Adaptive H_(∞)Filtering Algorithm for Train Positioning Based on Prior Combination Constraints

To solve the problem of data fusion for prior information such as track information and train status in train positioning,an adaptive H∞filtering algorithm with combination constraint is proposed,which fuses prior information with other sensor information in the form of constraints.Firstly,the train precise track constraint method of the train is proposed,and the plane position constraint and train motion state constraints are analysed.A model for combining prior information with constraints is established.Then an adaptive H∞filter with combination constraints is derived based on the adaptive adjustment method of the robustness factor.Finally,the positioning effect of the proposed algorithm is simulated and analysed under the conditions of a straight track and a curved track.The results show that the positioning accuracy of the algorithm with constrained filtering is significantly better than that of the algorithm without constrained filtering and that the algorithm with constrained filtering can achieve better performance when combined with track and condition information,which can significantly reduce the train positioning error.The effectiveness of the proposed algorithm is verified.

Research on train integrated positioning based on grey neural network

Train positioning is the key to ensure the transportation and efficient operation of the railway.Due to the low accuracy and the poor real-time of the train positioning,a train positioning system based on global navigation satellite system/inertial measurement unit/odometer(GNSS/IMU/ODO)combination framework and a train integrated positioning method based on grey neural network are put forward.A data updating method based on the established grey prediction model of train positioning is put forward,which uses the accumulation and summary of the grey theory for the rough prediction of the data.The purpose of the method is to reduce the noise of the original data.Moreover,the radial basis function(RBF)neural network is introduced to correct residual sequence of the grey prediction model.Compared with the single model calibration,this method can make full use of the advantages of each model,thus getting a high positioning accuracy in the case of small samples and poor information.Experiments show that the method has good real-time performance and high accuracy,and has certain application value.

Enhancing train position perception through Al-driven multi-source information fusion

This paper addresses the challenge of accurately and timely determining the position of a train,with specific consideration given to the integration of the global navigation satellite system(GNSS)and inertial navigation system(INS).To overcome the increasing errors in the INS during interruptions in GNSS signals,as well as the uncertainty associated with process and measurement noise,a deep learning-based method for train positioning is proposed.This method combines convolutional neural networks(CNN),long short-term memory(LSTM),and the invariant extended Kalman filter(IEKF)to enhance the perception of train positions.It effectively handles GNSS signal interruptions and mitigates the impact of noise.Experimental evaluation and comparisons with existing approaches are provided to illustrate the effectiveness and robustness of the proposed method.

Text retrieval algorithm that decreases confusion

To overcome the problem that the confusion between texts limits the precision in text re- trieval, a new text retrieval algorithm that decrease confusion （DCTR） is proposed. The algorithm constructs the searching template to represent the user＇ s searching intention through positive and negative training. By using the prior probabilities in the template, the supported probability and anti- supported probability of each text in the text library can be estimated for discrimination. The search- ing result can be ranked according to similarities between retrieved texts and the template. The com- plexity of DCTR is close to term frequency and mversed document frequency （TF-IDF）. Its distin- guishing ability to confusable texts could be advanced and the performance of the result would be im- proved with increasing of training times.

Propagation Mechanisms of Incident Tsunami Wave in Jiangsu Coastal Area,Caused by Eastern Japan Earthquake on March 11,2011

At 13：46 on March 11, 2011（Beijing time）, an earthquake of Mw=9.0 occurred in Japan. By comparing the tsunami data from Guanhekou marine station with other tsunami wave observation gathered from southeast coastal area of China, it was evident that, only in Guanhekou, the position of the maximum wave height appeared in the middle part rather than in the front of the tsunami wave train. A numerical model of tsunami propagation based on 2-D nonlinear shallow water equations was built to study the impact range and main causes of the special tsunami waveform discovered in Jiangsu coastal area. The results showed that nearly three-quarters of the Jiangsu coastal area, mainly comprised the part north of the radial sand ridges, reached its maximum tsunami wave height in the middle part of the wave train. The main cause of the special waveform was the special underwater topography condition of the Yellow Sea and the East China Sea area, which influenced the tsunami propagation and waveform significantly. Although land boundary reflection brought an effect on the position of the maximum wave height to a certain extent, as the limits of the incident waveform and distances between the observation points and shore, it was not the dominant influence factor of the special waveform. Coriolis force＇s impact on the tsunami waves was so weak that it was not the main cause for the special phenomenon in Jiangsu coastal area. The study reminds us that the most destructive wave might not appear in the first one in tsunami wave train.

Integrity assurance of GNSS-based train integrated positioning system

This paper presents a novel Autonomous Integrity Monitoring and Assurance （AIMA） scheme for integrity assurance of the GNSS-based train integrated positioning system. In this scheme, integrity assurance strategies are combined with a three-stage hierarchical architecture, considering the coupling effects among sensor collection, sensor fusion and matching decision level in train integrated positioning. In sensor collecting stage, the AIMA scheme deals with sensor faults and failures with a PCA-based fault detection, diagnosis and isolation approach. In multi-sensor fusion stage, a novel cubature point H0o filter is presented to enhance the fault tolerance capability, and a hybrid approach is applied to indicating and monitoring the protection level of position estimation, concerning both the estimating covariance and measurement slopes. In map matching stage, hypothesis testing with specific test statistic is carried out to determine effectiveness of positioning results. Position calculation will be invalid with an alarm triggered if the specific integrity criterion is not satisfied in any stage. Since independent solutions are applied in AIMA, integrity assurance is closely coupled with information processing in train integrated positioning. Numerical results of the three cases correspond to the hierarchical architecture with field data and simulations are presented to illustrate features and applicability of the proposed AIMA scheme and specific solutions.