Papers by Milena Petkovic
Journal on processing and energy in agriculture, 2010
The paper describes the development and implementation of an expert system for fault detection of... more The paper describes the development and implementation of an expert system for fault detection of induction motors. Early detection of induction motors failures may prevent the occurrence of malfunction and ensure timely replacement and servicing. In order to make timely and accurate fault detection an expert system is designed and developed. The expert system is a software system aimed at "simulating" human-expert knowledge and assistance in making decisions in a particular area. This paper presents a conceptually new type of expert system based on the artificial neural networks. Inputs into the expert system are the results of the algorithms to detect faults based on different physical quantities (current and vibration). The expert system performs analysis of input data and, based on them, it finally defines the type of fault or faults in the case of multiple failures.
Operations Research Proceedings 2022
Lecture Notes in Operations Research
Forecasting Natural Gas Flows in Large Networks
Natural gas is the cleanest fossil fuel since it emits the lowest amount of other remains after b... more Natural gas is the cleanest fossil fuel since it emits the lowest amount of other remains after being burned. Over the years, natural gas usage has increased significantly. Accurate forecasting is crucial for maintaining gas supplies, transportation and network stability. This paper presents two methodologies to identify the optimal configuration o parameters of a Neural Network (NN) to forecast the next 24 h of gas flow for each node of a large gas network.
In this paper, a case study is presented which demonstrates the efficiency of vibration analysis ... more In this paper, a case study is presented which demonstrates the efficiency of vibration analysis in induction motor rotor fault detection and diagnosis. Vibration signals of a 3,15 MW induction motor were acquired. The observed motor is specific due to its very low slip, which can cause some difficulties in fault diagnostic process. Employing some of well-known signal processing and analysis techniques, characteristic features in frequency domain were observed. Using the previous experience in fault detection and diagnosis, it is determined that a rotor fault, a broken bar in specific, is present in the motor. Based on this analysis, a general repair of the motor was carried out and the diagnosed fault was confirmed. This way, applying the fault detection and diagnosis in early fault stage, some serious malfunctions and failures were avoided, which resulted in decreased repair costs and undisturbed delivery of heat energy during the heating season.
Journal on Processing and …, 2010
The paper describes the development and implementation of an expert system for fault detection of... more The paper describes the development and implementation of an expert system for fault detection of induction motors. Early detection of induction motors failures may prevent the occurrence of malfunction and ensure timely replacement and servicing. In order to make timely and accurate fault detection an expert system is designed and developed. The expert system is a software system aimed at "simulating" human-expert knowledge and assistance in making decisions in a particular area. This paper presents a conceptually new type of expert system based on the artificial neural networks. Inputs into the expert system are the results of the algorithms to detect faults based on different physical quantities (current and vibration). The expert system performs analysis of input data and, based on them, it finally defines the type of fault or faults in the case of multiple failures.
Journal on processing and energy in agriculture, 2014
This paper presents the application of some well-known global optimization techniques in optimiza... more This paper presents the application of some well-known global optimization techniques in optimization of an expert system controlling a ship locking process. Optimization was conducted in order to achieve better results in local distribution of ship arrivals, i.e. lower waiting times for ships and less empty lockages. Particle swarm optimization, artificial bee colony optimization and genetic algorithm were used. The results shown in this paper confirmed that all these procedures show similar results and provide overall improvement of ship lock operation performance, which speaks in favor of their application in similar transportation problem optimization.
Due to the current and foreseeable shifts in energy production, the trading and transport operati... more Due to the current and foreseeable shifts in energy production, the trading and transport operations of gas will become more dynamic, volatile, and hence also less predictable. Therefore, computer-aided support in terms of rapid simulation and control optimization will further broaden its importance for gas network dispatching. In this paper, we aim to contribute and openly publish two new mathematical models for regulators, also referred to as control valves, which together with compressors make up the most complex and involved types of active elements in gas network infrastructures. They provide full direct control over gas networks but are in turn controlled via target values, also known as set-point values, themselves. Our models incorporate up to six dynamical target values to define desired transient states for the elements’ local vicinity within the network. That is, each pair of every two target values defines a bounding box for the inlet pressure, outlet pressure as well as...
With annual consumption of approx. 95 billion cubic meters and similar amounts of gas just transs... more With annual consumption of approx. 95 billion cubic meters and similar amounts of gas just transshipped through Germany to other EU states, Germany’s gas transport system plays a vital role in European energy supply. The complex, more than 40,000 km long highpressure transmission network is controlled by several transmission system operators (TSOs) whose main task is to provide security of supply in a cost-efficient way. Given the slow speed of gas flows through the gas transmission network pipelines, it has been an essential task for the gas network operators to enhance the forecast tools to build an accurate and effective gas flow prediction model for the whole network. By incorporating the recent progress in mathematical programming and time series modeling, we aim to model natural gas network and predict gas inand out-flows at multiple supply and demand nodes for different forecasting horizons. Our model is able to describe the dynamics in the network by detecting the key nodes,...
Energy Systems, 2021
About 23% of the German energy demand is supplied by natural gas. Additionally, for about the sam... more About 23% of the German energy demand is supplied by natural gas. Additionally, for about the same amount Germany serves as a transit country. Thereby, the German network represents a central hub in the European natural gas transport network. The transport infrastructure is operated by transmissions system operators (TSOs). The number one priority of the TSOs is to ensure the security of supply. However, the TSOs have only very limited knowledge about the intentions and planned actions of the shippers (traders). Open Grid Europe (OGE), one of Germany’s largest TSO, operates a high-pressure transport network of about 12,000 km length. With the introduction of peak-load gas power stations, it is of great importance to predict in- and out-flow of the network to ensure the necessary flexibility and security of supply for the German Energy Transition (“Energiewende”). In this paper, we introduce a novel hybrid forecast method applied to gas flows at the boundary nodes of a transport netw...
Energy Science & Engineering, 2021
Germany is the largest market for natural gas in the European Union, with an annual consumption o... more Germany is the largest market for natural gas in the European Union, with an annual consumption of approx. 95 billion cubic meters. Germany's high-pressure gas pipeline network is roughly 40,000 km long, which enables highly fluctuating quantities of gas to be transported safely over long distances. Considering that similar amounts of gas are also transshipped through Germany to other EU states, it is clear that Germany's gas transport system is essential to the European energy supply. Since the average velocity of gas in a pipeline is only 25km/h, an adequate high-precision, high-frequency forecasting of supply and demand is crucial for efficient control and operation of such a transmission network. We propose a deep learning model based on spatio-temporal convolutional neural networks (DLST) to tackle the problem of gas flow forecasting in a complex high-pressure transmission network. Experiments show that our model effectively captures comprehensive spatio-temporal correlations through modeling gas networks and consistently outperforms state-of-theart benchmarks on real-world data sets by at least 21%. The results demonstrate that the proposed model can deal with complex nonlinear gas network flow forecasting with high accuracy and effectiveness.
European Journal of Mechanics - A/Solids, 2010
By using Pontryagin's principle we study the optimal shape of an elastic column with clamped ends... more By using Pontryagin's principle we study the optimal shape of an elastic column with clamped ends and positioned on elastic foundation of Winkler type. Two problems were treated. In the first one, which is a generalization of our previous work, we consider the case of a partially supported column. In the second problem we determine the optimal shape of a column on elastic foundation subjected to restrictions on minimal cross-sectional area. It is shown that in this case the optimization can be both bimodal and unimodal. We determine the transition value between unimodal and bimodal optimization for specified values of parameters.
Journal of Global Optimization
We consider the problem of verifying linear properties of neural networks. Despite their success ... more We consider the problem of verifying linear properties of neural networks. Despite their success in many classification and prediction tasks, neural networks may return unexpected results for certain inputs. This is highly problematic with respect to the application of neural networks for safety-critical tasks, e.g. in autonomous driving. We provide an overview of algorithmic approaches that aim to provide formal guarantees on the behaviour of neural networks. Moreover, we present new theoretical results with respect to the approximation of ReLU neural networks. On the other hand, we implement a solver for verification of ReLU neural networks which combines mixed integer programming with specialized branching and approximation techniques. To evaluate its performance, we conduct an extensive computational study. For that we use test instances based on the ACAS Xu system and the MNIST handwritten digit data set. The results indicate that our approach is very competitive with others, i...
Srpski arhiv za celokupno lekarstvo, 2016
Introduction. Identification of predictive factors for walking ability with a prosthesis, after l... more Introduction. Identification of predictive factors for walking ability with a prosthesis, after lower limb amputation, is very important in order to define patient?s potentials and realistic rehabilitation goals, however challenging they are. Objective. The objective of this study was to investigate whether variables determined at the beginning of rehabilitation process are able to predict walking ability at the end of the treatment using support vector machines (SVMs). Methods. This research was designed as a retrospective clinical case series. The outcome was defined as three-leveled ambulation ability. SVMs were used for predicting model forming. Results. The study included 263 patients, average age 60.82 ?} 9.27 years. In creating SVM models, eleven variables were included: age, gender, cause of amputation, amputation level, period from amputation to prosthetic rehabilitation, Functional Comorbidity Index (FCI), presence of diabetes, presence of a partner, restriction concerning...
Energy consumption forecasting in process industry using support vector machines and particle swarm optimization
Proceedings of the 11th Wseas International Conference on Mathematical Methods and Computational Techniques in Electrical Engineering, Sep 28, 2009
... MILENA R. PETKOVIĆ MILAN R. RAPAIĆ BORIS B. JAKOVLJEVIĆ Computing and Control Department Univ... more ... MILENA R. PETKOVIĆ MILAN R. RAPAIĆ BORIS B. JAKOVLJEVIĆ Computing and Control Department University of Novi Sad Trg Dositeja Obradovića 6 SERBIA milena5@uns.ac.rs ... Incorporation of PSO into SVM training process has greatly enhanced the quality of prediction. ...
In this paper, Support Vector Machines (SVMs) are applied in predicting electrical energy consump... more In this paper, Support Vector Machines (SVMs) are applied in predicting electrical energy consumption in the atmospheric distillation of oil refining at a particular oil refinery. During cross4validation process of the SVM training Particle Swarm Optimization (PSO) algorithm was utilized in selection of free SVM kernel parameters. Incorporation of PSO into SVM training process has greatly enhanced the quality of
Expert Systems with Applications, 2012
An adaptive clustering procedure specifically designed for process monitoring, fault detection an... more An adaptive clustering procedure specifically designed for process monitoring, fault detection and isolation is presented in this paper. The key feature of the proposed procedure can be identified as its underlying capability to detect novelties in the system's mode of operation and, thus, to identify previously unseen functioning modes of the process. Once a novelty is detected, relevant informations are used to enrich the knowledge-base of the algorithm and as a result the proposed clustering procedure evolves and learns the new features of the monitored process in accordance with the available process data. The suggested clustering procedure is theoretically illustrated and its effectiveness has been investigated experimentally. Particularly, the on-line implementation of the algorithm and its integration with a fault detection expert system have been considered by making reference to a pneumatic process.
An Adaptive Clustering Procedure with Applications to Fault Detection
P14 Correlation between the low molecular weight heparin prophylactic dose and the plasma levels of anti Xa activity in pregnant women
Thrombosis Research, 2009
European Journal of Mechanics - A/Solids, 2010
a b s t r a c t By using Pontryagin's principle we study the optimal shape of an elastic column w... more a b s t r a c t By using Pontryagin's principle we study the optimal shape of an elastic column with clamped ends and positioned on elastic foundation of Winkler type. Two problems were treated. In the first one, which is a generalization of our previous work, we consider the case of a partially supported column. In the second problem we determine the optimal shape of a column on elastic foundation subjected to restrictions on minimal cross-sectional area. It is shown that in this case the optimization can be both bimodal and unimodal. We determine the transition value between unimodal and bimodal optimization for specified values of parameters.
Uploads
Papers by Milena Petkovic