本文针对热电厂负荷变化的非平稳性,在分析传统预报方法的局限性基础上,提出了BP 网络结合知识库进行在线预报的新方法。正常工况时,BP 网络的预报精度是令人满意的;而工况剧变时,由知识库系统对 BP 网络的预报值进行修正。实验表明,其预报精度优于传统方法。 In this paper, based on the analysis of the limitations of traditional forecasting methods, a new method of on-line forecasting based on BP network combined with knowledge base is proposed. In normal working condition, the forecasting accuracy of BP network is satisfactory. When the working condition changes drastically, the forecast value of BP network is corrected by the knowledge base system. Experiments show that the prediction accuracy is better than the traditional method.