نُقدم في هذه المقالة طريقة، لإيجاد متحكم تكيّفيّ أمثل بالشكل المباشر للأنظمة الخطية
مستمرة الزمن، بدون معرفة المصفوفات الحركية للنظام. و تُوظف الطريقة المقترحة إحدى
تقنيات بحوث العمميات الذكية، و هي تقنية البرمجة الديناميكية التكيفية لحل معادلة ريكاتي
الجبرية بشكل تكراري، باستخدام معلومات مباشرة من الحالة و الدخل، و بدون الحاجة إلى
معرفة مُسبقة لحركيات النظام. و يُمكن بالإضافة لذلك إجراء كل التكرارات باستخدام
معلومات الحالة و الدخل ذاتها لمرات عديدة و على بعض الفترات الزمنية الثابتة. كما تم
في هذه المقالة تطوير خوارزمية عملية مباشرة، و تم تطبيقها لتصميم متحكم أمثل بمحرك
ديزل نفاث مع إعادة تدوير غاز العادم.
This paper presents a method for finding online adaptive optimal
controllers for continuous-time linear systems without knowing the
system dynamical matrices. The proposed method employs one of
Intelligent Operations Research Techniques, this technique is the
adaptive dynamic programming, to iteratively solve the algebraic
Riccati equation using the online information of state and input,
without requiring the a priori knowledge of the system dynamics. In
addition, all iterations can be conducted by using repeatedly the
same state and input information on some fixed time intervals. A
practical online algorithm is developed in this paper, and is applied
to the controller design for a turbocharged diesel engine with
exhaust gas recirculation.
References used
Al-Tamimi, A., Lewis, F. L., & Abu-Khalaf, M. (2007). Model-free Q-learning designs for linear discrete-time zero-sum games with application to H-infinity control. Automatica, 43(3), 473–481
(Baird, L.C.III. (1994). Reinforcement learning in continuous time: advantage updating. In Proceedings of IEEE international conference on neural networks. (pp.2448–2453
Bhasin, S., Sharma, N., Patre, P., & Dixon, W. E. (2011). Asymptotic tracking by a reinforcement learning-based adaptive critic controller. Journal of Control Theory and Applications, 9(3), 400–409
In this paper we consider the properties of linear systems by means of
directed graphs and numerical structures. We also state efficient algorithms
for determining an approximate number of the non-zero terms within
determinants' expressions of the
Earthmoving is the process of moving and processing soil from one location to another to alter an existing land surface into a desired configuration. Highways, dams, and airports are typical examples of heavy earthmoving projects. Over the years, con
This research tackles autolanding a power-off fixed-wing Unmanned Aerial Vehicle (UAV) on a
level or uphill landing strip with limited dimensions. New approaches to path planning, guidance,
and control are proposed for the final approach and landin
In this research, we investigate a problem of controllable and observerable for linear Continuous-time systems.
We have founded controllable and observerable conditions for the linear continuous-time system. Moreover, we put out a new algorithm for
In this paper, it has
merged two techniques of the artificial intelligent, they are the
ants colony optimization algorithm and the genetic algorithm, to
The recurrent reinforcement learning trading system
optimization. The proposed trading system