RJPGT 2024

  • INTEGRATED CONVOLUTIONAL NEURAL NETWORKS APPLICATION FOR ROAD TRAFFIC EFFICIENCY

    Ștefan Liviu-Andrei; Cărbureanu Mădălina
    6/30/2024
    10.51865/JPGT.2024.01.12
    No citations
    engineering; technology
    Road traffic is a problem that every country has to face for the benefit of its population. Everything related to the transportation of people, goods, and services can be delayed due to a deplorable infrastructure. From minor tasks like individual shopping to important services like ambulances and fire trucks, all vehicles in Romania will eventually pass through a traffic light-controlled intersection that is not managed in real-time and that is also highly inefficient. At such a location, it is critical for traffic flow to be as smooth as possible to prevent time losses, and for traffic information to be stored into a cloud for process optimization. The purpose of the developed application is to reduce the real-time traffic jams to allow the optimal vehicles movement in safe conditions for all traffic participants. Using deep learning (DL) and artificial intelligence (AI) techniques, the application is based on two convolutional neural networks (CNN’s), respectively one for real-time detection of cars and people, and another one for real-time detection of cars license plates. The cars detections with CNN’s is important for road traffic optimization, for the efficient pedestrian detection necessary for crosswalks, and the car licence plates detection necessary for preventing traffic violations. The developed application contains several modules that operate based on deep learning and devices that communicate with each other, ensuring efficient data saving in cloud, data visualization, real-time traffic light control, and the information processing from traffic cameras.
    Full text Read PDF

  • ARC WELDING ROBOTIC FLEXIBLE CELL SIMULATION USING ROBOGUIDE SOFTWARE

    Dragos-Lucian Baboi; Julian Andreoiu; Gabriela Bucur
    6/30/2024
    10.51865/JPGT.2024.01.11
    No citations
    engineering; technology
    The objective of the work is the design and simulation of a flexible manufacturing structure with two robots, integrated in a welding application, using the Roboguide software. FANUC ROBOGUIDE is a robot simulator that simulates both the movement of the robots and the commands from the designed application, significantly reducing the time needed to create new motion configurations.The possibility to import the CAD models of the components, of the fixing devices and of the final effectors of the robots integrated into the designed application, allows the creation and evaluation of various structures. Automatic program generation simplifies manual programming operations. ROBOGUIDE allows pre-programming of robots before they are installed in a cell, as well as visualization and confirmation of robot trajectories before downloading the programs to the real robot.
    Full text Read PDF

  • ARTIFICIAL INTELLIGENCE – POWERED VIDEO CONTENT GENERATION TOOLS

    Cosmina – Mihaela Roșca; Ionuț Adrian Gortoescu; Marius Radu Tănase
    6/29/2024
    10.51865/JPGT.2024.01.10
    17 citations
    engineering; technology
    This article discusses the considerations of artificial intelligence-powered video content generation tools, exploring their applications, ethical considerations, and evaluation criteria. Through discussions of various artificial intelligence (AI) tools, including features, limitations, and implications, the authors analyze the evolving landscape of video creation in the digital age. Key themes include the ethical implications of deep fake technology and the importance of responsible AI principles, exemplified by Microsoft's guidelines. This paper identifies five of the most promoted free social media tools. Evaluation criteria for these tools, such as visual quality, relevance, coherence, authenticity, and transparency, are examined to assess the suitability of AI-generated videos. While AI offers promising opportunities, the discussion underscores the continued need for human oversight and ethical considerations to ensure the responsible use of AI technologies in video content generation.
    Full text Read PDF

  • WATER SOFTENING PLANTS AND REDUCTION OF IRON AND MANGANESE BY MAGNETIC AND NANOBUBBLE CO2 TREATMENT: A TECHNICAL AND APPLICATIVE ANALYSIS

    Dan Ovidiu Cîrjan; Maria Stoicescu
    6/26/2024
    10.51865/JPGT.2024.01.09
    1 citation
    engineering; technology
    Human society and environment are based on water resources. Hard water with iron and manganese excess is spread across the world and softening of drinking water is widely applied for reasons of public health, client comfort, economic and environmental benefits. Also, from industrial or commercial point of view, using it produce scale deposits in water systems and equipment often result in ample technical and economic problems. Solutions of reducing its hardness and iron/manganese excess exists on the market, even with the substances presented in the work. The novelty this study brings comes from using high intensity permanent magnets arrangements and CO2 nanobubbles treatment that increased the speed, the volume of treatment, while decreasing the energy and complexity of the installation, also decreasing the pollution mark of the system. The detrimental contributions of softening, in particular the use of chemicals and energy, are taken into account in the carbon footprint of the drinking water companies. The beneficial contributions have not been included in the carbon footprint. For carbon capture in the crystallized calcite and dissolution of CO2 into the softened water, the carbon footprint is compensated by the net carbon benefit of softening.
    Full text Read PDF

  • DETERMINING THE PERFORMANCE OF A HEAT EXCHANGER USED IN THE FOOD INDUSTRY

    Maria Popa
    6/13/2024
    10.51865/JPGT.2024.01.08
    1 citation
    engineering; technology
    The study of heat transfer in the food industry is as important as in any other industry. Food products are constantly subjected to heat treatments. For this reason, a sunflower food oil, which undergoes heat treatment in the manufacturing process, was chosen for this study. The study was carried out on a laboratory plant and aimed to determine the heat transfer coefficients for three sets of determinations: partial heat transfer coefficient inside - where the warm sunflower oil circulates, partial heat transfer coefficient in the annular space - where cold water circulates and overall heat transfer coefficient, in a tube-in-tube heat exchanger made of copper. The obtained values of heat transfer coefficients were compared with literature data for the same type of food oil. This type of heat exchanger, tube-in-tube, is specific to the food industry. Countercurrent circulation of flows through the appliance was established from the outset, as this type of circulation is preferred from the point of view of determining the performance of heat exchange appliances. Efficiency values were also established for the three sets of experimental determinations. For the calculations, the values for the temperatures of the fluids, both at the inlet and outlet of the apparatus and the values for the volume flow rates of the fluids were required.
    Full text Read PDF

  • CONTRIBUTION OF SEISMIC AND GEOTHERMAL DATA ANALYSIS TO THE ASSESSMENT OF THE HYDROCARBON POTENTIAL OF THE CENTRAL BASIN OF THE D.R. CONGO

    Marlin Agolo Monza; Joel Etshekodi Lohadje; Franck Tondozi Keto; Raphael Matamba Jibikila; Néhémie Bikayi Tshiani
    6/12/2024
    10.51865/JPGT.2024.01.07
    No citations
    engineering; technology
    This paper presents an evaluation of the hydrocarbon potential of the Cuvette Centrale basin in the Democratic Republic of Congo (DRC) using an integrated approach that combines seismic and geothermal data. The envelope attribute of seismic data was used to identify different rocks of the petroleum system, including potential gas-prone zones. The interpretation of seismic profiles helped to delineate geological units and determine their lithology. Isobath maps based on seismic data revealed the presence of grabens and anticlines, which are favorable geological structures for hydrocarbon accumulation. Analysis of the geothermal gradient and temperature evolution in the formations allowed us to establish source rock maturity maps, highlighting two distinct zones: an overmature zone favorable for gas and a mature zone favorable for oil. These results suggest a strong hydrocarbon potential in the Cuvette Centrale basin.
    Full text Read PDF

  • SIMPLIFIED COMPUTATIONAL TOOL FOR PREDICTING FORMATION DAMAGE IN OIL WELLS

    Okologume Chinedu Wilfred; Shobowale Tolulope Joshua
    26.05/2024
    10.51865/JPGT.2024.01.06
    No citations
    engineering; technology
    The present study underscores the significance of regular well test analysis to ensure the accuracy and consistency of data pertaining to the permeability and skin of exploratory wells. This study advances the development of a novel computer model, ASPIRE, which predicts formation damage in oil wells by analysing well-test data. In this context, identifying blocked pore throats in the formation close to the wellbore by paraffinic deposits (scales) and its influence on permeability necessitates routine well-test analysis. The software employs a modified linear regression model developed in this study to perfectly fit the well-test data's infinitely acting linear flow (IARF) region to a straight line. The cases "CASE 1" and "CASE 2" were considered for constant rate transient drawdown well test analyses. The findings indicate that Case 1, with a high skin factor, requires remedial action, such as stimulation, to increase the formation's permeability close to the wellbore for enhanced productivity. In contrast, Case 2 has higher permeability and lower skin factor than Case 1, so stimulation is not required. In addition, R-squared analyses were conducted to validate the results obtained from the developed tool. The analyses reveal an R-square value of 1 for all cases, indicating a 100% accuracy. Therefore, the study concludes that the developed tool is instrumental in accurately predicting formation damage in oil wells.
    Full text Read PDF

  • CYBER-PHYSICAL SYSTEM FOR REMOTE MONITORING AND CONTROL OF A DRINKING WATER NETWORK

    Ciprian Manea; Gabriela Bucur
    4/5/2024
    10.51865/JPGT.2024.01.05
    No citations
    engineering; technology
    The fundamental aim of this paper is to investigate and explore the design and simulation methods for a cyber-physical system (CPS) for the monitoring and control of drinking water capture, treatment and distribution processes. This research aims to provide a deep understanding of the theoretical concepts underlying CPS systems, as well as a detailed analysis of the technologies and methodologies used in the design and simulation of these complex systems. Through this investigation, we aim to identify effective solutions for the management of drinking water resources, given the critical importance of water in modern society. By analyzing case studies and current practices, we will assess the advantages and challenges associated with implementing a CPS system in the real-world context of water supply infrastructure. This work not only aims to provide a theoretical perspective on the concept of CPS applied in the field of drinking water supply, but also to contribute to the development and implementation of practical solutions in order to ensure universal access to quality water and to protect the environment. Through academic approach and rigorous research, we hope to make a contribution to the field of mechatronic engineering and environmental technologies.
    Full text Read PDF

  • FLUID FLOW MODEL BASED ON THE ANALYSIS OF WATER INJECTION DATA IN THE TURONIAN RESERVOIR OF THE LIAWENDA FIELD, OFFSHORE COASTAL BASIN OF D.R. CONGO

    Munene Asidi Djonive; Kanika Mayena Thomas; Ndjanga Ndjondjo Pierre; Yakubu Jean-Pierre; Mbudi Diambu Shams; Iyolo Lungembo Jean; Kabuya Kalemba Faurysse; Lingwangasa Masaka Reddy; Ahumbila Bozo Patrick
    3/6/2026
    10.51865/JPGT.2024.01.04
    1 citation
    engineering; technology
    Arranged the hydrocarbons in an oil reservoir require several techniques for their exploitation. The Liawenda field, discovered in December 1971 following the drilling of the Liawenda-01 exploration well, has a total of 186 wells with an annual production of 3,009,553 barrels. Having started production several years ago, the field has used the water injection technique following a drop in pressure. Despite this recourse to water injection methods, production from the Liawenda field is not always satisfactory. Knowledge of fluid flow inside an oil reservoir is important because it enables us to estimate certain useful parameters that can determine fluid movements in order to identify the causes of excessive water production. Thus, the present paper deals with water injection data in order to understand fluid movements in the Turonian reservoir of the Liawenda Field: - What is the fluid movement like in the Turonian reservoir of the Liawenda Field? - How does water move in relation to oil? - What are the efficiencies of fluid movement within the Liawenda Field? - What is the speed and travel time of the fluids in this reservoir? - How mobile are fluids?
    Full text Read PDF

  • INTERPRETATION OF MAGNETIC AND GRAVIMETRIC SIGNATURES IN RELATION TO GEOLOGICAL STRUCTURES OF PETROLEUM INTEREST IN THE WESTERN PART OF THE CENTRAL BASIN OF THE D.R. CONGO

    Joel Etshekodi Lohadje; Marlin Agolo Monza
    2/25/2024
    10.51865/JPGT.2024.01.03
    2 citations
    engineering; technology
    The Cuvette Centrale is a sedimentary basin stretching from the Democratic Republic of the Congo to the Republic of Congo, Gabon and Angola. The existence of hydrocarbons in this large basin is demonstrated by the presence of indications on the DR Congo side and by the discovery of hydrocarbons by the Ngoki well (Republic of Congo) diagonally across the Lokoro sub-basin (DR Congo). In view of this evidence, the four boreholes drilled in the DR Congo's Cuvette Centrale have not reported the presence of hydrocarbons. With this in mind, this study reinterprets the geophysical data (magnetism and gravimetry) to highlight geological structures of petroleum interest. After processing and interpretation, we understand that the region contains interesting structures linked to hydrocarbon trapping. These include anticlines and faults. We discovered that there is a close relationship between the geological structures of these two countries (DR Congo and R Congo). They are all made up of the same geological structures separated by two major strike-slip faults crossed by the Congo River (NE-SW direction). These are the Dextre Fault, which displaces the compartments on the DR Congo side in a SW-NE direction, and the Senestre Fault, which runs NE-SW.
    Full text Read PDF

  • A MODEL FOR FORECASTING DEW POINT PRESSURE IN NIGER DELTA CONDENSATE RESERVOIRS USING CONSTANT VOLUME DEPLETION TESTS DATA

    Chukwuka Peace; Ogali Ikechukwu Oscar; Okologume Chinedu Wilfred; Dawaki Adamu
    1/11/2024
    10.51865/JPGT.2024.01.02
    No citations
    engineering; technology
    The dew point pressure plays a critical role in developing gas condensate reservoirs. It is a crucial factor used in fluid characterisation, performance estimation of gas reservoirs, and design of production systems. However, the composition of gas condensate fluid varies from one location to another, and thus, empirical correlations have been developed to determine the dew point pressure without conducting routine tests. As a result, correlations that are solely useful in the region where they were developed and analysed are developed. This work developed an empirical correlation using data from gas condensate wells in the Niger Delta using multiple linear regression. The model was developed using the Analytical Tools and techniques in Microsoft Excel. To develop the model, we utilised 63 data sets from the Constant Volume Depletion (CVD) experiment, which involved gas condensates from resources in the Niger Delta. The model comprises an empirical correlation that estimates the dew point pressure for gas condensate reservoirs. It uses compositional information of the fluid and reservoir temperature as input parameters. The correlation is derived through multiple regression analyses. Comparing the prediction accuracy of formulas based on the developed model and other conventional methods indicated that this model is more accurate than other statistical methods in predicting DPP within the Niger Delta region. This model can produce more accurate results than other estimation methods when working under limited field information and time constraints. The correlation developed in this process has a coefficient of determination of R2=0.869 and an Average Absolute Relative Error (AARE) of -2.0767%, along with a root mean square of 195279, indicating a high level of reliability in the proposed correlation.
    Full text Read PDF

  • MACHINE LEARNING METHODS APPLIED IN AIR QUALITY PREDICTION

    Mihai-Claudiu Vieru; Mădălina Cărbureanu
    1/11/2024
    10.51865/JPGT.2024.01.01
    6 citations
    engineering; technology
    Air quality is an important environmental component that has a significant influence on public health and well-being. Poor air quality can cause a variety of health problems, including respiratory and cardiovascular disorders. Therefore, there is a growing demand for air quality prediction tools to enable consumers and authorities to take the best decisions and to implement the necessary actions to reduce air pollution. The present paper describes an innovative application that uses machine learning techniques to supply to the users real-time air quality predictions made on past data from their unique location. The Scikit-learn Python package was used to implement five machine learning algorithms, including K-Nearest Neighbors, Random Forest, Gradient Boosting, Support Vector Regression (SVR) and AdaBoost. To achieve robust model performance, compatibility with cross-validation approaches was evaluated. The obtained results indicate that these machine learning techniques are successful at forecasting air quality. The AdaBoost method emerged as the best accurate predictor after extensive investigation, closely followed by Gradient Boosting, SVR, Random Forest, and K-Nearest Neighbors. Furthermore, the investigation also focused on the adapted handling of inaccurate data and providing graphical visualizations to highlight the algorithm's efficacy.
    Full text Read PDF