Adaptive Neural-based Fault Tolerant Control for Nonlinear Systems

Fuente, José Luis de la; Mateo, Victor; Sainz, Gregorio; Saludes, Sergio

doi:10.3182/20080706-5-kr-1001.00437

Cited by 2 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It was also demonstrated that the trained neural network can diagnose the fault levels even which are absent during the training process [24]. The study [25] proposed a two-layer perceptron-based NN control loop system for reducing errors in a nonlinear control system having unknown parameters. A stable faulttolerant system through continuous updating of weights and biases in a simulated pH plant was achieved [25].…”

Section: Ann For Fault Diagnosismentioning

confidence: 99%

“…The study [25] proposed a two-layer perceptron-based NN control loop system for reducing errors in a nonlinear control system having unknown parameters. A stable faulttolerant system through continuous updating of weights and biases in a simulated pH plant was achieved [25]. The study [26] used a hybrid technique of FDI and estimation of faults in a general nonlinear system using both parallel and series neural parameter estimators.…”

Section: Ann For Fault Diagnosismentioning

confidence: 99%

“…The present research focuses on creating a benchmark dataset for intermittent faults of the sensors and uses it for training machine learning models, as the non availability of suitable testing datasets has been emphasized by [3]. It can be inferred from the literature that though different machine learning algorithms k-NN [4]- [9], Ensemble [15]- [19], SVM [10]- [14], ANN [20]- [22], [25]- [28] have been deployed, there is no consensus in the literature about the algorithm for the classification of sensor faults. Also, studies related to the diagnosis of intermittent faults in sensors are scarce.…”

Section: A Objectives Of the Studymentioning

confidence: 99%

See 2 more Smart Citations

Intermittent Fault Diagnosis in Sensors using Artificial Neural Network: A Comparative Study

Mishra¹,

Mohanty²

2022

2022 IEEE International Conference on Current Development in Engineering and Technology (CCET)

View full text Add to dashboard Cite

Processing algorithms and processing hardware have developed at a very rapid pace in the last three decades. Sensors play a vital role in the condition monitoring of various components of a manufacturing system and to measure different variables that may affect the performance of these systems. Real-time collection of data, processing of the collected data, and decision-making are challenges. Intermittent fault diagnosis is difficult as it occurs randomly and does not follow a pattern. Non-availability of a suitably labeled dataset for testing the algorithms is also a challenge. Keeping these things in mind in the present research fault-injected sensor signals are developed from the publicly available Intel Lab dataset for temperature and light sensor signals. With the help of the proposed algorithm, a Matlab code for intermittent fault injection is developed. The performances of the various machine-learning algorithms extensively used in literature are also compared with the help of accuracy, precision, recall, and F1 score values. The performances of the artificial neural networks are compared with SVM, Ensemble, and k-NN in classifying various intermittent fault modes using the classification learner application of Matlab. The trained bilayer neural network has achieved an F1 score of 0.89 which is the highest among the other tested machine learning algorithms.

show abstract

Section: Ann For Fault Diagnosismentioning

confidence: 99%