Performance Optimization Analysis of Partial Discharge Detection Manipulator Based on STPSO-BP and CM-SA Algorithms

Research on characteristics of acoustic signal of typical partial discharge models

Partial discharge (PD) detection is essential for evaluating insulation health in overhead lines with covered conductors (CC), particularly within smart grid systems. However, since transient PD signals require high-sampling-rate equipment for capture and analysis, PD detection faces the challenge of efficiently extracting sparse PD features from long signals. To address these challenges, this paper proposes a novel LWPET framework for PD detection. Specifically, we design the Legendre multi-wavelet channel attention (LWCA) module and the Legendre multi-wavelet spatial attention (LWSA) module in the multi-wavelet multi-scale frequency domain to effectively extract PD features. This approach fully leverages the multi-regularity of LW, which closely matches the physical characteristics of PD faults, to enable in-depth PD pattern mining and also enhances the analytical capacity of the feature extraction model through attention mechanisms. Additionally, the Legendre multi-wavelet patch embedding (LWPE) module is introduced to address the difficulty of long-sequence representation learning. This module extracts key patch-level features using LWCA and LWSA, and then feeds the refined features into a Transformer Encoder for further PD feature extraction. Experiments on the VSB dataset demonstrate that LWPET achieves high accuracy (MCC 0.822, precision 0.866, recall 0.800) and efficiency, demonstrating its potential for real-time PD detection in smart grids.

Due to their specially designed structures, the partial discharge detection of hybrid high-voltage power transmission lines (HHVPTL) composed of overhead lines and power cables has made it difficult to monitor the conditions of power transmission lines. A parallel recognition method for partial discharge patterns of HHVPTLs is proposed by implementing wavelet analysis and improved backpropagation neural network (BPNN) to address the shortcomings of low efficiency, poor accuracy, and inability to parallel analysis of current partial discharge (PD) detection algorithms for HHVPTLs. Firstly, considering the non-smoothness of the partial discharge of the HHVPTLs, the wavelet packet decomposition algorithm is implemented to decompose the PD of the HHVPTL and resolve the relevant signal indicators to form the attribute vectors. Then, BPNN is implemented as a classification model. A beetle optimization (DBO) algorithm based on orthogonal contrastive learning improvement is introduced to optimize the BPNN parameters since BPNN has a slow convergence problem and fails easily into a local optimum. The proposed IDBO-BPNN is employed as the model that recognizes and analyzes the parallel partial discharge patterns of HHVPTLs. Finally, the suggested model is implemented to investigate the local discharge data of an HHVPTL in the Kaggle Featured Prediction Competition and is compared with other algorithms. The experimental results indicate that the proposed model can more accurately identify whether PDs occur in an HHVPTL and detect phases where PDs occur, with higher overall accuracy and efficiency. An excellent practical performance is achieved. The proposed model can achieve the recognition accuracy of 95.5%, which is 5.3333% higher than that of the DBO-BPNN and far more than other recognition algorithms.

Partial discharge detection on power equipment using a magneto-resistive sensor

This paper presents a novel self-sensing partial discharge (PD) detection method for power transformers that leverages the transformer's iron core as an ultra-high frequency (UHF) sensor. The method aims to address the limitations of traditional PD detection techniques, which either require intrusive internal sensors or are susceptible to external interference. The experiments conducted on a 220kV transformer model with a suspension discharge defect model demonstrate the high detection sensitivity and anti-interference performance of the proposed method. The results show that the iron core can effectively sense PD UHF signals, providing a reliable and practical approach for on-site PD detection in transformers. This PD detection method solves the problem that the internal UHF sensor has security risks while the external sensor is susceptible to interference. It provides a new method for PD detection of transformers in field.

Partial discharge (PD) detection is crucial for ensuring the reliability and longevity of high-voltage insulation systems, as undetected PD can lead to catastrophic failures. This paper presents a novel hybrid detection system integrating Convolutional Neural Networks (CNN) using the ResNet architecture for feature extraction and k-Nearest Neighbors (KNN) for classification. The proposed model achieves an impressive 98.79% accuracy, 99.41% precision, and 98.74% F1-score, significantly outperforming traditional methods such as SVM and CNN-SVM hybrids. The system demonstrates robust noise resistance, maintaining a detection rate above 98%, even in adverse operational conditions. Experimental validation on both synthetic and real-world PD datasets confirms the model’s scalability, computational efficiency, and ability to classify PD signals with minimal false positives and negatives. Additionally, it quantifies critical PD characteristics, achieving a mean true charge of 19.73 pC and a mean apparent charge of 3.15 pC, enabling improved insulation diagnostics. This work establishes a new benchmark in PD detection by addressing key challenges such as noise interference, real-time monitoring, and fault classification accuracy, paving the way for industrial deployment in high-voltage equipment monitoring systems. Future research will be directed toward extending the applicability of the model to other types of electrical insulation faults, enhancing its real-time performance, and integrating it into industrial monitoring systems for comprehensive fault diagnostics. These advancements position the proposed hybrid model as a pivotal tool for improving the safety and reliability of high-voltage insulation systems.

Partial Discharge (PD) detection and its estimation is a vital event for all the power equipment. Acoustic sensor based PD detection is more advantageous than the other available PD measurement technique. Acoustic PD detection technique has noise immunity ability to perform online partial discharge detection. In this work, a real life transformer model (RLTM) has been developed in the laboratory. Experimental procedure using acoustic sensor has been adopted to generate PD within RLTM. Several acoustic PD data have been acquired through acoustic sensors by placing the artificially created PD source at various locations inside the RL TM. Each of the sensor readings can be thought of as a waveform (time-series data) whose structure changes depending on the fault location. The novelty of the work lies in the fact that a number of features have been extracted using the Time Series Feature Extraction on Basis of Scalable Hypothesis tests (tsfresh- A Python Package) from the acoustic partial discharge data followed by classification using Random Forest classifier. Feature Selection is executed using Mutual Information Method. Percentage of identification accuracy for individual and coupled partial discharge sources are 94.4% and 91.5% respectively

This paper describes an on-line partial discharge (PD) detection technique in power cables. The technique uses a digital spectrum analyzer with a high-frequency preamplifier and several types of high-frequency inductive sensors. In extruded and impregnated cables, the PD detection is made in the VHF range. The suitability and the sensitivity of the VHF technique were checked against two other conventional PD detecting methods (Pulse Phase Analyzer and Fast Digital Scope) by performing PD measurements in EPR-insulated cable under laboratory-controlled conditions. The suitability and sensitivity of the VHF method were as good as the two conventional PD detection method. The VHF method runs used to conduct on-site PD measurement in several power cables. These measurements were conducted while the cables were in service. Special care was given to distinguish between external electromagnetic noise and electromagnetic signals produced by the PD activities inside the cable insulation.

<div class="section abstract"><div class="htmlview paragraph">Partial discharge (PD) detection has been always a fundamental tool, potentially, for the design, quality control, commissioning, and reliability monitoring for the of insulation systems. The word “potentially” stems from the objective consideration of the intrinsic limitations suffered by the existing partial discharge, PD, measurement technologies, especially the need of experts to interpret results and the lack of clear correlation between PD-related quantities, and the condition-based maintenance approach. On the whole, a thorough revision of insulation systems design procedures and of the tools to evaluate aging and failure risk is needed, especially in components of electrical assets which are critical in terms of reliability, resilience, and safety. This paper focuses on critical asset components, such as ships, aircrafts, aerospace, and any type of vehicles, where the coming electrification is significantly increasing nominal voltage, power density and efficiency, and where power electronics is the operative core. A new design approach, PD-free and reliability redundant, is briefly discussed, highlighting the importance to develop an innovative PD detection and analytics approach where measurements and interpretation are fully automatic and unsupervised, and experts are replaced by artificial intelligence. The aim is to remove the adverb “potentially” applied to the usefulness of PD detection and monitoring. The application of this innovative PD technology to measurements on dedicated test objects, able to incept either internal or surface discharges, or both, show how the capability to identify automatically the source typology of PD can help both in insulation system design and in devising health-condition monitoring systems for the asset components.</div></div>

Aiming at the problem of multi-objective path planning (MOPP) and dynamic obstacle avoidance of manipulator in dynamic environment, this paper proposes a solution based on hierarchical reinforcement learning (HRL) framework. Traditional path planning methods have some problems in dynamic scenes, such as poor real-time performance, difficult to balance multi-objective conflicts and insufficient adaptability to environmental changes. Therefore, this paper designs a two-tier architecture including global path planning layer and local obstacle avoidance layer, which is trained by Proximal policy optimization (PPO) and Soft Actor-Critic (SAC) algorithms respectively, and achieves collaborative optimization through an efficient information exchange mechanism between layers. At the same time, a multi-objective reward function based on dynamic weight adjustment strategy is introduced. Fuzzy logic is used to adaptively balance the relationship among path length, obstacle avoidance safety and energy consumption according to environmental complexity. Combined with Long Short-Term Memory (LSTM), the trajectory of obstacles is predicted, and the potential field method is further introduced to modify the obstacle avoidance reward, which improves the real-time response ability and robustness of the algorithm in dynamic environment. The experimental results show that the HRL-SAC-PPO method proposed in this paper shows superior performance in both static and dynamic scenarios. In the static scene, the success rate of this method reaches 100%, the average path length is shortened to 2.13m, no collision occurs, and the energy consumption is reduced to 1.12 kJ, which shows a good multi-objective optimization effect. In the dynamic scene, the trajectory error of obstacles predicted by LSTM is only 4.2%, and the safe distance between the robot arm and obstacles is improved by 35%, which significantly enhances the reliability of obstacle avoidance. In addition, the average decision delay of this method is only 11.3ms, and the peak delay is 23ms, which is much lower than that of the contrast algorithm, showing stronger real-time response ability. The ablation experiment further verified the key role of LSTM trajectory prediction, dynamic weight adjustment and layered structure on the overall performance. In the welding task verification of the real UR5 manipulator, the success rate of the system in dynamic environment is 95.3%, the average path length is 3.41m, and the maximum joint acceleration is only 0.87 radian/s², which is far below the safety threshold, indicating that the algorithm has good stability and obstacle avoidance ability in practical application. The comprehensive performance comparison shows that this method performs well in different industrial scenarios, and has stronger environmental adaptability and comprehensive path planning ability.

This paper proposes two alternative methods for online partial discharge (PD) detection and localization of a 6.2/7 kV XLPE insulated medium voltage (MV) power cable. The artificial defect as surface discharge was made in the middle of the cable at the joint connecting between two of 10 m length cables with 50 sq.mm diameter. Therefore, the total length of the cable is 20 m. In addition, the corona discharge was also made at the end of cable termination. The PD measurement was performed under uncontrollable noises with limitations of cable characteristics. UHF and HFCT sensors together with their supplemented techniques as Trending method for UHF sensor as well as Time Domain Reflectometry (TDR) technique for HFCT sensor are applied in the experiment in order to identify and locate the PD types. The results for PD identification and localization of both UHF and HFCT sensors are satisfied.

Acoustic partial discharge (PD) detection method has been developed as an important non-destructive testing technique adopted for monitoring the material processes and for testing, detection, and characterization of any defect in an electrical apparatus like power transformers. This method has advantages like the placement of several sensors on the outside of the tank allows a localization of PD source and measurements can be performed on-line and on-site. The paper describes a combination of UHF/electrical and acoustic method because combination of methods more increases plausibility of PD activity than pure acoustic method. This method can find PD sources with higher sensitivity especially for hidden PD defects. An experimental validation has been done on the transformer insulation model using an acoustic sensor at first in this paper. The study was complemented with measurements on transformers in test field.

Partial discharge (PD) detection is an important method to verify the reliability of the insulation structure of high voltage power electronics devices. Although there are many researches on PD detection inside power modules, they mainly focus on traditional electrical detection methods and 50 Hz working conditions, which do not meet the repetitive unipolar impulsive voltage conditions of power modules, and traditional methods cannot solve the electromagnetic interference (EMI) problem under working conditions. This paper proposes a novel approach to PD detection in power modules. This approach designs an optic fiber sensing (OFS) system based on optic theory, and conducts the detailed mathematical theoretical deduction. In addition, A partial discharge inception voltage (PDIV) signal processing method based on PD acoustic signal is proposed. Finally, the proposed approach is applied to a power module. The PD signal and PDIV is successfully captured without EMI interference and new insulation problems.

At present, the partial discharge(PD) detection of high voltage power capacitor usually employs a resonant circuit which requires a very bulky reactor, and a PD detector with ultrasonic sensors. One of the problems with this approach is difficult experimental setup. Another is the limitation of PD signal analyze and get further valuable information, due to the properties of ultrasonic signal itself. This paper reports on a new user-friendly and effective way to carry out PD test of HV power capacitor. This system contains a supply module, a specially made sampling impedance and a PD pulse collector. The supply module, consists of high voltage DC power generator, protection resistance, damping resistance, semiconductor switch, which is integrated designed, characterized by small size, light weight, and low power consumption. The specially made sampling impedance which is employed to obtain PD signals could be applied to the detection of capacitor samples with different capacity, and the impedance can be directly connected to the end of the capacitor without the influence of large current signal. And the PD pulse collector is different from PD detectors under stable voltage, which needs to grasp the PD signal accurately in several cycles of the test loop oscillation, and the signal acquisition is required to be continuous. Compared with the previous approach, the oscillating wave circuit with specially made impedance reported in this paper, showed much more portability for large power capacitors PD detection, and the results provided chances for time and frequency domain spectrum analysis, which could be helpful to identify the PD type of HV power capacitors.

At present, photovoltaic power generation is becoming more and more important in the field of new energy power generation. The traditional BP neural network algorithm is prone to fall into local extreme points in the training process of the short-term photovoltaic power prediction model, and the training model If the global optimum is not reached, the optimization is stopped, and the weights of the initial network are randomly selected, which leads to problems such as low model prediction accuracy and low iteration efficiency. This paper proposes a short-term photovoltaic power prediction algorithm based on improved BP neural network. The method uses the Levenberg-Marquardt algorithm to replace the traditional gradient descent method for training, which improves the iterative speed of the traditional BP neural network training, and uses the genetic algorithm to optimize the initial weight of the network model, which further improves the model prediction accuracy. The simulation results show that the prediction accuracy of the improved algorithm for short-term photovoltaic power is significantly better than that of the algorithm before the improvement, and the stability and iterative efficiency are greatly improved.