Fengqin Huang

In this study, a robust speed-stator flux tolerant predictive control (RS-SFTPC) strategy is proposed for the permanent magnet synchronous motor (PMSM) drives with parameters disturbance faults. The parameters disturbance sensitivity of speed external loop and stator flux internal loop is conducted for the PMSM drives system. Then, the inherent structure of predictive control model is modified by utilizing ultra-local model theory, and the improved tolerant predictive controller is applied to both the speed external loop and the stator flux internal loop. Moreover, a composite discrete extended state observer (ESO) is designed to diagnose parameters disturbance faults and observe input states, which can enhance the robustness of tolerant predictive control systems. The RS-SFTPC strategy are proposed for parameters disturbance faults diagnosis by utilizing the composite discrete ESO, which can eliminate the impact of parameters disturbance on the PMSM drives system. Finally, the comparison of simulation and experimental results show that the proposed RS-SFTPC method does not depend on any model parameters and always has better stator flux/ torque control performance than conventional PI-MPC method.

Recently, the cross-domain fault diagnosis method based on domain adaptation (DA) has been developed to solve the domain inconsistency problem caused by the variable working conditions. However, most of the existing methods only consider the case where the fault categories of the source and target domains are consistent, and depend on the ideal setting that the source domain samples are correctly labeled. The fault category inconsistency and noisy samples may lead to the degradation of diagnostic performance. To cater to more practical application scenarios, this article proposes a novel denoising universal DA network (DUDAN) for fault diagnosis of permanent magnet synchronous motor (PMSM). First, the output divergence of multiple classifiers is dynamically optimized to filter out noisy samples with incorrect labels in the source domain. Then, One-vs-All classifier learning and entropy minimization strategies are introduced to learn the minimum boundary distance between fault categories. Thus, DUDAN can achieve the alignment of samples in the shared label space, while the samples in the private label space are kept separately, and the fault category inconsistency is solved. Extensive experiments in various situations demonstrate the superiority of the proposed method.

Harmonic reducers (HR), as precision components in industrial robots, are susceptible to failure in complex working conditions. The current intelligent diagnosis methods for HR are limited and lack sufficient fault data to train deep learning models effectively. This paper presents a novel few-shot learning (FSL) fault diagnosis model named transformer convolution integration feature metric network (TCIFMN) which is based on metric learning (ML) and combines the advantages of convolutional neural networks (CNN) module and Transformer architecture. The transformer convolution integration module enhances the capability of extracting fault information and provides an input pair for feature metric network which calculates similarity scores based on the idea of the relation network. Additionally, to enhance the fault features of HR, the continuous wavelet transform (CWT) is employed to turn the fault signal into images in this paper. CWT can represent the fault information in the time domain and the frequency domain. The experimental results demonstrate that even with extremely limited training data, TCIFMN achieves prominent performance with 93% accuracy under complex working conditions, surpassing other comparative models.

The existing intelligent fault diagnosis methods for motors mainly focus on the supervised learning of 1-D signals, which ignores the global features of the signal and requires large training samples of labeled data. For this reason, this article proposes a custom double-sided phase space reconstruction (CDPSR) image-driven fault diagnosis method for permanent magnet synchronous motor (PMSM) under few-labeled samples. To reveal 2-D features in the signal, a CDPSR method is proposed to convert the fault signal into data images. The two-parallel diagnostic framework is designed, which includes 1) two semisupervised stacked autoencoders for image feature extraction and primary classification and 2) the weighted decision fusion layer to output the final diagnosis result. The extensive diagnostic results on the experimental platform verify the effectiveness of the proposed method for PMSM fault diagnosis.

In traditional one-dimensional signal-based fault diagnosis methods, there are difficulties in signal feature extraction and complexities in adjusting model hyperparameters. Therefore, a demagnetization fault diagnosis method for permanent magnet synchronous motor (PMSM) using custom phase space reconstruction (CPSR) image is proposed, which can be generalized to condition recognition. First, a CPSR method is proposed to reconstruct the magnetic leakage signal into a two-dimensional data image. Second, to overcome the problem of poor diagnosability of high-dimensional shallow features in existing local feature extraction methods, an image feature coding method is proposed, which can improve diagnostic performance through deep feature extraction and coding. Third, the improved autonomous learning multi-model constructs different fault data clouds with coded information, and realizes fault diagnosis according to the fuzzy rules of data cloud. Four kinds of demagnetized fault motors were manufactured for experimental verification. The extensive experimental results demonstrate that the proposed method is effective.

Motor fault diagnosis methods based on visual image features have made certain achievements. However, there are still some limitations. First, image features have poor adaptability to changes in operating conditions. Second, multi-sensor information is seldom considered, resulting in some industrial data not being fully utilized. Thus, a new multi-sensor-driven cross-domain motor fault diagnosis method is proposed in this paper to solve the above problems. To be specific, a multi-basis energy pattern (MBEP) method is proposed to reduce the impact of changes in operating conditions on image features. Then, to fully utilize the information of multiple sensors, a fault diagnosis framework based on manifold embedded distribution alignment-evidence theory (MEDA-ET) is proposed. The validity of the proposed method is evidenced under multiple and time-varying operating conditions, with the average accuracy in fault diagnosis reaching 99.21% and 96.27%, respectively.

Domain adaptation-based methods have been widely developed for fault diagnosis. However, the existing approaches mainly focus on the global distribution alignment of single-to-single domain without considering multiple scenarios, and overlooking the alignment of subdomains, which causes misclassification near the class boundaries. Thus, a multisource unsupervised subdomain adaptation network is proposed in this paper to solve fault diagnosis of rotary machines under multiple and variable working conditions. Using data images as inputs, a domain feature extractor is constructed to extract the domain-invariant features and map each source-target pair into the advanced feature space. Multi-kernel local maximum mean discrepancy is introduced to align subdomains. Moreover, the domain-specific classifiers are applied to diagnose fault category, and diagnosis result is jointly determined by multiple classifiers through weighted decision-making strategy. The experiment results on two sets of rotary machines achieve average accuracy of 98.01% and 96.04%, respectively, which demonstrates the validity of the proposed method.

The motor fault detection based on data-driven approach has achieved some results. However, there are still some problems, such as complex signal processing, long training time and poor adaptability to different working conditions. A new fault detection method for permanent magnet synchronous motor based on image content retrieval is proposed in this paper, which does not require complex signal processing and model training, and has strong adaptability to conditions. First, the fault signals are converted into images by the symmetrized dot pattern method. Second, an image coding technology based on KAZE feature and bag of features is proposed to reduce the computational cost. Then, to improve adaptability of conditions, a cyclic update algorithm of image retrieval library based on image fusion is proposed. Finally, fault detection is realized through image retrieval of feature code matching. Extensive experiments demonstrate the superiority and effectiveness of the proposed method.

In most industrial applications, it is difficult to obtain complete demagnetization fault signals of all conditions with labels for permanent magnet synchronous motor (PMSM), and motors are not allowed to be disassembled, so non-contact diagnostic methods are essential. A non-contact fault diagnosis method using magnetic leakage signal based on wavelet scattering convolution network (WSCN) and semi-supervised deep rule-based (SSDRB) classifier is proposed. Through magnetic equivalent circuit model analysis, the magnetic leakage signal on motor surface is selected as fault signal. To avoid complex signal processing, the symmetrized dot pattern method is introduced to convert fault signals into two-dimensional images. Then, WSCN is applied to extract features from images, and SSDRB classifier is adopted to diagnose demagnetization fault. Finally, faulty motor prototypes are manufactured for experiment. By comparing with other methods, the superiority and effectiveness of the proposed method using a small number of labeled samples under different conditions are verified.

In this study, a characteristic simulation method of a megawatt three-blade horizontal axis wind turbine (MW-THAWT) is proposed based on a laboratory kilowatt low-power motor system, which can realize the parameter correspondence and the rotational inertia compensation between the simulation platform and the wind turbine. First, the virtual proportional THAWT model of MW-THAWT is established to make the parameters of the motor and the wind turbine correspond. The control strategies of speed output and torque output are then designed to solve the problem that the conventional method cannot simulate the unstable region. The dynamic simulation strategy combining the shaft torque feedback rotational inertia compensation method and load characteristic simulation is proposed, which can ensure the consistency of the change time and mode between the simulation platform and the wind power system in the dynamic process. Finally, the MW-THAWT simulation experiment platform based on 1.4-KW motor is developed for theoretical verification. The experimental results verify that the proposed method can realize the characteristic simulation of static and dynamic of MW-THAWT in full speed range and is suitable for industrial production and laboratory research of wind turbine.