Unlock instant, AI-driven research and patent intelligence for your innovation.
CFD model type selection method based on neural network
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A neural network, BP neural network technology, applied in biological neural network models, neural learning methods, neural architectures, etc., can solve the problems of increasing time cost and long simulation time, and achieve the effect of saving time cost
Active Publication Date: 2021-11-12
CHENGDU WANJIANGGANGLI TECH
View PDF4 Cites 0 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0006] The two methods have their own advantages and disadvantages. Generally speaking, the VOF method is a general method, but the simulation time is too long, which is several times that of the Ganggai assumption method.
The Ganggay method is a special method, but only for a specific type, and can only be used in channels where the maximum flow velocity occurs on the free surface
Since the VOF method is a general method, generally only the VOF method is used in the simulation process, which greatly increases the time cost
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0048] Example 1, such as figure 1 shown
[0049] The data set is obtained through CFD simulation, and the values of the bottom width b in this embodiment are 0.5m, 0.6m, 0.8m and 1m;
[0050] The values of water depth h are 0.1m, 0.2m, 0.3m, 0.4m, 0.5m, 0.6m and 0.7m;
[0051] The angle values are 110°, 115°, 120°, 125° and 130°;
[0052] The inlet velocity values are 0.1 m / s, 0.2 m / s, 0.3 m / s, 0.4 m / s and 0.5 m / s.
[0053] Using the above data as the input conditions of CFD simulation, the information of the flow velocity field and the position where the maximum flow velocity occurs can be obtained.
[0054] It should be noted that when the maximum flow velocity appears on the water surface, the output result is 1; when the maximum flow velocity does not appear on the miscellaneous water surface, the output result is 0.
[0055] Combine the above parameters to get a lot of data, the data format is as follows: Table 1:
[0056] Table 1
[0057]
[0058] After...
Embodiment 2
[0062] Example 2, such as figure 1 shown
[0063] The data set is obtained through CFD simulation, and the values of the bottom width b in this embodiment are 0.5m, 0.605m, 0.745m and 0.85m;
[0064] The values of water depth h are 0.1m, 0.2m, 0.3m, 0.4m and 0.5m;
[0065] The angle values are 130°, 135° and 140°;
[0066] The inlet velocity values are 0.4 m / s, 0.8 m / s, 1.2 m / s, 1.6 m / s, 2.0 m / s, 2.4 m / s and 2.8 m / s.
[0067] Using the above data as the input conditions of CFD simulation, the information of the flow velocity field and the position where the maximum flow velocity occurs can be obtained.
[0068] It should be noted that when the maximum flow velocity appears on the water surface, the output result is 1; when the maximum flow velocity does not appear on the miscellaneous water surface, the output result is 0.
[0069] Combine the above parameters to get a lot of data, and the data format is as follows: Table 2:
[0070] Table 2
[0071]
[0072] ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More
PUM
Login to View More
Abstract
The invention discloses a CFD model type selection method based on a neural network. The method specifically comprises the following steps of: carrying out modeling simulation on a channel to obtain a data set, and dividing the data set into a training set and a test set; adding a first layer weight and bias, outputting a result through an activation function, adopting the result as input of a second layer, further performing weighted summation, and outputting a result through the activation function; adjusting the weight and the bias of a network model through back propagation, reducing a cost function, continuously updating the weight and the bias, and finally minimizing the error; inputting actually acquired data into the neural network model to obtain the maximum flow velocity, and selecting a free watersurface processing method by analyzing and judging the maximum flow velocity; and judging whether the maximum flow velocity appears on a free water surface or not, if so, selecting a rigid cover assumption method, otherwise, using a VOF method. According to the method, the VOF method and the rigid cover assumption method can be judged by using the neural network, and the most adaptive method can be used in channel judgment, so that the time cost is saved.
Description
technical field [0001] The invention relates to the technical field of water resource management, in particular to a neural network-based CFD model type selection method. Background technique [0002] The researchers did not know the velocity field of the channel before running the simulation, and therefore did not know whether the maximum velocity occurred at the free surface. After the simulation, the flow velocity field can be obtained, at which point the position of the maximum flow velocity is known. In the simulation process, there are two methods to deal with the free water surface, one is the VOF method, and the other is the Ganggai assumption method. [0003] In a document titled "Validation of 3D numerical model of open channel water flow based on FLuent", it is proposed to use the just cover assumption method and the VOF method to deal with the free water surface, based on the rectangular open channel test model data of Tominaga and Nezu et al. Fluent software i...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More
Application Information
Patent Timeline
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to View More 
Login to View More