393-406.

[13] Zhu K, Fuh J Y H, Lin X. Metal-based additive manufacturing condition monitoring: a review on machine learning based approaches[J]. IEEE/ASME Transactions on Mechatronics, 2021, 27(5): 2495-2510.

[14] Al-Naggar Y M, Jamil N, Hassan M F, et al. Condition monitoring based on IoT for predictive maintenance of CNC machines[J]. Procedia CIRP, 2021, 102: 314-318.

[15] Pimenov D Y, Bustillo A, Wojciechowski S, et al. Artificial intelligence systems for tool condition monitoring in machining: analysis and critical review[J]. Journal of Intelligent Manufacturing, 2023, 34(5): 2079-2121.