Two-Step Neural-Network-Based Fault Isolation for Stochastic Systems
This paper studies a fault isolation method for an optical fiber vibration source detection and early warning system. We regard the vibration sources in the system as faults and then detect and isolate the faults of the system based on a two-step neural network. Firstly, the square root B-spline exp...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/10/22/4261 |
| _version_ | 1797464708990631936 |
|---|---|
| author | Liping Yin Jianguo Liu Hongquan Qu Tao Li |
| author_facet | Liping Yin Jianguo Liu Hongquan Qu Tao Li |
| author_sort | Liping Yin |
| collection | DOAJ |
| description | This paper studies a fault isolation method for an optical fiber vibration source detection and early warning system. We regard the vibration sources in the system as faults and then detect and isolate the faults of the system based on a two-step neural network. Firstly, the square root B-spline expansion method is used to approximate the output probability density functions. Secondly, the nonlinear weight dynamic model is established through a dynamic neural network. Thirdly, the nonlinear filter and residual generator are constructed to estimate the weight, analyze the residual, and estimate the threshold, so as to detect, diagnose, and isolate the faults. The feasibility criterion of fault detection and isolation is given by using some linear matrix inequalities, and the stability of the estimation error system is proven according to the Lyapunov theorem. Finally, simulation experiments based on a optical fiber vibration source system are given to verify the effectiveness of this method. |
| first_indexed | 2024-03-09T18:11:01Z |
| format | Article |
| id | doaj.art-94af17c4a0a84e0b9c1e447a7e57b0dd |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-09T18:11:01Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-94af17c4a0a84e0b9c1e447a7e57b0dd2023-11-24T09:08:35ZengMDPI AGMathematics2227-73902022-11-011022426110.3390/math10224261Two-Step Neural-Network-Based Fault Isolation for Stochastic SystemsLiping Yin0Jianguo Liu1Hongquan Qu2Tao Li3Shoool of Ationautom, Nanjing University of Information Science & Techonlogy, Nanjing 210044, ChinaShoool of Ationautom, Nanjing University of Information Science & Techonlogy, Nanjing 210044, ChinaSchool of Information, North China University of Technology, Langfang 065000, ChinaShoool of Ationautom, Nanjing University of Information Science & Techonlogy, Nanjing 210044, ChinaThis paper studies a fault isolation method for an optical fiber vibration source detection and early warning system. We regard the vibration sources in the system as faults and then detect and isolate the faults of the system based on a two-step neural network. Firstly, the square root B-spline expansion method is used to approximate the output probability density functions. Secondly, the nonlinear weight dynamic model is established through a dynamic neural network. Thirdly, the nonlinear filter and residual generator are constructed to estimate the weight, analyze the residual, and estimate the threshold, so as to detect, diagnose, and isolate the faults. The feasibility criterion of fault detection and isolation is given by using some linear matrix inequalities, and the stability of the estimation error system is proven according to the Lyapunov theorem. Finally, simulation experiments based on a optical fiber vibration source system are given to verify the effectiveness of this method.https://www.mdpi.com/2227-7390/10/22/4261fault detectionfault isolationB-splinefilterprobability density functions |
| spellingShingle | Liping Yin Jianguo Liu Hongquan Qu Tao Li Two-Step Neural-Network-Based Fault Isolation for Stochastic Systems Mathematics fault detection fault isolation B-spline filter probability density functions |
| title | Two-Step Neural-Network-Based Fault Isolation for Stochastic Systems |
| title_full | Two-Step Neural-Network-Based Fault Isolation for Stochastic Systems |
| title_fullStr | Two-Step Neural-Network-Based Fault Isolation for Stochastic Systems |
| title_full_unstemmed | Two-Step Neural-Network-Based Fault Isolation for Stochastic Systems |
| title_short | Two-Step Neural-Network-Based Fault Isolation for Stochastic Systems |
| title_sort | two step neural network based fault isolation for stochastic systems |
| topic | fault detection fault isolation B-spline filter probability density functions |
| url | https://www.mdpi.com/2227-7390/10/22/4261 |
| work_keys_str_mv | AT lipingyin twostepneuralnetworkbasedfaultisolationforstochasticsystems AT jianguoliu twostepneuralnetworkbasedfaultisolationforstochasticsystems AT hongquanqu twostepneuralnetworkbasedfaultisolationforstochasticsystems AT taoli twostepneuralnetworkbasedfaultisolationforstochasticsystems |