A Diagnosis Method for the Compound Fault of Gearboxes Based on Multi-Feature and BP-AdaBoost

Abstract

Gearbox is an important structure of rotating machinery, and the accurate fault diagnosis of gearboxes is of great significance for ensuring efficient and safe operation of rotating machinery. Aiming at the problem that there is little common compound fault data of gearboxes, and there is a lack of an effective diagnosis method, a gearbox fault simulation experiment platform is set up, and a diagnosis method for the compound fault of gearboxes based on multi-feature and BP-AdaBoost is proposed. Firstly, the vibration signals of six typical states of gearbox are obtained, and the original signals are decomposed by empirical mode decomposition and reconstruct the new signal to achieve the purpose of noise reduction. Then, perform the time domain analysis and wavelet packet analysis on the reconstructed signal, extract three time domain feature parameters with higher sensitivity, and combine them with eight frequency band energy feature parameters obtained by wavelet packet decomposition to form the gearbox state feature vector. Finally, AdaBoost algorithm and BP neural network are used to build the BP-AdaBoost strong classifier model, and feature vectors are input into the model for training and verification. The results show that the proposed method can effectively identify the gearbox failure modes, and has higher accuracy than the traditional fault diagnosis methods, and has certain reference significance and engineering application value.

Condition monitoring of water pump bearings using ensemble classifier

“…The multi-sensory data collection setup has a high cost and AdaBoost performance was not satisfactory. Zhang et al 53 have used time-domain vibrational analysis of gearbox. The wavelet packet decomposition was used as a feature extraction method and AdaBoost classifier was used to achieve a classification accuracy of 96.94%.…”

Compound Fault Diagnosis of Rolling Bearing Based on ACMD, Gini Index Fusion and AO-LSTM

“…The optimization rule of the AO algorithm starts from the population of the candidate solution (X) in Equation (19), which is randomly generated between the upper bound (UB) and the lower bound (LB) of a given problem. The best-obtained solution, so far, is determined as the optimal solution approximately in each iteration.…”

“…Chen [18] used a combination of wavelet packet decomposition (WPD), overall average empirical mode decomposition (EEMD) and information entropy to extract the multiple features of the signal, and used the multi-classifier group composed of support vector machine (SVM) sub-classifiers to identify the multiple features, so as to realize the diagnosis and recognition of compound faults of rolling bearings. Zhang et al [19] used the AdaBoost algorithm and the back propagation (BP) neural network to effectively identify the compound fault mode of gearbox. However, SVM and the BP neural network used in pattern recognition are shallow networks, the number of hidden layers and the ability of feature learning and expression are limited, and the training can easily to fall into the local extremum.…”

Research on the construction of evaluation index system for equipment maintenance support capability based on AHP

“…According to the principle of constructing the evaluation index system, through the analysis of equipment composition, establishment tasks and structural characteristics of the Synthetic Brigade, and through expert consultation and literature review, the evaluation indicators are strictly selected. The equipment maintenance support capability of the Synthetic Brigade includes organization planning capability, equipment maintenance capability, equipment support capability and data support capability [3][4][5]. According to the three levels of "ability -evaluation elements -standard requirements", it is decomposed and refined [6].…”