Multi-Objective Optimal Placement of Sensors Based on Quantitative Evaluation of Fault Diagnosability

Abstract

A multi-objective optimal sensor placement method based on quantitative evaluation of fault diagnosability is proposed. Fault diagnosability evaluation is the basis of fault diagnosis, and insufficient sensor point information is the main reason for the low quantitative evaluation index of fault diagnosability. Therefore, a method to improve the fault diagnosability of a system by adding soft and hard sensors is presented. However, increasing sensors is limited by the constraints of cost, reliability and complexity. In view of this and based on ensuring the fault diagnosability, a multi-objective optimization method for the sensors is proposed to improve system reliability and promote development towards stability, efficiency and economy.

Keywords

• Fault diagnosability
• quantitative evaluation
• sensor placement
• NSGA-II