Affiliations: [a] School of Electronic and Information Engineering, Hebei University of Technology, Tianjin, China
| [b] Department of Basic Science, Army Military Transportation University, Tianjin, China
| [c] Department of Military Vehicle, Army Military Transportation University, Tianjin, China
Correspondence:
[*]
Corresponding author. Zhao Hongdong, School of Electronic and Information Engineering, Hebei University of Technology, Tianjin 300401, China. E-mail: vb6277028rangre@163.com.
Abstract: In order to improve the identification rate of fuel supply fault in diesel engine by using the vibration acceleration signal, a method of using the orthogonal vibration signals at the top and side of the cylinder head is proposed. Vibration sensors are installed at the top and side of the diesel engine to synchronously acquire the vibration acceleration signals at the two places perpendicular to each other. The fault identification of diesel engine fuel supply is achieved by extracting 17 domain time eigenvalues together with the peak value and peak-to-peak value of cross-correlation function of the orthogonal vibration signals and by using Generalized Regression Neural Network (GRNN) for classification and identification. The experimental results show that the recognition rate of fuel supply fault in diesel engine can be improved greatly by using orthogonal vibration signal, which has great engineering application value.
