Improved BP neural network based active disturbance rejection control for magnetic sensitivity calibration system

Minlin Wang; Xueming Dong; Xuemei Ren

doi:10.1109/DDCLS58216.2023.10167186

Improved BP neural network based active disturbance rejection control for magnetic sensitivity calibration system

Minlin Wang, Xueming Dong, Xuemei Ren

School of Automation

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In the magnetic sensitivity calibration system, the calibration accuracy of inertial sensor is directly related to the control accuracy of the magnetic induction intensity. Since the helmholtz coils in the calibration system have large parameter uncertainties and the magnetic field sensor has some time-delay, the traditional PID controller cannot satisfy the accuracy requirement of the magnetic induction intensity. Therefore, an improved neural network based active disturbance rejection controller (ADRC) is proposed, which utilizes the conjugate gradient algorithm and Fletcher-Reeves linear search method to adjust the parameters of ADRC for achieving the optimal control efforts. Moreover, the extended state observer of ADRC can compensate for the parameter uncertainties and time-delay exactly such that the control accuracy of the magnetic induction intensity can be largely improved. The simulations are conducted to show the effectiveness and superiority of the proposed control algorithm.

Original language	English
Title of host publication	Proceedings of 2023 IEEE 12th Data Driven Control and Learning Systems Conference, DDCLS 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1002-1007
Number of pages	6
ISBN (Electronic)	9798350321050
DOIs	https://doi.org/10.1109/DDCLS58216.2023.10167186
Publication status	Published - 2023
Event	12th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2023 - Xiangtan, China Duration: 12 May 2023 → 14 May 2023

Publication series

Name	Proceedings of 2023 IEEE 12th Data Driven Control and Learning Systems Conference, DDCLS 2023

Conference

Conference	12th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2023
Country/Territory	China
City	Xiangtan
Period	12/05/23 → 14/05/23

Keywords

ADRC
Fletcher-Reeves linear search method
conjugate gradient algorithm
magnetic sensitivity calibration system
neural network
parameter uncertainties and time-delay

Access to Document

10.1109/DDCLS58216.2023.10167186

Cite this

Wang, M., Dong, X., & Ren, X. (2023). Improved BP neural network based active disturbance rejection control for magnetic sensitivity calibration system. In Proceedings of 2023 IEEE 12th Data Driven Control and Learning Systems Conference, DDCLS 2023 (pp. 1002-1007). (Proceedings of 2023 IEEE 12th Data Driven Control and Learning Systems Conference, DDCLS 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/DDCLS58216.2023.10167186

Wang, Minlin ; Dong, Xueming ; Ren, Xuemei. / Improved BP neural network based active disturbance rejection control for magnetic sensitivity calibration system. Proceedings of 2023 IEEE 12th Data Driven Control and Learning Systems Conference, DDCLS 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 1002-1007 (Proceedings of 2023 IEEE 12th Data Driven Control and Learning Systems Conference, DDCLS 2023).

@inproceedings{159851d539a749b8b4161699c1fa856b,

title = "Improved BP neural network based active disturbance rejection control for magnetic sensitivity calibration system",

abstract = "In the magnetic sensitivity calibration system, the calibration accuracy of inertial sensor is directly related to the control accuracy of the magnetic induction intensity. Since the helmholtz coils in the calibration system have large parameter uncertainties and the magnetic field sensor has some time-delay, the traditional PID controller cannot satisfy the accuracy requirement of the magnetic induction intensity. Therefore, an improved neural network based active disturbance rejection controller (ADRC) is proposed, which utilizes the conjugate gradient algorithm and Fletcher-Reeves linear search method to adjust the parameters of ADRC for achieving the optimal control efforts. Moreover, the extended state observer of ADRC can compensate for the parameter uncertainties and time-delay exactly such that the control accuracy of the magnetic induction intensity can be largely improved. The simulations are conducted to show the effectiveness and superiority of the proposed control algorithm.",

keywords = "ADRC, Fletcher-Reeves linear search method, conjugate gradient algorithm, magnetic sensitivity calibration system, neural network, parameter uncertainties and time-delay",

author = "Minlin Wang and Xueming Dong and Xuemei Ren",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 12th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2023 ; Conference date: 12-05-2023 Through 14-05-2023",

year = "2023",

doi = "10.1109/DDCLS58216.2023.10167186",

language = "English",

series = "Proceedings of 2023 IEEE 12th Data Driven Control and Learning Systems Conference, DDCLS 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1002--1007",

booktitle = "Proceedings of 2023 IEEE 12th Data Driven Control and Learning Systems Conference, DDCLS 2023",

address = "United States",

}

Wang, M, Dong, X & Ren, X 2023, Improved BP neural network based active disturbance rejection control for magnetic sensitivity calibration system. in Proceedings of 2023 IEEE 12th Data Driven Control and Learning Systems Conference, DDCLS 2023. Proceedings of 2023 IEEE 12th Data Driven Control and Learning Systems Conference, DDCLS 2023, Institute of Electrical and Electronics Engineers Inc., pp. 1002-1007, 12th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2023, Xiangtan, China, 12/05/23. https://doi.org/10.1109/DDCLS58216.2023.10167186

Improved BP neural network based active disturbance rejection control for magnetic sensitivity calibration system. / Wang, Minlin; Dong, Xueming; Ren, Xuemei.
Proceedings of 2023 IEEE 12th Data Driven Control and Learning Systems Conference, DDCLS 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 1002-1007 (Proceedings of 2023 IEEE 12th Data Driven Control and Learning Systems Conference, DDCLS 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Improved BP neural network based active disturbance rejection control for magnetic sensitivity calibration system

AU - Wang, Minlin

AU - Dong, Xueming

AU - Ren, Xuemei

PY - 2023

Y1 - 2023

N2 - In the magnetic sensitivity calibration system, the calibration accuracy of inertial sensor is directly related to the control accuracy of the magnetic induction intensity. Since the helmholtz coils in the calibration system have large parameter uncertainties and the magnetic field sensor has some time-delay, the traditional PID controller cannot satisfy the accuracy requirement of the magnetic induction intensity. Therefore, an improved neural network based active disturbance rejection controller (ADRC) is proposed, which utilizes the conjugate gradient algorithm and Fletcher-Reeves linear search method to adjust the parameters of ADRC for achieving the optimal control efforts. Moreover, the extended state observer of ADRC can compensate for the parameter uncertainties and time-delay exactly such that the control accuracy of the magnetic induction intensity can be largely improved. The simulations are conducted to show the effectiveness and superiority of the proposed control algorithm.

AB - In the magnetic sensitivity calibration system, the calibration accuracy of inertial sensor is directly related to the control accuracy of the magnetic induction intensity. Since the helmholtz coils in the calibration system have large parameter uncertainties and the magnetic field sensor has some time-delay, the traditional PID controller cannot satisfy the accuracy requirement of the magnetic induction intensity. Therefore, an improved neural network based active disturbance rejection controller (ADRC) is proposed, which utilizes the conjugate gradient algorithm and Fletcher-Reeves linear search method to adjust the parameters of ADRC for achieving the optimal control efforts. Moreover, the extended state observer of ADRC can compensate for the parameter uncertainties and time-delay exactly such that the control accuracy of the magnetic induction intensity can be largely improved. The simulations are conducted to show the effectiveness and superiority of the proposed control algorithm.

KW - ADRC

KW - Fletcher-Reeves linear search method

KW - conjugate gradient algorithm

KW - magnetic sensitivity calibration system

KW - neural network

KW - parameter uncertainties and time-delay

UR - http://www.scopus.com/inward/record.url?scp=85166012136&partnerID=8YFLogxK

U2 - 10.1109/DDCLS58216.2023.10167186

DO - 10.1109/DDCLS58216.2023.10167186

M3 - Conference contribution

AN - SCOPUS:85166012136

T3 - Proceedings of 2023 IEEE 12th Data Driven Control and Learning Systems Conference, DDCLS 2023

SP - 1002

EP - 1007

BT - Proceedings of 2023 IEEE 12th Data Driven Control and Learning Systems Conference, DDCLS 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 12th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2023

Y2 - 12 May 2023 through 14 May 2023

ER -

Wang M, Dong X, Ren X. Improved BP neural network based active disturbance rejection control for magnetic sensitivity calibration system. In Proceedings of 2023 IEEE 12th Data Driven Control and Learning Systems Conference, DDCLS 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 1002-1007. (Proceedings of 2023 IEEE 12th Data Driven Control and Learning Systems Conference, DDCLS 2023). doi: 10.1109/DDCLS58216.2023.10167186

Improved BP neural network based active disturbance rejection control for magnetic sensitivity calibration system

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this