Quantitative Relationship Analysis of Mechanical Properties with Mg Content and Heat Treatment Parameters in Al–7Si Alloys Using Artificial Neural Network

Wu, Xiaoyan; Zhang, Huarui; Haiyang, Cui; Ma, Zhen; Song, Wanqing; Yang, Weimin

doi:10.3390/ma12050718

Cited by 9 publications

(6 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Today, the field of ML has proven useful in many industries and scientific fields. ML algorithms have shown great promise as effective methods for simulation and classification of dynamic manufacturing processes and materials science problems. − When compared to traditional statistical modeling techniques like linear regression and response surface methodology, ML-based approaches have shown dominance as modeling techniques for data sets with nonlinear relationships. , These techniques have demonstrated surprising capability in recognizing patterns in complex systems and capture interactions among input and output variables in a system. They have also shown enormous performance in quantitative structure–property relationship investigations .…”

Section: Introductionmentioning

confidence: 99%

The Effect of Machine Learning Algorithms on the Prediction of Layer-by-Layer Coating Properties

et al. 2023

View full text Add to dashboard Cite

Layer-by-layer film (LbL) coatings made of polyelectrolytes are a powerful tool for surface modification, including the applications in the biomedical field, for food packaging, and in many electrochemical systems. However, despite the number of publications related to LbL assembly, predicting LbL coating properties represents quite a challenge, can take a long time, and be very costly. Machine learning (ML) methodologies that are now emerging can accelerate and improve new coating development and potentially revolutionize the field. Recently, we have demonstrated a preliminary ML-based model for coating thickness prediction. In this paper, we compared several ML algorithms for optimizing a methodology for coating thickness prediction, namely, linear regression, Support Vector Regressor, Random Forest Regressor, and Extra Tree Regressor. The current research has shown that learning algorithms are effective in predicting the coating output value, with the Extra Tree Regressor algorithm demonstrating superior predictive performance, when used in combination with optimized hyperparameters and with missing data imputation. The best predictors of the coating thickness were determined, and they can be later used to accurately predict coating thickness, avoiding measurement of multiple parameters. The development of optimized methodologies will ensure different reliable predictive models for coating property/function relations. As a continuation, the methodology can be adapted and used for predicting the outputs connected to antimicrobial, anti-inflammatory, and antiviral properties in order to be able to respond to actual biomedical problems such as antibiotic resistance, implant rejection, or COVID-19 outbreak.

show abstract

Section: Introductionmentioning

confidence: 99%

The Effect of Machine Learning Algorithms on the Prediction of Layer-by-Layer Coating Properties

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Recently, machine learning (ML) methods have been developed to evaluate mechanical properties from mechanical test data 34–36 and predict mechanical parameters from mechanical test data 37–39 . In many studies, the combination of ML methods and CZM methods has shown great potential to effectively determine the CZM traction separation law or fracture energy of different materials.…”

Section: Introductionmentioning

confidence: 99%

“…However, CZM parameters will affect the determination of the traction separation rule of bonded joints, which is of great significance for reliability evaluation. [31][32][33] Recently, machine learning (ML) methods have been developed to evaluate mechanical properties from mechanical test data [34][35][36] and predict mechanical parameters from mechanical test data. [37][38][39] In many studies, the combination of ML methods and CZM methods has shown great potential to effectively determine the CZM traction separation law or fracture energy of different materials.…”

mentioning

confidence: 99%

Deep neural network aided cohesive zone parameter identifications through die shear test in electronic packaging

Zhao,

Dai,

Wei

et al. 2023

Fatigue Fract Eng Mat Struct

View full text Add to dashboard Cite

The die shear test is a feasible and conventional method to characterize the shear strength of die‐attaching layer materials in electronic packaging. A new method for determining cohesive zone model (CZM) parameters using deep neural networks (DNN) and die shear tests is proposed, different from classical fracture framework or lap shear test‐based methods. With the sintered nano‐silver die shear test, the results show that the bilinear CZM inversion results agree well with the experimental results. It is found that the DNN model has high accuracy in predicting and identifying the maximum shear traction strength τmax, separation displacement of the interface δf, and the interface stiffness k1 of CZM parameters for sintered nano‐silver adhesive layer through die shear test load versus displacement curves. The presented DNN‐aided inverse identifying method through the die shear test in this paper could provide an alternative and convenient method for extracting CZM parameters of various kinds of adhesive materials in electronic packaging.

show abstract

“…It promotes the availability of online data and low-cost computing through algorithm learning [5]. Artificial neural network (ANN) is the main machine learning method for material performance prediction, and has been widely used in materials science [6,7], such as the prediction of high temperature flow stress for deformed alloys [8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Test parameters optimization for constrained spray forming of aluminum alloy based on artificial neural network

2020

View full text Add to dashboard Cite

Spray deposition with following continuous extrusion (SD-CE) forming technique is a novel technology that combines spray forming and continuous extrusion. Optimization of test parameters for spray deposition is an important part of SD-CE. In this study, Al-20Si alloy was produced by spray forming at different melt temperature and gas pressure, and obtained grain diameter of 8 group primary silicon phase. Based on the experimental results, an Artificial Neural Network (ANN) with single hidden layers composing of 10 neurons was employed to simulate optimizing of test parameters for spray deposition. The inputs of the model are melt temperature and gas pressure. The output of the model is grain diameter. Finally, the minimum relative error of grain diameter is 0.09%, the maximum relative error is 8.38%, and error majority concentrate within 3.80%, the average absolute relative error(AARE) is 1.04%, R is 0.097, the error is small. The optimal test parameters for spray deposition are melt temperature(829 °C) and gas pressure(0.2 MPa). The results indicate that the ANN model is an easy and practical method to optimize the test parameters for spray deposition of Al-20Si alloy. Thereby this model is a useful reference for optimizing the test parameters of SD-CE

show abstract

Quantitative Relationship Analysis of Mechanical Properties with Mg Content and Heat Treatment Parameters in Al–7Si Alloys Using Artificial Neural Network

Cited by 9 publications

References 38 publications

The Effect of Machine Learning Algorithms on the Prediction of Layer-by-Layer Coating Properties

The Effect of Machine Learning Algorithms on the Prediction of Layer-by-Layer Coating Properties

Deep neural network aided cohesive zone parameter identifications through die shear test in electronic packaging

Test parameters optimization for constrained spray forming of aluminum alloy based on artificial neural network

Contact Info

Product

Resources

About