A Fault Diagnosis Model of Marine Diesel Engine Fuel Oil Supply System Using PCA and Optimized SVM

Abstract

The fuel oil supply system of the marine diesel engine contains many components, which fits plenty of sensors to monitor the condition of all components. A fault sample consists of data collected from all the sensors at certain time, which lead the dimension of the fault sample is very high. When the ship is sailing, there is a randomness in fault categories and fault duration, which leads the fault data unbalanced. This paper proposes an appropriate combinational approach to address the above problems. First, to reduce computational complexity, the high dimensional fault samples are converted into the low dimensional ones using the principal component analysis (PCA). Second, a sample size optimization (SSO) strategy is proposed to address the problem of the learning from the imbalanced datasets, which improve the classification performance of support vector machine (SVM). Third, a three-dimensional Arnold mapping is introduced into the particle swarm optimization (PSO) algorithm to improve its generalization capability. Finally, the SVM optimized by the improved PSO is trained as the classifier to identify the ten faults in the fuel oil supply system. Results demonstrate that the average correct diagnosis ratio can be as high as 93.9%.

Research on adaptive diagnosis algorithm for fuel injection failure system of construction machinery diesel engine

“…The fault data samples are processed by principal component analysis and sample size optimisation strategy to improve the classification performance of the fault recognition model. The results show that the diagnosis accuracy of the fault recognition model is high (Hou et al, 2020).…”

“…The results show that the classification accuracy of the diagnosis model is high, the operation is simple, and the application prospect is good (Bi et al, 2020). Hou et al (2020) proposed to build a diesel engine fault classification and recognition model based on support vector machine algorithm, and optimise it by using the improved particle swarm optimisation algorithm. The fault data samples are processed by principal component analysis and sample size optimisation strategy to improve the classification performance of the fault recognition model.…”

A multi-output fault diagnosis framework for hydraulic system using a CNN-SVM hierarchical learning strategy

“…Furthermore, they presented a hybrid kernel limit learning machine technique for multi-output hydraulic system fault diagnosis. Hou et al [9] proposed an effective combination method that combines PSO with principal component analysis (PCA) and SVM to address the challenges associated with random fault types and durations, high-dimensional fault data, and data imbalance in ship navigation and achieves superior classification results. SVM, which is based on the structural risk minimization principle and statistical learning theory, is adept at solving problems related to small sample size and overfitting.…”

Research on Diesel Engine Fault Diagnosis Method Based on Stacked Sparse Autoencoder and Support Vector Machine

“…The implementation of dimension reduction methodology provides an effective method for better fault diagnosis. This technology includes methods such as linear discriminant analysis [9], principal component analysis (PCA) [10], and popular learning methods [11]. Javad, et al [12], used principal component analysis to reduce the size of the data set, and to eliminate the possible singularity of the data set.…”