Sensitive boarder method for control performance indices adjustment

The aim of the paper is to introduce a new approach for the Regions of Required Quality (RRQ) construction under the Control Systems computer-aided analysis and design. Application of the Artificial Neural Networks (ANNs) as a tool in the proposed techniques is represented under the title “Method of Sensitive Border”. The developed Neural network model of the RRQ-region's border allows one to get more available information on the performance indices' behavior in the vicinity of the border. Calculation of recommended value for scanning step norm and performance indices gradient enclosed in the ANNs model (NDM) enables the use of the NDM-model as a source of important information under solving interpolation or extrapolation problems. As opposed to traditional approaches mostly based on approximations through preliminary stored and classified experimental data files, the Sensitive Boarder method exploits the NDM-model as an element of searching procedure via successive experimentation. The theoretical results were applied for the RRQ-regions construction with reference to 320 KW Synchronous Machine control. The obtained regions allowed one to define the best combinations of tunings for provision of the desired levels for appointed performance indices related to output voltage, frequency, power and system stability.