Rosenberger Technologies Co., Ltd.

Rosenberger Technologies LLC

Soochow University

Xu Wang

Jing Sun

Jun Wang

Weiguo Huang

Zhongkui Zhu

Yongzhong Li

Juanjuan Shi

Tao Jiang

Dong Wang

Changqing Shen

Xingxing Jiang

Aiwen Zhang

Fan Li

Zhonghao Zou

Dongmiao Song

Dele Wang

Guifu Du

Jun Zhao

Yongjun Shen

Qun Chen

Shuangjie Liu

Ke Zhou

Zaigang Chen

Jing Xie

Xiaofeng Shang

The present invention provides a dynamic joint distribution alignment network-based bearing fault diagnosis method under variable working conditions, including acquiring bearing vibration data under different working conditions to obtain a source domain sample and a target domain sample; establishing a deep convolutional neural network model with dynamic joint distribution alignment; feeding both the source domain sample and the target domain sample into the deep convolutional neural network model with initialized parameters, and extracting, by a feature extractor, high-level features of the source domain sample and the target domain sample; calculating a marginal distribution distance and a conditional distribution distance; obtaining a joint distribution distance according to the marginal distribution distance and the conditional distribution distance, and combining the joint distribution distance and a label loss to obtain a target function; and optimizing the target function by using SGD, and training the deep convolutional neural network model.

Dynamic joint distribution alignment network-based bearing fault diagnosis method under variable working conditions

The invention relates to a fault diagnosis method for a rolling bearing under variable working conditions. Based on a convolutional neural network, a transfer learning algorithm is combined to handle the problem of the reduced universality of deep learning models. Data acquired under different working conditions is segmented to obtain samples. The samples are preprocessed by using FFT. Low-level features of the samples are extracted by using improved ResNet-50, and a multi-scale feature extractor analyzes the low-level features to obtain high-level features as inputs of a classifier. In a training process, high-level features of training samples and test samples are extracted, and a conditional distribution distance between them is calculated as a part of a target function for backpropagation to implement intra-class adaptation, thereby reducing the impact of domain shift, to enable a deep learning model to better carry out fault diagnosis tasks.

Intra-class adaptation fault diagnosis method for bearing under variable working conditions

A phase shifter transmission device includes: a power mechanism, a driving rod, a plurality of transmission assemblies, and at least one row of phase shifters. The power mechanism is connected to the driving rod and configured to drive the driving rod to rotate. The plurality of transmission assemblies are connected to the driving rod, distributed along an axial direction of the driving rod, and driven by the driving rod to rotate synchronously. Each row of phase shifters includes a plurality of phase shifters distributed along the axial direction of the driving rod, and each phase shifter of each row of phase shifters is connected to the corresponding transmission assembly. The at least one row of phase shifters are configured, when being driven by the plurality of transmission assemblies, to synchronously adjust phases of radiated signals corresponding to the phase shifters.

Phase shifter transmission device

An antenna element includes a base body. The base body includes a plate portion, a support column, and a metal layer. The plate portion is formed by non-metallic material. The at least one support column, each of the support column is connected to the plate portion. The metal layer covers the base body.

Antenna element and antenna

An antenna assembly includes a radiation plate, a first feed board, and a second feed board. The radiation plate includes a radiation patch and a plurality of slot members, and each slot member includes a fixing groove and a guide groove communicating with the fixing groove. The first feed board includes a first fixing member at an end facing the radiation patch. The second feed board includes a second fixing member at an end facing the radiation patch, and the second feed board is compatible with the first feed board through a plug-in connection. The fixing grooves of the plurality of slot members respectively match the first fixing member and the second fixing member to realize an in-line cooperation of the radiation plate, the first feed board, and the second feed board.

Antenna assembly

Growing community of inventors

Suzhou, China

Xu Wang