In recent years, image recognition, along with improvements in image processing technology, has become a mainstream method of object inspection. The quality of images directly affects the image-recognition rate. Track monitoring systems play an important role in ensuring safety and preventing derailments of trains, on the basis of the prevailing track conditions. Therefore, the conditions of track systems are very important. In this research, a high-speed frame grabber system is designed. The triggering rate of its line scan camera can be adjusted to match the vehicle speed of the train, so that the pixels per inch of images captured by this camera are fixed. The hardware equipment of the designed system includes a line scan camera, an image acquisition card, artificial lightings, a contrast sensor, and a system on a programmable chip (SOPC) development board. An exposure time control system is designed on the basis of a field-programmable gate array (FPGA) core. The designed system can acquire clear high-speed images while the vehicle speed changes dramatically. The experimental results confirm the feasibility of using line scan cameras for railway vehicles.

The design for the conductor rail gaps of a rapid transit system complies with service and maintenance criteria for crossovers, pocket track turnouts, walkway side variations, terminal stations, and different power supply sections. The collector shoes of a moving train passing the gaps will produce mechanical abrasion and switching transient characteristics. If the transient voltage is very large, it will produce electrical erosion on the leaving termination of the conductor rail. Maintenance technicians must often replace the damaged components beside the gaps with a new one to maintain service quality, thus, deciding the position and the type of the gaps to reduce arc voltage is very important. This study analyzed transient voltage of Taipei transit train passing crossovers, pocket track turnouts, and the distinct power supply section from deducing electrical circuits. If non-bridgeable gaps are replaced with bridgeable gaps, the bridgeable gaps will produce more arcing current than non-bridgeable gaps for the circuit from transient to steady state. The analysis results indicate that the magnitude of transient voltage depends on the charge and discharge time of the line impedance, the train operation speed and the overlap time of the two collector shoes touching the two sides of the conductor rail.

In recent years, the railway transportation system has become one of the main means of transportation. Therefore, driving safety is of great importance. However, because of the potential of multiple breaks of elastic rail clips in a fixed rail, accidents may occur when a train passes through the track. This paper presents the development of a computer visual recognition system which can detect the status of elastic rail clips. This visual recognition system can be used in mass rapid transit systems to reduce the substantial need of manpower for checking elastic rail clips at present. The visual recognition system under current development includes five components: preprocessing, identification of rail position, search of elastic rail clip regions, selection of the elastic rail clip, and recognition of the elastic rail clip. The preprocessing system transforms the colored images into grey-level images and eliminates noises. The identification of rail position system uses characteristics of the grey-level variation and confirms the rail position. The search system uses wavelet transformation to carry out the search of elastic rail clip regions. The selection system finds a suitable threshold, using techniques from morphological processing, object search and image processing. The recognition system processes characteristics and structures of elastic rail clips. Experimental testing shows the ability of the developed system to recognize both normal elastic rail clip images and broken elastic rail clip images. This result confirms the feasibility in developing such a visual recognition system.

This paper presents a method for optimizing train-speed trajectory between two neighboring stations of a mass rapid transit system. This research uses the MAX-MIN ant system of the ant colony optimization algorithms to minimize energy consumption based on the framework of a moving-block signaling system of the mass rapid transit system. The alignment gradient is considered for energy saving. Several constrains, for example acceleration/deceleration and jerk of the train, as well as the average train speed, are also addressed according to the requirements of practical systems. In conclusion, this method will be used to design an operational system.

This paper presents an approach to optimize the running speed code of each signaling block between two neighboring stations of mass rapid transit (MRT) systems with fixed-block signaling (FBS) system. Its objective is to minimize train energy consumption under maximum train capacity with considerations of gradients of alignment, minimum headway of automatic train operation (ATO) system and train average speed and to reduce train peak power under proper selection of running speed code of each signaling block. The speed codes and the shortest block length are searched by using genetic algorithms (GA) with different aspects. Dynamic programming (DP) is used to determine the optimal combination of running speed code of each signaling block.