Deep Learning for Robust Adaptive Inverse Control of Nonlinear Dynamic Systems: Improved Settling Time with an Autoencoder

Alwan, Nuha A. S.; Hussain, Zahir M.

doi:10.3390/s22165935

Cited by 4 publications

(5 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This step may involve dividing the data into testing, validation and training sets and using techniques such as backpropagation to update the weights of the network [30]. There are different backpropagation algorithms [39], a few of which are presented in table 1.…”

Section: Work Methodologymentioning

confidence: 99%

A Comprehensive Overview on Performance of Cascaded Three Tank Level System using Neural Network Predictive Controller

Prasad

Kumar

Singh

2023

IJEER

View full text Add to dashboard Cite

A Neural Network Predictive Controller (NNPC) is a deep learning-based controller (DLC) that uses artificial neural networks (ANN) to predict the future behavior of a system and accordingly control its outputs. In this paper, an NNPC was used to predict the level of the three cascaded tank and then adjust the inputs as flow rate to maintain the desired level in the tank. A three-tank level system is a system consisting of three interconnected tanks used to store liquids. To achieve the desired level, the NNPC first collects data on system behavior, including inputs and outputs, and uses this data to train the neural network. The trained network was then used to make predictions about the future level of each tank and to generate control signals to adjust the inputs as needed. NNPC also incorporates feedback from the system to continuously refine its predictions and improve its control performance over time. The mean squared error (MSE) of different backpropagation training algorithms available in MATLAB deep learning toolbox were evaluated and presented. Based on the MSE and best validation, Levenberg Marquardt algorithm were used in NNPC controller for further step response tracking. Different performance metrics were evaluated and presented.

show abstract

Section: Work Methodologymentioning

confidence: 99%

A Comprehensive Overview on Performance of Cascaded Three Tank Level System using Neural Network Predictive Controller

Prasad

Kumar

Singh

2023

IJEER

View full text Add to dashboard Cite

show abstract

“…To address these limitations, there has been a growing interest in developing more advanced control strategies, such as deep learning controllers [7,11,12]. Deep learning controllers are based on artificial neural networks that can learn to model the process dynamics directly from data, without requiring a priori knowledge of the system [13,14]. This allows them to handle highly nonlinear and complex processes that may be difficult to model using classical control techniques.…”

Section: Introductionmentioning

confidence: 99%

“…Unlike classical controllers, which rely on fixed parameters and control strategies, deep learning controllers can adjust their control actions dynamically based on the current state of the process. This makes them more robust and flexible [14], which is particularly important for processes that are subject to unpredictable disturbances or changes in operating conditions.…”

Section: Introductionmentioning

confidence: 99%

“…Deep learning-based controllers have shown promising results in process control systems due to their ability to learn complex nonlinear relationships between input and output variables. An NN can be trained and used for function approximation to replace a conventional controller in a process control system [14]. The relevant recent works in the field of process control systems using neural networks (NN) and deep learning (DL) techniques include [13,[16][17][18][19][20][21], deep reinforcement learning-based controllers [11,18,[22][23][24][25] transfer learning based controller [26].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Performance analysis of various training algorithms of deep learning based controller

2023

View full text Add to dashboard Cite

Advances in artificial neural networks (ANN), specifically deep learning (DL), have widened the application domain of process control. DL algorithms and models have become quite common these days. The training algorithm is the most important part of an ANN that affects the performance of the controller. Training algorithms optimize the weights and biases of the ANN according to the input-output patterns. In this paper, the performance of different training algorithms was evaluated, analysed, and compared in a feed-forward backpropagation architecture. The training algorithms were simulated on MATLAB R2021b with license number 1075356. Training data were generated using two benchmark problems of the process control system. The performance, gradient, training error, validation error, testing error, and regression of the different training algorithms were obtained and analysed. The data shows that the Levenberg-Marquardt (LM) algorithm produced the best validation performance with a value of 2.669*10−14 at 2000 epochs, while ‘traingd’ and ‘traingdm’ algorithms did not improve beyond their initial values. The LM algorithm tends to produce better results than other algorithms. These results indicate that the LM backpropagation best suits these types of benchmark problems. The results also suggest that the choice of training algorithm can significantly impact the performance of a neural network.

show abstract

“…The literature [25] presents a novel adaptive feedforward controller design for reset control systems. Furthermore, adaptive control has been applied in different fields and is used to study different objects [26,27].…”

Section: Introductionmentioning

confidence: 99%

An Adaptive Controller Design for Nonlinear Active Air Suspension Systems with Uncertainties

Zhang

Yang

2023

Mathematics

View full text Add to dashboard Cite

Active air spring suspensions can improve the vehicle ride comfort and meanwhile realize the vehicle height regulation, and therefore, they have been widely used and studied. However, to achieve better ride comfort and a satisfactory vehicle body height adjustment, the active air suspension controller becomes an indispensable and significant part of the system. Since the nonlinear suspension system possesses uncertainties, it is difficult to take into account both ride comfort and height regulation. This study innovatively proposes an adaptive control algorithm to specifically address the problem of vehicle height regulation and ride comfort for nonlinear active air suspension systems with uncertainties. The accurate tracking to reference vehicle body height curves is realized, and the ride comfort is also improved. Through simulations with two scenarios, it is illustrated that the active air suspension controller owns better control effectiveness than the PID controller. Compared with the PID controller, the designed controller can track the reference vehicle body height curves faster and more accurately. The result also verifies the priority of the designed controller.

show abstract

Deep Learning for Robust Adaptive Inverse Control of Nonlinear Dynamic Systems: Improved Settling Time with an Autoencoder

Cited by 4 publications

References 32 publications

A Comprehensive Overview on Performance of Cascaded Three Tank Level System using Neural Network Predictive Controller

A Comprehensive Overview on Performance of Cascaded Three Tank Level System using Neural Network Predictive Controller

Performance analysis of various training algorithms of deep learning based controller

An Adaptive Controller Design for Nonlinear Active Air Suspension Systems with Uncertainties

Contact Info

Product

Resources

About