An enhanced understanding of the intricate relationships among the process parameters in carbon dioxide capture enables prediction and optimization, thereby improving the efficiency of the CO2 capture process.
The technology of amine-based carbon dioxide (CO2) capture has been widely adopted for reducing CO2 emissions and mitigating global warming. The operation of an amine-based CO2 capture system is complicated and involves monitoring over one hundred process parameters and careful manipulation of numerous valves and pumps. The monitoring and control of critical parameters of the process is an important task because it directly impacts plant performance and capture efficiency of CO2. In this study, artificial intelligence techniques were applied to develop a knowledge-based expert system that aims to effectively monitor and control the CO2 capture process, and thereby enhance CO2 capture efficiency.
The Knowledge-Based System for Carbon Dioxide Capture (KBSCDC) was implemented with DeltaV Simulate (trademark of Emerson Corp., USA). DeltaV Simulate provides control utilities and algorithms which support the configuration of control strategies in modular components.
The KBSCDC can conduct real-time monitoring and diagnosis, as well as suggest remedies for any abnormality detected. The expert system enhances performance and efficiency of the CO2 capture system because it supports automated diagnosis of the system should any abnormal conditions occur. The knowledge base of KBSCDC can be shared and reused, and can contribute to future study of the CO2 capture process.
The idea of using artificial intelligence for carbon dioxide capture was attempted by the scientists at the University of Regina as they published a paper on “An application of neuro-fuzzy technology for analysis of the CO2 capture process”.
The researchers primarily focused in the following two areas:
(1) Study of the behaviour of the conventional amine solvents and development of new or improved solvents with higher CO2 absorption capacities, faster CO2 reaction rates, higher degradation resistance, and lower heat consumption for regeneration.
(2) Selection of appropriate solvents for different applications to reduce the energy penalty. The objective of this study is to develop a knowledge-based expert system for monitoring and control of the CO2 capture process.
The expert system in this study was implemented on DeltaV Simulate (trademark of Emerson Corp., USA). The hierarchy of the DeltaV system includes five levels: plant area (level 1), module (level 2), algorithm (level 3), function block (level 4), and parameter (level 5). The plant areas are logical divisions of the process control system. A plant area consists of modules. Each module is a logic control entity to configure the control strategies. Function block diagrams (FBD) were used to continuously execute control strategies. The basic component of a FBD is a function block, which contains the control algorithm and defines the behaviour of the module. Each function block contains parameters that are the user-defined data utilized for performing its calculations and logic.
To develop the knowledge-based expert system for monitoring and control of the CO2 capture process, the Inferential Modelling Technique (IMT) was applied to analyze the domain knowledge and problem-solving techniques and a knowledge base was established.
The expert system helps to enhance system performance and CO2 capture efficiency by dramatically reducing the time for problem diagnosis and resolution when abnormal operating conditions occur. The expert system can be used as a decision-support tool for inexperienced operators for controlling the plant and can be used for training novice operators.
However, there are two disadvantages in the expert system in its current version. Since there are sixteen components involved in the CO2 capture process, an abnormal condition can be caused by incorrect performance of more than one component or parameter. However, the system in its current version can only deal with abnormal operation of one component at a time. Moreover, the knowledge captured for the diagnosis and system control represents the problem-solving expertise of only one expert operator.
Since the expert system developed is in an infant stage, further research on the same will help in addressing these setbacks.