Primož Potočnik

Primož Potočnik
University of Ljubljana · Laboratory of Synergetics

Doctor of Engineering

About

45
Publications
6,520
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
722
Citations
Introduction
machine learning; neural networks; modelling of processes; time series forecasting; signal processing; nonlinear predictive control; condition monitoring and diagnostics of processes; industrial applications.

Publications

Publications (45)
Article
Full-text available
This study presents the results of acoustic emission (AE) measurements and characterization in the loading of biocomposites at room and low temperatures that can be observed in the aviation industry. The fiber optic sensors (FOS) that can outperform electrical sensors in challenging operational environments were used. Standard features were extract...
Article
Full-text available
Characterization of acoustic emission (AE) signals in loaded materials can reveal structural damage and consequently provide early warnings about product failures. Therefore, extraction of the most informative features from AE signals is an important part of the characterization process. This study considers the characterization of AE signals obtai...
Article
Short-term heat demand forecasting in district heating (DH) systems is essential for a sufficient heat supply and optimal operation of the DH. In this study, a machine learning based multi-step short-term heat demand forecasting approach using the data of the largest Slovenian DH system is considered. The proposed approach involved feature extracti...
Article
The quality and condition of valves installed in district heating systems can be reflected by the sounds emitted. In this paper, a framework for a systematic approach towards the classification of valve sounds is proposed, based on acoustic features and machine learning models. The methods include the extraction of spectral and psychoacoustic featu...
Article
This paper is concerned with the weather compensated heating of buildings by means of air-to-water heat pumps. A novel adaptive method is proposed for on-line optimization of the heating curve which defines the relation between the heating temperature and the outdoor temperature. Parametrization of the linear heating curve with two reference points...
Article
In this paper, the possibilities of developing machine learning based data-driven models for the short-term prediction of indoor temperature within prediction horizons ranging from 1 hour up to 12 hours are systematically investigated. The study was based on a TRNSYS emulation of a residential building heated by a heat pump, combined with measured...
Article
Full-text available
Forecasting the residential natural gas demand for large groups of buildings is extremely important for efficient logistics in the energy sector. In this paper different forecast models for residential natural gas demand of an urban area were implemented and compared. The models forecast gas demand with hourly resolution up to 60 h into the future....
Article
In the described research an investigation was performed into how thermal comfort in residential buildings could be improved by means of the smart control and optimization of weather-controlled air-to-water heat pumps, taking into account the new-generation heat pumps which can be adapted to different environmental conditions. A novel approach to t...
Article
Semi-supervised vibration-based classification and condition monitoring of the reciprocating compressors installed in refrigeration appliances is proposed in this paper. The method addresses the problem of industrial condition monitoring where prior class definitions are often not available or difficult to obtain from local experts. The proposed me...
Conference Paper
Results of applied short-term forecasting for the Slovenian natural gas market are presented. A case study for one of the major Slovenian natural gas distribution companies is considered, with forecasting results in hourly resolution in the forecasting horizon from 1 to 48 hours. The development of a forecasting strategy is presented, which include...
Conference Paper
Extreme learning machines (ELM) represent a new fast learning algorithm for single layer feedforward networks. In this paper, we investigate several practical properties of training ELM in the context of a simulated function approximation task. ELM with different hidden layer activation functions and varying number of hidden nodes are applied in th...
Article
Full-text available
Successful operation of a district heating system requires optimal scheduling of heating resources to satisfy heating demands. The optimal operation, therefore, requires accurate short-term forecasts of future heat load. In this paper, short-term forecasting of heat load in a district heating system of Ljubljana is presented. Heat load data and wea...
Article
Full-text available
A novel hybrid two-stage method of facility layout planning, based on self-organized clustering, is presented. In the first stage, a self-organizing map (SOM) is applied in order to organize the production process into production cells which encapsulate products with similar properties and similar machining requirements. In the second stage, the in...
Article
Organising and optimising production in small and medium enterprises with batch production and many different products can be very difficult due to high complexity of possible solutions. The paper presents a method of fine layout planning that rearranges production resources and minimises work and material flow transfer between production cells. Th...
Article
Full-text available
In this paper the performance of static and adaptive models for short-term natural gas load forecasting has been investigated. The study is based on two sets of data, i.e. natural gas consumption data for an individual model house, and natural gas consumption data for a local distribution company. Various forecasting models including linear models,...
Article
Full-text available
One of the most detrimental instability phenomena in metal band sawing is chatter, i.e. high amplitude vibrations of the tool and/or workpiece. In this paper, the influence of the cutting speed and of the distance between the blade supports on chatter phenomena is investigated. For this purpose a series of experiments with triangular cutting speed...
Article
In the paper chatter detection in band sawing is considered as a signal processing and classification problem. A multi-sensory experimental setup was established on an industrial band saw including sound, acceleration and cutting force, and measurements. Based on an experimental analysis sound signal is shown to be the most appropriate for chatter...
Article
Natural gas is known as a clean energy source used for space heating in residential buildings. Residential sector is a major natural gas consumer that usually demands significant amount of total natural gas supplied in distribution systems. Since demands of all consumers should be satisfied and distribution systems have limited capacity, accurate p...
Chapter
In the paper the results of the characterization of the chatter phenomenon in the band sawing process are presented. In particular, the influence of the cutting speed and of the distance between the cutting blade supports on chatter characteristics was investigated. In addition to the cutting forces, and emitted sound, the machine vibrations descri...
Article
Full-text available
With the development and application of expensive, difficult to cut metals and metal alloys, the minimization of waste material for final operations has, together with the quality of the band sawing process, become more and more important. As the onset of chatter can have a very detrimental effect on the quality of the cut, on the quality of the re...
Article
Short term forecasting of natural gas consumption in daily resolution for the next gas consumption day is considered in this paper. Various forecasting models are constructed and compared, including linear models and neural network models that are trained with either static or adaptive algorithms. The models are trained on two winter seasons and th...
Article
Organizing and optimizing production in small and medium enterprises with small batch production and many different products can be very difficult. This paper presents an approach to organize the production cells by means of clustering-manufactured products into groups with similar product properties. Several clustering methods are compared, includ...
Chapter
Full-text available
Tool damage due to chatter poses harmful economic impact in modern machining production therefore it is important to avoid or suppress chatter during the production process. In order to establish automated chatter-free cutting conditions, the methods for online recognition of chatter and chatter-free cutting should be developed. It this paper a ban...
Conference Paper
Analysis and short-term forecasting of traffic flow data for several locations of the Slovenia highway network are presented. Daily and weekly seasonal components of the data are analysed and several features are extracted to support the forecasting. Various short-term forecasting models are developed for one hour ahead forecasting of the traffic f...
Conference Paper
Full-text available
An application of clustering methods for production planning is proposed. Hierarchical clustering, k-means and SOM clustering are applied to production data from the company KGL in Slovenia. A database of 252 products manufactured in the company is clustered according to the required operations and product features. Clustering results are evaluated...
Article
The paper presents a procedure for forecasting the lead times of production orders on the basis of past actual lead time data. A customer for a particular production order will select the best bidder. It is rather risky to make a bid just on the basis of sales experience. A procedure is therefore proposed by which, on the basis of the actual lead t...
Chapter
Full-text available
Natural gas consumption forecasting is required to balance the supply and consumption of natural gas. Companies and natural gas distributors are motivated to forecast their consumption by the economic incentive model that dictates the cash flow rules corresponding to the forecasting accuracy. The rules are quite challenging but enable the company t...
Article
Full-text available
Automatic condition monitoring application for the detection of spring faults during assembling of reciprocating compressors is presented in this paper. Spring faults are characterized by incorrect positioning of compressor body on the supporting springs. Consequently, compressors with such faults should be detected and eliminated from the producti...
Article
Full-text available
Entering on market, companies confront with different problems. But the largest problems of today's time are too long lead times of orders. A client that wants a particular product to be made will select the best bidder considering on delivery time. To make a bid just on the basis of experience of employees is very risky nowadays. Therefore we prop...
Conference Paper
The natural gas market requires forecasting for the optimisation of leasing additional storage capacities. Consequently, natural gas distribution companies have an economic stimulus to accurately forecast their future gas consumption. A method for short-term forecasting of natural gas consumption is presented in this paper. The method consists of a...
Article
Efficient operation of modern energy distribution systems often requires forecasting future energy demand. This paper proposes a strategy to estimate forecasting risk. The objective of the proposed method is to improve knowledge about expected forecasting risk and to estimate the expected cash flow in advance, based on the risk model. The strategy...
Article
Full-text available
A method for nondestructive machine fault detection, based on evaluation of acoustic machine signatures, is presented. Various mechanical defects of rotary machines can be reflected in altered acoustic signatures. Such phenomena can be often perceived by skilled human operators who can also explain the type of defect merely based on slightly change...
Article
Full-text available
A method for machine diagnosis, based on acoustic signals, is proposed. The method is based on psychoacoustic modelling, which simulates the ability of human aural analysis. The solution approach combines psychoacoustic pre-processing, feature-extraction modules, and feature-evaluation modules. Feature-extraction methods are defined for the detecti...
Chapter
Neural network based experimental and hybrid approaches to modeling of processes are presented. A hybrid modeling, combining parametric model with radial basis function network, is proposed. The parametric model is used for principal modeling of the process and the radial basis function network is applied for nonlinear error correction. Experimenta...
Article
Automated fault detection system for the industrial production of commercial compressors is presented. Acoustic emission (AE) signals of the finalized compressor are measured and analysed by an industrial computer. Based on AE power spectra, features are extracted for detection of the following defects: 1) noxious space, 2) lubrication defect, 3) b...
Article
Full-text available
Nonlinear model predictive control (MPC) of a simulated chaotic cutting process is presented. The nonlinear MPC combines a neural-network model and a genetic-algorithm-based optimizer. The control scheme comprises a process, a model, an optimizer, a controller and a corrector. Neural networks are used to build a nonlinear experimental model of the...
Article
: We describe the application of empirical modeling of natural phenomena to the optimal selfcontrol of an autonomous system in a chaotic environment. The system consists of a network of sensors, a modeler, a controller, a plant, and a utility estimator. The modeler contains a self-organizing neural network and a conditional average estimator. An em...
Article
: The object of research is a production of antibiotics by fed batch fermentation. An intelligent system with a structure of neural network and a genetic algorithm are used in nonparametric modeling of the fermentation process. The goal is to build a model for the prediction of fermentation efficiency. A priori knowledge of experts, who are control...
Article
Full-text available
A Hybrid modeling approach, combining an analytical model with a radial basis function neural network is introduced in this paper. The modeling procedure is combined with genetic algorithm based feature selection designed to select informative variables from the set of available measurements. By only using informative inputs, the model's generaliza...
Article
Empirical modeling of the industrial antibiotic fed-batch fermentation process is discussed in this paper. Several methods including neural networks, genetic algorithms and feature selection are combined with prior knowledge in the research methodology. A linear model, a radial basis function neural network and a hybrid linear–neural network model...
Chapter
Modeling of processes with many input variables requires selection of informative inputs in order to construct less complex models with good generalization abilities. In this paper two feature selection methods are compared: mutual information (MI) based feature selection and genetic algorithm (GA) based feature selection. As a modeling structure a...

Network

Cited By