Adaptive Critic-Based Neural Networks for Agile Missile Control

Dong-Hoon, Han; Balakrishnan, S. N.

doi:10.2514/2.4895

Cited by 25 publications

(20 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Adaptive critic controllers have been successfully trained offline for two-axle vehicle steering and speed control, 5 agile missile interception, 6 aircraft autolanding and control, 7−9 and turbogenerator control. 4 Although several architectures have been proposed to accelerate convergence to the optimal solution (as in Refs.…”

Section: Introductionmentioning

confidence: 99%

Online Adaptive Critic Flight Control

Ferrari

Stengel

2004

Journal of Guidance, Control, and Dynamics

129

View full text Add to dashboard Cite

A nonlinear control system comprising a network of networks is taught by the use of a two-phase learning procedure realized through novel training techniques and an adaptive critic design. The neural network controller is trained algebraically, offline, by the observation that its gradients must equal corresponding linear gain matrices at chosen operating points. Online learning by a dual heuristic adaptive critic architecture optimizes performance incrementally over time by accounting for plant dynamics and nonlinear effects that are revealed during large, coupled motions. The method is implemented to control the six-degree-of-freedom simulation of a business jet aircraft over its full operating envelope. The result is a controller that improves its performance while unexpected conditions, such as unmodeled dynamics, parameter variations, and control failures, are experienced for the first time.

show abstract

Section: Introductionmentioning

confidence: 99%

Online Adaptive Critic Flight Control

Ferrari

Stengel

2004

Journal of Guidance, Control, and Dynamics

129

View full text Add to dashboard Cite

show abstract

“…Adaptive critic designs constitute a class of approximate dynamic programming (ADP) methods that use incremental optimization combined with parametric structures that approximate the optimal cost and the control [36][37][38]. Both classical DP and ADP methods have been used to train neural networks for many nonlinear control applications, such as steering and controlling the speed of a two-axle vehicle [39], intercepting an agile missile [40], performing auto landing and control of an aircraft [41][42][43], controlling a turbogenerator [44], and tracking control with time delays [45]. As for GCC controllers, neural networks have been primarily used to generate external reference signals.…”

Section: Fig 1 Application Of Grid-connected Rectifier/inverter In mentioning

confidence: 99%

Artificial Neural Networks for Control of a Grid-Connected Rectifier/Inverter Under Disturbance, Dynamic and Power Converter Switching Conditions

Fairbank

Johnson

et al. 2014

IEEE Trans. Neural Netw. Learning Syst.

128

View full text Add to dashboard Cite

This is the accepted version of the paper.This version of the publication may differ from the final published version. Permanent repository link City Research OnlineAbstract --Three-phase grid-connected converters are widely used in renewable and electric power system applications. Traditionally, grid-connected converters are controlled with standard decoupled d-q vector control mechanisms. However, recent studies indicate that such mechanisms show limitations in their applicability to dynamic systems. This paper investigates how to mitigate such restrictions using a neural network to control a grid-connected rectifier/inverter. The neural network implements a dynamic programming algorithm and is trained by using backpropagation through time. To enhance performance and stability under disturbance, additional strategies are adopted, including the use of integrals of error signals to the network inputs and the introduction of grid disturbance voltage to the outputs of a well-trained network. The performance of the neural network controller is studied under typical vector control conditions and compared against conventional vector control methods, which demonstrates that the neural vector control strategy proposed in this paper is effective. Even in dynamic and power converter switching environments, the neural vector controller shows strong ability to trace rapidly changing reference commands, tolerate system disturbances, and satisfy control requirements for a faulted power system.

show abstract

“…The speedloop controller is normally a PI controller that is designed based on the torque equation (7). The current-loop controller is developed by rewriting (1) and (2) as (10) where the item in the bracket of (9) and (10) is treated as the state equation between the voltage and current in the d-or qaxis loops, and the other items are treated as compensation terms [12,25]. This treatment assumes that v sd in (9) has no major influence on i sq and v sq in (10) has no main effect on i sd .…”

Section: Conventional Pm Motor Vector Controlmentioning

confidence: 99%

“…Adaptive critic designs constitute a class of approximate dynamic programming (ADP) methods that use incremental optimization combined with parametric structures that approximate the optimal cost and the control [22,23]. Both classical DP and ADP methods have been used to train neural networks for a large number of nonlinear control applications, such as steering and controlling the speed of a two-axle vehicle [24], intercepting an agile missile [25], performing auto landing and control of an aircraft [26][27][28], and controlling a turbogenerator [29]. However, no research has been conducted regarding the vector control of PMSMs using DP or ADP-based neural networks.…”

Section: Introductionmentioning

confidence: 99%

Nested-loop neural network vector control of permanent magnet synchronous motors

Fairbank

et al. 2013

The 2013 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

--With the improvement of battery technology over the past two decades and automotive technology advances, more and more vehicle manufacturers have joined in the race to produce new generation of affordable, high-performance electric drive vehicles (EDVs). Permanent magnet synchronous motors (PMSMs) are at the top of AC motors in high performance drive systems for EDVs. Traditionally, A PMSM is controlled with standard decoupled d-q vector control mechanisms. However, recent studies indicate that such mechanisms show limitations. This paper investigates how to mitigate such problems using a nested-loop recurrent neural network architecture to control a PMSM. The neural networks are trained using backpropagation through time to implement a dynamic programming (DP) algorithm. The performance of the neural controller is studied for typical vector control conditions and compared with conventional vector control methods, which demonstrates the neural vector control strategy proposed in this paper is effective. Even in a highly dynamic switching environment, the neural vector controller shows strong ability to trace rapidly changing reference commands, tolerate system disturbances, and satisfy control requirements for complex EDV drive needs.Index Terms -Permanent magnet synchronous motor, decoupled vector control, electric drive vehicle, recurrent neural network, dynamic programming, backpropagation through time

show abstract

Adaptive Critic-Based Neural Networks for Agile Missile Control

Cited by 25 publications

References 4 publications

Online Adaptive Critic Flight Control

Online Adaptive Critic Flight Control

Artificial Neural Networks for Control of a Grid-Connected Rectifier/Inverter Under Disturbance, Dynamic and Power Converter Switching Conditions

Nested-loop neural network vector control of permanent magnet synchronous motors

Contact Info

Product

Resources

About