Acoustic Emission Based Fault Detection of Substation Power Transformer

Ma, Xin; Luo, Yu; Shi, Jian; Huagang, Xiong

doi:10.3390/app12052759

Cited by 8 publications

(4 citation statements)

References 29 publications

(30 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…( The rapid advancements in deep learning have ushered in a new era for substation noise processing in recent years [19][20][21][22][23], with a notable emphasis placed on anomaly detection of substation equipment's operational status through voiceprint recognition. In the realm of audio separation, the majority of existing studies have focused on isolating multiple human voices in speech signals.…”

Section: Audio Separation Methodsmentioning

confidence: 99%

Intelligent Substation Noise Monitoring System: Design, Implementation and Evaluation

Chen,

Liu,

Gao

et al. 2024

Energies

View full text Add to dashboard Cite

In recent years, the State Grid of China has placed significant emphasis on the monitoring of noise in substations, driven by growing environmental concerns. This paper presents a substation noise monitoring system designed based on an end-network-cloud architecture, aiming to acquire and analyze substation noise, and report anomalous noise levels that exceed national standards for substation operation and maintenance. To collect real-time noise data at substations, a self-developed noise acquisition device is developed, enabling precise analysis of acoustic characteristics. Moreover, to subtract the interfering environmental background noise (bird/insect chirping, human voice, etc.) and determine if noise exceedances are originating from substation equipment, an intelligent noise separation algorithm is proposed by leveraging the convolutional time-domain audio separation network (Conv-TasNet), dual-path recurrent neural network (DPRNN), and dual-path transformer network (DPTNet), respectively, and evaluated under various scenarios. Experimental results show that (1) deep-learning-based separation algorithms outperform the traditional spectral subtraction method, where the signal-to-distortion ratio improvement (SDRi) and the scale-invariant signal-to-noise ratio improvement (SI-SNRi) of Conv-TasNet, DPRNN, DPTNet and the traditional spectral subtraction are 12.6 and 11.8, 13.6 and 12.4, 14.2 and 12.9, and 4.6 and 4.1, respectively; (2) DPTNet and DPRNN exhibit superior performance in environment noise separation and substation equipment noise separation, respectively; and (3) 91% of post-separation data maintains sound pressure level deviations within 1 dB, showcasing the effectiveness of the proposed algorithm in separating interfering noises while preserving the accuracy of substation noise sound pressure levels.

show abstract

Section: Audio Separation Methodsmentioning

confidence: 99%

Intelligent Substation Noise Monitoring System: Design, Implementation and Evaluation

Chen,

Liu,

Gao

et al. 2024

Energies

View full text Add to dashboard Cite

show abstract

“…Gradually, they can also be extended to tasks of fault detection. Although deep learning technology can process a large amount of data, it causes some problems for researchers in the face of resource conservation [61]. In many cases, traditional methods will also retain some advantages.…”

Section: Application Of Artificial Intelligence In Cavitation Detectionmentioning

confidence: 99%

A Review of Pump Cavitation Fault Detection Methods Based on Different Signals

et al. 2023

View full text Add to dashboard Cite

As one of the research hotspots in the field of pumps, cavitation detection plays an important role in equipment maintenance and cost-saving. Based on this, this paper analyzes detection methods of cavitation faults based on different signals, including vibration signals, acoustic emission signals, noise signals, and pressure pulsation signals. First, the principle of each detection method is introduced. Then, the research status of the four detection methods is summarized from the aspects of cavitation-induced signal characteristics, signal processing methods, feature extraction, intelligent algorithm identification of cavitation state, detection efficiency, and measurement point distribution position. Among these methods, we focus on the most widely used one, the vibration method. The advantages and disadvantages of various detection methods are analyzed and proposed: acoustic methods including noise and acoustic emission can detect early cavitation very well; the vibration method is usually chosen first due to its universality; the anti-interference ability of the pressure pulsation method is relatively strong. Finally, the development trend of detecting cavitation faults based on signals is given: continue to optimize the existing detection methods; intelligent algorithms such as reinforcement learning and deep reinforcement learning will be gradually integrated into the field of cavitation status identification in the future; detection systems still need to be further improved to accommodate different types of pumps; advanced sensing devices combined with advanced signal processing techniques are one of the effective means to detect cavitation in a timely manner; draw on other fault detection methods such as bearing faults and motor faults.

show abstract

“…It is necessary to implement the detailed rules for construction and supervision of geological foundation construction of substations around the country, as well as the detailed rules for monitoring, early warning and treatment of geological foundation settlement of substations [5]. At present, the geological settlement disaster of the substation is mainly monitored by means of manual observation, video images, geological displacement monitoring and other means to monitor the settlement of the geological foundation of the substation [6][7]. There are such defects as poor real-time, difficult to judge or poor accuracy when the phenomenon characteristics are not obvious, and it is impossible to find and eliminate hidden dangers in time.…”

Section: Introductionmentioning

confidence: 99%

Intelligent monitoring of substation infrastructure based on fiber Bragg grating flexible sensor

Zhu¹,

Li²,

Wang³

et al. 2023

Fourth International Conference on Optoelectronic Science and Materials (ICOSM 2022)

View full text Add to dashboard Cite

To reduce the loss caused by uneven settlement of substation foundation buildings, it is urgent to carry out long-term and real-time monitoring of the engineering structure. The FBG (fiber Bragg grating) flexible sensor was fabricated by using the POM (polyoxymethylene) material with waterproof and moisture-proof properties as the flexible substrate, and encapsulating the sensing points in the substrate by means of grooves. Temperature sensing experiments have shown that flexible sensors have good temperature self-compensation properties. In the displacement sensing experiment, the mean absolute errors of Type 1, 2 and 3 were 2.67 mm, 2.77 mm and 6.76 mm, respectively, after the curvature information obtained by the sensing point was corrected by B-spline interpolation. Compared with before correction, the mean absolute errors were reduced by 38.28 mm, 9.94 mm and 28.54 mm, respectively. The mean absolute displacement error percentages of Type 1, 2, and 3 after correction by B-spline interpolation were 1.87%, 5.28%, and 6.98%, respectively, which were 26.83%, 18.94% and 29.49% lower than those before correction. The above has shown that the interpolation algorithm effectively improves the sensing accuracy of the flexible sensor for displacement. The FBG flexible sensor designed in this paper can realize real-time monitoring of substation settlement and provide early warning, which has important application and promotion value.

show abstract

Acoustic Emission Based Fault Detection of Substation Power Transformer

Cited by 8 publications

References 29 publications

Intelligent Substation Noise Monitoring System: Design, Implementation and Evaluation

Intelligent Substation Noise Monitoring System: Design, Implementation and Evaluation

A Review of Pump Cavitation Fault Detection Methods Based on Different Signals

Intelligent monitoring of substation infrastructure based on fiber Bragg grating flexible sensor

Contact Info

Product

Resources

About