In this paper, we conduct a study on failure prediction of industrial machinery and equipment in order to improve the competitiveness of enterprises. We use Bootstrap to resample the dataset before the experiment. Then, we used four algorithms to build the prediction model, and used GridSearchCV to automatically adjust the parameters and train the equipment records extracted from the dataset. We selected the accuracy, F1 score, and ROC curve as the evaluation indexes of the model, and the evaluation results were compared, so we finally chose the fault prediction model built by LightGBMClassifier algorithm, and then used the confusion matrix to evaluate the model performance.

Mingmin Jiang, Wen Zhou, Yan Gou. Fault prediction of industrial machinery and equipment. International Journal of Frontiers in Engineering Technology (2023), Vol. 5, Issue 3: 26-31. https://doi.org/10.25236/IJFET.2023.050305.

[1] Hu Yujian. Application of mechanical automation technology in machinery manufacturing industry [J]. Modern Industrial Economics and Informatization, 2021, 11(08):140-146.

[2] Cao Yingming. Portable rotational speed measuring instrument[J]. Measurement and Testing Technology, 2017, 44(09):27-29.

[3] Wang Lin. Common methods of mechanical equipment fault diagnosis and monitoring and its development trend [J]. Journal of Wuhan University of Technology, 2000(03):62-64.

[4] Fu Xitao. Research and prospect of reciprocating compressor fault diagnosis [J]. Technology and Market, 2014, 21(07):119-120.

[5] Scientific Platform Serving for Statistics Professional 2021. SPSSPRO. (Version 1.0.11)[Online Application Software]. Retrieved from https://www.spsspro.com.

[6] Jia JP, He XQ, Jin Y. Statistics (4th ed.) [M]. People's University of China Press, 2009.