A Gear Fault Diagnosis Method Based on Improved Accommodative Random Weighting Algorithm and Bb-1d-Tp

Gears can damage the structure or even the entire gear train in the case of a failure. As a result, advanced fault diagnosis method is critical to the system's operation. This paper proposes a gear fault diagnosis method based on improved adaptive random weighting theory and a balanced binary one-dimensional three-value model. It enables diagnosing the fault types of gears under multi-channel and strong background noise. An improved adaptive random weighting algorithm reduces the total mean square error by adaptively adjusting the proportional relationship between the measured value at the current state and the previous state. Then a balanced binary algorithm extracts the texture features of the fault signal for signal enhancement. In the end, the characteristic frequency domain map of the fault signal is input to the classifier for classification. The result of the experiment demonstrated that the method effectively improves the accuracy and efficiency of gear fault identification