多智能体信息融合(multi-agent information fusion,MAIF)系统主要面向多个智能体之间的信息融合、调节、交流和矛盾处理。研究针对数据高度冲突条件下的D-S证据理论失效问题,提出一种将重构的基本概率分配和信念熵相结合的多智能体系...多智能体信息融合(multi-agent information fusion,MAIF)系统主要面向多个智能体之间的信息融合、调节、交流和矛盾处理。研究针对数据高度冲突条件下的D-S证据理论失效问题,提出一种将重构的基本概率分配和信念熵相结合的多智能体系统冲突数据融合方法。该方法使用重构的基本概率分配和信念熵修正证据的可靠性,获得更合理的证据,使用Dempster组合规则将证据进行融合得到结果,在2个实验中均得到了超过90%的置信度。实验表明了该方法的有效性,提高了MAIF系统辨识过程的精度。展开更多
准确判别燃爆状态是测量燃爆延滞期并计算爆发点参数的关键。针对单一传感器判别效果不佳、多个传感器判别结果相互冲突的问题,利用D-S(Dempster-Shafer)证据理论对冲突证据进行联合判别。首先根据含能材料燃爆特性和爆发点测试原理,设...准确判别燃爆状态是测量燃爆延滞期并计算爆发点参数的关键。针对单一传感器判别效果不佳、多个传感器判别结果相互冲突的问题,利用D-S(Dempster-Shafer)证据理论对冲突证据进行联合判别。首先根据含能材料燃爆特性和爆发点测试原理,设计了基于温度和声音的联合判别装置;从实验数据出发,采用模型拟合提取温度特征值,以及声音信号最大值为声音特征值。其次,根据Sigmoid模型求解出BPA(Basic Probability Assignment)函数,并通过信度熵对可能存在冲突的BPA函数值进行预处理;最终,利用D-S证据理论进行燃爆状态联合判别。实验结果表明,所提方法有效提高了实验装置的鲁棒性和状态判别的置信概率,燃爆判别准确率达到了96.5%,优于温度、声音等单一传感器的判别效果。展开更多
>Transformer faults are quite complicated phenomena and can occur due to a variety of reasons.There have been several methods for transformer fault synthetic diagnosis,but each of them has its own limitations in re...>Transformer faults are quite complicated phenomena and can occur due to a variety of reasons.There have been several methods for transformer fault synthetic diagnosis,but each of them has its own limitations in real fault diagnosis applications.In order to overcome those shortcomings in the existing methods,a new transformer fault diagnosis method based on a wavelet neural network optimized by adaptive genetic algorithm(AGA)and an improved D-S evidence theory fusion technique is proposed in this paper.The proposed method combines the oil chromatogram data and the off-line electrical test data of transformers to carry out fault diagnosis.Based on the fusion mechanism of D-S evidence theory,the comprehensive reliability of evidence is constructed by considering the evidence importance,the outputs of the neural network and the expert experience.The new method increases the objectivity of the basic probability assignment(BPA)and reduces the basic probability assigned for uncertain and unimportant information.The case study results of using the proposed method show that it has a good performance of fault diagnosis for transformers.展开更多
针对在短期负荷功率预测过程中,因负荷功率波动大而导致单一模型存在预测精度低的问题,提出基于时间特征分析的短期负荷功率NST-IRN组合预测模型。首先,深度挖掘负荷功率的时间特性变化,将其分解为趋势成分以及循环分量,构建新型时间序...针对在短期负荷功率预测过程中,因负荷功率波动大而导致单一模型存在预测精度低的问题,提出基于时间特征分析的短期负荷功率NST-IRN组合预测模型。首先,深度挖掘负荷功率的时间特性变化,将其分解为趋势成分以及循环分量,构建新型时间序列(NTS)模型。其次,考虑多时间尺度输入特征与日类型对负荷功率的影响,构建含特征输入结构与深度学习结构的改进残差神经网络(IRN)模型。最后,利用D-S证据理论对NTS与IRN模型的预测结果进行权重融合,以获取最终负荷预测结果。以ISO New England的真实负荷数据进行仿真实验,结果表明所提模型具有较高的预测精度和鲁棒性。展开更多
文摘多智能体信息融合(multi-agent information fusion,MAIF)系统主要面向多个智能体之间的信息融合、调节、交流和矛盾处理。研究针对数据高度冲突条件下的D-S证据理论失效问题,提出一种将重构的基本概率分配和信念熵相结合的多智能体系统冲突数据融合方法。该方法使用重构的基本概率分配和信念熵修正证据的可靠性,获得更合理的证据,使用Dempster组合规则将证据进行融合得到结果,在2个实验中均得到了超过90%的置信度。实验表明了该方法的有效性,提高了MAIF系统辨识过程的精度。
文摘准确判别燃爆状态是测量燃爆延滞期并计算爆发点参数的关键。针对单一传感器判别效果不佳、多个传感器判别结果相互冲突的问题,利用D-S(Dempster-Shafer)证据理论对冲突证据进行联合判别。首先根据含能材料燃爆特性和爆发点测试原理,设计了基于温度和声音的联合判别装置;从实验数据出发,采用模型拟合提取温度特征值,以及声音信号最大值为声音特征值。其次,根据Sigmoid模型求解出BPA(Basic Probability Assignment)函数,并通过信度熵对可能存在冲突的BPA函数值进行预处理;最终,利用D-S证据理论进行燃爆状态联合判别。实验结果表明,所提方法有效提高了实验装置的鲁棒性和状态判别的置信概率,燃爆判别准确率达到了96.5%,优于温度、声音等单一传感器的判别效果。
基金Project Supported by National Natural Science Foundation of China （ 50777069 ）.
文摘>Transformer faults are quite complicated phenomena and can occur due to a variety of reasons.There have been several methods for transformer fault synthetic diagnosis,but each of them has its own limitations in real fault diagnosis applications.In order to overcome those shortcomings in the existing methods,a new transformer fault diagnosis method based on a wavelet neural network optimized by adaptive genetic algorithm(AGA)and an improved D-S evidence theory fusion technique is proposed in this paper.The proposed method combines the oil chromatogram data and the off-line electrical test data of transformers to carry out fault diagnosis.Based on the fusion mechanism of D-S evidence theory,the comprehensive reliability of evidence is constructed by considering the evidence importance,the outputs of the neural network and the expert experience.The new method increases the objectivity of the basic probability assignment(BPA)and reduces the basic probability assigned for uncertain and unimportant information.The case study results of using the proposed method show that it has a good performance of fault diagnosis for transformers.
文摘针对在短期负荷功率预测过程中,因负荷功率波动大而导致单一模型存在预测精度低的问题,提出基于时间特征分析的短期负荷功率NST-IRN组合预测模型。首先,深度挖掘负荷功率的时间特性变化,将其分解为趋势成分以及循环分量,构建新型时间序列(NTS)模型。其次,考虑多时间尺度输入特征与日类型对负荷功率的影响,构建含特征输入结构与深度学习结构的改进残差神经网络(IRN)模型。最后,利用D-S证据理论对NTS与IRN模型的预测结果进行权重融合,以获取最终负荷预测结果。以ISO New England的真实负荷数据进行仿真实验,结果表明所提模型具有较高的预测精度和鲁棒性。
