摘要
【目的】研究目前传统BP(back propagation)模型对热网泄漏故障诊断过程中存在故障识别率低、收敛速度慢以及易陷入局部极值等问题。【方法】提出了一种基于遗传蚁群(genetic algorithm-ant colony optimization,GA-ACO)算法优化的BP模型。利用GA算法的交叉变异算子改进了信息素初始值,通过ACO算法提高了模型的迭代速度以及最优解的寻找,优化了BP模型的初始权值和阈值,并通过系统仿真软件将此模型应用到热网泄漏故障诊断中。【结果】结果表明:相比于传统BP模型和GA-BP模型,GA-ACO-BP模型具有更快的收敛速度,预测值更加接近期望值且误差更小,有效提高了热网泄漏故障的预测精度,能够实现对泄漏故障快速、准确的诊断和定位。
【Purposes】This work has been done in order to overcome the problems of low fault recognition rate,slow convergence speed,and easy falling into local extremum in the current tradition⁃al back propagation(BP)model for heat network leakage fault diagnosis.【Methods】An optimized BP model based on genetic algorithm-ant colony optimization(GA-ACO)algorithm is proposed.The initial value of the pheromone is improved by using the cross-variance operator of the GA algo⁃rithm,the iteration speed of the model and the search for the optimal solution are advanced by using the ACO algorithm,the initial weights and thresholds of the BP model are optimized,and the model is applied to the diagnosis of heat network leakage faults through the system simulation software.【Results】The results show that compared with traditional BP and GA-BP model,the GA-ACO-BP model possesses faster convergence speed and the predicted value is closer to the expected value with less error,which effectively improves the prediction accuracy of heat network leakage faults and en⁃ables fast and accurate diagnosis and localization of leakage faults.
作者
郝江勇
段鹏飞
杜永峰
冯梦丹
陈京磊
HAO Jiangyong;DUAN Pengfei;DU Yongfeng;FENG Mengdan;CHEN Jinglei(College of Civil Engineering,Taiyuan University of Technology,Taiyuan 030024,China)
出处
《太原理工大学学报》
CAS
北大核心
2024年第2期338-347,共10页
Journal of Taiyuan University of Technology
基金
山西省重点研发计划资助项目(201903D321043)。
关键词
热网泄漏
BP神经网络
遗传算法
蚁群算法
故障诊断
heat network leakage
BP neural network
genetic algorithm
ant colony optimization
fault diagnosis