利索-全球专利检索

  1. 登录
  2. 注册
发明公开
CN110794360A 一种基于机器学习预测智能电能表故障的方法及系统 审中-公开

一种基于机器学习预测智能电能表故障的方法及系统
摘要：
本发明公开了一种基于机器学习预测智能电能表故障的方法及系统，属于机器学习技术领域。本发明方法包括：确定故障智能电能表的故障类型；删除重复数据和与故障智能电能表故障无关的数据，补全故障智能电能表故障退运数据缺失值，获取预测数据；确定与故障有关的特征数据；获取智能电能表故障预测模型；获取智能电能表与故障有关的特征数据；根据智能电能表故障预测模型，对智能电能表故障进行预测，确定智能电能表预测故障类型。本发明结合机器学习和神经网络的方法对智能电表故障数据进行分析，可以有效的预测出智能电表的故障类型。
摘要（英）：

The invention discloses a method and system for predicting a fault of an intelligent electric energy meter based on machine learning, and belongs to the technical field of machine learning. The methodcomprises the steps of determining a fault type of the intelligent electric energy meter with the fault; deleting repeated data and data irrelevant to the fault of the intelligent electric energy meter with the fault, complementing a fault refund data missing value of the intelligent electric energy meter with the fault, and obtaining prediction data; determining feature data related to the fault; obtaining an intelligent electric energy meter fault prediction model; obtaining feature data related to the fault of the intelligent electric energy meter; and predicting the fault of the intelligent electric energy meter according to the intelligent electric energy meter fault prediction model, and determining a predicted fault type of the intelligent electric energy meter. According to the method and the system, the fault data of the intelligent electric energy meter is analyzed by combining machine learning and a neural network method, so that the fault type of the intelligent electric energy meter can be effectively predicted.

0/0