Simplifying the powder metallurgy manufacturing process using soft computing tools

Radha, P.; Chandrasekaran, Ganesh; Selvakumar, N.

doi:10.1016/j.asoc.2014.11.011

Cited by 9 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This optimization minimizes a grouping of weights and squared errors, and the best arrangement is constructed, which generalizes well. The network's weights are defined as follows for the objective function: 71 (16) in which the objective function, the sum of model errors, and the sum of squared model weights are, respectively, donated by F(ω), E D , and, E ω . In the above equation, the coefficients of α and β are objective function parameters that are defined according to the theorem of the Bayes.…”

Section: Multilayer Perceptron (Mlp)mentioning

confidence: 99%

“…One of the most precise predictive techniques is soft computations that are appropriate to tremendously complicated and multidimensional input/output engineering problems. − Using these intelligent approaches, a significant number of studies have been accomplished successfully to evaluate many properties in broad metallurgy and material science engineering areas. Design of advanced ultrahigh-strength stainless steels, predicting glass transition temperatures, fracture toughness, coating thickness, compositional optimization, and acoustic properties of tellurite glasses was performed successfully by using intelligent models.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Modeling of the Sintered Density in Cu-Al Alloy Using Machine Learning Approaches

et al. 2023

View full text Add to dashboard Cite

In powder metallurgy materials, sintered density in Cu-Al alloy plays a critical role in detecting mechanical properties. Experimental measurement of this property is costly and time-consuming. In this study, adaptive boosting decision tree, support vector regression, k-nearest neighbors, extreme gradient boosting, and four multilayer perceptron (MLP) models tuned by resilient backpropagation, Levenberg− Marquardt (LM), scaled conjugate gradient, and Bayesian regularization were employed for predicting powder densification through sintering. Yield strength, Young's modulus, volume variation caused by the phase transformation, hardness, liquid volume, liquidus temperature, the solubility ratio among the liquid phase and the solid phase, sintered temperature, solidus temperature, sintered atmosphere, holding time, compaction pressure, particle size, and specific shape factor were regarded as the input parameters of the suggested models. The cross plot, error distribution curve, and cumulative frequency diagram as graphical tools and average percent relative error (APRE), average absolute percent relative error (AAPRE), root mean square error (RMSE), standard deviation (SD), and coefficient of correlation (R) as the statistical evaluations were utilized to estimate the models' accuracy. All of the developed models were compared with preexisting approaches, and the results exhibited that the developed models in the present work are more precise and valid than the existing ones. The designed MLP-LM model was found to be the most precise approach with AAPRE = 1.292%, APRE = −0.032%, SD = 0.020, RMSE = 0.016, and R = 0.989. Lately, outlier detection was applied performing the leverage technique to detect the suspected data points. The outlier detection discovered that few points are located out of the applicability domain of the proposed MLP-LM model.

show abstract

Section: Multilayer Perceptron (Mlp)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Modeling of the Sintered Density in Cu-Al Alloy Using Machine Learning Approaches

et al. 2023

View full text Add to dashboard Cite

show abstract

“…v) Update all weights of the network in accordance with the changes computed in step as defined in Eqns. (11) and (12).…”

Section: Using Prediction Toolmentioning

confidence: 99%

“…Even though the Correlation coefficient value is good, it is not applicable practically to find the relation between two parameters. The AARE% (Average Absolute Relative Error) is used mostly by the researcher [11] as given in Eqn. ( 13), since it OPEN ACCESS http://scidoc.org/IJCNE.php is an unbiased term to measure the error accurately.…”

Section: Ann Approach To Predict the Properties Of Dry Wearmentioning

confidence: 99%

“…However, due to its poor wetting between Ti-Al-V and B 4 C, liquid phase method OPEN ACCESS http://scidoc.org/IJCNE.php of knowledge engineering. Many researchers have attempted to use soft computing tools like Artificial Neural Network (ANN), Fuzzy Logic (FL) and Genetic Algorithm (GA) for material design, controlling materials fabrication and simplifying the various processes involved in the manufacturing section of P/M Lab [11]. ANN is used to predict the wear properties of dry and high temperature conditions of nano composites without conducting experiments in P/M Lab for the wide range of tests.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Neural Networks for Predicting the Wear Properties of Sintered Ti-6Al-4V Composite Reinforced with Nano B4C Particle and Classification using Data Mining Tools

Radha¹,

Selvakumar²

2016

IJCNE

View full text Add to dashboard Cite

Powder metallurgy (P/M) processing is an alternative method to fabricate of Ti-6Al-4V-B 4 C composites. Moreover in this process, the problem of non-wettability of B 4 C with molten TMC does not arise. Mechanical alloying is a good-looking P/M technique that produces uniform dispersion of the secondary particles in the matrix.By considering the above advantages, the P/M Lab uses composites preform (Ti-6Al-4V) with an addition of (2-10) wt. % of nano B 4 C using mechanical alloying method to improve the strength of materials. This strategy mixes the metal powders such as Ti, Al and V with B 4 C to avoid the dimension loss of composites due to friction and heat. While measuring the dry and high temperature wear using pin-on-disk testing machine, the temperature, load, sliding distance are varied for identifying the wear resistance of the prepared composites.

show abstract

Investigation of Mechanical Behavior of Industry Waste and Al2O3 Reinforced Aluminium Matrix Composites by Powder Metallurgy Technique

Pirjade

Kulkarni

2017

Techno-Societal 2016

View full text Add to dashboard Cite

Simplifying the powder metallurgy manufacturing process using soft computing tools

Cited by 9 publications

References 26 publications

Modeling of the Sintered Density in Cu-Al Alloy Using Machine Learning Approaches

Modeling of the Sintered Density in Cu-Al Alloy Using Machine Learning Approaches

Neural Networks for Predicting the Wear Properties of Sintered Ti-6Al-4V Composite Reinforced with Nano B4C Particle and Classification using Data Mining Tools

Investigation of Mechanical Behavior of Industry Waste and Al2O3 Reinforced Aluminium Matrix Composites by Powder Metallurgy Technique

Contact Info

Product

Resources

About