基于复合BP神经网络的天然气工况监测系统研究Research on Working Condition Monitoring System of Natural Gas Based on Composite BP Neural Network
沈国良,苏祥伟,谭汉,邵迪
SHEN Guoliang,SU Xiangwei,TAN Han,SHAO Di
摘要(Abstract):
天然气站场无人化建设规划中,对于供天然气发电机组的电厂站,由于机组负荷大,工况变化复杂,建立有效的工况分析和预警机制一直是管网调度的难题。因此,应用Levenberg-Marquardt法和共轭双极法各自训练2个独立的BP神经网络,分别用于整体计算和小流量区修正,以此通过复合网络的形式建立天然气电厂站输配调节的流调模型,在此基础上通过比对相同工况下现场反馈流量和模型计算流量来实现工况监测和预警的目的。
In the planning of unattended operation of the natural gas station, it is a difficult problem to set up an effective working condition analysis and early warning mechanism for the power station of natural gas generating set due to the heavy load of the unit and the complex change of the working condition. In this paper,Levenberg-Marquardt method and conjugate bipolar method are used to train two independent BP neural networks, which are respectively used for global calculation and small flow area correction, and then a flow regulation model for natural gas power station transmission and distribution regulation is established by means of the composite network. On this basis, early warning and the monitoring of the working conditions can be realized by comparing the field feedback flow rate with the model calculation flow rate under the same working condition.
关键词(KeyWords):
神经网络;数据挖掘;流调模型;工况监测
neural networks;data mining;regulation model;working condition monitoring
基金项目(Foundation): 浙江浙能天然气运行有限公司2017年科技项目(ZNKJ-2017-057)
作者(Author):
沈国良,苏祥伟,谭汉,邵迪
SHEN Guoliang,SU Xiangwei,TAN Han,SHAO Di
DOI: 10.19585/j.zjdl.201903020
参考文献(References):
- [1]张甫仁,徐湃,曾小燕.燃气管网系统仿真的理论分析与应用[J].哈尔滨工业大学学报,2009,41(7):193-198.
- [2]李长俊,曾自强.气体管网系统仿真[J].油气储运,1997,16(2):21-25.
- [3]郑建国,陈国群,艾慕阳,等.大型天然气管网动态仿真研究与实现[J].计算机仿真,2012,29(7):354-357.
- [4]郑建国,宋飞,陈国群,等.大型天然气管道仿真软件RealPipe-Gas研发[J].油气储运,2011,30(9):659-662.
- [5]马江平,李帆,管延文.城市高压燃气管网动态模拟计算[J].管道技术与设备,2006(6):8-9.
- [6]王瑜琦,于恩禄.天然气管网的瞬变流动数值模拟[J].中国新技术新产品,2009(12):9-10.
- [7]付卫东,袁修干,梅志光,等.管路系统通过调节阀控制气体流动的动态数学模型建立[C]//中国航空学会人体工程、航医、救生专业分会学术年会,1998.
- [8]裘哲勇.燃气输配的数学模型[J].数学的实践与认识,2004,34(12):1-7.
- [9]黄燕平,吴长春,陈潜,等.基于不确定性用气量的输气管网供气可靠度计算方法[J].天然气工业,2018,38(8):126-133.
- [10]杨昭,刘燕,苗志彬,等.人工神经网络在天然气负荷预测中的应用[J].煤气与热力,2003,23(6):331-332.
- [11]周伟国,刘晓婧,王海.燃气管网仿真技术的发展状况[J].世界科技研究与发展,2013,35(1):99-100.
- [12]尚星宇,何永君,王瑞,等.基于数据拟合的汽轮机调节阀流量特性优化[J].热力发电,2017,46(3):121-125.
- [13]杨毅,周志斌,李长俊,等.天然气管输调节控制仿真模型[J].天然气工业,2008,28(10):98-100.
- [14]孙倩.基于LM-BP神经网络的推荐算法的研究与应用[D].北京:北京交通大学,2016.
- [15]周建华.共轭梯度法在BP网络中的应用[J].计算机工程与应用,1993(3):16-18.
- [16]许少华,李玉龙,刘志刚.一种基于最优分段函数逼近的过程神经网络训练算法[J].计算机与数字工程,2014(6):919-923.