Research on Fault Diagnosis and Fault-Tolerant Control Technology of Instrument and Control System Under Complex Working Conditions of Nuclear Engineering

Fault diagnosis technology for instrument and control system is studied deeply in this paper. Adaptive Fuzzy Particle Swarm Optimization (AFPSO-DBN) is presented. An adaptive fuzzy mechanism is introduced in this algorithm to improve searching efficiency. Then, the weights and thresholds are optimized to improve the accuracy of fault diagnosis. This paper constructs a fault diagnosis model based on typical complicated working conditions in nuclear engineering. Compared with traditional algorithm, AFPSO-DBN improves the accuracy of fault diagnosis by <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$15 \% \sim 95 \%$</tex>. Misdiagnosis rate is reduced to 3 %. Error rate is reduced to 2 %. Dynamic redundant fault tolerant control strategy has been adopted in the experiment based on fault diagnosis results. When system failure occurs, control mode can quickly switch within 0.5 s and keep system key performance index fluctuation range within <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{5 \%}$</tex>.