论文部分内容阅读
针对钢铁企业副产煤气系统产消量频繁波动,不平衡现象比较严重,供需之间的平衡程度对钢铁企业的生产成本、能源消耗情况影响较大,并且钢铁企业中工序、设备繁多,每道工序都涉及多种能源介质的问题,利用HP滤波、支持向量机分类(SVC)、最小二乘支持向量机(LSSVM)和Elman神经网络的特性建立了SVC-HP-ENNLSSVM模型,并根据用能设备的能源利用特点和预测结果对副产煤气进行优化调度。模型应用表明:所建预测模型对煤气系统的预测平均相对误差小于4%,满足工业生产需要。根据预测结果进行的优化调度解决了煤气系统的不平衡问题,应用于钢铁企业典型工况,主工序可降低10%左右能耗,应用其自备电厂(一年按照330天计算),可多产蒸汽约104 148 t,节能约9 998 208 kg标煤。
Steel products by-product gas production for frequent fluctuations in the system, the imbalance is more serious, the balance between supply and demand of steel production costs, energy consumption greater impact, and steel companies in the process, equipment, each channel The process involves a variety of energy media problems. SVC-HP-ENNLSSVM model is established by using the characteristics of HP filter, support vector machine classification (SVC), least square support vector machine (LSSVM) and Elman neural network, Equipment utilization characteristics of the energy and forecast results of the optimal scheduling of by-product gas. The application of the model shows that the predicted average relative error of the predicted model to the gas system is less than 4%, which meets the needs of industrial production. The optimal scheduling based on the prediction results solves the problem of the imbalance of the gas system and is applied to the typical operating conditions of the iron and steel enterprises. The main process can reduce the energy consumption by about 10%. By using its own power plant (330 days a year) Steam production of about 104 148 t, saving about 99,998 208 kg of standard coal.