Double weighted combat data quality evaluation method based on CVF optimized FAHP.

During multi-agent combat simulation exercises, accurately assessing the quality of collected combat data is a critical step. Addressing the current issue of low accuracy in combat data quality evaluation, which fails to effectively support simulation exercises, this paper proposes a Double-Weighted FAHP optimized by CVF (comparative value function) method for assessing combat data quality. First, a three-tiered evaluation framework for combat data quality indicators is established, with threshold values determined for each indicator. The weights obtained from the FAHP method are optimized using the Satisfaction Consistency Approach to derive the first-tier weights. Subsequently, the CVF is constructed to obtain the second-tier weights. The double-weighted evaluation theory combines these two tiers of weights to produce the final assessment. Analysis of the experimental results indicates that the proposed method reduces the mean squared error to 5.35 when compared to results obtained using FAHP, interval intuitionistic fuzzy methods, and artificial neural networks, bringing it closer to actual standard values. This method provides a more accurate evaluation of the quality of multi-agent combat data, offering robust data support for future combat simulation exercises and military drills.