Претрага

Упит dcterms_subject_txt:diagnostics of operating coditions,Random Forest

2837 items

  • Application of machine learning for diagnosing the operation of a deep well pump in oil production

    Maja Trikić (2024)
    This paper will thoroughly examine how machine learning can improve the diagnosis of deep well pumps by analyzing the role and function of the pumps, dynamograms, sensor technologies, and diagnostic methods.Our analysis will provide insights into modern techniques and approaches for enhancing the performance and reliability of oil production systems, targeting cost reduction and increased operational efficiency.
    deep well pump, dynamograms, machine learning, diagnostics of operating coditions,Random Forest, XGBoost
    ... approaches for enhancing the performance and reliability of oil production systems, targeting cost reduction and increased operational efficiency. KEYWORDS:deep well pump, dynamograms,machine learning,diagnostics of operating coditions,Random Forest, XGBoost. CONTENTS 1. INTRODUCTION ... a aaaaaaeaa ...
    ... tuning can help improve performance. 2. Random Forest: Random forest is an enhanced version of decision trees that uses multiple trees for decision-making. This algorithm reduces the risk of overfitting and improves classification accuracy. Random forest is effective in recognizing complex patterns ...
    ... applied techniques and the number of samples per class.Table 3 shows the organization of the tests into groups GroupA GroupB GroupC Group D ML algorithms Decision tree, Random forest and XGBoost AutoML Decision tree, Random forest and XGBoost Decision tree Number of instances per class 30 30 90 180 ...

  • Interpretation of Trace Element Chemistry of Zircons from Bor and Cukaru Peki: Conventional Approach and Random Forest Classification

    Dina Klimentyeva, Milos Velojic , Albrecht Von Quadt, Shawn Hood (2022)
    Geohemija cirkona, Mašinsko učenje, Timočki magmatski komplkes, Bor, Čukaru Peki

  • Application of geophysical and multispectral imagery data for predictive mapping of a complex geo-tectonic unit: a case study of the East Vardar Ophiolite Zone, North-Macedonia

    Filip Arnaut, Dragana Đurić, Uroš Đurić, Mileva Samardžić-Petrović, Igor Peshevski (2024)
    General Earth and Planetary Sciences
    ... Germany, part of Springer Nature 2024 Abstract The Random Forest (RF) and K nearest neighbors (KNN) machine learning (ML) algorithms were evaluated for their abil- ity to predict ophiolite occurrences, in the East Vardar Zone (EVZ) of central North Macedonia. A predictive map of the investigated ...
    ... involving the prediction of spatially dispersed catego- ries in extremely complex processes, these algorithms have proven to be immensely useful (Kanevski et al. 2009). The Random Forest (RF) algorithm is widely used for predictive University of Belgrade, Institute of Physics Belgrade, Pregrevica ...
    ... evidenced by Table 2. Results Random forest The RF algorithm was applied to all three datasets (A, B, and C) with varying numbers of data points and distinct ratios of the two binary categorical classes pertaining to 1633 Table 2 Datasets A, B and C with number of points and ratios for training ...

  • Prognoziranje iznadprosečnih vrednosti kvaliteta vazduha u Novom Sadu koriščenjem Random Forest modela

    Filip Arnaut, Vesna Cvetkov, Dragana Đurić (2023)

  • Machine learning based landslide assessment of the Belgrade metropolitan area: Pixel resolution effects and a cross-scaling concept

    Uroš Đurić, Miloš Marjanović, Zoran Radić, Biljana Abolmasov (2019)
    Improvements of Machine Learning-based landslide prediction models can be made by optimizing scale, customizing training samples to provide sets with the best examples, feature selection, etc. Herein, a novel approach, named Cross-Scaling, is proposed that includes the mixing of training and testing set resolutions. Hypothetically, training on a coarser resolution dataset and testing the model on a finer resolution should help the algorithm to better generalize ambiguous examples of landslide classes and yield fewer over/underestimations in the model. This ...
    klizišta, podložnost, mašinsko učenje

  • Concepts for Improving Machine Learning Based Landslide Assessment

    Miloš Marjanović, Mileva Samardžić Petrović, Biljana Abolmasov, Uroš Đurić (2019)
    Katastar klizišta, Podložnost, Hazard, Mašinsko učenje, Uzorkovanje, Validacija

  • Sentiment Analysis of Serbian Old Novels

    Ranka Stanković, Miloš Košprdić, Milica Ikonić Nešić, Tijana Radović (2022)
    In this paper we present first study of Sentiment Analysis (SA) of Serbian novels from the 1840-1920 period. The preparation of sentiment lexicon was based on three existing lexicons: NRC, AFFIN and Bing with additional extensive corrections. The first phase of dataset refinement included filtering the word that are not found in Serbian morphological dictionary and in second automatic POS tagging and lemma were manually corrected. The polarity lexicon was extracted and transformed into ontolex-lemon and published as initial ...
    sentiment lexicon, sentiment analysis, distant-reading, machine learning, old novels

  • Integrating landslide magnitude in the susceptibility assessment of the City of Doboj, using machine learning and heuristic approach

    Cvjetko Sandić, Miloš Marjanović, Biljana Abolmasov, Radislav Tošić (2023)
    In this work, landslide assessment of the Doboj City area was modeled by combining machine learning and heuristic tools. The machine learning part was used to map the Morphometric factor. i.e. probability of landslides based on relation between the magnitude of events and morphometric parameters: elevation, distance to streams, slope, profile curvature, and aspect. The Random Forest and Support Vector Machines algorithms were implemented in the learning protocol, which included several strategies: balancing of the training/testing set size, algorithm ...
    podložnost na kliženje, magnituda klizišta, mašinsko učenje, heuristički pristup, Doboj

  • Long-term planning methodology for improving wood biomass utilization

    Vladimir Vukašinović, Dušan Gordić, Marija Živković, Davor Koncalović, Dubravka Živković (2019)
    The insufficiently developed forest management system is often followed by undeveloped forest resources supply chain and insufficient institutional support. These cause inefficient usage of fuel-wood as well as huge amounts of unused forest residues. In order to achieve optimal and long-term sustainable utilisation of biomass, an original methodology based on the interaction of mathematical optimization and backcasting approach has been developed. Mathematical optimization is used for both generation and consideration of techno-economic parameters of the forest biomass supply chain. ...
    Long-term planning methodology, Forest biomass, MINLP, Backcasting

  • Development of the Availability Concept by Using Fuzzy Theory with AHP Correction, a Case Study: Bulldozers in the Open-Pit Lignite Mine

    Stevan Đenadić, Dragan Ignjatović, Miloš Tanasijević, Uglješa Bugarić, Ivan Janković, Tomislav Šubaranović (2019)
    Availability is one of the most used terms in maintainability engineering. This concept is used to denote: The quality of service of an engineering system, i.e., machines, weak points’ analysis, asset management, as well as making decisions in the process of life cycle management. Availability is an overall indicator and contains partial indicators that are oriented towards reliability, maintenance, and logistical support. Availability presents a variable value and changes in time and space. Usually, availability is shown as the ...
    raspoloživost, fazi teorija, AHP višekriterijumska analiza, eksperska ocena, buldozer
    ... 2019, 12, 4044 2 of 18 defines availability as a measure of the degree to which an item is in an operable state and can be committed at the start of a mission when the mission is called for at an unknown (random) point in time. Availability, as measured by the user, is a function of how often failures ...
    ... The last step in the AHP method is to check the error, i.e., verification of the consistency of the decision-maker [26,27]. The consistency condition is that the value of the random consistency index Energies 2019, 12, 4044 9 of 18 CR (22) is less than 10%. A mathematical consistency check is performed ...
    ... indicators, and as such, is a measure of functional safety, and thus of the quality of service. Monitoring and availability analysis are significant because of the known fact that the machine must, above all, be available for operation, in order to realize other operating performance. American military standard ...

  • Evaluation And Perspectives Of Underground Coal Mines In Serbia

    Vladimir Milisavljević, Milena Lekić, Ivica Ristović, Vojin Čokorilo, Aleksandar Cvjetić (2017)
    ... Cvjetić1 1University of Belgrade, Faculty of Mining and Geology, Djušina 7,Belgrade; vladimir.milisavljevic@rgf.rs; milena.lekic@rgf.rs; ivica.ristovic@rgf.bg.ac.rs; vojin.cokorilo@rgf.bg.ac.rs; aleksandar.cvjetic@rgf.bg.ac.rs Summary: This paper provides analysis of mines operating in Public Company ...
    ... this is called the Consistency Ratio. The consistency ratio is a measure of how much variation is allowed and must be less than 10%. Finally, random index (RI) is given in Table 6. Table 4. Pairwise comparison matrix of criteria C1 C2 C3 C4 C5 C6 C7 C1 1 2 3 1 1 2 4 C2 0.5 1 0.5 0.5 0.5 ...
    ... ( λ) = 7.355393; CI = 0.059232; RI = 1.32; CR = 0.044873; Table 6. Random index n 3 4 5 6 7 8 9 10 RI 0.58 0.9 1.12 1.24 1.32 1.41 1.49 1.51 Rank of the underground coal mines operated by PCUCE obtained after completion of the calculation according to the AHP method is given in the Table ...

  • Hidrogeološke karakteristike područja Cerničkog polja (Istočna Hercegovina) sa posebnim osvrtom na rizik od zagađena podzemnih vodnih resursa

    Petar Vojnović (2023)
    ... Vazduh (Va) Va-1. Filip Arnaut, Vesna Cvetkov, Dragana Đurić: Prognoziranje iznadprosečnih vrednosti kvaliteta vazduha u Novom Sadu korišćenjem Random Forest modela Va-2. Radmila Lišanin, Čedo Lalović: Modelovanje atmosferske disperzije mikropolutanata Sekcija: Sediment (S) S-1. Miloš Dubovina ...
    ... радовима запослених доступним у слободном приступу. - Претрага репозиторијума доступна је на www.dr.rgf.bg.ac.rs The Digital repository of The University of Belgrade Faculty of Mining and Geology archives faculty publications available in open access, as well as the employees' publications. - The Repository ...
    ... Svetozarević, Nataša Šekuljica, Ana Dajić, Marina Mihajlović, Zorica Knežević- Jugović, Dušan Mijin: Continuous flow for degradation of dyes. Value added utilization of potato peel V-2. Aleksandar Jovanović, Mladen Bugarčić, Nataša Knežević, Miroslav Sokić, Vladimir Pavićević, Aleksandar Marinković: ...

  • Business Models for Small-scale Biomass Projects Development

    Dejan Ivezić, Miodrag Gluščević, Marija Živković (2019)
    Biomass is recognized as the most promising renewable energy source in Serbia. The share of biomass in Serbian final energy consumption is over 10%, but mostly related to traditional use in stoves and ovens. One of the main obstacles for wider implementation of contemporary biomass facilities is the inexperience of consumers and stakeholders in the implementation of “innovative” business models, especially in the cases of small-scale projects. In this paper, three different business models (public utility company, energy cooperative ...
    ... In the case of replacement of existing boiler in local school by woodchips boilers, technical staff of PUC “BB Term” would be in charge for operating and maintaining the new boilers. In this model, the local population has the opportunity to participate, as a tenderer, in the process of public procurement ...
    ... been operating since 2007 as a part of the Public Utility Company (PUC) “BB term” from Bajina Bašta. A boiler plant is located in the local schoolyard. The biomass project is given in detail in [4 - 6] and it includes a fuel switch to biomass, i.e. wood chips. Based on an increased utilization of the ...
    ... This concept is widely implemented in some of the most developed European countries [7]. Figure 1: Operating model for citizen cooperative [8] Energy cooperative model is primarily interesting for development of district heating system in Kostojevići. Energy cooperative as legal entity would provide ...

  • Effectiveness Analysis of Different Bucket-wheel Excavators

    Stevan Đenadić, Predrag Jovančić, Dragan Ignjatović, Miloš Tanasijević, Filip Miletić (2021)
    Coal production in open-pit lignite mines in the Republic of Serbia is performed with continuous work systems. In addition to coal production, the same systems are used for the exploitation of large quantities of overburden. According to the reliability concept, continuous systems are in linear connection. If the failure occurs in one part of the system, that will produce a downtime of the entire system. The initial and most important factor of continuous systems is the bucket-wheel excavator. It ...
    bucket-wheel excavator, open-pit coal mine, mining, multi-criteria decision methods

  • Application of stochastic models for mine planning and coal quality control

    Dejan Stevanović, Božo Kolonja, Ranka Stanković, Dinko Knežević, Mirjana Banković (2014)
    ... properties, and with the effect of off-design coal characteristics on power plant performance and cost. According to Shih and Frey [3] sulfur and ash content and heating value are considered as normally distributed random variables. The objectives of a model to optimize operation of a plant must include m ...
    ... by the simulation algorithm used. Generation of dataset for this case study was performed in statistical package Rsim [15], with rlnorm function which can generate random numbers whose distribution is lognormal, with arguments: the number of random numbers, the mean and standard deviation. The following ...
    ... i ( ) | | ( )� � � x (10) where |V| is the volume of the integration region, and � x i are the points in the random sample taken from the integration region. The value An(f) converges to true value IV(f) as n goes to infin- ity. The variance of this estimate is calculated as: Var A f V Var f n ...

  • A tool for identifying the criticality in the disordered systems with metastable dynamics

    Svetislav Mijatović, Dragutin Jovković, Sanja Janićević, Stefan Graovac, Đorđe Spasojević (2021)
    Физика кондензоване материје

  • Threshold-induced correlations in the Random Field Ising Model

    Sanja Janićević, Dragutin Jovković, Lasse Laurson, Đorđe Spasojević (2018)
    Multidisciplinary
    ... the response signal is random. 1Faculty of Physics, University of Belgrade, POB 368, 11001, Belgrade, Serbia. 2COMP Centre of Excellence, Department of Applied Physics, Aalto University, P.O. Box 11100, 00076, Aalto, Espoo, Finland. 3Helsinki Institute of Physics, Department of Applied Physics, Aalto ...
    ... the response signal is random. Faculty of Physics, University of Belgrade, POB 368, 11001, Belgrade, Serbia. ?COMP Centre of Excellence, Department of Applied Physics, Aalto University, P.O. Box 11100, 00076, Aalto, Espoo, Finland. *Helsinki Institute of Physics, Department of Applied Physics, Aalto ...
    ... the inset - distributions D(S) of size S obtained in simulations of 3D RFIM systems with a single value of lattice size L = 1024 and disorder R = 2.25 Figure 1. �resholding of RFIM signal. �e signal is obtained in simulations of 3D system with size L = 1024 and 40 random �eld con�gurations for each ...

  • Nonequilibrium athermal random-field Ising model on hexagonal lattices

    Svetislav Mijatović, Dragutin Jovković, Đorđe Spasojević (2021)
    Изингов модел, хексагонална решетка

  • Application of decision trees and random forests to zircon geochemistry

    Dina Klimentyeva, Miloš Velojić, Bojan Kostić, Albrecht von Quadt (2022)

  • Simulation of Hydrogeological Environmental Discharge in Case of Interruption Constant Observations

    Marina Čokorilo Ilić, Dragoljub Bajić, Miroslav Popović (2024)
    Monitoring Network, data, hydrogeological environment, tunnel, simulation