Modified triple modular redundancy based fault-tolerant three-phase matrix converter design with AI driven diagnostic capabilities
Three-Phase Matrix Converters (TPMCs) are mostly used in various potential applications, including aircraft, wind turbines, and AC drives. These system applications are endangered by severe disruptions due to critical faults in power electronic switches, which can cause whole system shutdowns and co...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Results in Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590123025005328 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850037508598923264 |
|---|---|
| author | Faizan Ahmad Mohaira Ahmad Faisal Hayat Sami ud Din Muhammad Adnan Arslan Ahmed Amin |
| author_facet | Faizan Ahmad Mohaira Ahmad Faisal Hayat Sami ud Din Muhammad Adnan Arslan Ahmed Amin |
| author_sort | Faizan Ahmad |
| collection | DOAJ |
| description | Three-Phase Matrix Converters (TPMCs) are mostly used in various potential applications, including aircraft, wind turbines, and AC drives. These system applications are endangered by severe disruptions due to critical faults in power electronic switches, which can cause whole system shutdowns and component damage. To reduce these risks and ensure reliable operation under faulty conditions, a robust Fault-Tolerant Control System (FTCS) for TPMC is essential. This paper introduces the diagnosed open-circuit switches fault and fault-tolerant control for TPMCs. The Fault Detection and Isolation (FDI) unit is recommended for integration with the Artificial Neural Networks (ANN) based FTCS to identify and isolate defective switches. The FDI unit is additionally outfitted with Modified Triple Modular Redundancy (MTMR) to ensure fault tolerance. To prevent system shutdowns and ensure process continuity, this system can detect faulty switches, isolate them, and then replace them with redundant ones. This strategy mitigates the impact of defective components on the system's overall performance by ensuring their prompt identification and repair. The proposed FTCS, together with MTMR and a cutting-edge FDI unit, will significantly improve the reliability. The MATLAB/Simulink results indicate that the proposed system provides 99.9 % reliability and ANN's parallel computations allow the system to offer fast fault detection. Investigations in this domain have demonstrated that the proposed methodology is an effective means of maintaining operational continuity despite the existence of open circuit failures. |
| format | Article |
| id | doaj-art-41daf12ce32a4d15a6ab7eef73047564 |
| institution | DOAJ |
| issn | 2590-1230 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Engineering |
| spelling | doaj-art-41daf12ce32a4d15a6ab7eef730475642025-08-20T02:56:51ZengElsevierResults in Engineering2590-12302025-03-012510445410.1016/j.rineng.2025.104454Modified triple modular redundancy based fault-tolerant three-phase matrix converter design with AI driven diagnostic capabilitiesFaizan Ahmad0Mohaira Ahmad1Faisal Hayat2Sami ud Din3Muhammad Adnan4Arslan Ahmed Amin5Department of Electrical Engineering, Namal University Mianwali, Mianwali 42250, Pakistan; Corresponding authors.School of Electrical Engineering and Computer Science, National University of Sciences and Technology, Islamabad, Pakistan; Corresponding authors.Department of Electrical Engineering, FAST National University of Computer and Emerging Sciences, Chiniot Faisalabad Campus, Punjab 35400, PakistanDepartment of Electrical Engineering, Namal University Mianwali, Mianwali 42250, PakistanDepartment of Electrical Engineering, FAST National University of Computer and Emerging Sciences, Chiniot Faisalabad Campus, Punjab 35400, PakistanDepartment of Electrical Engineering, FAST National University of Computer and Emerging Sciences, Chiniot Faisalabad Campus, Punjab 35400, PakistanThree-Phase Matrix Converters (TPMCs) are mostly used in various potential applications, including aircraft, wind turbines, and AC drives. These system applications are endangered by severe disruptions due to critical faults in power electronic switches, which can cause whole system shutdowns and component damage. To reduce these risks and ensure reliable operation under faulty conditions, a robust Fault-Tolerant Control System (FTCS) for TPMC is essential. This paper introduces the diagnosed open-circuit switches fault and fault-tolerant control for TPMCs. The Fault Detection and Isolation (FDI) unit is recommended for integration with the Artificial Neural Networks (ANN) based FTCS to identify and isolate defective switches. The FDI unit is additionally outfitted with Modified Triple Modular Redundancy (MTMR) to ensure fault tolerance. To prevent system shutdowns and ensure process continuity, this system can detect faulty switches, isolate them, and then replace them with redundant ones. This strategy mitigates the impact of defective components on the system's overall performance by ensuring their prompt identification and repair. The proposed FTCS, together with MTMR and a cutting-edge FDI unit, will significantly improve the reliability. The MATLAB/Simulink results indicate that the proposed system provides 99.9 % reliability and ANN's parallel computations allow the system to offer fast fault detection. Investigations in this domain have demonstrated that the proposed methodology is an effective means of maintaining operational continuity despite the existence of open circuit failures.http://www.sciencedirect.com/science/article/pii/S2590123025005328Fault-tolerant controlFault diagnosisStandby componentsArtificial neural networksModified triple modular redundancy |
| spellingShingle | Faizan Ahmad Mohaira Ahmad Faisal Hayat Sami ud Din Muhammad Adnan Arslan Ahmed Amin Modified triple modular redundancy based fault-tolerant three-phase matrix converter design with AI driven diagnostic capabilities Results in Engineering Fault-tolerant control Fault diagnosis Standby components Artificial neural networks Modified triple modular redundancy |
| title | Modified triple modular redundancy based fault-tolerant three-phase matrix converter design with AI driven diagnostic capabilities |
| title_full | Modified triple modular redundancy based fault-tolerant three-phase matrix converter design with AI driven diagnostic capabilities |
| title_fullStr | Modified triple modular redundancy based fault-tolerant three-phase matrix converter design with AI driven diagnostic capabilities |
| title_full_unstemmed | Modified triple modular redundancy based fault-tolerant three-phase matrix converter design with AI driven diagnostic capabilities |
| title_short | Modified triple modular redundancy based fault-tolerant three-phase matrix converter design with AI driven diagnostic capabilities |
| title_sort | modified triple modular redundancy based fault tolerant three phase matrix converter design with ai driven diagnostic capabilities |
| topic | Fault-tolerant control Fault diagnosis Standby components Artificial neural networks Modified triple modular redundancy |
| url | http://www.sciencedirect.com/science/article/pii/S2590123025005328 |
| work_keys_str_mv | AT faizanahmad modifiedtriplemodularredundancybasedfaulttolerantthreephasematrixconverterdesignwithaidrivendiagnosticcapabilities AT mohairaahmad modifiedtriplemodularredundancybasedfaulttolerantthreephasematrixconverterdesignwithaidrivendiagnosticcapabilities AT faisalhayat modifiedtriplemodularredundancybasedfaulttolerantthreephasematrixconverterdesignwithaidrivendiagnosticcapabilities AT samiuddin modifiedtriplemodularredundancybasedfaulttolerantthreephasematrixconverterdesignwithaidrivendiagnosticcapabilities AT muhammadadnan modifiedtriplemodularredundancybasedfaulttolerantthreephasematrixconverterdesignwithaidrivendiagnosticcapabilities AT arslanahmedamin modifiedtriplemodularredundancybasedfaulttolerantthreephasematrixconverterdesignwithaidrivendiagnosticcapabilities |