An approach to inverse nonlinear control using neural networks

Lee, T.H.; Hang, C.C.; Lian, Li; Lim, Byeonghwa

doi:10.1016/0957-4158(92)90047-r

Cited by 25 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, we further extend the earlier work (Lee et al 1992, Lee and Tan 1993), that we have carried out in neural-net work-based servomechanism control systems and develop a real-time neural-based controller applicable to the gyro-mirror LOS stabilization platform. Note that this is a multivariable servomechanism with nonlinear dynamics and, in the developments presented in this paper, adaptive techniques are utilized and two types of radial basis function (RBF) neural networks are considered: the Gaussian RBF and the Hardy multiquadric RBF.…”

Section: Introductionmentioning

confidence: 90%

“…Thus, motivated by the neural network-based controllers previously developed by Lee et al (1992), Lee and Tan (1993) and , the controller for the gyro-mirror platform can take the following form: In the design of the neural-network-based controller described above, it is pertinent to point out that the neural networks are only used to compute Mnn(q) and…”

Section: Controller Designmentioning

confidence: 99%

“…However, most of these lose effectiveness when the servomechanisms have fairly severe nonlinear dynamics and, more recently, there has been increasing research and development work to address this problem with the design of control systems, incorporating neural networks. Some examples have been given by Nguyen and Widrow (1990), Ozaki et al (1991), Tzirkel and Fallside (1991), Lee et al (1992), Sanner and Siotine (1992), Lee and Tan (1993) and , but there are undoubtedly other interesting and related developments. In these, neural networks are used in various ways to construct nonlinear control systems to handle a variety of control objectives.…”

Section: Introductionmentioning

confidence: 96%

See 2 more Smart Citations

Real-time neural-network-based control of a gyro-mirror line-of-sight stabilization platform

Lee¹,

Ge²,

Hang³

et al. 1998

International Journal of Systems Science

View full text Add to dashboard Cite

In this paper, we consider the real-time neural-network-based control of a gyro-mirror line-of-sight stabilization platform. This is an example of a multivariablc nonlinear servomechanism encountered in certain practiced applications, and the appropriate neural-network-based modelling and controller design are discussed. In the paper, real-time experimental results in applying the proposed controller to a pilot-scale gyro-mirror platform are presented to demonstrate its effectiveness. These experiments also serve to verify the analytical results in a proptotype real-time application.

show abstract

Section: Introductionmentioning

confidence: 90%

Section: Controller Designmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 96%

See 1 more Smart Citation

Real-time neural-network-based control of a gyro-mirror line-of-sight stabilization platform

Lee¹,

Ge²,

Hang³

et al. 1998

International Journal of Systems Science

View full text Add to dashboard Cite

show abstract

“…The reference (setpoint) is often employed as the input to ANN inverse dynamics controllers [25,26,28,47,51,52]; disturbances have also been used as the input to these controllers [54] since the late 1990s. Both reference and measurable disturbances have either been used as the input to these neuro controllers [55].…”

Section: Ann Inverse Dynamics Control Systemsmentioning

confidence: 99%

“…This approach is called inverse dynamics or the inverse modeling method and used to be the dominant approach in the era of the pioneers of neuro control [25,26] without directly mentioning the word "inverse" as the name of the method. The term "inverse" gradually appeared to introduce this approach in the early 1990s [27,28]. Narendra and Parthasarathy used two ANNs for modeling and control at the same time and devised model reference neuro control [29].…”

Section: An Introduction To Neuro Controlmentioning

confidence: 99%

A critical review of the most popular types of neuro control

Mohammadzaheri

Chen

Grainger

2011

Asian Journal of Control

View full text Add to dashboard Cite

In this review article, the most popular types of neural network control systems are briefly introduced and their main features are reviewed. Neuro control systems are defined as control systems in which at least one artificial neural network (ANN) is directly involved in generating the control command. Initially, neural networks were mostly used to model system dynamics inversely to produce a control command which pushes the system towards a desired or reference value of the output (1989). At the next stage, neural networks were trained to track a reference model, and ANN model reference control appeared (1990). In that method, ANNs were used to extend the application of adaptive reference model control, which was a well-known control technique. This attitude towards the extension of the application of well-known control methods using ANNs was followed by the development of ANN model-predictive (1991), ANN sliding mode (1994) and ANN feedback linearization (1995) techniques. As the first category of neuro controllers, inverse dynamics ANN controllers were frequently used to form a control system together with other controllers, but this attitude faded as other types of ANN control systems were developed. However, recently, this approach has been revived. In the last decade, control system designers started to use ANNs to compensate/cancel undesired or uncertain parts of systems' dynamics to facilitate the use of well-known conventional control systems. The resultant control system usually includes two or three controllers. In this paper, applications of different ANN control systems are also addressed.Key Words: Control, neural network, adaptive, feedback linearization, predictive, model reference, perceptron, radial basis. I. ARTIFICIAL NEURAL NETWORKS USABLE IN CONTROLArtificial neural networks (ANNs) are special mathematical models inspired by human neural networks. An ANN usually includes neurons, connections and biases. Neurons are arranged in 'layers'. There are a variety of neural networks suitable for different purposes [1,2]. In neuro control, it is a difficult and unsolved problem to find the best ANN structure for each specific application; thus, a fairly large ANN is usually employed to deal with relatively complex approximation problems [3]. In this paper, the most common types of artificial neural networks in the area of control are introduced: multi layer perceptrons (MLPs) and radial basis function networks (RBFNs). Both of these are known as universal approximators of systems [4,5]. The advantage of RBFNs is their quick training process compared with MLPs; however, for complicated systems with many inputs, the number of neurons in RBFNs are usually considerably higher than MLPs [1,2]. Regardless of the main structure, if the output of an ANN depends not only on the current q

show abstract

Neural Systems and Applications

Siddique

Adeli

2013

Computational Intelligence

View full text Add to dashboard Cite

An approach to inverse nonlinear control using neural networks

Cited by 25 publications

References 9 publications

Real-time neural-network-based control of a gyro-mirror line-of-sight stabilization platform

Real-time neural-network-based control of a gyro-mirror line-of-sight stabilization platform

A critical review of the most popular types of neuro control

Neural Systems and Applications

Contact Info

Product

Resources

About