专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO2017131953A1 DESIGN OPTIMIZATION FOR A WIND TURBINE TOWER 审中-公开
标题翻译：风力机塔的设计优化
公开(公告)号：WO2017131953A1
公开(公告)日：2017-08-03
申请号：PCT/US2017/012935
申请日：2017-01-11
申请人： SIEMENS CORPORATION
发明人： ARISOY, Erhan , BRANDSTETTER, Veronika , CAI, Bin , MIRABELLA, Lucia , MUSUVATHY, Suraj Ravi , PARLAK, Ayse , SRIVASTAVA, Sanjeev , TANG, Tsz Ling Elaine
IPC分类号： G06F17/50 , E04H12/00 , H02K7/18
CPC分类号： G06F17/5018 , E04H12/00 , F03D13/20 , F05B2260/84 , F05B2270/331 , F05B2270/334 , G06F2217/16 , Y02E10/728
摘要： The structure of a wind turbine tower is optimized (22) based on cost. Following rules, the optimization (22) is constrained (22A) based on physical effect of the design. An initial design of the structure is updated (22C) in the optimization (22) and each update is checked (22A, 26A) for constraint violation and cost. The constraint violation and cost evaluation is determined from three-dimensional modeling (26C) of the structure.
摘要翻译：根据成本优化风力涡轮机塔架的结构（22）。遵循规则，优化（22）基于设计的物理效应被约束（22A）。在优化（22）中更新结构的初始设计（22C），并检查每个更新（22A，26A）的约束违规和成本。约束违规和成本评估由结构的三维建模（26C）确定。

2. 发明申请

WO2020046273A1 FAST APPROXIMATE PREDICTION OF MATERIAL PROPERTIES OF LATTICE STRUCTURES 审中-公开
公开(公告)号：WO2020046273A1
公开(公告)日：2020-03-05
申请号：PCT/US2018/048254
申请日：2018-08-28
申请人： SIEMENS AKTIENGESELLSCHAFT , SIEMENS CORPORATION
发明人： MUSUVATHY, Suraj Ravi , MIRABELLA, Lucia , TANG, Tsz Ling Elaine , ARISOY, Erhan
IPC分类号： G06F17/50 , G06N3/10
摘要： A computer-implemented method includes training a prediction model to learn a mapping from a plurality of training feature vectors to a plurality of training sets of material properties. A plurality of component feature vectors are constructed to represent a plurality of component lattices. Together, the plurality of component lattices form a new lattice, and each component feature vector of the plurality of component feature vectors represents a respective component lattice of the plurality of component lattices. Using the prediction model, a respective component set of material properties is predicted for each component feature vector of the plurality of component feature vectors.

3. 发明申请

WO2020046290A1 FUNCTIONAL TOLERANCING TO ENABLE EFFECTIVE DESIGN AND MANUFACTURING PROCESS PLANNING OF ADDITIVELY MANUFACTURED OBJECTS 审中-公开
公开(公告)号：WO2020046290A1
公开(公告)日：2020-03-05
申请号：PCT/US2018/048514
申请日：2018-08-29
申请人： SIEMENS AKTIENGESELLSCHAFT , SIEMENS CORPORATION
发明人： MUSUVATHY, Suraj Ravi , ARISOY, Erhan , BURHOP, Mark R. , KUMAR, Pranav Srinivas
IPC分类号： G06F17/50 , B33Y50/00
摘要： Systems, methods, and computer-readable media are disclosed for specifying and evaluating functional tolerances for additively manufactured parts. The method includes creating, using a processor, a design for a part. The method further includes specifying, using the processor, one or more functional tolerances for mechanical properties associated with the part. The method additionally includes simulating, using the processor, operation of the part. The method further includes verifying, using the processor, that the design meets design goals associated with the one or more functional tolerance in response to the simulation.

4. 发明申请

WO2019103778A1 MISSING LABEL CLASSIFICATION AND ANOMALY DETECTION FOR SPARSELY POPULATED MANUFACTURING KNOWLEDGE GRAPHS 审中-公开
公开(公告)号：WO2019103778A1
公开(公告)日：2019-05-31
申请号：PCT/US2018/049159
申请日：2018-08-31
申请人： SIEMENS AKTIENGESELLSCHAFT , SIEMENS CORPORATION
发明人： REN, Guannan , SRIVASTAVA, Sanjeev , ARISOY, Erhan
IPC分类号： G06N5/02 , G06N5/00
CPC分类号： G06N5/022 , G06F16/215 , G06N5/003
摘要： Systems, methods, and computer-readable media are described for identifying missing or mislabeled information in a manufacturing knowledge graph. Example embodiments address the technical challenge of sparsity of information in the manufacturing domain by using a collection of prior stored manufacturing knowledge graphs to learn latent representations present within the stored graphs through localized traversals of the stored graphs using a graph traversal technique such as a random walk traversal. The latent representations of the stored manufacturing knowledge graphs correspond to an encoding of the stored manufacturing knowledge graphs as a collection of encoded manufacturing knowledge graphs, which are compared to an encoded new manufacturing knowledge graph to identify a stored manufacturing knowledge graph that is most structurally similar to the new manufacturing knowledge graph. This most similar manufacturing knowledge graph can then be used to identify missing or mislabeled information in the new manufacturing knowledge graph.

5. 发明申请

WO2016118682A1 OPTIMIZED PARTITIONING OF SOLID 3D MODELS FOR ADDITIVE MANUFACTURING 审中-公开
标题翻译：用于添加剂制造的固体3D模型的优化分区
公开(公告)号：WO2016118682A1
公开(公告)日：2016-07-28
申请号：PCT/US2016/014208
申请日：2016-01-21
申请人： SIEMENS CORPORATION
发明人： ARISOY, Erhan , DALLORO, Livio , MIRABELLA, Lucia , MUSUVATHY, Suraj Ravi , SRIVASTAVA, Sanjeev
IPC分类号： B29C67/00 , G06F17/50
CPC分类号： G06F17/5086 , B33Y50/00
摘要： A method of partitioning a model to facilitate printing of the model on a 3D printer includes identifying partition sensitive locations on the model and creating a binary tree with a root note representative of the model. An iterative partitioning process is applied to divide the model into objects by selecting a node of the binary tree without any children nodes, identifying a portion of the model corresponding to the node, and determining candidate cutting planes on the portion of the model based on the partition sensitive locations. During the process, analytic hierarchical processing (AHP) is applied to select an optimal cutting plane from the candidate cutting planes based on partitioning criteria. The optimal cutting plane is used to segment the portion of the model into sub-portions, and two children nodes representative of these subportions are created on the node of the binary tree.
摘要翻译：划分模型以便于在3D打印机上打印模型的方法包括识别模型上的分区敏感位置并创建具有代表该模型的根音符的二叉树。应用迭代分割过程，通过选择没有任何子节点的二叉树节点，识别对应于节点的模型的一部分，以及基于模型的部分确定候选切割平面来将模型划分为对象分区敏感位置。在此过程中，应用分层分层处理（AHP），根据划分标准从候选切割平面中选择最佳切割平面。最佳切割平面用于将模型的部分分割成子部分，并且在二叉树的节点上创建代表这些子部分的两个子节点。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式