Induced Voltage Noise Compensation Method Based on CWW + CNN-BiLSTM-Attention
- 29 August 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-11
Abstract
Induced voltage noise is a significant source of interference in voltage detection, seriously affecting measurement accuracy and system stability. In the complex electromagnetic environment of the Tokamak system, induced voltage noise can exceed 500 V, posing a great challenge to noise suppression in voltage detection signals. This paper presents a two-stage noise compensation approach designed to address the problem. The first stage utilizes a hardware-based Co-wound Wire (CWW) primary compensation method, effectively reducing the induced voltage noise from over 500 V to below 10 V. Building on this foundation, the second stage introduces a deep learning model based on CNN-BiLSTM-Attention as the secondary compensation module, which further reduce the residual noise to below 100 mV over a 1-second window. The proposed method was validated through real-time deployment on the Experimental Advanced Superconducting Tokamak (EAST). Experimental results demonstrate that the method not only achieves excellent compensation effect but also preserves the integrity of critical voltage detection signals throughout operation.Keywords
Funding Information
- Comprehensive Research Facility for Fusion Technology Program of China (2018-000052-73-01-001228)
- Experimental Advanced Superconducting Tokamak (EAST) Quench Detection (075ETYF301)
This publication has 33 references indexed in Scilit:
- Deep learning as a highly efficient tool for digital signal processing designLight: Science & Applications, 2024
- Innovative measurement and noise reduction of voltage coupling in shielded cables for enhanced signal integrityAIP Advances, 2023
- Superconducting materials: Challenges and opportunities for large-scale applicationsiScience, 2021
- Research on induced current and induced voltage of 500 kV double circuit transmission lineEnergy Reports, 2021
- The Performance of LSTM and BiLSTM in Forecasting Time Series2019
- A novel real-time feedback compensation system associated with inductive voltage generated by plasma in the EAST PF coil quench detection systemFusion Engineering and Design, 2019
- Deep learning for universal linear embeddings of nonlinear dynamicsNature Communications, 2018
- The Eddy Currents Calculation Based on the Least Square Algorithm for EAST2011
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Learning long-term dependencies with gradient descent is difficultIEEE Transactions on Neural Networks, 1994