A New PID Neural Network Controller Design for Nonlinear Processes

Zribi, Akram; Chtourou, Mohamed; Djemel, Mohamed

doi:10.1142/s0218126618500652

Cited by 37 publications

(19 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another approach of bringing intelligent control methods into flight control is using artificial intelligence based versions of classical controllers. For instance, there is the PIDNN controller [40][41][42]. This controller is inspired by and based on the PID controller but consists of learning neurons that imitate the PID behaviour.…”

Section: Advanced Intelligent Control Methodsmentioning

confidence: 99%

“…The learning objective is to minimize the tracking error. In general, a PIDNN is a single-input-single-output (SISO) controller that can be extended to a MIMO controller, see [40,43]. Each neuron is defined by its input u(t) 2 R and output x(t) 2 R at time t, whereas u(t) equals the weighted sum of all neurons inputs for neurons with multiple inputs.…”

Section: A Pid Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Design and evaluation of advanced intelligent flight controllers

Milz

Looye

2020

AIAA Scitech 2020 Forum

View full text Add to dashboard Cite

Reinforcement learning based methods could be feasible of solving adaptive optimal control problems for nonlinear dynamical systems. This work presents a proof of concept for applying reinforcement learning based methods to robust and adaptive flight control tasks. A framework for designing and examining these methods is introduced by means of the open research civil aircraft model (RCAM) and optimality criteria. A state-of-the-art robust flight controller -the incremental nonlinear dynamic inversion (INDI) controller -serves as a reference controller. Two intelligent control methods are introduced and examined. The deep deterministic policy gradient (DDPG) controller is selected as a promising actor critic reinforcement learning method that currently gains much attraction in the field of robotics. In addition, an adaptive version of a proportional-integral-derivative (PID) controller, the PID neural network (PIDNN) controller, is selected as the second method. The results show that all controllers are able to control the aircraft model. Moreover, the PIDNN controller exhibits improved reference tracking if a good initial guess of its weights is available. In turn, the DDPG algorithm is able to control the nonlinear aircraft model while minimizing a multi-objective value function. This work provides insight into the usability of selected intelligent controllers as flight control functions as well as a comparison to state-of-the-art flight control functions.

show abstract

Section: Advanced Intelligent Control Methodsmentioning

confidence: 99%

Section: A Pid Neural Networkmentioning

confidence: 99%

Design and evaluation of advanced intelligent flight controllers

Milz

Looye

2020

AIAA Scitech 2020 Forum

View full text Add to dashboard Cite

show abstract

“…The nonredundant limbs are controlled by the BP neural network PID controller. Figure 3 shows the block diagram of the BP neural network model which is employed in the intelligent gain tuning by online learning [37][38][39][40][41]. In this model, the NN has four input layers, eight hidden layers, and three output layers, and w o and w i are the weight factors of input layers and output layers that can be continuously updated by machine learning.…”

Section: Control Designmentioning

confidence: 99%

Trajectory Tracking Control Study of a New Parallel Mechanism with Redundant Actuation

Zhang

Fang

Zhang

et al. 2020

International Journal of Aerospace Engineering

View full text Add to dashboard Cite

Parallel mechanisms with redundant actuation are attracting numerous scholars’ research interest due to their inherent advantages. In this paper, an efficient trajectory tracking control scheme for the new redundantly actuated parallel mechanism by integrating force/position hybrid control with the combination of inertia feed-forward control and back propagation (BP) neural network PID control is proposed. The dynamic models including the joint space and task space are formulated explicitly in efficient and compact form by means of the principle of virtual work and d’Alembert formulations. The force/position hybrid control is implemented to perform trajectory tracking and optimize the driving force configuration in MATLAB/Simulink environment, before being applied to an actual parallel mechanism. The illustrative simulation results demonstrate that the force/position hybrid control scheme is available to provide good trajectory tracking performance. Simultaneously, the feasibility of the proposed control scheme is verified by comparison analysis with the aforementioned conventional control method.

show abstract

“…In this work, globally optimized PID parameters tend to operate the CSTR process in its entire operating range to over come the limitations of the linear PID controller. The simulation study reveals that the GA based PID controller tuned with fixed PID parameters provides satisfactory performance in terms of set point tracking and disturbance rejection.. Wen Tan [2]the author compared the well-known PID tuning rules. Criteria based on disturbance rejection and system robustness are proposed to assess the performance of PID controllers.…”

Section: Literature Reviewmentioning

confidence: 99%

Comparative Analysis of Pso-Pid and Hu-Pid

Thakur¹,

Batish²

2017

IJERA

View full text Add to dashboard Cite

PID control is an important ingredient of a distributed control system. The controllers are also embedded in many special purpose control systems. PID control is often combined with logic, sequential functions, selectors, and simple function blocks to build the complicated automation systems used for energy production, transportation, and manufacturing. Many sophisticated control strategies, such as model predictive control, are also organized hierarchically. PID control is used at the lowest level; the multivariable controller gives the set points to the controllers at the lower level. The PID controller can thus be said to be the "bread and butter" of power system engineering. It is an important component in every control engineer"s tool box. PID controllers have survived many changes in technology, from mechanics and pneumatics to microprocessors via electronic tubes, transistors, integrated circuits. The microprocessor has had a dramatic influence on the PID controller

show abstract

A New PID Neural Network Controller Design for Nonlinear Processes

Cited by 37 publications

References 18 publications

Design and evaluation of advanced intelligent flight controllers

Design and evaluation of advanced intelligent flight controllers

Trajectory Tracking Control Study of a New Parallel Mechanism with Redundant Actuation

Comparative Analysis of Pso-Pid and Hu-Pid

Contact Info

Product

Resources

About