公开(公告)号：US20220092428A1

公开(公告)日：2022-03-24

申请号：US17312278

申请日：2020-09-28

Applicant: DALIAN UNIVERSITY OF TECHNOLOGY

Inventor： Ximing SUN ,  Fuxiang QUAN ,  Hongyang ZHAO ,  Yanhua MA ,  Pan QIN

IPC: G06N3/08 ,  G06N3/04

Abstract: The present invention relates to a prediction method for stall and surge of an axial compressor based on deep learning. The method comprises the following steps: firstly, preprocessing data with stall and surge of an aeroengine, and partitioning a test data set and a training data set from experimental data. Secondly, constructing an LR branch network module, a WaveNet branch network module and a LR-WaveNet prediction model in sequence. Finally, conducting real-time prediction on the test data: preprocessing test set data in the same manner, and adjusting data dimension according to input requirements of the LR-WaveNet prediction model; giving surge prediction probabilities of all samples by means of the LR-WaveNet prediction model according to time sequence; and giving the probability of surge that data with noise points changes over time by means of the LR-WaveNet prediction model, to test the anti-interference performance of the model.

公开(公告)号：US20240012965A1

公开(公告)日：2024-01-11

申请号：US17920167

申请日：2021-12-27

Applicant: DALIAN UNIVERSITY OF TECHNOLOGY

Inventor： Bin YANG ,  Xinyuan ZHANG ,  Ximing SUN ,  Fuxiang QUAN

IPC: G06F30/27 ,  G06F30/28

CPC classification number: G06F30/27 ,  G06F30/28

Abstract: A steady flow prediction method in a plane cascade based on a generative adversarial network is provided. Firstly, CFD simulation experimental data in the plane cascade are preprocessed, and a test dataset and a training dataset are divided from the simulation experimental data. Then, an Encoding-Forecasting network module, a deep convolutional network module and a generative adversarial network prediction model are constructed successively. Finally, prediction is conducted on test set data: the test set data is preprocessed in the same manner, and data dimensions are adjusted according to input requirements of a saved optimal prediction model; and flow field images in the plane cascade at an inlet attack angle of 10° are obtained through the prediction model. The present invention can effectively avoid the problem of limited measurement range of sensors in an axial flow compressor, and the prediction result is highly consistent with the calculation result of CFD.

公开(公告)号：US20230392556A1

公开(公告)日：2023-12-07

申请号：US18032898

申请日：2021-06-04

Applicant: DALIAN UNIVERSITY OF TECHNOLOGY

Inventor： Ximing SUN ,  Fuxiang QUAN ,  Chongyi SUN ,  Yanhua MA

IPC: F02C9/16 ,  F04D27/02 ,  G06N7/02

CPC classification number: F02C9/16 ,  F04D27/02 ,  G06N7/02 ,  F05D2270/707

Abstract: An aero-engine surge active control system based on fuzzy controller switching is provided. The present invention selects a basic controller with the most appropriate current state for switching control according to the operating state of a compressor based on the principle of fuzzy switching, and can realize large-range, adaptive and performance-optimized surge active control. Controllers designed by the present invention realize large-range surge active control through fuzzy switching, so that the effective operating ranges of the controllers are expanded and the reliability of the controllers is improved. The designed controllers can be applied to the active control of surge caused by various causes, so that the adaptability of the controllers is improved and is closer to the actual operating condition of the engine. Some optimization indexes are added in the design process of the controllers, which can realize optimal control under corresponding optimization objectives.

公开(公告)号：US20230316051A1

公开(公告)日：2023-10-05

申请号：US17795095

申请日：2021-09-18

Applicant: DALIAN UNIVERSITY OF TECHNOLOGY

Inventor： Ximing SUN ,  Yuhui LI ,  Fuxiang QUAN

IPC: G06N3/049 ,  F04D27/00 ,  G06N3/048 ,  G06N3/0455

CPC classification number: G06N3/049 ,  F04D27/001 ,  G06N3/048 ,  G06N3/0455

Abstract: A pre-alarming method for rotary stall of compressors based on a temporal dilated convolutional neural network includes firstly, preprocessing dynamic pressure data of an aero-engine, and dividing a test dataset and a training dataset from experimental data; secondly, constructing a temporal convolutional network module, a Resnet-v network module and a temporal dilated convolutional network prediction model in sequence, and saving an optimal prediction model. Finally, conducting real-time prediction on test data: adjusting data dimension of the test dataset according to input requirements of the temporal dilated convolutional network prediction model; calculating predicted surge probability of each sample by the temporal dilated convolutional network prediction model in chronological order; calculating real-time surge probability of a pair of samples with and without covariates by the temporal dilated convolutional network prediction model, and observing improvement action of covariates on model prediction effect.

公开(公告)号：US20250052251A1

公开(公告)日：2025-02-13

申请号：US18884715

申请日：2024-09-13

Applicant: DALIAN UNIVERSITY OF TECHNOLOGY

Inventor： Ximing SUN ,  Chongyi SUN ,  Fuxiang QUAN ,  Wei REN ,  Hongxin LI ,  Zhibo ZHANG ,  Mingsui YANG

IPC: F04D27/02 ,  G05D7/06

Abstract: The present invention belongs to the field of aviation compressor control, and relates to an aviation compressor active stabilization control method based on disturbance observation and compensation. Modeling errors and external disturbances of models used in design of a controller are observed, and sub-controllers are individually designed for state variables of interest to compensate for the disturbances, thus to simultaneously solve the problems of rotating stall and surge of an aviation compressor in a variety of complex situations. Partial differential model of the compressor is converted to an ordinary differential equation by Galerkin projection method, partial differential characteristics of the compressor are reserved in the form of disturbances during conversion, and an active stabilization controller of the aviation compressor is designed in combination with disturbance observation and compensation technology, thus to ensure that the models used in the design of the controller have higher accuracy, high robustness and high reliability.

公开(公告)号：US20240077039A1

公开(公告)日：2024-03-07

申请号：US18025531

申请日：2022-05-11

Applicant: DALIAN UNIVERSITY OF TECHNOLOGY

Inventor： Ximing SUN ,  Junhong CHEN ,  Fuxiang QUAN ,  Chongyi SUN

IPC: F02C9/44 ,  G05B13/02 ,  G05B13/04

CPC classification number: F02C9/44 ,  G05B13/027 ,  G05B13/042

Abstract: The present invention provides an optimization control method for an aero-engine transient state based on reinforcement learning, and belongs to the technical field of aero-engine transient states. The method comprises: adjusting an existing twin-spool turbo-fan engine model as a model for invoking a reinforcement learning algorithm; to simultaneously satisfy high level state space and continuous action output of a real-time model, designing an Actor-Critic network model; designing a deep deterministic policy gradient (DDPG) algorithm based on an Actor-Critic frame, to simultaneously solve the problems of high-dimensional state space and continuous action output; training the model after combining the Actor-Critic frame with the DDPG algorithm; and obtaining the control law of engine acceleration transition from the above training process, and using the method to control an engine acceleration process.

公开(公告)号：US20220372891A1

公开(公告)日：2022-11-24

申请号：US17606180

申请日：2021-01-14

Applicant: DALIAN UNIVERSITY OF TECHNOLOGY

Inventor： Ximing SUN ,  Qi TANG ,  Hongyang ZHAO ,  Fuxiang QUAN ,  Ziyao DING ,  Di GUO

IPC: F01D21/00 ,  G06F30/28

Abstract: A method for stability analysis of a combustion chamber of a gas turbine engine based on image sequence analysis belongs to the field of fault prediction and health management of aeroengine. Firstly, flow field data inside a combustion chamber of a gas turbine engine is acquired. Secondly, flow field images of the combustion chamber are preprocessed to respectively obtain a discrimination model data set and a prediction model data set. Then, a 3DWaveNet model is constructed as a generation network of a prediction model. A discrimination network of the module is constructed. The generation network and the discrimination network are combined to form the prediction model. Finally, a discrimination model is constructed according to the discrimination model data set; the training set in the discrimination model data set is used for training, and the test set is used for assessment.