Premium
A novel fault diagnosis technique based on model and computational intelligence applied to vehicle active suspension systems
Author(s) -
Shahab Mahdi,
Moavenian Majid
Publication year - 2018
Publication title -
international journal of numerical modelling: electronic networks, devices and fields
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.249
H-Index - 30
eISSN - 1099-1204
pISSN - 0894-3370
DOI - 10.1002/jnm.2541
Subject(s) - reliability (semiconductor) , fault detection and isolation , computer science , fault (geology) , nonlinear system , computational intelligence , point (geometry) , artificial intelligence , machine learning , mathematics , seismology , actuator , geology , power (physics) , physics , geometry , quantum mechanics
This paper introduces a novel approach to design fault detection and diagnosis systems by using computational intelligence techniques for industrial plants and processes. According to the increasing development of machine learning algorithms, selecting an appropriate algorithm for identifying and estimating the size of faults in dynamic systems can turn in to a challenge. A notable point in this regard is that although the available intelligent algorithms have considerable advantages and strengths, they are also vitiated by some weaknesses too. Therefore, using a proper and intelligent structure through combining common algorithms can be considered as a new and appropriate strategy to increase the efficiency and accuracy of fault detection and diagnosis systems. Given the importance of improving safety and reliability in vehicles, the proposed approach based on dynamic behavior is implemented on a simulated nonlinear active suspension system model. The results obtained from multiple tests indicate that the proposed method with a novel architecture has managed to increase the accuracy and reduce the announcement of false alarm and computational load, compared with other conventional methods. This achievement leads to improvement of diagnostic systems' performance.