Title:
METHOD FOR PREDICTING BIOMASS COKE GASIFICATION REACTION CHARACTERISTICS
Document Type and Number:
WIPO Patent Application WO/2023/005302
Kind Code:
A1
Abstract:
The present invention provides a method for predicting biomass coke gasification reaction characteristics, comprising the following steps: step 10), collecting training data of a biomass coke gasification reaction; step 20), establishing a BP neural network model comprising an input layer, a hidden layer, and an output layer, input parameters of the BP neural network model being a coking temperature, a specific surface area of a coke sample, and a gasification time, and an output parameter being a coke conversion rate; step 30), training the BP neural network model by using the training data, and optimizing the BP neural network model by using a particle swarm optimization algorithm, so as to obtain a BP neural network model having high prediction precision; and step 40), predicting the coke conversion rate of the biomass coke gasification reaction by using the BP neural network model having high prediction precision. According to the method for predicting biomass coke gasification reaction characteristics of the present invention, an air gasification reaction process of biomass coke can be simulated in a high coincidence degree, such that the biomass coke gasification reaction characteristics can be accurately predicted.
Inventors:
ZHANG HUIYAN (CN)
ZHA ZHENTING (CN)
GE ZEFENG (CN)
MA YUNA (CN)
ZHA ZHENTING (CN)
GE ZEFENG (CN)
MA YUNA (CN)
Application Number:
PCT/CN2022/089540
Publication Date:
February 02, 2023
Filing Date:
April 27, 2022
Export Citation:
Assignee:
UNIV SOUTHEAST (CN)
International Classes:
G06F30/27
Domestic Patent References:
| WO2017209548A1 | 2017-12-07 |
Foreign References:
| CN113657591A | 2021-11-16 | |||
| CN111950854A | 2020-11-17 | |||
| CN112926767A | 2021-06-08 |
Attorney, Agent or Firm:
JW IP LAW FIRM (CN)
Download PDF: