Comparison of different growing radial basis functions algorithms for control systems applications

Fravolini, Mario Luca; Campa, Giampiero; Napolitano, M.; Cava, M. La

doi:10.1109/acc.2002.1023141

Cited by 11 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Growing RBF-NN algorithm is one of the approaches to address this problem. The main advantage of this architecture is that their dimensionality is not predefined but grows incrementally along with the complexity of the model (Fravolini et al, 2002). This algorithm was used in the current application.…”

Section: Neural Network (Nn) Classificationmentioning

confidence: 99%

See 1 more Smart Citation

Ultrasound based glass fragments detection in glass containers filled with beverages using neural networks and short time Fourier transform

Zhao

Yang

Basir

et al. 2006

Food Research International

View full text Add to dashboard Cite

Section: Neural Network (Nn) Classificationmentioning

confidence: 99%

“…This feature is realized by the training process of the network, which iteratively updates the centroid vector by the error information (Fravolini, Campa, Napolitano, & La Cava, 2002). After training, the RBF-NN is able to perform the classification.…”

Section: Background Of Neural Network (Nn)mentioning

confidence: 99%

Ultrasound based glass fragments detection in glass containers filled with beverages using neural networks and short time Fourier transform

Zhao

Yang

Basir

et al. 2006

Food Research International

View full text Add to dashboard Cite

“…Essentially, the EMRAN algorithm allocates neurons in order to decrease the estimation error in regions of the state space where the mapping accuracy is poor. This strategy results in a significant reduction of the number of parameters to be updated on-line, thus reducing the computational burden, and therefore making this architecture particularly suitable for on-line applications [24][25][26][27] . For Gaussian basis functions, the output of each neuron is computed with the expression: …”

Section: B Extended Minimal Resource Allocating Network (Emran)mentioning

confidence: 99%

Performance evaluation of neural network based approaches for airspeed Sensor Failure Accommodation on a small UAV

Gururajan

Fravolini

Huo

et al. 2013

21st Mediterranean Conference on Control and Automation

View full text Add to dashboard Cite

Abstract² Traditional approaches to sensor fault tolerance for flight control systems have been based on triple or quadruple physical redundancy. However, recent events have KLJKOLJKWHG WKH FULWLFDOLW\ RI ³FRPPRQ PRGH´ IDLOXUHV RQ WKH Air Data System (ADS). In fact, since the parameters of flight control laws are typically scheduled as a function of airspeed, incorrect readings from the ADS can lead to potentially catastrophic conditions. In this paper, we describe the evaluation of an analytical redundancy-based approach to the problem of Sensor Failure Accommodation following simulated failures on the ADS of a research UAV, using Artificial Neural Networks (ANNs). Specifically, two different neural networks are evaluated -the Extended Minimal Resource Allocating Network and a Multilayer Feedforward NN. These neural networks are trained and validated using experimental flight data from the WVU YF-22 research aircraft which was designed, manufactured, instrumented, and flight tested by researchers at the Flight Control Systems Laboratory at West Virginia University. The performance of the two approaches is evaluated in terms of the statistics of the tracking error in the estimation of the airspeed, as compared to actual measurements from the ADS, operating under nominal conditions. * Srikanth Gururajan is with the

show abstract

“…Therefore, the concept of growing neurons is introduced. In this idea, a small number of neurons are assigned to the controller, then, according to the criteria of growing neurons, 3,18 the number of neurons is increased automatically to meet the suitable performance. Criteria for adding one neuron: One new neuron will be added into the current network as long as all of these following criteria are satisfied: (The sub-index i = 1, 2 indicates for different RBF neural networks W T i ϕ i ) (1) Current estimation error criteria:…”

Section: Ivb Discretization and Growing Neuron Mechanismmentioning

confidence: 99%

“…In Growing Radial Basis Function Neural Networks (GRBFNN), the number of nodes is optimized as well. Mario and his colleagues 3 published a paper that compared and summarized different growing radial basis function (GRBF) algorithms for control system applications. In the textbook, 18 they present a systematic approach for GRBF neural networks control of nonlinear systems utilizing an extended Kalman Filter.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Backstepping Design for a Longitudinal UAV Model Utilizing a Fully Tuned Growing Radial Basis Function Network

Luo

Yeh

Ishihara

2011

Infotech@Aerospace 2011

View full text Add to dashboard Cite

Classical Radial Basis Function (RBF) neural network controller designs typically fix the number of basis functions and tune only the weights. In this paper we present a backstepping neural network controller algorithm in which all RBF parameters, including centers, variances and weight matrices are tuned online. By using a Lyapunov approach, tuning rules for updating the RBF parameters are derived and a stability and robustness analysis is presented. Additionally, we incorporate the ability to append RBF neurons such that both tracking performance and computational cost can be optimized. The condition for adding a neuron is based on a sliding RMS error window. In addition to the theoretical results, we present the controller implemented in several simulations of an auto landing sequence for a unmanned aerial vehicle (UAV) model.

show abstract

Comparison of different growing radial basis functions algorithms for control systems applications

Cited by 11 publications

References 13 publications

Ultrasound based glass fragments detection in glass containers filled with beverages using neural networks and short time Fourier transform

Ultrasound based glass fragments detection in glass containers filled with beverages using neural networks and short time Fourier transform

Performance evaluation of neural network based approaches for airspeed Sensor Failure Accommodation on a small UAV

Adaptive Backstepping Design for a Longitudinal UAV Model Utilizing a Fully Tuned Growing Radial Basis Function Network

Contact Info

Product

Resources

About