Fault Diagnosis Method for Vacuum Contactor Based on Time-Frequency Graph Optimization Technique and ShuffleNetV2.

Sensors (Basel)

Shanxi Key Laboratory of Mining Electrical Equipment and Intelligent Control, Taiyuan University of Technology, Taiyuan 030024, China.

Published: September 2024


Category Ranking

98%

Total Visits

921

Avg Visit Duration

2 minutes

Citations

20

Article Abstract

This paper presents a fault diagnosis method for a vacuum contactor using the generalized Stockwell transform (GST) of vibration signals. The objective is to solve the problem of low diagnostic performance efficiency caused by the inadequate feature extraction capability and the redundant pixels in the graph background. The proposed method is based on the time-frequency graph optimization technique and ShuffleNetV2 network. Firstly, vibration signals in different states are collected and converted into GST time-frequency graphs. Secondly, multi-resolution GST time-frequency graphs are generated to cover signal characteristics in all frequency bands by adjusting the GST Gaussian window width factor . The OTSU algorithm is then combined to crop the energy concentration area, and the size of these time-frequency graphs is optimized by 68.86%. Finally, considering the advantages of the channel split and channel shuffle methods, the ShuffleNetV2 network is adopted to improve the feature learning ability and identify fault categories. In this paper, the CKJ5-400/1140 vacuum contactor is taken as the test object. The fault recognition accuracy reaches 99.74%, and the single iteration time of model training is reduced by 19.42%.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11478669PMC
http://dx.doi.org/10.3390/s24196274DOI Listing

Publication Analysis

Top Keywords

vacuum contactor
12
time-frequency graphs
12
fault diagnosis
8
diagnosis method
8
method vacuum
8
based time-frequency
8
time-frequency graph
8
graph optimization
8
optimization technique
8
technique shufflenetv2
8

Similar Publications

Synergistic ammonia recovery from high-ammonia anaerobic digestate via coupled bipolar electrodialysis and membrane contactor system.

Bioresour Technol

September 2025

Center for Water Cycle Research, Climate and Environmental Research Institute, Korea Institute of Science and Technology, Seoul 02792, Republic of Korea; Division of Energy & Environment Technology, KIST School, Korea University of Science and Technology, Seoul 02792, Republic of Korea. Electronic a

This study evaluates ammonia gas recovery from high-strength anaerobic digestate using a bipolar membrane electrodialysis (BPED) and membrane contactor (MC). Ammonia is a promising carbon-neutral energy carrier, while digestates present both environmental challenges and opportunities for ammonia recovery. The BPED was tested at 2,000---10,000 mg-N/L under varying voltages and flow rates, achieving up to 87.

View Article and Find Full Text PDF

This study presents a comprehensive comparison between the packed bed and monolith contactor configurations for direct air capture (DAC) via process modeling of a temperature-vacuum swing adsorption (TVSA) process. We investigate various design parameters to optimize performance across different contactor geometries, including pellet size, monolith wall thickness, active sorbent content in monoliths, and packed bed structure configurations, considering both a traditional long column (PB) and multiple shorter columns configured in parallel (PB). Our parametric analysis assesses specific exergy consumption, sorbent, and volume requirements across different operating conditions of a five-step TVSA cycle.

View Article and Find Full Text PDF

Fault Diagnosis Method for Vacuum Contactor Based on Time-Frequency Graph Optimization Technique and ShuffleNetV2.

Sensors (Basel)

September 2024

Shanxi Key Laboratory of Mining Electrical Equipment and Intelligent Control, Taiyuan University of Technology, Taiyuan 030024, China.

Article Synopsis
  • This paper introduces a fault diagnosis method for vacuum contactors that uses the generalized Stockwell transform (GST) to analyze vibration signals for better diagnosis.
  • The method enhances diagnostic efficiency by improving feature extraction and reducing unnecessary details in visual data through multi-resolution GST time-frequency graphs and optimizing their size using the OTSU algorithm.
  • Leveraging ShuffleNetV2 helps improve the ability to learn features and accurately classify faults, achieving a recognition accuracy of 99.74% and faster model training times.
View Article and Find Full Text PDF

Given the significance of dissolved HS, various techniques have been explored in the literature. The current review describes in detail the various membrane-based techniques, such as membrane contactors, for removing dissolved HS from various wastewater streams. Various types of hydrophobic membranes have been used, with more emphasis placed on PVDF hollow fiber membranes.

View Article and Find Full Text PDF

Chemical and Physical Ionic Liquids in CO Capture System Using Membrane Vacuum Regeneration.

Membranes (Basel)

August 2022

Departamento de Ingenierías Química y Biomolecular, Universidad de Cantabria, ETSIIT, 39005 Santander, Spain.

Carbon Capture Utilization and Storage technologies are essential mitigation options to reach net-zero CO emissions. However, this challenge requires the development of sustainable and economic separation technologies. This work presents a novel CO capture technology strategy based on non-dispersive CO absorption and membrane vacuum regeneration (MVR) technology, and employs two imidazolium ionic liquids (ILs), [emim][Ac] and [emim][MS], with different behavior to absorb CO.

View Article and Find Full Text PDF