article · Electrical Engineering
Combining particle swarm optimisation with a back propagation neural network improves fault diagnosis in photovoltaic array systems. By extracting output parameters from the solar array, the hybrid model uses deep learning capabilities for classification and prediction alongside heuristic search techniques to identify optimal solutions. Comparative testing demonstrates that the hybrid approach accelerates the training phase, converging in 250 steps compared to the 350 steps required by standard back propagation alone. Diagnostic precision also improves markedly, rising from approximately 87.8 percent with standard back propagation to 95 percent correct predictions when augmented by particle swarm optimisation. Overall, the combined technique provides faster simulation convergence and more dependable fault detection performance for solar power installations.
Solar arrays require precise monitoring to maintain efficiency and avoid costly downtime. Diagnosing electrical faults quickly and reliably prevents power generation losses and equipment damage. By accelerating computational training times and boosting detection accuracy to 95 percent, this approach supports more dependable automated oversight, enabling operators to detect and resolve technical failures faster.
This work could enable automated monitoring and diagnostic software for solar energy plant operators and asset maintenance providers. By processing extracted operational output parameters, the algorithm could be integrated into predictive maintenance software. As the findings reflect simulation and algorithmic training results, the technology remains at an early applied research stage, requiring real-world validation on physical solar infrastructure prior to commercial adoption.
AI-generated from the published abstract. Always read the original work before citing.
Abstract A heuristic particle swarm optimization combined with Back Propagation Neural Network (BPNN-PSO) technique is proposed in this paper to improve the convergence and the accuracy of prediction for fault diagnosis of Photovoltaic (PV) array system. This technique works by applying the ability of deep learning for classification and prediction combined with the particle swarm optimization ability to find the best solution in the search space. Some parameters are extracted from the output of the PV array to be used for identification purpose for the fault diagnosis of the system. The results using the back propagation neural network method only and the method of the back propagation heuristic combination technique are compared. The back propagation algorithm converges after 350 steps while the proposed BP-PSO algorithm converges only after 250 steps in the training phase. The accuracy of prediction using the BP algorithms is about 87.8% while the proposed BP-PSO algorithm achieved 95% of right predictions. It was clearly shown that the results of the back propagation heuristic combination technique had better results in the convergence of the simulation as well as in the accuracy of the prediction of the fault diagnosis in the PV system.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1007/s00202-023-01806-6
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
