Model Predictive Control

Pages 18 (4518 words)
Download 0
The detection and diagnosis of abnormal conditions in industrial plants is important for several reasons that include reducing variability in product quality, detecting equipment wear or instrument malfunction, and ensuring plant safety. Large industrial plants commonly store thousands of process variables as often as every second in historical databases.


By having access to data for several previous occurrences, it is more likely that a person familiar with the process can discern important patterns and identify the underlying cause(s) for the abnormal condition. Suppose that it is desired to analyze an abnormal condition, which is represented by multivariate time-series data for key process variables (e.g., measurements of controlled and manipulated variables for several interacting control loops). The objective is to locate similar, previous episodes (if they exist) in a large historical database, using an unsupervised learning technique. The proposed method does not require a process model, training data, or planned experiments. Instead, the analysis is based on historical operating data, which may be compressed
Chemical manufacturing processes present many challenging control problems, including: nonlinear dynamic behaviour; multivariable interactions between manipulated and controlled variables; unmeasured state variables; unmeasured and frequent disturbances; high-order and distributed processes; uncertain and time-varying parameters; unmodelled dynamics; constraints on manipulated and state variables; and (variable) dead time on inputs and measurements. ...
Download paper
Not exactly what you need?