引用本文: | 郑元兵,陈伟根,李 剑,杜 林,"孙才新.基于BIC与SVRM的变压器油中气体预测模型[J].电力自动化设备,2011,31(9): |
| ZHENG Yuanbing,CHEN Weigen,LI Jian,DU Lin,SUN Caixin.Forecasting model based on BIC and SVRM for dissolved gas in transformer oil[J].Electric Power Automation Equipment,2011,31(9): |
|
摘要: |
基于v-支持向量回归机(v-SVRM)算法建立了变压器油中溶解气体变化预测模型,并引入贝叶斯证据框架对预测模型的参数进行了优化选取?同时,结合预测模型的预测正确率及预测模型的简洁度建立了预测模型的评价机制,并利用改进的贝叶斯信息标准(BIC)作为最终的评价函数量化了评价机制?在实例中与灰色理论预测模型进行了比较,结果表明在同为小样本训练数据的情况下,v-SVRM预测模型比灰色模型有更高的预测准确率,且在所提出的评价机制里表现更好? |
关键词: 支持向量机 支持向量回归机 故障检测 预测 电力变压器 贝叶斯信息标准 优化 |
DOI: |
分类号: |
基金项目:国家973计划重点项目(2009CB724506) |
|
Forecasting model based on BIC and SVRM for dissolved gas in transformer oil |
ZHENG Yuanbing, CHEN Weigen, LI Jian, DU Lin, SUN Caixin
|
State Key Laboratory of Power Transmission Equipment & System Security and New Technology,Chongqing University,Chongqing 400030,China
|
Abstract: |
A forecasting model of dissolved gases in transformer oil is established based on v-SVRM(v-Support Vector Regression Machine) algorithm and the Bayesian framework is introduced to optimally select its parameters. An evaluation mechanism combining forecasting accuracy and model simplicity is set and the improved BIC(Bayesian Information Criterion) is taken as the final evaluation function to quantify the evaluation mechanism. The case study shows that,compared with GM(Gray Model),v-SVRM forecasting model has higher forecasting accuracy with the same small-scale samples and better performance in the proposed model evaluation function. |
Key words: support vector machines support vector regression machine fault detection forecasting electric transformers Bayesian information criterion optimization |