基于灰狼算法优化支持向量回归的110 kV电力变压器全寿命周期成本预测模型

A Study on the Forecast Model of the Life Cycle Cost of the 110 kV Power Transformer Based on the GWO-SVR Algorithm

电力变压器是电力企业的核心设备,充分预测电力变压器全寿命成本对于电力企业经济效益改善具有重要意义。基于电力设备全寿命周期成本标准框架,对83台110 kV电力变压器的历年数据进行处理,构造了含有变压器中标价格、变压器容量、空载损耗、负载损耗、硅钢材料成本、铜线成本、大修年故障频率、小修年故障频率及其对应的全寿命周期成本数据集。基于该数据集构建了灰狼算法(grey wolf algorithm,GWO)优化支持向量回归(support vector regression,SVR)的电力变压器全寿命周期成本预测模型,并对该模型进行了算例仿真,结果显示其在测试集中的平均相对误差仅为5.20%。此电力变压器模型为预测和评估电力变压器全寿命周期成本提供了一个新的方法。

The power transformer is the essential equipment for power enterprises.The forecast of the life cycle cost(LCC)of the power transformer is significant in improving economic benefits of power enterprises.Based on the standard LCC framework of power equipment,historic data from 83110kV power transformers has been processed,to establish a data set including their bid-winning prices,capacities,open circuit losses,load losses,costs of silicon steel materials,costs of copper wires,annual failure frequencies of overhauls,annual failure frequencies of daily repairs and their corresponding LCCs.With the data set,the forecast model of the LCC of the power transformer based on the GWO-SVR algorithm has been established.Multiple example simulations have been implemented and the result shows that the MAPE of the test data set is only 5.20%.Therefore,this model provides a new way of forecasting and evaluating the LCC of the power transformer.