Comparative evaluation of supervised machine learning algorithms in the prediction of the relative density of 316L stainless steel fabricated by selective laser melting

Barrionuevo, Germán; Ramos‐Grez, Jorge; Walczak, Magdalena; Betancourt, Carlos

doi:10.1007/s00170-021-06596-4

Cited by 58 publications

(24 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…KNN, STR, and GPR will not be recommended as they are considered the worst-performing algorithms here. [76] Minimum error artificial data were generated for processing, and the method used here is flexible and considered best for evaluating the tribo-parameters.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

A Cutting-Edge Survey of Tribological Behavior Evaluation Using Artificial and Computational Intelligence Models

Selvaraj

Raj

Dharnidharka

et al. 2021

Advances in Materials Science and Engineering

View full text Add to dashboard Cite

Any metal surface’s usefulness is essential in various applications such as machining and welding and aerospace and aerodynamic applications. There is a great deal of wear in metals, used widely in machines and appliances. The gradual loss of the upper metal layers in all metal parts is inevitable over the machine or component’s lifetime. Artificial intelligence implementations and computational models are being studied to evaluate different metals’ tribological behavior, as technological progress has been made in this field. Different neural networks were used for different metals. They are classified in this paper, together with a description of their benefits and inconveniences and an overview and use of the different types of wear. Artificial intelligence is a relatively new term that uses mechanical engineering. There is still no scientific progress to examine various metal wear cases and compare AI and computational models’ accuracy in wear behavior.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Collected from 13 references of 316L SS parts processed by SLM Python TensorFlow, scikit-learn, Google Colab [76] e ANN with BP is applied along with ANOVA to decide the potential parameters to predict the specific wear rate reduction.…”

Section: Supervised Learningmentioning

confidence: 99%

A Cutting-Edge Survey of Tribological Behavior Evaluation Using Artificial and Computational Intelligence Models

Selvaraj

Raj

Dharnidharka

et al. 2021

Advances in Materials Science and Engineering

View full text Add to dashboard Cite

show abstract

“…On the other hand, 316 L stainless steel (SS) is perhaps the most common ferrous alloy used in SLM today (Amanov, 2020). The density, surface quality, microstructure and mechanical properties in the 316 L stainless steel SLM were (2020) and reported by several other authors (Barrionuevo et al, 2021;La Fé-Perdomo et al, 2021;Zeng et al, 2021). The authors declare the influence of process parameters in building 316 L structures at various building orientations and for which the fracture toughness was measured.…”

Section: Ferrous-based Alloysmentioning

confidence: 96%

Selective laser melting: lessons from medical devices industry and other applications

Fé-Perdomo

Ramos‐Grez

Beruvides³

et al. 2021

RPJ

View full text Add to dashboard Cite

Purpose The purpose of this paper is to outline some key aspects such as material systems used, phenomenological and statistical process modeling, techniques applied to monitor the process and optimization approaches reported. All these need to be taken into account for the ongoing development of the SLM technique, particularly in health care applications. The outcomes from this review allow not only to summarize the main features of the process but also to collect a considerable amount of investigation effort so far achieved by the researcher community. Design/methodology/approach This paper reviews four significant areas of the selective laser melting (SLM) process of metallic systems within the scope of medical devices as follows: established and novel materials used, process modeling, process tracking and quality evaluation, and finally, the attempts for optimizing some process features such as surface roughness, porosity and mechanical properties. All the consulted literature has been highly detailed and discussed to understand the current and existing research gaps. Findings With this review, there is a prevailing need for further investigation on copper alloys, particularly when conformal cooling, antibacterial and antiviral properties are sought after. Moreover, artificial intelligence techniques for modeling and optimizing the SLM process parameters are still at a poor application level in this field. Furthermore, plenty of research work needs to be done to improve the existent online monitoring techniques. Research limitations/implications This review is limited only to the materials, models, monitoring methods, and optimization approaches reported on the SLM process for metallic systems, particularly those found in the health care arena. Practical implications SLM is a widely used metal additive manufacturing process due to the possibility of elaborating complex and customized tridimensional parts or components. It is corroborated that SLM produces minimal amounts of waste and enables optimal designs that allow considerable environmental advantages and promotes sustainability. Social implications The key perspectives about the applications of novel materials in the field of medicine are proposed. Originality/value The investigations about SLM contain an increasing amount of knowledge, motivated by the growing interest of the scientific community in this relatively young manufacturing process. This study can be seen as a compilation of relevant researches and findings in the field of the metal printing process.

show abstract

“…Several of the most popular algorithms were used in this study. Decision tree, random forest, gradient boosting, Gaussian process, and multi-layer perceptron were accurately detailed in [33]. Extreme gradient boosting regressor (XGBRegressor) is an optimized distributed gradient boosting library designed to be highly efficient, flexible, and portable [34].…”

Section: Machine Learning Algorithmsmentioning

confidence: 99%

“…Five-fold Cross-validation (CV) was employed to avoid overfitting during the training process [23], [37]. To assess the prediction accuracy, Barrionuevo et al [33] introduced an index of merit (IM), which combines multiple metrics to get a unique metric of the algorithms' accuracy.…”

Section: Accuracy Evaluationmentioning

confidence: 99%

Predicting the ultimate tensile strength of AISI 1045 steel and 2017-T4 aluminum alloy joints in a laser-assisted rotary friction welding process using machine learning: a comparison with response surface methodology

Barrionuevo

Mullo

Ramos‐Grez

2021

Int J Adv Manuf Technol

Self Cite

View full text Add to dashboard Cite

Welding metal alloys with dissimilar melting points make conventional welding processes not feasible to be used. Friction welding, on the other hand, has proven to be a promising technology. However, obtaining the welded joint's mechanical properties with characteristics similar to the base materials remains a challenge. In the development of this work, several of the machine learning (ML) regressors (e.g., Gaussian process, decision tree, random forest, gradient boosting, and multi-layer perceptron) were evaluated for the prediction of the ultimate tensile strength (UTS) in joints of AISI 1045 steel and 2017-T4 aluminum alloy produced by rotary friction welding with laser assistance. A mixed design of experiments was employed to assess the effect of the rotation speed, friction pressure, and laser power over the UTS. Furthermore, the response surface methodology (RSM) was employed to determine an empirical equation for predicting the UTS, and contours maps determine the main interactions. A total of 48 specimens were employed to train the regressors; the 5-fold cross-validation methodology was used to find the algorithm with greater precision. The gradient boosting regressor (GBR) and Gaussian processes regressors present the highest precision with a less than 3% percentage error for the laser-assisted rotary friction welding process. The capability of the GBR exceeds the accuracy of the RSM with a coefficient of determination (R 2 ) of 90.90 versus 83.24 %, respectively.

show abstract

Comparative evaluation of supervised machine learning algorithms in the prediction of the relative density of 316L stainless steel fabricated by selective laser melting

Cited by 58 publications

References 50 publications

A Cutting-Edge Survey of Tribological Behavior Evaluation Using Artificial and Computational Intelligence Models

A Cutting-Edge Survey of Tribological Behavior Evaluation Using Artificial and Computational Intelligence Models

Selective laser melting: lessons from medical devices industry and other applications

Predicting the ultimate tensile strength of AISI 1045 steel and 2017-T4 aluminum alloy joints in a laser-assisted rotary friction welding process using machine learning: a comparison with response surface methodology

Contact Info

Product

Resources

About