A Novel Online Active Fault Diagnosis Method Based on Invariant Sets

Yang, Songlin; Xu, Feng; Wang, Xueqian; Liang, Bin

doi:10.1109/lcsys.2020.3003875

Cited by 18 publications

(6 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The above result provides an upper bound on the common area between the model output PDFs, which can be evaluated in closed form. Next, we deal with the TV distance constraint given by (8).…”

Section: Robust Active Fault Diagnosis a Optimal Input Design Under A...mentioning

confidence: 99%

“…A graphical illustration of the TV distance constraint, as well as, the feasible regions of interest D μ j and D σ j , are shown in Figure 1 for a known nominal normal PDF and with TV distance parameter pre-selected within [0, 1]. We note that, if the TV distance between the true and the nominal output PDFs is characterised through an equality constraint (i.e., see [1]), then (8) it is addressed through a feasible set of points. By the above discussion, we have that both (7) and (8), can be equivalently expressed as follows.…”

Section: Robust Active Fault Diagnosis a Optimal Input Design Under A...mentioning

confidence: 99%

“…We note that, if the TV distance between the true and the nominal output PDFs is characterised through an equality constraint (i.e., see [1]), then (8) it is addressed through a feasible set of points. By the above discussion, we have that both (7) and (8), can be equivalently expressed as follows.…”

Section: Robust Active Fault Diagnosis a Optimal Input Design Under A...mentioning

confidence: 99%

See 2 more Smart Citations

Active Fault Diagnosis for a Class of Nonlinear Uncertain Systems: A Distributionally Robust Approach

Tzortzis,

Polycarpou

2021

Preprint

View full text Add to dashboard Cite

This work is devoted to the development of a distributionally robust active fault diagnosis approach for a class of nonlinear systems, which takes into account any ambiguity in distribution information of the uncertain model parameters. More specifically, a new approach is presented using the total variation distance metric as an information constraint, and as a measure for the separation of multiple models based on the similarity of their output probability density functions. A practical aspect of the proposed approach is that different levels of ambiguity may be assigned to the models pertaining to the different fault scenarios. The main feature of the proposed solution is that it is expressed in terms of distribution's first and second moments, and hence, can be applied to alternative distributions other than normal. In addition, necessary and sufficient conditions of optimality are derived, and an offline active fault diagnosis procedure is provided to exemplify the implementation of the proposed scheme. The effectiveness of the proposed distributionally robust approach is demonstrated through an application to a three-tank benchmark system under multiple fault scenarios.

show abstract

Section: Robust Active Fault Diagnosis a Optimal Input Design Under A...mentioning

confidence: 99%

Section: Robust Active Fault Diagnosis a Optimal Input Design Under A...mentioning

confidence: 99%

Section: Robust Active Fault Diagnosis a Optimal Input Design Under A...mentioning

confidence: 99%

See 1 more Smart Citation

Active Fault Diagnosis for a Class of Nonlinear Uncertain Systems: A Distributionally Robust Approach

Tzortzis,

Polycarpou

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In the literature, various time-varying thresholds are designed to reduce the occurrence of false alarms based on the assumption that the uncertainties are unknown but bounded. [29][30][31] The dynamic thresholds based on the peak-to-peak performance were applied to residual evaluation in the aforementioned results, while their large conservatism in the initial periods may lead to missing alarms. Since all the admissible residuals are bounded by some compact sets, the set-based approaches can compute adaptive thresholds by representing and propagating the bounded uncertainties by geometric sets such as polytopes, zonotopes and ellipsoids.…”

Section: Introductionmentioning

confidence: 99%

“…However, constant thresholds may cause large conservatism within a specific time domain since they are invariable and unchanged. In the literature, various time‐varying thresholds are designed to reduce the occurrence of false alarms based on the assumption that the uncertainties are unknown but bounded 29‐31 . The dynamic thresholds based on the peak‐to‐peak performance were applied to residual evaluation in the aforementioned results, while their large conservatism in the initial periods may lead to missing alarms.…”

Section: Introductionmentioning

confidence: 99%

Fault diagnosis by interval‐based adaptive thresholds and peak‐to‐peak observers

Wang

Meslem

et al. 2022

Adaptive Control & Signal

View full text Add to dashboard Cite

This article investigates actuator fault diagnosis for continuous-time systems with unknown but bounded uncertainties. A novel interval-based adaptive threshold computation approach is proposed for residual evaluation. Meanwhile, peak-to-peak performance is applied to generate robust residuals against system uncertainties. By integrating the designed peak-to-peak residual generator with adaptive thresholds, we can achieve promising fault detection results.Furthermore, based on the general observer scheme, the proposed residual generator and adaptive thresholds can be equally used for fault isolation. Simulation results are given to illustrate the effectiveness and superiority of the proposed fault detection and isolation method.

show abstract

Closed-Loop Active Model Diagnosis Using Bhattacharyya Coefficient: Application to Automated Visual Inspection

Noom

Thao

Soloviev

et al. 2021

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

This manuscript presents an improvement of state-of-the-art Closed-Loop Active Model Diagnosis (CLAMD). The proposed method utilizes weighted Bhattacharyya coefficients evaluated at the vertices of the polytopic constraint set to provide a good trade-off between computational efficiency and satisfactory input choice for separation of candidate models of a system. A simulation of a dynamical system shows the closed-loop performance not being susceptible to the combination of candidate models. Additionally, the broad applicability of CLAMD is shown by means of a demonstrative application in automated visual inspection. This application involves sequential determination of the optimal object inspection region for the next measurement. As compared to the conventional approach using one full image to recognize handwritten digits from the MNIST dataset, the novel CLAMD-approach needs significantly (up to 78%) less data to achieve similar accuracy.

show abstract

A Novel Online Active Fault Diagnosis Method Based on Invariant Sets

Cited by 18 publications

References 16 publications

Active Fault Diagnosis for a Class of Nonlinear Uncertain Systems: A Distributionally Robust Approach

Active Fault Diagnosis for a Class of Nonlinear Uncertain Systems: A Distributionally Robust Approach

Fault diagnosis by interval‐based adaptive thresholds and peak‐to‐peak observers

Closed-Loop Active Model Diagnosis Using Bhattacharyya Coefficient: Application to Automated Visual Inspection

Contact Info

Product

Resources

About