Bidirectional fluid-solid coupling calculation method based on mask deep neural network

• Main Authors: TANG YUMENG, ZHAO SHIHANG, WANG FEITONG, LIU YANGWEI
• Format: Patent
• Language: Chinese; English
• Published: 12.04.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention discloses a bidirectional fluid-solid coupling calculation method based on a mask deep neural network. The method mainly comprises the steps of 1, establishing a database; 2, constructing a training set and a test set according to the time sequence; 3, building a mask deep neural network and training the mask deep neural network; and step 4, performing fluid-solid coupling calculation by combining the mask deep neural network and the calculation structural mechanics solver. According to the method, the flow field reduced-order model based on the mask deep neural network is established to replace a computational fluid mechanics solver part in the bidirectional fluid-solid coupling solving system, rapid prediction of the flow field solving part in the solving process is achieved, the model is coupled with a computational structural mechanics solver, the calculation consumption of the bidirectional fluid-solid coupling solving system is reduced, and the calculation efficiency of the bidirectional f