Embodiments are directed to computer methods and systems that construct a calibrated operation-centric first-principles model suitable for online deployment to monitor, predict, and control real-time plant operations. The methods and systems identify a plant- wide first-principles model configured for offline use and select a modeled operating unit contained in the plant- wide model. The methods and systems convert the plant- wide model to an operation-centric first-principles model of the selected modeled operating unit. The methods and systems recalibrate the operation-centric model to function using real-time measurements collected by physical instruments of the operating unit at the plant. The recalibration may include reconciling flow and temperature, estimating feed compositions, and tuning liquid and vapor traffic flow in the model. The methods and systems deploy the operation-centric model to calculate KPIs using real-time measurements and employ the KPIs to automatically (by a processor) predict and control behavior of the physical operating unit at the plant.

Computer system and method for the dynamic construction and online deployment of an operation-centric first-principles process model for predictive analytics

Computer-based process modeling and simulation methods and systems combine first principles models and machine learning models to benefit where either model is lacking. In one example, input values (measurements) are adjusted by first principles techniques. A machine learning model of the chemical process of interest is trained on the adjusted values. In another example, a machine learning model represents the residual (delta) between a first principles model prediction and empirical data. Residual machine learning models correct physical phenomena predictions in a first principles model of the chemical process. In another example, a first principles simulation model uses the process input data and predictions of the machine learning model to generate simulated results of the chemical process. The hybrid models enable a process engineer to troubleshoot the chemical process, enable debottlenecking the chemical process, enable optimizing performance of the chemical process at the subject industrial plant, and enable automated process control.

Combining Machine Learning With Domain Knowledge And First Principles For Modeling In The Process Industries

Development of Smart Grid requires power plants to be more intelligent, efficient, and reliable, which raises new challenges of the control system design for modern power plants. Regarding these requirements, an integrated multi-task control system using artificial intelligence technologies is proposed to improve the efficiency and reliability of a hybrid fuel-cell with gas turbine power plant. The integrated control system consists of a hybrid Neural Network plant model with online learning ability, an Optimal Reference Governor generating optimal setpoints as local control references, and a Fault Diagnosis and Accommodation system to detect internal plant faults and to regulate the plant during plant failures. The three subsystems are integrated to provide compressive management for the power plant. The hybrid fuel-cell power plant is introduced; the structure and strategies of the control system are discussed, and simulation results are presented.

Wenli Yang

Papers

An integrated multi-task control system for fuel-cell power plants