A knowledge-based system approach for sensor fault modeling, detection and mitigation

Silva, Jonny Carlos da; Saxena, Abhinav; Balaban, Edward; Goebel, Kai

doi:10.1016/j.eswa.2012.03.026

Cited by 80 publications

(38 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…While large biases, in general, can be detected relatively easy, it is known that drifts are among those failure types, which are, because of the temporal component in the failure signature, most difficult to detect [67]. Nevertheless, the results from the laboratory experiments demonstrate that the FDI modules of the wireless sensor nodes are capable to autonomously detect and isolate these faults.…”

Section: Discussion Of the Resultsmentioning

confidence: 76%

Decentralized fault detection and isolation in wireless structural health monitoring systems using analytical redundancy

Smarsly

Law

2014

Advances in Engineering Software

View full text Add to dashboard Cite

One of the most critical issues when deploying wireless sensor networks for long-term structural health monitoring (SHM) is the correct and reliable operation of sensors. Sensor faults may reduce the quality of monitoring and, if remaining undetected, might cause significant economic loss due to inaccurate or missing sensor data required for structural assessment and life-cycle management of the monitored structure. This paper presents a fully decentralized approach towards autonomous sensor fault detection and isolation in wireless SHM systems. Instead of physically installing multiple redundant sensors in the monitored structure ("physical redundancy"), which would involve substantial penalties in cost and maintainability, the information inherent in the SHM system is used for fault detection and isolation ("analytical redundancy"). Unlike traditional centralized approaches, the analytical redundancy approach is implemented distributively: Partial models of the wireless SHM system, implemented in terms of artificial neural networks in an object-oriented fashion, are embedded into the wireless sensor nodes deployed for monitoring. In this paper, the design and the prototype implementation of a wireless SHM system capable of autonomously detecting and isolating various types of sensor faults are shown. In laboratory experiments, the prototype SHM system is validated by injecting faults into the wireless sensor nodes while being deployed on a test structure. The paper concludes with a discussion of the results and an outlook on possible future research directions.

show abstract

Section: Discussion Of the Resultsmentioning

confidence: 76%

Decentralized fault detection and isolation in wireless structural health monitoring systems using analytical redundancy

Smarsly

Law

2014

Advances in Engineering Software

View full text Add to dashboard Cite

show abstract

“… Bias, offset and excessive noise due to measurement considered as additional faults [2][3][4][5][6][7][8][9][10][11][12].  Gain fault where the encoder signal is amplified [13].…”

Section: Introductionmentioning

confidence: 99%

Speed Sensor Faults Diagnosis in an Induction Motor Vector Controlled Drive

Bouakoura¹,

Naăźt-Saăźd²,

Naăźt-Saăźd³

2017

AEI

View full text Add to dashboard Cite

show abstract

“…A knowledge-based system for sensor fault modeling, detection, and mitigation is presented in [3]. The results are illustrated on an electro-mechanical actuator application and compared to a previously deployed neural network based system.…”

Section: Introductionmentioning

confidence: 99%

Improving Energy Efficiency and Thermal Comfort of Smart Buildings with HVAC Systems in the Presence of Sensor Faults

Gunes

Peter

Givargis

2015

2015 IEEE 17th International Conference on High Performance Computing and Communications, 2015 IEEE 7th International Symposium

View full text Add to dashboard Cite

Abstract-The smart building, as an application of the cyberphysical systems (CPSs), plays an important role in everyday lives of people. Thermal comfort and energy efficiency are primary goals for HVAC systems in smart buildings. Since the controllers of the HVACs heavily rely on data of sensors that are deployed in the buildings, temporary or permanent sensor faults may lead to increased energy consumption or decreased thermal comfort far below expectations. In this paper, we examine sensor data faults observed in the real-world sensor deployments, and their effects on thermal comfort and energy efficiency in multi-room buildings. The read-back and nearest neighbor monitoring approaches are proposed considering temporal and spatial correlations between data of sensors to mitigate the faults of interest. We adopt a model-based design methodology for the multi-room building as a CPS application and develop reusable system models in the MATLAB/Simulink environment. We conclude that the aforementioned faults may significantly reduce energy efficiency and thermal comfort unless mitigated. The proposed approaches improved thermal comfort by up to 75% for the room where the faulty sensor was deployed and reduced total energy consumption by up to 38%.

show abstract

A knowledge-based system approach for sensor fault modeling, detection and mitigation

Cited by 80 publications

References 11 publications

Decentralized fault detection and isolation in wireless structural health monitoring systems using analytical redundancy

Decentralized fault detection and isolation in wireless structural health monitoring systems using analytical redundancy

Speed Sensor Faults Diagnosis in an Induction Motor Vector Controlled Drive

Improving Energy Efficiency and Thermal Comfort of Smart Buildings with HVAC Systems in the Presence of Sensor Faults

Contact Info

Product

Resources

About