Application of predictive control methods for Radio telescope disk rotation control
- 263 Downloads
Radio telescope (RT) installations are highly valuable assets and during the period of their service life they need regular repair and maintenance to be carried out for delivering satisfactory performance and minimizing downtime. Same down time can be expected during machinery usage. Constant control of telescope rotation angle is done manually using visual inspection of hardware. The accuracy of this procedure is very low, therefore, automation and computer control systems are required. With the growing automation technologies, predictive control can prove to be a better approach than the traditionally applied visual inspection policy and linear control models. In this paper, Irbene Radio telescope RT-16 disk rotation control motors are analysed using control voltage from the converters. Retrieved data from the small DC motor is used for the predictive control approach using two different methods: a neural network trained with Basic Levenberg-Marquardt method and a linear model. A multilayer perceptron network approach is used for prediction of the indicator voltage output which affects the monitoring of the disk rotating angle. Finally, an experimental control system was proposed and installed using National Instruments equipment.
KeywordsPredictive control Multi-layer perceptron Neural network Data processing
This work was supported by the European Regional Development Fund in the IT4Innovations Centre of Excellence project (CZ.1.05/1.1.00/02.0070) and by the Development of human resources in research and development of latest soft computing methods and their application in practice project (CZ.1.07/2.3.00/20.0072) funded by Operational Programme Education for Competitiveness, co-financed by ESF and state budget of the Czech Republic, also this work has been supported by the Latvia-Lithuania cross border cooperation programme within the project “JRTC Extension in Area of Development of Distributed Real-Time Signal Processing and Control Systems”, project code LLIV-215.
- Snasel V, Husek D, Frolov A, Rezankova H, Moravec P, Polyakov P (2007) Bars problem solving—new neural network method and comparison. Lect Notes Comput Sci 4827:671–682 Google Scholar
- Thimm G, Fiesler E (1996) Neural network pruning and pruning parameters. The 1st Online workshop on Soft ComputingGoogle Scholar