Adaptive Single Neuron Anti-Windup PID Controller Based on the Extended Kalman Filter Algorithm
In this paper, an adaptive single neuron Proportional–Integral–Derivative (PID) controller based on the extended Kalman filter (EKF) training algorithm is proposed. The use of EKF training allows online training with faster learning and convergence speeds than backpropagation training method. Moreov...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-04-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/9/4/636 |
| _version_ | 1797570846246567936 |
|---|---|
| author | Jesus Hernandez-Barragan Jorge D. Rios Alma Y. Alanis Carlos Lopez-Franco Javier Gomez-Avila Nancy Arana-Daniel |
| author_facet | Jesus Hernandez-Barragan Jorge D. Rios Alma Y. Alanis Carlos Lopez-Franco Javier Gomez-Avila Nancy Arana-Daniel |
| author_sort | Jesus Hernandez-Barragan |
| collection | DOAJ |
| description | In this paper, an adaptive single neuron Proportional–Integral–Derivative (PID) controller based on the extended Kalman filter (EKF) training algorithm is proposed. The use of EKF training allows online training with faster learning and convergence speeds than backpropagation training method. Moreover, the propose adaptive PID approach includes a back-calculation anti-windup scheme to deal with windup effects, which is a common problem in PID controllers. The performance of the proposed approach is shown by presenting both simulation and experimental tests, giving results that are comparable to similar and more complex implementations. Tests are performed for a four wheeled omnidirectional mobile robot. Tests show the superiority of the proposed adaptive PID controller over the conventional PID and other adaptive neural PID approaches. Experimental tests are performed on a KUKA<sup>®</sup> Youbot<sup>®</sup> omnidirectional platform. |
| first_indexed | 2024-03-10T20:32:12Z |
| format | Article |
| id | doaj.art-ac8d06716c4b4cafb8cfbf632b2d8f1d |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T20:32:12Z |
| publishDate | 2020-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-ac8d06716c4b4cafb8cfbf632b2d8f1d2023-11-19T21:22:06ZengMDPI AGElectronics2079-92922020-04-019463610.3390/electronics9040636Adaptive Single Neuron Anti-Windup PID Controller Based on the Extended Kalman Filter AlgorithmJesus Hernandez-Barragan0Jorge D. Rios1Alma Y. Alanis2Carlos Lopez-Franco3Javier Gomez-Avila4Nancy Arana-Daniel5Centro Universitario de Ciencias Exactas e Ingenierías, Universidad de Guadalajara, Blvd. Marcelino García Barragán 1421, Guadalajara C.P. 44430, Jalisco, MexicoCentro Universitario de Ciencias Exactas e Ingenierías, Universidad de Guadalajara, Blvd. Marcelino García Barragán 1421, Guadalajara C.P. 44430, Jalisco, MexicoCentro Universitario de Ciencias Exactas e Ingenierías, Universidad de Guadalajara, Blvd. Marcelino García Barragán 1421, Guadalajara C.P. 44430, Jalisco, MexicoCentro Universitario de Ciencias Exactas e Ingenierías, Universidad de Guadalajara, Blvd. Marcelino García Barragán 1421, Guadalajara C.P. 44430, Jalisco, MexicoCentro Universitario de Ciencias Exactas e Ingenierías, Universidad de Guadalajara, Blvd. Marcelino García Barragán 1421, Guadalajara C.P. 44430, Jalisco, MexicoCentro Universitario de Ciencias Exactas e Ingenierías, Universidad de Guadalajara, Blvd. Marcelino García Barragán 1421, Guadalajara C.P. 44430, Jalisco, MexicoIn this paper, an adaptive single neuron Proportional–Integral–Derivative (PID) controller based on the extended Kalman filter (EKF) training algorithm is proposed. The use of EKF training allows online training with faster learning and convergence speeds than backpropagation training method. Moreover, the propose adaptive PID approach includes a back-calculation anti-windup scheme to deal with windup effects, which is a common problem in PID controllers. The performance of the proposed approach is shown by presenting both simulation and experimental tests, giving results that are comparable to similar and more complex implementations. Tests are performed for a four wheeled omnidirectional mobile robot. Tests show the superiority of the proposed adaptive PID controller over the conventional PID and other adaptive neural PID approaches. Experimental tests are performed on a KUKA<sup>®</sup> Youbot<sup>®</sup> omnidirectional platform.https://www.mdpi.com/2079-9292/9/4/636neuron PIDKalman filteringomnidirectional mobile robotimplementationsanti-windup |
| spellingShingle | Jesus Hernandez-Barragan Jorge D. Rios Alma Y. Alanis Carlos Lopez-Franco Javier Gomez-Avila Nancy Arana-Daniel Adaptive Single Neuron Anti-Windup PID Controller Based on the Extended Kalman Filter Algorithm Electronics neuron PID Kalman filtering omnidirectional mobile robot implementations anti-windup |
| title | Adaptive Single Neuron Anti-Windup PID Controller Based on the Extended Kalman Filter Algorithm |
| title_full | Adaptive Single Neuron Anti-Windup PID Controller Based on the Extended Kalman Filter Algorithm |
| title_fullStr | Adaptive Single Neuron Anti-Windup PID Controller Based on the Extended Kalman Filter Algorithm |
| title_full_unstemmed | Adaptive Single Neuron Anti-Windup PID Controller Based on the Extended Kalman Filter Algorithm |
| title_short | Adaptive Single Neuron Anti-Windup PID Controller Based on the Extended Kalman Filter Algorithm |
| title_sort | adaptive single neuron anti windup pid controller based on the extended kalman filter algorithm |
| topic | neuron PID Kalman filtering omnidirectional mobile robot implementations anti-windup |
| url | https://www.mdpi.com/2079-9292/9/4/636 |
| work_keys_str_mv | AT jesushernandezbarragan adaptivesingleneuronantiwinduppidcontrollerbasedontheextendedkalmanfilteralgorithm AT jorgedrios adaptivesingleneuronantiwinduppidcontrollerbasedontheextendedkalmanfilteralgorithm AT almayalanis adaptivesingleneuronantiwinduppidcontrollerbasedontheextendedkalmanfilteralgorithm AT carloslopezfranco adaptivesingleneuronantiwinduppidcontrollerbasedontheextendedkalmanfilteralgorithm AT javiergomezavila adaptivesingleneuronantiwinduppidcontrollerbasedontheextendedkalmanfilteralgorithm AT nancyaranadaniel adaptivesingleneuronantiwinduppidcontrollerbasedontheextendedkalmanfilteralgorithm |