Combustion Control System Adapting to Fuel Variations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing control systems for combustion plants face challenges in efficiently managing combustion gas compositions and reducing toxic emissions like NOx and CO, especially when fuel properties change, due to the complexity of combustion phenomena and the need for lengthy model construction periods using reinforcement learning methods.
Innovation Solution
A control system that includes a basic control command unit, a fuel data storage unit, a running results database, a data creating unit, a modeling unit, and a correcting unit to model relationships between operation parameters and combustion gas components, allowing for real-time adjustment of operation commands to minimize NOx and CO concentrations, using numerical analysis and reinforcement learning to shorten model construction time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If reinforcement learning methods are used to model combustion characteristics, then the control system can adapt to fuel property changes, but the model construction period becomes excessively long
Solution Approach 1:
The patent pre-calculates combustion characteristics for multiple fuel types and stores them in a database before actual operation. During runtime, the system directly retrieves pre-computed data instead of performing real-time reinforcement learning, thus eliminating the lengthy model construction period while maintaining adaptability to different fuel properties.
Solution Approach 2:
The system prepares combustion characteristic data for various fuel types in advance and stores them as reference data. This pre-prepared data acts as a cushion that allows the control system to immediately respond to fuel property changes without requiring time-consuming learning processes during actual operation.
2Reliability
If trial and error processes are used for system introduction, then the control system can learn optimal parameters, but the time required for system introduction increases significantly
Solution Approach 1:
The patent performs parameter optimization and learning processes during the offline database construction phase rather than during system introduction. Optimal control parameters for different fuel types are predetermined and stored, allowing rapid system deployment without extensive trial-and-error periods.
Solution Approach 2:
The system uses pre-computed combustion characteristic data as templates for different fuel types. Instead of learning from scratch during system introduction, the control system copies and applies appropriate pre-optimized parameter sets based on the detected fuel type, dramatically reducing introduction time while maintaining control reliability.
3Object-generated harmful factors
If detailed combustion modeling is performed to control exhaust gas components, then emission control improves, but the computational complexity and device requirements increase
Solution Approach 1:
The patent pre-computes detailed combustion characteristics including exhaust gas compositions for various fuel types and operating conditions, storing this data in a database. During operation, the system retrieves pre-calculated data based on fuel type identification, achieving accurate emission control without requiring complex real-time computational models.
Solution Approach 2:
The patent introduces a fuel type identification system and pre-computed database as intermediaries between the simple fuel input and the complex combustion process. This intermediary layer allows detailed combustion modeling results to be obtained through simple database lookups rather than complex real-time calculations, reducing device complexity while maintaining control accuracy.
Data Source
AI summary
A control system includes a basic control command operating unit, a fuel data storage unit, a running results database for storing past running results values of a control subject, a data creating unit configured to calculate a distance between data of the past running results values and the data sets and determining data set in which a distance between data becomes minimum, a modeling unit configured to model a relationship between operation parameters of a combustion apparatus and components in combustion gas of the combustion apparatus by using the data set determined by the data creating unit and a correcting unit for calculating combustion apparatus operation parameters with which components having a better condition than that of the components in a current gas are provided by using a model of the modeling unit and correcting operation command values of the basic control command operating unit by calculated operation parameters.