Intelligent Systems in Process Control
Overview of successful application areas for intelligent systems in process control
The following are proven successful application areas for a Knowledge-Based Expert System (KBES):
• Fault diagnosis: detection, root cause analysis, repetitive problem recognition
• Supervisory control
• Complex control schemes
• Recovery from extreme conditions
• Emergency shutdown
• Heuristic optimization, e.g., debottlenecking
• Startup or shutdown monitoring
• Batch phase transition detection and subsequent control mode switching
• Process and control performance monitoring
• Statistical Process Control (SPC)
• Real Time Quality Management (combination of the above)
• Online "smart" operator and troubleshooting manual
• Sequential or batch control
• Control system validation
• Object-oriented simulation of processes and control systems
Other applications have been successful as well.
A survey paper of knowledge-based systems in process control
The survey paper below was presented by Greg Stanley as the plenary session for an IFAC (International Federation of Automatic Control) conference. It is a summary of the state of the art in applying real-time knowledge-based systems (Artificial Intelligence & expert systems) in process control. After a brief overview of the features of a Knowledge-Based Expert System (KBES) useful in industrial control, several case studies are reviewed. The lessons learned are summarized.
Experiences Using Knowledge-Based Reasoning in Online Control Systems (pdf)
Expert system requirements to meet the needs of process control
The G2 product by Gensym is the most popular real time expert system used by the process industries and others. The following technical paper by Moore, Rosenof, and Stanley describes the requirements and issues addressed by a real time expert system: Process Control Using a Real Time Expert System (pdf)
BDAC - Big Data Approximating Control
In more recent years, there has been substantial progress in machine learning, pattern recognition, and dealing with large volumes and varieties of of data. A new technical paper by Stanley outlines an entirely new method of process estimation and control based on approximate pattern matching. An overview and references are found in the section on Big Data Approximating Control.
|
