基于智能优化算法的农村供水管网水力参数反演

Inversion of Hydraulic Parameters of Rural Water Supply Network Based on Intelligent Optimization Algorithm

管道的摩阻因数是供水系统设计计算、运行调度优化及故障诊断中的关键参数。为准确确定该参数,提出了一种动态搜索烟花算法(dyn FWA)耦合管网水力计算模型的管段摩阻因数智能反分析方法。将节点水压与摩阻因数的偏导关系作为节点灵敏度,在改进遗传算法中以节点最大灵敏度之和最大为目标,优化布置监测点;基于优化后监测点处的水压监测值,以水压监测值与计算值的最小二乘误差值为目标,采用dyn FWA算法反演各管段的摩阻因数。同时,为验证dyn FWA算法优化反演的性能,对比分析了dyn FWA算法及粒子群算法(PSO)反演摩阻因数的情况。结果表明,在监测点优化前后摩阻因数反演值最大相对误差分别为17.7%、0.7%,证明了监测点选取的必要性和改进遗传算法进行监测点选取的优越性;在监测点水压加入噪声的情况下,基于dyn FWA算法与PSO算法的摩阻因数反演结果最大相对误差分别为9.67%、14.33%,监测点处实际水压值与模拟水压值之间最大相对误差为0.358%、0.655%,证明了相较于PSO算法,dyn FWA算法在参数反演问题中具有更高的准确性。

The friction factor of pipeline is a key parameter in the design calculation,operation scheduling optimization and fault diagnosis of water supply system.In order to determine this parameter accurately,an intelligent back-analysis method of pipe section friction factor based on dynamic search fireworks algorithm(dynFWA)coupled with hydraulic calculation model of pipe network was proposed.The partial derivative relationship between node water pressure and friction factor was taken as the node sensitivity.In the improved genetic algorithm,the maximum sum of node maximum sensitivity was taken as the goal to optimize the layout of monitoring points.Based on the optimized water pressure monitoring value at the monitoring point,the dynFWA algorithm was used to inverse the friction factor of each pipe section with the objective of minimizing the average double error between the water pressure monitoring value and the calculated value.In order to verify the inversion performance of dynFWA algorithm,the inversion of friction factor by dynFWA algorithm and particle swarm optimization(PSO)algorithm were compared.The results show that the maximum relative errors of the inverse value of the friction factor are 17.7%and 0.7%before and after the optimization of the monitoring points,which proves the necessity of the monitoring point selection and the superiority of the improved genetic algorithm for the monitoring point selection.Under the condition that the water pressure at the monitoring node is added to noise,the relative errors of the friction factor inversion results based on the dynFWA algorithm and the PSO algorithm are 9.67%and 14.33%respectively,and the maximum relative errors between the actual water pressure value and the simulated water pressure value at the monitoring point are 0.358%and 0.655%,which proves that the dynFWA algorithm has higher accuracy in the parameter inversion problem compared with the PSO algorithm.