Kalman Filter Based Controlled Online System Identification
Journal Title: Журнал інженерних наук - Year 2018, Vol 5, Issue 2
Abstract
In the development of model predictive controllers a significant amount of time and effort is necessary for the development of the empirical control models. Even if on-line measurements are available, the control models have to be estimated carefully. The payback time of a model predictive controller could be significantly reduced, if a common identification tool would be available which could be introduced in a control scheme right away. In this work it was developed a control system which consists of a neural network (NN) with external recurrence only, whose parameters are adjusted by the extended Kalman filter in real-time. The output of the neural network is used in a control loop to study its accuracy in a control loop. At the moment this control loop is a NN-model based minimum variance controller. The on-line system identification with controller was tested on a simulation of a fed-batch penicillin production process to understand its behaviour in a complex environment. On every signal process and measurements noise was applied. Even though the NN was never trained before, the controller did not diverge. Although it seemed like the on-line prediction of the NN was quite accurate, the real process was not learned yet. This was checked by simulating the process with the NN obtained at the end of the batch. Nevertheless the process was maintained under control near the wanted set-points. These results show a promising start for a model predictive controller using an on-line system identification method, which could greatly reduce implementation times.
Authors and Affiliations
E. N. Ganesh
Keywords
Related Articles
- EP ID EP416416
- DOI 10.21272/jes.2018.5(2).e5
- Views 61
- Downloads 0
Efficiency Analysis of Tracking and Stationary Solar Panel Modes Against Solar Radiation
The utilization of solar energy sources is done by using photovoltaic (solar panels). The energy emitted by the sun is fluctuating. This change in radiation energy will also affect the output of solar panels. The relatio...
Increasing the Speed of Fractal Image Compression Using Two-Dimensional Approximating Transformations
Fractal image compression algorithm is known for allowing very high compression rates (the best examples – up to 1 000 times with acceptable visual quality) for real photos of natural objects, which is not possible for o...
Directions of the environmental protection processes optimization at heat power engineering enterprises
The article observes the impact factors of heat power engineering enterprises on the environment and ways of anthropogenic impact reduction during the application of ecological security control technological methods. The...
Theoretical research of some parameters of contact area of wheel cutting surface and workpiece at flat face grinding with preliminary inclination of spindle axis
Theoretical researches that have made it possible to obtain the analytical dependences connecting the parameters of contact area of wheel cutting surface such as length, width, arc length, form deviation of flat surface...
Polymeric compositional materials based on polycarbonate for units of devices for transform solar into thermal energy
Modern development of the industry is complicated without introduction of energy-saving technologies based on renewable natural energy sources. Solar and wind power plants, heat generators, solar collectors are wide spre...