Fault diagnosis of silage harvester based on a modified random forest

The objective of this study is to investigate the effectiveness of a multi-parameter intelligent fault diagnosis method based on a modified random forest algorithm (RFNB algorithm), so as to reduce the impact of blockage fault on the operation of a silage harvester, thus providing a reference for the intelligent control. In brief, the forward speed, cutting speed, engine speed and engine load were selected as the input variables. Then, a random forest (RF) was used to construct a naive Bayes classifier for each node of the decision tree, and finally the RFNB algorithm constituted based on the naive Bayes tree (NBTree). The results revealed that by improving the classification accuracy of a single decision tree, the fault diagnosis accuracy of the entire RF was improved. When the sample data were consistent, the accuracy of the RFNB algorithm was 97.9%, while that of the RF algorithm was only 93.27%. Besides, the performance of RFNB classifiers was significantly better than that of RF classifiers. In conclusion, the RFNB model can accurately identify the fault status of the silage harvester with its good robustness, which provides a new idea for the fault monitoring and early warning of large agricultural rotating machinery in the future.