Diesel Engine Valve Clearance Fault Diagnosis Based on Improved Variational Mode Decomposition and Bispectrum

Abstract

The evaluation and fault diagnosis of a diesel engine’s health conditions without disassembly are very important for diesel engine safe operation. Currently, the research on fault diagnosis has focused on the time domain or frequency domain processing of vibration signals. However, early fault signals are mostly weak energy signals, and the fault information cannot be completely extracted by time domain and frequency domain analysis. Thus, in this article, a novel fault diagnosis method of diesel engine valve clearance using the improved variational mode decomposition (VMD) and bispectrum algorithm is proposed. First, the experimental study was designed to obtain fault vibration signals. The improved VMD method by choosing the optimal decomposition layers is applied to denoise vibration signals. Then the bispectrum analysis of the reconstructed signal after VMD decomposition is carried out. The results show that bispectrum image under different working conditions exhibits obviously different characteristics respectively. At last, the diagonal projection method proposed in this paper was used to process the bispectrum image, and the fourth order cumulant is calculated. The calculation results show that three states of the valve clearance are successfully distinguished.

A Novel Improved Local Binary Pattern and Its Application to the Fault Diagnosis of Diesel Engine

“…Encoding parameters [R, P] of LBP are determined. In the test, 60 groups of vibration signals were collected under each working condition, and the duration of each group of signals was 0.08 s. 30 groups were randomly selected from the data In Figure 13, whether SVM or NNC is used as the classifier, the highest recognition accuracy rate is achieved when [R, P] � [2,16]. e correct recognition rate is up to 90% for SVM and 83.33% for NNC.…”

“…It indicates that when the radius of the operator reaches is 2 and the number of sampling points is 16, the texture information of the timefrequency image has a good description ability. erefore, this parameter combination is set as [R, P] � [2,16] in the subsequent valve fault diagnosis. We use the circular LBP operator, rotation-invariant LBP operator, uniform mode LBP operator, and ILBP operator to extract features of the STFT, wavelet packet, WVD, PWVD, SPWVD, and Rihaczek time-frequency distribution images.…”

“…To further illustrate the advantage of the proposed ILBP method, several related works are introduced for comparison. One is the fault diagnosis approach for diesel engines based on selfadaptive WVD, fast correlation-based filter, and relevance vector machine proposed in [10]; the other is the fault diagnosis method of diesel engine valve clearance using the improved variational mode decomposition (VMD) and bispectrum algorithm proposed in [2]. e hamming window with width of 115 is selected in the WVD; Euclidean distance and grid search algorithm are used for parameter selection in RVM.…”

“…Abnormal valve clearance and leakage are very easy to happen since the valve mechanism always works under high temperature and high-speed airflow, which greatly affects normal operation of diesel engine [1,2].…”

Misfire Fault Diagnosis Method for Diesel Engine Based on MEMD and Dispersion Entropy

“…e vibration signal of cylinder head is widely concerned because of its rich information and easy access. However, due to the complicated structure of diesel engine and many moving parts, the vibration signal of cylinder head mixes the signals of different frequency excitation sources and strong noise, which makes it nonstationary and nonlinear [6]. It is the key to extract the fault feature from the complex vibration signal for the state recognition.…”