A Fault Diagnosis Methodology for Gear Pump Based on EEMD and Bayesian Network

Abstract

This paper proposes a fault diagnosis methodology for a gear pump based on the ensemble empirical mode decomposition (EEMD) method and the Bayesian network. Essentially, the presented scheme is a multi-source information fusion based methodology. Compared with the conventional fault diagnosis with only EEMD, the proposed method is able to take advantage of all useful information besides sensor signals. The presented diagnostic Bayesian network consists of a fault layer, a fault feature layer and a multi-source information layer. Vibration signals from sensor measurement are decomposed by the EEMD method and the energy of intrinsic mode functions (IMFs) are calculated as fault features. These features are added into the fault feature layer in the Bayesian network. The other sources of useful information are added to the information layer. The generalized three-layer Bayesian network can be developed by fully incorporating faults and fault symptoms as well as other useful information such as naked eye inspection and maintenance records. Therefore, diagnostic accuracy and capacity can be improved. The proposed methodology is applied to the fault diagnosis of a gear pump and the structure and parameters of the Bayesian network is established. Compared with artificial neural network and support vector machine classification algorithms, the proposed model has the best diagnostic performance when sensor data is used only. A case study has demonstrated that some information from human observation or system repair records is very helpful to the fault diagnosis. It is effective and efficient in diagnosing faults based on uncertain, incomplete information.

Fault diagnosis of rotating machinery based on time-frequency decomposition and envelope spectrum analysis

“…Additionally, experimental verification can be found in Refs. [16,17]. In this study, each feature is extracted from 4000 points from the vibration signal; hence, the length of the data segment processed by IEEMD is 4000 sampling values.…”

“…In the recent years, empirical mode decomposition (EMD), a self-adaptive, time-frequency analysis method has been presented and employed for mechanical fault diagnosis [11][12][13]. To solve the drawbacks of EMD, EEMD was proposed and also introduced to the field of mechanical fault diagnosis [14][15][16]. Although EEMD has been successfully used to diagnose mechanical faults, its non-IMF problem is a concern and needs to be considered.…”

Intelligent Fault Inference of Inverters Based on a Three‐Layer Bayesian Network

“…To consider the environmental conditions and working conditions, researchers in different fields have established specific three-layer Bayesian Network (BN) containing such factors as a layer [8,[20][21][22]. Bin Gang Xu [8] constructed a three-layer BN including machine operating state layer to diagnose four types of faults of a flexible rotor: rotor unbalance, rotor crack, etc.…”

“…Bin Gang Xu [8] constructed a three-layer BN including machine operating state layer to diagnose four types of faults of a flexible rotor: rotor unbalance, rotor crack, etc. Zengkai Liu [20] et al proposed a threelayer BN based on empirical mode decomposition method to diagnose the faults of gear pumps. In addition to the usual fault layer and fault symptom layer, the BN also contains a multisource information layer, which considers the factors such as human observation information, system maintenance information, or abnormal operation records.…”

Mathematical Morphology and Deep Learning-based Approach for Bearing Fault Recognition

“…In recent years, various fault feature extraction methods of mechanical vibration signals have been proposed and developed, such as time domain features [25,27], frequency domain features [2], entropy features [1,5], and wavelet packet energy features [15]. Features of vibration signals and various conditions recognition methods are proposed too, such as support vector machine (SVM) [2,13,28], artificial neural network (ANN) [13,17,18], Bayesian classification [21,27], genetic algorithm [6], deep learning [11,24], and k-nearest neighbor (KNN) [9,26]. Each kind of feature may contain multiple parameters, and each parameter has a different sensitivity to the condition of the machine.…”