Knowledge-based prediction implementation

The chapters on establishing and maintaining a total plant predictive maintenance program will provide the practical knowledge required implementing a cost-effective vibration-based program that will provide maximum benefits. 

Since both the on-line dynamic optimization and the model-based control strategy rely on process models, the knowledge of current states and/or model parameters is required. However, in most industrial processes, state variables are not all measurable and some parameters are not known exactly. As a consequence, there is a need for estimating these states and parameters. In this work, two Extended Kalman Filters (EKF) are implemented. The first one is applied to predict the reactant concentration, which will be used for on-line dynamic optimization, from its delayed measurement. The other one is applied to estimate the unknown heat of reaction, which will be used for model-based controller, from the frequently available measurements of temperature. 

Armed with reasonably good knowledge or hypotheses of the underlying biochemistry and the ability to formulate models based on physico-chemical principles, the models must be implemented to obtain and analyze the quantitative results and to generate predictions. Except in very simple, idealized cases, this task requires the use of various numerical methods and tools. In this section, an overview of the various model types and associated methods is offered. 

---