Predicting Diffusion Coefficients in Nafion Membranes during the Soaking Process Using a Machine Learning Approach.

Nafion, a versatile polymer used in electrochemistry and membrane technologies, exhibits complex behaviors in saline environments. This study explores Nafion membrane's IR spectra during soaking and subsequent drying processes in salt solutions at various concentrations. Utilizing the principles of Fick's second law, diffusion coefficients for these processes are derived via exponential approximation. By harnessing machine learning (ML) techniques, including the optimization of neural network hyperparameters via a genetic algorithm (GA) and leveraging various regressors, we effectively pinpointed the optimal model for predicting diffusion coefficients. Notably, for the prediction of soaking coefficients, our model is composed of layers with 64, 64, 32, and 16 neurons, employing ReLU, ELU, sigmoid, and ELU activation functions, respectively. Conversely, for drying coefficients, our model features two hidden layers with 16 and 12 neurons, utilizing sigmoid and ELU activation functions, respectively.

Optimizing Neural Networks for Chemical Reaction Prediction: Insights from Methylene Blue Reduction Reactions.

This paper offers a thorough investigation of hyperparameter tuning for neural network architectures using datasets encompassing various combinations of Methylene Blue (MB) Reduction by Ascorbic Acid (AA) reactions with different solvents and concentrations. The aim is to predict coefficients of decay plots for MB absorbance, shedding light on the complex dynamics of chemical reactions. Our findings reveal that the optimal model, determined through our investigation, consists of five hidden layers, each with sixteen neurons and employing the Swish activation function. This model yields an NMSE of 0.05, 0.03, and 0.04 for predicting the coefficients A, B, and C, respectively, in the exponential decay equation A + B · e-x/C. These findings contribute to the realm of drug design based on machine learning, providing valuable insights into optimizing chemical reaction predictions.

Mechanical Testing of Selective-Laser-Sintered Polyamide PA2200 Details: Analysis of Tensile Properties via Finite Element Method and Machine Learning Approaches.

This study delves into the mechanical characteristics of polyamide PA2200 components crafted using selective laser sintering (SLS) technology. Our primary objective is to analyze the tensile behavior of the components printed at various orientations, showing its response to diverse loading conditions. Finite element method (FEM) modeling was employed to analyze the tensile behavior of these details. The time determined for breaking the detail is 9 s. In addition we forecast key properties, such as tensile behavior and strength, using machine learning (ML) techniques, and the best models are for predicting relative elongation are KNeighborsRegressor and SVR.

Reuse and Mechanochemical Processing of Ore Dressing Tailings Used for Extracting Pb and Zn.

The increasing accumulation of rock waste obtained due to ore processing and its environmental impacts, such as acid mine drainage and elevated concentrations of heavy metals in soils, necessitates the transformation of mining technologies based on the concept of circular waste management. The research is aimed at improving the parameters of the mechanical activation effect produced on technogenic georesources, as well as at expanding the application scope of disintegrators in the field of using the partial backfill of the mined-out space when developing stratified deposits. In this regard, the research purpose was to substantiate the parameters of extracting metals from enrichment tailings using their mechanochemical activation to ensure cyclic waste management. The research involved the application of three-dimensional interpolation methods used for processing the data and the graphical representation. As a result, the following was found to be characteristic of the waste of the Sadonsky mine management. The degree of extracting zinc from pre-activated tailings increases logarithmically when the H2SO4 concentration and the NaCl proportion decrease 3.5 times. The degree of extracting lead from the activated tailings increases according to the Fourier law when decreasing the NaCl mass concentration, and an optimal range of the H2SO4 (0.38-0.51%) proportion decreases six times. One of the key results of the research is the justification of expanding the scope of applying disintegrators in the case of a directed activation influence exerted on the components of the stowing strips. The obtained results expand the understanding of the mechanism of the influence of the mechanochemical activation of dry tailings on the reactivity unevenness when extracting several metals from them.

Production of Workpieces from Martensitic Stainless Steel Using Electron-Beam Surfacing and Investigation of Cutting Forces When Milling Workpieces.

The aim of this study was to investigate cutting force when milling 40 × 13 stainless steel samples obtained via electron-beam surfacing. The samples were obtained by surfacing the wire made from the martensitic 40 × 13 stainless steel. The microstructure of the samples and the hardness are discussed in the present study. Emphasis is placed on the study of cutting forces when handling the samples. The structure of the samples obtained by electron-beam surfacing consisted of tempered martensite. The average hardness of the samples was similar to the hardness obtained after quenching and tempering the samples-576 HV for horizontally printed workpieces and 525 HV for vertically printed workpieces. High-speed milling, high-efficiency milling, and conventional milling have been proven to be suitable for handling such workpieces. This study shows that an increase in milling width leads to a gradual decrease in specific cutting force. As the milling depth increases, the specific cutting force decreases intensively at first but then more slowly with time. Machining the workpieces made of the martensitic stainless steel and produced by electron-beam surfacing requires the use of purely carbide mills with a diameter of at least 12 mm. Using a high-speed steel as a tool material results in the rapid failure of the tool. The cutting conditions during the investigation allowed for a decrease in the temperature of the cutting edge, cutting force, and the low-rigid end mill bending. Therefore, this study has made it possible to select modes that allow for a reduction in the vibration of the lathe-fixture-tool-part system.

Provision of Rational Parameters for the Turning Mode of Small-Sized Parts Made of the 29 NK Alloy and Beryllium Bronze for Subsequent Thermal Pulse Deburring.

The increase in the share of physical and technical processing methods in the arsenal of deburring technologies used in modern production is associated both with the use of difficult-to-machine materials, such as beryllium bronze and the 29 NK alloy, and with the need to solve technological problems for the production of small-sized products with hard-to-reach surfaces. The aim of the study is to improve the processes of blade processing of small-sized parts made of beryllium bronze and the 29 NK alloy to provide rational conditions for thermal pulse deburring. Surface samples were experimentally obtained after turning in different modes on a CITIZEN CINCOM K16E-VII automatic lathe equipped with an Applitec micromechanics tool. The surface quality and burr characteristics were examined using a JEOL JIB-Z4500 electron microscope and a ContourGT-K optical profilometer. The program Statistica 6 allowed processing of the results. The relationship between the parameters of the turning mode and the thickness of the root of the burrs formed on the machined surface, the limitation of which is one of the conditions for the application of the thermal pulse method, was established. The obtained empirical regression dependencies establish a rational range of cutting mode parameters, and the implementation of the formulated recommendations for setting blade modes ensures deburring by the thermal pulse method in compliance with the requirements of drawing under maximum processing performance.

Classification of Acoustic Influences Registered with Phase-Sensitive OTDR Using Pattern Recognition Methods.

This article is devoted to the development of a classification method based on an artificial neural network architecture to solve the problem of recognizing the sources of acoustic influences recorded by a phase-sensitive OTDR. At the initial stage of signal processing, we propose the use of a band-pass filter to collect data sets with an increased signal-to-noise ratio. When solving the classification problem, we study three widely used convolutional neural network architectures: AlexNet, ResNet50, and DenseNet169. As a result of computational experiments, it is shown that the AlexNet and DenseNet169 architectures can obtain accuracies above 90%. In addition, we propose a novel CNN architecture based on AlexNet, which obtains the best results; in particular, its accuracy is above 98%. The advantages of the proposed model include low power consumption (400 mW) and high speed (0.032 s per net evaluation). In further studies, in order to increase the accuracy, reliability, and data invariance, the use of new algorithms for the filtering and extraction of acoustic signals recorded by a phase-sensitive reflectometer will be considered.

Estimation and Prediction of the Polymers' Physical Characteristics Using the Machine Learning Models.

This article investigates the utility of machine learning (ML) methods for predicting and analyzing the diverse physical characteristics of polymers. Leveraging a rich dataset of polymers' characteristics, the study encompasses an extensive range of polymer properties, spanning compressive and tensile strength to thermal and electrical behaviors. Using various regression methods like Ensemble, Tree-based, Regularization, and Distance-based, the research undergoes thorough evaluation using the most common quality metrics. As a result of a series of experimental studies on the selection of effective model parameters, those that provide a high-quality solution to the stated problem were found. The best results were achieved by Random Forest with the highest R2 scores of 0.71, 0.73, and 0.88 for glass transition, thermal decomposition, and melting temperatures, respectively. The outcomes are intricately compared, providing valuable insights into the efficiency of distinct ML approaches in predicting polymer properties. Unknown values for each characteristic were predicted, and a method validation was performed by training on the predicted values, comparing the results with the specified variance values of each characteristic. The research not only advances our comprehension of polymer physics but also contributes to informed model selection and optimization for materials science applications.

The Technology of Using Liquid Glass Mixture Waste for Reducing the Harmful Environmental Impact.

The spent liquid glass mixture, which is widely used in foundries as a binder after knocking out of moldings, contains pieces of different sizes and strengths, and there is a strong silicate film on the sand grains themselves. The proposed regeneration plants, which provide for the removal of the silicate film by scrubbing, have low productivity and lead to abrasion of the grains themselves. For this reason, the knocked-out mixture is taken to the dump. As a result of the study of the state of the spent liquid glass mixture in the dump, it was found that, in the spent mixture that had lain for 8-10 years, under prolonged exposure to atmospheric precipitation at plus and minus temperatures, part of the silicate film dissolves and almost all monolithic pieces are destroyed. Further use of hydraulic regeneration allows us to reduce the film thickness and thereby reduce the percentage of liquid glass from 5-5.5% to 0.8-1.2%. This made it possible to select the composition of the molding sand for an automatic line, using the AlpHaset-process, which consists of 22-29% of liquid glass mixture from a dump, 65-72% of liquid glass, 5.5% of liquid glass, and a hardener in the amount of 0.55%.

The Use of Collections of Artificial Neural Networks to Improve the Control Quality of the Induction Soldering Process.

In industries that implement the technology of induction soldering, various sensors, including non-contact pyrometric ones, are widely used to control the technological process. The use of this type of sensor implies the need to choose a solution that is effective in different operating conditions in terms of the accuracy of the data obtained and the reliability of the measurement equipment and duplication in case of a failure. The present article discusses the development of intelligent technology based on a collection of artificial neural networks, which allows a number of problems associated with technological process control when using pyrometric sensors to be solved: assessing the quality of measurements, correcting measurements when non-standard errors are detected, and controlling the process of induction heating in the absence of reliable readings of the measurement instruments. The collection of artificial neural networks is self-configuring with the use of multicriterion genetic algorithms. The use of the proposed intelligent technology made it possible to improve the control quality of the technological process of the induction brazing of waveguide paths of spacecraft: the overregulation was decreased from 0-20 to 0, and the difference in the heating temperatures of the elements of the brazed waveguide assembly was decreased from 20-100 to 0-10. In addition, the overall process duration decreased and became more stable. When using the classical control technology, the time varied in the range of 20-60 s; when using the proposed technology, it stabilized in the range of 30-35 s.