Open AccessThe Intelligent Fault Diagnosis of Diesel Engine Based on the Ensemble Learning
Author(s) -
Mingqi Shao,
Jin Wang,
Sibo Wang
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1549/4/042106
Subject(s) - diesel engine , classifier (uml) , internal combustion engine , ensemble learning , fault (geology) , computer science , reliability (semiconductor) , fault detection and isolation , combustion , artificial intelligence , automotive engineering , machine learning , engineering , power (physics) , chemistry , physics , organic chemistry , quantum mechanics , seismology , actuator , geology
As the source of power, internal combustion engine is widely used. Because the structure of internal combustion engine is complex and the working condition is bad, the possibility of failure is great. The condition monitoring and fault diagnosis of internal combustion engine can discover and eliminate the faults in time, and ensure the safety and reliability of the operation process. With the rapid progress of machine learning technology, fault diagnosis system is gradually moving towards intelligent development. The enesmble learning uses different methods to change the distribution of the original training samples, so as to build multiple different classifiers, and combine these classifiers to get a stronger classifier to make the final decision. In this paper, through the simulation model of 7k98mc diesel engine to simulate the normal and fault conditions of diesel engine, the ensemble learning algorithm is verified. The results show that the ensemble learning algorithm has higher accuracy and better stability than shallow classifiers.