基于ANFIS的目标毁伤等级预测模型

Battle Damage Level Prediction Model Based on ANFIS

分析了神经网络和模糊推理系统的优缺点，研究了自适应神经模糊推理系统（ANFIS）结构模型及后向传播和递归最小二乘算法相结合的混合算法．在分析了目标毁伤等级主要影响因素的基础上，构建了目标毁伤等级预测ANFIS模型，利用毁伤试验样本数据训练该模型，得到了与实际一致的目标毁伤等级，并将预测结果与基于BP神经网络的预测结果进行了仿真对比分析．仿真结果表明，该目标毁伤等级预测模型能够准确地预测出目标的毁伤等级，并且其预测精度较BP神经网络方法高，为目标毁伤等级预测提供了一种有效的方法．

The advantage and disadvantage of neural network and fuzzy inference system are ana- lyzed. Adaptive neural fuzzy inference system （ANFIS） architecture and the hybrid-learning algo- rithm by applying back-propagation and least mean squares procedure are studied. ANFIS model for battle damage level prediction is established based on the analysis of the main influence factors of battle damage level. The prediction of battle damage level being consistent with the factual damage level is achieved by training the proposed ANFIS model using damage test data. Simula- tion comparing analysis for battle damage level prediction results are conducted using the pro- posed method and BP neutral network respectively. Simulation results demonstrate that the pro- posed method can predict battle damage level correctly and the precision is higher than that of BP neutral network, which provide an effective method for battle damage level prediction.