【摘要】：針對現(xiàn)有城市系統(tǒng)作戰(zhàn)能力評估方法較少的問題,利用反向傳播(back propagation,BP)神經(jīng)網(wǎng)絡在能力評估方面所具有的自適應、自學習、強容錯性和泛化映射等優(yōu)勢,建立了評估指標體系并給出了指標的隸屬函數(shù)。通過模擬退火遺傳算法(simulated annealing and genetic algorithm,SAGA)優(yōu)化BP神經(jīng)網(wǎng)絡的連接權重和閥值,弱化了指標評價中的人為因素,提高了評價結果的準確性、客觀性和權威性,有效解決了傳統(tǒng)遺傳算法和BP神經(jīng)網(wǎng)絡易陷入局部極小值、收斂速度慢和抗干擾能力差等問題。仿真實例驗證了該方法對城市系統(tǒng)作戰(zhàn)能力評估的可行性和有效性。
[Abstract]:In order to solve the problem that there are few methods for evaluating the operational capability of urban systems, the advantages of adaptive, self-learning, strong fault-tolerance and generalization mapping of back propagations-BP neural network are used in this paper. The evaluation index system is established and the membership function of the index is given. The connection weight and threshold value of BP neural network are optimized by simulated annealing genetic algorithm (simulated annealing and genetic algorithm saga), which weakens the human factors in index evaluation and improves the accuracy, objectivity and authority of evaluation results. The traditional genetic algorithm and BP neural network are easy to fall into local minima, slow convergence speed and poor anti-interference ability. A simulation example is given to verify the feasibility and effectiveness of this method in evaluating the operational capability of urban systems.
【作者單位】： 火箭軍工程大學初級指揮學院;
【基金】：國家自然科學基金(61372167,61379104)資助課題
【分類號】：TP18
，

本文編號：2191142