基于CABC-BP模型的供热管网泄漏诊断研究

Leakage diagnosis model of heating pipe network based on CABC optimization of BP neural network

针对人工蜂群算法(artificial bee colony algorithm,ABC)在供热管网泄漏检测中收敛速度慢,且易陷入局部最优解的问题,利用混沌算法遍历性、规则性的特点,采用Logistic混沌映射对人工蜂群算法初始蜜源的选择策略和侦查蜂的搜索策略进行优化改进,提出了一种基于混沌蜂群算法(chaotic artificial bee colony algorithm,CABC)优化BP神经网络的供热管网泄漏诊断模型。通过对4个标准测试函数进行仿真验证,并与ABC算法相比,验证了其可行性。将CABC算法用于供热管网泄漏故障诊断中,采用该算法优化BP神经网络的权值和阈值,利用BP神经网络自学习的特点确定泄漏的具体管段以及泄漏点具体位置。实验结果显示,相对于ABC-BP模型和传统BP模型,CABC-BP模型对供热管网泄漏诊断精度显著提高,一级网络诊断准确率为98.33%,二级网络诊断准确率为95.83%,诊断误差均在5%以内。

Aiming at the problem that the artificial bee colony algorithm has a slow convergence speed and is easy to fall into the local optimal solution in the leakage detection of the heating pipe network,using the characteristics of ergodicity and regularity of the chaotic algorithm,the Logistic chaotic map is used to analyze the initial nectar source of the artificial bee colony algorithm.The selection strategy and the search strategy of the scout bee are optimized and improved,and a leak diagnosis model of the heating pipe network based on the chaotic artificial bee colony algorithm(CABC)optimized BP neural network is proposed.The feasibitity is verified by simulating the four standard test function and comparing them with the ABC algorithm.The CABC algorithm is used in the leakage fault diagnosis of the heating pipe network,and the weights and thresholds of the BP neural network are optimized by this algorithm,and the specific pipe section and the specific location of the leakage point are determined by using the self-learning characteristics of the BP neural network.The experimental results show that compared with ABC-BP model and traditional BP model,CABC-BP model significantly improves the leakage diagnosis accuracy of the heating pipe network.The diagnostic accuracy of the first-level network is 98.33%,the second-level network is 95.83%,and the diagnosis errors are within 5%.