Fig 5 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
The goal of the research carried out was to develop the fuzzy systems, allowing the determination of the Jominy hardenability curve based on the chemical composition of structural steels for quenching and tempering. Fuzzy system was created to calculate hardness of the steel, based on the alloying elements concentrations, and to forecast the harden...
Similar publications
The effect of interfacial bonding of glass hollow microspheres and a polymer matrix on the elastic properties of syntactic foam was investigated using representative volume element (RVE) models, including partially debonded interfaces. Finite element analysis, with models having different debonding geometries, was performed to numerically estimate...
Over the past decade, evolutionary algorithms, data mining and other methods showed great success in solving the main problem of theoretical crystallography: finding the stable structure for a given chemical composition. Here we develop a method that addresses the central problem of computational materials science: prediction of material(s), among...
Citations
... Recently, fuzzy systems were also adopted to estimate the Jominy profile using the steel metallurgy, [39] but the research work focused on structural steels for quenching and tempering. ...
The possibility to estimate the Jominy profile of steel based on its chemical composition is of utmost importance and high practical relevance for industries, at enables a preliminary assessment of the suitability of a specific steel grade to a particular application or to the requirements of a customer, by saving time and resources as the Jominy end‐quench test is costly and time consuming. More importantly, an estimator can be used in steel grade design, by supporting the investigation of the most suitable chemistry to meet some given specifications. The paper proposes a novel approach to estimate the hardenability profile of medium Carbon quench hardenable steels, which exploits the potential of deep learning to correlate the steel metallurgy to the entire shape of the curve rather than to its single points, by thus being adaptable to a wide range of steel grades while providing very accurate estimates. Moreover, the proposed approach is suitable implement a transfer learning paradigm, as it can exploit the knowledge acquired by training on a specific dataset to adapt the model to different steel grades for which less data or data holding different features are available.
This article is protected by copyright. All rights reserved.
... It is worth noting that OFN finds wider and wider applications in practice [17,18], also among the achievements of the main authors of this article, especially in the area of control devices and tools [19][20][21][22] and in finance [14,15,23,24]. ...
... In order to overcome such issue, Colla et al. in [37] proposed a parametric approach, where the Jominy profile is represented through a parametric mathematical function of the distance from the quenched end (e.g. a quasi-sigmoidal monotonic decreasing function) and wavelet NNs are applied to correlate the steel chemistry to the function parameters. Quite recently also fuzzy systems have been applied for the determination of the Jominy hardenability curve based on the chemical composition, although the investigation was limited to structural steels for quenching and tempering [38]. ...
The paper proposes an approach to the design of the chemical composition of steel, which is based on neural networks and genetic algorithms and aims at achieving a desired hardenability behavior possibly matching other constraints related to the steel production. Hardenability is a mechanical feature of steel, which is extremely relevant for a wide range of steel applications and refers to the steel capability to improve its hardness following a heat treatment. In the proposed approach, a neural-network-based predictor of the so-called Jominy hardenability profile is exploited, and an optimization problem is formulated, where the optimization function allows taking into account both the desired accuracy in meeting the target Jominy profile and other constraint. The optimization is performed through genetic algorithms. Numerical results are presented and discussed, showing the efficiency of the proposed approach together with its flexibility and easy customization with respect to the user demands and production objectives.
... Aside from mathematical modelling and the numerical methods related to it, bio-inspired methods are used increasingly frequently. The increasing popularity of artificial intelligence and computational intelligence methods in many fields of science and engineering is also reflected by the area of materials engineering [2][3][4][5][6][7]. Use of hybrid methods is a visible trend related to modelling in materials engineering [8,9]. ...
Purpose: The paper presents the new neural networks model making it possible to estimate the hardness of continuously-cooled steel from the austenitizing temperature. Design/methodology/approach: The method proposed in the paper employs two applications of the neural networks of: classification and regression. Classification and consists in determining the value of dichotomous variables describing the occurrence of: ferrite, pearlite, bainite and martensite in the microstructure of a steel. The values of dichotomous variables have been used for calculating steel hardness. The other task is regression, which aims at calculating the steel hardness. Findings: The presented neural networks model can be used only in the range of concentrations of alloying elements shown in this paper. Practical implications: The model worked out makes it possible to calculate hardness for the steel with a known chemical composition. This model deliver important information for the rational selection of steel for those parts of the machines that are subjected to the heat treatment. The presented model make it possible the analysis of the interaction of the chemical composition on the hardness curves of the steel cooled from the austenitizing temperature. Originality/value: The paper presents the method for calculating hardness of the structural and engineering steels, depending on their chemical composition, austenitizing temperature and cooling rate.
The article deals with the search for short-term trends based on the exchange rates of the leading currencies. A novel method of detecting patterns in trends written in a linguistic manner has been proposed. Linguistic variables take their values as a result of applying calculations in the Ordered Fuzzy Numbers notation. The solution is based on the application of fuzzification of the source data, using the transposition of the parameters (change direction, max, min, opening and closing prices) of the daily exchange rates of the EUR to USD currency pair. These exchange rate data for each trade day were recorded using single OFN numbers. This is an innovative application to the description of the Forex exchange rate notation allowing for the processing of five standard numerical data in one OFN. Then the data takes the form of linguistics. Based on the parameters set, the level of trend sequence similarity is determined. Parameters include: percent sequence compatibility of the trend with the frame set at the beginning, frame size, threshold and frequency. Undoubtedly, the analyzed patterns have different coefficients of similarity of the whole and individual elements. The study used a dedicated computer program that searches for patterns. The euro-dollar exchange rate from 1999–2019 served as the research material. These promising research are part of the rule-based forecasting methodology for financial applications.
