1.Liaoning Technical University;2.BusinessBigData TECH. CO., LTD
Study on dynamic optimization of material flow direction of open-pit mine based on spatiotemporal sequence inversion ;Prediction method and application research of coal and gas outburst based on big data；Spatial-temporal evolution mechanism and stability calculation method of downdip soft rock slope in opencast coal mine
针对郊狼优化（Coyote Optimization Algorithm，COA）算法优化性能弱及多样性低等问题，提出了一种基于反时限衰减算子的混沌郊狼优化算法（COA with Inverse time chaotic，ICCOA）.首先，在个体迭代更新过程中加入反时限衰减权重因子，使得全局搜索与局部开发能力保持平衡的同时提高算法的搜索速度；其次，加入基于Tent混沌映射的混沌干扰机制，将种群中部分较差个体经过映射产生新个体，进而增大种群多样性.为了验证ICCOA 算法的优化能力，分别在10、30和 100 维度下进行函数优化测试，并与5种优化算法进行比较，其实验结果表明 ICCOA 算法具有良好的优化性能.最后，将ICCOA算法应用于BP神经网络参数优化，提出新的神经网络模型（BP neural network with ICCOA，简称ICCOABP），并与标准神经网络、基于遗传算法的BP神经网络参数优化方法一同应用于机器学习的分类任务，进行性能比较，实验结果表明ICCOABP算法具有高效性.
A chaotic coyote optimization algorithm based on inverse time-decay operator(ICCOA) is proposed to solve the coyote optimization algorithm(COA),such as the poor performance and low diversity. Firstly, the inverse time decay weight factor is added in the process of individual iterative updating, so as to maintain the balance between global search and local development ability and improve the search speed of the algorithm. Secondly, add the chaotic interference mechanism based on Tent chaotic map,some poor individuals in the population were mapped to produce new individuals, thus increasing the diversity of the population. In order to verify the optimization ability of ICCOA algorithm, functional optimization tests were carried out in 10, 30 and 100 dimensions respectively, and compared with five optimization algorithms. The experimental results show that ICCOA algorithm has good optimization performance.Finally, the ICCOA algorithm is applied to the parameter optimization of BP neural network, and a new neural network model (ICCOABP) is proposed. Compared with the standard neural network and the BP neural network parameter optimization method based on genetic algorithm, the experimental results show that the ICCOABP algorithm is efficient.