20240012965. STEADY FLOW PREDICTION METHOD IN PLANE CASCADE BASED ON GENERATIVE ADVERSARIAL NETWORK simplified abstract (DALIAN UNIVERSITY OF TECHNOLOGY)

From WikiPatents
Jump to navigation Jump to search

STEADY FLOW PREDICTION METHOD IN PLANE CASCADE BASED ON GENERATIVE ADVERSARIAL NETWORK

Organization Name

DALIAN UNIVERSITY OF TECHNOLOGY

Inventor(s)

Bin Yang of Dalian, Liaoning (CN)

Xinyuan Zhang of Dalian, Liaoning (CN)

Ximing Sun of Dalian, Liaoning (CN)

Fuxiang Quan of Dalian, Liaoning (CN)

STEADY FLOW PREDICTION METHOD IN PLANE CASCADE BASED ON GENERATIVE ADVERSARIAL NETWORK - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240012965 titled 'STEADY FLOW PREDICTION METHOD IN PLANE CASCADE BASED ON GENERATIVE ADVERSARIAL NETWORK

Simplified Explanation

The abstract of the patent application describes a method for predicting steady flow in a plane cascade using a generative adversarial network. The method involves preprocessing CFD simulation experimental data and dividing it into test and training datasets. The method then constructs an encoding-forecasting network module, a deep convolutional network module, and a generative adversarial network prediction model. The prediction is conducted on the test set data by preprocessing it in the same manner and adjusting the data dimensions according to the input requirements of the prediction model. The predicted flow field images in the plane cascade are obtained at a specific inlet attack angle. The invention solves the problem of limited measurement range of sensors in an axial flow compressor and provides highly consistent prediction results with the calculation results of CFD.

  • The method uses CFD simulation experimental data to predict steady flow in a plane cascade.
  • The data is preprocessed and divided into test and training datasets.
  • An encoding-forecasting network module, a deep convolutional network module, and a generative adversarial network prediction model are constructed.
  • The prediction is conducted on the test set data by preprocessing it and adjusting the data dimensions.
  • The predicted flow field images in the plane cascade are obtained at a specific inlet attack angle.
  • The method avoids the problem of limited measurement range of sensors in an axial flow compressor.
  • The prediction results are highly consistent with the calculation results of CFD.

Potential Applications

This technology can be applied in the field of aerodynamics and fluid mechanics for predicting steady flow in plane cascades. It can be used in the design and optimization of axial flow compressors, turbines, and other fluid flow systems. It can also be used in the development of efficient and reliable flow control strategies.

Problems Solved

1. Limited measurement range of sensors in an axial flow compressor. 2. Difficulty in accurately predicting steady flow in a plane cascade using traditional methods. 3. Lack of a comprehensive and efficient prediction model for flow field images.

Benefits

1. Improved accuracy in predicting steady flow in a plane cascade. 2. Enhanced understanding of flow behavior and performance in fluid flow systems. 3. Optimization of design and control strategies for axial flow compressors and other fluid flow systems. 4. Reduction in the need for expensive and time-consuming experimental testing. 5. Potential for cost savings and improved efficiency in various industries relying on fluid flow systems.


Original Abstract Submitted

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.

Retrieved from "http://wikipatents.org/index.php?title=20240012965._STEADY_FLOW_PREDICTION_METHOD_IN_PLANE_CASCADE_BASED_ON_GENERATIVE_ADVERSARIAL_NETWORK_simplified_abstract_(DALIAN_UNIVERSITY_OF_TECHNOLOGY)&oldid=27144"