An Optimized Multilayer Perceptrons Model Using Grey Wolf Optimizer to Predict Mechanical and Microstructural Properties of Friction Stir Processed Aluminum Alloy Reinforced by Nanoparticles

Khoshaim, Ahmed B.; Moustafa, Essam B.; Bafakeeh, Omar T.; Elsheikh, Ammar H.

doi:10.3390/coatings11121476

Cited by 78 publications

(23 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To overcome this challenge, more complex neural network structures or hybrid approaches (see refs. [ 24 , 33 , 34 ]) should be applied instead of basic neural networks or interpolation algorithms. Also, like computational simulations, the computing time and cost are limits for the metamodel process, especially for products with a high number of design variables.…”

Section: Resultsmentioning

confidence: 99%

Metal Additive Manufacturing of Plastic Injection Molds with Conformal Cooling Channels

et al. 2022

View full text Add to dashboard Cite

Conformal cooling channels (CCCs) are widely used in the plastic injection molding process to improve the product quality and operational performance. Tooling that incorporates CCCs can be fabricated through metal additive manufacturing (MAM). The present work focuses on the MAM of a plastic injection mold insert with different CCC types that are circular, serpentine, and tapered channels with/without body-centered cubic (BCC) lattices. The entire manufacturing process of the mold insert is explained from the design step to the final printing step including the computational thermal & mechanical simulations, performance assessments, and multiobjective optimization. Compared to the traditional channels, conformal cooling channels achieved up to 62.9% better cooling performance with a better thermal uniformity on the mold surface. The optimum mold geometry is decided using the multiobjective optimization procedure according to the multiple objectives of cooling time, temperature non-uniformity, and pressure drop in the channel. Direct Metal Laser Sintering (DMLS) method is used for manufacturing the molds and the quality of the printed molds are analyzed with the X-ray Computed Tomography (X-ray CT) technique. The errors between the design and the printed parameters are less than 5% for the circular and tapered channels while the maximum deviation of the strut diameters of the BCC is 0.06 mm.

show abstract

Section: Resultsmentioning

confidence: 99%

Metal Additive Manufacturing of Plastic Injection Molds with Conformal Cooling Channels

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The optimal cutting conditions that minimize the cutting forces and surface roughness could be determined metaheuristic approaches [ 37 , 38 , 39 , 40 ]. The process responses could be also predicted using artificial intelligence tools [ 41 , 42 , 43 , 44 ].…”

Section: Resultsmentioning

confidence: 99%

Machinability Investigation of Nitronic 60 Steel Turning Using SiAlON Ceramic Tools under Different Cooling/Lubrication Conditions

Padhan

Das

et al. 2022

Materials

Self Cite

View full text Add to dashboard Cite

The machining of nickel-based super alloys is challenging, owing to the generation of high cutting temperatures, as well as difficulty in maintaining dimensional accuracy and minimizing surface roughness, which compels the use of cutting fluids for reducing these issues due to efficient cooling/lubrication strategies. The present work investigates the comparative performance of four cooling/lubrication techniques: dry cutting, wet, minimum quantity lubricant (MQL) and compressed-air modes in turning Nitronic 60 steel using a new-generation SiAlON ceramic inserts. Several machinability parameters were analyzed for performance evaluation. For this purpose, 16 cycles of turning trials were performed based on Taguchi’s L16 orthogonal array experimental design by varying cutting conditions and lubrication modes. MQL exhibits beneficial effects as compared to the other lubrication conditions concerning low cutting force, improved surface finish, decreased cutting temperature, longer tool life, and lower white layer thickness on machined surface. Burr formation on the saw-tooth chip surface, as well as friction, greatly influenced the tool flank wear due to improper cooling and poor lubrication approach in dry, wet, and compressed-air-cooled machining environments in comparison to MQL-machining. From an economical perspective, the tool life in MQL machining improved by 11%, 72%, and 138% in the comparison with flooded, compressed-air, and dry conditions, respectively. The results of the study demonstrate that using the MQL system can help with heat extraction capability, and provide some promising outcomes.

show abstract

“…They also revealed that if a wide range of machining conditions will be adopted, better results can be predicted through this method. Khoshaim et al (2021) predicted both mechanical and micro-structural properties of friction stir processed aluminium reinforced material using Grey Wolf optimizer. The input parameters are rotational speed, linear processing speed and number of passes, while the outputs were grain size, aspect ratio, micro-hardness and ultimate tensile strength.…”

Section: Introductionmentioning

confidence: 99%

Machine learning based modelling and optimization in hard turning of AISI D6 steel with newly developed AlTiSiN coated carbide tool

Das¹,

Das²,

Panda³

et al. 2022

Preprint

View full text Add to dashboard Cite

In recent times Mechanical and Production industries are facing increasing challenges related to the shift toward sustainable manufacturing. In this article machining was performed in dry cutting condition with a newly developed coated insert called AlTiSiN coated carbides coated through scalable pulsed power plasma technique in dry cutting condition and a dataset was generated for different machining parameters and output responses. The machining parameters are speed, feed, depth of cut and the output responses are surface roughness, cutting force, crater wear length, crater wear width and flank wear. The data collected from the machining operation is used for the development machine learning (ML) based surrogate models to test, evaluate and optimize various input machining parameters. Different ML approaches such as polynomial regression (PR), random forest (RF) regression, gradient boosted (GB) trees and adaptive boosting (AB) based regression are used to model different output responses in the hard machining of AISI D6 steel. The surrogate models for different output responses are used to prepare a complex objective function for the germinal center algorithm based optimization of the machining parameters of the hard turning operation.

show abstract

An Optimized Multilayer Perceptrons Model Using Grey Wolf Optimizer to Predict Mechanical and Microstructural Properties of Friction Stir Processed Aluminum Alloy Reinforced by Nanoparticles

Cited by 78 publications

References 57 publications

Metal Additive Manufacturing of Plastic Injection Molds with Conformal Cooling Channels

Metal Additive Manufacturing of Plastic Injection Molds with Conformal Cooling Channels

Machinability Investigation of Nitronic 60 Steel Turning Using SiAlON Ceramic Tools under Different Cooling/Lubrication Conditions

Machine learning based modelling and optimization in hard turning of AISI D6 steel with newly developed AlTiSiN coated carbide tool

Contact Info

Product

Resources

About