Free

Condition monitoring- Fault diagnosis - Literature review Example

Comments (0) Cite this document
Summary
The relative accuracy of RVM systems supported by GAs provide better classification rates for small learning data sets than for other…
Download full paperFile format: .doc, available for editing
GRAB THE BEST PAPER91.4% of users find it useful
Condition monitoring- Fault diagnosis
Read TextPreview

Extract of sample "Condition monitoring- Fault diagnosis"

Chapter 10 Fault Diagnosis of reciprocating compressors using relevance Vector Machines with a Genetic Algorithm based on vibration data Literature Review of RVM and GA-RVM for Fault Classification
Relevance vector machines (RVM) have been used in tandem with genetic algorithms (GA) in order to classify faults in non linear systems. The relative accuracy of RVM systems supported by GAs provide better classification rates for small learning data sets than for other comparable artificial intelligence fault classification methods.
RVM has been utilised along with GA in order to to optimally control nonlinear manufacturing processes. The technique relies on discerning approximately optimal control parameters of the manufacturing device. In turn, the nonlinear behavior of the manufacturing device has regression performed to filter out noise through the utilization of a kernel based Bayesian structure. The GA tabulates the near optimal control parameters in order to maximize the required objective (Yuan et al., 2007).
Rotating machinery fault diagnosis has been attempted using thermal imaging processed through RVM methods in combination with bi-dimensional empirical mode decomposition (BEMD) and generalized discriminant analysis (GDA). The BEMD enhanced thermal image is treated with GDA to reduce features after which RVM is implemented for fault classification (Tran et al., 2013).
RVM has been compared to support vector machine (SVM) methods to demonstrate its robustness for gear fault detection. Compared to SVM, the RVM method required lesser kernel functions and learning time while demonstrating comparable performance (He et al., 2009).
RVM combined with GA has been utilized in state classification of roll bearings. The GA is applied to determine training parameters for RVM. Experimentation and analysis revealed that the application of GA in combination with RVM produced better results than back propagation neural networks and SVM (Li & Liu, 2010).
A comparison of multi class RVM and SVM methods for low speed bearing fault detection revealed that RVM methods held great promise for accurate fault classification. Component analysis was carried out in order to classify features and to reduce the dimensions of the raw data set. Fault diagnosis was carried out with feature extraction and without it (Widodo et al., 2009).
Wavelet packet feature extraction was applied in tandem with RVM for detecting gear faults. Using the Fisher criterion, the discrimination power of the features is tabulated and two optimal features are selected in the time domain and wavelet domain. These are used as inputs to the RVM. Comparisons with SVM revealed that the RVM based method produced better results for online classification (Li et al., 2011).
RVM methods have been used on multi class discrimination problems in order to examine sparsity and recognition problems. RVM was used in tandem with multi class and multi kernel methods to test a number of different real world data sets. Results obtained from these methods were compared to results obtained from existing classification techniques. The application of multi kernel RVM methods demonstrated accuracy in producing multi class discrimination problems (Psorakis et al., 2010).
RVM methods were applied to analog circuits for the diagnosis of faults modeled as multi class machine learning problems. Investigation was carried out on a first order Op-amp reluctance capacitance (RC) circuit in order to demonstrate the capabilities of RVM methods in resolving such problems. Results indicated that these methods could be utilized in order to diagnose faults in more intricate analog circuits that involve a greater number of components (Jain et al., 2011).
Bibliography
He, C. et al., 2009. Relevance vector machine based gear fault detection. In CCPR, ed. Chinese Conference on Pattern Recognition. Nanjing, 2009.
Jain, V., Pillai, G.N. & Gupta, I., 2011. Fault diagnosis in analog circuits using multiclass relevance vector machines. In Proceedings of ICETECT., 2011.
Li, Y. & Liu, T., 2010. Study on classification model based on relevance vector machine with genetic algorithm. In ICIFE, ed. 2nd IEEE International Conference on Information and Financial Engineering. Chongqing, 2010.
Li, N. et al., 2011. Gear fault detection based on adaptive wavelet packet feature extraction and relevance vector machine. In SAGE, ed. Proceedings of the Institution of Mechanical Engineers, Part C, Journal of Mechnical Engineering Science., 2011. Institution of Mechanical Engineers.
Psorakis, I., Damoulas, T. & Girolami, M.A., 2010. Multiclass relevance vector machines: sparsity and accuracy. IEEE Transactions on Neural Networks, 21(10), pp.1588-98.
Tran, V.T., Yang, B.-S., Gu, F. & Ball, A., 2013. Thermal image enhancement using bi-dimensional empirical mode decomposition in combination with relevance vector machine for rotating machinery fault diagnosis. Mechanical Systems and Signal Processing, 38(2), pp.601-14.
Widodo, A. et al., 2009. Fault diagnosis of low speed bearing based on relevance vector machine and support vector machine. Expert Systems with Applications, 36, pp.7252-61.
Yuan, J., Wang, K., Yu, T. & Fang, M., 2007. Integrating relevance vector machines and genetic algorithms for optimisation of seed-separating process. Engineering Application of Artificial Intelligence, 20, pp.970-79. Read More
Cite this document
  • APA
  • MLA
  • CHICAGO
(“Condition monitoring- Fault diagnosis Literature review”, n.d.)
Retrieved from https://studentshare.org/engineering-and-construction/1633730-condition-monitoring-fault-diagnosis
(Condition Monitoring- Fault Diagnosis Literature Review)
https://studentshare.org/engineering-and-construction/1633730-condition-monitoring-fault-diagnosis.
“Condition Monitoring- Fault Diagnosis Literature Review”, n.d. https://studentshare.org/engineering-and-construction/1633730-condition-monitoring-fault-diagnosis.
  • Cited: 0 times
Comments (0)
Click to create a comment or rate a document

CHECK THESE SAMPLES OF Condition monitoring- Fault diagnosis

Condition Monitoring Photovoltaic Energy Systems-based reliability

...is quite complicated in nature which deliberates the need for continuous observations, periodic reviews and programmed precautionary repairs. Reliability in PV system involves identification and recognition of the types of faults and development of new approaches which can ensure greater performance and durability (Olita, “Advanced Control and Condition Monitoring PV Systems”; Trapani, “Performance Testing of Lacustrine and Marine Deployment Environments for Large Scale Photovoltaic Arrays”). Works Cited CSR Building Products Ltd. Thermal Stress & Thermal Fracture in Glass, 22 Dec. 2008. Web. 01 Aug. 2012. Chow, Annie. Modeling Urban Solar Energy with High Spatiotemporal Resolution....
11 Pages(2750 words)Research Paper

Condition monitoring

...(2003), Transformer PD Diagnosis using Acoustic Emission Technique. 10th International Symposium on High Voltage Engineering. Montreal, Canada. 2. Blackburn (1998), Acoustic Detection of Partial Discharges Using Non-Intrusive Optical Fibre Sensors. IEEE International Conference on Condution and Breakdown in Solid Dielectrics, Vasteras, Sweden. 3. Darley (2001), Partial Discharges within Power Transformers and the Use of Ultrasonic Techniques in Their Location. IEE Colloquium on Assessment of Degradation Within Transformer Insulation Systems, London, U.K. 4. Eleftherion (2005), Partial Discharge XXI: Acoustic Emission-Based PD Source Location in Transformers. IEEE Electrical Insulation Magazine. vol. 11, pp. 22-26. 5....
6 Pages(1500 words)Essay

Condition monitoring, fault diagnosis, fault classification or fiding fault for machenary

...methods in order to deal with condition monitoring and fault classification for machines (Mills, 2010). The realm of artificial intelligence and its application may be infant as yet but still involves the application of various methods and techniques for achieving desired ends. The current research will look into various artificial intelligence methods that have been applied to the condition monitoring and fault diagnosis for a reciprocating air compressor based on emerging and already developed methods and techniques. 1.2 Artificial IntelligenCe Based Methods It is possible to solicit problems in plant machinery using...
25 Pages(6250 words)Dissertation

Condition monitoring - fault detection and diagnosis

...an increase in the use of artificial intelligence and a number of mathematical techniques, such as principal component analysis (PCA), in order to isolate faults and offer diagnosis for industrial systems. Need for Artificial Intelligence (AI) Applications in Condition Monitoring AI techniques have been applied to a number of different industrial systems including condition monitoring. It must be recognised that the application of conventional techniques such as time domain, frequency domain and envelope analysis do not always yield satisfactory fault detection. In order to drive up the reliability of the...
4 Pages(1000 words)Dissertation

Diagnosis

...determine whether the drug reaches the desired therapeutic level in the blood. As a result, the patients can experience profound differences in how they respond to the drug. 11. The common gastrointestinal conditions that can give rise to the above scenario are acute infectious colitis, diverticulitis, colonic or intestinal neoplasms, amoebiasis, bacillary dysentery, pseudomembranous colitis, irritable bowel syndrome, abdominal lymphoma, and nongranulomatous ulcerative jejunoileitis. Q2. 1. The most likely diagnosis is acute myocardial infarction (MI). Those patients who have a family history of heart disease, personal history of smoking, hypertension, dyslipidaemia indicated by increased cholesterol...
3 Pages(750 words)Case Study

No-Fault Divorce

...No-Fault Divorce 2009 No-Fault Divorce Since the adoption of a no-fault divorce approach by the majority of s in the 1970's, this issue has become one of the most controversial and debated social policy problems in the United States. Reasoning of governments that passed the no-fault legislation was understandable: to reduce the emotional stress and finger-pointing that often accompanied full-scale divorce trials. Giving more freedom to individuals in their decision-making about marriage and family was another seeming advantage of the no-fault approach. However, the current crisis of marriage as a valid social institution made many policymakers and...
5 Pages(1250 words)Essay

The laboratory diagnosis, monitoring and management of the diabetic patient

.... New York, John Wiley and Sons. Pp 54-56. Jacobs D (1996). Laboratory Test handbook. Lexi-Comp publishers Johnstone M and Veves A (2005). Diabetes and cardiovascular disease. Hamana Press. Pp 345-350. Katsilambros N, Diakoumopoulou E and Loannidis L (2006). Diabetes in clinical practice: questions and answers from case studies. John Wiley and Sons. Pp 20-30. Lien L (2010). Glycemic Control in the Hoapitalized Patient: A comprehensive clinical guide. Springer. Pp 34-40. Reinauer H (2002). Laboratory diagnosis and monitoring of diabetes mellitus. World Health Organization. Sinclair A (2009). Diabetes in old age. New York, Wiley and Sons. Pp 30-45. Verney H, Kriebs J and Gegor C (2004). Verney’s Midwifery....
9 Pages(2250 words)Essay

Condition monitoring - fault detection and diagnosis

...Fault Identification and Diagnosis for Reciprocating Compressors Based on Support Vector Machine and Genetic Algorithm Support vector machine (SVM) methods have been used along with grid search and other learning techniques. Similarly, SVM methods have been applied in tandem with Genetic Algorithms (GAs) to obtain fault classification for fault prone software components. Comparably, SVM in tandem with GAs produced the best classification results proving its superiority over other methods for fault classification (Martino et al., 2011). Mathematical modelling and testing of SVM methods with GA indicate their superiority over regular SVM methods in dealing...
2 Pages(500 words)Literature review

Diagnosis

...Treating Addiction. Diagnostics by Before the assessment can be started it is extremely important to establish a good rapport with the client in order to foster honesty, cooperation, and trust in relationships. Only in such conditions I will be able to understand what the patient is going through and will be able to help. First, I will congratulate the client for taking such an important first step on his/her way to full life without drugs. Then I will disclose some information about myself concentrating on where addiction took me. I will let the client know that it takes courage to admit a problem and seek change though treatment. I will also let the client know that I am not going to judge him/her, and that all services...
1 Pages(250 words)Assignment

Monitoring

... Monitoring of Internet Usage The privacy of data has been a trending concern in today’s society. Employershave put in place measures that monitor the usage of computers by their employees. Some employers monitor the internet sites accessed by the employees in the course of working. In the recruitment process, the employer must inform the employee on the company’s online privacy policy. If the employer does not communicate such policies to the employee, then they have no right to monitor the internet usage of the employees. However, in most states, employers do not have an obligation by law to disclose whether they monitor the employee internet usage (Lawinfo). It may be legal for an employee to make negative comments about... the society...
1 Pages(250 words)Essay
sponsored ads
We use cookies to create the best experience for you. Keep on browsing if you are OK with that, or find out how to manage cookies.

Let us find you another Literature review on topic Condition monitoring- Fault diagnosis for FREE!

Contact Us