Reverse Gasification Design Using TEM-ANN and Fuzzy Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional gasification process designing methods face challenges in simultaneously addressing multiple design objectives, requiring extensive workloads and lacking accuracy due to non-linear parameters, especially in determining gasification temperature and geometry, leading to suboptimal design schemes and practical production issues.
Innovation Solution
A reverse design method combining a product prediction module, parameter optimization module, and clustering analysis module, utilizing a TEM-ANN model, MOGA, and non-dominated fuzzy sorting to optimize gasification parameters based on designer preferences and requirements, integrating a device comprising a processor and memory for executing the method.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If thermodynamic equilibrium model (TEM) is used for gasification process design, then the model is simple and feasible, but it cannot reach chemical equilibrium states in practical production leading to large errors
Solution Approach 1:
The patent combines TEM and ANN models into a hybrid TEM-ANN model. The TEM provides initial predictions with simple calculations, while the ANN model corrects deviations by learning from experimental data. This merging allows the system to maintain the simplicity of TEM while achieving the accuracy of data-driven approaches, resolving the contradiction between model complexity and prediction accuracy.
Solution Approach 2:
The ANN model acts as an intermediary that bridges the gap between the simplified TEM model and actual gasification processes. It learns the discrepancies between TEM predictions and real-world outcomes, then uses this knowledge to correct TEM predictions, enabling accurate predictions without requiring the full complexity of detailed kinetic models.
2Reliability
If trial and error method with large number of simulations is used, then design variables meeting objectives can be found, but the workload is heavy and optimal design scheme is difficult to determine
Solution Approach 1:
The patent implements feedback mechanisms where the ANN model learns from the discrepancies between predicted and actual outcomes. The system continuously refines its predictions by incorporating feedback from experimental data and simulation results, enabling it to identify optimal design schemes with high reliability without requiring exhaustive trial and error simulations.
Solution Approach 2:
The TEM-ANN model performs preliminary predictions and screenings before detailed simulations are conducted. By pre-identifying promising design schemes through the hybrid model, the system reduces the number of full simulations needed, thereby maintaining high design quality while significantly improving efficiency.
3Productivity
If artificial neural network (ANN) is used for prediction, then high speed and accurate prediction can be achieved, but it is difficult to determine important input parameter gasification temperature during design stage
Solution Approach 1:
The TEM model performs preliminary estimation of gasification temperature and other critical parameters before the ANN model conducts detailed predictions. This preliminary action provides reasonable initial values and constraints for the ANN, making it easier to determine input parameters during the design stage while maintaining the high prediction speed and accuracy of the ANN approach.
4Device complexity
If empirical methods with designer experience are used, then design can be performed with simple methods, but it is very difficult to treat multiple design objectives simultaneously
Solution Approach 1:
The TEM-ANN model serves multiple functions: it predicts gas composition, calculates heating values, estimates yields, and optimizes design parameters. This multi-functional capability allows the system to handle multiple design objectives simultaneously while maintaining relative simplicity, as the same hybrid model framework addresses various design concerns without requiring separate complex methodologies for each objective.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The method achieves more accurate, efficient, and practical design results by optimizing design variables and objectives, reducing workload, and ensuring the design meets production requirements, with improved prediction accuracy and reduced errors in gasification outcomes.
Implementation Method 1
thermodynamic equilibrium models (TEMs)... in which multiple chemical reactions in the gasification process are assumed to reach chemical equilibrium states respectively when leaving the gasification reactor
Implementation Method 2
the results of the gasification reactions are predicted based on the mass conservation, energy conservation and chemical equilibrium analyses
Implementation Method 3
the results of the gasification reactions are predicted based on the mass conservation, energy conservation and chemical equilibrium analyses
Data Source
Figure 1~2
Figure 3~4
Figure 5
AI summary
A method for designing of a gasification process comprises following steps: determining feature(s) of raw material and design requirement(s), wherein the design requirement(s) are numerical range(s) of design objective(s); giving assumed value(s) of design variable(s) according to the feature(s) of the raw material and design requirement(s), and obtaining initial value(s) of the design variable(s) by calculation using the assumed value(s) and empirical formula(s); determining optimization range(s) of the design variable(s) for reverse designing according to the initial value(s) of the design variable(s); sorting the individuals in the initial population by a non-dominated fuzzy sorting method; clustering all the non-dominated individuals by a pedigree clustering method with a fuzzy objective weight coefficient; and finally sorting different clusters by a non-dominated fuzzy sorting method, to obtain the design variable interval(s) and the design objective interval(s) which meet the design requirement(s) best. The reverse design has broader requirements for the design objectives, more comprehensive design variables, and more clear direction in the designing method, resulting in design results meeting the design requirements better and greatly reduced workload. Also, no well-experienced designers are required.