As one of the critical state parameters of the battery management system, the state of charge (SOC) of lithium batteries can provide an essential reference for battery safety management, charge/discharge control, and the energy management of electric vehicles (EVs). To analyze the application of deep learning in electric vehicles’ power battery SOC estimation, this study reviewed the technical process, common public datasets, and the neural networks used, as well as the structural characteristics and advantages and disadvantages of lithium battery SOC estimation in deep learning methods. First, the specific technical processes of the deep learning method for SOC estimation were analyzed, including data collection, data preprocessing, feature engineering, model training, and model evaluation. Second, the current commonly and publicly used lithium battery dataset was summarized. Then, the input variables, data sets, errors, and advantages and disadvantages of three types of deep learning methods were obtained using the structure of the neural network used for training as the classification criterion; further, the selection of the deep learning structure for SOC estimation was discussed. Finally, the challenges and future development directions of lithium battery SOC estimation using the deep learning method were explained. Over all, this review provides insights into deep learning for EVs’ Li-ion battery SOC estimation in the future.

Research focused on the real-time rescheduling of high-speed railway traffic with a quasi-moving blocking system and transition process affected by the entrance delays and disruptions determining speed limitation. A mixed-integer linear program model related to a job shop model of operations is formulated to reduce the final delay (tardiness) of trains, where three objective functions combine different manners related to traffic control and speed management. The dynamic interaction between train speed and distance headway is considered in the model. Through experiments on a real-world high-speed line in China, the solution quality of the model is assessed by the delay distribution of trains or the smooth degree of train speed profile. The model manages to optimize traffic in the transition from a disordered condition (when disruptions appear) to a normal condition (after disruptions) for real-time operations. In conclusion, there are two and three transition phases for the cases without and with entrance delays, respectively, seen by analyzing the deviation between the rescheduled and planned timetables.

With development of the heavy-haul railway, the increased axle load and traction weight bring a significant challenge for the service performance and safety maintenance of the railway track. Conducting defect recognition on concrete sleepers and ballast using big data is vital. This paper focused on the detection of absent sleeper support in a ballasted track with an emphasis on the integration of model-based and data-driven methods. To this end, a mathematical model consisting of the wagon, track and wheel–rail contact subsystems was first established to acquire the necessary raw data for the data-driven method, in which the wagon was regarded as a 47-degree-of-freedom multi-body subsystem, and the track was treated as a multi-layer discrete-elastic support beam subsystem with absent sleeper support. Then, an architectural hierarchy of a three-layer convolutional neural network (TLCNN) was developed, which includes three convolutional layers and two pooling layers, and a method for reconstructing one-dimensional sleeper vertical displacement to a two-dimensional time–space matrix was also proposed. Thirdly, verification was carried out by comparing the simulation and experimental results to illustrate the accuracy and reliability of the mathematical model, and the dynamic behaviour of the track with absent sleeper support was investigated. Lastly, the established TLCNN was used to train the raw data of the sleeper vertical displacement and detect the existence of absent sleeper support. Results show that the integration of model-based and data-driven methods was a reliable and effective approach for the detection of absent sleeper support. The proposed TLCNN can acquire and extract robust characteristics in a noisy environment. To handle more complex recognition tasks and further improve performance, deeper CNN models and larger sample sizes should be preferentially considered in practical applications.

It is known that it is critical for train rescheduling problem to address some uncertain disturbances to keep the normal condition of railway traffic. This paper is keen on a mathematical model to reschedule high-speed trains controlled by the quasi-moving blocking signalling system impacted by multidisturbances (i.e., primary delay, speed limitation, and siding line blockage). To be specific, a mixed-integer linear programming is formulated based on an improved alternative graph theory, by the means of rerouting, reordering, retiming, and train control. In order to adjust the train speed and find the best routes for trains, the set of alternative arcs and alternative arrival/departure paths are considered in the constraints, respectively. Due to this complex NP-hard problem, a two-step algorithm with three scheduling rules based on a commercial optimizer is applied to solve the problem efficiently in a real-word case, and the efficiency, validity, and feasibility of this method are demonstrated by a series of experimental tests. Finally, the graphical timetables rescheduled are analysed in terms of free conflicts of the solution. Consequently, the proposed mathematical model enriches the existing theory about train rescheduling, and it can also assist train dispatchers to figure out disturbances efficiently.

As one of the critical state parameters of the battery management system, lithium battery state of charge (SOC) can provide an essential reference for battery safety management, charge/discharge control, and energy management of electric vehicles. To analyze the application of deep learning in electric vehicle power battery SOC estimation, this study reviewed the technical process, common public datasets, and the neural networks used, structural characteristics, advantages and disadvantages of lithium battery SOC estimation in deep learning method. First, the specific technical processes of the deep learning method for SOC estimation were analyzed, including data collection, data preprocessing, feature engineering, model training, and model evaluation. Secondly, the current commonly and publicly used lithium battery dataset was summarized. Then, the input variables, data sets, errors, and advantages and disadvantages of four types of deep learning methods, were concluded using the structure of neural network used for training as the classification criterion. Finally, the challenges and future development directions of lithium battery SOC estimation in deep learning method were explained.