Probabilistic reasoning in intelligent systems: networks of plausible inference
Probabilistic reasoning in intelligent systems: networks of plausible inference
Soft Sensors for Monitoring and Control of Industrial Processes (Advances in Industrial Control)
Soft Sensors for Monitoring and Control of Industrial Processes (Advances in Industrial Control)
Probabilistic Virtual Sensor for On-line Viscosity Estimation
MICAI '08 Proceedings of the 2008 Seventh Mexican International Conference on Artificial Intelligence
The WEKA data mining software: an update
ACM SIGKDD Explorations Newsletter
Evaluating probabilistic models learned from data
MICAI'11 Proceedings of the 10th international conference on Artificial Intelligence: advances in Soft Computing - Volume Part II
| Hi-index | 0.00 |
Fuel oil viscosity is an important parameter in the control of combustion in power plants. If the viscosity is optimal at the entrance of the boiler, then the combustion is optimal causing a minimum of contamination and a maximum of efficiency. Hardware viscosimeters are expensive and difficult to operate. Laboratory analyses calculate the viscosity based on chemical analysis but not in real time. This paper describes the development of a virtual sensor that utilizes artificial intelligence (AI) techniques for the construction of models. The models are used to estimate the viscosity based on related measurements concerning the combustion in a power plant. A probabilistic model is constructed using automatic learning algorithms and an analytical model is defined using physical principles and chemical analysis. Sensor fusion is applied to estimate the on-line value of the fuel viscosity. The virtual sensor is being installed in the Tuxpan power plant in Veracruz, Mexico.