Detection and Dispersion Analysis of Water Globules in Oil Samples Using Artificial Intelligence Algorithms.

Fluid particle detection technology is of great importance in the oil and gas industry for improving oil-refining techniques and in evaluating the quality of refining equipment. The article discusses the process of creating a computer vision algorithm that allows the user to detect water globules in oil samples and analyze their sizes. The process of developing an algorithm based on the convolutional neural network (CNN) YOLOv4 is presented. For this study, our own empirical base was proposed, which comprised microphotographs of samples of raw materials and water-oil emulsions taken at various points and in different operating modes of an oil refinery. The number of images for training the neural network algorithm was increased by applying the authors' augmentation algorithm. The developed program makes it possible to detect particles in a fluid medium with the level of accuracy required by a researcher, which can be controlled at the stage of training the CNN. Based on the results of processing the output data from the algorithm, a dispersion analysis of localized water globules was carried out, supplemented with a frequency diagram describing the ratio of the size and number of particles found. The evaluation of the quality of the results of the work of the intelligent algorithm in comparison with the manual method on the verification microphotographs and the comparison of two empirical distributions allow us to conclude that the model based on the CNN can be verified and accepted for use in the search for particles in a fluid medium. The accuracy of the model was AP@50 = 89% and AP@75 = 78%.

Determining the Rheological Parameters of Polymers Using Artificial Neural Networks.

Artificial neural networks have great prospects in solving the problems of predicting the properties of polymers. The purpose of this work was to study the possibility of using artificial neural networks to determine the rheological parameters of polymers from stress relaxation curves. The nonlinear Maxwell-Gurevich equation was used as the deformation law. The problem was solved in the MATLAB environment. The substantiation for the choice of the neural network input and output parameters was made. An algorithm for obtaining the data for neural network training was also proposed. Neural networks were trained on theoretical stress relaxation curves constructed with the Euler method. The value of the mean square error (MSE) was used as a criterion for the performance of the training. The constructed model of the artificial neural network was tested on the experimental relaxation curves of recycled polyvinyl chloride. The quality of the experimental curve approximation was quite good and was comparable with the standard methods for processing stress relaxation curves. Unlike the standard methods, when using artificial neural networks, no preliminary data smoothing was required. It is possible to use the proposed technique for processing not only relaxation curves, but also creep curves as well as processing creep tests not only in central tension, but also in bending, torsion and shear.

Nonlinear Rheological Processes Modeling in Three-Layer Plates with a Polyurethane Foam Core.

INTRODUCTION: Three-layer structures with a polyurethane foam filler are widely used in construction as roofing and wall panels. The purpose of this work is to develop a method for calculating the bending of three-layer plates with a polyurethane foam filler, taking into account the nonlinear creep of the middle layer. The non-linear Maxwell-Gurevich equation is used as the polyurethane foam creep law. METHODS: In the article, the system of resolving the equations is obtained, and the solution is carried out numerically by the finite difference method in combination with the Euler method in a MATLAB environment. An analytical solution is also obtained for a plate hinged along the contour. RESULTS: The developed model and calculation algorithms are verified by comparison with the calculation in the ANSYS software package. A comparison with the calculation according to the linear theory is also carried out, and the effects caused by the non-linear creep of polyurethane foam are revealed. CONCLUSION: It has been established that when nonlinear creep is taken into account, in contrast to the linear law, the stresses in the plate are not constant in time. In the faces, at the initial stage, the stresses increase with a subsequent return to the initial values, and in the filler, on the contrary, the stresses at the initial stage decrease. These results indicate the need to take into account the nonlinear creep of polyurethane foam in the calculation of sandwich panels.

Optimization of Thick-Walled Viscoelastic Hollow Polymer Cylinders by Artificial Heterogeneity Creation: Theoretical Aspects.

A theoretical solution of the problem of thick-walled shell optimization by varying the mechanical characteristics of the material over the thickness of the structure is proposed, taking into account its rheological properties. The optimization technique is considered by the example of a cylindrical shell made of high-density polyethylene with hydroxyapatite subjected to internal pressure. Radial heterogeneity can be created by centrifugation during the curing of the polymer mixed with the additive. The nonlinear Maxwell-Gurevich equation is used as the law describing polymer creep. The relationship of the change in the additive content along with the radius r, at which the structure is equally stressed following the four classical criteria of fracture, is determined in an elastic formulation. Moreover, it is shown that a cylinder with equal stress at the beginning of the creep process ceases to be equally stressed during creep. Finally, an algorithm for defining the relationship of the additive mass content on coordinate r, at which the structure is equally stressed at the end of the creep process, is proposed. The developed algorithm, implemented in the MATLAB software, allows modeling both equally stressed and equally strength structures.