钢铁企业氧气系统预测及优化调度模型研究

发布时间：2018-05-03 09:03

本文选题：钢铁企业 + 氧气系统　；参考：《天津理工大学》2017年硕士论文

【摘要】：作为占国民经济总量的26%的重要基础性产业,钢铁产业在提高我国经济实力和综合国力的同时,也带来了能源的巨大消耗,因此,节能降耗成了钢铁企业目前亟待解决的问题。氧气作为钢铁生产中必不可少自产能源介质,其制氧电耗约占钢铁企业总耗电的20%。因此,对氧气进行优化调度是钢铁企业节能降耗的一个重要途径。本课题选取钢铁企业氧气系统作为研究对象,以钢铁企业节能降耗为目的,对其进行进行优化调度建模研究,主要的研究成果如下:(1)氧气消耗具有强耦合性、高度的非线性以及扰动变化激烈且幅度大等特点,很难对其建立精确机理模型。基于此,建立了一种基于灰色模型和遗传算法优化的BP神经网络的耗氧量组合预测模型。通过实例验证,该预测方法对钢铁企业炼钢和炼铁工序耗氧量的预测拟合度较高,具有一定的实用价值。(2)由于氧气系统的氧气产耗变化的无规律,使得氧气管网压力呈现无规律变化,造成检测值与实际值之间存在一定的误差。基于此,提出了一种基于变分模态分解VMD-样本熵SE-最小二乘支持向量机LS-SVM的氧气管网压力预测方法。通过实例仿真,证明该方法预测精度较高。(3)选取氧气系统的放散量最小、经济效益最大两个指标作为目标函数,以设备能力、工艺流程等作为约束,采用混合整数线性规划模型建模,对氧气系统进行优化。最后,总结本文研究成果,并就下一步的研究方向进行了展望。
[Abstract]:As an important basic industry accounting for 26% of the total national economy, iron and steel industry not only improves China's economic strength and comprehensive national strength, but also brings huge consumption of energy. Therefore, energy saving and consumption reduction has become the urgent problem for iron and steel enterprises to solve. Oxygen is an essential energy medium in iron and steel production, and its oxygen consumption accounts for about 20 percent of the total electricity consumption in iron and steel enterprises. Therefore, the optimal scheduling of oxygen is an important way for iron and steel enterprises to save energy and reduce consumption. In this paper, the oxygen system of iron and steel enterprises is chosen as the research object, and the purpose of energy saving and consumption reduction in iron and steel enterprises is studied. The main research results are as follows: 1) oxygen consumption has strong coupling. It is difficult to establish an accurate mechanism model for the high nonlinearity and the intense and large amplitude of the disturbance. Based on this, a BP neural network based on grey model and genetic algorithm is established to predict oxygen consumption. It is proved by an example that the forecasting method has a high fitting degree for oxygen consumption prediction in steelmaking and ironmaking processes in iron and steel enterprises, and has certain practical value. (2) because of the irregular change of oxygen production consumption in oxygen system, The pressure of oxygen trachea network changes irregularly, resulting in a certain error between the detection value and the actual value. Based on VMD-sample entropy SE-least-squares support vector machine (LS-SVM), a pressure prediction method for oxygen pipe network is proposed. The simulation results show that this method has high prediction accuracy.) the oxygen system is chosen as the minimum emission quantity, the maximum economic benefit is taken as the objective function, and the equipment capacity and technological process are taken as the constraints. The mixed integer linear programming model is used to optimize the oxygen system. Finally, the research results of this paper are summarized, and the future research direction is prospected.
【学位授予单位】：天津理工大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：TQ083;TP18

【相似文献】