Evaluation of Nonlinear Model-Based Predictive Control Approaches Using Derivative-Free Optimization and FCC Neural Networks

Negri, Gabriel H.; Cavalca, Mariana Santos Matos; Oliveira, José de; Araújo, Celso J. F.; Celiberto, Luiz A.

doi:10.1007/s40313-017-0327-x

Cited by 7 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To fit the kinetic parameters, the main species ( 1 , 2 , 3 , 7 ) concentrations at the FTIR measurement point were estimated and compared with the experimentally-measured values. The kinetic parameters were then tuned to minimize the quadratic error using the BOBYQA (bound optimization by quadratic approximation) 59 optimization algorithm, from the nonlinear optimization toolbox. Although several optimization algorithms were tested, this provided the best fit of the kinetic parameters and had a very low computational cost.…”

Section: Resultsmentioning

confidence: 99%

Dynamic experiments in flow accelerate reaction network definition in a complex hydrogenation using catalytic static mixers

Martinuzzi,

Tranninger,

Sagmeister

et al. 2024

React. Chem. Eng.

View full text Add to dashboard Cite

show abstract

Section: Resultsmentioning

confidence: 99%

Dynamic experiments in flow accelerate reaction network definition in a complex hydrogenation using catalytic static mixers

Martinuzzi,

Tranninger,

Sagmeister

et al. 2024

React. Chem. Eng.

View full text Add to dashboard Cite

show abstract

“…For a nonlinear prediction model, cost function and constraints, gradient‐based and gradient‐free methods can be applied. In the present work, the gradient‐free method BOBYQA was employed, using the Nlopt implementation, since it does not depend on the cost function derivatives . Such feature is desirable for a robot control framework because if the robot topology is changed, the cost function derivatives do not necessarily need to be algebraically obtained, but only the forward kinematics model will need to be adapted.…”

Section: Model Predictive Controlmentioning

confidence: 99%

Nonlinear predictive control applied to a biped walker with adjustable step length using a passive walking‐based reference generator

Negri

Rosa

Cavalca

et al. 2020

Optim Control Appl Methods

Self Cite

View full text Add to dashboard Cite

This paper presents the use of passive dynamics to generate the sagittal plane references for a biped walker. In order to achieve an adjustable gait width, a neural network reference generator, trained with passive walking data on different slopes, was applied. The control algorithm was implemented with an Nonlinear Model Predictive Control (NMPC) strategy, in order to perform multiple-input multiple-output reference tracking while maintaining balance. The main contributions of the present work are using a kneed passive walker model for reference generation, which creates gait profiles that are more natural than the compass gait model, presenting a low computational cost, since only the forward kinematic model is used, and enabling adjustable gait width, due to the use of a neural network trained with data from the passive walker. Simulation results using V-REP (Virtual Robot Experimentation Platform) are presented, using a sagittal kneed walker with a torso and arms, demonstrating the effectiveness of the proposed method.

show abstract

“…An RNN has a unique structure where the outputs from the previous step are fed into the current step, which makes it a good approximator for time series data. In addition, a fully connected cascade (FCC) network, which has direct connections from all input neurons to all output and hidden neurons, was applied by Negri et al [11] in MPC for pressure control of a water tank.…”

Section: Introductionmentioning

confidence: 99%

Fault compensation by online updating of genetic algorithm-selected neural network model for model predictive control

et al. 2019

View full text Add to dashboard Cite

This paper presents a methodology that combines a dual-net model and the model predictive control (MPC) to compensate degraded system performance caused by slow-paced faults/anomalies. The dual-net model is comprised of an offline and an online artificial neural networks (ANNs) along with a switch that selects one of them for MPC. Through selective online updating of weight parameters, the online ANN is able to accurately capture the fault-induced variations in system dynamics, and can be used for MPC reconfiguration and fault compensation. Specifically, the system dynamics is identified by training a multilayer perceptron (MLP). To improve the model accuracy, a meta-optimization approach based on the genetic algorithm is applied to optimize the MLP hyperparameters and the training algorithm. A dual-thread decision maker is proposed to manage the robust model updating scheme and the dual-net model switch. A case study of numerical simulation using an unmanned quadrotor is undertaken to verify the feasibility of the proposed method to mitigate performance degradation. Salient performance in the response prediction and control, subject to gradually growing anomaly is successfully demonstrated. Quantitatively, the proposed updating model outperforms the offline ANN model and yields 2× and 4× lower errors, respectively, for prediction and control of the system response.

show abstract

Evaluation of Nonlinear Model-Based Predictive Control Approaches Using Derivative-Free Optimization and FCC Neural Networks

Cited by 7 publications

References 26 publications

Dynamic experiments in flow accelerate reaction network definition in a complex hydrogenation using catalytic static mixers

Dynamic experiments in flow accelerate reaction network definition in a complex hydrogenation using catalytic static mixers

Nonlinear predictive control applied to a biped walker with adjustable step length using a passive walking‐based reference generator

Fault compensation by online updating of genetic algorithm-selected neural network model for model predictive control

Contact Info

Product

Resources

About