Search

For enhancing the intelligence of urban traffic, connected automated vehicle (CAV) is recognised as the leading technology in the near future. With on-board sensors and communication devices, status of the vehicles can be obtained to better coordinate the traffic. However, the limited environmental perception range cannot lead to the best efficiency of the global urban traffic. In this study, a three-step evolution strategy of the CAV perception mode is proposed, from autonomous perception to interactive perception to networked perception. Key technologies in these three steps are studied. In autonomous perception, vehicle positioning and dynamic target tracking approaches are proposed. In interactive perception, a reliable multi-mode information exchange mechanism is studied. Finally, a new traffic big data storage and advanced analytics solution in networked perception is introduced. Related experiments about the above key issues are designed, implemented, and verified based on the hardware platform, open source dataset, and cloud platform, respectively. The results show that the positioning distance root mean square achieves 3.9 m, object tracking speed reaches 30fps, and communication average packet loss rate is 2%. As can be seen from testing and simulation results, our proposed approaches can meet technical requirements and support environment perception mode evolution of CAV.

The fault diagnosis and analysis of high-speed train is of great significance for train's safe and highly efficient operation. The complexity and quantity of on-train information which is closely related with fault diagnosis and analysis is increasing rapidly as the development of high-speed railway. Onboard system fault recording files contains lots of important fault information described in short-text which is recorded by maintainers in nature language(NL). This paper makes an analysis on operation and fault information of on-board system recorded in NL based on text mining. The fault text dictionary is constructed for word segmentation, and fault text chain is defined as well as the construction method in order to process the fault recording files. At last, the method is applied to segment the on-board system fault recording files and construct fault text chains, therefore the faults of on-board equipment are analyzed and we obtained the faults' distribution.

Traditional lane-changing (LC) behavioral researches usually focus on the driver’s cognitive performance which includes the driver’s psychological and behavioral habit characteristics, rarely involving the affection of expert driver’s comprehensive behavioral preferences, such as: safety and comfort performance in LC process. Towards the free LC process, a novel LC safety and comfort degree index is proposed in this paper, as well as, the novel definition of LC driving behavioral preferences is described in detail. Taking advantage of interactive evolutionary computing (IEC) and real-time optimization (RTO) metrics, a kind of LC behavioral preferences on-line learning agent extending traditional Belief-Desire-Intention (BDI) structure is explicitly proposed, which can perform behavioral preferences learning activities in the LC process. In addition, driving behavioral preferences learning strategies are introduced which can gradually grasp essentials in driver’s subjective judgments in decision-making of the LC process and make the LC process more safety and scientific. Specifically, a conceptual model of the agent, driving behavioral preferences learning-BDI (DpL-BDI) agent is introduced, along with corresponding functional modules to grasp driving behavioral preferences. Furthermore, colored Petri nets are used to realize the components and scheduler of the DpL-BDI agents. In the end, to compare with the traditional LC parameters’ learning methods (such as: the least squares methods and Genetic Algorithms), a kind of LC problems is suggested to case studies, testing and verifying the validity of the contribution.

Due to the poor environment in the West of China, this research firstly analyzes the application requirements of low density, low cost and high reliability, and then focuses on the integrated BeiDou Navigation Satellite System (BDS) and Inertial Navigation System (INS) to achieve seamless positioning. The map-matching technology in the switch section is studied and its process is discussed and tested, whose accuracy can rise up to 98.6%. On the basis of the above research, a train position system is constructed. The test indicates the positioning precision is less than 3 meters in the differential mode, meeting the demand of the western Low Density Lines.

T rain-ground communication subsystem is a key subsystem in high-speed train control system and plays an important role during the operation of high-speed train. So the reliability of train-ground communication subsystem should be studied in depth. The dynamic fault tree model for train-ground communication subsystem that is modeled based on the structure chart of the subsystem is transformed to Dynamic Bayesian networks. After this, probability of the top event can be obtained by inference algorithm of Bayesian network, and the probability of sub-equipment's failure under the premise of system's failure will be obtained through reverse inference algorithm, which can provide reference information for fault location. The simulations reveal that the reliability of train-ground communication subsystem at any time can be obtained by Dynamic Bayesian Networks method, so we can perform real-time reliability evaluation on train-ground communication subsystem.

System Testing is a key technology of CVIS (Cooperative Vehicle Infrastructure System). A shortest test sequence generating approach in CVIS is proposed in this paper. The paper firstly analyzes the spatial-temporal state of vehicle and complexity of infrastructure in network. Then paper designs system features and test cases, and introduces the concept of support index of the test case to system feature. Then a shortest test sequences generating method and GA method are used to accelerate the convergence speed. The method in this paper provide theoretical basis and implementation guidance in CVIS testing.

With the rapid development of the intelligence and complication to railway systems, there are increasing demands of electromagnetic compatibility performance for train borne system, where the electromagnetic compatibility performance of train positioning system (TPS) is crucial to the design process of the entire system. In this paper, the system architecture of TPS integrating multi sensors is introduced, based on the overall design of the multi-sensor based train integrated positioning system, the electromagnetic interference of the TPS is analyzed at the power module, communication module, transmission and PCB routing, then the electromagnetic compatibility solutions are introduced in hardware and software. Lab test of the TPS validates the performance with proposed strategies.

Basic principle, composition and classification of European Train Control System (ETCS) are introduced. Train Traction model and Brake model of ETCS controlling Curves are studied, which includes increasing and decreasing curve model. At last, the application and development of ETCS in high-speed railway are introduced, which could be as reference of Chinese train control system controlling curves model.

As we known, how to describe rail track with precise data is one important problem in train positioning research fields, research of variational curve model base on Level Set and GVF (Gradient Vector Flow) was studied systematically and the GPS data reduction model, method and algorithm base on variational curve model in limited restriction condition was studied, combine with real track data, analyzed the limited restriction condition in practical rail application environment, raised the limited restriction mathematical model, using the GPS data reduction algorithm Base on Level Set and GVF variational curve model adapt to different environment to realize data reduction and error point deletion, extract some key point or track data from track database to describe rail track in a certain satisfactory error region. The experiment proves that the algorithm model Base on Level Set and GVF could extract precise positioning information and improve rail track database automatic generation method, which is adapt to precise positioning of train control system base on GPS.

Train operation control system is one complex system with some feature like real-time and distributing, aim at different application purpose and operation process of system lifecycle, the emphasize point and level of detail is different. In this paper, MRM-based Simulation Support Technology and it’s application was studied, the modeling theory and method was studied systematically; the Aggregation-Disaggregation problem and settle method of MRM model run together in distributing simulation was studied, solving the couple consistency problem of MRM model; design the distributing and interactive simulation system structure base on HLA, the simulation support technology base on different level resolution was studied. Aim at practical demand of Chinese railway development, the modeling method base on MRM and modeling system structure aim at different simulation motivation was studied, the MRM modeling of key subsystem and parts of Train operation control system was studied, combine with practical work pattern of key parts, study the simulation of constructed model.

In recent years, vehicles detection base on the magnetic effect is a major hot spot in the field of vehicles detection. This paper has studied and realized a wireless magneto-resistive sensor based vehicles detection system, and improved the vehicle detection algorithm. The thesis has used a testing algorithm based on iterative optimal wavelet threshold used to focus on testing whether vehicles passing by. For the speed detection, the traditional algorithm of speed detection has been improved; a new speed detection method which is based on clock synchronization has been used. In that way the error of speed detection will be minimized. The effectiveness of the algorithms has been tested by using the vehicle detection signals of wireless magneto-resistive sensors. Experimental result shows that, the vehicle detection algorithms are available for the vehicles detection and the speed measurement.

Under the development of high technology, GPS software receiver has been more and more highly developed, thus becoming the hot issue in the GPS receiver research field. This paper demonstrates GPS software receiver using IF signal from the NewStar210A IF signal sampler as the raw data, then using Matlab as the software for signal acquisition and tracking. The navigation data, pseudo range, carrier phase information is got. Carrier Noise Ratio Method is applied to rough capture, while carrier location method is also used to get the users location. The experiment result mentions that carrier noise ratio method is used to improve the speed of acquisition and carrier location method can get a higher positioning accuracy

The low-cost train control system is new trend for modern train operation and management. Based on the functional requirement of track map database, generation of track map in GIS and schematic form are mainly studied in this paper, as well as their mapping description. In the low-cost scheme, the flow of the generation is discussed in detailed and several strategies are employed to realize the mapping of GIS and schematic track. With the generating software developed in this work, the generated track map database is validated in the simulation environment and the correction and effectiveness are guaranteed.

Research of variational curve model in limited restriction condition and application in rail train control track database was studied in this paper, raised the method, model and algorithm for digital track map auto-generation from GPS track data, through lots of testify, comparison and improvement using practical data between those algorithm and method, aim at track data, construct mathematical model of data reduction, analyze the limited restriction condition of practical train operation situation, and studied the curve evolution theory, using the algorithm base on variational curve model evolution theory to realize data reduction and error deletion, obtain a few key data automatically to describe rail track in a certain satisfactory error condition, improve the track database automatic generation and optimization method, realize real-time and precise positioning of rail control system base on GPS.

Because of complexity of CTCS-3 train control system, interworking testing and function evaluation could not be operated directly on the system, which means that deep research on modeling and simulation of train operation control system should be carried out. This paper proposes a modeling and verification method based on UML and colored Petri net. On the basis of analysis of advantages and disadvantages of UML modeling, colored Petri net is used as formal specification of UML modeling, which improves scalability of formal method and make up for the deficiency of UML, as lack of analysis of model and verification method. Aiming at sequence diagram, dynamic model of UML, colored Petri net is suggested as a modeling method. Sequence diagram of communication between on-board and RBC during conversion from CTCS-3 to CTCS-2 is designed and transformed into colored Petri net model. Based on information interaction between objects to each other, colored Petri net model of onboard and RBC is obtained. Using CPN tools, the model is simulated and analyzed boundedness and deadlock of model. Thus, correctness of model is verified.

Precise location of a train on the rail network is important to train control system. The general problem of locating a train on closely-spaced parallel tracks is hard to determine the track occupied by train simply relying on GNSS. Hidden Markov Model (HMM) is widely used in speech processing of a time series model. This paper applied the HMM to the track occupied automatic identification, established the HMM of tracks, resolved the problem of track occupied identification using GNSS, and progressive studied the impact on identification, when changing the state number of the HMM, GNSS output frequency and train speed, then the optimal parameters are determined.