Neural networks are very promising in the design and control of distributed systems due to their powerful computing power, learning and adaptive capabilities, and distributed capabilities. The purpose of this work is to study fault-tolerant control of distributed systems based on neural networks. For nonlinear systems with actuator failures, fault-tolerant control based on a small portion of the network is required. By combining error tracking and forecasting methods to build performance metrics and reduced fault-tolerant systems, this translates into a control problem. The PSO algorithm is introduced to train the judgment neural network, which avoids the selection of the initial vector and improves the training success rate to a certain extent. To mitigate the effects of actuator errors, a neural network error observer is designed to estimate and compensate for errors. Finally, the effectiveness of the proposed fault-tolerant supervisory control method is proved by an example simulation.

Pascual Espada Jordan. Fault Tolerant Control of Distributed System Based on Neural Network. Distributed Processing System (2020), Vol. 1, Issue 3: 1-8. https://doi.org/10.38007/DPS.2020.010301.

[1] Asghari S A, Marvasti M B, Rahmani A M. Enhancing transient fault tolerance in embedded systems through an OS task level redundancy approach. Future Generation Computer Systems, 2018, 87(OCT.):58-65.

[2] Kumar G K, Elangovan D. Review on fault-diagnosis and fault-tolerance for DC–DC converters. IET Power Electronics, 2020, 13(1):1-13.

[3] Halabi L M, Alsofyani I, Lee K B. Multi Open/Short Circuit Fault-Tolerance using Modified SVM Technique for Three-Level HANPC Converters. IEEE Transactions on Power Electronics, 2020, PP(99):1-1.

[4] Boranbayev A, Boranbayev S, Nurusheva A, et al. Development of a software system to ensure the reliability and fault tolerance in information systems. Journal of Engineering and Applied Sciences, 2018, 13(23):10080-10085.

[5] Bintoudi A, Zyglakis L, Tsolakis A C, et al. Hybrid multi-agent-based adaptive control scheme for AC microgrids with increased fault-tolerance needs. IET Renewable Power Generation, 2020, 14(1):13-26.

[6] Khaldi M, Rebbah M, Meftah B, et al. Fault tolerance for a scientific workflow system in a Cloud computing environment. International Journal of Computers and Applications, 2019, 42(3):1-10.

[7] Alvarez I, Ballesteros A, Barranco M, et al. Fault Tolerance in Highly Reliable Ethernet-Based Industrial Systems. Proceedings of the IEEE, 2019, 107(6):977-1010.

[8] Florez-Tapia A M, Vadillo J, Echeverria J M. Fault tolerance of the bidirectional trans quasi-Z-source inverter. International Journal of Electrical Power & Energy Systems, 2018, 95(feb.):440-450.

[9] Jara N, Pempelfort H, Rubino G, et al. A fault-tolerance solution to any set of failure scenarios on dynamic WDM optical networks with wavelength continuity constraints. IEEE Access, 2020, PP(99):1-1.

[10] James B, Quinn H, Wirthlin M, et al. Applying Compiler-Automated Software Fault Tolerance to Multiple Processor Platforms. IEEE Transactions on Nuclear Science, 2019, PP(99):1-1.

[11] Aznar F, Pujol M, Rizo R. Obtaining Fault Tolerance Avoidance Behavior using Deep Reinforcement Learning. Neurocomputing, 2019, 345(JUN.14):77-91.

[12] Khamayseh Y, Yassein M B, Al-Nassan H. Highly Improved Artificial Bee Colony Scheme to Enhance Coverage and Fault Tolerance in Sensor Networks. International Journal on Communications Antenna and Propagation, 2019, 9(3):207-217.

[13] Bhupati, Sastry J. A framework for effecting fault tolerance within IoT network. Journal of Advanced Research in Dynamical and Control Systems, 2018, 10(2):424-432.

[14] Mireshghallah F S, Bakhshalipour M, Sadrosadati M, et al. Energy-Efficient Permanent Fault Tolerance in Hard Real-Time Systems. IEEE Transactions on Computers, 2019, PP(10):1-1.

[15] Elhadef M, Grira S. Partial syndrome-based system-level fault diagnosis using game theory. Parallel Algorithms and Applications, 2018, 33(1-2):69-86.

[16] Shahbaz M H, Amin A A. Design of Active Fault Tolerant Control System for Air Fuel Ratio Control of Internal Combustion Engines Using Artificial Neural Networks. IEEE Access, 2020, PP(99):1-1.

[17] Jinia A J, Maurer T E, Meert C A, et al. An Artificial Neural Network System for Photon-Based Active Interrogation Applications. IEEE Access, 2020, PP(99):1-1.

[18] Vita A D, Russo A, Pau D, et al. A Partially Binarized Hybrid Neural Network System for Low-Power and Resource Constrained Human Activity Recognition. Circuits and Systems I: Regular Papers, IEEE Transactions on, 2020, PP(99):1-12.