Feedback-based optimization of feed-forward neural network for the modeling of complex nonlinear dynamical systems using novel APSOBP algorithm

This work proposes a novel hybrid Adaptive Particle Swarm Optimization-Back-propagation algorithm for training feed-forward neural networks to identify nonlinear dynamical systems. The approach begins by using Particle Swarm Optimization to optimize the network weights, followed by back propagation...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	ISA transactions Ročník 167; číslo Pt B; s. 1637
Hlavní autori:	R., Shobana, Kumar, Rajesh, Jaint, Bhavnesh
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	United States Elsevier Ltd 01.12.2025
Predmet:	Adaptive particle swarm optimization-back-propagation algorithm Back-propagation algorithm Feed forward neural network Particle swarm optimization algorithm Feed forward neural network Adaptive particle swarm optimization-back-propagation algorithm Back-propagation algorithm Particle swarm optimization algorithm
ISSN:	0019-0578, 1879-2022, 1879-2022
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	This work proposes a novel hybrid Adaptive Particle Swarm Optimization-Back-propagation algorithm for training feed-forward neural networks to identify nonlinear dynamical systems. The approach begins by using Particle Swarm Optimization to optimize the network weights, followed by back propagation to fine-tune the optimized weights, thereby improving the overall solution quality. To prevent early convergence, Particle Swarm Optimization parameters such as inertia weight and other hyperparameters are dynamically adjusted based on a performance index, which is calculated as the difference between the fitness value of the global best solution across consecutive iterations. Convergence analysis using Lyapunov stability theory is also conducted to ensure the proposed algorithm converges to a stable solution. The proposed hybrid approach is evaluated on three benchmark nonlinear problems to validate its effectiveness. Experimental results demonstrate that the hybrid algorithm outperforms traditional Particle Swarm Optimization and back-propagation algorithms in terms of convergence, accuracy, and robustness. •A novel hybrid adaptive particle swarm optimization-back propagation algorithm (APSOBP) for training feed-forward neural networks to identify nonlinear dynamical systems is proposed.•Hybrid adaptive particle swarm optimization and back-propagation algorithm are applied to optimize the weights of the feed-forward neural network.•To avoid premature convergence and improve performance, the inertia weight and cognitive and social components of PSO are dynamically adjusted based on a performance index criterion.•The experimental results of training feed-forward neural network using the APSOBP algorithm are compared to traditional feed-forward neural network training using PSO (FFNN-PSO) and BP (FFNN-BP) algorithms.•The effect of disturbance tolerance on feed-forward neural networks using the APSOBP algorithm is also discussed in the study.
Bibliografia:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ISSN:	0019-0578 1879-2022 1879-2022
DOI:	10.1016/j.isatra.2025.09.013