对于小电流接地系统的单相接地故障选线,传统方法普遍采用基于一维信号的选线模型,存在选线准确率低、抗噪性弱等问题。为此提出一种改进的变分模态分解及Conv Ne Xt的小电流接地系统单相接地故障选线方法。首先引入蚁狮算法优化变分模...对于小电流接地系统的单相接地故障选线,传统方法普遍采用基于一维信号的选线模型,存在选线准确率低、抗噪性弱等问题。为此提出一种改进的变分模态分解及Conv Ne Xt的小电流接地系统单相接地故障选线方法。首先引入蚁狮算法优化变分模态分解算法,通过蚁狮算法自动寻优选取合适的分解次数和惩罚因子,计算分解得到的各分量的分布熵,将其中的噪声分量筛选去除,将其余有效分量进行线性重构得到降噪后的零序电流信号;其次,将经过降噪处理后的一维零序电流信号经格拉姆角场转换为二维图像,制备故障选线数据集;然后,引入预训练的ConvNeXt模型,根据该研究数据模型特征,在其已有权重基础上对模型参数进行对应微调,从而提高模型精度并形成最终的选线模型;最后引入绝对平均误差、均方根误差作为评价指标验证所提降噪算法有效性。分别在加入噪声与否的前提下,将所提模型与3种选线模型相比较。实验结果表明该模型的准确率最高、抗噪性方面更好,其中该研究算法准确率达到了99.82%并且在不同噪声条件下都能维持91%以上的准确率,高于其他选线模型,克服了传统故障选线方法准确率低、抗噪性差的问题。展开更多
The control of gas extraction in coal mines relies on the effectiveness of gas extraction.The main method of gas extraction is to drive drill pipes into the coal seam through a drilling rig and use technologies such a...The control of gas extraction in coal mines relies on the effectiveness of gas extraction.The main method of gas extraction is to drive drill pipes into the coal seam through a drilling rig and use technologies such as hydraulic fracturing to pre-extract gas in the drill holes.Therefore,the real-time detection of the drill pipe status is closely related to the effectiveness of gas extraction.To achieve fast and accurate identification of drill pipes,we propose FSSYOLO,which is a lightweight drill pipe detection method based on YOLOv8n-obb.This method first introduces the FasterBlock module into the C2f module of YOLOv8n-obb to reduce the number of model parameters and decrease the computational cost of the model and redundant feature maps.Next,the SimAM attention mechanism is added to the backbone network to enhance the weight of important features in the feature map and improve the model’s feature extraction capability.In addition,using shared convolution to optimize the detection head,not only lightens the detection head but also enhances its ability to learn features of different scales,improving the model’s generalization ability.Finally,the FSS-YOLO algorithm is validated on the self-built dataset.The results show that compared with the original algorithm,FSS-YOLO achieves improvements of 5.1%in mAP50 and 11.5%in Recall,reduces the number of parameters by 45.8%,and achieves an inference speed of 27.8 ms/frame on Jetson Orin NX.Additionally,the visual detection results for different scenarios demonstrate that the improved YOLOv8n-obb algorithm has promising application prospects.展开更多
基于生成对抗网络中的循环一致性原则,提出了一个基于循环一致性损失的知识图谱嵌入模型。该模型首先使用ConvE模型利用头实体和关系构造的“图片”对尾实体进行预测,再利用尾实体和关系构造的“逆图片”对头实体进行预测。同时根据循...基于生成对抗网络中的循环一致性原则,提出了一个基于循环一致性损失的知识图谱嵌入模型。该模型首先使用ConvE模型利用头实体和关系构造的“图片”对尾实体进行预测,再利用尾实体和关系构造的“逆图片”对头实体进行预测。同时根据循环一致性原理,构造了ConvE模型的一个新的损失函数,解决了网络的可逆性。在WN18、FB15k以及YAGO3-10三个数据集上设计实验,证明了模型有效地缩短了头实体和原头实体的语义空间距离。Based on the cyclic consistency principle in generative adversarial networks, a knowledge graph embedding model based on cyclic consistency loss is proposed. Firstly, the ConvE model is used to predict the tail entity by using the “picture” constructed by the head entity and the relationship, and then the “inverse picture” constructed by the tail entity and the relationship is used to predict the head entity. According to the principle of cyclic consistency, a new loss function of ConvE model is constructed to solve the reversibility of the network. Experiments are designed on WN18, FB15k and YAGO3-10 data sets, and it is proved that the model can effectively shorten the semantic space distance between the header entity and the original header entity.展开更多
The indirect use of language is a common,widespread phenomenon in daily linguistic communication,with an aim to keep a harmonious interpersonal relationship.Though indirectness manifests itself in many ways,this paper...The indirect use of language is a common,widespread phenomenon in daily linguistic communication,with an aim to keep a harmonious interpersonal relationship.Though indirectness manifests itself in many ways,this paper is to discuss the four different forms of indirectness in people's daily communications with typical examples found in both Chinese and English:politeness,indirect speech acts,conversational implicature and figures of speech.展开更多
Though numerical wave models have been applied widely to significant wave height prediction,they consume massive computing memory and their accuracy needs to be further improved.In this paper,a two-dimensional(2D)sign...Though numerical wave models have been applied widely to significant wave height prediction,they consume massive computing memory and their accuracy needs to be further improved.In this paper,a two-dimensional(2D)significant wave height(SWH)prediction model is established for the South and East China Seas.The proposed model is trained by Wave Watch III(WW3)reanalysis data based on a convolutional neural network,the bidirectional long short-term memory and the attention mechanism(CNNBiLSTM-Attention).It adopts the convolutional neural network to extract spatial features of original wave height to reduce the redundant information input into the BiLSTM network.Meanwhile,the BiLSTM model is applied to fully extract the features of the associated information of time series data.Besides,the attention mechanism is used to assign probability weight to the output information of the BiLSTM layer units,and finally,a training model is constructed.Up to 24-h prediction experiments are conducted under normal and extreme conditions,respectively.Under the normal wave condition,for 3-,6-,12-and 24-h forecasting,the mean values of the correlation coefficients on the test set are 0.996,0.991,0.980,and 0.945,respectively.The corresponding mean values of the root mean square errors are measured at 0.063 m,0.105 m,0.172 m,and 0.281 m,respectively.Under the typhoon-forced extreme condition,the model based on CNN-BiLSTM-Attention is trained by typhooninduced SWH extracted from the WW3 reanalysis data.For 3-,6-,12-and 24-h forecasting,the mean values of correlation coefficients on the test set are respectively 0.993,0.983,0.958,and 0.921,and the averaged root mean square errors are 0.159 m,0.257 m,0.437 m,and 0.555 m,respectively.The model performs better than that trained by all the WW3 reanalysis data.The result suggests that the proposed algorithm can be applied to the 2D wave forecast with higher accuracy and efficiency.展开更多
文摘对于小电流接地系统的单相接地故障选线,传统方法普遍采用基于一维信号的选线模型,存在选线准确率低、抗噪性弱等问题。为此提出一种改进的变分模态分解及Conv Ne Xt的小电流接地系统单相接地故障选线方法。首先引入蚁狮算法优化变分模态分解算法,通过蚁狮算法自动寻优选取合适的分解次数和惩罚因子,计算分解得到的各分量的分布熵,将其中的噪声分量筛选去除,将其余有效分量进行线性重构得到降噪后的零序电流信号;其次,将经过降噪处理后的一维零序电流信号经格拉姆角场转换为二维图像,制备故障选线数据集;然后,引入预训练的ConvNeXt模型,根据该研究数据模型特征,在其已有权重基础上对模型参数进行对应微调,从而提高模型精度并形成最终的选线模型;最后引入绝对平均误差、均方根误差作为评价指标验证所提降噪算法有效性。分别在加入噪声与否的前提下,将所提模型与3种选线模型相比较。实验结果表明该模型的准确率最高、抗噪性方面更好,其中该研究算法准确率达到了99.82%并且在不同噪声条件下都能维持91%以上的准确率,高于其他选线模型,克服了传统故障选线方法准确率低、抗噪性差的问题。
文摘The control of gas extraction in coal mines relies on the effectiveness of gas extraction.The main method of gas extraction is to drive drill pipes into the coal seam through a drilling rig and use technologies such as hydraulic fracturing to pre-extract gas in the drill holes.Therefore,the real-time detection of the drill pipe status is closely related to the effectiveness of gas extraction.To achieve fast and accurate identification of drill pipes,we propose FSSYOLO,which is a lightweight drill pipe detection method based on YOLOv8n-obb.This method first introduces the FasterBlock module into the C2f module of YOLOv8n-obb to reduce the number of model parameters and decrease the computational cost of the model and redundant feature maps.Next,the SimAM attention mechanism is added to the backbone network to enhance the weight of important features in the feature map and improve the model’s feature extraction capability.In addition,using shared convolution to optimize the detection head,not only lightens the detection head but also enhances its ability to learn features of different scales,improving the model’s generalization ability.Finally,the FSS-YOLO algorithm is validated on the self-built dataset.The results show that compared with the original algorithm,FSS-YOLO achieves improvements of 5.1%in mAP50 and 11.5%in Recall,reduces the number of parameters by 45.8%,and achieves an inference speed of 27.8 ms/frame on Jetson Orin NX.Additionally,the visual detection results for different scenarios demonstrate that the improved YOLOv8n-obb algorithm has promising application prospects.
文摘基于生成对抗网络中的循环一致性原则,提出了一个基于循环一致性损失的知识图谱嵌入模型。该模型首先使用ConvE模型利用头实体和关系构造的“图片”对尾实体进行预测,再利用尾实体和关系构造的“逆图片”对头实体进行预测。同时根据循环一致性原理,构造了ConvE模型的一个新的损失函数,解决了网络的可逆性。在WN18、FB15k以及YAGO3-10三个数据集上设计实验,证明了模型有效地缩短了头实体和原头实体的语义空间距离。Based on the cyclic consistency principle in generative adversarial networks, a knowledge graph embedding model based on cyclic consistency loss is proposed. Firstly, the ConvE model is used to predict the tail entity by using the “picture” constructed by the head entity and the relationship, and then the “inverse picture” constructed by the tail entity and the relationship is used to predict the head entity. According to the principle of cyclic consistency, a new loss function of ConvE model is constructed to solve the reversibility of the network. Experiments are designed on WN18, FB15k and YAGO3-10 data sets, and it is proved that the model can effectively shorten the semantic space distance between the header entity and the original header entity.
文摘The indirect use of language is a common,widespread phenomenon in daily linguistic communication,with an aim to keep a harmonious interpersonal relationship.Though indirectness manifests itself in many ways,this paper is to discuss the four different forms of indirectness in people's daily communications with typical examples found in both Chinese and English:politeness,indirect speech acts,conversational implicature and figures of speech.
基金This study is supported by the project supported by the Southern Marine Science and Engineering Guangdong Laboratory(Zhuhai)(SML2020SP007)the National Natural Science Foundation of China(Nos.61772280 and 62072249).
文摘Though numerical wave models have been applied widely to significant wave height prediction,they consume massive computing memory and their accuracy needs to be further improved.In this paper,a two-dimensional(2D)significant wave height(SWH)prediction model is established for the South and East China Seas.The proposed model is trained by Wave Watch III(WW3)reanalysis data based on a convolutional neural network,the bidirectional long short-term memory and the attention mechanism(CNNBiLSTM-Attention).It adopts the convolutional neural network to extract spatial features of original wave height to reduce the redundant information input into the BiLSTM network.Meanwhile,the BiLSTM model is applied to fully extract the features of the associated information of time series data.Besides,the attention mechanism is used to assign probability weight to the output information of the BiLSTM layer units,and finally,a training model is constructed.Up to 24-h prediction experiments are conducted under normal and extreme conditions,respectively.Under the normal wave condition,for 3-,6-,12-and 24-h forecasting,the mean values of the correlation coefficients on the test set are 0.996,0.991,0.980,and 0.945,respectively.The corresponding mean values of the root mean square errors are measured at 0.063 m,0.105 m,0.172 m,and 0.281 m,respectively.Under the typhoon-forced extreme condition,the model based on CNN-BiLSTM-Attention is trained by typhooninduced SWH extracted from the WW3 reanalysis data.For 3-,6-,12-and 24-h forecasting,the mean values of correlation coefficients on the test set are respectively 0.993,0.983,0.958,and 0.921,and the averaged root mean square errors are 0.159 m,0.257 m,0.437 m,and 0.555 m,respectively.The model performs better than that trained by all the WW3 reanalysis data.The result suggests that the proposed algorithm can be applied to the 2D wave forecast with higher accuracy and efficiency.
