TULTECH Journals
Not a member yet
235 research outputs found
Sort by
Smart Dashboard of Water Distribution Network Operation: A Case Study of Tehran
No full textNumerous water supply utilities around the world face challenges in successfully distributing water in distribution networks due to increased urbanization, population growth, and climate change. The age of the water supply facilities is a particular issue, which is aggravated by their inadequate maintenance and operation. Due of this, many water utilities have recently adopted integrated and intelligent water supply solutions that leverage information technology, artificial intelligence, big data, and IOT (Internet of Things) to handle water supply system issues. In this study, a smart dashboard of water distribution network operation was developed to improve the effectiveness of Tehran, Iran\u27s water delivery system. In order to properly manage water resources, the article proposes adopting knowledge management systems in Tehran\u27s municipal water distribution and transmission networks
Energy Consumption Processes Overview in Metallurgical Sector for Aluminium Production: The Case of Albania
No full textNowadays, most of the Albanian economy\u27s target in the industry sector is concentrated on the metallurgy industry. All the largest metallurgical industries have been focused on the production of the metals, respectively, steel, aluminium, copper, and chromium. The materials and energy needed for the production of materials and their transformation into products are extracted from natural sources like ores, minerals, and fossil hydrocarbons. Due to global energy crises and sustainable development, our research work will be focused on the process’s identification and overview of energy consumption in the “Everest Ltd.” company for aluminium production that operates in Albania
Design of Control System for Self-Driving Vehicles
No full textSelf-driving vehicles and the control system design have been undergoing rapid changes in the last decade and affecting the concept and behaviour of human traffic. However, the control system design for autonomous driving vehicles is still a great challenge since the real vehicles are subject to enormous dynamic constraints depending on the vehicle physical limitations, environmental constraints and surrounding obstacles. This paper presents a new scheme of nonlinear model predictive control subject to softened constraints for autonomous driving vehicles. When some vehicle dynamic limitations can be converted to softened constraints, the model predictive control optimizer can be easier to find out the optimal control action. This helps to improve the system stability and the application for further intelligent control in the future. Simulation results show that the new controller can drive the vehicle tracking well on different trajectories amid dynamic constraints on states, outputs and inputs
Distribution Network Reconfiguration Considering Feeder Length as a Reliability Index
No full textPower distribution network reconfiguration is achieved by opening or closing sectionalizes and tie switches to optimize a set of objectives. Active loss reduction is the objective in the reconfiguration of distribution networks since distribution networks usually record high levels of power losses. Reliability of the network is also an important objective. In this work, the objective function of the optimization is the reduction of power loss, improvement of line loading index and improvement of reliability. This paper seeks to shift the focus from the traditional objectives of passive (without distributed generations) networks to the security and reliability objectives. Since network reconfiguration is a planning problem, the work was performed to solve the problem for multi – period scenarios which spanned 24hrs. Genetic Algorithm was employed in this study and the simulation was performed in MATLAB software environment using a modified IEEE 69 Bus test system
Evaluation of Ceramic Water Filters’ Performance and Analysis of Managerial Insights by SWOT Matrix
No full textFiltration is a crucial step in the water treatment process, typically preceding disinfection. Filters trap microorganisms and suspended solids, reducing their amount in the environment. The latest technology in filtration is ceramic filters, and in this study, the performance of silicon carbide ceramic filters (SIC) is evaluated. These filters were installed at three different locations within a water treatment plant (entrance storage, raw water, and backwash water), and changes in physical and chemical water parameters were measured. Results indicate high efficiency in turbidity removal, effectively clarifying volatile suspended solids (VSS) and fixed suspended solids (FSS). The turbidity removal efficiency was 99% for entrance storage and 65% for raw water. The SWOT (Strengths, Weaknesses, Opportunities, and Threats) matrix was used to analyse the results of the SIC and highlight its strengths, weaknesses, opportunities, and threats
Agent-Based Modelling of Cooperative and Competitive Behaviours in a Multi-Agent System with Stochastic Payoffs
No full textThis study presents a simulation of a social dilemma game, where a group of ten agents repeatedly decide whether to cooperate or compete. The game parameters include the number of agents, the number of iterations, and the probabilities of cooperation and competition. The initial payoffs are randomly assigned to each agent. The simulation calculates the payoffs for each agent based on their own behaviour and the behaviour of others in the same round. The results show the payoffs and behaviours of each agent over time, revealing how individual behaviour and group dynamics evolve in the social dilemma game. This simulation can be used to study cooperation and competition in various social contexts and to explore strategies for promoting cooperation
Emerging Trends in Artificial Intelligence Education: Advancements, Opportunities, and Impact on Educational Technology
No full textArtificial intelligence (AI) has recently gained prominence in the field of educational technology as an emerging area. It encompasses the study and advancements that have led to the creation of intelligent computers, machines, and other artifacts that possess cognitive abilities, learning capacity, adaptability, and decision-making skills similar to those of humans. The demand for training and platform development for artificial intelligence education may be seen by analyzing the development trends in artificial intelligence education across various countries. Technology diversity, individualized training, and clever student assessment are features of artificial intelligence education. As a complement to human teachers, virtual tutors and chatbots powered by artificial intelligence offer personalized guidance and support. The continued advancement of AI in education offers students an opportunity to gain practical experience, make data-driven decisions, and stay abreast of new developments. AI-powered educational tools enable efficient administrative tasks, freeing up valuable time for educators. AI algorithms can automate grading processes, analyze student performance data, and generate insightful reports, allowing teachers to focus on instructional planning and individualized instruction
AI-Based Smart Delivery System Using Image Processing and Computer Vision
No full textRapid growth in e-commerce and logistics has created a need for intelligent systems to optimize delivery operations. This paper proposes an AI-based smart delivery system leveraging computer vision to recognize packages and improve efficiency. An ESP32 microcontroller performs real-time object detection using images from an OV7670 camera module. Open-source libraries like OpenCV and TensorFlow enable processing algorithms for detection and classification. Key benefits include accurate labeling, routing, and sorting of packages, reducing human errors and delays. The modular design allows integration with tracking devices and transportation mechanisms for end-to-end automation. Limitations around transparency and lighting conditions are outweighed by the potential for scalability across sectors like food delivery, healthcare logistics, and transportation. With further development, such AI-powered systems can transform traditional supply chains into intelligent, self-regulating delivery ecosystems, providing visibility and reliability. This paper provides practical frameworks to build low-cost solutions using accessible hardware and software tools
Intelligent Estimation of Total Suspended Solids (TSS) in Wastewater Treatment Plants Utilizing Non-Liner Regression Analysis
No full textThe hazardous pollutants in industrial wastewater could risk the ecosystem at danger if it is not properly treated. Industrial wastewater, which contains more pollution than municipal wastewater, is a major part of the wastewater produced in modern countries. Monitoring the physico-chemical parameters such as total suspended solids (TSS) in wastewater treatment plants could reduce environmental impacts; however, it could be laborious and time consuming. Therefore, using intelligent models for measuring these parameters could simplify and expedite the procedures. In this study, the amount of the facile measure total dissolved solids (TDS) was evaluated by using electrical conductivity (EC) conversion, and then the amounts of total solids (TS) and total suspended solids (TSS) were calculated by statistical and regression analysis
A Social-Based Decision Support System for Flood Damage Risk Reduction in European Smart Cities
No full textToday, Decision Support Systems (DSS), which include monitoring, prediction, and control sections, are assumed to be tools for smart, sustainable management of disasters such as floods. On the platforms, first, a process is designed for receiving valid data before, during, and after a flood. Then, with the application of artificial intelligence (AI) models, the essential features can be predicted. Meanwhile, the main predicted factors should be determined according to the goals of each research project. In the present study, two-stage machine learning models will be used, including damage values in cities and rural regions and social impacts. In the first step, damages will be estimated by machine learning computations based on rainfall (mm), hourly flow of the river (m3/s), type of vegetation, density, etc. In a parallel way, after the determination of structural equation modeling (SEM) of social parameters in flood and their weights, in the second step of AI modeling, the social feedback factor will be forecasted based on effective achieved features. Finally, with the application of controlling systems such as the Decision Tree (DT) model, a fast reaction system is designed