基于改进ACO-BP算法的弹药贮存可靠性评估
|
摘要
针对BP算法易陷入局部最优和收敛速度慢的问题,提出两种改进蚁群优化BP神经网络的可靠性评估算法(自适应蚁群优化BP神经网络评估算法和精英蚁群优化BP神经网络评估算法优化网络的初始配置;实验结果表明:两种智能模型都显著提高了BP网络的精度和稳定性,减少了网络的迭代次数;前一种算法在评估的精度和迭代次数方面优于后一种算法,而后一种算法比前一种算法更稳定。
BP algorithm is easy to fall into the problem of local optimum and slow convergence. Two reliability evaluation algorithms were proposed. They were adaptive ant colony optimization BP neural network evaluation algorithm( AACA-BP) and elite ant colony optimization BP neural network evaluation algorithm( EACO-BP). Two algorithms were used to optimize the initial configuration of the network. The experimental results show that the accuracy and stability of BP network are improved and the number of iterations is reduced with two intelligent algorithms. EACO-BP algorithm is superior to AACA-BP algorithm in evaluation accuracy and iteration times. AACA-BP algorithm is more stable than EACO-BP algorithm.
BP algorithm is easy to fall into the problem of local optimum and slow convergence. Two reliability evaluation algorithms were proposed. They were adaptive ant colony optimization BP neural network evaluation algorithm( AACA-BP) and elite ant colony optimization BP neural network evaluation algorithm( EACO-BP). Two algorithms were used to optimize the initial configuration of the network. The experimental results show that the accuracy and stability of BP network are improved and the number of iterations is reduced with two intelligent algorithms. EACO-BP algorithm is superior to AACA-BP algorithm in evaluation accuracy and iteration times. AACA-BP algorithm is more stable than EACO-BP algorithm.
引文
[1]ZHANG Y J,ZHAO M,ZHANG S.et al.An integrated approach to estimate storage reliability with initial failures based on E-bayesian estimates[J].Reliability Engineering&System Safety,2017,159(3):24-36.
[2]郑波,许和贵,姜志保.一种基于Poisson过程的弹药贮存寿命评估方法[J].兵工学报,2005,26(4):528-530.
[3]WANG Z Q,HU C H,WANG W B,et al.A case study of remaining storage life prediction using stochastic filtering with the influence of condition monitoring[J].Reliability Engineering&Systems Safety,2014,132(132):186-195.
[4]SI X,HU C.H,KONG X.et al.,A residual storage life prediction approach for systems with operation state switches[J].IEEE Transactions on Industrial Electronics,2014,61(11):6304-6315.
[5]龚绍文,赵月琴.导弹电缆工作状态可靠性预计[J].兵器装备工程学报,2018,39(11):36-38.
[6]邹心遥,姚若河.小子样统计理论及IC可靠性评估[J].控制与决策,2008,23(3):241-245.
[7]陈海建,滕克难,李波等.神经网络在导弹贮存可靠性预测中的应用[J].弹箭与制导学报,2010,30(6):78-81.
[8]章恩泽,陈庆伟.不确定可靠性优化问题的多目标粒子群优化算法[J].控制与决策,2015,30(9):1701-1705.
[9]TIAN Z,WONG L,SAFAEI N.A neural network approach for remaining useful life prediction utilizing both failure and suspension histories[J].Mechanical Systems&Signal Processing,2010,24(5):1542-1555.
[10]LOUIT D,PASCUAL R,BANJEVIC D,et al.Conditionbased spares ordering for critical components[J].Mechanical Systems&Signal Processing,2011,25(5):1837-1848.
[11]张光云.基于动力系统理论的一类金融混沌系统的定性分析[J].重庆工商大学学报(自然科学版),2017,34(2):37-40.
[12]GONG H,ZHANG E M,YAO J.BP neural network optimized by PSO algorithm on ammunition storage reliability prediction[C]//2017 Chinese Automation Congress(CAC).Jinan,2017:692-696.
[2]郑波,许和贵,姜志保.一种基于Poisson过程的弹药贮存寿命评估方法[J].兵工学报,2005,26(4):528-530.
[3]WANG Z Q,HU C H,WANG W B,et al.A case study of remaining storage life prediction using stochastic filtering with the influence of condition monitoring[J].Reliability Engineering&Systems Safety,2014,132(132):186-195.
[4]SI X,HU C.H,KONG X.et al.,A residual storage life prediction approach for systems with operation state switches[J].IEEE Transactions on Industrial Electronics,2014,61(11):6304-6315.
[5]龚绍文,赵月琴.导弹电缆工作状态可靠性预计[J].兵器装备工程学报,2018,39(11):36-38.
[6]邹心遥,姚若河.小子样统计理论及IC可靠性评估[J].控制与决策,2008,23(3):241-245.
[7]陈海建,滕克难,李波等.神经网络在导弹贮存可靠性预测中的应用[J].弹箭与制导学报,2010,30(6):78-81.
[8]章恩泽,陈庆伟.不确定可靠性优化问题的多目标粒子群优化算法[J].控制与决策,2015,30(9):1701-1705.
[9]TIAN Z,WONG L,SAFAEI N.A neural network approach for remaining useful life prediction utilizing both failure and suspension histories[J].Mechanical Systems&Signal Processing,2010,24(5):1542-1555.
[10]LOUIT D,PASCUAL R,BANJEVIC D,et al.Conditionbased spares ordering for critical components[J].Mechanical Systems&Signal Processing,2011,25(5):1837-1848.
[11]张光云.基于动力系统理论的一类金融混沌系统的定性分析[J].重庆工商大学学报(自然科学版),2017,34(2):37-40.
[12]GONG H,ZHANG E M,YAO J.BP neural network optimized by PSO algorithm on ammunition storage reliability prediction[C]//2017 Chinese Automation Congress(CAC).Jinan,2017:692-696.