Disassembly sequence planning is an important step of mechanical maintenance. This article presents an integrated study about the generation and optimizing algorithm of the disassembly sequence. Mechanical products ar...Disassembly sequence planning is an important step of mechanical maintenance. This article presents an integrated study about the generation and optimizing algorithm of the disassembly sequence. Mechanical products are divided into two categories of components and connectors. The article uses component-joint graph to represent assembly constraints, including the incidence constraints are represented by incidence matrix and the interference constraints are represented by interference constraints. The inspiring factor and pheromone matrix are calculated according to assembly constraints. Then the ant generates its own disassembly sequences one by one and updates the inspiring factor and pheromone matrix. After all iterations, the best disassembly sequence planning of components and connectors are given. Finally, an application instance of the disassembly sequence of the jack is presented to illustrate the validity of this method.展开更多
目前,大部分将知识图谱引入推荐系统的方法只是将已知的表层知识图谱实体进行引入,没有对图谱的内在关系进行预测和挖掘,因此无法利用知识图谱中的隐藏关系。针对上述问题,提出联合学习推荐模型E-TUP(enhance towards understanding of ...目前,大部分将知识图谱引入推荐系统的方法只是将已知的表层知识图谱实体进行引入,没有对图谱的内在关系进行预测和挖掘,因此无法利用知识图谱中的隐藏关系。针对上述问题,提出联合学习推荐模型E-TUP(enhance towards understanding of user preference),使用E-CP(enhance canonical polyadic)进行知识图谱补全并将完整信息进行传递。利用储存空间负采样方法,将优质负例三元组进行存储,并随训练过程进行更新,以提高知识图谱补全中负例三元组的质量。链接预测实验结果显示,储存空间方法使E-TUP模型链接预测准确率对比现有模型最高提升10.3%。在MovieLens-1m和DBbook2014数据集上进行推荐实验,在多个评价指标上取得最佳结果,对比现有模型实现最高5.5%的提升,表明E-TUP可以有效利用知识图谱中的隐藏关系提高模型推荐准确率。基于汽车维修数据进行推荐实验,结果表明E-TUP可以有效推荐相关知识。展开更多
针对大多数跨度模型将文本分割成跨度序列时,产生大量非实体跨度,导致了数据不平衡和计算复杂度高等问题,提出了基于跨度和边界探测的实体关系联合抽取模型(joint extraction model for entity relationships based on span and boundar...针对大多数跨度模型将文本分割成跨度序列时,产生大量非实体跨度,导致了数据不平衡和计算复杂度高等问题,提出了基于跨度和边界探测的实体关系联合抽取模型(joint extraction model for entity relationships based on span and boundary detection,SBDM)。SBDM首先使用训练Transformer的双向编码器表征量(bidirectional encoder representations from Transformer,BERT)模型将文本转化为词向量,并融合了通过图卷积获取的句法依赖信息以形成文本的特征表示;接着通过局部信息和句子上下文信息去探测实体边界并进行标记,以减少非实体跨度;然后将实体边界标记形成的跨度序列进行实体识别;最后将局部上下文信息融合到1个跨度实体对中并使用sigmoid函数进行关系分类。实验表明,SBDM在SciERC(multi-task identification of entities,relations,and coreference for scientific knowledge graph construction)数据集、CoNLL04(the 2004 conference on natural language learning)数据集上的关系分类指标S F1分别达到52.86%、74.47%,取得了较好效果。SBDM用于关系分类任务中,能促进跨度分类方法在关系抽取上的研究。展开更多
为实现板梁桥铰接缝损伤的定量定位识别,提出了一种基于递归奇异能量指标的损伤识别方法:首先将待测桥梁各相邻梁体的竖向冲击振动响应进行交叉递归分析并得到无阈值交叉递归矩阵,其次对各递归矩阵进行奇异值分解以进一步提取损伤特征,...为实现板梁桥铰接缝损伤的定量定位识别,提出了一种基于递归奇异能量指标的损伤识别方法:首先将待测桥梁各相邻梁体的竖向冲击振动响应进行交叉递归分析并得到无阈值交叉递归矩阵,其次对各递归矩阵进行奇异值分解以进一步提取损伤特征,最后对奇异值求取能量(递归奇异能量指标(recurrence singular energy index,RSEI)),进一步建立了基于该指标的铰接缝损伤识别方法,并对其适用性进行了分析。结果表明:RSEI指标对板梁桥铰接缝损伤较为敏感,所提方法仅在板梁桥跨中布置一排传感器即可实现铰接缝平均损伤程度的定量识别,并可实现损伤铰缝的定位,识别效果良好;铰接缝损伤位置、损伤个数及噪声对识别结果的影响极小,冲击位置会对识别结果造成一定影响,但识别效果在可接受的范围之内;应用RSEI指标开展板梁桥铰接缝损伤识别时,建议将冲击位置设在边梁跨中,可避免冲击位置对识别结果造成的影响,取得更加理想的识别效果。展开更多
知识图谱嵌入技术已在推荐系统领域引起广泛关注,将结构化知识图谱中的信息融入到推荐模型中,可以提高推荐的个性化程度。然而,因为初始数据的不准确性会导致推荐结果不正确,现存的知识图谱推荐模型中仍存在误差传播问题。针对这个问题...知识图谱嵌入技术已在推荐系统领域引起广泛关注,将结构化知识图谱中的信息融入到推荐模型中,可以提高推荐的个性化程度。然而,因为初始数据的不准确性会导致推荐结果不正确,现存的知识图谱推荐模型中仍存在误差传播问题。针对这个问题,该文提出了RR-KGE模型,由知识图谱嵌入模块和推荐算法模块组成;其中聚焦于知识图谱嵌入框架,将规则嵌入和知识图谱嵌入进行联合学习,通过规则给予模型更多的约束条件,以减少误差传播;并结合此框架将推荐算法ALS(Alternating Least Squares)和RNN(Recurrent Neural Network)相融合来获得更加精确的推荐结果;最后将RR-KGE与不同基准模型进行比较,在两个数据集上多项指标均优于对比模型,证明了推荐方法的有效性。展开更多
In this paper, a new kind of simple-encoding irregular systematic LDPC codes suitable for one-relay coded cooperation is designed, where the proposed joint iterative decoding is effectively performed in the destinatio...In this paper, a new kind of simple-encoding irregular systematic LDPC codes suitable for one-relay coded cooperation is designed, where the proposed joint iterative decoding is effectively performed in the destination which is in accordance with the corresponding joint Tanner graph characterizing two different component LDPC codes used by the source and relay in ideal and non-ideal relay cooperations. The theoretical analysis and simulations show that the coded cooperation scheme obviously outperforms the coded non-cooperation one under the same code rate and decoding complex. The significant performance improvement can be virtually credited to the additional mutual exchange of the extrinsic information resulted by the LDPC code employed by the source and its counterpart used by the relay in both ideal and non-ideal cooperations.展开更多
文摘Disassembly sequence planning is an important step of mechanical maintenance. This article presents an integrated study about the generation and optimizing algorithm of the disassembly sequence. Mechanical products are divided into two categories of components and connectors. The article uses component-joint graph to represent assembly constraints, including the incidence constraints are represented by incidence matrix and the interference constraints are represented by interference constraints. The inspiring factor and pheromone matrix are calculated according to assembly constraints. Then the ant generates its own disassembly sequences one by one and updates the inspiring factor and pheromone matrix. After all iterations, the best disassembly sequence planning of components and connectors are given. Finally, an application instance of the disassembly sequence of the jack is presented to illustrate the validity of this method.
文摘目前,大部分将知识图谱引入推荐系统的方法只是将已知的表层知识图谱实体进行引入,没有对图谱的内在关系进行预测和挖掘,因此无法利用知识图谱中的隐藏关系。针对上述问题,提出联合学习推荐模型E-TUP(enhance towards understanding of user preference),使用E-CP(enhance canonical polyadic)进行知识图谱补全并将完整信息进行传递。利用储存空间负采样方法,将优质负例三元组进行存储,并随训练过程进行更新,以提高知识图谱补全中负例三元组的质量。链接预测实验结果显示,储存空间方法使E-TUP模型链接预测准确率对比现有模型最高提升10.3%。在MovieLens-1m和DBbook2014数据集上进行推荐实验,在多个评价指标上取得最佳结果,对比现有模型实现最高5.5%的提升,表明E-TUP可以有效利用知识图谱中的隐藏关系提高模型推荐准确率。基于汽车维修数据进行推荐实验,结果表明E-TUP可以有效推荐相关知识。
文摘针对大多数跨度模型将文本分割成跨度序列时,产生大量非实体跨度,导致了数据不平衡和计算复杂度高等问题,提出了基于跨度和边界探测的实体关系联合抽取模型(joint extraction model for entity relationships based on span and boundary detection,SBDM)。SBDM首先使用训练Transformer的双向编码器表征量(bidirectional encoder representations from Transformer,BERT)模型将文本转化为词向量,并融合了通过图卷积获取的句法依赖信息以形成文本的特征表示;接着通过局部信息和句子上下文信息去探测实体边界并进行标记,以减少非实体跨度;然后将实体边界标记形成的跨度序列进行实体识别;最后将局部上下文信息融合到1个跨度实体对中并使用sigmoid函数进行关系分类。实验表明,SBDM在SciERC(multi-task identification of entities,relations,and coreference for scientific knowledge graph construction)数据集、CoNLL04(the 2004 conference on natural language learning)数据集上的关系分类指标S F1分别达到52.86%、74.47%,取得了较好效果。SBDM用于关系分类任务中,能促进跨度分类方法在关系抽取上的研究。
文摘为实现板梁桥铰接缝损伤的定量定位识别,提出了一种基于递归奇异能量指标的损伤识别方法:首先将待测桥梁各相邻梁体的竖向冲击振动响应进行交叉递归分析并得到无阈值交叉递归矩阵,其次对各递归矩阵进行奇异值分解以进一步提取损伤特征,最后对奇异值求取能量(递归奇异能量指标(recurrence singular energy index,RSEI)),进一步建立了基于该指标的铰接缝损伤识别方法,并对其适用性进行了分析。结果表明:RSEI指标对板梁桥铰接缝损伤较为敏感,所提方法仅在板梁桥跨中布置一排传感器即可实现铰接缝平均损伤程度的定量识别,并可实现损伤铰缝的定位,识别效果良好;铰接缝损伤位置、损伤个数及噪声对识别结果的影响极小,冲击位置会对识别结果造成一定影响,但识别效果在可接受的范围之内;应用RSEI指标开展板梁桥铰接缝损伤识别时,建议将冲击位置设在边梁跨中,可避免冲击位置对识别结果造成的影响,取得更加理想的识别效果。
文摘知识图谱嵌入技术已在推荐系统领域引起广泛关注,将结构化知识图谱中的信息融入到推荐模型中,可以提高推荐的个性化程度。然而,因为初始数据的不准确性会导致推荐结果不正确,现存的知识图谱推荐模型中仍存在误差传播问题。针对这个问题,该文提出了RR-KGE模型,由知识图谱嵌入模块和推荐算法模块组成;其中聚焦于知识图谱嵌入框架,将规则嵌入和知识图谱嵌入进行联合学习,通过规则给予模型更多的约束条件,以减少误差传播;并结合此框架将推荐算法ALS(Alternating Least Squares)和RNN(Recurrent Neural Network)相融合来获得更加精确的推荐结果;最后将RR-KGE与不同基准模型进行比较,在两个数据集上多项指标均优于对比模型,证明了推荐方法的有效性。
基金Supported by the Open Research Fund of National Moblie Communications Research Laboratory of Southeast Uni-versity (No. W200704)
文摘In this paper, a new kind of simple-encoding irregular systematic LDPC codes suitable for one-relay coded cooperation is designed, where the proposed joint iterative decoding is effectively performed in the destination which is in accordance with the corresponding joint Tanner graph characterizing two different component LDPC codes used by the source and relay in ideal and non-ideal relay cooperations. The theoretical analysis and simulations show that the coded cooperation scheme obviously outperforms the coded non-cooperation one under the same code rate and decoding complex. The significant performance improvement can be virtually credited to the additional mutual exchange of the extrinsic information resulted by the LDPC code employed by the source and its counterpart used by the relay in both ideal and non-ideal cooperations.