A New Feature Selection-Aided Observer for Sensor Fault Diagnosis of an Industrial Gas Turbine

Akbari, Mahyar; Khoshnood, Abdol Majid

doi:10.1109/jsen.2021.3085209

Cited by 8 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Consequently, ML fault detection is continuously improved upon through alternative methods or techniques such as prior knowledge incorporation [1,25]. Central to fault detection approaches leveraging ML methods is the appropriate identification and selection of features for dimensional reduction of data, widely practiced in the work examining industrial plant processes [29,30,31] and in ML approaches more broadly [32,33]. This work extends on previous studies of ML and fault detection by coupling ML methods with Expected Value of Information calculations (see next section).…”

Section: Fault Detection In Industrial Systemsmentioning

confidence: 79%

Dynamic Placement of Rapidly Deployable Mobile Sensor Robots Using Machine Learning and Expected Value of Information

Agogino¹,

Jang²,

Rao³

et al. 2021

Preprint

View full text Add to dashboard Cite

Although the Industrial Internet of Things has increased the number of sensors permanently installed in industrial plants, there will be gaps in coverage due to broken sensors or sparse density in very large plants, such as in the petrochemical industry. Modern emergency response operations are beginning to use Small Unmanned Aerial Systems (sUAS) that have the ability to drop sensor robots to precise locations. sUAS can provide longer-term persistent monitoring that aerial drones are unable to provide. Despite the relatively low cost of these assets, the choice of which robotic sensing systems to deploy to which part of an industrial process in a complex plant environment during emergency response remains challenging.This paper describes a framework for optimizing the deployment of emergency sensors as a preliminary step towards realizing the responsiveness of robots in disaster circumstances. AI techniques (Long short-term memory, 1-dimensional convo- * Address all correspondence to this author. lutional neural network, logistic regression, and random forest) identify regions where sensors would be most valued without requiring humans to enter the potentially dangerous area. In the case study described, the cost function for optimization considers costs of false-positive and false-negative errors. Decisions on mitigation include implementing repairs or shutting down the plant. The Expected Value of Information (EVI) is used to identify the most valuable type and location of physical sensors to be deployed to increase the decision-analytic value of a sensor network. This method is applied to a case study using the Tennessee Eastman process data set of a chemical plant, and we discuss implications of our findings for operation, distribution, and decision-making of sensors in plant emergency and resilience scenarios.

show abstract

Section: Fault Detection In Industrial Systemsmentioning

confidence: 79%

Dynamic Placement of Rapidly Deployable Mobile Sensor Robots Using Machine Learning and Expected Value of Information

Agogino¹,

Jang²,

Rao³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The authors trained multiple models, including random forests (RF), k-nearest neighbours (kNN), and ANN, and obtained the highest accuracy of 97.5% with RF. Akbari and Khoshnood (2021) constructed a FSaided observer to extract features from the time-series data of GT sensors. A sliding window observer is coupled with a decision tree model, which essentially utilises MI to rank the feature importance, to select salient features that are used to indicate the health state of GTs.…”

Section: Statistical Characteristicsmentioning

confidence: 99%

Feature selection and feature learning in machine learning applications for gas turbines: A review

Xie

Sage

Zhao

2023

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

“…Fault diagnosis methods for sensors in industrial gas turbines are proposed in Akbari and Khoshnood. 18 Ma et al 19 and Abbaspour et al 20 design diagnosis methods for sensor faults in unmanned aerial vehicle (UAV) systems. Xiong et al 21 designs a kind of sensor fault diagnosis method for electric car lithium-ion batteries.…”

Section: Introductionmentioning

confidence: 99%

A novel H∞ observer for sensor fault diagnosis of vehicle electronic stability control system with disturbance and input delay

Wang

Zhang

Han

et al. 2022

Proceedings of the Institution of Mechanical Engineers, Part D:

View full text Add to dashboard Cite

This paper mainly focuses on the sensor fault diagnosis method based on H∞ observer in vehicle electronic stability control (ESC) system with disturbance and input delay. Firstly, the four-wheel steering vehicle model is established. Secondly, the system state and sensor fault are reconstructed into new system variables by a special matrix transformation method, based on which a new H∞ observer is developed to estimate system state and sensor fault signals. Then, based on Lyapunov method and linear matrix inequality (LMI) theory, the conditions for asymptotic stability and H∞ performance of the estimation error system are proved. Finally, Carsim and Matlab/Simulink co-simulation are used to show the effectiveness of the method.

show abstract

A New Feature Selection-Aided Observer for Sensor Fault Diagnosis of an Industrial Gas Turbine

Cited by 8 publications

References 26 publications

Dynamic Placement of Rapidly Deployable Mobile Sensor Robots Using Machine Learning and Expected Value of Information

Dynamic Placement of Rapidly Deployable Mobile Sensor Robots Using Machine Learning and Expected Value of Information

Feature selection and feature learning in machine learning applications for gas turbines: A review

A novel H∞ observer for sensor fault diagnosis of vehicle electronic stability control system with disturbance and input delay

Contact Info

Product

Resources

About