Kaizhuang Zhu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Kaizhuang Zhu has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
Fangcheng Lv
Hebei Provincial Key Laboratory of Power Transmission Equipment Security Defense North China Electric Power University Baoding China
1 shared publication- Fangcheng Lü
Hebei Provincial Key Laboratory of Power Transmission Equipment Security Defense, North China Electric Power University, Baoding, Hebei, China
1 shared publication Jiayi Guo
Hebei Provincial Key Laboratory of Power Transmission Equipment Security Defense North China Electric Power University Baoding China
1 shared publication- Jiayi Guo
Hebei Provincial Key Laboratory of Power Transmission Equipment Security Defense, North China Electric Power University, Baoding, China
1 shared publication Jingyun Zhao
Hebei Provincial Key Laboratory of Power Transmission Equipment Security Defense North China Electric Power University Baoding China
1 shared publication- Jingyun Zhao
Hebei Provincial Key Laboratory of Power Transmission Equipment Security Defense, North China Electric Power University, Baoding, Hebei, China
1 shared publication
Latest Publications
- 30 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75 (00189456) , 1-12
An Optimization Method for Acoustic Monitoring Points on Reactors: Conditional Mutual Information and CPSO-GWO Algorithm
The acoustic signals generated by ultra-high voltage shunt reactors during operation contain valuable information about the operating status of reactors. By deploying acoustic sensor devices, on-line monitoring and diagnostics can be achieved. The placement of these sensor points affects the effectiveness of monitoring and diagnosis. To improve field monitoring effectiveness, an optimization method for monitoring point locations is proposed based on conditional mutual information (CMI) and Chaos Particle Swarm-Gray Wolf Optimization (CPSO-GWO) hybrid algorithm. First, a simulation model of the near-field acoustic environment of reactors is constructed to obtain the acoustic characteristics of external sensor points. Based on this, CMI is utilized to assess the ability of sensor signals to represent the equivalent sound-source signals from the oil tank surface. The CPSO-GWO algorithm is then employed to optimize the selection of multiple optimal acoustic monitoring points, with the goal of maximizing CMI. Taking the 500 kV high-voltage parallel reactor at a converter station as an example, simulation and experimental verification demonstrate that this proposed method is highly applicable and effective in optimizing the placement of multiple acoustic monitoring points for reactors. The CMI value of the four optimized points reaches 2.226, indicative of improvements of 1.682 and 1.331 compared to random selection (0.544) and correlation-based methods (0.895), respectively. This significantly enhances the acoustic characterization of the reactor’s operational state and provides a more comprehensive reflection of its acoustic properties. The method not only resolves issues related to sensor redundancy and improves the placement accuracy but also compensates for the limitations of existing single-point optimization strategies. The research provides a practical and feasible technical solution for optimization of acoustic monitoring points in fields such as acoustic monitoring and fault diagnosis.
- 30 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75 (00189456) , 1-12
An Optimization Method for Acoustic Monitoring Points on Reactors: Conditional Mutual Information and CPSO-GWO Algorithm
The acoustic signals generated by ultra-high voltage shunt reactors during operation contain valuable information about the operating status of reactors. By deploying acoustic sensor devices, on-line monitoring and diagnostics can be achieved. The placement of these sensor points affects the effectiveness of monitoring and diagnosis. To improve field monitoring effectiveness, an optimization method for monitoring point locations is proposed based on conditional mutual information (CMI) and Chaos Particle Swarm-Gray Wolf Optimization (CPSO-GWO) hybrid algorithm. First, a simulation model of the near-field acoustic environment of reactors is constructed to obtain the acoustic characteristics of external sensor points. Based on this, CMI is utilized to assess the ability of sensor signals to represent the equivalent sound-source signals from the oil tank surface. The CPSO-GWO algorithm is then employed to optimize the selection of multiple optimal acoustic monitoring points, with the goal of maximizing CMI. Taking the 500 kV high-voltage parallel reactor at a converter station as an example, simulation and experimental verification demonstrate that this proposed method is highly applicable and effective in optimizing the placement of multiple acoustic monitoring points for reactors. The CMI value of the four optimized points reaches 2.226, indicative of improvements of 1.682 and 1.331 compared to random selection (0.544) and correlation-based methods (0.895), respectively. This significantly enhances the acoustic characterization of the reactor’s operational state and provides a more comprehensive reflection of its acoustic properties. The method not only resolves issues related to sensor redundancy and improves the placement accuracy but also compensates for the limitations of existing single-point optimization strategies. The research provides a practical and feasible technical solution for optimization of acoustic monitoring points in fields such as acoustic monitoring and fault diagnosis.
- Open Access
- 13 December 2024
- Published by Institution of Engineering and Technology (IET) in IET Electric Power Applications
- Vol. 19 (1)
Inversion of the temperature field in oil‐immersed reactors using optimal measurement points selected by random forest
To address the subjective issue of selecting measurement points based on mainstream line methods for hotspot temperature inversion in oil‐immersed power equipment, this paper demonstrates an oil‐immersed reactor temperature field inversion method based on random forest (RF) measurement point optimisation. Firstly, a temperature field calculation method for a 22‐kV oil‐immersed reactor is proposed. In combination with Latin hypercube sampling, 50 sets of temperature field data are calculated. Based on these samples, the selection of measurement points based on RF feature importance and the training of the genetic algorithm‐optimised back propagation (GA‐BP) inversion model are undertaken. Finally, the optimal combination of external tank wall measurement points is determined based on comprehensive error indicators, achieving accurate inversion of internal hotspot temperatures in the reactor (with an error of 0.243 °C). The inversion errors are reduced by 2.91 °C and 1.47 °C on average per group compared to existing methods, evincing the superiority of the proposed model.
- 13 December 2024
- Published by Institution of Engineering and Technology (IET) in IET Electric Power Applications
- Vol. 19 (1)
Open AccessInversion of the temperature field in oil‐immersed reactors using optimal measurement points selected by random forest
To address the subjective issue of selecting measurement points based on mainstream line methods for hotspot temperature inversion in oil‐immersed power equipment, this paper demonstrates an oil‐immersed reactor temperature field inversion method based on random forest (RF) measurement point optimisation. Firstly, a temperature field calculation method for a 22‐kV oil‐immersed reactor is proposed. In combination with Latin hypercube sampling, 50 sets of temperature field data are calculated. Based on these samples, the selection of measurement points based on RF feature importance and the training of the genetic algorithm‐optimised back propagation (GA‐BP) inversion model are undertaken. Finally, the optimal combination of external tank wall measurement points is determined based on comprehensive error indicators, achieving accurate inversion of internal hotspot temperatures in the reactor (with an error of 0.243 °C). The inversion errors are reduced by 2.91 °C and 1.47 °C on average per group compared to existing methods, evincing the superiority of the proposed model.