Search

Abstract Partial discharge (PD) detection of cable terminals is crucial for the safe operation of the traction power system in trains. However, similar PD signals in complex train‐operating environments cause difficulty to recognise the insulation defects. Therefore, a PD signal image transformation recognition method is proposed for PD detection of cable terminal defects to identify defects in cable terminals with similar PD characteristics accurately. In the proposed method, the raw PD signals are firstly transformed to images via the Gramian angular field (GAF) representation. This can reveal the discriminative characteristics embedded in the original PD signals and subsequently facilitate differentiating the PD sources, which exhibit similar characteristic in the time domain. The obtained GAF representation of PD signals (named as PD GAF images) is extracted from local and global features to train an efficient MobileVIT model, which is then utilised to identify similar types of PD sources in cable terminals. The results show that the proposed method achieves 97.5% recognition accuracy in the field experiment, which is superior to other methods.

Cable termination is an important part of energy transmission in high-speed trains, and it is also a weak link in the insulation. It is important to determine the insulation status of cable terminals by the detection results of partial discharge signals, but the partial discharge signals in the field test circuit are mixed with a large amount of external corona interference, which affects the detection accuracy. This paper proposes a signal recognition model that incorporates Stockwell transform (ST) and 2DCNN, which in combination with wavelet noise reduction can achieve a high-precision classification effect for partial discharge and corona interference with an accuracy rate of up to 98.75%. By selecting the maximum energy moment in the ST matrix to correct the position of the time window during the recognition of long time series signals, the problem of corona interference being truncated by the time window and being misidentified as partial discharge is overcome, and the generalization ability of the model is enhanced. Experimental results show that the method has an excellent performance in separating partial discharge and corona interference in long time series signals.

Abstract The valve‐side bushing of the UHV converter transformer is the key equipment in the DC transmission project, and its running state directly affects the security and stability of the power system. This paper analyses the attributes of the physical entities, uses the digital twins to establish the state feature set and proposes a zero‐sample state evaluation algorithm for the valve‐side bushing. First, the geometric, materials and electrical characteristics are analyzed, and the detailed components of carrier current are obtained by empirical mode decomposition. Then, COMSOL is used to establish digital twins, verify the validity of twins with axial heat distribution of bushing, and establish a state feature set with the extreme temperature inside and outside bushing. Finally, the fuzzy clustering algorithm is used to classify the state feature set, and the similarity is used as the index to realize the zero‐sample state evaluation of the valve‐side bushing. Through the demonstration and analysis of examples, the evaluation model solves the problems of difficulty in extracting the internal features, fewer fault samples, and training difficulty, which is conducive to improving the operation and maintenance management level of power transmission equipment.

Thermal defects widely occur in electrical equipment and affect its stable operation. This paper proposes a novel detection method based on derivatives for thermal defects of electrical equipment. First, the equivalent models of the equipment are established to analyze the surface temperature formed by different defects. Second, the theoretical foundation of the derivative-based detection method is described, and numerical calculations on thermal defect detection based on derivative characteristic curves are carried out. The results show that the method can detect the position effectively and calculate the depth with an error of 1.6%. Then, the thermal defects in different situations are analyzed, and the results indicate that the method is effective in all cases. Finally, the experiment is conducted by artificially preparing samples with thermal defects, and the achieved calculation error of the experimental results is within 3.3%, which indicates the validity of this method.

Cable termination serves as a crucial carrier for high-speed train power transmission and a weak part of the cable insulation system. Partial discharge detection plays a significant role in evaluating insulation status. However, field testing signals are often contaminated by external corona interference, which affects detection accuracy. This paper proposes a classification model based on wavelet transform (WT) and deep belief network (DBN) to accurately and rapidly identify corona discharge in the partial discharge signals of vehicle-mounted cable terminals. The method utilizes wavelet transform for noise reduction, employing the sigmoid activation function and analyzing the impact of WT on DBN classification performance. Research indicates that this method can achieve an accuracy of over 89% even with limited training samples. Finally, the reliability of the proposed classification model is verified using measured mixed signals.

Partial discharge detection is considered a crucial technique for evaluating insulation performance and identifying defect types in cable terminals of high-speed electric multiple units (EMUs). In this study, terminal samples exhibiting four typical defects were prepared from high-speed EMUs. A cable discharge testing system, utilizing high-frequency current sensing, was developed to collect discharge signals, and datasets corresponding to these defects were established. This study proposes the use of the convolutional neural network (CNN) for the classification of discharge signals associated with specific defects, comparing this method with two existing neural network (NN)-based classification models that employ the back-propagation NN and the radial basis function NN, respectively. The comparative results demonstrate that the CNN-based model excels in accurately identifying signals from various defect types in the cable terminals of high-speed EMUs, surpassing the two existing NN-based classification models.