Neurocontrol Design for an Aerodynamics System: Simple Backpropagation Approach

Norsahperi, Nor Mohd Haziq; Danapalasingam, Kumeresan A.

doi:10.1007/978-981-13-6447-1_1

Cited by 3 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LQR control has been attracting several researchers to reduce energy consumption of the system by considering energy consumption of the systems, such as in [38]. The common quadratic performance index can be defined as: (19) where u CLQRT is the control signal of the LQRT, while Q LQRT and R LQRT are the symmetric positive definite state weighting matrices, respectively. However, as mentioned in [39], the conventional LQR controller cannot eliminate the steady-state error.…”

Section: Linear-quadratic Regulator With Integral Actionmentioning

confidence: 99%

See 1 more Smart Citation

A Comparative Study of LQR and Integral Sliding Mode Control Strategies for Position Tracking Control of Robotic Manipulators

Norsahperi

Danapalasingam

2020

Int. j. electr. comput. eng. syst. (Online)

Self Cite

View full text Add to dashboard Cite

This paper provides a systematic comparative study of position tracking control of nonlinear robotic manipulators. The main contribution of this study is a comprehensive numerical simulation assessing position tracking performances and energy consumption of integral sliding mode control (ISMC), a linear-quadratic regulator with integral action (LQRT ), and optimal integral sliding mode control (OISMC) under three conditions; namely, Case I) without the coupling effect, Case II) with the coupling effect on Link 1 only, and Case III) with the coupling effect on Link 2 only. The viability of the concept is evaluated based on three performance criteria, i.e., the step-response characteristics, position tracking error, and energy consumption of the aforementioned controllers. Based upon the simulation study, it has been found that OISMC offers performances almost similar to ISMC with more than 90% improvement of tracking performance under several cases compared to LQRT; however, energy consumption is successfully reduced by 3.6% in comparison to ISMC. Energy consumption of OISMC can be further reduced by applying optimization algorithms in tuning the weighting matrices. This paper can be considered significant as a robotic system with high tracking accuracy and low energy consumption is highly demanded to be implemented in smart factories, especially for autonomous systems.

show abstract

Section: Linear-quadratic Regulator With Integral Actionmentioning

confidence: 99%

“…Intelligent control offers an effective way to design a control system without a deep insight into the physical model of the system. However, the determination of its various parameters and complex rules is technically challenging and it relies on the designer's experience to construct an effective membership function [5,18,19].…”

Section: Introductionmentioning

confidence: 99%

A Comparative Study of LQR and Integral Sliding Mode Control Strategies for Position Tracking Control of Robotic Manipulators

Norsahperi

Danapalasingam

2020

Int. j. electr. comput. eng. syst. (Online)

Self Cite

View full text Add to dashboard Cite

show abstract

Tracking error control of robotic manipulator using optimal integral sliding mode control in the presence of external disturbances

Waseem

Ali

2023

2023 4th International Conference on Computing, Mathematics and Engineering Technologies (iCoMET)

View full text Add to dashboard Cite

Двухэтапная Процедура Синтеза Управления Нелинейными Нестационарными Объектами С Использованием Многослойного Персептрона

Фролов,

Синдеев,

Коробов

et al. 2020

Моделирование

View full text Add to dashboard Cite

Представлен обзор методов нейроуправления и анализ их достоинств и недостатков. Поставлена задача поиска квазиоптимальных настроечных параметров нейроуправления нелинейным нестационарным объектом при наличии случайных возмущений. Предложена процедура синтеза управления нелинейными нестационарными объектами с использованием многослойного персептрона, состоящая из двух этапов. На первом этапе решается задача робастного нейроуправления путем поиска вектора настроечных параметров алгоритма адаптации на основе предполагаемого множества вариантов модели объекта. Найденные настроечные параметры алгоритма адаптации используются на втором этапе – безмодельном нейроуправлении, на котором осуществляется поиск квазиоптимальных настроечных параметров алгоритма безмодельного нейроуправления. Устойчивость поиска настроечных параметров алгоритма безмодельного нейроуправления достигается за счет применения метода регуляризации. На основе модельного примера показана эффективность и устойчивость предложенной процедуры синтеза управления нелинейными нестационарными объектами. В численном эксперименте был выбран объект, описываемый нелинейным дифференциальным уравнением с коэффициентами, которые зависят от времени. На первом этапе было сформировано случайным образом 20 вариантов модели объекта, найдена архитектура нейронной сети, настроечные коэффициенты алгоритма адаптации. Нейронная сеть включает 2 нейрона во внутреннем слое и использует сигмоидальную функцию активации. На втором этапе проведены численные исследования процесса адаптивного управления. В результате работы алгоритма адаптации степень затухания переходных процессов превышает 50% и процесс управления является устойчивым при значительном отклонении параметров объекта от номинальных значений. Представленный метод является эффективным при управлении многосвязными нестационарными нелинейными объектами в робототехнике, в транспортных системах, химических производствах. The review of neurocontrol methods and analysis of their advantages and disadvantages is presented. The problem of searching of quasioptimal tuning parameters of neurocontrol for nonlinear non-stationary objects in the presence of random disturbances is formulated. A procedure for the synthesis of control for nonlinear non-stationary objects using a multi-layer perceptron, which consists of two stages, is presented. In the first stage the problem of finding a robust neurocontrol vector tuning parameters for adaptation algorithm based on the proposed set of variants of the model is solved. Founded tuning parameters for adaptation algorithm are used in the second stage - model-free neurocontrol, which searching for quasi-optimal tuning parameters for the algorithm of model-free neurocontrol. Stability of tuning parameters search procedure for the algorithm of model-free neurocontrol achieved by using the regularization method. Effectiveness and stability of the proposed procedure for the synthesis of control for nonlinear non-stationary objects are shown using the model example. In the numerical experiment, an object was chosen that was described by a nonlinear differential equation with coefficients that depend on time. At the first stage, 20 variants of the object model were randomly generated, the architecture of the neural network, the tuning coefficients of the adaptation algorithm were found. The neural network includes 2 neurons in the inner layer and uses a sigmoidal activation function. At the second stage, numerical studies of the adaptive control process were carried out. As a result of the adaptation algorithm, the degree of attenuation of transient processes exceeds 50% and the control process is stable with a significant deviation of the object's parameters from the nominal values. The presented method is effective for the control of multiply connected non-stationary nonlinear objects in robotics, transport systems, and chemical industries.

show abstract

Neurocontrol Design for an Aerodynamics System: Simple Backpropagation Approach

Cited by 3 publications

References 17 publications

A Comparative Study of LQR and Integral Sliding Mode Control Strategies for Position Tracking Control of Robotic Manipulators

A Comparative Study of LQR and Integral Sliding Mode Control Strategies for Position Tracking Control of Robotic Manipulators

Tracking error control of robotic manipulator using optimal integral sliding mode control in the presence of external disturbances

Двухэтапная Процедура Синтеза Управления Нелинейными Нестационарными Объектами С Использованием Многослойного Персептрона

Contact Info

Product

Resources

About