Provide PDF Format
PRCI PR-179-9131
- State of the Art Intelligent Control for Large Engines
- Report / Survey by Pipeline Research Council International, 09/01/1996
- Publisher: PRCI
$25.00$49.00
L51756e
Colorado State University
Need: Computers have become a vital part of the control of pipeline compressors and compressor stations. For many tasks, computers have helped to improve accuracy, reliability, and safety, and have reduced operating costs. Computers excel at repetitive, precise tasks that humans perform poorly - calculation, measurement, statistical analysis, control, etc. Computers are used to perform these type of precise tasks at compressor stations: engine / turbine speed control, ignition control, horsepower estimation, or control of complicated sequences of events during startup and/or shutdown. For other tasks, however, computers perform very poorly at tasks that humans find to be trivial. A discussion of the differences in the way humans and computer process information is crucial to an understanding of the field of artificial intelligence.
Benefit: In this project, several artificial intelligence/ intelligent control systems were examined: heuristic search techniques, adaptive control, expert systems, fuzzy logic, neural networks, and genetic algorithms. Of these, neural networks showed the most potential for use on large bore engines because of their ability to recognize patterns in incomplete, noisy data. Two sets of experimental tests were conducted to test the predictive capabilities of neural networks. The first involved predicting the ignition timing from combustion pressure histories; the best networks responded within a specified tolerance level 90% to 98.8% of the time. In the second experiment, neural networks were used to predict NOx, A/F ratio, and fuel consumption. NOx prediction accuracy was 91.4%, A/F ratio accuracy was 82.9%, and fuel consumption accuracy was 52.9%. This report documents the assessment of the state of the art of artificial intelligence for application to the monitoring and control of large-bore natural gas engines.
Result: Research conducted for this project and documented in this report have shown the ability to predict emissions levels through the use of neural networks to process combustion pressure - time histories. It has been proposed in this report that the results can be further improved through the combination of a neural network-based pattern classification system with an emissions-predicting network.
Colorado State University
Need: Computers have become a vital part of the control of pipeline compressors and compressor stations. For many tasks, computers have helped to improve accuracy, reliability, and safety, and have reduced operating costs. Computers excel at repetitive, precise tasks that humans perform poorly - calculation, measurement, statistical analysis, control, etc. Computers are used to perform these type of precise tasks at compressor stations: engine / turbine speed control, ignition control, horsepower estimation, or control of complicated sequences of events during startup and/or shutdown. For other tasks, however, computers perform very poorly at tasks that humans find to be trivial. A discussion of the differences in the way humans and computer process information is crucial to an understanding of the field of artificial intelligence.
Benefit: In this project, several artificial intelligence/ intelligent control systems were examined: heuristic search techniques, adaptive control, expert systems, fuzzy logic, neural networks, and genetic algorithms. Of these, neural networks showed the most potential for use on large bore engines because of their ability to recognize patterns in incomplete, noisy data. Two sets of experimental tests were conducted to test the predictive capabilities of neural networks. The first involved predicting the ignition timing from combustion pressure histories; the best networks responded within a specified tolerance level 90% to 98.8% of the time. In the second experiment, neural networks were used to predict NOx, A/F ratio, and fuel consumption. NOx prediction accuracy was 91.4%, A/F ratio accuracy was 82.9%, and fuel consumption accuracy was 52.9%. This report documents the assessment of the state of the art of artificial intelligence for application to the monitoring and control of large-bore natural gas engines.
Result: Research conducted for this project and documented in this report have shown the ability to predict emissions levels through the use of neural networks to process combustion pressure - time histories. It has been proposed in this report that the results can be further improved through the combination of a neural network-based pattern classification system with an emissions-predicting network.
Related Products
PRCI PR-3-41
Analysis of the Effects of High-Voltage Direct-Current Transmission Systems on Buried Pipelines..
$198.00 $395.00
