To address the challenges of flight control modeling—namely, the large number of parameters involved in assessing the reliability of equivalent models, the complexity of comparison dimensions, and the cumbersome evaluation process—an evaluation scheme combining neural networks and a fuzzy evaluation framework was designed. First, the paper introduces the parameter classification and processing workflow for this task, as well as the operational mechanism of the fuzzy evaluation framework. It then details the structural composition and loss function design of a four-branch heterogeneous neural network. Subsequently, this paper uses a specific type of interceptor as an example to demonstrate a complete evaluation process, including feature dimension adjustment and hyperparameter tuning of the neural network. Finally, we compared the evaluation results of the controlled perturbation model between the conventional evaluation approach and the neural network evaluation approach; the overall reliability rankings and reliability scores of the models evaluated by both approaches showed a high degree of consistency. Comparative experiments revealed that introducing the loss in three stages resulted in a 31.5% improvement in performance compared to introducing the entire loss at once, confirming the necessity of a staged training strategy. Furthermore, it was found that as the number of models to be evaluated increased, the acceleration ratio of the neural network evaluation path compared to the conventional error-handling evaluation path showed an overall upward trend, highlighting its efficiency. This study indicates that this evaluation method has significant potential for broader application.
[1]秦立格.复杂仿真系统可信度评估及其工具研究[D]. 哈尔滨: 哈尔滨工业大学, 2009: 1-63.
[2]李勇君, 吴晓燕, 吴静, 等.复杂仿真系统可信度评估辅助工具设计与实现[J].现代防御技术, 2011, 39(06):191-197
[3]FAVARO L, RYLKO A, QUARANTA G.Building Credible VTOL Flight Models for Handling Quality Certification by Simulation[J].Aerospace (MDPI Publishing), 2025, 12(6):559-559
[4]JAHANGIRI F, SHIRGIR A, MOJTAHEDI A.Credibility assessment of a Lagrangian-based model for long-term simulation of oil spill dynamics: A case study on Sanchi incident[J].Results in Engineering, 2026, 30:109846-109846
[5]SCUOPPO R, CATALANO C, CRASCì F, et al.Credibility Assessment of the Patient-Specific Modeling of the Aneurysmal Ascending Thoracic Aorta: Verification,Validation and Uncertainty Quantification[J].Cardiovascular Engineering and Technology, 2025, 16(6):1-15
[6]NIU Z, WU Y, LAN S, et al.Enhancing trustworthiness in deep learning-based transient stability assessment: A multi-head attention model with dual-level interpretability[J].International Journal of Electrical Power and Energy Systems, 2025, 173:111373-111373
[7]ERS?Z B A, BOSCHé F.Evaluating confidence in geometric matching between 3D point clouds and BIM models by integrating coverage,distance,and distribution metrics[J].Automation in Construction, 2026, 181(PA):106636-106636
[8]高昂, 周国印, 张小超, 等.任务级CGF对手模型可信度评估方法研究[J].系统工程与电子技术, 2026, :1-10
[9]冉培志, 李伟, 鲍然, 等.基于改进模糊综合评判的仿真可信度评估方法[J].系统仿真报, 2020, 32(12):2469-2474
[10]苍宏宇, 谭宗颖.国内外信息检索研究热点分析——基于Z-Score标准化的词频[J].图书馆建设, 2009, (01):93-98
[11]张游, 黄永辉, 李志豪, 等.基于-滤波和互模糊函数的时频差参数估计算法[J].系统工程与电子技术, 2025, 47(05):1395-1403
[12]焦鹏, 唐见兵, 查亚兵.仿真可信度评估中相似度方法的改进及其应用[J].系统仿真学报, 2007, 19(12):2658-2660
[13]ZHANG Q, ZHOU J, GU B, et al.Three-degree-of-freedom motion posture stabilization control of platform based on DTW-LSTM-MATD3 under high and low frequency disturbances of ships[J][J].Journal of Zhejiang University-SCIENCE A, 2026, :1-16
[14]李志特, 孙继祥.基于模糊隶属度函数的船舶驾驶智能避碰决策方法[J].舰船科学技术, 2026, 48(04):190-195
[15]邵云虹, 邓彩霞, 贺鹏.利用充分光滑的形函数构造小波[J].哈尔滨理工大学学报, 2019, 24(02):127-134
[16]李晓菲, 缪建明, 沈丙振.基于改进方差最大化的主客观组合赋权方法[J].火力与指挥控制, 2022, 47(03):124-128
[17]周启航.深度ReLU全连接与二维卷积网络的表达能力及逼近速率研究[D]. 大连: 大连理工大学, 2025: 1-62.
[18]张宗宇, 徐军, 陈士超.基于策略的卷积神经网络的数字识别效果研究[J].兰州文理学院学报自然科学版, 2025, 39(03):43-47
[19]IOFFE S, SZEGEDY C.Batch normalization: accelerating deep network training by reducing internal covariate shift[C]// Proceedings of the 32nd International Conference on Machine Learning. Lille: PMLR, 2015: 448-456.
[20]KIRANYAZ S, INCE T, GABBOUJ M.Real-time patient-specific ECG classification by 1-D convolutional neural networks[J].IEEE Transactions on Biomedical Engineering, 2016, 63(3):664-675
[21]ZERVEAS G, JAYARAMAN S, PATEL D, et al.A transformer-based framework for multivariate time series representation learning[C]// Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining (KDD ' 21). New York: ACM, 2021: 2114-2124.
[22]VASWANI A, SHAZEER N, PARMAR N, et al.Attention is all you need[C]// Advances in Neural Information Processing Systems 30. Long Beach: NIPS, 2017: 5998-6008.
[23]余雄辉.基于环形扩张卷积和辛格卷积的运动想象分类算法研究[D]. 保定: 河北大学, 2024: 1-75.
[24]RAVANELLI M, BENGIO Y.Speaker recognition from raw waveform with SincNet[C]// 2018 IEEE Spo-ken Language Technology Workshop (SLT). Athens: IEEE, 2018: 1021-1028.
[25]GUO C, PLEISS G, SUN Y, et al.On calibration of modern neural networks[C]// International conference on machine learning. PMLR, 2017: 1321-1330.
[26]WANG X, CHEN Y, ZHU W.A survey on curriculum learning[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(9):4555-4576
[27]TAKADA Y, MOCHIDA R, NAKAJIMA M, et al.Stochastic dual coordinate ascent for learning sign constrained linear predictors[J].IEICE Transactions on Information and Systems, 2024, E107-D(12):1493-1503
[28]杨勇, 王昊.基于自监督学习的试剂识别方法, 系统及计算机程序产品: CN202411851847.0[P]. CN119942173A [2026-04-05].
[29]KOU G, LU Y, PENG Y, et al.Evaluation of classification algorithms using MCDM and rank correlation[J].International Journal of Information Technology & Decision Making, 2012, 11(1):197-225
[30]ABOUNAIMA M C, MAZOURI F Z E, LAMRINI L, et al.The Pearson correlation coefficient applied to compare multi-criteria methods: Case the ranking problematic[C]// 2020 1st International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET). Meknes: IEEE, 2020: 1-6. DOI: 10.1109/IRASET48871.2020.9092242.
CJA