Fault diagnosis of manufacturing systems using data mining techniques

Djelloul, Imene; Sari, Zaki; Sidibe, Ibrahima dit Bouran

doi:10.1109/codit.2018.8394807

Cited by 13 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From previous work in Djelloul et al, 27 the following equation gives the coefficient of correlation R as…”

Section: Theoretical Backgroundmentioning

confidence: 99%

“…This article extends the shorter preliminary work presented at a conference. 27 In addition to the performance of data mining techniques, this article considers the comparison of the obtained results to other new approaches found in the literature.…”

Section: Related Workmentioning

confidence: 99%

“…These complex and huge historical data introduce several patterns in infinite time which can be extracted to infer about the health state of the system, leading to an important problem of data mining. 27 For example, prediction and description models in data mining are two important tasks in the field of engineering. Predictive model is when the statistics are used, from existing databases, to predict the fututre output values.…”

Section: Data Mining Techniquesmentioning

confidence: 99%

“…, X k , A is a vector of coefficients of the model, and f(X, A) is the regression. According to Djelloul et al, 27 the above equation can equivalently be written as…”

Section: Regression-based Neural Networkmentioning

confidence: 99%

“…Now, it will be shown that the matrix notation is given by where Y is the vector of observations (of size n), A is the vector of coefficients, E is the vector of residues, and X is the matrix of experiences. From previous work in Djelloul et al, 27 the following equation gives the coefficient of correlation R as…”

Section: Regression-based Neural Networkmentioning

confidence: 99%

See 4 more Smart Citations

Fault diagnosis based on the quality effect of learning algorithm for manufacturing systems

Djelloul

Sari

Sidibe³

2019

Proceedings of the Institution of Mechanical Engineers, Part I:

Self Cite

View full text Add to dashboard Cite

Fault diagnosis is becoming an important issue in industrial environment, and the accurate diagnosis is the most significant part in fault handling. This article discusses a fault detection and diagnosis problem for manufacturing systems taking into account rapid detection and speed performances of fault isolation with minimum ambiguity. However, in many complex real plants, it may not be possible to discover accurately the causes of probable faults. The accuracy of fault or fault detection by the traditional approaches is not adequate. Considering the quality effect of the learning algorithm, a new hybrid neural network approach is developed using the integration of a regression task for classification accuracy. Two models of neural networks: gradient descent and momentum & adaptive learning rate and Levenberg–Marquardt are investigated and compared. The performance of the proposed approach is evaluated using mean square error, convergence speed, and classification accuracy. The case study and experimental results are presented and discussed. A comparison with the Levenberg–Marquardt regression approach shows the importance of considering the proposed learning algorithm quality in the fault detection and diagnosis problem compared with those reported in the literature.

show abstract

“…From previous work in Djelloul et al, 27 the following equation gives the coefficient of correlation R as…”

Section: Theoretical Backgroundmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Data Mining Techniquesmentioning

confidence: 99%

“…, X k , A is a vector of coefficients of the model, and f(X, A) is the regression. According to Djelloul et al, 27 the above equation can equivalently be written as…”

Section: Regression-based Neural Networkmentioning

confidence: 99%

Section: Regression-based Neural Networkmentioning

confidence: 99%

See 3 more Smart Citations