This paper presents the application of machine learning in the control of the metal melting process. Metal melting is a dynamic production process characterized by nonlinear relations between process parameters. In this particular case, the subject of research is the production of white cast iron. Two supervised machine learning algorithms have been applied: the neural network and the support vector regression. The goal of their application is the prediction of the amount of alloying additives in order to obtain the desired chemical composition of white cast iron. The neural network model provided better results than the support vector regression model in the training and testing phases, which qualifies it to be used in the control of the white cast iron production.
Experimental research of cutting force components during dry face milling operations are presented in the paper. The study was provided when milling of ductile cast iron alloyed with copper and its austempered ductile iron after the proper austempering process. In the study, virtual instrumentation designed for cutting forces components monitoring was used. During the research, orthogonal cutting forces components versus time were monitored and relationship of cutting forces components versus speed, feed and depth of cut were determined by artificial neural network and response surface methodology. An analysis was made regarding the consistency of the measured cutting forces and the values obtained from the model supported by an artificial neural network for the investigated interval of the cutting regime. Based on the results, an analysis of the feasibility of the application of austempered ductile iron in the industrial sector with the aspect of machinability as well as the application of the models based on artificial intelligence, was given. At the end of the presentation, the influence of the aforementioned cutting regimes on cutting force components is presented as well.
On the way to building smart factories as the vision of Industry 4.0, the casting process stands out as a specific manufacturing process due to its diversity and complexity. One of the segments of smart foundry design is the application of artificial intelligence in the improvement of the casting process. This paper presents an overview of the conducted research studies, which deal with the application of artificial intelligence in the improvement of the casting process. In the review, 37 studies were analyzed over the last 15 years, with a clear indication of the type of casting process, the field of application of artificial intelligence techniques, and the benefits that artificial intelligence brought. The goals of this paper are to bring to attention the great possibilities of the application of artificial intelligence for the improvement of manufacturing processes in foundries, and to encourage new ideas among researchers and engineers.
2 August 2016 in Facta Universitatis, Series: Mechanical Engineering
The aim of this study was to determine the connection between oscillations in operating pressure values and the appearance of various irregularities on machined surfaces. Such oscillations are a consequence of the high water pressure generated during abrasive water jet machining. Oscillations in the operating pressure values are periodic, namely due to the cyclic operation of the intensifier and the physical characteristics of water. One of the most common means of reducing this phenomenon is installing an attenuator in the hydraulic system or a phased intensifier system. The main hypothesis of this study was that the topography of a machined surface is directly influenced by the inability of the pressure accumulator to fully absorb water pressure oscillations. In this study, we monitored changes in hydraulic oil pressure values at the intensifier entrance and their connection with irregularities on the machined surface—such as waviness—when cutting aluminum AlMg3 of different thicknesses. Experimental research was conducted in order to establish this connection. Aluminum AlMg3 of different thicknesses—from 6 mm to 12 mm—was cut with different traverse speeds while hydraulic oil pressure values were monitored. The pressure signals thus obtained were analyzed by applying the fast Fourier transform (FFT) algorithm. We identified a single-sided pressure signal amplitude spectrum. The frequency axis can be transformed by multiplying inverse frequency data with traverse speed; in this way, a single-sided amplitude spectrum can be obtained, examined against the period in which striations are expected to appear (in millimeters). In the lower zone of the analyzed samples, striations are observed at intervals determined by the dominant hydraulic oil pressure harmonics, which are transferred to the operating pressure. In other words, we demonstrate how the machined surface topography is directly induced by water jet pressure frequency characteristics.