A compound fault integrated diagnosis method for rotating machinery base on dimensionless immune detector

Real-time and accuracy fault diagnosis is the key technique to realize timely effective maintenance and health management for rotating machinery, most faults of which are compound under actual working conditions. Many compound faults are coupled with each other, fuzzy, object and some complex characteristics so it is a bottleneck problem which is very tough to break through in fault diagnosis field. Early research results indicate that diagnosis with dimensionless parameters have got good effects in single fault for rotating machinery, but under simulating actual working state of compound faults, there are obvious overlap in ranges of dimensionless parameters calculated by vibration monitoring data of each compound faults, that is to say, it is hard to distinguish the ranges of dimensionless parameters of each fault, causing complexity of diagnosis rise, and the existing method is hard to deal with this problem. To solve the difficult problem, an online fusion fault diagnosis method for rotating machinery based on dimensionless immune detector and evidence reasoning (ER) is proposed. Experimental result demonstrates that the method can realize effectively real-time fault diagnose for rotating machinery and has high potential applications in real project.