论文部分内容阅读
在钢铁企业能源系统的低压氮气使用过程中,由于氮气使用单元分散且在管网中的位置不同,对管网压力的影响会出现短时间的延迟.鉴于此种情况,本文提出了一种基于影响因素输入延迟的多核最小二乘支持向量机对管网压力进行建模预测.该方法首先对低压氮气压力影响因素的延迟时间进行确定,提出一种基于因果关系的影响因素延迟时间计算方法,同时根据不同的影响因素和对应的延迟时间分别构造训练样本,进而建立基于最小二乘支持向量机的预测模型.通过对某钢铁企业现场低压氮气管网压力的两种不同情况,即正常工况和超限工况分别进行建模仿真验证,说明了本文提出的方法在压力预测上具有较高的精度.
In the process of using low-pressure nitrogen in the energy system of iron and steel enterprises, due to the scattered nitrogen use units and the different locations in the pipe network, the pressure on the pipe network will be delayed for a short period of time.In view of this situation, This paper first establishes the prediction of the pipeline pressure by using the multi-core least squares support vector machine with input delay.The method first determines the delay time of the influencing factors of the low pressure nitrogen pressure and proposes a method of calculating the delay time of the influencing factors based on the causal relationship, At the same time, the training samples are respectively constructed according to different influencing factors and the corresponding delay time, and then a prediction model based on least square support vector machine is established.By two different situations of low pressure nitrogen pipe network pressure in a steel enterprise, namely normal working condition And overrun conditions were simulated respectively, which shows that the proposed method has higher accuracy in pressure prediction.