Intelligent Fault Diagnosis for BLDC With Incorporating Accuracy and False Negative Rate in Feature Selection Optimization

Abstract

Early fault diagnosis is essential for the proper operation of rotating machines. This article proposes a fitness function in differential evolution (DE) that considers accuracy rate and false negative rate for optimization in brushless DC (BLDC) motor fault diagnosis. Feature selection based on a distance discriminant (FSDD) calculates the feature factors which base on the category separability of features after the Hilbert-Huang transform (HHT) which extracts the features of four different type signals from BLDC motor Hall sensor. The feature rank through DE to optimize before the features into the backpropagation neural network (BPNN) in order. By reducing the feature number of Hall signal and decreasing the complexity of neural network input, the combined method was proposed in this article can significantly reduce the calculation cost. Finally, the identification model obtained an accuracy rate of 98.98% and false negative rate of 13.66% when there were 18 features; besides, receiver operating characteristic (ROC) curve and probability curve have been evidenced the number of false negative is decreased. Moreover, the experiments have verified that the proposed method is effective in UCI data set.

Multi-Objective Optimization of an Axial Flux Permanent Magnet Brushless DC Motor with Arc-Shaped Magnets

“…In the past two decades, the AFPMBLDCs have been widely researched throughout the world. In [3,4], we found that the AFPMBLDC can provide a larger output torque compared with the radial flux brushless DC motor. However, the torque ripple cannot be neglected due to the high cogging torque.…”

“…Polar arc coefficient 0.6-0.9 Permanent magnet thickness 2.0-3.5 permanent magnet arc radius 18-24 Air-gap length 0.5-1.5 Based on the four variable optimization parameters selected above, a range of four level factors were determined for each parameter, an orthogonal table was established. If the traditional single-variable optimization method was used; 4 4 = 256 experiments are required, while only 4 × 4 = 16 experiments are required to achieve the multivariable and multi-objective optimization design of the motor using Taguchi's method. The orthogonal table for establishing experiment L16(4 × 4) is shown in Table 4.…”

In Search of the Proper Dimensions of the Optimum In-Wheel Permanent Magnet Synchronous Motor Design

“…Permanent Magnet Synchronous Motors (PMSMs) are widely applied in industrial applications and have been comprehensively improved through the development of outstanding features such as high efficiency, low noise, and small volume [1,2]. In recent decades, PMSMs and Brushless Direct Current motors (BLDCMs) have been preferred for LEV applications by manufacturers due to their advantages such as high performance, ease of manufacture and regenerative braking capability [3,4]. BLDCMs are obviously a type of PMSM.…”