摘要
针对常规技术难以量化电网复杂信息的问题,引入深度学习算法,构建出新型的学习系统。通过BP神经网络算法模型能够监测电力设备的运行故障,应用随机矩阵理论模型能够对电力设备相关参数信息建立起逻辑关系联系,以评价一种参数对另一种参数的影响。通过决策树分类算法能够对电力设备智能运行方式的各个数据信息进行分类,可以使用户快速查找数据。试验结果表明,所研究的算法提高了数据分析能力。
Aiming at the problem that it is difficult to quantify the complex information of the power grid in the conventional technology,a deep learning algorithm is introduced to construct a new learning system.Through the BP neural network algorithm model,it is possible to monitor the operation faults of power equipment,and the application of a random matrix theory model can establish a logical relationship between the relevant parameter information of power equipment to evaluate the influence of one parameter on one parameter.Through the decision tree classification algorithm,it is possible to classify various data information of the intelligent operation mode of the power equipment,so that the user can quickly find the data.Experiments show that the algorithm of this study improves the data analysis ability.
作者
虞跃
YU Yue(Qinhuangdao Power Supply Company,State Grid Jibei Electric Power Co.,Ltd.,Qinhuangdao 066000,China)
出处
《自动化与仪表》
2020年第7期20-24,67,共6页
Automation & Instrumentation
关键词
电力市场
深度学习
BP神经网络算法模型
随机矩阵理论模型
决策树分类算法
electricity market
deep learning
BP neural network algorithm model
random matrix theory model
decision tree classification algorithm
