针对智能分析系统在页岩气领域的空白问题,基于知识图谱技术进行构建研究,在现有实体识别的基础上引入注意力机制和伪训练样本,提出了一种基于多神经网络与注意力机制的页岩气实体识别方法。首先将字映射为具有上下文语义的密集向量序列...针对智能分析系统在页岩气领域的空白问题,基于知识图谱技术进行构建研究,在现有实体识别的基础上引入注意力机制和伪训练样本,提出了一种基于多神经网络与注意力机制的页岩气实体识别方法。首先将字映射为具有上下文语义的密集向量序列,并采用卷积神经网络(convolutional neural networks,CNN)过滤局部语境;然后通过双向长短期记忆(bidirectional long short term memory,BiLSTM)网络对上下文隐藏状态进行捕获;最后利用注意力机制来解决标注不一致的问题,并结合条件随机场(conditional random field,CRF)进一步约束,实现高精度实体分类。在SGAS数据集上进行的实验与测试表明,所提方法的精确度、召回率、F度量值可分别达到99.32%、99.57%、99.44%,得到首个页岩气高精度实体识别模型,验证了所提方法的高效性。展开更多
Existing power grid fault diagnosis methods relyon manual experience to design diagnosis models, lack theability to extract fault knowledge, and are difficult to adaptto complex and changeable engineering sites. Consi...Existing power grid fault diagnosis methods relyon manual experience to design diagnosis models, lack theability to extract fault knowledge, and are difficult to adaptto complex and changeable engineering sites. Considering thissituation, this paper proposes a power grid fault diagnosismethod based on a deep pyramid convolutional neural networkfor the alarm information set. This approach uses the deepfeature extraction ability of the network to extract fault featureknowledge from alarm information texts and achieve end-to-endfault classification and fault device identification. First, a deeppyramid convolutional neural network model for extracting theoverall characteristics of fault events is constructed to identifyfault types. Second, a deep pyramidal convolutional neuralnetwork model for alarm information text is constructed, thetext description characteristics associated with alarm informationtexts are extracted, the key information corresponding to faultsin the alarm information set is identified, and suspicious faultydevices are selected. Then, a fault device identification strategythat integrates fault-type and time sequence priorities is proposedto identify faulty devices. Finally, the actual fault cases and thefault cases generated by the simulation are studied, and theresults verify the effectiveness and practicability of the methodpresented in this paper.展开更多
文摘针对智能分析系统在页岩气领域的空白问题,基于知识图谱技术进行构建研究,在现有实体识别的基础上引入注意力机制和伪训练样本,提出了一种基于多神经网络与注意力机制的页岩气实体识别方法。首先将字映射为具有上下文语义的密集向量序列,并采用卷积神经网络(convolutional neural networks,CNN)过滤局部语境;然后通过双向长短期记忆(bidirectional long short term memory,BiLSTM)网络对上下文隐藏状态进行捕获;最后利用注意力机制来解决标注不一致的问题,并结合条件随机场(conditional random field,CRF)进一步约束,实现高精度实体分类。在SGAS数据集上进行的实验与测试表明,所提方法的精确度、召回率、F度量值可分别达到99.32%、99.57%、99.44%,得到首个页岩气高精度实体识别模型,验证了所提方法的高效性。
基金the National Natural Science Foundation of China(51877079).
文摘Existing power grid fault diagnosis methods relyon manual experience to design diagnosis models, lack theability to extract fault knowledge, and are difficult to adaptto complex and changeable engineering sites. Considering thissituation, this paper proposes a power grid fault diagnosismethod based on a deep pyramid convolutional neural networkfor the alarm information set. This approach uses the deepfeature extraction ability of the network to extract fault featureknowledge from alarm information texts and achieve end-to-endfault classification and fault device identification. First, a deeppyramid convolutional neural network model for extracting theoverall characteristics of fault events is constructed to identifyfault types. Second, a deep pyramidal convolutional neuralnetwork model for alarm information text is constructed, thetext description characteristics associated with alarm informationtexts are extracted, the key information corresponding to faultsin the alarm information set is identified, and suspicious faultydevices are selected. Then, a fault device identification strategythat integrates fault-type and time sequence priorities is proposedto identify faulty devices. Finally, the actual fault cases and thefault cases generated by the simulation are studied, and theresults verify the effectiveness and practicability of the methodpresented in this paper.
