ANN model of RF MEMS Lateral SPDT switches for millimeter wave applications

Suganthi, S.; Murugesan, K.; Raghavan, S.

doi:10.1590/s2179-10742012000100011

Cited by 13 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The Artificial Neural Network (ANN) is a mathematical method that aims to simulate the human brain in the knowledge acquisition process, with successful applications in nonlinear mapping between input and output variables, pattern recognition and classification, optimization, just to name a few [20][21][22].…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Nonlinear Autoregressive Neural Network Models for Prediction of Transformer Oil-Dissolved Gas Concentrations

et al. 2018

View full text Add to dashboard Cite

Transformers are one of the most important part in a power system and, especially in key-facilities, they should be closely and continuously monitored. In this context, methods based on the dissolved gas ratios allow to associate values of gas concentrations with the occurrence of some faults, such as partial discharges and thermal faults. So, an accurate prediction of oil-dissolved gas concentrations is a valuable tool to monitor the transformer condition and to develop a fault diagnosis system. This study proposes a nonlinear autoregressive neural network model coupled with the discrete wavelet transform for predicting transformer oil-dissolved gas concentrations. The data fitting and accurate prediction ability of the proposed model is evaluated in a real world example, showing better results in relation to current prediction models and common time series techniques.

show abstract

Section: Artificial Neural Networkmentioning

confidence: 99%

Nonlinear Autoregressive Neural Network Models for Prediction of Transformer Oil-Dissolved Gas Concentrations

et al. 2018

View full text Add to dashboard Cite

show abstract

“…The of input and output neurons are set according to the nature of the problem whereas an appropriate number of neuron in the hidden layer has been chosen by trial and error method as insufficient neurons may cause under fitting while too many neurons might lead to over fitting [67,68,69]. The training of the ANN model is carried out with the complete input data set to the network till the MSE is minimized [70,71,72,73]. A model should be trained properly in order to have its high correlation coefficient (R) close to 1 and low MSE.…”

Section: Analysis Of Ann Modelmentioning

confidence: 99%

Artificial Intelligence (AI) Based Tools for Predicting the Removal Efficiency of Heavy Metals by Adsorption

Parveen¹

2016

New Polymeric Composite Materials: Environmental, Biomedical, Actuator and Fuel Cell Applications

View full text Add to dashboard Cite

The two most popular artificial intelligence (AI) techniques namely, artificial neural networks (ANN) and support vector machines (SVM) have been applied for predicting the removal efficiency of heavy metals like Copper (II), Arsenic (III), Lead (II), etc. in an adsorption process using low cost biosorbents. A comparison has been made between ANN, SVM and multiple linear regression (MLR) models based on the statistical parameters such as: correlation coefficient (R), average absolute relative error (AARE) etc. SVM is found to be the better predictive model than the commonly used MLR model and ANN model. Hence, its results are more accurate and generalized.

show abstract

“…Inspirada na biologia de cérebro humano, a rede neural tem alguns elementos básicos como neurônios artificiais, sinapses, pesos neurais e funções de transferência [78], [79]. Redes neurais artificiais são extensamente utilizadas como aproximadores universais de função, reconhecimento e classificação de padrões, sistemas de otimização, entre outras aplicações [80], [81]. Neste caso, foram consideradas como variáveis de entrada os ângulos de comutação (ϴ on e ϴ c ) e, como variável de saída, o nível de vibração (aceleração) medido na frequência de 400 Hz (componente fundamental da ondulação de torque) [1].…”

Section: A Rede Neural Artificial (Rna)unclassified

Metodologia para a redução da vibração e da ondulação de torque de um motor de relutância chaveado especial a partir do uso de simulações multifásicas e de algoritmos genéticos.

Correa¹

View full text Add to dashboard Cite

The initial purpose of this study was developing a multi-physical computational model of a power electronic motor drive, composed to a 2-Phase Switched Reluctance Motor (SRM) 4/2, a power electronic converter, a controller, motor mechanical and structural components and the coupling among different physical domains. For implementing of the proposed model, it was used FEM (Finite Element Method) coupled and numerical simulations resources in a multi-physic simulation platform, in order to accomplish the coupling among the three areas of knowledge: electrical circuits, electromagnetic fields and structural and mechanics components and vibration. Once finished the multi-physical model, it was associated with a optimization procedure of firing angles which uses genetic algorithm model and, as a whole, it was applied on the SRM vibration and torque ripple reduction, resulting in a new methodology to approaching these problems. In order to prove obtained simulation results, it was carried out several experimental tests to validate each development stage, such as the voltage and currents wave forms mapping, vibration tests, etc. The developed models were tested as much function of drive control parameters as the rotor geometry mechanical and structural modifications.

show abstract

ANN model of RF MEMS Lateral SPDT switches for millimeter wave applications

Cited by 13 publications

References 13 publications

Nonlinear Autoregressive Neural Network Models for Prediction of Transformer Oil-Dissolved Gas Concentrations

Nonlinear Autoregressive Neural Network Models for Prediction of Transformer Oil-Dissolved Gas Concentrations

Artificial Intelligence (AI) Based Tools for Predicting the Removal Efficiency of Heavy Metals by Adsorption

Metodologia para a redução da vibração e da ondulação de torque de um motor de relutância chaveado especial a partir do uso de simulações multifásicas e de algoritmos genéticos.

Contact Info

Product

Resources

About