Weak thruster fault detection for AUV based on Bayesian network and Hidden Markov model

Yao, Feng; Chen, Zeyu; Liu, Xing; Zhang, Mingjun

doi:10.1177/14750902221101798

Cited by 2 publications

(2 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various shortcomings in different systems can be identified and diagnosed with the use of optimization techniques, which have found widespread use in this area. Faults in the transmission network, for instance, can be detected and localized using optimization-based fault detection algorithms [38] in the power systems industry. Optimization methods have also been used in the chemical industry to enhance both the effectiveness and dependability of complex system problem detection and diagnosis [39].…”

Section: B Literature Reviewmentioning

confidence: 99%

Advanced Statistical and Meta-Heuristic Based Optimization Fault Diagnosis Techniques in Complex Industrial Processes: A Comparative Analysis

Mustafa,

Khan,

Samee

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Industrial processes are nonlinear and complicated, requiring accurate fault identification to minimize performance deterioration and respond quickly to emergencies. This work investigates industrial process defect identification and isolation, which is analytically difficult owing to their complexity. This paper carefully analyzes four design methods for flaw identification and isolation based on Principal Component Analysis (PCA), Fisher Discriminant Analysis (FDA), Kernel Fisher Discriminant Analysis (KFDA), and Sequential quadratic programming (SQP). Our study includes the Tennessee Eastman Process (TEP) and the Penicillin Fermentation Process (PFP), among other comparable methods. We assess the proposed fault detection and isolation methods through detailed analysis and comparison. The simulation findings from our extensive investigation provide remarkable insights. Simulation findings show that FDA and KFDA work well in fault identification and isolation, but PCA has certain limits. We also considered SQP as a TEP fault detection and isolation improvement tool. SQP is noted for its success in nonlinear and restricted optimization problems, making it ideal for fault identification and isolation in complicated industrial processes. Data-driven design approaches increase problem identification in complicated industrial processes with greater reliability and efficiency than PCA-based methods. This study also shows that advanced data-driven techniques can improve industrial fault diagnosis, improving operational safety and system performance by leveraging the FDA, KFDA, and SQP.

show abstract

Section: B Literature Reviewmentioning

confidence: 99%

Advanced Statistical and Meta-Heuristic Based Optimization Fault Diagnosis Techniques in Complex Industrial Processes: A Comparative Analysis

Mustafa,

Khan,

Samee

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…How to extract fault features from this complex signal has always been the hot point problem of underwater thruster fault diagnosis. 10 Common fault diagnosis methods include the state observer, 11,12 hidden Markov model, 13,14 wavelet time-frequency analysis, 15 D-S evidence theory, 16 support vector machine, 17 and neural network. 18,19 The application of deep learning technology, such as neural network, to intelligent fault diagnosis of underwater thrusters has attracted the attention of researchers.…”

Section: Introductionmentioning

confidence: 99%

Correlation analysis and fault detection of current and speed signals for underwater thruster entanglement

Zhang¹,

Geng²,

Wang³

2023

Adv Control Appl

View full text Add to dashboard Cite

The fault detection with a single sensor cannot comprehensively use the multi‐sensor correlation information of underwater thruster. To solve the issue that in the case of entanglement, a kind of fault diagnosis method of underwater thruster based on the combination of current and rotational speed signal correlation analysis and support vector machine is proposed. Firstly, the collected current and speed signals of underwater thrusters under different states are normalized, the variable sampling data points is adopted to refine the time of fault occurrence; Secondly, the cross correlation and autocorrelation coefficients of normalized current and speed signals are calculated based the variable sampling data points number and the correlation matrix is formed at different sampling time based on the cross correlation and autocorrelation coefficients. Finally, the support vector machine was applied to diagnose whether or not the fault produces and the time of fault occurrence with the correlation coefficients sequence. To verify the effectiveness of the proposed method, the fault simulation platform and data acquisition software are designed, the fault data in the case of thruster with entanglement are collected in time to test the proposed method. The results show that compared with the fault diagnosis method using only one speed or current signal, the proposed analytical method based on the correlation coefficients can fully extract the correlation information of underwater thruster fault, and the time extraction of fault occurrence is more sufficient, effectively improving the accuracy of underwater thruster fault diagnosis.

show abstract

Weak thruster fault detection for AUV based on Bayesian network and Hidden Markov model

Cited by 2 publications

References 32 publications

Advanced Statistical and Meta-Heuristic Based Optimization Fault Diagnosis Techniques in Complex Industrial Processes: A Comparative Analysis

Advanced Statistical and Meta-Heuristic Based Optimization Fault Diagnosis Techniques in Complex Industrial Processes: A Comparative Analysis

Correlation analysis and fault detection of current and speed signals for underwater thruster entanglement

Contact Info

Product

Resources

About