Data Science Techniques, Assumptions, and Challenges in Alloy Clustering and Property Prediction

International Journal of Collaborative Enterprise, 2015

Data mining (DM) algorithms arose as a promising and flourishing discipline at manufacturing and industrial engineering. This paper proposes an efficient decision support approach for manufacturing engineering. The proposed approach tackles clustering challenges for engineering materials properties. It adopts the hierarchal clustering for mining engineering materials properties. Extensive experiments and comparisons are conducted on three different real-world datasets for engineering materials properties. In addition, a study of different similarity measures is carried out to choose the best fit

International Journal of Minerals, Metallurgy and Materials

Data-driven algorithms for predicting mechanical properties with small datasets are evaluated in a case study on gear steel hardenability. The limitations of current data-driven algorithms and empirical models are identified. Challenges in analysing small datasets are discussed, and solution is proposed to handle small datasets with multiple variables. Gaussian methods in combination with novel predictive algorithms are utilized to overcome the challenges in analysing gear steel hardenability data and to gain insight into alloying elements interaction and structure homogeneity. The gained fundamental knowledge integrated with machine learning is shown to be superior to the empirical equations in predicting hardenability. Metallurgical-property relationships between chemistry, sample size, and hardness are predicted via two optimized machine learning algorithms: neural networks (NNs) and extreme gradient boosting (XGboost). A comparison is drawn between all algorithms, evaluating the...

Metals

The ability to accurately predict the mechanical properties of metals is essential for their correct use in the design of structures and components. This is even more important in the presence of materials, such as metal cast alloys, whose properties can vary significantly in relation to their constituent elements, microstructures, process parameters or treatments. This study shows how a machine learning approach, based on pattern recognition analysis on experimental data, is able to offer acceptable precision predictions with respect to the main mechanical properties of metals, as in the case of ductile cast iron and compact graphite cast iron. The metallographic properties, such as graphite, ferrite and perlite content, extrapolated through macro indicators from micrographs by image analysis, are used as inputs for the machine learning algorithms, while the mechanical properties, such as yield strength, ultimate strength, ultimate strain and Young’s modulus, are derived as output....

ISIJ International, 2009

Materials & Design, 2021

An integrated machine learning and physical modelling to predict straininduced martensite in austenitic steels. • A fully predictive model of SIM features, responsible for the TRIP effect in many steels, is devised. • The model provides accurate predictions in comprehensive temperature and strain range in austenitic and dual phase steels. • The model can readily be extended to consider further factors such as strain rate and stress state.

— The purpose of this paper is to predict the mechanical properties of galvanized steel, using appropriate data mining techniques such as neural network, support vector machine, regression analysis and regression tree methods. It is found that by using the neural network technique one can get the best result for predicting the mechanical properties of galvanized steel according to the values of input parameters and also considering the effects of annealing temperature and line speed as the controlling parameters.

Progress in Materials Science, 2022

Machine learning is now applied in virtually every sphere of life for data analysis and interpretation. The main strengths of the method lie in the relative ease of the construction of its structures and its ability to model complex non-linear relationships and behaviours. While application of existing materials have enabled significant technological advancement there are still needs for novel materials that will enable even greater achievement at lower cost and higher effectiveness. The physics underlining the phenomena involved in materials processing and behaviour however still pose considerable challenge and yet require solving. Machine learning can facilitate the achievement of these new aspirations and desires by learning from existing knowledge and data to fill in gaps that have so far been intractable for various reasons including cost and time. This paper reviews the applications of machine learning to various aspects of materials design, processing, characterisation, and some aspects of fabrication and environmental impact evaluation.

Computer Modeling in Engineering & Sciences

Predicting the mechanical properties of additively manufactured parts is often a tedious process, requiring the integration of multiple stand-alone and expensive simulations. Furthermore, as properties are highly location-dependent due to repeated heating and cooling cycles, the properties prediction models must be run for multiple locations before the part-level performance can be analyzed for certification, compounding the computational expense. This work has proposed a rapid prediction framework that replaces the physics-based mechanistic models with Gaussian process metamodels, a type of machine learning model for statistical inference with limited data. The metamodels can predict the varying properties within an entire part in a fraction of the time while providing uncertainty quantification. The framework was demonstrated with the prediction of the tensile yield strength of Ferrium ® PH48S maraging stainless steel fabricated by additive manufacturing. Impressive agreement was found between the metamodels and the mechanistic models, and the computation was dramatically decreased from hours of physics-based simulations to less than a second with metamodels. This method can be extended to predict various materials properties in different alloy systems whose processstructure-property-performance interrelationships are linked by mechanistic models. It is powerful for rapidly identifying the spatial properties of a part with compositional and processing parameter variations, and can support part certification by providing a fast interface between materials models and part-level thermal and performance simulations.

Journal of Industrial and Management Optimization, 2007

We describe the second step in a two-step approach for the development of new and improved alloys. The first step, proposed by Golodnikov et al [3], entails using experimental data to statistically model tensile yield strength and the 20th percentile of the impact toughness, as a function of alloy composition and processing variables. We demonstrate how the models can be used in the second step to search for combinations of the variables in small neighborhoods of the data space, that result in alloys having optimal levels of the properties modeled. The optimization is performed via the efficient frontier methodology. Such an approach, based on validated statistical models, can lead to a substantial reduction in the experimental effort and cost associated with alloy development. The procedure can also be used at various stages of the experimental program, to indicate what changes should be made in the composition and processing variables in order to shift the alloy development process toward the efficient frontier. Data from these more refined experiments can then be used to adjust the model and improve the second step, in an iterative search for superior alloys.

Metals

Cast iron is a very common and useful metal alloy, characterized by its high carbon content (>4%) in the allotropic state of graphite. The correct shape and distribution of graphite are essential for ensuring that the material has the right properties. The present investigation examines the metallurgical and mechanical characterization of a spheroidal (nodular) cast iron, an alloy that derives its name and its excellent properties from the presence of graphite as spheroidal nodules. Experimental data are detected and considered from a data mining perspective, with the scope to extract new and little-known information. Specifically, a machine learning toolkit (i.e., Orange Data Mining) is used as a means of permitting supervised learners/classifiers (such as neural networks, k-nearest neighbors, and many others) to understand related metallurgical and mechanical features. An accuracy rate of over 90% can be considered as representative of the method. Finally, interesting considera...

Integrating Materials and Manufacturing Innovation

This study examines the link between microstructure and mechanical properties of additively manufactured metal parts by developing a predictive model that can estimate properties such as ultimate tensile strength, yield strength, and elongation at fracture based upon microstructural data for 17-4 PH stainless steel. The main benefit of the approach presented is the generalizability, as necessary testing is further reduced in comparison with similar methods that generate full process–structure–property linkages. Data were collected from the available literature on AM-built 17-4 PH stainless steel, in-house tensile testing and imaging, and testing conducted by an AM company. After standardizing the image size and grain boundary extraction via image processing, the features such as grain size distributions and aspect ratios were extracted. By using artificial neural networks, relationships were established between grain size and shape features and corresponding mechanical properties, and subsequently, properties were predicted for novel samples to which the network had not previously been exposed. The model produced correlation coefficients of R2 = 0.957 for ultimate tensile strength, R2 = 0.939 for yield strength, and R2 = 0.931 for fracture elongation. These results demonstrate the efficacy of predictive models that focus upon microstructure–property relationships and highlight an opportunity for further exploration as predictive modeling of metal additive manufacturing continues to improve.

Modelling and Simulation in Materials Science and Engineering, 2005

We propose the use of regression models as a tool to reduce time and cost associated with the development and selection of new metallic alloys. A multiple regression model is developed which can accurately predict tensile yield strength of high strength low alloy steel based on its chemical composition and processing parameters. Quantile regression is used to model the fracture toughness response as measured by Charpy V-Notch (CVN) values, which exhibits substantial variability and is therefore not usefully modelled via standard regression with its focus on the mean. Using Monte-Carlo simulation, we determine that the three CVN values corresponding to each steel specimen can be plausibly modelled as observations from the 20th, 50th and 80th percentiles of the CVN distribution. Separate quantile regression models fitted at each of these percentile levels prove sufficiently accurate for ranking steels and selecting the best combinations of composition and processing parameters.

Nature Communications, 2019

The field of multi-principal element or (single-phase) high-entropy (HE) alloys has recently seen exponential growth as these systems represent a paradigm shift in alloy development, in some cases exhibiting unexpected structures and superior mechanical properties. However, the identification of promising HE alloys presents a daunting challenge given the associated vastness of the chemistry/composition space. We describe here a supervised learning strategy for the efficient screening of HE alloys that combines two complementary tools, namely: (1) a multiple regression analysis and its generalization, a canonical-correlation analysis (CCA) and (2) a genetic algorithm (GA) with a CCA-inspired fitness function. These tools permit the identification of promising multi-principal element alloys. We implement this procedure using a database for which mechanical property information exists and highlight new alloys having high hardnesses. Our methodology is validated by comparing predicted hardnesses with alloys fabricated by arc-melting, identifying alloys having very high measured hardnesses.

Materials, 2022

This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY

Archives of Foundry Engineering, 2022

The paper presents a methodology of modeling relationships between chemical composition and hardenability of structural alloy steels using computational intelligence methods, that are artificial neural network and multiple regression models. Particularly, the researchers used unidirectional multilayer teaching method based on the error backpropagation algorithm and a quasi-newton methods. Based on previously known methodologies, it was found that there is no universal method of modeling hardenability, and it was also noted that there are errors related to the calculation of the curve. The study was performed on large set of experimental data containing required information on about the chemical compositions and corresponding Jominy hardenability curves for over 400 data steel heats with variety of chemical compositions. It is demonstrated that the full practical usefulness of the developed models in the selection of materials for particular applications with intended performance in the area of application.