Fault Diagnosis of Diesel Engine Valve Clearance Based on Variational Mode Decomposition and Random Forest

Abstract

Diesel engines, as power equipment, are widely used in the fields of the automobile industry, ship industry, and power equipment. Due to wear or faulty adjustment, the valve train clearance abnormal fault is a typical failure of diesel engines, which may result in the performance degradation, even valve fracture and cylinder hit fault. However, the failure mechanism features mainly in the time domain and angular domain, on which the current diagnosis methods are based, are easily affected by working conditions or are hard to extract accurate enough from, as the diesel engine keeps running in transient and non-stationary processes. This work aimed at diagnosing this fault mainly based on frequency band features, which would change when the valve clearance fault occurs. For the purpose of extracting a series of frequency band features adaptively, a decomposition technique based on improved variational mode decomposition was investigated in this work. As the connection between the features and the fault was fuzzy, the random forest algorithm was used to analyze the correspondence between features and faults. In addition, the feature dimension was reduced to improve the operation efficiency according to importance score. The experimental results under variable speed condition showed that the method based on variational mode decomposition and random forest was capable to detect the valve clearance fault effectively.

A Hybrid System Based on LSTM for Short-Term Power Load Forecasting

“…Step 2: Adjust the estimated center frequency e −jω k t by adding an exponential term to each mode [34]:…”

Mechanical Fault Diagnosis of a High Voltage Circuit Breaker Based on High-Efficiency Time-Domain Feature Extraction with Entropy Features

“…According to the optimal classifier constructed in Table 3 , another 10 sets of data were selected to verify the performance of the optimal classifier, and the classification results are shown in Figure 10 . (RF) [ 20 ], (SVM)…”

“…At present, the common methods of state recognition for HVCBs include Neural Network (NNs) [ 19 ], Random Forest (RF) [ 20 ], Support Vector Machine (SVM) [ 21 , 22 ], XGBoost [ 23 , 24 ], etc. NNs have a strong self-learning ability and nonlinear pattern recognition ability, but its training speed is slow and it is easy to fall into local optimal solution [ 25 ].…”

Threshold‐Optimized Swarm Decomposition Using Grey Wolf Optimizer for the Acoustic‐Based Internal Defect Detection of Arc Magnets

“…Some modern signal processing technologies based on the multiscale adaptive decomposition have already opened the possibility to analyze the acoustic signal of arc magnets. Due to the advantage in decomposing an original signal into several different components adaptively, these methods, for instance, empirical mode decomposition (EMD) [6], local mean decomposition (LMD) [7], ensemble empirical mode decomposition (EEMD) [8], and variational mode decomposition (VMD) [9], are rather beneficial to explore the features and even weak information in nonstationary and nonlinear signals. However, the inability to overcome the adverse influence of the mode aliasing severely limits the decomposition accuracy of both EMD and LMD [10].…”