Aleksander Król

Impact of the Factors Determining the Natural Stack Effect on the Safety Conditions in a Road Tunnel

Impact of weather conditions and natural stack effect on the operation of the mechanical ventilation system in a road tunnel is considered in the study. The work presents the measurements conducted in an opened road tunnel. Then, with the use of Ansys Fluent software the numerical model was built and validated. The numerical analyses were extended to other tunnel inclinations and temperature differences between tunnel portals. Taguchi method of experiment design was used to diminish the number of required simulations and to analyse the results.

Application of the Genetic Algorithm for Optimization of the Public Transportation Lines

The public transport operators must find a compromise between the growing demands and the available resources or budget constraints. Very often a significant improvement of the efficiency of the public transportation system can be attained by minor changes of the layout of communication lines or the timetable. Such optimization problems are computationally very complex, thus some heuristic procedures should be applied. In this paper a genetic algorithm is used to find the optimal structure of public transport network with given rolling stock. As the objective function the total time of realization of the transportation demands is assumed. The case study of a city in southern Poland is presented.

The Traffic Flow Prediction Using Bayesian and Neural Networks

The article presents two short-term forecasting models for determining the traffic flow volumes. The road traffic characteristics are essential for identification the trends in the distribution of the road traffic in the network, determination the capacity of the roads and the traffic variability over the time. The presented model is based on the historical, detailed data concerning the road traffic. The aim of the study was to compare the short-term forecasting models based on Bayesian networks (BN) and artificial neural networks (NN), which can be used in traffic control systems especially incorporated into modules of Intelligent Transportation Systems (ITS). Additionally the comparison with forecasts provided by the Bayesian Dynamic Linear Model (DLM) was performed. The results of the research shows that artificial intelligence methods can be successfully used in traffic management systems.

Estimation of the Number of Threatened People in a Case of Fire in Road Tunnels

Factors influencing the conditions in a road tunnel in a case of fire were considered. The specifics of road tunnels as parts of the transportation network from the safety point of view was discussed. A brief overview on tunnel emergency systems and evacuation process was presented. Selected road tunnels in Poland were taken into account and a number of scenarios of traffic accidents with fire were detailed described. Some observations from carried-out full-scale hot smoke test were used. As a result of each such case study the estimated number of threatened tunnel users was obtained. Conclusion section contains some recommendations which would lead to increase the safety level in road tunnels.

The Choice of the Fire Ventilation System for a Short Road Tunnel

The operation of the natural ventilation system and the operation of the mechanical ventilation system with axial fans during the fire development were compared in the study. The study was founded on the numerical fluid mechanics. Two models were built corresponding to the two systems being tested. The use of the CFD program (Computational Fluid Dynamics) allowed for the comparison of the values of important parameters at any points of both tunnels. The temperature, the velocity of the air and hot gases and the soot concentration were examined. The results have shown that the operation of mechanical ventilation with the axial fans cleans the access road to the source of the fire from one of the portals. In the case of the natural ventilation the same, however worse evacuation conditions are maintained throughout the whole tunnel. But it should be remembered, that this type of ventilation system is very sensitive to the effects of ambient air parameters such as the temperature and the wind direction and speed.

Assessment of Polish Railway Infrastructure and the Use of Artificial Intelligence Methods for Prediction of Its Further Development

The aim of this chapter is to analyze economic trends in rail freight volume in Poland, based on the analysis of data from the years 2009–2013, for evaluating decisions on planned investments in railway infrastructure envisioned by Poland and the EU at the time the EU was founded. The theoretical analysis presents a trend of functional Polish railways and its impact on investment decisions. In addition, it shows the long-term plans for railway transport in Poland from both the Polish government and the EU perspectives. An analysis of the current investment to support the development of railways in Poland is also elaborated. The research part of the chapter presents an analysis of statistical data on rail freight. Forecasts are precisely presented of selected transport parameters made by the Bayesian network method and Holt-Winters double exponential smoothing using an artificial immune system to determine parameters and initial conditions.

THE DESIGN OF THE PUBLIC TRANSPORT LINES WITH THE USE OF THE FAST GENETIC ALGORITHM

Background: The growing role of public transport and the press ure of economic criteria requires the new optimization tools for process of public transp ort planning. These problems are computationally ve ry complex, thus it is preferable to use various approximate methods , leading to a good solution within an acceptable t ime. Methods: One of such method is the genetic algorithm mimicking the processes of evolution and natural selectio n in the nature. In this paper, the different variants of th e public transport lines layout are subjected to th e artificial selection. The essence of the proposed approach is a simplified me thod of calculating the value of the fit function f or a single individual, which brings relatively short computation time even for large jobs. Results : It was shown that despite the introduced simplifi cations the quality of the results is not worsened. Using the data obtained from KZK GOP (Communications Municipal Association of Upper Silesian Industrial Region) the des cribed algorithm was used to optimize the layout of the ne twork of bus lines located within the borders of Ka towice. Conclusion : The proposed algorithm was applied to a real, ver y complex network of public transportation and a possibility of a significant improvement of its e fficiency was indicated. The obtained results give hope that the presented model, after some improvements can be the basis of the scientific method, and in a consequen ce of a further development to find practical application.