Scholarlink

<p>As a key component in power systems, the safety of transformers is directly related to the stable operation of the power grid. Due to the frequent mechanical operations of the on-load tap changer (OLTC) during long-term service, mechanical faults are prone to occur. Traditional fault diagnosis methods often suffer from insufficient feature extraction and low diagnostic accuracy under complex operating conditions. To address these issues, this study proposes a novel OLTC mechanical fault diagnosis model based on CLPO-VMD-ECM-TLB. First, the improved Pgar optimization algorithm (CLPO) is used to optimize the variational mode decomposition (VMD), enhancing the ability to mitigate modal aliasing inherent in traditional methods. Then, the error correction model (ECM) is combined with a weighted reconstruction model (TCN, BiLSTM, LSTM) to further improve diagnostic accuracy and robustness.The experimental dataset consists of a total of 1920 samples. For each operating condition, 240 samples were randomly divided into training, validation, and test sets at a ratio of 8:1:1. Data acquisition was performed using three UTL2001X piezoelectric accelerometers (sensitivity: 500 mV/g, numbered 1–3), and the vibration signals were recorded with a DI-4108 data acquisition system (DATAQ Instruments, USA). Experimental results demonstrate that the designed ECM-TLB model performs excellently in OLTC mechanical fault diagnosis, achieving an average classification accuracy of 91.5%, outperforming traditional SVM, LSTM, and BiLSTM models. The model effectively enhances diagnostic accuracy and exhibits strong adaptability and real-time performance, providing robust support for the safe operation of power systems.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Design of Mechanical Fault Diagnosis Model for On-Load Tap Switch Based on CLPO-VMD-ECM-TLB

  • 期刊论文

  • 发表日期：

    2026年2月19日

查看全文
  • Mingshen Xu,
  • Po Guan,
  • Wanli Liu,
  • Jianghai Geng

摘要

As a key component in power systems, the safety of transformers is directly related to the stable operation of the power grid. Due to the frequent mechanical operations of the on-load tap changer (OLTC) during long-term service, mechanical faults are prone to occur. Traditional fault diagnosis methods often suffer from insufficient feature extraction and low diagnostic accuracy under complex operating conditions. To address these issues, this study proposes a novel OLTC mechanical fault diagnosis model based on CLPO-VMD-ECM-TLB. First, the improved Pgar optimization algorithm (CLPO) is used to optimize the variational mode decomposition (VMD), enhancing the ability to mitigate modal aliasing inherent in traditional methods. Then, the error correction model (ECM) is combined with a weighted reconstruction model (TCN, BiLSTM, LSTM) to further improve diagnostic accuracy and robustness.The experimental dataset consists of a total of 1920 samples. For each operating condition, 240 samples were randomly divided into training, validation, and test sets at a ratio of 8:1:1. Data acquisition was performed using three UTL2001X piezoelectric accelerometers (sensitivity: 500 mV/g, numbered 1–3), and the vibration signals were recorded with a DI-4108 data acquisition system (DATAQ Instruments, USA). Experimental results demonstrate that the designed ECM-TLB model performs excellently in OLTC mechanical fault diagnosis, achieving an average classification accuracy of 91.5%, outperforming traditional SVM, LSTM, and BiLSTM models. The model effectively enhances diagnostic accuracy and exhibits strong adaptability and real-time performance, providing robust support for the safe operation of power systems.