Data Association-Based Fault Diagnosis of IMUs: Optimized DBN Design and Wheeled Robot Evaluation

Abstract

Deep belief network (DBN) is now being recognized as a powerful and eminently practical tool for large scale data processing. The main characteristics of DBN are the feature extension from low-level content to high-level data association and the representation of joint distribution between original data and matched labels. For a wheeled robot with no other available location reference supports, the internally integrated inertial measurement units (IMUs) essentially requires the robot to be able to implement efficient fault diagnosis to locate and identify the faults, especially for the accumulated error caused by large drifts of gyroscopes. An optimized DBN based fault diagnosis design is proposed to deal with such faults with complexity and diversity. The highlights of the proposed DBN model lies in its combination of weight value optimization via an inexact LSA-GA (abbreviates 'inexact linear searching algorithm-genetic algorithm') and dynamic adjustment for hidden-layer neurons of constituent RBMs (abbreviates 'restricted Boltzmann machines'). The problems associated with DBN anatomy, bat algorithm (BA) description and fault diagnosis modeling are discussed in detail. The real robot platform experiments and dataset tests are conducted. The results indicate that, the optimized DBN design leads to a better fault classification with excellent generalization ability on given datasets, and the adjustable 'DBN structure' contributes to the data association extraction between multiples of fault categories. The proposed scheme may therefore be considered to provide preferred reference models for a class of data based fault diagnosis problems.

Bearing fault diagnosis using transfer learning and optimized deep belief network

“…Gou et al [27] proposed an aeroengine fault diagnosis method based on continuous wavelet transform and convolutional neural network model, which effectively reveals the fault of the signal in the sensor and can accurately identify the type of fault. Xia et al [28] proposed an optimized DBN-based fault diagnosis design to deal with such complex and diverse faults. Tran et al [29] proposed a method based on wavelet transform and DBN.…”

Deep residual neural-network-based robot joint fault diagnosis method

“…Neural network (NN) method has the advantages of massively parallel, distributed processing, self-organization and self-learning capacity, so it is very popular on fault diagnosis [18][19][20] . The main stream of NN include basic perceptron, Feed-Forward NN (FFNN), long short-term memory (LSTM), CNN and RNN etc.…”