Surface quality is one of the most important indicators of the quality of machined parts. The analytical method of defining the arithmetic mean roughness is not applied in practice due to its complexity and empirical models are applied only for certain values of machining parameters. This paper presents the design and development of artificial neural networks (ANNs) for the prediction of the arithmetic mean roughness, which is one of the most common surface roughness parameters. The dataset used for ANN development were obtained experimentally by machining AA7075 aluminum alloy under various machining conditions. With four factors, each having three levels, the full factorial design considers a total of 81 experiments that have to be carried out. Using input factor-level settings and adopting the Taguchi method, the experiments were reduced from 81 runs to 27 runs through an orthogonal design. In this study we aimed to check how reliable the results of artificial neural networks were when obtained based on a small input-output dataset, as in the case of applying the Taguchi methodology of planning a four-factor and three-level experiment, in which 27 trials were conducted. Furthermore, this paper considers the optimization of machining parameters for minimizing surface roughness in machining AA7075 aluminum alloy. The results show that ANNs can be successfully trained with small data and used to predict the arithmetic mean roughness. The best results were achieved by backpropagation multilayer feedforward neural networks using the BR algorithm for training.
Mechanical engineering plays an important role in the design and manufacture of medical devices, implants, prostheses, and other medical equipment, where the machining of bio-compatible materials have a special place. There are a lot of different conventional and non-conventional types of machining of biocompatible materials. One of the most frequently used methods is milling. The first part of this research explores the machining parameters optimization minimizing surface roughness in milling titanium alloy Ti-6Al-4V. A full factorial design involving four factors (cutting speed, feed rate, depth of cut, and the cooling/lubricating method), each having three levels, implies the 81 experimental runs. Using the Taguchi method, the number of experimental runs was reduced from 81 to 27 through an orthogonal design. According to the analysis of variance (ANOVA), the most significant parameter for surface roughness is feed rate. The second part explores the possibilities of using different ML techniques to create a predictive model for average surface roughness using the previously created small datasets. The paper presents a comparative analysis of several commonly used techniques for handling small datasets and regression problems. The best results indicate that the widely used machine learning algorithm Random Forest excels in handling regression problems and small datasets.
This paper presents the development and evaluation of neural network models using a small input–output dataset to predict the thermal behavior of a high-speed motorized spindles. Different neural multi-output regression models were developed and evaluated using Keras, one of the most popular deep learning frameworks at the moment. ANN was developed and evaluated considering the following: the influence of the topology (number of hidden layers and neurons within), the learning parameter, and validation techniques. The neural network was simulated using a dataset that was completely unknown to the network. The ANN model was used for analyzing the effect of working conditions on the thermal behavior of the motorized grinder spindle. The prediction accuracy of the ANN model for the spindle thermal behavior ranged from 95% to 98%. The results show that the ANN model with small datasets can accurately predict the temperature of the spindle under different working conditions. In addition, the analysis showed a very strong effect of type coolant on spindle unit temperature, particularly for intensive cooling with water.
The performances of high-speed machine tools depend not only on the speed, power, torque, dynamic and static stiffness, but also on the thermal behavior of the spindle. These parameters directly affect the productivity and quality of machining operations. This paper presents a 3-D finite element thermal model, which was based on the thermo mechanical bearing model and the numerical model of the spindle. Based on thermo mechanical analysis of bearings with angular contact, generated heat and thermal contact resistance are determined for each position of the ball. To provide the most accurate analysis possible in determining thermal contact resistance , bearings are divided into several zones based on the geometry of their cross-section. The aforementioned constraints have been applied to the 3-D FEM model which allowed for establishing temperature field distribution, and spindle thermal balance. In order to prove the efficacy of the proposed model, experimental measurements of spindle and bearing temperatures were done by using thermocouples and thermal imager.
Self-excited vibrations represent one of the most unfavorable phenomena in the cutting process because they can lead to the accelerated wear or breakage of the tool, a sudden deterioration in the quality of the machined surface, and an increase in noise and energy consumption. To avoid these negative effects, stability diagrams are used when defining the cutting regimes, which, depending on the main spindle speed and the cutting depth, show the border between the stable and unstable machine tool operation states from the aspect of self-excited vibrations. These diagrams, known as “stability lobe diagrams”, can be defined using mathematical models (analytical or numerical) or through experimental methods. However, when machining at relatively low main spindle revolutions, process damping occurs, which increases the system stability, i.e., enables a greater cutting depth limit. For the stability diagram to be effectively used for predicting the cutting depth limits at low machining speeds, it is necessary to take the effect of process damping into account. This paper introduces an experimental method for the determination of process damping and its integration into the mathematical framework of the Fourier series method, commonly utilized for the construction of stability lobe diagrams.
Mechanical engineering plays an important role in the design and manufacture of medical devices, implants, prostheses, and other medical equipment, where the machining of bio-compatible materials have a special place. There are a lot of different conventional and non-conventional types of machining of biocompatible materials. One of the most frequently used methods is milling. The first part of this paper considers the optimization of machining parameters for minimizing surface roughness in milling biocompatible alloy Ti-6Al-4V. With four factors (cutting speed, feed rate, depth of cut, and cooling/lubricating method), each having three levels, the full factorial design implies 81 experiments have to be carried out. Using the Taguchi method, the experiment number was reduced from 81 to 27 runs through an orthogonal design. According to the analysis of variance (ANOVA), the most significant parameter for surface roughness is feed rate. In the second part possibilities of different ML techniques to create a predictive model for average surface roughness using previously created small dataset are explored. Several ML technologies and techniques that can deal successfully with small dataset were explored. The best results show commonly used machine learning algorithm Random Forest that is widely used in regression problems.