Dewang Chen

Intelligent Train Operation Algorithms for Subway by Expert System and Reinforcement Learning

Current research in automatic train operation concentrates on optimizing an energy-efficient speed profile and designing control algorithms to track the speed profile, which may reduce the comfort of passengers and impair the intelligence of train operation. Different from previous studies, this paper presents two intelligent train operation (ITO) algorithms without using precise train model information and offline optimized speed profiles. The first algorithm, i.e., ITOe, is based on an expert system that contains expert rules and a heuristic expert inference method. Then, in order to minimize the energy consumption of train operation online, an ITOr algorithm based on reinforcement learning (RL) is developed via designing an RL policy, reward, and value function. In addition, from the field data in the Yizhuang Line of the Beijing Subway, we choose the manual driving data with the best performance as ITOm. Finally, we present some numerical examples to test the ITO algorithms on the simulation platform established with actual data. The results indicate that, compared with ITOm, both ITOe and ITOr can improve punctuality and reduce energy consumption on the basis of ensuring passenger comfort. Moreover, ITOr can save about 10% energy consumption more than ITOe. In addition, ITOr is capable of adjusting the trip time dynamically, even in the case of accidents.

Freeway traffic stream modeling based on principal curves and its analysis

We have proposed to use the method of principal curves to describe and analyze the interaction among freeway traffic-stream variables and their joint behaviors without utilizing conventional assumptions made on the functional forms of interactions, as in previous studies. As a nonparameter modeling approach, the performance of the proposed method depends only on the data used and involves no assumed knowledge regarding the relationship among the traffic-stream variables. First, we discuss the basic algorithm for data analysis using principal curves and the corresponding data filter algorithm for determining principal curves for application in traffic-steam analysis. Second, a case study is used to compare the performance of the proposed method to that of the classical model proposed by Greenshields; results indicate that the proposed model is better than the classical one in both data accuracy and curve shape. Finally, the traffic-stream models generated with principal curves at different locations and lanes are compared with each others and the three-dimensional traffic-stream models developed from principal curves are discussed. Clearly, our results have demonstrated the feasibility and advantages of applying principal curves in freeway traffic-stream modeling and analysis.

Time series prediction based on ensemble ANFIS

In this paper, random and bootstrap sampling method and ANFIS (adaptive network based fuzzy inference system) are integrated into En-ANFIS (an ensemble ANFIS) to predict chaotic and traffic flow time series. The prediction results of En-ANFIS are compared with an ANFIS using all training data and each ANFIS unit in En-ANFIS. Experimental results show that the prediction accuracy of the En-ANFIS is higher than that of single ANFIS unit, while the number of training sample and training time of the En-ANFIS are less than that of the ANFIS using all training data. So, En-ANFIS is an effective method to achieve both high accuracy and less computational complexity for time series prediction.

Online Learning Algorithms for Train Automatic Stop Control Using Precise Location Data of Balises

For urban metro systems with platform screen doors, train automatic stop control (TASC) has recently attracted significant attention from both industry and academia. Existing solutions to TASC are challenged by uncertain stopping errors and the fast decrease in service life of braking systems. In this paper, we try to solve the TASC problem using a new machine learning technique and propose a novel online learning control strategy with the help of the precise location data of balises installed at stations. By modeling and analysis, we find that the learning-based TASC is a challenging problem, having characteristics of small sample sizes and online learning. We then propose three algorithms for TASC by referring to heuristics, gradient descent, and reinforcement learning (RL), which are called heuristic online learning algorithm (HOA), gradient-descent-based online learning algorithm (GOA), and RL-based online learning algorithm (RLA), respectively. We also perform an extensive comparison study on a real-world data set collected in the Beijing subway. Our experimental results show that our approaches control all stopping errors in the range of ±0.30 m under various disturbances. In addition, our approaches can greatly increase the service life of braking systems by only changing the deceleration rate a few times, which is similar to experienced drivers. Among the three algorithms, RLA achieves the best results, and GOA is a little better than HOA. As online learning algorithms can dynamically reduce stopping errors by using the precise location data from balises, it is a promising technique in solving real-world problems.

Soft computing methods applied to train station parking in urban rail transit

This paper presents three models - a linear model, a generalized regression neural network (GRNN) and an adaptive network based fuzzy inference system (ANFIS) - to estimate the train station parking (TSP) error in urban rail transit. We also develop some statistical indices to evaluate the reliability of controlling parking errors in a certain range. By comparing modeling errors, the subtractive clustering method other than grid partition method is chosen to generate an initial fuzzy system for ANFIS. Then, the collected TSP data from two railway stations are employed to identify the parameters of the proposed three models. The three models can make the average parking errors under an acceptable error, and tuning the parameters of the models is effective in dynamically reducing parking errors. Experiments in two stations indicate that, among the three models, (1) the linear model ranks the third in training and the second in testing, nevertheless, it can meet the required reliability for two stations, (2) the GRNN based model achieves the best performance in training, but the poorest one in testing due to overfitting, resulting in failing to meet the required reliability for the two stations, (3) the ANFIS based model obtains better performance than model 1 both in training and testing. After analyzing parking error characteristics and developing a parking strategy, finally, we confirm the effectiveness of the proposed ANFIS model in the real-world application.

Adaptive Constraint K-Segment Principal Curves for Intelligent Transportation Systems

This paper revisits the construction of principal curves. Although they have a solid theoretical foundation as a nonlinear extension to principal components, this paper shows that they are difficult to implement in practice if the data distribution is sparse and uneven or if the data contain outliers. These issues may hamper the application of principal curves to an intelligent transportation system. To address these problems, this paper introduces an adaptive constraint K-segment principal curve (ACKPC) algorithm that can be applied in the presence of uneven and sparse distributions, as well as outliers. The benefits of the ACKPC algorithm are as follows: (1) It utilizes predefined endpoints of the curve to reduce the computational effort, and (2) it shows to be less sensitive to parameter settings and outliers. These benefits are demonstrated using two benchmark studies and experimental data from a freeway traffic stream system as well as recorded data from a Global Positioning System (GPS) data from a low-precision GPS receiver.

Modeling and Algorithms of GPS Data Reduction for the Qinghai–Tibet Railway

Satellites are currently being used to track the positions of trains. Positioning systems using satellites can help reduce the cost of installing and maintaining trackside equipment. This paper develops a nonlinear combinatorial data reduction model for a large amount of railway Global Positioning System (GPS) data to decrease the memory space and, thus, speed up train positioning. Three algorithms are proposed by employing the concept of looking ahead, using the dichotomy idea, or adopting the breadth-first strategy after changing the problem into a shortest path problem to obtain an optimal solution. Two techniques are developed to substantially cut down the computing time for the optimal algorithm. The surveyed GPS data of the Qinghai-Tibet railway (QTR) are used to compare the performance of the algorithms. Results show that the algorithms can extract a few data points from the large amount of GPS data points, thus enabling a simpler representation of the train tracks. Furthermore, these proposed algorithms show a tradeoff between the solution quality and computation time of the algorithms.

Position computation models for high-speed train based on support vector machine approach

Graphical abstractDisplay Omitted HighlightsWe increase the positioning accuracy of high-speed train in a new view of advanced computing methods.We formulate a mathematical model based on the analysis of wireless message from train control system.Three positioning computation models and their parameter updating methods are developed.Although LSSVM-based model performs almost the same as SVM-based model, both of them perform much better than the LSM-based model.LSSVM-based model with parameter updating method performs the best among the three models for the online positioning for high-speed trains. High-accuracy positioning is not only an essential issue for efficient running of high-speed train (HST), but also an important guarantee for the safe operation of high-speed train. Positioning error is zero when the train is passing through a balise. However, positioning error between adjacent balises is going up as the train is moving away from the previous balise. Although average speed method (ASM) is commonly used to compute the position of train in engineering, its positioning error is somewhat large by analyzing the field data. In this paper, we firstly establish a mathematical model for computing position of HST after analyzing wireless message from the train control system. Then, we propose three position computation models based on least square method (LSM), support vector machine (SVM) and least square support vector machine (LSSVM). Finally, the proposed models are trained and tested by the field data collected in Wuhan-Guangzhou high-speed railway. The results show that: (1) compared with ASM, the three models proposed are capable of reducing positioning error; (2) compared with ASM, the percentage error of LSM model is reduced by 50.2% in training and 53.9% in testing; (3) compared with LSM model, the percentage error of SVM model is further reduced by 38.8% in training and 14.3% in testing; (4) although LSSVM model performs almost the same with SVM model, LSSVM model has advantages over SVM model in terms of running time. We also put forward some online learning methods to update the parameters in the three models and better positioning accuracy is obtained. With the three position computation models we proposed, we can improve the positioning accuracy for HST and potentially reduce the number of balises to achieve the same positioning accuracy.

Road link traffic speed pattern mining in probe vehicle data via soft computing techniques

This paper develops two soft computing models, i.e., the multilayer feedforward network (MFN) based model and the adaptive-network-based fuzzy inference system (ANFIS) based model, to mine the traffic speed patterns/trends for a road link using the sparse historical probe vehicles (PVs) data at the same link. The two models and an additional naive arithmetical average model are tested on the field datasets obtained in some Beijing (China)s urban expressways. The results illustrate that the soft computing based models have higher robustness to the problem of missing data and their generalization capabilities are better than the arithmetic average model. Comprehensively considering all the performance metrics suggest that the ANFIS offers the best model of traffic trends in studied links. Furthermore, the traffic trends produced by ANFIS provide us the opportunities to identify some meaningful hidden traffic speed patterns. The missing datas influence on the mined traffic speed patterns is also investigated. It is found that the reliability of mined traffic speed patterns decreases with the increasing of the missing datas percentage. Nevertheless, ANFIS based model shows great robustness to the missing data problem.

Freeway traffic stream modeling based on principal curves

The paper first analyses the importance of freeway traffic steam model, then focus on the macroscopic traffic stream model which reflect the relationship between the aggregative traffic variables: traffic density or occupancy, speed, and flow. Different from the conventional method, principal curves are used to modeling the traffic stream without the assumption of certain function form. Furthermore, we presume that the traffic variables interact with each other and would like to summarize the joint behavior of the traffic variables. After giving a brief description of principal curves and the algorithm is given, experiments in two sets of traffic data were carried out for the comparison of the model accuracy between the proposed model and the classical model proposed by Greenshields. Results show that the accuracy of the proposed model is better than that of the classical model. What is more important, it gives a non-parameter modeling method that may be used as the uniform method for traffic stream modeling as long as enough and accurate traffic data are obtained. The conclusion and further work are outlined in the last section of this paper.