CN-121983156-A - Catalyst synthesis parameter optimization method and system based on denitration index evaluation

CN121983156ACN 121983156 ACN121983156 ACN 121983156ACN-121983156-A

Abstract

The invention relates to the technical field of catalyst synthesis, in particular to a catalyst synthesis parameter optimization method and system based on denitration index evaluation, comprising the following steps: setting a metal element set to be selected, acquiring a test catalyst set based on the metal element set to be selected, performing catalytic simulation on the test catalyst set according to a plurality of scenes to be denitrified and the denitrification performance evaluation standards to obtain a catalyst denitrification data set, performing deep learning by using the catalyst denitrification data set to obtain a catalyst component selection model, and obtaining a target catalyst according to a target scene feature vector and the catalyst component selection model. The invention can improve the design accuracy and denitration performance of the catalyst and obviously reduce the development period.

Inventors

KONG MING
SHEN XUESONG
LIU ZHIFANG
MENG FEI
LIU HAO
SHEN LI
JIANG LIYUAN

Assignees

重庆科技大学

Dates

Publication Date: 20260505
Application Date: 20251210

Claims (10)

1. A method for optimizing catalyst synthesis parameters based on denitration index evaluation, the method comprising: Confirming a catalyst product to be synthesized and low-titanium blast furnace slag, and setting a metal element set to be selected based on the catalyst product to be synthesized and the low-titanium blast furnace slag; Sequentially extracting metal elements to be selected from a metal element set to be selected, inquiring a plurality of available metal raw materials based on the metal elements to be selected, performing catalyst synthesis according to the plurality of available metal raw materials to obtain a plurality of test catalyst groups, and combining the plurality of test catalyst groups corresponding to the metal elements to be selected to obtain a test catalyst set; confirming a plurality of scenes to be denitrified and denitrification performance evaluation standards, and carrying out catalytic simulation on the test catalyst set according to the scenes to be denitrified and the denitrification performance evaluation standards to obtain a catalyst denitrification data set; deep learning is carried out by utilizing the catalyst denitration data set, and a catalyst component selection model is obtained; constructing a target scene feature vector based on a preset target denitration scene, and inputting the target scene feature vector into a catalyst component selection model to obtain a plurality of predicted catalyst structure vectors and a plurality of predicted catalyst performance vectors; And selecting a target catalyst according to the plurality of predicted catalyst structure vectors and the plurality of predicted catalyst performance vectors, and completing catalyst synthesis parameter optimization based on denitration index evaluation based on the target catalyst.
2. The method for optimizing catalyst synthesis parameters based on denitration index evaluation as set forth in claim 1, wherein said synthesizing the catalyst based on a plurality of available metal raw materials to obtain a plurality of test catalyst groups comprises: Sequentially extracting available metal raw materials from a plurality of available metal raw materials, and performing the following operations on the extracted available metal raw materials: Theoretical proportion setting is carried out on available metal raw materials to obtain a catalyst raw material proportion group; Synthesizing a catalyst according to the catalyst raw material proportion group to obtain a test catalyst group, wherein the metal raw material proportion in the catalyst raw material proportion group corresponds to the test catalysts in the test catalyst group one by one; and summarizing the test catalyst groups corresponding to each available metal raw material in the available metal raw materials to obtain a plurality of test catalyst groups.
3. The method for optimizing catalyst synthesis parameters based on denitration index evaluation as set forth in claim 2, wherein the performing catalytic simulation on the test catalyst set according to the plurality of scenes to be denitration and the denitration performance evaluation criteria to obtain the catalyst denitration data set includes: sequentially extracting test catalysts in the test catalyst set, and performing the following operations on the extracted test catalysts: inquiring the catalyst synthesis energy consumption and the catalyst synthesis efficiency of the test catalyst in the synthesis process; Extracting structural features of the test catalyst to obtain a simulated catalyst structural vector; Based on a plurality of scenes to be denitrified, a denitrification performance evaluation standard, catalyst synthesis energy consumption, catalyst synthesis efficiency and simulated catalyst structure vectors, performing multi-scene denitrification simulation on the tested catalyst to obtain a plurality of catalyst denitrification data; and merging the plurality of catalyst denitration data corresponding to each test catalyst in the test catalyst set to obtain a catalyst denitration data set.
4. The method for optimizing catalyst synthesis parameters based on denitration index evaluation as recited in claim 3, wherein the step of extracting structural features of the test catalyst to obtain a simulated catalyst structural vector comprises the steps of: Carrying out microscopic photographing on the test catalyst to obtain a microscopic image of the catalyst; Preprocessing the catalyst microscopic image to obtain an enhanced microscopic image, wherein the preprocessing comprises denoising and contrast enhancement; dividing the enhanced microscopic image to obtain a binary microscopic image; and inputting the binary microscopic image into a pre-trained feature extractor to obtain a simulated catalyst structure vector, wherein the feature extractor is a convolutional neural network.
5. The method for optimizing catalyst synthesis parameters based on denitration index evaluation as set forth in claim 4, wherein the performing a multi-scenario denitration simulation on the test catalyst based on a plurality of scenes to be denitration, denitration performance evaluation criteria, catalyst synthesis energy consumption, catalyst synthesis efficiency and simulated catalyst structure vector to obtain a plurality of catalyst denitration data comprises: Sequentially extracting the scenes to be denitrified from a plurality of scenes to be denitrified; performing scene denitration simulation based on a scene to be denitration and a test catalyst to obtain a simulated scene feature vector and a simulated denitration performance vector; Supplementing the catalyst synthesis energy consumption and the catalyst synthesis efficiency to the simulated denitration performance vector to obtain a simulated catalyst performance vector; combining the simulated catalyst structure vector, the simulated catalyst performance vector and the simulated scene feature vector to obtain original denitration data; carrying out data validity assessment on the original denitration data based on a denitration performance assessment standard to obtain a data validity result, wherein the data validity result is valid or invalid; if the data effective result is effective, the original denitration data is recorded as catalyst denitration data; and summarizing the catalyst denitration data corresponding to the scene to be denitration to obtain a plurality of catalyst denitration data.
6. The method for optimizing catalyst synthesis parameters based on denitration index evaluation as set forth in claim 5, wherein the scene denitration simulation is performed based on a scene to be denitration and a test catalyst to obtain a simulated scene feature vector and a simulated denitration performance vector, and the method comprises: Simulating the components of the waste incineration flue gas based on the scene to be denitrified to obtain simulated incineration flue gas, and constructing scene characteristics of the simulated incineration flue gas to obtain a simulated scene characteristic vector; placing a test catalyst in a pre-constructed reaction tube to obtain a denitration environment, wherein the denitration environment comprises a gas inlet and a gas outlet; Performing denitration test by using denitration environment and simulated incineration flue gas to obtain effective denitration temperature span and effective denitration rate; recording the byproduct generation amount and the byproduct damage index in the denitration test; Acquiring a stable temperature interval of a test catalyst, and performing catalyst life test on the test catalyst based on the stable temperature interval and a preset denitration rate threshold value to obtain the catalyst life; Vector generation is carried out based on the effective denitration temperature span, the effective denitration rate, the byproduct generation amount, the byproduct damage index and the catalyst life, and a simulated denitration performance vector is obtained.
7. The method for optimizing catalyst synthesis parameters based on denitration index evaluation as set forth in claim 6, wherein said performing denitration test using a denitration environment and a simulated incineration flue gas to obtain an effective denitration temperature span and an effective denitration rate comprises: obtaining the quality of a catalyst in a denitration environment; Acquiring a catalyst environment temperature set and an initial denitration rate set based on the catalyst quality, the denitration environment and the simulated incineration flue gas; performing curve fitting according to the catalyst environment temperature set and the initial denitration rate set to obtain a denitration rate temperature curve; and identifying an effective denitration temperature span and an effective denitration rate in a denitration rate temperature curve based on the denitration rate threshold.
8. The method for optimizing catalyst synthesis parameters based on denitration index evaluation as recited in claim 7, wherein the obtaining a set of catalyst ambient temperatures and an initial set of denitration rates based on catalyst quality, denitration environment, and simulated incineration flue gas comprises: according to the preset gas volume flow and the preset catalyst environment temperature, introducing the simulated incineration flue gas into a denitration environment, and continuously detecting a gas inlet and a gas outlet by using a preset gas analyzer to obtain an inlet nitrate concentration sequence and an outlet nitrate concentration sequence; Calculating an initial denitration rate based on the gas volume flow, the catalyst mass, the inlet nitrate concentration sequence and the outlet nitrate concentration sequence; Adjusting the ambient temperature of the catalyst according to a preset temperature change strategy to obtain an adjusted ambient temperature; taking the adjusted environmental temperature as the catalyst environmental temperature, returning the step of introducing the simulated incineration flue gas into the denitration environment according to the preset gas volume flow and the preset catalyst environmental temperature until a preset stopping test instruction is received; and respectively summarizing the catalyst environment temperature and the initial denitration rate to obtain a catalyst environment temperature set and an initial denitration rate set.
9. The method for optimizing catalyst synthesis parameters based on denitration index evaluation as recited in claim 8, wherein selecting the target catalyst based on the plurality of predicted catalyst structure vectors and the plurality of predicted catalyst performance vectors comprises: identifying a plurality of similar catalysts in a preset catalyst structure characteristic table according to the plurality of predicted catalyst structure vectors; Receiving a set of catalyst performance weights, wherein the number of catalyst performance weights in the set of catalyst performance weights is the same as the vector dimension of the predicted catalyst performance vector; Sequentially extracting predicted catalyst performance vectors from the plurality of predicted catalyst performance vectors, and performing weighted calculation according to the predicted catalyst performance vectors and the catalyst performance weight set to obtain a comprehensive catalytic performance value; Summarizing the comprehensive catalytic performance values to obtain a plurality of comprehensive catalytic performance values, and identifying the maximum catalytic performance value in the plurality of comprehensive catalytic performance values; the target catalyst corresponding to the maximum catalytic performance value is identified among the plurality of similar catalysts.
10. A catalyst synthesis parameter optimization system based on denitration index evaluation, the system comprising: the metal element setting module is used for identifying a catalyst product to be synthesized and low-titanium blast furnace slag, and setting a metal element set to be selected based on the catalyst product to be synthesized and the low-titanium blast furnace slag; The test catalyst preparation module is used for sequentially extracting the metal elements to be selected in the metal element set to be selected, inquiring a plurality of available metal raw materials based on the metal elements to be selected, performing catalyst synthesis according to the plurality of available metal raw materials to obtain a plurality of test catalyst groups, and combining the plurality of test catalyst groups corresponding to the metal elements to be selected to obtain a test catalyst set; The method comprises the steps of selecting a model construction module, performing catalytic simulation on a test catalyst set according to a plurality of scenes to be denitrified and denitrification performance evaluation standards to obtain a catalyst denitrification data set, and performing deep learning by using the catalyst denitrification data set to obtain a catalyst component selection model; The target catalyst selection module is used for constructing a target scene feature vector based on a preset target denitration scene, inputting the target scene feature vector into the catalyst component selection model to obtain a plurality of predicted catalyst structure vectors and a plurality of predicted catalyst performance vectors, and selecting a target catalyst according to the plurality of predicted catalyst structure vectors and the plurality of predicted catalyst performance vectors.

Description

Catalyst synthesis parameter optimization method and system based on denitration index evaluation Technical Field The invention relates to the technical field of catalyst synthesis, in particular to a catalyst synthesis parameter optimization method and system based on denitration index evaluation. Background In the field of industrial flue gas treatment, the synthesis of the denitration catalyst is a core link for realizing the efficient purification of nitrogen oxides and meeting increasingly strict environmental protection emission standards. The catalyst with excellent performance and controllable cost is developed, has important significance for the green sustainable development of high pollution industries such as garbage incineration, ferrous metallurgy and the like, and the denitration efficiency and the service life of the catalyst are directly determined by the accurate optimization of synthesis parameters. The traditional catalyst synthesis optimization mainly relies on the experience of researchers to carry out repeated trial and error experiments, but the experimental process is strong in blindness, long in period and high in cost, comprehensive influences of various metal elements, raw material proportions and complex working conditions on performances are difficult to systematically inspect, an optimal solution is easy to miss, meanwhile, the traditional method is single in optimization dimension, only the denitration rate is usually focused, and key indexes such as catalyst service life, synthesis energy consumption and byproduct control are ignored. Disclosure of Invention The invention provides a catalyst synthesis parameter optimization method and system based on denitration index evaluation, which mainly aim at improving the design accuracy and denitration performance of a catalyst and remarkably reducing the development period. In order to achieve the above object, the present invention provides a catalyst synthesis parameter optimization method based on denitration index evaluation, including: Confirming a catalyst product to be synthesized and low-titanium blast furnace slag, and setting a metal element set to be selected based on the catalyst product to be synthesized and the low-titanium blast furnace slag; Sequentially extracting metal elements to be selected from a metal element set to be selected, inquiring a plurality of available metal raw materials based on the metal elements to be selected, performing catalyst synthesis according to the plurality of available metal raw materials to obtain a plurality of test catalyst groups, and combining the plurality of test catalyst groups corresponding to the metal elements to be selected to obtain a test catalyst set; confirming a plurality of scenes to be denitrified and denitrification performance evaluation standards, and carrying out catalytic simulation on the test catalyst set according to the scenes to be denitrified and the denitrification performance evaluation standards to obtain a catalyst denitrification data set; deep learning is carried out by utilizing the catalyst denitration data set, and a catalyst component selection model is obtained; constructing a target scene feature vector based on a preset target denitration scene, and inputting the target scene feature vector into a catalyst component selection model to obtain a plurality of predicted catalyst structure vectors and a plurality of predicted catalyst performance vectors; And selecting a target catalyst according to the plurality of predicted catalyst structure vectors and the plurality of predicted catalyst performance vectors, and completing catalyst synthesis parameter optimization based on denitration index evaluation based on the target catalyst. Optionally, the catalyst synthesis is performed according to a plurality of available metal raw materials to obtain a plurality of test catalyst groups, including: Sequentially extracting available metal raw materials from a plurality of available metal raw materials, and performing the following operations on the extracted available metal raw materials: Theoretical proportion setting is carried out on available metal raw materials to obtain a catalyst raw material proportion group; Synthesizing a catalyst according to the catalyst raw material proportion group to obtain a test catalyst group, wherein the metal raw material proportion in the catalyst raw material proportion group corresponds to the test catalysts in the test catalyst group one by one; and summarizing the test catalyst groups corresponding to each available metal raw material in the available metal raw materials to obtain a plurality of test catalyst groups. Optionally, the performing catalytic simulation on the test catalyst set according to a plurality of to-be-denitrified scenes and the denitrification performance evaluation criteria to obtain a catalyst denitrification data set includes: sequentially extracting test catalysts in the test catalyst s