Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
413905 | Robotics and Computer-Integrated Manufacturing | 2007 | 10 Pages |
Abstract
With reference to a real industrial application of process control, some considerations are discussed concerning the accuracy of methods for auto-tuning of proportional, integral and derivative factor (PID). In particular, a theoretical–experimental approach is described, that allows to evaluate the adequateness of new methods for auto-tuning of PID, able to significantly reduce the time duration for auto-tuning with respect to traditional ones. This result has been achieved by using suitable techniques of experimental data processing, based on neural-networks algorithms, set for this specific application. The effect on described methodology of environmental and operating disturbances is also described.
Related Topics
Physical Sciences and Engineering
Computer Science
Artificial Intelligence
Authors
Giulio D’Emilia, Antonio Marra, Emanuela Natale,