A neural network based methodology for the prediction of roll force and roll torque in fuzzy form for cold flat rolling process

Dixit, Uday S.; Chandra, S.

doi:10.1007/s00170-003-1628-8

Cited by 33 publications

(16 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…blade tip speed, free stream velocity with blockage and rotor inlet velocity are normalized such that their values lie between 0.1 and 0.9. This is in accordance with the literature [1].…”

Section: Normalizationsupporting

confidence: 94%

“…Minimum number of training data = 2 x (input + hidden + output) neurons (1) Maximum number of training data = 10 x (input + hidden + output) neurons (2)…”

Section: No Of Neurons In Hidden Layermentioning

confidence: 99%

“…The size of the data-set is decided by the performance of the network, while optimum number of hidden neurons should be obtained from training the network. Otherwise, desired performance may not be obtained as too much increase of hidden neurons will unnecessarily reduce the testing error though training error may be improved [1]. The optimum number of hidden layer neurons is obtained by hit and trial method by running the code for number of times with different training and testing sets and checking the prediction errors.…”

Section: Introductionmentioning

confidence: 99%

“…The network is termed to be a superior one if more testing dataset fit the network that predicts the functional relationship between input and output, and the testing error comes out to be less than the training *Address correspondence to this author at the NIT Silchar (Assam) India, 788004; Tel: +91 3842 242913; Fax: +91 3842 233797; E-mail: agnibis@yahoo.co.in error. It is seen from the literature that the functional relationship between three inputs and single output system can be modeled using artificial neural network and that too, with minimum number of training and testing datasets [1]. Too many hidden layers prolong the computational time, though a single hidden layer can accurately predict for such system.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

An Artificial Neural Network Based Methodology for the Prediction of Power & Torque Coefficients of a Two Bladed Airfoil Shaped H-Rotor

Biswas¹,

Gupta²

2009

TOREJ

View full text Add to dashboard Cite

An artificial neural network based model can effectively predict any functional relationship. In this paper, a neural network model is used to predict power coefficient and torque coefficient of a two bladed airfoil shaped H-rotor as function of different input parameters. The important input parameters considered are blade tip speed, free stream velocity with blockage and rotor inlet velocity. The values of all the process parameters are taken from the experimental work done on two-bladed airfoil shaped H-rotor. The rotor was earlier designed, fabricated, and tested in a subsonic wind tunnel available in the department. Since neural networks are good at interpolation, once the model is properly trained & tested, it has successfully interpolated the values of power and torque coefficients within an acceptable accuracy. Initially, the optimum no. of neurons in the hidden layer has been found out using hit and trial method by training the network using back propagation learning algorithm. The effect of increasing the size of training and testing data set is studied as well. It is found that only a single neuron has been able to predict both the coefficients successfully. A strategy has been developed to reduce both the training and testing errors. The root mean squared functional errors (rms error) of testing and training for power coefficient prediction are 0.0357 and 0.0387 respectively, while the corresponding values for torque coefficients are 0.0283 and 0.0449 respectively. The proposed methodology is fast and accurate. And testing error being less than the training error, makes the proposed algorithm a superior one.

show abstract

“…blade tip speed, free stream velocity with blockage and rotor inlet velocity are normalized such that their values lie between 0.1 and 0.9. This is in accordance with the literature [1].…”

Section: Normalizationsupporting

confidence: 94%

“…Minimum number of training data = 2 x (input + hidden + output) neurons (1) Maximum number of training data = 10 x (input + hidden + output) neurons (2)…”

Section: No Of Neurons In Hidden Layermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An Artificial Neural Network Based Methodology for the Prediction of Power & Torque Coefficients of a Two Bladed Airfoil Shaped H-Rotor

Biswas¹,

Gupta²

2009

TOREJ

View full text Add to dashboard Cite

show abstract

“…Dixit and Chandra [36] have suggested a selection method for ANNs. According to their suggestions, for n inputs, the minimum number of training set should be such that it includes the corners of n-dimensional space with respect to more contribution to input variables with more influence on output.…”

Section: Methodsmentioning

confidence: 99%

Desirability Improvement of Committee Machine to Solve Multiple Response Optimization Problems

Golestaneh

Ismail

Ariffin

et al. 2013

Advances in Artificial Neural Systems

View full text Add to dashboard Cite

Multiple response optimization (MRO) problems are usually solved in three phases that include experiment design, modeling, and optimization. Committee machine (CM) as a set of some experts such as some artificial neural networks (ANNs) is used for modeling phase. Also, the optimization phase is done with different optimization techniques such as genetic algorithm (GA). The current paper is a development of recent authors' work on application of CM in MRO problem solving. In the modeling phase, the CM weights are determined with GA in which its fitness function is minimizing the RMSE. Then, in the optimization phase, the GA specifies the final response with the object to maximize the global desirability. Due to the fact that GA has a stochastic nature, it usually finds the response points near to optimum. Therefore, the performance the algorithm for several times will yield different responses with different GD values. This study includes a committee machine with four different ANNs. The algorithm was implemented on five case studies and the results represent for selected cases, when number of performances is equal to five, increasing in maximum GD with respect to average value of GD will be eleven percent. Increasing repeat number from five to forty-five will raise the maximum GD by only about three percent more. Consequently, the economic run number of the algorithm is five.

show abstract

Analysis and Prospects of Lubrication and Friction Characteristics in Cold Strip Rolling: A Review

Jin,

Li,

Gao

et al. 2024

steel research int.

View full text Add to dashboard Cite

Lubrication and friction are the core processes in cold strip rolling, which are the key links to realizing the stable production of high‐quality strips, reflecting country advanced level in rolling technology. This review investigates the crucial properties of lubrication and friction in cold strip rolling by analyzing the mechanism, characterization methods, and influencing factors. The lubricant forms an oil film on the surface of rolls and strips based on the lubrication dynamics and tribology theory, changing the asperity contact state in the loaded roll gap, leading to changes in friction characteristics. Oil film thickness and coefficient of friction (COF) are crucial parameters for characterizing and judging the characteristics of lubrication and friction, theoretical calculations have become the core analytical method, and the study of the measurement method is still a great challenge. Parameters like rolling speed and oil viscosity affect the lubricant distribution and asperity contact in the loaded roll gap, changing the lubrication and friction state. The influence of parameters is strongly linked to the experimental or rolling environment. Prospective research trends on lubrication and friction in cold strip rolling are presented based on the status of research on lubrication and friction characterization.

show abstract

A neural network based methodology for the prediction of roll force and roll torque in fuzzy form for cold flat rolling process

Cited by 33 publications

References 6 publications

An Artificial Neural Network Based Methodology for the Prediction of Power & Torque Coefficients of a Two Bladed Airfoil Shaped H-Rotor

An Artificial Neural Network Based Methodology for the Prediction of Power & Torque Coefficients of a Two Bladed Airfoil Shaped H-Rotor

Desirability Improvement of Committee Machine to Solve Multiple Response Optimization Problems

Analysis and Prospects of Lubrication and Friction Characteristics in Cold Strip Rolling: A Review

Contact Info

Product

Resources

About