Sensitivity Analysis of Cutting Force on Milling Process using Factorial Experimental Planning and Artificial Neural Networks

Nascimento, Eriberto Oliveira do; Oliveira, Lucas Nonato de

doi:10.1109/tla.2016.7817015

Cited by 8 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this work, it was employed the modified version of the Profile Method (PM) [47,48], hereinafter referred to as the Modified Profile Method (MPM), which was successfully applied by Nascimento and Oliveira [49] and by Nascimento et al [50]. According to Lek et al [47], the original PM calculated the profile curves of each variable.…”

Section: Of 20mentioning

confidence: 99%

Application of Artificial Neural Networks for Noise Barrier Optimization

et al. 2018

Self Cite

View full text Add to dashboard Cite

In the modern world, noise pollution continues to be a major problem that impairs people’s health, and road traffic is a primary contributor to noise emissions. This article describes an environmental impact study of the noise generated by the reconstruction of an urban section of a highway. Noise maps were calculated, and an environmental impact matrix was generated to determine the environmental impact of this reconstruction. The implementation of noise barriers was simulated based on these noise maps, and the effectiveness of the barriers was evaluated using Artificial Neural Networks (ANNs) combined with Design of Experiments (DoE). A functional variable significance analysis was then made for two parameters, namely, the coefficient of absorption of the barrier material and the barrier height. The aim was to determine the influence of these parameters on sound attenuation and on the formation of acoustic shadows. The results obtained from the ANNs and DoE were consistent in demonstrating that the absorption coefficient strongly influences the noise attenuation provided by noise barriers, while barrier height is correlated with the formation of larger areas of acoustic shadow. The environmental impact matrix also indicates that the existence of noise pollution has a negative effect on the environment, but that this impact can be reversed or minimized. The application of simulated noise barriers demonstrated that noise levels can be reduced to legally acceptable levels.

show abstract

Section: Of 20mentioning

confidence: 99%

Application of Artificial Neural Networks for Noise Barrier Optimization

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…Through sensitivity analysis, decision makers can clearly understand which parameters have a greater impact on the evaluation results of the economic operation grade, and can select measures to improve the economic operation grade according to the sensitivity analysis result. In this paper, a sensitivity analysis method is proposed based on the work in [22,23] to evaluate the main parameters and the weights of the active power distribution network.…”

Section: Sensitivity Analysis Of Adn Economy Evaluationmentioning

confidence: 99%

“…According to the scale of importance in Table II, the cloud model weights of the first-order indexes and the second-order indexes are calculated through (20), (21), and (22). And the expectations of the second-order index weights are normalized.…”

Section: Economical Operation Evaluation Of Adn 1 Index Weight Set Bamentioning

confidence: 99%

Evaluation and sensitivity analysis for economical operation of active distribution network

Zhu

Gao

et al. 2018

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

memberWith the connection of a large number of distributed energy resources to the power grid, the problem of economical operation of an active distribution network (ADN) has restricted its application. According to the economics of ADN operation, an innovative evaluation index system is proposed and a cloud model is established for evaluating the economical operation of an ADN. In addition, a sensitivity analysis is carried out on the value and weight of the index value. First, the ADN accommodation profit rate, ADN loss contribution rate, etc. are defined. In addition, an evaluation index system is established for the economical operation of ADNs. Index weight cloud model, evaluation grade boundary cloud model, correlation evaluation matrix cloud model, and final evaluation results cloud model are proposed based on the three numeric characteristics of the cloud model, namely expectation value (Ex), entropy (En), and hyper entropy (He). Our evaluation results are close to the actual ones considering uncertainty. Besides, a method for analyzing the the index value and index weight is proposed, which provides a basis for improving the economical operation of ADNs. Finally, simulation results demonstrate the rationale and validity of the index system and the evaluation method of the cloud model, as well as the practicability of sensitive analysis.

show abstract

“…Los datos fueron clasificados por corridas, seleccionando aleatoriamente las corridas que serían empleadas para el entrenamiento. Para la selección de las variables de entrada y la de mayor significancia, algunos consideran que no hay una correlación que permita conseguir cuál es la variable que más impacta en la salida (Nascimento y Oliveira, 2016); sin embargo, para nuestro caso, se cuenta con una medición de temperatura en el tiempo, por lo que serán las variables seleccionadas, además de las condiciones iniciales (temperatura ambiente y concentración inicial). Véase la figura 2.…”

Section: Selección De Los Datos Y De Las Variables De Entradaunclassified

Redes neuronales de base radial como modelos dinámicos para la puesta en marcha de columnas de destilación por lotes

Sosa

Pérez

2017

Ingeniería

View full text Add to dashboard Cite

Recibido: 3 de setiembre 2017Aceptado: 12 de octubre 2017 _____________________________________________________________________ ResumenEn la literatura existen pocos modelos rigurosos para describir el perfil de temperatura durante el periodo de puesta en marcha de las columnas de destilación. En este trabajo, se desarrolla un modelo empleando redes neurales de base radial con datos recolectados durante el período de puesta en marcha de una columna de destilación discontinua para la de mezcla etanol y agua. El entrenamiento de la eficacia de la red neuronal se obtiene realizando un pre-procesamiento de las entradas y un cambio de escala. Para obtener el perfil de temperatura, se recolectan datos a lo largo de diferentes puntos de la columna y los resultados se aplican a múltiples redes. Esto permite la construcción del perfil de temperatura en la columna hasta obtener un error cuadrático medio menor que los valores máximos establecidos durante el preprocesamiento (mse = 0,001) de las redes. Finalmente, se obtiene un modelo que permite observar la transición en la columna desde el estado frío vacío hasta el estado estacionario, normalmente un desafío en los modelos convencionales. Palabras clave:Destilación, redes neuronales artificiales, proceso de arranque, modelación. AbstractFew rigorous models exist in literature for describing the temperature profile during start-up periods of distillation columns. In this work, a model is developed by applying several radial basis neural networks to data collected during the start-up period of a batch distillation column consisting of ethanol and water. Neural network efficiency training is introduced through rescale

show abstract

Sensitivity Analysis of Cutting Force on Milling Process using Factorial Experimental Planning and Artificial Neural Networks

Cited by 8 publications

References 17 publications

Application of Artificial Neural Networks for Noise Barrier Optimization

Application of Artificial Neural Networks for Noise Barrier Optimization

Evaluation and sensitivity analysis for economical operation of active distribution network

Redes neuronales de base radial como modelos dinámicos para la puesta en marcha de columnas de destilación por lotes

Contact Info

Product

Resources

About