Multiobjective-Based Acoustic Sensor Configuration for Structural Health Monitoring of Compressor Blade

TL;DR: In this article , the optimal sensor placement (OSP) method is presented for multiple acoustic sensors based on the proposed multiobjective optimization (MOO) model and evaluation strategy, which can transform the OSP into the nonlinear mathematical MOO problem.

Abstract: Structural health monitoring (SHM) is essential to maintain the stability and efficiency of the compressor. Based on the characteristics of nondestructive evaluation, acoustic sensors are widely utilized for SHM of compressor blades. As the monitoring data of compressor blades are unable to effectively reflect damage under improper sensor configuration, the number and placements of acoustic sensors need to be optimized. In this article, the optimal sensor placement (OSP) method is presented for multiple acoustic sensors based on the proposed multiobjective optimization (MOO) model and evaluation strategy. Specially, the proposed MOO model is established from five objectives by comprehensively considering the sensor cost and monitoring reliability. It can transform the OSP into the nonlinear mathematical MOO problem. Besides, an evaluation strategy is presented to select the optimal solution from the Pareto solution set (PSS) by fully evaluating its performance. Finally, the compressor experiments are implemented to validate the effectiveness of the proposed method. Based on the experimental data collected at the OSP, the proposed method can reach an average accuracy of 97.74% under different working conditions. Through discussing and comparing with other methods, the reliability and superiority of the proposed method are verified for OSP searching and SHM. The results indicate that the proposed method can obtain reliable monitoring information and realize SHM with efficient sensor configuration.