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.