Papers by Keyword: Prediction

Abstract: In this scientific study, the main properties of structurally inhomogeneous materials are predicted by computer modelling methods. The automatic combination of a scanning microscope and a program cell makes it possible to view the procedure in detail before and after etching with the necessary increase in resolution. Based on the results obtained, we constructed a graphical dependence of the particle sizes of 40 XН steel on the iterative process, and also studied in detail the procedure for the effect of different particle sizes on porosity. We modelled 2D and 3D drawings of the PRT – 7 shaft part. We justified the predicted number of properties, in particular: porosity, particle shape, grain size, microstructure of the sample surface, pre-etching process, post-etching process, as well as the main advantages of the iterative process.

Abstract: Machine learning is used in many fields nowadays to predict events, be it a pure classification or the prediction of certain values. Thus, these methods are also increasingly used in mechanical joining technology, for example for the prediction of joint strengths, in the classification of defects and rivet head positions or in the prediction of discrete result values such as interlock. This paper further shows how the complete joint contour including the output of stresses, strains and damage can be predicted and visualized in real time for self-piercing riveting with semi-tubular rivet. First, classical sampling is carried out in experiments with steel and aluminum sheets of different types and thicknesses. These are used as a basis for the qualification of the numerical simulations. For this validation experiments and simulations are compared via joint contour and force curves. For the simulations validated in such way several tool variants are carried out in variation calculations for each material-thickness combination. The simulation meshes of the thus generated database are standardized with respect to comparability (same number of nodes) and a data reduction is performed. After testing different approximation approaches, the best possible results are predicted and can be visualized in the developed software demonstrator.

Abstract: Palm Fatty Acid Distillate (PFAD) consists of more than 80% of free fatty acids, primarily palmitic acid and oleic acid, which can be esterified and added to the biofuel and oleo-chemical industries as feedstock. Oleic Acid is also known as cis-9-octadecenoic acid has the chemical formula C₁₈H₃₄O₂ or (CH₃(CH₂)₇CHCH(CH₂)₇COOH). There have been numerous studies that demonstrate the nutritional value of oleic acid. The objectives of this research were to simulate the mechanism reaction design for Molecularly Imprinted Polymer (MIP) synthesis and to predict the bonding formed after synthesis by comparing the monomers and template. The mechanism and complexes formed were drawn according to the theoretical mechanism of MIP. The chemicals involved were allylthiourea as the monomer, oleic acid as the template, ethylene glycol dimethacrylate (EGDMA) as the cross-linker, 2,2-azobisisobutyronitrile (AIBN) as the initiator, and acetonitrile as porogenic solvent. The monomer, allylthiourea was compared with the other two monomers which are vinylpyridine and acrylamide in MIP synthesis prediction. On average, when the allylthiourea was used as the monomer, the bond length was quite similar for each connection of atoms (1.316 Angstrom). However, when the vinylpyridine and acrylamide were used as the monomers, the length of the bonds was not similar to each other. On top of that, the bond angles prediction for allylthiourea-oleic acid complex agreed with the molecular geometry shape was tetrahedral due to the average angle was 109.5^o. Next, two different templates; oleic acid and palmitic acid; were compared in MIP synthesis prediction. The bond length for oleic acid was on average quite similar to each other (1.316 Angstrom) whereas for palmitic acid as the template the bond length was not similar. The palmitic acid-allylthiourea complex showed the angles reading was not synchronized to each other and quite unstable, unlike the oleic acid-allylthiourea complex. The results agree that oleic acid as the template was the best in this setting parameter for MIP synthesis.

Abstract: In this paper, we present a modeling of the photovoltaic array in order to tracking the maximum power point (MPPT) using a soft computing approach based on artificial neural network, The maximum power point tracking MPPT play a crucial role in photovoltaic systems for their ability to maximize the power output under varying conditions; The photovoltaic array modeled and implemented in matlab simulink environnement using the conventional perturb and observe algorithm for multiple ranges under varying temperatures and irradiances levels, a feed forward neural network collect the training data from the photovoltaic array simulink model, after the training process check, the neural network model tested with new temperatures and irradiance data to predict the maximum power point of the photovoltaic array, The developed neural network model shown an interesting results compared to simulink model based on classic perturb and observe algorithm.

Abstract: Geotechnical structures, design of embankment, earth and rock fill dam, tunnels, and slope stability require further attention in determining the shear strength of soil and other parameters that govern the result. The shear strength of soil commonly obtained by conducting laboratory testing such as Unconfined Compression Strength (UCS) Test and Unconsolidated Undrained (UU) Test. However, random errors and systematic errors can occur during experimental works and caused the findings imprecise. Besides, the laboratory test also consuming a lot of time and some of them are quite costly. Therefore, soft computational tools are developed to improve the accuracy of the results and time effectively when compared to conventional method. In this study, Artificial Neural Network (ANN) was employed to develop a predictive model to correlate the moisture content (MC), liquid limit (LL), plastic limit (PL), and liquidity index (LI) of cohesive soil with the undrained shear strength of soil. A total of 10 databases was developed by using MATLAB 7.0 - matrix laboratory with 318 of UCS tests and 451 of UU tests which are collected from the verified site investigation (SI) report, respectively. All the SI reports collected were conducted in Sarawak, Malaysia. The datasets were split into ratio of 3:1:1 which is 60:20:20 (training: validation: testing) with one hidden layer and eight hidden neurons. The input parameter of Liquidity index (LI) has shown the highest R-value (regression coefficient) which are 0.926 and 0.904 for UCS and UU model, respectively. In addition, the predictive models were tested and compare with the predicted and observed cohesion obtained from the collected experimental results. In summary, the ANN has the feasibility to be used as a predictive tool in estimating the shear strength of the soil.

Abstract: The strength of materials is determined by their atomic molecular structure and the process of decay of atomic molecular bonds, which must be taken into account when optimizing materials strength control technologies. The fracture photomicrograph of metal microdamage of welded joint at various moments of time, a multilevel model of flow of acoustic emission signals of materials are presented. The physical meaning, the scale level of parameters included in the model are revealed. The structure of the mathematical model of the flow of AE signals with components of its informative elements of different scale level by strength characteristics of structural materials and resource of technical objects is shown. The multilevel model of the AE signal flow is hierarchically structured, obtained by generalizing deterministic-statistical variability. It describes the process of randomly recording deterministic accumulated damages in the material both before and after the formation of a crack at the stage of waiting for its next leap. It is shown that the proposed nanotechnology of strength control of materials is reduced to non-destructive determination of parameters of prognostic homogeneous destruction, identification of which is based on multilevel modeling of time dependence of micro-crack formation, formulation of criterion of strength homogeneity, registration of AE parameters related to the model of a specific product, which can be automated processing of registration results and determination of universal strength nanoconstants from already published reference data of fatigue tests of standard material samples.

Abstract: Numerical simulation and prediction of grain formation and defects, including the stray grain and high angle orientation deviation during directional solidification process of a single crystal superalloy hollow turbine blade are experimentally conducted by means of commercial software ProCAST and backscattering scanning electron microscope. The results show that the initial nucleation amount at the beginning section of the starter block is 10⁴ of magnitude, and the number of grains decreases gradually with the competitive growth, and the number is about 100 at the spiral of the selector. And the orientation distribution of grains is close to <001> direction, with the orientation deviation between 10° and 15°. Moreover, with the increase of withdrawal rate, the curvature of isoline of liquidus of single crystal blade increases, and the tendency to form stray grains defects increases. The grain with a large deviation from orientation blocks the growth of other grains at the first rotating transition site of the selector, and then gradually grows and solidifies to form the final blade.

Abstract: The article provides the results of a statistical research of the relation of mechanical properties and chemical composition of Ø 15-rolled, forged, and pressed bars made of various modifications of the Ti-6Al-4V titanium alloy. The authors studied the correlation of mechanical properties and the content of alloying elements, impurities, bar diameter, and post-annealing (using various industrial modes) structural parameters, on the basis of the analysis of production data, and established regression dependencies for estimating average values of mechanical properties of bars on aluminum and molybdenum strength equivalents of alloying elements and impurities.

Abstract: The need to develop new methods for predicting the properties of polymeric materials is also justified by the goal of designing new innovative materials with the required functional properties and increased competitiveness. The classical methods for predicting deformation processes of polymeric materials are based on the numerical solution of integral constitutive equations for polymer viscoelasticity of the Boltzmann-Volterra type, which do not consider corrections for the irreversibility of the plastic component of deformation and therefore can lead to significant prediction errors. To improve the accuracy of predicting the deformation processes of polymer materials it is proposed to introduce a physically justified correction with account for the irreversibility of the plastic component of deformation. The introduction of this correction significantly increases the reliability and accuracy of predicting the functional and operational properties of polymer materials. The article suggests demonstrating the methods for predicting deformation processes with the example of the polyester textile yarn made of polyester fibers. Unlike many other synthetic fibers, the polyester ones have such important properties as structural stability, softness along with high strength, elasticity, resilience, tensile strength, crease and pilling resistance, temperature regulation, shape retention, etc. The polyester fiber has a hollow structure and its single components have the form of spiral springs which give the effect of a springy base when intertwined.

Abstract: Tapioca starch adulterated with dolomite is sold in markets, but this adulteration cannot be identified by normal visual inspection. Near infrared (NIR) hyperspectral imaging has been successfully used as a non-destructive method of identifying various characteristics of food, therefore it was tested to identify dolomite adulteration. Adulterated tapioca starch samples were prepared by adding dolomite in the range of 0.5-100% (wt/wt). Samples (N=400) of pure tapioca starch (0) and adulterated tapioca starch (1) were divided into calibration set (N=300) and a prediction set (N=100). All samples were scanned using NIR hyperspectral imaging (935-1720 nm) and spectra were pre-processed using Savitzky-Golay first derivative differentiation pretreatment in order to obtain the optimal conditions for establishing a classification model. Partial least squares-discriminant analysis was carried out to evaluate the accuracy of classification tapioca starch adulterated with dolomite. The results showed the total accuracy of prediction for classification was 100%. Therefore, NIR hyperspectral imaging was demonstrated to have a potential for use in detecting adulteration of tapioca starch with dolomite.