This study provides quantitative support for analyzing current fire communication command systems and enabling their iterative upgrades. A four-level efficacy evaluation index system for brigade-level fire command communication systems was constructed, based on fire communication command system design specifications. This system assessed three key dimensions: operational support capability, data service capability, and communication assurance capability. An IPSO-BP-based system efficacy evaluation method was proposed, building upon BP neural network algorithm. Parameters were optimized using IPSO algorithm. Sample data were acquired through a combination of expert scoring and the Analytic Hierarchy Process (AHP). Principal Component Analysis (PCA) was applied for dimensionality reduction. Simulation comparisons were conducted using three distinct models: BP neural network, PSO-BP neural network, and IPSO-BP neural network. Results demonstrate that IPSO-BP neural network model achieves the fastest convergence speed. Its mean square error decreases by 75.71% compared to BP neural network model and by 45.96% compared to PSO-BP neural network model, representing the lowest error value among the three models. Furthermore, IPSO-BP model reasonably and accurately evaluates brigade-level fire communication command system efficacy, demonstrating considerable generalizability.

fire communication command system  /  efficacy evaluation  /  back propagation (BP) neural network  /  improved particle swarm optimization (IPSO)  /  index system