BP neural network tuned PID controller for position tracking of a pneumatic artificial muscle

Fan, Jizhuang; Zhong, Jun; Zhao, Jie; Zhu, Yanhe

doi:10.3233/thc-150958

Cited by 36 publications

(10 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The input and output of the output layer are as follows. (27) where ω In order to reduce the deviation between the expected value and the actual sample value, the performance index function is selected as the criterion of the BP neural network correction weight coefficient [27], and the index function is expressed as follows.…”

Section: ) Design Of Bp-pid Control Algorithm A: Forward Propagationmentioning

confidence: 99%

Variable Pitch Active Disturbance Rejection Control of Wind Turbines Based on BP Neural Network PID

et al. 2020

View full text Add to dashboard Cite

When wind speeds are above the rated speed of variable speed variable pitch wind turbines, pitch angles are changed to keep output powers and rotor speeds at their rated values. For wind turbines with nonlinear and complex structure, conventional PID variable pitch controller is difficult to achieve precise control. In this paper, a variable pitch controller combining back-propagation(BP) neural network with PID (BP-PID) is proposed. By real-time detecting the deviation of the rotor speeds, the BP neural network with self-learning and weighting coefficient correction capability is used to adjust the PID parameters online and further to achieve the optimal combination of the PID parameters. Considering various uncertain disturbances and parameter changes on the mechanical components of the wind turbines, an active disturbance rejection pitch controller of the wind turbines is designed based on BP-PID algorithm. Combined with a tracking differentiator, an extended state observer (ESO) is employed to observe the state and disturbance of the system. In addition, in order to compensate the BP-PID variable pitch controller, nonlinear state error feedback control laws are designed by configuring nonlinear structures according to the state deviation between the extended state observer and the tracking differentiator. The simulation results show that the variable pitch active disturbance rejection control (ADRC) based on BP-PID can effectively estimate the system states and disturbances. And the proposed controller has good dynamic performance and strong robustness. INDEX TERMS Wind turbine, pitch control, BP-PID, active disturbance rejection control, extended state observer.

show abstract

Section: ) Design Of Bp-pid Control Algorithm A: Forward Propagationmentioning

confidence: 99%

Variable Pitch Active Disturbance Rejection Control of Wind Turbines Based on BP Neural Network PID

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The experimental modeling of PAM has been carried out by Ganguly et al [6] and many other researchers. On the other hand the phenomenological model of PAM has been developed by many researchers such as Fan et al [7] etc. Various researchers have developed a number of control strategies for PAM, which can be broadly categorized as follows: PID control; Nonlinear PID control; Neural network control; Fuzzy logic control; Neuro -Fuzzy control; Adaptive control; Impedance control; Hybrid control; Sliding mode control; Cascaded Control;…”

Section: Figure 1: Inflation and Deflation Conditions Of Pammentioning

confidence: 99%

“…The sliding mode control was adopted by Yang and Lilly [14] etc. The cascaded control strategy was explored by Fan et al [7] etc. The Control strategies for safe human interaction have been formulated by Choi et al [15] etc.…”

Section: Figure 1: Inflation and Deflation Conditions Of Pammentioning

confidence: 99%

Modeling and Controller Design for Pneumatic Artificial Muscle for Ankle-Foot Orthotic Device

Kumar,

Tewari

2019

IJEAT

View full text Add to dashboard Cite

In the present era Electric motors are most commonly used actuators for various robotic and bio-robotic applications. However, the functioning of electric motor is not similar to human skeletal muscles. Also, the electric motors are prone to harm human beings in case of failure. Hence, the present work has focused on exploring a bio-inspired actuator, which functions similar to human skeletal muscles and is safe for human beings. The literature review has revealed that such an actuator is pneumatic artificial muscle (PAM). In the present work the researchers have focused on developing an efficient model and control strategy for PAM in order to use it for biorobotic applications. An experimental setup has been prepared to analyze the behavior of PAM for different speeds of operation and different loading conditions during inflation/ deflation. Based on the experimental datasets an experimental model of PAM and Proportional Pressure Regulator (PPR) has been developed using polynomial curve fitting tool of MATLAB. Then a switched mode feedback PID control strategy has been developed for PAM which takes care for the hysteresis behavior of PAM. The control strategy has been simulated to achieve the trajectory angle tracking of ankle joint during the complete gait cycle. The simulation of the proposed control strategy with the developed model has shown that the proposed approach works fairly well and the error in the ankle joint movement could be limited in the range of -0.8° to 0.6° for the complete gait cycle. The result obtained in the present study is similar to the results as reported in the literature. However, this could be achieved with less system complexity using simpler modeling technique and “switched mode feedback PID controller”, which has not been reported by any researcher till date

show abstract

“…For the DDC method, the controller is designed directly using online or offline input/output data of the controlled system without employing the mathematical model of the controlled plant. Examples of DDC algorithms are PID control (Fan et al, 2015), neural network nonlinear control (Chiang & Chen, 2017), fuzzy control (Jiang et al, 2015), model-free adaptive control (Ahmed, Wang & Yang, 2018) and data-driven predictive control. Although MBC ensures a higher positioning precision for PAM applications compared to DDC, its design process requires that the system be modelled and that there be an adequate knowledge of control theory, making it difficult for engineers who are unacquainted with the modeling and controller design to implement and make the controller impracticable for realtime systems.…”

Section: Introductionmentioning

confidence: 99%

Real-Time Implementation of Data-Driven Predictive Controller for an Artificial Muscle

Kaplanoğlu¹,

Akgün²,

Ülkir³

2019

STUD INFORM CONTROL

View full text Add to dashboard Cite

This study presents a position tracking control method, with reference to Data-Driven Predictive Controller (DDPC), for a Pneumatic Artificial Muscle (PAM) system. The design of predictive controller is created from the subspace identification matrices acquired by input/output data. The control scheme is entirely data-based without explicit use of a model in the control application that can rectify the nonlinearity and uncertainties of the PAM. Firstly, subspace matrices are developed employing the identification method as a predictor by using open-loop experiments. Secondly, the estimated subspace matrices are used to design the so-called DDPC. In this instance, the quadratic programming (QR) decomposition method is used to obtain the prediction matrices. Consequently, experiments are carried out by the PAM actuator with different testing and loading conditions. The real-time experimental results demonstrate the feasibility and efficiency of the suggested control approach for nonlinear systems.

show abstract

BP neural network tuned PID controller for position tracking of a pneumatic artificial muscle

Cited by 36 publications

References 21 publications

Variable Pitch Active Disturbance Rejection Control of Wind Turbines Based on BP Neural Network PID

Variable Pitch Active Disturbance Rejection Control of Wind Turbines Based on BP Neural Network PID

Modeling and Controller Design for Pneumatic Artificial Muscle for Ankle-Foot Orthotic Device

Real-Time Implementation of Data-Driven Predictive Controller for an Artificial Muscle

Contact Info

Product

Resources

About