Using neural networks in the process of calibrating the microsimulation models in the analysis and design of roundabouts in urban areasIrena Ištoka Otković
, 2011, dissertation
Abstract: The thesis researches the application of neural networks in computer program calibration of traffic micro-simulation models. The calibration process is designed on the basis of the VISSIM micro-simulation model of local urban roundabouts.
From the five analyzed methods of computer program calibration, Methods I, II and V were selected for a more detailed research. The three chosen calibration methods varied the number of outgoing traffic indicators predicted by neural networks and a number of neural networks in the computer program calibration procedure. Within the calibration program, the task of neural networks was to predict the output of VISSIM simulations for selected functional traffic parameters - traveling time between the measurement points and queue parameters (maximum queue and number of stopping at the roundabout entrance). The Databases for neural network training consisted of 1379 combinations of input parameters whereas the number of output indicators of VISSIM simulations was varied. The neural networks (176 of them) were trained and compared for the calibration process according to training and generalization criteria. The best neural network for each calibration method was chosen by using the two-phase validation of neural networks.
The Method I is the calibration method based on calibration of a traffic indicator -traveling time and it enables validation related to the second observed indicator – queue parameters. Methods II and V connect the previously described calibration and validation procedures in one calibration process which calibrates input parameters according to two traffic indicators.
Validation of the analyzed calibration methods was performed on three new sets of measured data - two sets at the same roundabout and one set on another location. The best results in validation of computer program calibration were achieved by the Method I which is the recommended method for computer program calibration.
The modeling results of selected traffic parameters obtained by calibrated VISSIM traffic model were compared with: values obtained by measurements in the field, the existing analysis methods of operational roundabouts characteristics (Lausanne method, Kimber-Hollis, HCM) and modeling by the uncalibrated VISSIM model. The calibrated model shows good correspondence with measured values in real traffic conditions. The efficiency of the calibration process was confirmed by comparing the measured and modeled values of delays, of an independent traffic indicator that was not used in the process of calibration and validation of traffic micro-simulation models.
There is also an example of using the calibrated model in the impact analysis of pedestrian flows on conflicting input and output flows of vehicles in the roundabout. Different traffic scenarios were analyzed in the real and anticipated traffic conditions.
Keywords: traffic models, traffic micro-simulation, calibration of the VISSIM model, computer program calibration method, neural networks in the calibration process, micro-simulation of roundabouts, traffic modeling parameters, driving time, queue parameters, delay
Published: 02.06.2011; Views: 3610; Downloads: 252
Full text (13,21 MB)
Analysis of growth models for batch kefir grain biomass production in RC1 reaction systemMarko Tramšek
, Andreja Goršek
, 2008, original scientific article
Abstract: This work describes the statistical analysis of three mathematical models, modified for describing the kefir grain biomass growth curve. Experimental data of time-dependent kefir grain mass increase were used. The propagation was performed in RC1 batch reaction system under optimal bioprocess parameters (temperature, rotational frequency of stirrer, glucose mass concentration) using traditional cultivation in fresh, high-temperature, pasteurized whole fat cow's milk. We compared values of biological parameters obtained by applying the nonlinear regression of experimental data in logistic, Gompertz and Richards models. The most statistically appropriate model was determined using the seven statistical indicators. We established that the kefir grain biomass growth curve during batch propagation under optimal bioprocess conditions can be most successfully described using the Gompertz growth model.
Keywords: chemical processing, milk products, kefir grain growth, process parameters, design of experiments, modeling, mathematical models, Gompertz growth model, RC1
Published: 31.05.2012; Views: 1770; Downloads: 61
Link to full text
Quantitative examination of process parameters during kefir grain biomass productionAndreja Goršek
, Marko Tramšek
, 2007, short scientific article
Abstract: This article examines the propagation of kefir grains in fresh HTP whole fat cows' milk, with some additions (glucose and bakers yeast). The objective of our work was an experimental determination of the various process parameters relative influence on the propagation and daily kefir grain increase mass, using the Taguchi method for experimental design. The effects of medium temperature, glucose mass concentration, bakers yeast mass concentration and the rotational frequency of the stirrer at four levels were studied. Orthogonal array layout of L16 was selected for the proposed experimental design. All experiments were performed in an automated laboratory reaction calorimeter RC1 (Mettler-Toledo) with the same milk (3.5 % fat). The gravimetric method was used to determine daily kefir grain mass increases. Relative contributions of the proposed influencing process parameters on the daily kefir grains increase mass were estimated by analysis of the variance (ANOVA). The highest increase (51.5 %) was found at the rotational frequency of the stirrer 90 (1/min), at glucose mass concentration 20 g/L, and at mediumtemperature 24 °C. Within the observed range of yeast mass concentrationthis process parameter was found to be insignificant compared to others. The rotational frequency of the stirrer has the highest relative influence on the daily kefir grains increase mass (37.3 %) while glucose mass concentration and medium temperature have lower ones, 18.8 % and 9.9 %, respectively. The remaining fraction represents error influence. The main reason for its relatively high value (34.0 %) is that kefir grains are bulky and awkward to handle. This fact confirms the importance of optimal kefir grains production management.
Keywords: chemical processing, milk products, kefir, kefir grain growth, process parameters, design of experiments, Taguchi method, RC1
Published: 31.05.2012; Views: 1589; Downloads: 32
Link to full text
Determination of the process parameters relative influence on k[sub]La value using Taguchi design methodologyMarko Tramšek
, Andreja Goršek
, 2007, original scientific article
Abstract: This article describes experimental determination of the relative impact of significant process parameters that influence volumetric oxygen mass transfer coefficient (kLa) using Taguchi design methodology. For this purpose an automated RC1 reaction calorimeter (Mettler-Toledo), which was originally developed for chemical processes, was modified for the bioprocesses. Simple fermentation using Baker's yeast was studied to illustrate the design procedure. Orthogonal array L25 was selected for the proposed design and ANOVA method was used for recognizing the relative influence of the process parameters. Within the observed range of temperature (?), fermentation media volume (VFM), and yeast mass concentration (?Y), these process parameters were found to be unimportant compared to the volumetric air flow rate (qV,a) and rotational frequency of the stirrer (fm). The qV,a had a substantial effect on the kLa value (89.2 %) and the fm had just a small one (3.6 %), meanwhile the remain fraction to 100 % represents error. The results refer strictly to the selected case study. Anyhow, the proposed procedure shows that application of the Taguchi approach for analyzing the oxygen mass transfer based on the experimental data obtained from a highly-automated laboratory reactor appears to have potential usage in general biopharmaceutical process design.
Keywords: bioprocess parameters, mass transfer, volumetric oxygen mass transfer coefficient, process parameters, Taguchi method, analysis of variance
Published: 31.05.2012; Views: 1451; Downloads: 22
Link to full text
Investigations of the structure and process parameters of sewing operationDaniela Zavec Pavlinič
, Zvonko Dragčević
, Dubravko Rogale
, Jelka Geršak
, 1999, original scientific article
Abstract: An original measuring equipment and a system for investigating process parameters of the sewing operation structure and for establishing optimal working methods and real working conditions of the man-machine system in garment sewing are presented. The measuring equipment consists of a process parameter measuring and data storing system and a bi-plane video recording system. The measuring and data storage system is equipped with four sensors which measure the rotation speed of the main shaft, the movements of arms in the picking-up and laying-off zones, and the movements of the pedal regulator used to control the sewing dynamics. The bi-plane video recording system is used to record simultaneously the working movements (working methods) performed at the discussed workplace. From the process parameter measurements graphs for the technological operation structure are obtained, including the duration of individual suboperations and changes occuring due to pedal regulator movements. The bi-plane video recording system investigates the working method employed, the basic movements and and the optimal logical sets of movements, as well as the cyclograms of the movements used to define space and time values. The results obtained are compared with the MTM results, and the differences between them are presented.
Keywords: textile industry, garment engineering, sewing operation structure, process parameters, bi-plane video recording, workplace design
Published: 01.06.2012; Views: 1230; Downloads: 21
Link to full text
Segmenting risks in risk managementBorut Jereb
, 2009, original scientific article
Abstract: The paper describes a segmentation of risks to make each risk segment more manageable. The proposed approach is primarily intended to improve the confidentiality of risk simulations. The description of the approach is based on a logistics business process system which requires that its input is represented as a process graph. Each process is defined in terms of input and output; input comprises general input as well as risks; output comprises general output as well as impacts. The model takes into consideration internalas well as external input and output. Parameters can be used to define individual processes. Processes include functions that calculate new values of parameters and output on the bases of given input. Based on given tolerance levels for risks, impacts and process parameters, the model determines whether these levels are acceptable. The model assumes that parameters and functions are non-deterministic, i.e. parameters and functions may change in time. Although the approach is described on a very general level, each segment can be further subdivided into subsegments in order to include more characteristics of observed risks.
Keywords: risk, impact, segmentation, risk management, process parameters, logistics, model, simulation tools, non-deterministic
Published: 05.06.2012; Views: 1296; Downloads: 27
Link to full text
Analysis of the influence of car-following input parameters on the modelled travelling timeIrena Ištoka Otković
, Tomaž Tollazzi
, Matjaž Šraml
, 2013, short scientific article
Abstract: The calibration process is a basic condition of traffic model application in local conditions. The choice of input parameters, which are used in calibration process, influences the success of the calibration process itself; therefore, the goal is to choose parameters with a larger influence on the modelling process. This paper offers a detailed analysis of car-following input parameters and their influence on the modelled travelling time. The experimental basis was a one-lane roundabout, and the tool used for traffic simulation was the VISSIM microsimulation traffic model. The results show that the car-following input parameters should be a part of the set of input parameters, which will enter the process of calibration. The examined car-following input parameters affect the capacity of intersections and results show that it is necessary to revise the range of input values of one of the observed car-following input parameters.
Keywords: car-following input parameters, input parameters for the process of calibration, VISSIM
Published: 11.07.2017; Views: 356; Downloads: 59
Full text (680,10 KB)
This document has many files! More...