基于DBN神经网络的能源电力企业发展评价方法

Development Evaluation Method of Energy and Power Enterprises Based on DBN Neural Network

随着全球能源互联网建设的发展,能源电力企业发展规模不断扩大,世界一流能源电力企业的对标和发展评价就显得十分重要。为解决国内能源电力企业在世界一流能源企业对标和发展评价中存在的关联信息挖掘不足,评价准确率低的问题,提出了一种基于DBN神经网络的能源电力企业发展评价方法。通过在线文本转换获取世界一流能源企业的年报数据,然后,对能源电力企业发展数据进行近邻传播聚类,并建立能源电力企业发展评价关键指标体系;采用改进粒子群算法调整能源电力企业发展评价指标的权重;采用DBN神经网络对能源电力企业发展进行评价和评价结果分析;通过对国内某能源电力企业发展评价的实例分析,其结果验证了所提方法的有效性。

With the global energy Internet construction and the continuous expansion of the development scale of energy and power enterprises, the benchmarking and development evaluation of world-class energy and power enterprises is very important. In order to solve the problems of insufficient association information mining and low evaluation accuracy of domestic energy and power enterprises in benchmarking and development evaluation of world-class energy enterprises, this paper proposes a DBN neural network-based development evaluation method for energy and power enterprises. The annual report data of world-class energy enterprises are obtained through online text conversion. The development data of energy and power enterprises are clustered by neighbor propagation, and the key index system of development evaluation of energy and power enterprises is established. The improved particle swarm optimization algorithm is used to adjust the weight of the development evaluation index. DBN neural network is used to evaluate the development of energy and power enterprises, and analyze the evaluation results. The effectiveness of the proposed method is verified by an example of a domestic energy and power enterprise development evaluation.