Open AccessAn Efficient Cuckoo Search Algorithm for System‐Level Fault Diagnosis
Author(s) -
Xuan Hengg,
Zhang Runchi,
Shi Shengsheng
Publication year - 2016
Publication title -
chinese journal of electronics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.267
H-Index - 25
eISSN - 2075-5597
pISSN - 1022-4653
DOI - 10.1049/cje.2016.06.035
Subject(s) - cuckoo search , initialization , computer science , algorithm , correctness , binary number , fault (geology) , partition (number theory) , mathematics , particle swarm optimization , arithmetic , seismology , programming language , geology , combinatorics
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.