Forecast and Control of Anode Shape in Electrochemical Machining Using Neural Network

Pang, Guibing; Xu, Wenji; Zhai, Xiaobing; Jinjin, Zhou

doi:10.1007/978-3-540-28648-6_41

Cited by 8 publications

(8 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Whatever may be the approach, most researchers found that the predicted values by ANN are consistent with the experimental values [1,3,6,[10][11][12][13]15]. Milewski et al [3] reported that ANN model can also adapt to changes in input conditions.…”

Section: A Artificial Neural Network Modellingmentioning

confidence: 88%

“…Analytical mathematical tools are often used to predict the values of dependent parameters if there is an existing mathematical relationship between the dependent and the independent parameters. Artificial neural network is an important tool in predicting the values of dependent parameters where no mathematical model is available [10] or even though some mathematical relationship is available, it is hard to find parameters required by the model [3,11].…”

Section: A Artificial Neural Network Modellingmentioning

confidence: 99%

“…For the training of the model, the back-propagation training algorithm is the most popular one [3,5,10,12,[11][12][13][14][15][16][17][18][19]. Among various training algorithms, the Levenberg-Marquardt algorithm is preferred by many researchers [3,12,16,20]; however, other training algorithms are used as well [11,15].…”

Section: A Artificial Neural Network Modellingmentioning

confidence: 99%

See 2 more Smart Citations

An artificial neural network model for predicting the CO2 reactivity of carbon anodes used in the primary aluminum production

Bhattacharyay

Kocaefe

et al. 2015

Neural Comput & Applic

View full text Add to dashboard Cite

Carbon anode is one of the key components for the electrolytic production of aluminum. It is mainly composed of calcined petroleum coke, coal tar pitch, and recycled carbon materials. The impurities in the raw materials, which are mainly by-products of different industries, influence significantly the quality of anodes. Usually, no well-known mathematical relationship exists between the various physical and chemical properties of raw materials and the final anode properties. In such situations, the artificial neural network (ANN) methods can serve as a useful tool to predict anode properties. In this study, published data have been used to show the proficiency of different artificial neural networks using the Matlab software. The average error between the predicted and experimental values is around 6%. The artificial neural network was also used to identify the effect of impurities such as, vanadium, iron, sodium, and sulfur on the CO2 reactivity of anodes. ANN also showed the effect of pitch percentage and coke porosity on the CO2 reactivity of anodes. The effect of CO2 and air reactivities of coke on the CO2 reactivity of anode was also studied. The predictions were found to be in good agreement with the results of other studies in the literature.

show abstract

Section: A Artificial Neural Network Modellingmentioning

confidence: 88%

Section: A Artificial Neural Network Modellingmentioning

confidence: 99%

Section: A Artificial Neural Network Modellingmentioning

confidence: 99%

See 1 more Smart Citation

An artificial neural network model for predicting the CO2 reactivity of carbon anodes used in the primary aluminum production

Bhattacharyay

Kocaefe

et al. 2015

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

“…Its application and advantages have been discussed in many references [16][17][18] (Fausett, 1994;Haykin 2002;Pang et al, 2004). A feed forward BP neural network has novelty been developed to forecast the anode accuracy with an uneven interelectrode gap in this paper.…”

Section: Introductionmentioning

confidence: 99%

Application of BP Neural Network for Predicting Anode Accuracy in ECM

Shang¹,

Sun²

2008

2008 International Symposium on Information Science and Engineering

View full text Add to dashboard Cite

It is difficult for numerical method to predict the anode accuracy in electrochemical machining (ECM) with an uneven interelectrode gap, so this paper introduces forward feed forward back propagation (BP) neural network to solve this problem. Based on analyzing effect of parameters including workpiece, electrolyte and cathode on machined accuracy, meanwhile considering the practical machining condition, the neurons of BP neural network in the input layer are confirmed. The trial and error procedure was employed to optimize the number of neurons in the hidden layer. The architecture of BP neural network is constructed to ensure the minimum total prediction error. Levenberg Marquadt (LM) algorithm is used to train this network. To verify the validity of the trained network, results obtained by BP neural network are compared with that obtained by the experiments. It shows that the former is close to the later, the maximum prediction error is lower than 10%, which indicates that it is feasible to apply BP neural network to predict anode accuracy.

show abstract

“…Artificial neural network is used for predicting the values of dependent parameters for which no mathematical relation is available (Parthiban, 2007) or even though some mathematical relationship is available, it is hard to find the numerical parameters (Milewski, 2009). ANN models are widely used in various research fields including quality control (Bahlmann, 1999;Pang, 2004;Fruhwirth, 2007;Parthiban, 2007;Saengrung, 2007;Shang, 2008;Piuleac, 2010;Bhagavatula, 2012), prediction of compositions and properties of metallic and nonmetallic compounds (Wang, 2008;Asadi-Eydivand, 2014;Mohanty, 2014), aluminum reduction cell (Meghlaoui, 1998;Biedler, 2002;Boadu, 2010). However, there are only a few studies available (Berezin, 2002;Bhattacharyay, 2013;Bhattacharyay, 2015) in literature, which are directly related to carbon anodes used for the production of primary aluminum.…”

Section: Introductionmentioning

confidence: 99%

Effect of Coke Granulometry on the Properties of Carbon Anodes based on Experimental Study and ANN Analysis

Sarkar¹,

Kocaefe

Kocaefe³

et al. 2016

JMSR

View full text Add to dashboard Cite

<p class="1Body">The available anode-quality petroleum coke is not sufficient to cover the need created by the increase in the world aluminum production. Understanding the consequences of varying calcined coke quality is necessary to possibly compensate for the reduction in coke quality and adjust the anode paste recipe in the subsequent use of coke in order to obtain economically viable production of aluminum. Different fractions of coke particles were mixed to optimize the anode recipe; however, it was laborious to find experimentally the suitable percentage of each fraction in anode paste which would give good anode properties. In this study, Artificial Neural Network (ANN) model was developed for adjusting the granulometry of the raw materials for anode production. Tapped bulk density of dry aggregates was used to predict the anode paste recipe using the ANN method. A new anode recipe (by adjusting the medium fraction in the paste) was proposed based on the predictions of an ANN model, which resulted in improved anode properties.</p>

show abstract

Forecast and Control of Anode Shape in Electrochemical Machining Using Neural Network

Cited by 8 publications

References 4 publications

An artificial neural network model for predicting the CO2 reactivity of carbon anodes used in the primary aluminum production

An artificial neural network model for predicting the CO2 reactivity of carbon anodes used in the primary aluminum production

Application of BP Neural Network for Predicting Anode Accuracy in ECM

Effect of Coke Granulometry on the Properties of Carbon Anodes based on Experimental Study and ANN Analysis

Contact Info

Product

Resources

About