Robust intelligent fault diagnosis strategy using Kalman observers and neuro-fuzzy systems for a wind turbine benchmark

Zemali, Zakaria; Cherroun, Lakhmissi; Hadroug, Nadji; Hafaifa, Ahmed; Iratni, Abdelhamid; Alshammari, Obaid; Çolak, İlhami

doi:10.1016/j.renene.2023.01.095

Cited by 16 publications

(7 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The KF is a set of equations provides a computational recursive algorithm of estimation can be applied to dynamic systems. Kalman's Filter uses are many and in various areas [23,24,26]. It can also estimate the process state in all interval times.…”

Section: Kalman Filtermentioning

confidence: 99%

See 1 more Smart Citation

Fault diagnosis-based observers using Kalman filters and Luenberger estimators: Application to the pitch system fault actuators

Zemali¹,

Cherroun²,

Hadroug³

et al. 2023

Diagnostyka

View full text Add to dashboard Cite

This paper aims to present a robust fault diagnosis structure-based observers for actuator faults in the pitch part system of the wind turbine benchmark. In this work, two linear estimators have been proposed and investigated: the Kalman filter and the Luenberger estimator for observing the output states of the pitch system in order to generate the appropriate residual between the measured positions of blades and the estimated values. An inference step as a decision block is employed to decide the existence of faults in the process, and to classify the detected faults using a predetermined threshold defined by upper and lower limits. All actuator faults in the pitch system of the horizontal wind turbine benchmark are studied and investigated. The obtained simulation results show the ability of the proposed diagnosis system to determine effectively the occurred faults in the pitch system. Estimation of the output variables is effectively realized in both situations: without and with the occurrence of faults in the studied process. A comparison between the two used observers is demonstrated.

show abstract

Section: Kalman Filtermentioning

confidence: 99%

“…Fault diagnosis based observers are a very interesting methodology for dynamic systems [3,23,24,25,33]. It is a model-based fault detection approach, where the principal idea is to estimate and observe unmeasured variables and uncertainty parameters of the studied process [24].…”

Section: Introductionmentioning

confidence: 99%

Fault diagnosis-based observers using Kalman filters and Luenberger estimators: Application to the pitch system fault actuators

Zemali¹,

Cherroun²,

Hadroug³

et al. 2023

Diagnostyka

View full text Add to dashboard Cite

show abstract

“…Fang et al [3] introduced a fault detection system for autonomous vehicles, combining One-Class SVM and Kalman filters. Similarly, Rezamand et al [4] and Zemali et al [5] targeted wind turbine faults, with the former integrating GRNN-ESI, PCA, and waveletbased PDF, and the latter combining Kalman filters with adaptive neuro-fuzzy systems. Baghaee et al [6] introduced a neural network-based fault detection for microgrids; Hu et al [7] explored event-triggered control for nonlinear systems; Belkhiat et al [8] presented a robust observer scheme for MIMO hybrid systems; Dutta et al [9] employed statistical methods for rotor fault detection in multicopters.…”

Section: Introductionmentioning

confidence: 99%

A Novel Approach for Discriminating Faults and Replay Attacks in Hybrid Systems

Badr,

Talebi,

Khosravi

2024

IEEE Access

View full text Add to dashboard Cite

This study proposes an innovative approach specifically devised for discriminating faults and replay attacks in the context of hybrid system, significantly advancing cyber-physical system security. At the core of our method is the intricate process of embedding distinct series of non-recurring alphanumeric codes in each cell of the output matrix. This advanced encoding strategy is essential for the accurate identification of replay attacks, as it allows for the detailed analysis of code pattern variations that are indicative of malicious activities. Our approach is uniquely effective in revealing subtle anomalies and replicated data patterns, marking a substantial enhancement in the detection of sophisticated cyber threats. Complementing this is the implementation of a Sliding Mode Observer for precise fault detection, enabling our system to simultaneously differentiate between faults and replay attacks. This dual detection strategy is thoroughly demonstrated in complex system scenarios, highlighting its effectiveness as a robust defense mechanism. The introduction of this innovative method represents a significant step forward in fortifying the security and integrity of modern hybrid systems. A four-tank hybrid system is considered as a case study, to show the effectiveness of the proposed approach in identifying and countering faults and replay attacks within the system.INDEX TERMS adaptive threshold, cyber-physical systems, fault detection, hybrid system, replay attack.

show abstract

“…Many algorithms and techniques like Naive Bayes, Artificial Neural Networks, Genetic Algorithms, Hardware Redundancy, Multi-Layer Perceptron, Limit Checking, and many more can be used to identify faults [6][7][8][9][10], which can increase efficiency and save time. Even so, different methods can be distinguished based on various factors like presumptions, the accuracy and strengths and flaws of statistical models, and others.…”

Section: Introductionmentioning

confidence: 99%

An Insight Survey on Sensor Errors and Fault Detection Techniques in Smart Spaces

Sharma,

Gupta,

Gupta

et al. 2024

CMES

View full text Add to dashboard Cite

The widespread adoption of the Internet of Things (IoT) has transformed various sectors globally, making them more intelligent and connected. However, this advancement comes with challenges related to the effectiveness of IoT devices. These devices, present in offices, homes, industries, and more, need constant monitoring to ensure their proper functionality. The success of smart systems relies on their seamless operation and ability to handle faults. Sensors, crucial components of these systems, gather data and contribute to their functionality. Therefore, sensor faults can compromise the system's reliability and undermine the trustworthiness of smart environments. To address these concerns, various techniques and algorithms can be employed to enhance the performance of IoT devices through effective fault detection. This paper conducted a thorough review of the existing literature and conducted a detailed analysis. This analysis effectively links sensor errors with a prominent fault detection technique capable of addressing them. This study is innovative because it paves the way for future researchers to explore errors that have not yet been tackled by existing fault detection methods. Significant, the paper, also highlights essential factors for selecting and adopting fault detection techniques, as well as the characteristics of datasets and their corresponding recommended techniques. Additionally, the paper presents a methodical overview of fault detection techniques employed in smart devices, including the metrics used for evaluation. Furthermore, the paper examines the body of academic work related to sensor faults and fault detection techniques within the domain. This reflects the growing inclination and scholarly attention of researchers and academicians toward strategies for fault detection within the realm of the Internet of Things.

show abstract

Robust intelligent fault diagnosis strategy using Kalman observers and neuro-fuzzy systems for a wind turbine benchmark

Cited by 16 publications

References 50 publications

Fault diagnosis-based observers using Kalman filters and Luenberger estimators: Application to the pitch system fault actuators

Fault diagnosis-based observers using Kalman filters and Luenberger estimators: Application to the pitch system fault actuators

A Novel Approach for Discriminating Faults and Replay Attacks in Hybrid Systems

An Insight Survey on Sensor Errors and Fault Detection Techniques in Smart Spaces

Contact Info

Product

Resources

About