http://dx.doi.org/10.15344/2455-7412/2016/116
Abstract
For any faults of car engines, the diagnosis can be performed based on variety of symptoms. Traditionally, the description of the faulty symptom is just existence or not. However, this descriptioncannot lead to a high accuracy because the symptom sometimes appears in different degrees. Therefore, a knowledge representation method which could precisely reflect the nature of the symptom is necessary. In this paper, the fuzzy logic isfirstly appliedto quantify the degreesand uncertaintiesof symptoms.A probabilistic classification system is then constructed by using the fuzzified symptoms and a new technique, namely, Fuzzy Sparse Bayesian Extreme Learning Machine (FSBELM).Moreover, both Fuzzy Probabilistic Neural Network (FPNN) and Fuzzy Probabilistic Support Vector Machine (FPSVM) are usedto respectively construct similarclassification systems forcomparison with FSBELM. Experimental results show that FSBELM produces better performance than FPNN and FPSVM in terms of diagnostic accuracy and computational time.