Combine harvester assembly fault diagnosis based on optimized multi-scale reverse discrete entropy

An optimized multi-scale reverse discrete entropy (RDE, OMRDE) method for feature extraction is proposed to address the lack of effective feature extraction and detection methods for combine harvester assembly fault inspection. This method was used to extract the vibration signal features from the combine. A fault diagnostic method is designed to verify the efficiency of the associated methods. First, a comparative study of the RDE, multi-scale inverse DE (MRDE), and OMRDE methods was performed using simulated signals to verify the effectiveness of OMRDE. Second, the FSTPSO-VMD method was used to decompose the vibration signal of the combine assembly fault, and the OMRDE, MRDE, and fuzzy entropy were compared and analyzed. The actual feature extraction effect of the three entropy functions reached the highest classification accuracy (88.5%) after using OMRDE to extract features. Finally, a fusion feature set is constructed to further improve the classification accuracy, and the LSSVM classifier is optimized using FSTPSO. The analytical results show that the FSTPSO- LSSVM classifier constructed in this study adopts the fused feature with an accuracy of 93%, which is better than that of other common methods, and verifies the validity of the fault diagnostic model. Therefore, the performance of the OMRDE method proposed in this study is better than that of the MRDE. The proposed fault diagnostic model can accurately classify the fault detection of a combine harvester assembly.