Incremental Updating Multirobot Formation Using Nonlinear Model Predictive Control Method With General Projection Neural Network

Xiao, Hanzhen; Chen, C. L. Philip

doi:10.1109/tie.2018.2864707

Cited by 40 publications

(11 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The MPC has been proved to be successful in process control field due to its benign characteristics; however, the computational intensity is the main obstacle that limits the MPC to be applied widely. 38 In order to obtain efficient MPC design, a neurodynamic optimization system 20–29 based on PNN is established to solve the objective function formulated by MPC in this article. Finally, the proposed control design is tested using the high-fidelity simulation model under wave disturbances introduced in Section “High-fidelity simulation model” and Section “Description of wave disturbances”.…”

Section: Mathematical Model and Problem Formulationmentioning

confidence: 99%

“…Recently, the recurrent neural network (RNN) was found to be a powerful tool for solving this optimization problem. 19–27 In the 1980s, the successful implementation of Hopfield neural network, which belongs to the category of RNN, brought the renaissance of neural network. 24–26 The basic idea of neurodynamic optimization is to establish a neurodynamic system based on RNN and the dynamic information of system to solve the optimization problem parallelly.…”

Section: Introductionmentioning

confidence: 99%

“…20,21,24 Furthermore, the parallel structure of processing information of neural network is capable of solving the problem efficiently. 24,27 The distinctive feature of RNN makes it a powerful tool to solve the optimization problem efficiently with guaranteed stability. Currently, there are three main categories of RNN for solving the optimization problems: the Kennedy–Chua model, the Rodriguez–Vazquez model, and the projection neural network (PNN).…”

Section: Introductionmentioning

confidence: 99%

“…29 The PNN is then devised to overcome the above drawbacks. 19–23,27 Therefore, in this article, the PNN is employed to establish the neurodynamic system to parallelly solve the constrained optimization problem formulated by the MPC. The overall information of ship motion is normally difficult to be obtained, 30 particularly in rolling condition; therefore, a state observer is included to estimate the state of the plant.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

An efficient ship autopilot design using observer-based model predictive control

Wang

Liu

2020

Proceedings of the Institution of Mechanical Engineers, Part M:

View full text Add to dashboard Cite

An efficient model predictive control design for ship autopilot, which is a representative marine application, is proposed based on projection neural network in this article. Ship motion control at sea exhibits the characteristics of large inertia, strong nonlinearity, and large delay; furthermore, it is frequently influenced by the external disturbances, leading to a complex uncertain problem. In addition, the amplitude of control input—the rudder is constrained. Given the mechanism of on-line computing and the advantages of handling constraints, the model predictive control is one of the most favorable solutions for this problem. Nevertheless, the major challenge of the implementation of traditional model predictive control in application is the computation intensity. In this article, the capability of parallel computation of projection neural network is employed to optimize the objective function formulated by traditional model predictive control method, aiming to improve the computational efficiency. The overall information of ship motion is normally difficult to be obtained; therefore, a state observer should be also included. Extensive studies are conducted to illustrate the effectiveness of the proposed control design.

show abstract

Section: Mathematical Model and Problem Formulationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An efficient ship autopilot design using observer-based model predictive control

Wang

Liu

2020

Proceedings of the Institution of Mechanical Engineers, Part M:

View full text Add to dashboard Cite

show abstract

“…On the other hand, the nonlinear model predictive control (NMPC) strategy can incorporate the state and input limitations into the cost function and obtain a minimization closedloop optimal problem based on the consensus formation model over a predictive control horizon in each sampling time. In the previous works [15], [16], and [17], NMPC method is used to control the leader-follower wheeled robot formation system with separation-bearing orientation scheme (SBOS) framework and the system's boundaries can be considered. However, in [15]- [18] and [19], the formation systems are constructed by calculating robots' relative relationships but not in a consensus form.…”

mentioning

confidence: 99%

Leader-Follower Consensus Multi-Robot Formation Control Using Neurodynamic-Optimization-Based Nonlinear Model Predictive Control

Xiao

Chen

2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

This paper investigates a nonlinear-model-predictive-control (NMPC)-strategy-based distributed leader-follower consensus multi-robot formation system. The control objective of this system is to design a group of nonholonomic robots to converge into the desired geometric pattern and to track a designed path. A directed graph that specifies communication topology for the formation is given. A leader-follower consensus formation problem based on the mobile robot kinematic model is obtained, which is further reformulated into a constrained nonlinear minimization problem through the NMPC strategy. A general projection neural network (GPNN) is implemented to efficiently derive the optimal control inputs for the robots. The simulation results verify the effectiveness of the proposed formation algorithm.INDEX TERMS Nonholonomic Multi-robot formation, leader-follower consensus system, nonlinear model predictive control (NMPC), graph theory, general projection neural network (GPNN). I. INTRODUCTIONIn recent years, robot formation, which is one of the most important research areas in multi-robot coordination, has become more and more attractive. Many researchers are interested in its application prospects such as surveillance, transportation, mine sweeping, rescue operations, and geographical exploration. Compared to single robot, a team of robots can offer many superiorities on working. The consensus formation, whose objective is to control a group of robots to reach and maintain a designed geometric pattern during moving, is a typical formation scheme. Meanwhile, owing to Brockett's theorem [1], it is hard to directly implement the differentiable, or even continuous, pure state feedback algorithm on the nonholonomic-robot-based distributed consensus formation problem.Generally, there are two control paradigms for robot formation: centralized and distributed. In centralized formation,The associate editor coordinating the review of this manuscript and approving it for publication was Jinpeng Yu.

show abstract

Neural network predictive control of converter inlet temperature based on event‐triggered mechanism in flue gas acid production

Liu,

Li,

Wang

2024

Optim Control Appl Methods

View full text Add to dashboard Cite

The process of smelting non‐ferrous metals results in significant emissions of flue gas that contains sulfur dioxide (SO), which is very harmful to the environment. Through precise control of converter inlet temperature, it is feasible to enhance the conversion ratio of SO and simultaneously mitigate environmental pollution by generating acid from flue gas. Because of the high degree of uncertainty in smelting process, converter inlet temperature is challenging to regulate and controller frequently needs updating. To improve control performance and decrease controller update times, an event‐triggered neural network model predictive control (ETNMPC) strategy is proposed. First, long short‐term memory (LSTM) prediction model and model predictive controller are developed. Second, it is decided whether to update the existing controller by designing an event‐triggered mechanism. Finally, using real data from a copper facility in Jiangxi Province, the temperature control experiment of converter inlet is carried out. Simulation results demonstrate that the proposed ETNMPC outperforms conventional time‐triggered method in terms of control performance, greatly lowers the times of controller updates, and significantly lowers computation costs and communication burden.

show abstract

Incremental Updating Multirobot Formation Using Nonlinear Model Predictive Control Method With General Projection Neural Network

Cited by 40 publications

References 25 publications

An efficient ship autopilot design using observer-based model predictive control

An efficient ship autopilot design using observer-based model predictive control

Leader-Follower Consensus Multi-Robot Formation Control Using Neurodynamic-Optimization-Based Nonlinear Model Predictive Control

Neural network predictive control of converter inlet temperature based on event‐triggered mechanism in flue gas acid production

Contact Info

Product

Resources

About