Blockage fault diagnosis method of combine harvester based on BPNN and DS evidence theory

Jin Chen; Kai Xu; Yifan Wang; Kun Wang; Shuqing Wang

doi:10.1117/12.2265524

23 January 2017 Blockage fault diagnosis method of combine harvester based on BPNN and DS evidence theory

Jin Chen, Kai Xu, Yifan Wang, Kun Wang, Shuqing Wang

Proceedings Volume 10322, Seventh International Conference on Electronics and Information Engineering; 103224C (2017) https://doi.org/10.1117/12.2265524
Event: Seventh International Conference on Electronics and Information Engineering, 2016, Nanjing, China

Abstract

According to the complexity and the lack of intelligent analysis method of combine harvester blockage fault , this paper puts forward a method , based on the combination of BP neural network (BPNN)and DS evidence theory , for combine harvester blockage fault diagnosis. Choosing cutting table auger, conveyer trough, threshing cylinder and grain conveying auger as the study, this paper divides the condition of combine harvester into four categories, namely, normal, slightly blocking, blockage, severe blockage, which being as an identification framework for DS evidence theory. BP neural network is used for analysing speed information of monitoring points and distributing basic probability for each proposition in the identification framework. Dempster combination rule converged information at different time to obtain diagnostic results.Test results show that this method can timely and accurately judge the work state of combine harvester, the blocking fault warning time will be increased to 2 seconds and the success probability of blocking fault warning reach more than 90%.

Citation Download Citation

Jin Chen, Kai Xu, Yifan Wang, Kun Wang, and Shuqing Wang "Blockage fault diagnosis method of combine harvester based on BPNN and DS evidence theory", Proc. SPIE 10322, Seventh International Conference on Electronics and Information Engineering, 103224C (23 January 2017); https://doi.org/10.1117/12.2265524

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available