Interactive yield optimization method and system based on recurrent 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 cyclic neural network, interactive technology, applied in the field of chemical reaction yield optimization, can solve problems such as missing reaction conditions, achieve optimal reaction yield, solve experimental design problems, and reduce costs.
Active Publication Date: 2022-07-22
烟台国工智能科技有限公司
View PDF3 Cites 1 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
However, this often misses...
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
[0043] An interactive yield optimization method based on a cyclic neural network of the present invention, such as figure 1 shown, including the following steps:
[0044] S100. For the current chemical reaction, obtain a variety of experimental condition parameters, for numerical experimental condition parameters, encode them by delimiting a numerical value range, and for non-numerical experimental condition parameters, encode them by SMILES expression, Obtain the experimental condition parameters after encoding;
[0045]S200, taking the encoded experimental condition parameters as input, and simulating the current chemical reaction through the mixed Gaussian density function to obtain the reaction yield;
[0046] S300, constructing a chemical reaction model based on a cyclic neural network model, the chemical reaction model is used to predict and output the experimental condition parameters of the next round based on a historical data set, current experimental condition para...
Embodiment 2
[0092] The present invention is an interactive yield optimization system based on a cyclic neural network, comprising a data collection module, an initial data construction module, a model construction module, and a model training module. The system is used to implement a recurrent neural network-based interactive yield optimization method disclosed in Example 1.
[0093] For the current chemical reaction, the data collection module is used to obtain a variety of experimental condition parameters. For numerical experimental condition parameters, they are coded by delimiting the numerical value range. For non-numerical experimental condition parameters, the SMILES expression is used. Encoding is performed to obtain the post-encoding experimental condition parameters.
[0094] In this embodiment, the data collection module is used to obtain experimental data and perform preprocessing. As a specific implementation, the experimental conditions and auxiliary substances participatin...
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 an interactive yield optimization method and system based on a recurrent neural network, belongs to the technical field of chemical reaction yield optimization, and aims to solve the technical problem of how to obtain a relatively high chemical reaction yield on the premise of reducing the experiment cost. Comprising the following steps: acquiring various experimental condition parameters; simulating a current chemical reaction through a mixed Gaussian density function to obtain a reaction yield; constructing a chemical reaction model based on the recurrent neural network model; and initializing a historical data set, training the chemical reaction model by taking the encoded experimental condition parameters and the corresponding chemical reaction yield as current experimental condition parameters and corresponding reaction yield, outputting experimental condition parameters of the next round as target experimental parameters, and performing a chemical experiment based on the target experimental condition parameters. The obtained reaction yield is used as a target reaction yield; and under the condition that the target reaction yield reaches a threshold value, carrying out multiple rounds of training on the chemical reaction model.
Description
technical field [0001] The invention relates to the technical field of chemical reaction yield optimization, in particular to an interactive yield optimization method and system based on a cyclic neural network. Background technique [0002] In a chemical reaction, in addition to the reactants themselves, there are many factors that will affect the yield of the chemical reaction. In order to obtain a higher reaction yield, experts in the chemical field need to go through a lot of experiments, which inevitably requires a lot of time and money. Usually at the beginning of the experiment, some experimental plans are designed to reduce the number of experiments and reduce the cost of experiments. However, this often misses optimal reaction conditions. [0003] How to obtain a relatively high chemical reaction yield under the premise of reducing the experimental cost is a technical problem that needs to be solved. SUMMARY OF THE INVENTION [0004] The technical task of the p...
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