Multi Information Fusion Diagnosis Method for Diesel Engine Based on Optimized ANFIS

A novel diagnosis method based on optimized subtraction clustering ANFIS (adaptive neural fuzzy inference system) algorithm is proposed in order to improve the accuracy and reliability of diesel engine fault diagnosis. The improved analytic hierarchy process (AHP) and subtractive clustering algorith...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of physics. Conference series Jg. 1828; H. 1; S. 12040
Hauptverfasser: Han, Yuting, Fei, Jingzhou, Wang, Zhongwei
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Bristol IOP Publishing 01.02.2021
Schlagworte:
Accuracy
Adaptive algorithms
Adaptive systems
Algorithms
Analytic hierarchy process
Artificial neural networks
Clustering
Data integration
Diesel engines
Fault diagnosis
Fuzzy logic
Inference
Parameters
Physics
Reliability analysis
Subtraction
ISSN:1742-6588, 1742-6596
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A novel diagnosis method based on optimized subtraction clustering ANFIS (adaptive neural fuzzy inference system) algorithm is proposed in order to improve the accuracy and reliability of diesel engine fault diagnosis. The improved analytic hierarchy process (AHP) and subtractive clustering algorithm are combined to form a new ANFIS network suitable for multi information fusion diagnosis. The initial clustering centers of subtractive clustering algorithm and reasoning rules of ANFIS are automatically optimized by AHP algorithm without relying on expert experience. The effectiveness of the novel algorithm is investigated on the example of multi information fusion diagnosis of diesel engine, and the results indicate that the proposed method can eliminate the disadvantages of more inference rules, slow convergence speed and low diagnostic accuracy of the conventional ANFIS algorithm under multiple input parameters, which means this new method can effectively improve the accuracy of diesel engine fault diagnosis with the advantages of more fusion parameters and less calculation.
Bibliographie:ObjectType-Conference Proceeding-1
SourceType-Scholarly Journals-1
content type line 14
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/1828/1/012040