Neural Network-Based Model Predictive Control: Fault Tolerance and Stability

Patan, Krzysztof

doi:10.1109/tcst.2014.2354981

Cited by 88 publications

(48 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Indeed, it has been shown that there is no need for

false‖ bold-italicε {false‖}_{boldq}^{2}

to be equal to zero, as assumed in the work of Emami and Rezaeizadeh . The details of determining the terminal constraints in the stable MPC structures can be found in the works of Mayne et al It should be noted that the introduced terminal constraint in this paper is less conservative than the usual terminal constraints in conventional MPCs …”

Section: Trajectory Tracking Controlmentioning

confidence: 94%

“…Neural networks have been used in several FTC schemes thanks to their unique capabilities in modeling and identifying faulty systems. A NN‐based fault‐tolerant MPC has been proposed in the work of Patan . A NN‐based prediction model was proposed and the faults were detected using a multivalued diagnostic matrix, which uses the relations between symptoms and faults.…”

Section: Introductionmentioning

confidence: 99%

“…A NN-based fault-tolerant MPC has been proposed in the work of Patan. 15 A NN-based prediction model was proposed and the faults were detected using a multivalued diagnostic matrix, which uses the relations between symptoms and faults. However, use of such an approach may lead to incorrect FD in some cases as discussed in the paper.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Intelligent trajectory tracking of an aircraft in the presence of internal and external disturbances

Emami

Banazadeh

2019

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

Summary This research deals with developing an intelligent trajectory tracking control approach for an aircraft in the presence of internal and external disturbances. Internal disturbances including actuators faults, unmodeled dynamics, and model uncertainties as well as the external disturbances such as wind turbulence significantly affect the performance of the common trajectory tracking control approaches. There are several fault‐tolerant control approaches in the literature to overcome the effects of specific actuator or sensor faults during the flight. However, trajectory tracking control of an air vehicle in the presence of unexpected faults and simultaneous presence of wind turbulence is still a challenging problem. In this paper, an intelligent neural network‐based model predictive control structure is proposed, where the prediction model is updated in each iteration based on a novel proposed online sequential multimodel structure. A hybrid offline‐online learning algorithm is adopted in the introduced online sequential multimodel structure to identify the time‐varying dynamics of the system. The proposed control structure can satisfactorily deal with unexpected actuator faults and structural damages as well as unmodeled dynamics and wind turbulence. The stability of the closed‐loop system is proved under some realistic assumptions. The simulation results demonstrate the high capability of the proposed approach for trajectory tracking control of a conventional aircraft in the simultaneous presence of system faults and external disturbances.

show abstract

“…Indeed, it has been shown that there is no need for

false‖ bold-italicε {false‖}_{boldq}^{2}

Section: Trajectory Tracking Controlmentioning

confidence: 94%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Intelligent trajectory tracking of an aircraft in the presence of internal and external disturbances

Emami

Banazadeh

2019

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

show abstract

“…Two ANNs are used in the control loop of a DC motor drive, in which one network is used to estimate the drive dynamics and the other is used to generate voltage input signals to the drive. Different applications of ANNs in engineering include system identification, fault detection and power electronics applications, among others [13]- [15].…”

Section: Introductionmentioning

confidence: 99%

Back-EMF Based Rotor Position Estimation for Low Cost PMSM Drive Using Fully Connected Cascade Artificial Neural Networks

Negri¹,

Nazário²,

Oliveira³

et al. 2017

Eletrônica de Potência

View full text Add to dashboard Cite

-Permanent Magnet Synchronous Motors (PMSMs) are widely used mainly due to their high torque per volume, high efficiency and low maintenance cost, among other advantages. To perform vector control on rotor speed and stator currents, the feedback of those variables is necessary, which can be done directly or by estimation. Measuring rotor position and speed directly requires the use of a mechanical device attached to the motor shaft, increasing the drive system volume and its maintenance cost. To overcome such disadvantages, many sensorless methods for speed estimation have been proposed. Among those methods, various strategies based on Artificial Neural Networks (ANNs) can be found. This paper presents a back-electromotive force estimator based on Fully Connected Cascade ANNs (FCC-ANNs). From the estimator, rotor position and speed can be obtained. Simulation and experimental results using automatically generated C code functions for the FCC-ANNs using fixed point notation provided rotor position estimation with simple implementation.

show abstract

“…Nowadays, the most popular approach is model-based. One of the tools which are extensively exploited in this task are Artificial Neural Networks (ANN) [1,11,12]. Such model can reflect dynamics of the plant very closely but not perfectly.…”

Section: Introductionmentioning

confidence: 99%

Robust Fault Detection by Means of Echo State Neural Network

Czajkowski

Patan

2015

Advances in Intelligent Systems and Computing

Self Cite

View full text Add to dashboard Cite

This paper deals with the application of Echo State Network (ESN) model to robust fault diagnosis of the Twin Rotor Aero-Dynamical System (TRAS) through modeling the uncertainty of the neural model with the so-called Model Error Modeling method (MEM). The work describes the modeling process of the plant and scenarios in which the system is under influence of the unknown fault. In such fault scenarios the ESN model together with MEM are used to form the uncertainty bands. If the system output exceeds the uncertain region the fault occurrence is signalized. All data used in experiments are collected from the TRAS through the Matlab/Simulink environment.

show abstract

Neural Network-Based Model Predictive Control: Fault Tolerance and Stability

Cited by 88 publications

References 20 publications

Intelligent trajectory tracking of an aircraft in the presence of internal and external disturbances

Intelligent trajectory tracking of an aircraft in the presence of internal and external disturbances

Back-EMF Based Rotor Position Estimation for Low Cost PMSM Drive Using Fully Connected Cascade Artificial Neural Networks

Robust Fault Detection by Means of Echo State Neural Network

Contact Info

Product

Resources

About