Railway dispatching transportation intelligent system

Abstract

The invention discloses a railway dispatching transportation intelligent system. The system comprises a data acquisition module, a data preprocessing module, an intelligent analysis and prediction module, a dynamic dispatching optimization module, a communication and data exchange module, a user interface and interaction module, a system performance monitoring and adaptive learning module, an emergency response module and an energy management module. The system can acquire multivariate data in a railway network in real time, perform deep mining on the data through the intelligent analysis and prediction module, and accurately predict conditions such as train operation delay and fault risk, so that a dispatcher can take measures in advance to avoid or reduce delay, thereby remarkably improving punctuality and efficiency of railway transportation, and improving the safety of railway transportation. The dynamic scheduling optimization module can dynamically adjust the train operation plan according to the prediction result and the actual operation condition, the flexible scheduling mode can utilize railway resources to the maximum extent, waiting and conflicts between trains are reduced, and the transportation efficiency is further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of railway transportation management, and in particular to an intelligent railway transportation dispatching system. Background Art

[0002] Traditional railway dispatching and transportation systems mainly rely on manual dispatching and experience judgment, which makes it difficult to cope with complex and changing transportation needs and emergencies. With the rapid development of information technology, especially the widespread application of technologies such as big data, artificial intelligence and the Internet of Things, building a railway dispatching and transportation intelligent system that can collect data in real time, intelligently analyze and predict, and dynamically adjust dispatching plans has become an inevitable trend in the development of the industry.

[0003] Chinese patent announcement number CN103208055B discloses a railway transportation logistics intelligent dispatching system and its vehicle position tracking method. The present invention is implemented in the form of an industrial railway vehicle position tracking algorithm in software. The industrial railway vehicle position tracking algorithm is implemented in the logistics management server, and the overall function consists of several parts such as the vehicle position tracking module and the clearing information processing module. The intelligent dispatching computer, logistics management computer, logistics management server, logistics management database, ERP interface database, vehicle number recognition system and other computers communicate with the server via Ethernet, the intelligent dispatching computer and the signal system computer use RS232 communication, and the intelligent dispatching computer and the railway locomotive safety control system communicate via an industrial wireless network. The present invention can track the vehicle position during industrial railway transportation; however, the above patent document still has the following defects during implementation: Although the above patent can track the position of vehicles during transportation during implementation, it cannot accurately predict the actual operation of the train, nor can it predict changes in passenger demand to adjust the train operation plan. Summary of the invention

[0004] The main purpose of the present invention is to provide an intelligent railway dispatching and transportation system, which can effectively solve the problem of being unable to accurately predict the actual situation of train operation and unable to predict changes in passenger demand to adjust the train operation plan.

[0005] To achieve the above object, the technical solution adopted by the present invention is: a railway dispatching and transportation intelligent system, the system comprising: Data collection module: used to collect multi-dimensional data in the railway network in real time, including but not limited to train position, speed, signal status, track occupancy, weather conditions, cargo loading status and passenger flow; Data preprocessing module: cleans, verifies, formats and standardizes the data collected by the data acquisition module to produce high-quality data for subsequent analysis; Intelligent analysis and prediction module: Based on the data processed by the data preprocessing module, using big data analysis and machine learning algorithms, predict train operation delays, failure risks, changes in passenger demand and freight transportation demand, and generate a prediction report; Dynamic scheduling optimization module: based on the forecast report generated by the intelligent analysis and forecast module, dynamically adjust the train operation plan in combination with the actual operation status of the railway network. The train operation plan includes but is not limited to departure time, arrival time, stopover sites, operation path and train formation; Communication and data exchange module: adopts efficient and secure communication protocols to realize data exchange between modules within the system and with external systems, including but not limited to train control systems, station management systems and signal systems; User interface and interaction module: Provides an intuitive and easy-to-use operation interface to display the real-time status of the railway network, dispatching plan details and abnormal alarm information, and supports dispatchers to perform manual intervention and plan adjustments; System performance monitoring and adaptive learning module: The system continuously monitors the operating status of the system, including data processing efficiency, prediction model accuracy, and system resource usage, and automatically adjusts the prediction model and optimizes algorithm parameters based on scheduling execution results and user feedback; Emergency response module: automatically triggers emergency response plans when a train failure, signal failure or other emergency is detected, including but not limited to adjusting train operation plans, issuing emergency notifications and activating backup systems; Energy management module: Based on the train operation plan and real-time data, the optimization of energy use includes but is not limited to adjusting the train traction power and using regenerative braking to recover energy.

[0006] Preferably, the intelligent analysis and prediction module includes a prediction model trained based on historical data and real-time data.

[0007] Preferably, the dynamic scheduling optimization module includes a multi-objective optimization algorithm, which includes comprehensive consideration of transportation efficiency, energy consumption, passenger satisfaction, safety and environmental protection requirements.

[0008] Preferably, the communication and data exchange module includes a data encryption unit, which is used for the security and integrity of data transmission, and data conversion and adaptation between heterogeneous systems.

[0009] Preferably, the user interface and interaction module include dispatcher authority management and historical data query, wherein the dispatcher authority management is used to allow dispatchers with corresponding authority to perform operations and view sensitive information, and the historical data query is used for dispatchers to query past dispatch records and prediction results.

[0010] Preferably, the system performance monitoring and adaptive learning module includes a system performance warning and prediction model. The system performance warning is used to automatically issue a warning signal and prompt the dispatcher to handle the problem when the system performance is lower than a preset threshold. The prediction model is used to continuously receive new data and feedback and automatically adjust model parameters and algorithm strategies.

[0011] Preferably, the emergency response module includes an emergency plan library and emergency resource scheduling, the emergency plan library stores response plans for various emergency scenarios, the response plans include but are not limited to personnel evacuation, train rescue and signal restoration, the emergency resource scheduling is used according to the specific type and severity of the emergency, the emergency resource scheduling includes but is not limited to rescue trains, maintenance personnel and backup signal equipment.

[0012] Preferably, the energy management module includes energy usage forecasting and energy efficiency assessment, wherein the energy usage forecasting is based on historical data and real-time data to predict the energy demand of the train under different operating conditions, and the energy efficiency assessment is based on regular assessment of the energy usage efficiency of the train and the railway network, including but not limited to optimizing train operation plans and upgrading energy equipment.

[0013] Preferably, the adaptive learning module adopts a Transformer model, and a deviation learning module is set between the last hidden layer and the output layer of the Transformer model. The deviation learning module sets a deviation algorithm to improve the prediction accuracy. The formula is as follows: , is the output of the last hidden layer, is the number of hidden nodes, is the weight coefficient, ranging from (0.2-0.5), represents the activation function, Is the connection hidden node The weight vector of the input nodes, Represents hidden nodes The bias value of Represents hidden nodes The bias value of and is randomly generated; n is the number of iterations in one sampling period, It is the cumulative increment of the true value and the predicted value within a sampling period; Using mean square error To evaluate the training results of the proposed model: , in represents the number of samples, Represents the model for Sample prediction values, Indicates The true value in the sample.

[0014] Compared with the prior art, the present invention has the following beneficial effects: In the present invention, the system can collect multivariate data in the railway network in real time, and conduct in-depth mining of the data through an intelligent analysis and prediction module to accurately predict train operation delays, failure risks, etc. This enables dispatchers to take measures in advance to avoid or reduce the occurrence of delays, thereby significantly improving the punctuality and efficiency of railway transportation. The dynamic scheduling optimization module can dynamically adjust the train operation plan according to the prediction results and actual operating conditions, including departure time, arrival time, stop points, operation path, etc. This flexible scheduling method can maximize the use of railway resources, reduce waiting and conflicts between trains, and further improve transportation efficiency.

[0015] In the present invention, the system can predict changes in passenger demand and adjust train formation, stop sites, etc. according to demand to meet the diverse needs of passengers. The user interface and interaction module provide an intuitive and easy-to-use operation interface, allowing passengers to easily query train schedules, seat information, delays, etc., thereby improving passengers' travel experience. By reducing train delays and improving transportation efficiency, the system can also shorten passengers' travel time and improve passenger satisfaction.

[0016] In the present invention, the system can detect potential failure risks in advance through intelligent analysis and prediction, and take corresponding maintenance measures to avoid the occurrence of failures, which reduces the train shutdown and maintenance costs caused by failures. The dynamic scheduling optimization module can optimize the train operation plan, reduce waiting and conflicts between trains, thereby reducing energy consumption and operating costs. The system performance monitoring and adaptive learning module can continuously monitor the system operation status, automatically adjust the prediction model and optimize the algorithm parameters, improve the intelligence level of the system and the accuracy of scheduling decisions, and further reduce operating costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a flow chart of the present invention. DETAILED DESCRIPTION

[0018] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further explained below in conjunction with specific implementation methods.

[0019] A railway dispatching and transportation intelligent system, the system comprising: Data collection module: used to collect multi-dimensional data in the railway network in real time, including but not limited to train position, speed, signal status, track occupancy, weather conditions, cargo loading status and passenger flow; Data preprocessing module: cleans, verifies, formats and standardizes the data collected by the data acquisition module to produce high-quality data for subsequent analysis; Intelligent analysis and prediction module: Based on the data processed by the data preprocessing module, it uses big data analysis and machine learning algorithms to predict train operation delays, failure risks, changes in passenger demand and freight transportation demand, and generate prediction reports; Dynamic scheduling optimization module: Based on the forecast report generated by the intelligent analysis and forecast module and combined with the actual operation status of the railway network, the train operation plan is dynamically adjusted. The train operation plan includes but is not limited to departure time, arrival time, stopover stations, operation path and train formation; Communication and data exchange module: adopts efficient and secure communication protocols to realize data exchange between modules within the system and with external systems. Data exchange includes but is not limited to train control systems, station management systems and signal systems; User interface and interaction module: Provides an intuitive and easy-to-use operation interface to display the real-time status of the railway network, dispatching plan details and abnormal alarm information, and supports dispatchers to perform manual intervention and plan adjustments; System performance monitoring and adaptive learning module: continuously monitors the system operation status including data processing efficiency, prediction model accuracy and system resource usage, and automatically adjusts the prediction model and optimizes algorithm parameters based on scheduling execution results and user feedback; The adaptive learning module adopts the Transformer model, and sets a deviation learning module between the last hidden layer and the output layer of the Transformer model. The deviation learning module sets a deviation algorithm to improve the prediction accuracy. The formula is as follows: , is the output of the last hidden layer, is the number of hidden nodes, is the weight coefficient of , represents the activation function, Is the connection hidden node The weight vector of the input nodes, Represents hidden nodes The bias value of and is randomly generated; n is the number of iterations in one sampling period, It is the cumulative increment of the true value and the predicted value within a sampling period; Using mean square error To evaluate the training results of the proposed model: , in represents the number of samples, Represents the model for Sample prediction values, Indicates The true value in the sample.

[0020] , Coefficient of determination To evaluate the training results of the proposed model, represents the mean of the sample.

[0021] Emergency response module: automatically triggers emergency response plans when train failure, signal failure or other emergency situations are detected. Emergency response plans include but are not limited to adjusting train operation plans, issuing emergency notifications and activating backup systems; Energy management module: Based on the train operation plan and real-time data, optimize energy usage, including but not limited to adjusting the train traction power and using regenerative braking to recover energy.

[0022] The data acquisition module sends the collected data to the data preprocessing module for further processing. The data processed by the data preprocessing module will then be sent to the intelligent analysis and prediction module for analysis and prediction. The prediction report generated by the intelligent analysis and prediction module will be sent to the dynamic scheduling optimization module as the basis for scheduling decisions. At the same time, the intelligent analysis and prediction module will also provide a visual display of the prediction results to the user interface and interaction module for the dispatcher to view. The scheduling plan generated by the dynamic scheduling optimization module will be sent to external systems such as the train control system and station management system for execution. At the same time, the scheduling plan will also be displayed to the dispatcher for viewing and manual intervention through the user interface and interaction module. The communication and data exchange module is responsible for transmitting data and information between modules and between the system and external systems. The user interface and interaction module receives information from the intelligent analysis and prediction module. The information of the prediction module and the dynamic scheduling optimization module is analyzed and displayed to the dispatcher. The dispatcher can perform manual intervention and plan adjustment through this module, and send the instructions to the dynamic scheduling optimization module for execution. The system performance monitoring and adaptive learning module continuously monitors the system operation status and adjusts the prediction model and optimization algorithm parameters as needed. When the system performance is lower than the preset threshold, the module will automatically issue a warning signal and prompt the dispatcher to handle it. The emergency response module automatically triggers the emergency response plan when a train failure, signal failure or other emergency situation is detected. The energy management module optimizes energy use according to the train operation plan and real-time data, reduces operating costs and reduces environmental impact. The two modules also work together in emergency situations. For example, the emergency response module may trigger the energy management module to adjust the train traction power to deal with emergencies.

[0023] The intelligent analysis and prediction module includes prediction models trained based on historical data and real-time data.

[0024] Using big data analysis and machine learning algorithms, we can predict train operation delays, failure risks, changes in passenger demand and freight transportation demand based on these data and generate forecast reports.

[0025] The dynamic scheduling optimization module includes a multi-objective optimization algorithm, which comprehensively considers transportation efficiency, energy consumption, passenger satisfaction, safety and environmental protection requirements.

[0026] The dynamic scheduling optimization module generates the optimal scheduling plan based on the forecast report and the actual operating conditions of the railway network using a multi-objective optimization algorithm, and updates the scheduling plan in real time to adapt to changing conditions.

[0027] The communication and data exchange module includes a data encryption unit, which is used for the security and integrity of data transmission, and data conversion and adaptation between heterogeneous systems.

[0028] The communication and data exchange module adopts efficient and secure communication protocols to ensure the security and integrity of data transmission, and has data encryption and identity authentication functions.

[0029] The user interface and interaction module include dispatcher authority management and historical data query. Dispatcher authority management is used to ensure that dispatchers with corresponding authority can perform operations and view sensitive information. Historical data query is used for dispatchers to query past dispatch records and prediction results.

[0030] The user interface and interaction module provides an intuitive and easy-to-use operating interface that displays the real-time status of the railway network, dispatch plan details and abnormal alarm information. Dispatchers can view information, perform manual intervention and plan adjustments through this module, and receive early warning signals and processing prompts issued by the system.

[0031] The system performance monitoring and adaptive learning module includes system performance warning and prediction models. The system performance warning is used to automatically issue a warning signal and prompt the dispatcher to handle it when the system performance is lower than the preset threshold. The prediction model is used to continuously receive new data and feedback and automatically adjust model parameters and algorithm strategies.

[0032] The prediction model and optimization algorithm parameters are automatically adjusted according to the scheduling execution results and user feedback to improve the intelligence level of the system and the accuracy of scheduling decisions. At the same time, it also has a system performance early warning function, which automatically issues an early warning when the system performance is lower than the preset threshold.

[0033] The emergency response module includes an emergency plan library and emergency resource scheduling. The emergency plan library stores response plans for various emergency scenarios, including but not limited to personnel evacuation, train rescue and signal restoration. Emergency resource scheduling is used according to the specific type and severity of the emergency, including but not limited to rescue trains, maintenance personnel and backup signal equipment.

[0034] The energy management module includes energy usage forecasting and energy efficiency assessment. The energy usage forecasting is based on historical data and real-time data to predict the energy demand of trains under different operating conditions. The energy efficiency assessment is based on regular assessment of the energy usage efficiency of trains and railway networks, including but not limited to optimizing train operation plans and upgrading energy equipment.

[0035] When a train failure, signal failure or other emergency situation is detected, the emergency response plan is automatically triggered, including adjusting the train operation plan, issuing emergency notifications, etc. The energy management module optimizes energy use based on the train operation plan and real-time data, reduces operating costs and reduces environmental impact. The two modules also work together in emergency situations. For example, the emergency response module may trigger the energy management module to adjust the train traction power to respond to emergencies.

[0036] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A railway dispatching and transportation intelligent system, characterized in that: The system includes: Data collection module: used to collect multi-dimensional data in the railway network in real time, including but not limited to train position, speed, signal status, track occupancy, weather conditions, cargo loading status and passenger flow; Data preprocessing module: cleaning, verifying, formatting and standardizing the data collected by the data acquisition module to produce high-quality data for subsequent analysis; Intelligent analysis and prediction module: Based on the data processed by the data preprocessing module, using big data analysis and machine learning algorithms, predict train operation delays, failure risks, changes in passenger demand and freight transportation demand, and generate a prediction report; Dynamic scheduling optimization module: based on the forecast report generated by the intelligent analysis and forecast module, dynamically adjust the train operation plan in combination with the actual operation status of the railway network. The train operation plan includes but is not limited to departure time, arrival time, stopover sites, operation path and train formation; Communication and data exchange module: adopts efficient and secure communication protocols to realize data exchange between modules within the system and with external systems, including but not limited to train control systems, station management systems and signal systems; User interface and interaction module: Provides an intuitive and easy-to-use operation interface to display the real-time status of the railway network, dispatching plan details and abnormal alarm information, and supports dispatchers to perform manual intervention and plan adjustments; System performance monitoring and adaptive learning module: The system continuously monitors the operating status of the system, including data processing efficiency, prediction model accuracy, and system resource usage, and automatically adjusts the prediction model and optimizes algorithm parameters based on scheduling execution results and user feedback; Emergency response module: automatically triggers emergency response plans when a train failure, signal failure or other emergency is detected, including but not limited to adjusting train operation plans, issuing emergency notifications and activating backup systems; Energy management module: Based on the train operation plan and real-time data, the optimization of energy use includes but is not limited to adjusting the train traction power and using regenerative braking to recover energy.

2. The intelligent railway dispatching and transportation system according to claim 1 is characterized in that: The intelligent analysis and prediction module includes a prediction model trained based on historical data and real-time data.

3. According to claim 1, a railway dispatching and transportation intelligent system is characterized by: The dynamic scheduling optimization module includes a multi-objective optimization algorithm, which includes comprehensive consideration of transportation efficiency, energy consumption, passenger satisfaction, and safety.

4. The intelligent railway transportation dispatching system according to claim 1 is characterized in that: The communication and data exchange module includes a data encryption unit, which is used for the security and integrity of data transmission, and data conversion and adaptation between heterogeneous systems.

5. The intelligent railway dispatching and transportation system according to claim 1 is characterized in that: The user interface and interaction module include dispatcher authority management and historical data query. The dispatcher authority management is used to allow dispatchers with corresponding authority to perform operations and view sensitive information. The historical data query is used for dispatchers to query past dispatch records and prediction results.

6. The intelligent railway dispatching and transportation system according to claim 1, characterized in that: The system performance monitoring and adaptive learning module includes a system performance warning and prediction model. The system performance warning is used to automatically issue a warning signal and prompt the dispatcher to handle it when the system performance is lower than a preset threshold. The prediction model is used to continuously receive new data and feedback and automatically adjust model parameters and algorithm strategies.

7. The intelligent railway dispatching and transportation system according to claim 1 is characterized by: The emergency response module includes an emergency plan library and emergency resource scheduling. The emergency plan library stores response plans for various emergency scenarios, including but not limited to personnel evacuation, train rescue and signal restoration. The emergency resource scheduling is used according to the specific type and severity of the emergency, including but not limited to rescue trains, maintenance personnel and backup signal equipment.

8. The intelligent railway dispatching and transportation system according to claim 1, characterized in that: The energy management module includes energy usage prediction and energy efficiency assessment. The energy usage prediction is based on historical data and real-time data to predict the energy demand of the train under different operating conditions. The energy efficiency assessment is based on regular assessment of the energy usage efficiency of trains and railway networks, including but not limited to optimizing train operation plans and upgrading energy equipment.

9. The intelligent railway dispatching and transportation system according to claim 6, characterized in that: The adaptive learning module adopts the Transformer model, and sets a deviation learning module between the last hidden layer and the output layer of the Transformer model. The deviation learning module sets a deviation algorithm to improve the prediction accuracy. The formula is as follows: , is the output of the last hidden layer, is the number of hidden nodes, is the weight coefficient of , represents the activation function, Is the connection hidden node The weight vector of the input nodes, Represents hidden nodes The bias value of and is randomly generated; n is the number of iterations in one sampling period, It is the cumulative increment of the true value and the predicted value within a sampling period; Using mean square error To evaluate the training results of the proposed model: , in represents the number of samples, Represents the model for Sample prediction values, Indicates The true value in the sample.

Images