|
|
|
|
gmdh neural network-based enhanced data-driven adaptive control design for unknown nonlinear systems in the presence of quantized data.
|
|
|
|
|
|
|
|
نویسنده
|
mir mohammadreza ,maghfoori farsangi malihe ,asadi yasin ,mollaie emamzadeh mohammad
|
|
منبع
|
مهندسي برق دانشگاه تبريز - 2025 - دوره : 55 - شماره : 1 - صفحه:133 -144
|
|
چکیده
|
This research paper presents a new approach to controlling unknown nonlinear systems using the group method of data handling (gmdh) neural network. the proposed enhanced data-driven quantized model-free adaptive control structure addresses the challenge of data quantization in data-driven control systems, which results from data loss and affects the performance of the model-free adaptive control (mfac). in this study, the output quantized data is fed to the gmdh block, which derives a model to estimate the system's actual output based on the predictive feature of the network. the controller generates the input control signal based on the estimated output data. the stability analysis of the proposed control structure has been investigated through the lyapunov theory. the proposed structure has been tested and compared against the traditional mfac controller through simulation. the results illustrate the proposed approach's advantages in overcoming data quantization challenges in data-driven control methods.
|
|
کلیدواژه
|
data-driven control ,mfac method ,gmdh neural network ,data quantization
|
|
آدرس
|
shahid bahonar university of kerman, department of electrical engineering, iran, shahid bahonar university of kerman, department of electrical engineering, iran, shahid bahonar university of kerman, department of electrical engineering, iran, shahid bahonar university of kerman, department of electrical engineering, ایران
|
|
پست الکترونیکی
|
molaie@uk.ac.ir
|
|
|
|
|
|
|
|
|
|
|
|
|
|
gmdh neural network-based enhanced data-driven adaptive control design for unknown nonlinear systems in the presence of quantized data.
|
|
|
|
|
Authors
|
mir mohammadreza ,maghfoori farsangi malihe ,asadi yasin ,mollaie emamzadeh mohammad
|
|
Abstract
|
this paper proposes an enhanced data-driven quantized model-free adaptive control (edd-qmfac) structure for a class of unknown nonlinear systems based on the group method of data handling (gmdh) neural network. in this study, the output quantized data is given to the gmdh block to overcome the data quantization challenges in data-driven control methods. in the proposed control loop the gmdh derives a model to estimate the actual output of the system from the quantized output data based on the predictive feature of this network. the controller then generates the input control signal based on the system’s estimated actual output data. the lyapunov theory is used to prove the stability of the suggested structure. the simulation results demonstrate the advantages of the proposed control structure over the conventional qmfac.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|