![](/images/graphics-bg.png)
Neural networks for optimal selection of the PID parameters and designing feedforward controller
Joint Authors
al-Raji, Ahmad S.
Bunny, Miss May N.
Source
Iraqi Journal of Computer, Communications and Control Engineering
Issue
Vol. 6, Issue 2 (30 Jun. 2006), pp.92-111, 20 p.
Publisher
Publication Date
2006-06-30
Country of Publication
Iraq
No. of Pages
20
Main Subjects
Topics
Abstract AR
أن الشبكة العصبیة أساس المسیطر التغـذیـة الأمامـیة Controller) (Feedforward Neural و المسیطر PID ذات التنغیم التلقائي مع الخوارزمیة المثالیة قدمت في ھذا البحث .أن ھیكلیة المسیطر المستخدم تتألف من نموذجین غیر معرفین یصفان المنظومة مع خوارزمیة المثلى هذان.(Modified Elman Neural Network & NARMA-L2) ھما النموذجین أن نموذجین یتعلما بمرحلتین (On-line & Off-line) لكي یضمن أن إخراج النموذج یمثل ألا خراج الحقیقي و بصورة دقیقة.
أن الھدف من النموذج (NARMA-L2) ھو أیجاد معكوس مسیطر التغذیة الأمامیة Inverse Feedforward Controller و الذي یتحكم بالاستجابة النھائیة للمنظومة .و یطلق على النموذج (Modified (Elman Neural Network) الناتج بعد التعلم "المعرف" (Identifier) و من المعرف و الخوارزمیة المثلیة یمكن حساب القیم المثلى للعناصر المسیطر PID و من ثم یمكن حساب إشارة التغذیة العكسیة لعدد (ن) من الخطوات اللاحقھ و لكل لحظھ من اجل السیطرة على الاستجابة العابرة للمنظومة عن طریق تقلیل معامل الأداء و ھو مربع الفرق بین ألا خراج المرغوب و إخراج النموذج إضافة إلى مربع إشارة السیطرة.
و تم شرح ھذه الخوارزمیة و اخذ مثال ذات تصرف لاخطي.
Abstract EN
A neural network-based feedforward controller and self-tuning PID controller with optimization algorithm is presented.
The scheme of the controller is based on two unknown models that describe the system and optimization algorithm.
These models are modified Elman recurrent neural network and NARMA-L2.
The modified Elman recurrent neural network (MERNN) model and NARMA-L2 model are learned with two stages off-line and on-line, in order to guarantee that the output of the model accurately represents the actual output of the system.
The aim from the NARMA-L2 model is to find the Inverse Feedforward Controller (IFC) which controls the steadystate output of the system.
The MERNN model after being learned is called the identifier.
The feedback PID self tuning control signal for N-step ahead can be calculated the PID parameters by using the optimization algorithm with the quadratic performance index which is quadratic in the error between the desired set point and the model output, as well as quadratic of the control action.
The paper explains the algorithm for a general case, and then a specific application on non-linear dynamical plant is presented.
American Psychological Association (APA)
al-Raji, Ahmad S.& Bunny, Miss May N.. 2006. Neural networks for optimal selection of the PID parameters and designing feedforward controller. Iraqi Journal of Computer, Communications and Control Engineering،Vol. 6, no. 2, pp.92-111.
https://search.emarefa.net/detail/BIM-442490
Modern Language Association (MLA)
al-Raji, Ahmad S.& Bunny, Miss May N.. Neural networks for optimal selection of the PID parameters and designing feedforward controller. Iraqi Journal of Computer, Communications and Control Engineering Vol. 6, no. 2 (2006), pp.92-111.
https://search.emarefa.net/detail/BIM-442490
American Medical Association (AMA)
al-Raji, Ahmad S.& Bunny, Miss May N.. Neural networks for optimal selection of the PID parameters and designing feedforward controller. Iraqi Journal of Computer, Communications and Control Engineering. 2006. Vol. 6, no. 2, pp.92-111.
https://search.emarefa.net/detail/BIM-442490
Data Type
Journal Articles
Language
English
Notes
Includes appendices : p. 104-111
Record ID
BIM-442490