Enhanced diagnostic certainty using information entropy theory

As is well known, the information entropy is a basic notion in cybernetics. This paper mainly summarizes some applications of information entropy in our machinery diagnostic research practice. First, we use it as a quantitative measure of equipment diagnostibility, maintainability. Second, we introduce a criterion of complexity in frequency domain to evaluate the complexity of diagnostic signal in rotating machinery. Then a new criterion called the index of orbit complexity is proposed to evaluate the dynamic quality of rotor systems during their operation. Finally the entropy distance is applied as an effective diagnostic feature to discriminate the potential faults inside the operating machinery. Practical case studies and experiments show its effectiveness. q 2004 Elsevier Ltd. All rights reserved.