Artificial Neural Network Theory Research Articles

INVESTIGATION OF ENERGY EFFICIENCY OF WATER SUPPLY SYSTEM WHEN POWERED BY AN ALTERNATIVE ENERGY SOURCE

The nature of the efficiency change in pump systems powered by an alternative source of electricity in conditions of a given pressure stabilization is investigated. An electromechanical water supply system powered by an alternative energy source using a static compensator (STATCOM) is considered. The observer of energy efficiency of the pump installation based on theory of artificial neural networks, which training occurs on the basis of static characteristics of the unit, is constructed. The results and analysis of investigations of the efficiency level changes during a typical daily cycle of water consumption are shown. References 12, figure 5.

Structural Assembly Analysis of Concrete Buildings with Intelligent Finite Element Analysis

In recent years, with the rapid development of China’s construction industry, assembled buildings have become more and more common. In this context, China attaches great importance to the development of assembled buildings and has introduced a series of policies to support the promotion of assembled buildings. Assembled building technology has become relatively mature in some developed countries. From their experience, it can be learned that the construction of an assembled concrete structure technology system is the basis for the promotion of assembled concrete buildings. A factory-based production model enables prefabricated concrete elements to be produced to a good quality. The key to the technical system for the construction of assembled concrete structures is the connection of the prefabricated elements. At the same time, it is essential to consider not only the reliability of the structural performance of the assembled concrete structure but also the cost and safety of the design, production, transport, and construction processes. In fact, the safety of an assembled concrete structure depends to a large extent on whether the nodal connection technology meets the design and quality requirements. Unlike conventional cast-in-place concrete structures, the key nodes of assembled concrete structures have a greater impact on the mechanical properties of the load transfer. In other words, this influence is directly related to the design of the prefabricated elements. Hence, the mechanical properties of precast nodal joints, such as good stiffness, are essential for the structural safety of assembled buildings. In the case of assembled buildings, the correct form of nodal connection is decisive in ensuring that the connection meets the design and service requirements. In addition to this, the correct nodal connection form will ensure that the design life is maintained. The uneven quality of many prefabricated components has limited the promotion of assembled concrete structures and is a key constraint to their development. At this stage, there are no uniform standards for quality control systems and measures on site in China, and the level of technical management is not yet fully mature. What is more, the overall quality of construction personnel is not high enough, which might lead to some frequent issues with the quality of connections in the field during the actual construction process. As a result, the development of assembled concrete structures urgently requires perfect construction management standards as a guide for on-site joint construction, so as to guarantee the quality level of on-site joint construction. In order to study the force performance of assembled concrete structures, this paper establishes an analytical model for assembled concrete buildings based on the intelligent finite element method. To be specific, this research introduces artificial neural network theory into the structural analysis of assembled buildings and transports it into the finite element solution, thus forming an intelligent finite element method.

Nonlinear Reaction–Diffusion Equations with Delay: Partial Survey, Exact Solutions, Test Problems, and Numerical Integration

The paper describes essential reaction–diffusion models with delay arising in population theory, medicine, epidemiology, biology, chemistry, control theory, and the mathematical theory of artificial neural networks. A review of publications on the exact solutions and methods for their construction is carried out. Basic numerical methods for integrating nonlinear reaction–diffusion equations with delay are considered. The focus is on the method of lines. This method is based on the approximation of spatial derivatives by the corresponding finite differences, as a result of which the original delay PDE is replaced by an approximate system of delay ODEs. The resulting system is then solved by the implicit Runge–Kutta and BDF methods, built into Mathematica. Numerical solutions are compared with the exact solutions of the test problems.

Remanufacturing an evaluation system for electrical control systems of drilling rig based on the improved FCE and ANN.

The decision process of different remanufacturing schemes in an electronic control system has great fuzziness and uncertainty. Therefore, it is essential to use an appropriate method to show the characteristics of different schemes and support the users’ decision. Based on the concepts of the artificial neural network theory and the improved comprehensive evaluation method, the decision-making system of the electronic control remanufacturing scheme was constructed in the present study. In the first step, a classification method of parts is proposed from the perspective of manufacturing enterprises. Moreover, an artificial neural network model is used to determine parts of remanufacturing value. Then the pricing strategy is divided according to the users’ needs, and then a decision model is constructed. The combined subjective and objective methods are used to solve the compound weight of different equipment, and a set of improved fuzzy comprehensive decision methods is formed. Then the proposed model was applied to an electronic control transformation project as an example to evaluate the performance of different schemes. The evaluation results were consistent with the results of a third-party organization. It was concluded that the proposed scheme can be used as the theoretical basis to choose the best remanufacturing scheme to ensure the efficient operation of each part in an ECS.

Experimental Study of Language Models of "Transformer" in the Problem of Finding the Answer to a Question in a Russian-Language Text

The aim of the study is to obtain a more lightweight language model that is comparable in terms of EM and F1 with the best modern language models in the task of finding the answer to a question in a text in Russian. The results of the work can be used in various question-and-answer systems for which response time is important. Since the lighter model has fewer parameters than the original one, it can be used on less powerful computing devices, including mobile devices. In this paper, methods of natural language processing, machine learning, and the theory of artificial neural networks are used. The neural network is configured and trained using the Torch and Hugging face machine learning libraries. In the work, the DistilBERT model was trained on the SberQUAD dataset with and without distillation. The work of the received models is compared. The distilled DistilBERT model (EM 58,57 and F1 78,42) was able to outperform the results of the larger ruGPT-3-medium generative network (EM 57,60 and F1 77,73), despite the fact that ruGPT-3-medium had 6,5 times more parameters. The model also showed better EM and F1 metrics than the same model, but to which only conventional training without distillation was applied (EM 55,65, F1 76,51). Unfortunately, the resulting model lags further behind the larger robert discriminative model (EM 66,83, F1 84,95), which has 3,2 times more parameters. The application of the DistilBERT model in question-and-answer systems in Russian is substantiated. Directions for further research are proposed.

Применение нейронных сетей при построении нелинейных моделей полевых транзисторов

The nonlinear model of a field-effect transistor based on the mathematical apparatus of the theory of artificial neural networks was developed. The main feature of this model is the possibility of training neural networks used to approximate the current-voltage characteristic and the gate-drain and gate-source capacitances of a nonlinear transistor model by using optimization algorithms built into popular microwave CAD systems. This makes it possible to use the well-known advantages of neural networks in the problems of function approximation to increase the reliability of the results of non-linear modeling of microwave devices based on field-effect transistors.

English Process Assessment Based on Deep Learning and Cloud Computing

Summative assessment has long been the primary assessment method used in college English classes. Overemphasizing examinations has had a significant negative impact on foreign language instruction. We design and practice generative instructional objectives, open instructional activities, dynamic course resources, interactive instruction process, and developmental instructional assessment based on a cloud platform based on the basic idea of generative instruction and using the characteristics of a cloud computing platform. Measures to improve the generativeness of online classrooms have piqued students’ interest and enthusiasm for self-directed learning, allowing them to experience the joy of learning brought on by new technological advancements. We discovered that if you want to improve students’ language acquisition ability, you cannot just rely on assessment. The diversified process assessment can not only ensure that students complete their learning tasks efficiently and quickly but also ensure that students are assessed objectively and fairly. Using cloud computing, MATLAB algorithm, and artificial neural network theory, a mathematical model of an instruction quality assessment system is established in this paper. After the network has been trained, the quality of the instruction can be assessed, providing a useful reference point for future research into instruction quality assessment systems.

Evaluation Model of Student Satisfaction in International Student Education Based on Neural Networks

Artificial neural network (ANN) theory is a rapidly developing information science around the world. The Back Propagation (BP) network is one of many artificial neural network types. It is a multilayer feedforward network with sophisticated nonlinear mapping capabilities. It is actually a relatively complex and nonlinear comprehensive decision-making problem when taking into account the comprehensive evaluation of test scores based on evaluation indicators that reflect the quality of the test papers. The five major factors of education service quality are tentatively proposed in this paper, which uses a neural network to model and analyze it. This paper examines the five factors of the education service quality evaluation model one by one and analyzes the issues that exist in the education service quality of international students in China. According to empirical research, overall satisfaction with the quality of education service in Guangxi among foreign students in China is low, and subindicators of education service quality are unbalanced. This paper analyzes the reasons for this situation from the three levels of service consciousness, emotional investment, and professional quality and proposes that the main task of improving education service quality is to optimize the entire service process, in order to narrow the gap between foreign students’ expectations and actual perceptions of educational services.

The harmonic reduction techniques in shunt active power filter when integrated with non-conventional energy sources

<span>The article covers the control techniques of shunt active filters using switching devices using artificial neural network (ANN) Theory. The basic idea is to achieve perfect disturbance minimization in both steady and transient states. The paper talks about a four-legged converter with a voltage source that can adjust for biased currents and harmonic elements caused by non-linear loads. A shunt connected active filter is used to minimise harmonic currents. The new proposed ANN controller for the improvement of percent total harmonic distortion (THD) is in comparison. The entire power filter concept is based on a MATLAB-modeled with ANN controller. The proposed circuit in this research is studied under various operating situations and simulated, demonstrating the system's potential.</span>

МАТЕМАТИЧЕСКАЯ МОДЕЛЬ ДЛЯ РАЗРАБОТКИ ТЕХНОЛОГИЧЕСКОЙ ЛИНИИ ПО ПРОИЗВОДСТВУ ГУМИНОВЫХ УДОБРЕНИЙ НА ОСНОВЕ МОДУЛЬНОГО ОБОРУДОВАНИЯ

The development of organic agricultural production in Russia is hampered by the lack of the necessary organic fertilizers as modern technological lines processing peat, brown coal, sapropel, and biohumus are still unavailable. Because of the need for such technological lines, a mathematical model has been developed to describe the hydromechanical and mechanical processes, enabling operators to select the operating mode parameters of the technological line. For the first time, the proposed model can be used to form a suspension with the required fineness in a hydromechanical cleaner and reactor. The authors propose a technique for assembling technological lines based on modular equipment to process organic raw materials that ensures the industrial productivity and quality of humic fertilizers. It is shown that the presented mathematical model fully complies with the real technological production requirements and can be used for theoretical and engineering analysis. The mathematical model of the technological line processing organic raw materials is based on the theory of artificial neural networks. The model can be further improved to be used in the system for automatizing technological operations and monitoring the quality indicators of modular equipment in the processing of organic raw materials. This will provide a new level of synthesizing complex technical systems, which will be beneficial for agricultural roduction.

Intelligent Technologies and Robotic Machines for Garden Crops Cultivation

The existing models of industrial robots cannot perform technological processes of apple harvesting. It is noted that there is a need for developing special actuators, grippers and new control algorithms for harvesting horticulture products. (Research purpose) The research aimed to develop an intelligent control system for horticulture industrial technologies and robotic techniques for yield monitoring and fruit harvesting. (Materials and methods) The research methodology was based on such modern methods as computer modeling and programming. In particular, the following methods were applied: systems analysis, artificial neural networks theory, pattern recognition, digital signal processing. The development of software, hardware and software was carried out in accordance with the requirements of GOST technical standards. The following programming languages were used: (C / C ++)-based OpenCV library, Spyder Python Development Environment, PyTorch and Flask frameworks, and JavaScript. Image marking for training neural networks was carried out via VGG ImageAnnotator and in Labelbox. The design process was based on the finite element method, CAD SolidWorks software environment. (Results and discussion) An intelligent management system for horticulture industrial technologies has been created based the on the «Agrointellect VIM» hardware and software complex. The concept of the system is shown to be implemented via computer and communication technology, robotic machines, the software for collecting, organizing, analyzing and storing data. The gripper proves to fix an apple gently and holds it securely. Depending on the size, the fruit fixation time is 1.5-2.0 seconds, the fruit maximum size is 85 per 80 millimeters , and its maximum weight is 500 grams. (Conclusions) The developed intelligent control system for industrial technologies based on «Agrointellect VIM» hardware and software complex ensures the efficient real-time processing of information necessary for the design of intelligent agricultural technologies using robotic machines and artificial intelligence systems.

Development and comparison of the techniques for solving the inverse problem in photoacoustic characterization of semiconductors

In this work, theoretically/mathematically simulated (TMS) model is presented for the photoacoustic (PA) frequency response of a semiconductor in a minimum volume PA cell. By analyzing of the TMS model, the influences of thermal diffusivity and linear coefficient of thermal expansion on silicon sample PA frequency response were investigated and two methods were developed for their estimation. The first one is a self consistent inverse procedure for solving the exponential problems of mathematical physics, based on regression. The second one, a well trained three-layer perceptron with back propagation, based upon theory of artificial neural networks, is developed and presented. These two inverse problem solving concepts are applied to thermo-elastic characterization of silicon, compared and discussed in the domain of semiconductor characterization.

Foreign Trade Export Forecast Based on Fuzzy Neural Network

This article first analyzes the significance and methods of foreign trade export forecasting and determines the index system of foreign trade export forecasting by analyzing the results of foreign trade export forecasting research at home and abroad. Subsequently, the related concepts and principles of artificial neural network and fuzzy theory are explained, the types and training algorithms of the fuzzy neural network are introduced, and the neural network and fuzzy theory are combined to establish the prediction model. Finally, according to the characteristics of foreign trade exports, this article comprehensively considers the influence of various factors, applies the fuzzy neural network model to the foreign trade export forecast, introduces the whole process of the establishment of the fuzzy neural network forecasting model in detail, and predicts the change interval of foreign trade exports.

Predicting airline passengers’ loyalty using artificial neural network theory

The study explores a model for predicting airline loyalty using the antecedents indicated in previous studies. Data was collected using a questionnaire distributed to 614 domestic air passengers using the snowball sampling method. The measurement tool had 16 scale items constructed on the recommendations of previous studies. Passenger satisfaction, airline service quality, passenger perceived value, and airline image are identified as determinants for airline loyalty. The predictive analytical approach of Artificial Neural Network theory and covariance-based Structural Equation Modelling for determining causality is employed in the study. The artificial neural network model predicts airline loyalty with 89% accuracy. Sensitivity analysis suggests passenger satisfaction as the most significant predictor of airline loyalty. The causal study supports that passenger satisfaction mediates the relationship between airline service quality and airline loyalty.

ПОВЫШЕНИЕ ЭФФЕКТИВНОСТИ ДЕЯТЕЛЬНОСТИ ПРЕДПРИЯТИЯ НА ОСНОВЕ ПРИМЕНЕНИЯ МЕТОДА ДЕРЕВА РЕШЕНИЙ

The article is devoted to considering the use of the decision tree method, defects at a machine-building enterprise, the reasons for having defects in the product and proposals for amending the normative and technical documentation. At the moment, non-destructive diagnostics methods have become widespread, which make it possible to determine the places of fault localization and predict the object state without the need for research which requires making object inoperative or its dismantling. The construction of the diagnostic models is implemented using the methods and tools of regression analysis, the theory of artificial neural networks, etc. However, they do not have a high level of generalization, and neural networks are difficult to interpret, which complicates their application in practice.

Prediction of Pile Bearing Capacity Using Artificial Neural Networks.(Dept.C)

It is well known that the human brain has the advantage of handling disperse and parallel distributed data efficiently. On the basis of this fact, artificial neural networks theory was developed and has been applied to various fields of science successfully. In this study, error back propagation neural networks were utilized to predict the working bearing capacity of piles. The data of performed pile load tests are used to verify the applicability of the presented neural network procedure. The results showed that the maximum error of prediction did not exceed 25%. Thus, the use of Neural Networks to predict pile capacity seems to be feasible for practical purpose.

Research on Image Super-resolution Reconstruction Based on Deep Learning

Image super-resolution processing technology refers to the technology of reconstructing high-resolution images by using low-resolution images with mutual displacement of multiple frames of the same scene. At present, image super-resolution processing technology is widely used in image reconstruction in various fields, such as: medical images, remote sensing images, robot vision, etc. In recent years, deep learning has also been widely used in various fields, especially in computer vision and speech processing. Since image super-resolution reconstruction the method of deep learning is introduced into the technology. Due to the good performance advantages of the deep learning method, it has become an important method for the research of image superresolution reconstruction technology. In this paper, the current status of domestic and foreign research on image super-resolution reconstruction is first simplified. Then, the theory of deep learning was explained, mainly the artificial neural network theory, the related theory of super-resolution reconstruction based on deep learning, and the method of image super-resolution reconstruction based on deep learning.

МОДЕЛИРОВАНИЕ НЕЙРОПРОГНОЗИРУЮЩЕГО УПРАВЛЕНИЯ ДОЖДЕВАЛЬНЫМИ МАШИНАМИ

The purpose of the study is to develop new scientific approaches to improve the efficiency of irrigation machines. Modern digital technologies allow the collection of data, their analysis and operational management of equipment and technological processes, often in real time. All this allows, on the one hand, applying new approaches to modeling technical systems and processes (the so-called “data-driven models”), on the other hand, it requires the development of fundamentally new models, which will be based on the methods of artificial intelligence (artificial neural networks, fuzzy logic, machine learning algorithms and etc.).The analysis of the tracks and the actual speeds of the irrigation machines in real time showed their significant deviations in the range from the specified speed, which leads to a deterioration in the irrigation parameters. We have developed an irrigation machine’s control model based on predictive control approaches and the theory of artificial neural networks. Application of the model makes it possible to implement control algorithms with predicting the response of the irrigation machine to the control signal. A diagram of an algorithm for constructing predictive control, a structure of a neuroregulator and tools for its synthesis using modern software are proposed. The versatility of the model makes it possible to use it both to improve the efficiency of management of existing irrigation machines and to develop new ones with integrated intelligent control systems.

Consumer Decision‐Making Power Based on BP Neural Network and Fuzzy Mathematical Model

In real life, because of the uncertainty of risk, incomplete information, perceived cost, and other factors, there are irrational behaviors in the decision‐making power of consumers, so it is of great practical significance to study the decision‐making power of consumers in the choice of countermeasures and personalized product recommendation. The purpose of this paper is to analyze the decision‐making power of consumers based on the BP neural network and fuzzy mathematical model. First, the basic theory of artificial neural network and the concepts of set theory and fuzzy reasoning of fuzzy mathematics are described. Second, the behavior prediction model with the equal emphasis on rationality and irrationality and the integration of artificial neural network and fuzzy mathematics are constructed. The comments of a certain mobile phone are selected as the experimental objects to analyze the decision‐making reasoning and prediction of individual consumers in the network and the decision‐making reasoning of group consumers in the network, the experimental results show that through Mamdani reasoning, behavioral intention = 5.72. Through the fuzzy set processing, it is finally determined that the consumer’s purchase intention is close to the VT mode, which is “very inclined.” In the first method, the user’s recognition rate of product C1 is 82%, and in the second method, the user’s recognition rate is 55%. The comparison of the two methods is in line with the expectation. The first method extracts the user’s emotion and evaluation information from the comments, fully considers the personalized needs of consumers, and is closer to the prediction results of the system.

Optimization and Simulation of Enterprise Management Resource Scheduling Based on the Radial Basis Function (RBF) Neural Network.

In the human resource system of modern enterprises, human-post matching big data occupies an important irreplaceable position. With the deepening of the reform of state-owned enterprises, some shortcomings of human-post matching big data have become prominent. The purpose of this article is to solve the current state-owned enterprises. There are a variety of problems with big data in the enterprise, and an effective method is found that can accurately evaluate the degree of human-job matching in state-owned enterprises and provide a scientific basis for the manager of talent and resource allocation to make more rational decisions. Through the radial basis function (RBF) neural network-based big data model of human-post matching evaluation of state-owned enterprises, we scientifically and effectively evaluate the matching degree of the quality and ability of the personnel with the relevant requirements of the position and then help the company to adjust the personnel at any time changes in positions to maximize the efficiency of human resources. In this paper, considering the actual situation of the enterprise, the RBF neural network and the analytic hierarchy process (AHP) method are used comprehensively. Firstly, the AHP is used to obtain the weight of each evaluation index in the human-post matching index system. At the same time, the artificial neural network theory is self-adapting. Learning is helpful to solve the problem that the AHP method is too subjective. The two learn from each other's strong points and combine their weaknesses organically to increase the convenience and effectiveness of evaluation.