Case Study on Bearing Fault Diagnosis in Liquid Rocket Engine Using Envelope Detection Technique

Bearing failure is one of the foremost causes of breakdowns in rotating machinery and such failure can be catastrophic. Fault diagnosis is critical to maintaining the normal operation of the bearings. This paper proposes feature-level fusion method for rolling bearing fault diagnosis. Features are extracted from eight vibration signals to constitute a fusion vector. SVM is used for pattern recognition. The case study results show that the proposed method is useful for rolling bearing fault diagnosis.

Download Full-text

Development of fault diagnosis platform for liquid rocket engine based on experimental data

Journal of Physics Conference Series ◽

10.1088/1742-6596/2093/1/012022 ◽

2021 ◽

Vol 2093 (1) ◽

pp. 012022

Author(s):

Shoujin Chang ◽

Yong He ◽

Haitao Hu ◽

Jiaxin Chai ◽

Minghe Hu ◽

...

Keyword(s):

Experimental Data ◽

Fault Diagnosis ◽

Rocket Engine ◽

Support Vector ◽

Small Scale ◽

Liquid Rocket Engine ◽

K Nearest Neighbor ◽

Tree Model ◽

Machine Model ◽

Liquid Rocket

Abstract Aiming at the defects of difficult to establish fault diagnosis models caused by the small scale of liquid rocket engine test data, imbalanced categories and high fault coupling, the fault diagnosis platform with 10 fault diagnosis models are developed for fault diagnosis, covering K-nearest neighbor (KNN) model, optimized KNN model, logistic regression (LR) model, optimized LR model, support vector machine model, K-means model, decision tree model, neural network model, random forest model and light-GBM model. The prediction accuracies of these models are validated based on the experimental data. Among these models, the light-GBM model provide the best prediction accuracies, and 5 models have the prediction accuracy larger than 98%.

Download Full-text

An improved envelope detection method using particle swarm optimisation for rolling element bearing fault diagnosis

Journal of Computational Design and Engineering ◽

10.1016/j.jcde.2017.05.002 ◽

2017 ◽

Vol 4 (4) ◽

pp. 305-317 ◽

Cited By ~ 7

Author(s):

Sunil Tyagi ◽

S.K. Panigrahi

Keyword(s):

Fault Diagnosis ◽

Particle Swarm Optimisation ◽

Rolling Element Bearing ◽

Bearing Faults ◽

Bearing Fault ◽

Bearing Fault Diagnosis ◽

Envelope Detection ◽

Rolling Element ◽

Element Bearing ◽

Load Conditions

Abstract Traditionally Envelope Detection (ED) is implemented for detection of rolling element bearing faults by extracting the envelope of band-passed vibration signal and thereafter taking its Fourier transform. The performance of ED is highly sensitive to the envelope window (i.e. central frequency and bandwidth of the passband). This paper employs Particle Swarm Optimisation (PSO) to select the most optimum envelope window to band pass the vibration signals emanating from rotating driveline that was run in normal and with faults induced rolling element bearings. The envelopes of band-passed signals were extracted with the help of Hilbert Transform. The performance of ED whose envelope window was optimised by PSO to identify various commonly occurring bearing faults such as bearing with Outer Race Fault (ORF), Inner Race Fault (IRF) and Rolling Element Fault (REF) were checked under varying load conditions. The performance of ‘ED enhanced by PSO’ was also checked with increase in the severity of defect. It was shown that the improved ED method is successfully able to identify all types of bearing faults under different load conditions. It was shown that the by selecting envelope window by PSO makes ED especially useful to identify bearing faults at the incipient stage of defect. It was also shown by presenting comparative performance that by optimising the envelope window by PSO the performance of ED gets significantly enhanced in comparison to the traditional ED method for bearing fault diagnosis.

Download Full-text