The paper presents the results of research on the development of an algorithm for identifying the moment of the beginning of slag lapse during the functioning of the metallurgical unit "steel ladle-intermediate l...
The paper presents the results of research on the development of an algorithm for identifying the moment of the beginning of slag lapse during the functioning of the metallurgical unit "steel ladle-intermediate ladle". In the paper were performed works on the formation of datasets of the vibration acceleration signal at the functioning technological object. After that, experiments on amplitude and frequency analysis of the signal were performed in order to form a criterion for determining the moment of the beginning of slag flow. Then the possibility of application of autoencoder artificial neural network for identification of metallurgical unit state was tested.
This paper presents a comprehensive experimental study of a novel trust-based security architecture for edge computing environments. We introduce an adaptive security framework that combines dynamic trust evaluation w...
详细信息
This paper presents a comprehensive experimental study of a novel trust-based security architecture for edge computing environments. We introduce an adaptive security framework that combines dynamic trust evaluation with decentralized decision-making mechanisms to enhance threat detection and system resilience. Through extensive simulation experiments, we evaluate the architecture's performance across various network configurations, ranging from 20 to 100 nodes, with different operational parameters and security event patterns. The simulation framework implements a sophisticated spatial distribution model for edge nodes, incorporating computational constraints, memory limitations, and communication boundaries typical of edge computing environments. Our results demonstrate that the proposed architecture achieves an 83.0% threat detection rate while maintaining network resilience at 95.6%, significantly exceeding baseline security requirements. The trust management mechanism demonstrates robust adaptation to security events, maintaining average trust scores of 78.6% despite active security incidents. We provide detailed analysis of system behavior under various attack scenarios, including intrusion attempts, data leaks, DDoS attacks, and authentication failures. The architecture shows exceptional scalability characteristics, with improved detection rates and trust stability in larger network configurations. Performance metrics reveal consistent achievement above target thresholds across all evaluated dimensions, with minimum trust levels maintaining a 7.2 percentage point margin above requirements. Our findings provide empirical validation of the architecture's effectiveness while offering practical insights into deployment considerations for edge computing security. The study contributes to the field by establishing quantitative benchmarks for security performance in edge environments and demonstrating the viability of trust-based security mechanisms for distributed
The article is devoted to the development of a functional model of intercultural interactions inside a metal heating furnace before rolling. The analysis of data from a real heating furnace was performed, a full-scale...
详细信息
ISBN:
(数字)9798331532178
ISBN:
(纸本)9798331532185
The article is devoted to the development of a functional model of intercultural interactions inside a metal heating furnace before rolling. The analysis of data from a real heating furnace was performed, a full-scale experiment was conducted in order to search and study the interconnections. The result of the work is the developed functional scheme of the inter-circuit interactions of the metal heating furnace before rolling.
This paper discusses a mathematical model for establishing a single digital logistics platform as a link between all participants in the added-value creation chain, including producers, resource and services suppliers...
详细信息
The model of the 3-layer feed-forward neural network is introduced whose first hidden layer consists of bithreshold neurons and the other layers—of single-threshold ones. The proposed network is capable to recognize ...
The model of the 3-layer feed-forward neural network is introduced whose first hidden layer consists of bithreshold neurons and the other layers—of single-threshold ones. The proposed network is capable to recognize compact finite set of patterns using a union of hyperrectangular decision regions in n-dimensional space. We design a multiclass classifier on the base of such network, propose the synthesis algorithm for it and estimate the networks size as well as the time of computations. The simulation results demonstrate that the application of the additional hidden layer improves the accuracy of classification.
We deal with theoretical issues concerning the application of the multithreshold architecture in the theory of neural computation. The way of representing a multithreshold function by 2-layer neural network consisting...
We deal with theoretical issues concerning the application of the multithreshold architecture in the theory of neural computation. The way of representing a multithreshold function by 2-layer neural network consisting of single-threshold neural units with equal weights is established in the paper. We also study the complexity of the problem of the learning k-threshold neurons and prove that this problem is NP-hard if the number of thresholds is greater than one.
Currently, there are negative statistics on industrial accidents. There are more and more accidents due to the neglect of personal protective equipment. In this regard, it is necessary to develop an information system...
详细信息
The theoretical and practical issues of the development of a control system for the technical vision of robots, which is based on the specifics of the processed information and the principles of building an integral s...
详细信息
This article discusses the management of autonomous energy complex with renewable energy within the smart grid solutions in terms of different types of input data uncertainty. On the basis of the theory of fuzzy logic...
详细信息
This article describes the challenges of modeling switch fabric traffic that is part of NoC routers. Simulation is often used to validate a NoC design and identify potential performance bottlenecks before implementing...
This article describes the challenges of modeling switch fabric traffic that is part of NoC routers. Simulation is often used to validate a NoC design and identify potential performance bottlenecks before implementing hardware. Due to the distributed and complex network topology of routers, arbitration and routing algorithms, etc., timing, buffer queuing, and hence infrastructure performance are difficult to predict. Network traffic also generates application traffic in data processing nodes. When processing NoC traffic, the activity of IP cores is unstable and does not have stationarity, so it is very important to find traffic control mechanisms. Often, well-known models built on the basis of queuing theory do not always correctly reflect the connection request processing logic, do not take into account deadlocks and other features of the system functioning. An approach that can more accurately take into account the nuances of the switch is to build an agent-based model. To create it, we used the Mesa framework implemented in the Python programming language. The switch has small built-in buffers - one for each input. The model used a switch with 5 inputs and 5 outputs. The idea behind switch traffic management is to count how often there are transacts in the internal buffers that are directed to one exit. If they occur frequently enough, then the information flow is split and two or more outputs are given the same identifier to service such transacts in parallel.
暂无评论