Artificial Intelligence Approaches to Determine Graphite Nodularity in Ductile Iron

The complex metallurgical interrelationships in the production of ductile cast iron can lead to enormous differences in graphite formation and local microstructure by small variations during production. Artificial intelligence algorithms were used to describe graphite formation, which is influenced by a variety of metallurgical parameters. Moreover, complex physical relationships in the formation of graphite morphology are also controlled by boundary conditions of processing, the effect of which can hardly be assessed in everyday foundry operations. The influence of relevant input parameters can be predetermined using artificial intelligence based on conditions and patterns that occur simultaneously. By predicting the local graphite formation, measures to stabilise production were defined and thereby the accuracy of structure simulations improved. In course of this work, the most important dominating variables, from initial charging to final casting, were compiled and analysed with the help of statistical regression methods to predict the nodularity of graphite spheres. We compared the accuracy of the prediction by using Linear Regression, Gaussian Process Regression, Regression Trees, Boosted Trees, Support Vector Machines, Shallow Neural Networks and Deep Neural Networks. As input parameters we used 45 characteristics of the production process consisting of the basic information including the composition of the charge, the overheating time, the type of melting vessel, the type of the inoculant, the fading, and the solidification time. Additionally, the data of several thermal analysis, oxygen activity measurements and the final chemical analysis were included.Initial programme designs using machine learning algorithms based on neural networks achieved encouraging results. To improve the degree of accuracy, this algorithm was subsequently adapted and refined for the nodularity of graphite.

Mechanical properties of ductile cast iron relation to the charge elements

Summary In many recent publications on the optimisation of alloys in terms of, among other things, their strength and resistance to wear, a trend can be observed to look for new alloying additives to improve these properties. This paper presents the results of a study on the effect of changes in the chemical composition of EN-GJS-500-7 ductile alloy cast iron on its mechanical properties. In order to confirm the effect of alloying additives on the mechanical properties of the alloys, industrial melting of cast iron was carried out and samples were taken for testing. The smelts were not subjected to heat treatment, but were carried out differently in terms of the feedstock used and based on the analysis of the cooling curve using an automated smelting technology enabling the elimination of degraded Chunky graphite. The influence of the shape of graphite precipitates on tensile strength and hardness was determined, and spectroscopic studies of the microstructure of cast irons were carried out.

Locomotive engines and the future of railway automotive power in Africa: A review

This work presents the review of locomotives and the future of railway automotive power in Africa. Locomotives down time on account of inadequate spare parts still remains a challenge in African. It is thus, imperative to review the locomotives in African, to establish the current capabilities as well as provide recommendations to bridge the gaps and its extrapolated trends in future. Firstly, the comparison factors were track length, electrified rails, number of locomotives and yearly passengers on each of Egypt, Ghana, Kenya, Nigeria, South Africa and Zambia rails. Secondly, the focus was on engine parameters from literatures and maintenance logbooks of locomotives. From available data, it was found that South Africa and Egypt have more advanced rail system than the rest four selected countries. It was also found that additive manufacturing, 3D printing, ductile cast iron and die-forging can be used to produce the engine body for diesel engine using steel and aluminum alloys while aluminum silicon and tin doped with copper are good for reciprocation mechanisms. And finally, increased reliability of locomotives can be guided by an engine selection matrix, while use of renewable and energy hybridization are needed to meet the expansion of railroads in Africa.

Yield and fracture loci for a ductile cast iron EN-GJS-600-3 under biaxial stresses

Biaxial (axial and torsional loading) static tests were performed for the first time on EN-GJS-600–3 ductile cast iron tubular specimens obtained reproducing the solidification conditions typical of thick-walled castings. The experimental results were elaborated to determine the yield and fracture loci of the material, which exhibited significant deviations from those predicted by the Von Mises and Mohr-Coulomb criteria usually adopted for steels and grey cast iron, respectively. For this purpose, several alternative criteria proposed in the technical literature, some of them specifically devised for composite materials, have been calibrated and compared to account for the peculiar mechanical properties of this natural composite material.

High-temperature Cyclic Deformation Behavior and Damage-coupled Unified Viscoplastic Constitutive Model for a Ductile Cast Iron QTRSi4Mo1

Isothermal low cycle fatigue tests for a ductile cast iron QTRSi4Mo1 were carried out at 500°C and 760°C. The results showed that it exhibited initial cyclic hardening followed by saturation at 500°C, while gradual cyclic softening occurred at 760°C due to a more pronounced creep effect. A damage-coupled unified viscoplastic constitutive model incorporating two nonlinear and one linear strain range-dependent drag stress components was developed to model the distinct strain range-dependent deformation behaviors. The piecewise damage evolution law was introduced to reflect the slow linear and the rapid nonlinear evolution characteristics during the damage development. Furthermore, the parameter identification approach for the unified viscoplastic model was proposed, including the initial estimates combined with the genetic algorithm-based global optimization procedure. The results showed that the proposed damage-coupled viscoplastic model can simulate the cyclic deformation behaviors and predict the LCF failure life of the ductile cast iron QTRSi4Mo1.