The estimation of energy consumption is an important prerequisite for planning the required infrastructure for charging and optimising the schedules of battery electric buses used in public urban transport. This paper proposes a model using a reduced number of readily acquired bus trip parameters: arrival times at the bus stops, map positions of the bus stops and a parameter indicating the trip conditions. A deep learning network is developed for deriving the estimates of energy consumption stop by stop of bus lines. Deep learning networks belong to the important group of methods capable of the analysis of large datasets—“big data”. This property allows for the scaling of the method and application to different sized transport networks. Validation of the network is done using real-world data provided by bus authorities of the town of Jaworzno in Poland. The estimates of energy consumption are compared with the results obtained using a regression model that is based on the collected data. Estimation errors do not exceed 7.1% for the set of several thousand bus trips. The study results indicate spots in the public transport network of potential power deficiency which can be alleviated by introducing a charging station or correcting the bus trip schedules.

The detection of obstacles at rail level crossings (RLC) is an important task for ensuring the safety of train traffic. Traffic control systems require reliable sensors for determining the state of anRLC. Fusion of information from a number of sensors located at the site increases the capability for reacting to dangerous situations. One such source is video from monitoring cameras. This paper presents a method for processing video data, using deep learning, for the determination of the state of the area (region of interest—ROI) vital for a safe passage of the train. The proposed approach is validated using video surveillance material from a number of RLC sites in Poland. The films include 24/7 observations in all weather conditions and in all seasons of the year. Results show that the recall values reach 0.98 using significantly reduced processing resources. The solution can be used as an auxiliary source of signals for train control systems, together with other sensor data, and the fused dataset can meet railway safety standards.

Micro-electromechanical-systems (MEMS) based sensors are used for monitoring the state of machines in condition-based maintenance tasks. This approach is applied at tram depots for the purpose of identifying faulty wheels on trams in order to eliminate defective trams at the entry or dispatch gates. The application of MEMS-based sensors for the detection of wheel faults is the focus of this study. A method for processing of the collected sensor data is developed. It is based on assessing the energy of vibrations at different frequency bands. Maximal Overlap Discrete Wavelet Packet Transform (MODWPT) is used for obtaining a description of the sensor data. The task of finding the energy threshold for detecting faulty wheels, frequency band and parameters of MODWPT which most distinctly distinguish the wheels is the goal of the method. The weighted difference (DW) between the extreme values of energy in a frequency band for normal and faulty wheels is proposed as the measure of the ability to distinguish the wheels. The search for the solution is formulated as a discrete optimisation problem of maximising this measure. Both the simulation and experimental results indicate that faulty wheels have greater vibration energy than normal wheels. The properties of this approach are discussed and evaluated.

The condition monitoring of urban tramways constitutes an important task of municipal authorities for safeguarding the safety of public transport and efficient managing of the tram lines. Micro-electro-mechanical systems (MEMS) based sensors are low-cost and low-power devices easily integrated with elements of smart cities infrastructure. The aim of the study is to determine the bounds of application of MEMS sensors for monitoring the condition of tramway rail tracks. Monitoring the frequency spectrum of vibrations caused by rail track irregularities is proposed for deriving information on the rail conditions. The study employs a maximal overlap discrete wavelet packet transform (MODWPT) algorithm to extract the features from MEMS accelerometer datasets collected during tram trips. The Katowice (Poland) urban tramways are the objects of a case study. The results confirm that vibrations of tram bodies with high energy in characteristic frequency bands indicate faulty tramway tracks. The acceleration measurement ranges, and the sampling rates of the MEMS sensors fulfill the requirements of the proposed monitoring approach.