Study on fault diagnosis method of splitter intelligent wheelchair motor based on wavelet and energy feature

As a key component of a split-type intelligent sports wheelchair for the disabled, the reliability of the motor is related to the personal safety of the wheelchair user and the accurate realization of the wheelchair’s sports functions. This motor is actually just a rotating machine. In order to achieve detection and analysis of rotating machinery bearing vibration signal, a method based on wavelet and energy feature of rotating machinery fault diagnosis is introduced. This method applies wavelet to obtain de-noising and then uses wavelet packet energy feature extraction to diagnose faults effectively caused by rotating machinery such as rotor unbalance fault, rotor misalignment fault, and rotor-to-stator rub fault. Test results illustrate that when different faults occur to the bearing, it is viable to utilize pattern recognition to diagnose faults for the reason that discrepancies appear in sub-hand energy after wavelet packet decomposition. The main research conclusions of this paper are also directly applied to the fault diagnosis of such wheelchair motors.

A Fault Diagnosis Method of Rolling Bearing Integrated with Cooperative Energy Feature Extraction and Improved Least-Squares Support Vector Machine

To solve the problem that the bearing fault of variable working conditions is challenging to identify and classify in the industrial field, this paper proposes a new method based on optimization of multidimension fault energy characteristics and integrates with an improved least-squares support vector machine (LSSVM). First, because the traditional wavelet energy feature is difficult to effectively reflect the characteristics of rolling bearing under different working conditions, based on analyzing the wavelet energy feature extraction in detail, a collaborative method of multidimension fault energy feature extraction combined with the method of Transfer Component Analysis (TCA) is constructed, which improves the discrimination between the different features and the compactness between the same features of rolling bearing faults. Then, for solving the problem of the local optimal of particle swarm optimization (PSO) in fault diagnosis and recognition of rolling bearing, an improved LSSVM based on particle swarm optimization and wavelet mutation optimization is established to realize the collaborative optimization and adjustment of LSSVM dynamic parameters. Based on the improved LSSVM and optimization of multidimensional energy characteristics, a new method for fault diagnosis of rolling bearing is designed. Finally, the simulation and analysis of the proposed algorithm are verified by the experimental data of different working conditions. The experimental results show that this method can effectively extract the multidimensional fault characteristics under variable working conditions and has a high fault recognition rate.