Multiple sensor fault diagnosis for dynamic processes

Li, Cheng-Chih; Jeng, Jyh‐Cheng

doi:10.1016/j.isatra.2010.05.001

Cited by 13 publications

(3 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…27 But affected by various harsh working environments, sensor fault is one of the most common faults in the system, and it is also the fault which is easily overlooked when the system is abnormal. 28,29 It is pointed out by Li et al 28 that there are a great amount of sensors in the modern industrial plants and the fault diagnosis of the sensor fault plays an important role in the system safety and optimal operation process. Considering the problem of multiple sensor fault detection, isolation and identification for the multivariate dynamic systems, a fault diagnosis method based on the basic sensor fault matrix is proposed and the effectiveness of this method is verified by comparing two conventional PCA-based contribution plots.…”

Section: Introductionmentioning

confidence: 99%

Sensor fault estimation based on the constrained zonotopic Kalman filter

Liu

Wang

2021

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

For solving the additive and multiplicative sensor faults in the constrained system with unknown but bounded noise, the constrained zonotopic Kalman filter-based additive sensor fault estimator and multiplicative sensor fault estimator are designed, respectively. In the fault estimation process, the states of the system are contained in the zonotopic sets estimated by the constrained zonotopic Kalman filter. The fault detection is carried out by judging whether the true value of the system's output is within the upper and lower bounds of its estimated zonotopic set. Once a fault is detected in the system, the corresponding sensor fault estimator can be used to estimate the additive or multiplicative sensor faults, and the corresponding zonotopic set and interval set can be obtained, respectively. Finally, comparative analyses of the proposed constrained zonotopic Kalman filter-based fault estimators and the zonotopic Kalman filter-based fault estimators in both numerical and case simulations prove the feasibility and effectiveness of the proposed algorithm and show the advantages of this algorithm in view of conservativeness.

show abstract

Section: Introductionmentioning

confidence: 99%

Sensor fault estimation based on the constrained zonotopic Kalman filter

Liu

Wang

2021

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

show abstract

“…Even if the sensor reading is not used for closed‐loop control and just acts as an indicator, its inaccuracy can also disturb operators’ analysis of process operation conditions. Consequently, detection and isolation of sensor faults as early as possible is crucial to ensure safe, stable, and efficient operation for industrial processes …”

Section: Introductionmentioning

confidence: 99%

Diagnosis of sensor precision degradation using Kullback‐Leibler divergence

Zhou

2017

Can J Chem Eng

View full text Add to dashboard Cite

For practical industrial processes, detection and isolation of a sensor precision degradation fault is of vital importance. In comparison with other sensor fault types such as complete failure and mean shift, the precision degradation fault is usually more difficult to detect and further to isolate. This paper proposes a new fault detection algorithm for sensor precision degradation using Kullback-Leibler divergence (KLD). The KLD is employed to quantify the dissimilarity between probability densities of each reference score and the actual one within the principal component analysis (PCA) framework. Under the assumption of Gaussian-distributed data, KLD for each score reduces to a measure of the variance difference, which is proven effective in detecting sensor precision degradation. Control limit of the KLD is established based on historical data, and online fault detection is implemented by adopting a sliding window. The fault isolation issue is also discussed, which aims to determine the faulty sensor with precision degradation. This task may be achieved by checking the PCA loading matrix and matching the fault detection result. Case studies on a synthetic numerical example and the continuous stirred tank reactor (CSTR) process are carried out to demonstrate the effectiveness of the proposed method, in comparison with conventional approaches.

show abstract

“…• Fault detection of GTs [24][25][26][27][28][29][30][31][32];…”

Section: Introductionmentioning

confidence: 99%

Feature-based fault detection of industrial gas turbines using neural networks

Rasaienia¹,

Moshiri²,

Moezzi³

2013

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Gas turbine (GT) fault detection plays a vital role in the minimization of power plant operation costs associated with power plant overhaul time intervals. In other words, it is helpful in generating pre-alarms and paves the way for corrective actions in due time before incurring major equipment failures. Hence, finding an efficient fault detection technique that is applicable in the online operation of power plants involved with minor computations is an urgent need in the power generation industry. Such a method is studied in this paper for the V94.2 class of GTs. As the most leading stage for developing a feature-based fault detection system and moving from a fixed time-scheduled maintenance to a condition-based one, principal component analysis is used for dimension reduction in the sensor data space and dimensionless key features are employed instead. One healthy condition and 6 faulty conditions are used to provide a realistic data set that is used for feature extraction, training, and testing artificial neural networks. In the proposed method, multilayer perceptron (MLP) and learning vector quantization (LVQ) networks are used for the fault classification. The good performance of the LVQ networks is presented by properly selecting the network architecture and respective initial weight vectors. When comparing the results of the MLP and LVQ networks for the fault classification, the LVQ network shows better classification results.

show abstract

Multiple sensor fault diagnosis for dynamic processes

Cited by 13 publications

References 28 publications

Sensor fault estimation based on the constrained zonotopic Kalman filter

Sensor fault estimation based on the constrained zonotopic Kalman filter

Diagnosis of sensor precision degradation using Kullback‐Leibler divergence

Feature-based fault detection of industrial gas turbines using neural networks

Contact Info

Product

Resources

About