Artificial Neural Networks in Classification of Steel Grades Based on Non-Destructive Tests

Artificial Neural Network Prediction of Compliance Coefficients for Composite Shear Keys of Built-Up Timber Beams

This article explores the possibility of predicting the compliance coefficients for composite shear keys of built-up timber beams using artificial neural networks. The compliance coefficients determine the stresses and deflections of built-up timber beams. The article analyzes current theoretical methods for designing wooden built-up timber beams with shear keys and possible ways of applying them in modern construction. One of the design methods, based on the use of the compliance coefficients, is also discussed in detail. The novelty of this research is that the authors of the article collected, analysed, and combined data on the experimental values of the compliance coefficient for composite shear keys of built-up timber beams obtained by different researchers and published in other studies. For the first time, the authors of this article generated a table of input and output data for predicting compliance coefficients based on the analysis of the literature and collected data by the authors. As a result of this research, the article's authors proposed an artificial neural network (ANN) architecture and determined the mean absolute percentage error for the compliance coefficients kw and ki, which are equal to 0.054% and 0.052%, respectively. The proposed architecture can be used for practical application in designing built-up timber beams using various composite shear keys.

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%.

Prediction of Mechanical Properties of Highly Functional Lightweight Fiber-Reinforced Concrete Based on Deep Neural Network and Ensemble Regression Trees Methods

Currently, one of the topical areas of application of artificial intelligence methods in industrial production is neural networks, which allow for predicting the performance properties of products and structures that depend on the characteristics of the initial components and process parameters. The purpose of the study was to develop and train a neural network and an ensemble model to predict the mechanical properties of lightweight fiber-reinforced concrete using the accumulated empirical database and data from construction industry enterprises, and to improve production processes in the construction industry. The study applied deep learning and an ensemble of regression trees. The empirical base is the result of testing a series of experimental compositions of fiber-reinforced concrete. The predicted properties are cubic compressive strength, prismatic compressive strength, flexural tensile strength, and axial tensile strength. The quantitative picture of the accuracy of the applied methods for strength characteristics varies for the deep neural network method from 0.15 to 0.73 (MAE), from 0.17 to 0.89 (RMSE), and from 0.98% to 6.62% (MAPE), and for the ensemble of regression trees, from 0.11 to 0.62 (MAE), from 0.15 to 0.80 (RMSE), and from 1.30% to 3.4% (MAPE). Both methods have shown high efficiency in relation to such a hard-to-predict material as concrete, which is so heterogeneous in structure and depends on many factors. The value of the developed models lies in the possibility of obtaining additional useful information in the process of preparing highly functional lightweight fiber-reinforced concrete without additional experiments.

The Application of a Hybrid Method for the Identification of Elastic-Plastic Material Parameters

The indentation test is a popular method for the investigation of the mechanical properties of materials. The technique, which combines traditional indentation tests with mapping the shape of the imprint, provides more data describing the material parameters. In this paper, such methodology is employed for estimating the selected material parameters described by Ramberg-Osgood's law, i.e., Young's modulus, the yield point, and the material hardening exponent. Two combined identification methods were used: the P-A procedure, in which the material parameters are identified on the basis of the coordinates of the indentation curves, and the P-C procedure, which uses the coordinates describing the imprint profile. The inverse problem was solved by neural networks. The results of numerical indentation tests-pairs of coordinates describing the indentation curves and imprint profiles-were used as input data for the networks. In order to reduce the size of the input vector, a simple and effective method of approximating the branches of the curves was proposed. In the Results Section, we show the performance of the approximation as a data reduction mechanism on a synthetic dataset. The sparse model generated by the presented approach is also shown to efficiently reconstruct the data while minimizing error in the prediction of the mentioned material parameters. Our approach appeared to consistently provide better performance on the testing datasets with considerably easier computation than the principal component analysis compression results available in the literature.

Synergetic Synthesis of Nonlinear Laws of Throttle Control of a Pneumatic Drive

Currently, a significant trend in control in robotic systems is developing and improving linear and nonlinear control algorithms to improve the overall quality of production with high accuracy and adaptability. The present study considers a synergistic synthesis of throttle control of a pneumatic distributor valve and backpressure control for piston rod positioning. The article presents the synthesis of control laws for the position of a pneumatic cylinder piston using the method of analytical design of aggregated regulators (ADAR) of synergetic control theory (STC), which allows operation with nonlinear mathematical models, eliminating the loss of information about the object during linearization. A comparative calculation of the energy efficiency of backpressure control and throttle control methods was carried out, while the numerical value of the total airflow with throttle control is 0.0569 m3⁄s and, with backpressure control, it is 0.0337 m3⁄s. Using a P controller in a linear model gives a transient oscillatory process damped in 2–2.5 s. When using a PID controller, the process has an overshoot equal to 11.5%, while the synergistic controller allows you to smoothly move the drive stem to a given position without overshoot. The parametric uncertainty analysis of the considered mathematical model is carried out. The model’s main parameters are identified, which change the actual functioning of the system under study. The inconsistency of applying classical control laws based on typical controllers to parametrically indeterminate mathematical models is shown.

Enchainment of the Coefficient of Structural Quality of Elements in Compression and Bending by Combined Reinforcement of Concrete with Polymer Composite Bars and Dispersed Fiber

Polymer composite reinforcement (PCR) and its use to produce high-quality concrete with the right design and technological and formulation solutions can demonstrate the results obtained with the steel rebars. This article discusses the synergistic effect from the combined reinforcement of concrete with traditional polymer rods and dispersed fiber, which, as a result, lead to an increase in strength and deformation characteristics and an improvement in the performance of compressed and bent structural elements. The synergistic effect of the joint work of polymer rods and dispersed reinforcement is considered in the context of relative indicators (structural quality factor CSQ), showing the relationship between strength characteristics and concrete density. The behavior of glass fiber in a cement matrix and the nature of its deformation during fracture were studied by scanning electron microscopy. It is shown that the use of PCR and dispersed reinforcement makes it possible to increase the strength characteristics of concrete in bending. In quantitative terms, the achieved results demonstrated that the CSQ values of a beam reinforced with a PCR frame with the addition of glass fiber were 3.4 times higher compared to the CSQ of a beam reinforced with steel reinforcement frames. In addition, for a beam reinforced with a PCR frame with no fiber addition, the CSQ values were three times higher.

Nanomodification of Lightweight Fiber Reinforced Concrete with Micro Silica and Its Influence on the Constructive Quality Coefficient

A hypothesis was put forward that a nano-modifying additive of micro silica, which had a beneficial effect on achieving a perfect structure of heavy concrete, can also be effectively used in lightweight fiber-reinforced concrete. The nano-modifying additives of micro silica application in manufacturing lightweight fiber reinforced concrete products and structures can significantly enchain their strength characteristics without increasing their mass and consequently improve their design characteristics. The purpose of the work was to increase the structural quality coefficients for all types of strengths of lightweight fiber-reinforced concrete due to its modification with micro silica. The effect of nano-modifying additives of micro silica on the strength characteristics of lightweight fiber reinforced concrete was studied. The optimal amount of micro silica addition was experimentally confirmed and established of 10% of the cement mass. The coefficients of constructive quality for all experimentally determined strength characteristics of lightweight fiber-reinforced concrete modified with micro silica additives were calculated. The coefficient of constructive quality for tensile strength in bending of lightweight fiber reinforced concrete with additives was two and a half times higher than that of heavy concrete without additives and up to 37% higher than that of lightweight fiber-reinforced concrete without additives.

Influence of Mechanochemical Activation of Concrete Components on the Properties of Vibro-Centrifugated Heavy Concrete

One of the crucial problems in current construction is energy, resource, and material efficient technologies in both industrial and civil engineering, associated with new material manufacturing and building construction. This article is devoted to developing comprehensive technology for activation effects on concrete made by various production techniques: vibration, centrifugation, and vibro-centrifugation. The possibility of a significant improvement in the microstructure of concrete and obtaining materials with increased specified characteristics, depending on its manufacturing technology, were studied during the complex activation effect exposed to this concrete and its components. Chemical activation of water and mechanical activation of cement were considered. The urgency and prospects of double, complex mechanochemical activation of concrete mixture components were substantiated. It was proven that the complex mechanochemical activation of the concrete mixture components gives a synergistic effect in obtaining concrete composition with an improved structure and improved characteristics. Furthermore, the relationship between concrete production technology and the technology of activation of its components was established. It was revealed that the most effective is the complex mechanochemical activation of vibro-centrifuged concrete, which gives an increase in strength up to 30%. The study results indicate a further direction of development associated with an increase in variatropic characteristics using both prescription and technological factors.

Influence of Composition and Technological Factors on Variatropic Efficiency and Constructive Quality Coefficients of Lightweight Vibro-Centrifuged Concrete with Alkalized Mixing Water

Alkalization technology and its application to obtain high-performance concrete compositions is an urgent scientific problem that opens opportunities for improving building structures. The article is devoted to the new technology of manufacturing reinforced concrete structures with low energy consumption, resource, and labor intensity based on the improved variatropic configuration of vibro-centrifuged concrete using activated water with high pH. The synergistic effect of the joint use of the proposed novel solutions has been theoretically and experimentally proved. Thus, growth in physical and mechanical characteristics of up to 15–20% was obtained, the structure and its operational ability were improved (the effectiveness of structural improvement, expressed as a percentage, reached values over 70%, concerning control samples). A positive effect on the properties of vibro-centrifuged concrete over the entire thickness of the annular section has been revealed. A method for controlling the integral characteristics of concrete has been obtained. The possibility of regulating the variatropic structure and controlling the differential characteristics of vibro-centrifuged concrete has been established. An assessment of the constructive quality and variatropic efficiency of vibro-centrifuged concrete was carried out, and new calculated dependencies were proposed, expressed in the form of relative coefficients.

Optimization of Composition and Technological Factors for the Lightweight Fiber-Reinforced Concrete Production on a Combined Aggregate with an Increased Coefficient of Structural Quality

In recent years, developing lightweight concrete with both the necessary and sufficient strength characteristics is essential in the construction industry. This article studies the influence of the volumetric composition of lightweight fiber-reinforced concrete (LFRC) and the method of its distribution during the preparation of the fiber–concrete mixture on the strength and deformation characteristics of LFRC on a combined aggregate. The optimal grain size of the porous filler was calculated by the mathematical planning method of the experiment. Regression models of the strength and deformation characteristics on the volumetric content of fiber and its distribution method were obtained. The most effective combination of these factors has been determined. The model shows that the increase in compressive strength was 12%, the value of the prismatic strength increased by 25%, the bending tensile strength increased by 34%, and the axial tensile strength increased by 11%. The ultimate strains during axial compression decreased by 10%, axial tension decreased by 12%, and the elasticity modulus increased by 11% compared to the test results of the control composition samples without fiber and pumice. The coefficient of constructive quality (CCQ) of the LFRC on a combined aggregate compared to concrete with the control composition without fiber and pumice showed an increase of more than 32%. It was also found that fiber reinforcement with basalt fibers with a combination of heavy and porous aggregates achieves a synergistic effect together.

Improving the Structural Characteristics of Heavy Concrete by Combined Disperse Reinforcement

The development of perspective concrete mixes capable of resisting the action of external loads is an important scientific problem in the modern construction industry. This article presents a study of the influence of steel, basalt, and polypropylene fiber materials on concrete’s strength and deformation characteristics. A combination of various types of dispersed reinforcement is considered, and by methods of mathematical planning of the experiment, regression dependences of the strength and deformation characteristics on the combination of fibers and their volume fraction are obtained. It was shown that the increase in compressive strength was 35% in fiber-reinforced concretes made using a combination of steel and basalt fiber with a volume concentration of steel fiber of 2% and basalt fiber of 2%; tensile strength in bending increased by 79%, ultimate deformations during axial compression decreased by 52%, ultimate deformation under axial tension decreased by 39%, and elastic modulus increased by 33%. Similar results were obtained for other combinations of dispersed reinforcement. The studies carried out made it possible to determine the most effective combinations of fibers of various types of fibers with each other and their optimal volume concentration.

Quantitative Risk Assessment in Construction Disputes Based on Machine Learning Tools

A high monetary value of the construction projects is one of the reasons of frequent disputes between a general contractor (GC) and a client. A construction site is a unique, one-time, and single-product factory with many parties involved and dependent on each other. The organizational dependencies and their complexity make any fault or mistake propagate and influence the final result (delays, cost overruns). The constant will of the parties involved results in completing a construction object. The cost increase, over the expected level, may cause settlements between parties difficult and lead to disputes that often finish in a court. Such decision of taking a client to a court may influence the future relations with a client, the trademark of the GC, as well as, its finance. To ascertain the correctness of the decision of this kind, the machine learning tools as decision trees (DT) and artificial neural networks (ANN) are applied to predict the result of a dispute. The dataset of about 10 projects completed by an undisclosed contractor is analyzed. Based on that, a much bigger database is simulated for automated classifications onto the following two classes: a dispute won or lost. The accuracy of over 93% is achieved, and the reasoning based on results from DT and ANN is presented and analyzed. The novelty of the article is the usage of in-company data as the independent variables what makes the model tailored for a specific GC. Secondly, the calculation of the risk of wrong decisions based on machine learning tools predictions is introduced and discussed.

Spatiotemporal Monitoring and Evaluation Method for Sand-Filling of Immersed Tube Tunnel Foundation

The sand-filling method has been widely used in immersed tube tunnel engineering. However, for the problem of monitoring during the sand-filling process, the traditional methods can be inadequate for evaluating the state of sand deposits in real-time. Based on the high efficiency of elastic wave monitoring, and the superiority of the backpropagation (BP) neural network on solving nonlinear problems, a spatiotemporal monitoring and evaluation method is proposed for the filling performance of foundation cushion. Elastic wave data were collected during the sand-filling process, and the waveform, frequency spectrum, and time–frequency features were analysed. The feature parameters of the elastic wave were characterized by the time domain, frequency domain, and time-frequency domain. By analysing the changes of feature parameters with the sand-filling process, the feature parameters exhibited dynamic and strong nonlinearity. The data of elastic wave feature parameters and the corresponding sand-filling state were trained to establish the evaluation model using the BP neural network. The accuracy of the trained network model reached 93%. The side holes and middle holes were classified and analysed, revealing the characteristics of the dynamic expansion of the sand deposit along the diffusion radius. The evaluation results are consistent with the pressure gauge monitoring data, indicating the effectiveness of the evaluation and monitoring model for the spatiotemporal performance of sand deposits. For the sand-filling and grouting engineering, the machine-learning method could offer a better solution for spatiotemporal monitoring and evaluation in a complex environment.

Structural Monitoring of Underground Structures in Multi-Layer Media by Dynamic Methods

The actual problem of structural monitoring and modeling of dynamic response from buried building is considered in the framework of arbitrary dynamic load. The results can be used for designing underground transport constructions, crossings, buried reservoirs and foundations. In existing methods, the system of sensors that register the response to a dynamic action does not allow for effective interpretation of the signal without understanding the dynamic features and resonance phenomena. The analytical and numerical solution of the problem of the dynamics of a buried object in a layered medium is considered. A multilayer half-space is a set of rigidly interconnected layers characterized by elastic properties. At a distance, an arbitrary dynamic load acts on the half-space, which causes oscillations in the embedded structure, and the sensor system registers the response. The problem of assessing the dynamic stress-strain state (DSSS) is solved using Fourier transforms with the principle of limiting absorption. As an example, the behavior of an embedded massive structure of an underground pedestrian crossing under the influence of a dynamic surface source on a multilayer medium is considered, as well as instrumental support of the sensor system. The solution in the form of stress, strain and displacement fields is obtained and compared with the experimental data. The frequency-dependent characteristics of the system are determined and the possibility of determining the DSSS by a shock pulse is shown.