基于ACPSO算法的矿井通风网络解算研究  

Study on ACPSO algorithm for mine ventilation network

作　　者：张兴国 周玉 ZHANG Xingguo;ZHOU Yu(College of Business Administration,Liaoning Technical University,Huluflao 125100,China)

机构地区：[1]辽宁工程技术大学工商管理学院,辽宁葫芦岛125100

出　　处：《辽宁工程技术大学学报（社会科学版）》2018年第4期305-311,共7页Journal of Liaoning Technical University(Social Science Edition)

摘　　要：针对传统矿井通风网络解算算法的不足,提出一种新的自适应混沌粒子群优化算法。以矿井通风网络总功率最小为目标建立矿井通风网络的非线性优化数学模型,借助罚函数方法将节点风量平衡和回路风压平衡等式约束条件转化为目标函数中惩罚项;采用自适应粒子群优化算法对目标函数进行优化,当优化陷入局部最优时,借助混沌搜索引导粒子重新进行搜索。应用自适应混沌粒子群优化算法对一个通风网络模型进行风量优化求解,并与BP、PSO算法优化结果进行对比,结果表明:基于自适应混沌粒子群优化算法获得的风量优化方案具有较小的总能耗,且满足通风网络各用风点风量需求,符合实际应用需要。Aimed at the defect of solution method for traditional mine ventilation network, a new adaptive chaotic particle swarm optimization algorithm is proposed. Taking the minimum total power of the mine ventilation network as the objective, a nonlinear mathematical method for the structure of the mine ventilation network is established. By means of penalty function method, the constraints of node air volume balance and loop air pressure balance equation are transformed into penalty terms in the objective function. The adaptive particle swarm optimization algorithm is used to optimize the objective function. When the optimization falls into the local optimum, the particles are searched again by means of chaotic search. The adaptive chaotic particle swarm optimization（PSO） algorithm is used to solve the airflow optimization problem of a simple ventilation network model, and the results are compared with those of BP and PSO. Experimental results show that： the optimization scheme based on the adaptive chaotic particle swarm optimization algorithm has less total energy consumption, and meets the wind demand of each point in the ventilation network, which meets the need of practical application.

关 键 词：自适应混沌粒子群优化算法 矿井通风网络 惩罚函数 非线性优化 

分 类 号：TD725[矿业工程—矿井通风与安全]