An Efficient Cuckoo Search Algorithm for System-Level Fault Diagnosis

• Published in: Chinese Journal of Electronics Vol. 25; no. 6; pp. 999 - 1004
• Main Authors: Xuan, Hengnong, Zhang, Runchi, Shi, Shengsheng
• Format: Journal Article
• Language: English
• Published: Published by the IET on behalf of the CIE 01.11.2016
• Subjects: binary mapping algorithm optimization; CSFD; Cuckoo search; cuckoo search fault diagnosis; Cuckoo search fault diagnosis algorithm (CSFD); Equation model; fitness function; KMP algorithm; K‐means clustering; k‐means partition algorithm; optimisation; search problems; software fault tolerance; System‐level fault diagnosis; Equation model; Cuckoo search; Cuckoo search fault diagnosis algorithm (CSFD); K-means clustering; System-level fault diagnosis
• ISSN: 1022-4653; 2075-5597
• DOI: 10.1049/cje.2016.06.035

We propose a new efficient algorithm named Cuckoo search fault diagnosis（CSFD） to solve system-level fault diagnosis problem. KMP algorithm is proposed for initialization based on the K-means partition algorithm; a fitness function is designed according to the equation constraints satisfied by the test model; the binary mapping method is advanced by optimizing existing binary mapping algorithm. Experiments show that KMP algorithm significantly reduces the disparity between the initial solution and the actual solution, and CSFD algorithm improves the efficiency and correctness significantly compared with existing typical swarm intelligence diagnosis algorithm.