-
公开(公告)号:US20220320981A1
公开(公告)日:2022-10-06
申请号:US17366275
申请日:2021-07-02
Applicant: Hamilton Sundstrand Corporation
Inventor: Tod Policandriotes , Parag M. Kshirsagar , Suman Dwari , Beata I. Wawrzyniak , Jagadeesh Kumar Tangudu , Sreenivasa R. Voleti
Abstract: Provided are embodiments for a method and a hybrid axial/radial motor. Embodiments can include a central rotor that includes an axial segment, a first radial segment, and a second radial segment, wherein the first radial segment extends axially from a first side of the axial segment and the second radial segment extends axially from a second side of the axial segment, wherein the first side is opposite the second side. Embodiments can also include a stator adapted to receive the first radial segment or the second radial segment of the central rotor.
-
公开(公告)号:US20190332725A1
公开(公告)日:2019-10-31
申请号:US15920949
申请日:2018-04-30
Applicant: Hamilton Sundstrand Corporation
Inventor: Beata I. Wawrzyniak , Vivek Venugopalan , Parag M. Kshirsagar
IPC: G06F17/50
Abstract: An example method of designing an electrical machine includes providing at least one goal and at least one design constraint for a desired electrical machine to a deep neural network that comprises a plurality of nodes representing a plurality of prior electrical machine designs, the plurality of nodes connected by weights, each weight representing a correlation strength between two nodes. A proposed design is generated from the deep neural network for an electrical machine based on the goal(s) and design constraint(s). A plurality of the weights are adjusted based on a reward that rates at least one aspect of the proposed design. The proposed design is modified using the deep neural network after the weight adjustment. The adjusting and modifying are iteratively repeated to generate subsequent iterations of the proposed design, each subsequent iteration based on the reward from a preceding iteration. A system for designing electrical machines is also disclosed.
-