基于融合GMM与SVM的船载非侵入式负荷识别方法

为保障安全的船载用电环境,实现合理的用电配置与管理,在船载电力布局中引入非侵入式电力负荷监测。提出了一种融合高斯混合模型(GMM)与支持向量机(SVM)的电器类型识别算法。该方法利用暂态事件检测所提取的有效负荷特征,建立具有较好统计分布能力的GMM模型和具有较好泛化能力的SVM模型。对两种算法的概率分布进行融合生成最终识别结果。实验结果表明,相对单独应用SVM模型,本文所用方法在准确率和稳定性方面均有一定程度的提升,且实现复杂度低,具有良好的实用价值。

Shipborne Non-Intrusive Load Identification Method Based on Hybrid GMM/SVM

In order to ensure a safe shipboard electricity environment and realize reasonable electricity allocation and management,non-invasive power load monitoring is introduced into shipboard electricity distribution.An electrical type recognition algorithm based on Gaussian mixture model(GMM)and support vector machine(SVM)is proposed.This method utilizes the effective load features extracted from transient event detection to build GMM model with good statistical distribution ability and SVM model with good generalization ability.Finally,the probability distributions of the two algorithms are fused to generate the final recognition results.The experimental results show that the accuracy and stability of the method in this paper are improved to some extent,and the implementation complexity is low,which has good practical value.