Acoustic Sensor Placement Optimization for Compressor Based on Adversarial Transfer Learning and Vibro-Acoustic Simulation

Generally, the success of the optimal sensor placement (OSP) method based on artificial intelligence (AI) highly depends on signals at all feasible placements, which may be unavailable or expensive. Therefore, the acoustic sensor placement optimization method is proposed based on adversarial transfer learning (ATL) and vibro-acoustic simulation. First, the vibro-acoustic simulation is applied to provide sufficient simulation signals for all feasible placements. To bridge the deviation of simulation and measured signals, the ATL-based conditional generative adversarial network (CGAN) is presented, which can transfer signals from limited measured placements to unmeasured placements. In addition, a multi-objective optimization model is proposed to obtain the OSP from three aspects, and it is useful for structural health monitoring (SHM). The acoustic signals obtained from the experimental platform are utilized to explore the feasibility and effectiveness of the proposed method. It can accurately detect the fault with an average accuracy of 98.35% under four working conditions. The comparison investigations demonstrate that the proposed method can obtain high-quality signals at all feasible placements, which can realize SHM with the OSPs and the least sensor cost.