Technical operation station scheduling method and device

Abstract

The invention relates to a technical operation station scheduling method and device. The technical operation station scheduling method comprises the following steps: acquiring transportation operation related data from a technical operation station; based on the transportation operation related data, generating a manual scheduling system to simulate an operation mechanism of the technical operation station; determining an optimal scheduling scheme of the transportation operation process based on the manual scheduling system; and controlling the scheduling operation of the technical operation station based on the optimal scheduling scheme. According to the invention, based on the construction of the manual scheduling system, the parallel execution between the actual scheduling system and the manual scheduling system is realized through the calculation experiment optimization of various technical operations and the whole operation process, so that the command and scheduling capability of the technical operation station is improved, the intelligent and integrated operation management is realized, and the operation efficiency is improved. A more efficient and intelligent scheduling solution for rail transport is provided.

Description

Technical Field

[0001] The present disclosure relates to the field of rail transportation technology, and more specifically, to a method and device for scheduling a technical operation station. Background Art

[0002] The Technical Operations Station's responsibilities include supplying locomotives to adjacent railway sections, handling train disassembly and marshaling operations, and performing prescribed technical operations for arriving disassembly trains, departing marshaling trains, and unmarshaled transit trains. The Technical Operations Station is a large and complex operational system, and its dispatching and management face numerous random disturbances, increasing the complexity of command and dispatch. Summary of the Invention

[0003] In order to solve the above problems, the present disclosure proposes a technical operation station scheduling method and device, a computing system and a computer-readable storage medium.

[0004] According to one aspect of the present disclosure, a technical operation station scheduling method is provided, which includes: acquiring transportation operation-related data from the technical operation station; generating a manual scheduling system based on the transportation operation-related data to simulate the operation mechanism of the technical operation station; determining an optimal scheduling plan for the transportation operation process based on the manual scheduling system; and controlling the scheduling operation of the technical operation station based on the optimal scheduling plan.

[0005] Optionally, the transportation operation related data includes station information, train information, line information, equipment and facility information and operation plan information.

[0006] Optionally, the manual scheduling system includes manual personnel, manual vehicles, manual facilities and equipment, manual technical operations, artificial environment and a rule base, wherein the manual personnel, manual vehicles, manual facilities and equipment, manual technical operations and artificial environment respectively simulate the actual personnel, vehicles, facilities and equipment, technical operations and environmental factors involved in the scheduling operations of the technical operation station, and the rule base indicates the relationship between manual personnel, manual vehicles, manual facilities and equipment, manual technical operations and artificial environment and their respective operating standards.

[0007] Optionally, based on the manual scheduling system, determining the optimal scheduling plan for the transportation operation process includes: based on manual personnel, manual vehicles, manual facilities and equipment, manual technical operations, artificial environment and rule base, using the algorithms in the technical operation optimization algorithm library to perform corresponding computational experiments and train the optimal optimization model for technical operations to generate the optimal scheduling plan.

[0008] Optionally, the technical operation station scheduling method further includes: predicting the operation status of the technical operation station based on the transportation operation related data.

[0009] Optionally, the predicted time period for predicting the operating conditions of the technical operation station is determined based on the minimum value of the difference between the moment when the status of each incoming train changes and the current moment, wherein the moment when the status of each incoming train changes is determined based on the current position of each incoming train and the optimal scheduling plan.

[0010] Optionally, the technical operation station scheduling method further includes: cleaning, format conversion, integration and standardization of the transportation operation related data.

[0011] According to another aspect of the present disclosure, a technical operation station scheduling device is provided, which includes: a data acquisition unit, configured to acquire transportation operation-related data from the technical operation station; a manual scheduling unit, configured to generate a manual scheduling system based on the transportation operation-related data to simulate the operation mechanism of the technical operation station; a computational experiment unit, configured to determine the optimal scheduling plan for the transportation operation process based on the manual scheduling system; and a parallel execution unit, configured to control the scheduling operation of the technical operation station based on the optimal scheduling plan.

[0012] Optionally, the transportation operation related data includes station information, train information, line information, equipment and facility information and operation plan information.

[0013] Optionally, the manual scheduling system includes manual personnel, manual vehicles, manual facilities and equipment, manual technical operations, artificial environment and a rule base, wherein the manual personnel, manual vehicles, manual facilities and equipment, manual technical operations and artificial environment respectively simulate the actual personnel, vehicles, facilities and equipment, technical operations and environmental factors involved in the scheduling operations of the technical operation station, and the rule base indicates the relationship between manual personnel, manual vehicles, manual facilities and equipment, manual technical operations and artificial environment and their respective operating standards.

[0014] Optionally, the computational experiment unit is further configured to: based on human personnel, human vehicles, human facilities and equipment, human technical operations, artificial environment and rule base, use the algorithms in the technical operation optimization algorithm library to perform corresponding computational experiments and train the optimal optimization model for technical operations to generate the optimal scheduling plan.

[0015] Optionally, the computational experiment unit is further configured to: predict the operation status of the technical operation station based on the transportation operation related data.

[0016] Optionally, the predicted time period for predicting the operating conditions of the technical operation station is determined based on the minimum value of the difference between the moment when the status of each incoming train changes and the current moment, wherein the moment when the status of each incoming train changes is determined based on the current position of each incoming train and the optimal scheduling plan.

[0017] Optionally, the data acquisition unit is further configured to: clean, format-convert, integrate and standardize the transportation operation-related data.

[0018] According to another aspect of the present disclosure, a computing system is provided, comprising at least one computing device and at least one storage device storing instructions, wherein the instructions, when executed by the at least one computing device, prompt the at least one computing device to execute the technical work station scheduling method as described above.

[0019] According to yet another aspect of the present disclosure, a computer-readable storage medium storing instructions is provided, wherein when the instructions are executed by at least one computing device, the at least one computing device is prompted to execute the technical work station scheduling method as described above.

[0020] By adopting the present disclosure, based on the construction of a manual scheduling system and optimizing various technical operations and the overall operation process through computational experiments, parallel execution between the actual scheduling system and the manual scheduling system is achieved, thereby improving the command and scheduling capabilities of the technical operation station, realizing intelligent and integrated operation management, and providing a more efficient and intelligent scheduling solution for rail transportation. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above and / or other objects and advantages of the present disclosure will become more apparent through the following description of embodiments in conjunction with the accompanying drawings, in which: Figure 1 is a diagram illustrating a framework of an intelligent parallel scheduling system for technical operation stations according to an embodiment of the present disclosure; Figure 2 is a flow chart illustrating a method for scheduling a technical work station according to an exemplary embodiment of the present disclosure; Figure 3 is a flow chart illustrating a method for compiling basic data of a parallel scheduling system according to an exemplary embodiment of the present disclosure; Figure 4 is a block diagram illustrating a technical work station scheduling apparatus according to an exemplary embodiment of the present disclosure; Figure 5 is a block diagram illustrating a computing system including at least one computing device and at least one storage device storing instructions according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0022] Below, in conjunction with the accompanying drawings, a description of a specific embodiment is provided to help the reader obtain a comprehensive understanding of the methods, devices and / or systems described herein. However, after understanding the disclosure of the present application, various changes, modifications and equivalents of the methods, devices and / or systems described herein will be clear. For example, the order of operations described herein is merely an example and is not limited to those orders set forth herein, but can be changed as will be clear after understanding the disclosure of the present application, except for operations that must occur in a specific order. In addition, for greater clarity and conciseness, descriptions of features known in the art may be omitted.

[0023] ACP theory can be used for modeling, optimization and control of complex systems, and can achieve interactive optimization between the physical and virtual worlds through three steps: artificial systems, computational experiments and parallel execution. Specifically, digital models corresponding to physical systems are constructed through artificial systems (for example, digital twins) to simulate the operating mechanisms of the real world (for example, an artificial scheduling system is constructed to simulate the operating logic of personnel, vehicles, equipment, etc. in railway technical operation stations); a large number of simulation experiments are run on artificial systems through computational experiments to explore the optimal strategies under different conditions (for example, based on multi-agent simulation (Multi-Agent Simulation), combined with reinforcement learning (RL), optimization algorithms (for example, genetic algorithms), and considering controllable factors (for example, scheduling strategies) and random disturbances (for example, equipment failures), different scheduling schemes are tested in a digital twin environment to optimize train formation efficiency); through parallel execution (including, for example, cloud-edge collaboration (cloud optimization + edge execution), adaptive learning (online model update), dynamic interaction between physical and artificial systems, etc.), the optimal strategies obtained from computational experiments are applied to the physical system, and real-time feedback adjustments are made (for example, the optimized scheduling scheme is sent to the actual railway operation station, and the execution effect is monitored in real time).

[0024] Figure 1 This is a diagram showing the framework of the intelligent parallel dispatching system for a technical operation station according to an embodiment of the present disclosure. The command and dispatch work of a technical operation station involves too many factors, and the specific command and dispatch measures must be based on the overall transportation and there are certain variables, which is an extremely complex task. For this reason, Figure 1As shown, in the intelligent parallel dispatching system of the technical operation station according to the embodiment of the present disclosure, for complex scenarios in actual command and dispatch, the manual dispatching system can be used to conduct computational experiments, thereby simulating and deducing the optimal dispatching plan; further, in the process of parallel execution, the manual dispatching system is optimized and iterated according to the feedback and data update of the actual command and dispatch, and the computational experiments are dynamically adjusted to improve the dispatching plan in real time; in addition, a typical case library can be constructed based on the manual dispatching system to conduct learning and training for relevant personnel such as duty directors, station dispatchers, and station attendants (for example, data such as dispatching plans, emergency plans, and expert knowledge can be entered into a knowledge base, a dispatching case library, and an emergency plan library, and training courses for relevant knowledge and skills can be generated based on this; through the learning record and training evaluation functions, the learning situation and training effects of employees can be recorded and evaluated to help improve the professional level and work efficiency of employees; a three-dimensional simulation model of the railway technical operation station can be established to simulate and evaluate different dispatching plans and operation plans; the operation process and dispatching effects under various situations can be simulated to evaluate the advantages and disadvantages of different plans; and the simulation and drill function can be used to improve the dispatching personnel's adaptability and decision-making level). The architecture proposed in this disclosure can significantly improve the intelligence and integration level of technical operation stations, enhance the scheduling and management capabilities of technical operation stations for a large number of complex operation plans, and improve the quality and efficiency of railway transportation production.

[0025] In addition, the intelligent parallel scheduling system for technical operation stations according to the embodiments of the present disclosure can collect the hardware configurations and technical parameters of the railway technical operation stations, such as infrastructure, maintenance equipment, and testing instruments, as well as the actual working scope and capabilities of each workstation; organize key facility information such as station line layout, switch location, track length and capacity. Moreover, the computational experiment module can sort out and record the standard processes, safety regulations and required time for different types of operations based on the requirements of various types of vehicle inspection and maintenance operations on the railway; for parallel operation scenarios, analyze the mutual exclusivity and dependencies between different processes, and determine the combination of parallel operations that can be performed simultaneously. In addition, the computational experiment module can predict, for example, the flow of trains entering and leaving the operation station based on relevant operational data such as train operation diagrams and arrival and departure timetables; establish a task allocation model based on the train arrival sequence to ensure the rational use of resources and the timely completion of various technical operations. Moreover, according to the embodiment of the present disclosure, the intelligent parallel scheduling system for technical operation stations can also record the skill levels, job responsibilities and available time periods of the staff in the operation station, and build a human resources database; manage the inventory of various tools, spare parts, materials and other materials, and establish material flow rules that match the operation requirements; design intelligent scheduling algorithms that adapt to the characteristics of railway technical operations (for example, multi-objective optimization algorithms, constraint satisfaction planning, etc.); build a dynamic scheduling model based on real-time data to cope with flexible adjustments in situations such as train delays and temporary additions; create a data warehouse containing all basic information, procedures, plans, human and material resources; implement a regular update mechanism to maintain data accuracy, and discover potential problems through data analysis to continuously optimize scheduling strategies.

[0026] Figure 2 is a flowchart illustrating a technical work station scheduling method according to an exemplary embodiment of the present disclosure.

[0027] like Figure 2 As shown, in step S201, transport operation related data is obtained from the technical operation station. In this example, the transport operation related data includes station information, train information, route information, equipment and facility information, and operation plan information. In addition, the transport operation related data can also be cleaned, formatted, integrated, and standardized (for a detailed description of data cleaning, formatting, integration, and standardization, please refer to the Figure 3 corresponding content).

[0028] In step S202, a manual scheduling system is generated based on the transport operation-related data to simulate the operating mechanism of the technical operation station. In this example, the manual scheduling system includes human personnel, human vehicles, human facilities and equipment, human technical operations, a human environment, and a rule base. Human personnel, human vehicles, human facilities and equipment, human technical operations, and the human environment respectively simulate the actual personnel, vehicles, facilities and equipment, technical operations, and environmental factors involved in the scheduling of the technical operation station. The rule base indicates the relationships among human personnel, human vehicles, human facilities and equipment, human technical operations, and the human environment, as well as their respective operating standards.

[0029] For example, a variety of multimodal modeling methods can be used to model the data, mechanisms, and experience of real technical operation stations to construct a manual scheduling system that simulates the physical scheduling system; through the manual scheduling system, the railway transportation operation process can be dispatched in an integrated station area based on data and knowledge-driven methods. For example, "human personnel" is used to describe any person who may have an impact on transportation operations during the actual command and dispatch of a railway technical operation station, including dispatchers at all levels, station staff, train personnel, and agency personnel. "Human vehicles" is used to describe the respective attributes of different types of vehicles that may be involved in a technical operation station, including freight trains, passenger trains, maintenance vehicles, and shunting locomotives. "Human equipment and facilities" is used to describe the equipment and facilities required for a technical operation station to complete various technical operations, including yards, humps, locomotive equipment, vehicle equipment, and passenger and freight business equipment. "Human technical operations" is used to describe the technical operation tasks involved in a technical operation station, including shunting (vehicle) operations, non-shunting (vehicle) operations, local vehicle operations, locomotive operations, and vehicle operations. "Human environment" is used to describe environmental factors that may have an impact on the actual command and dispatch of a technical operation station, including weather factors, equipment factors, external environmental factors, and policy and regulatory factors. "Rule base" is used to describe the standards and rules for the operation of the five modules: human personnel, human vehicles, artificial facilities and equipment, human technical operations, and artificial environment, as well as the relationships and interactions between them.

[0030] In step S203, the optimal scheduling solution for the transportation operation is determined based on the manual scheduling system. In this example, algorithms in the technical operation optimization algorithm library are used to perform corresponding computational experiments based on human personnel, manual vehicles, manual facilities and equipment, manual technical operations, and the artificial environment, as well as a rule library, and to train an optimization model for optimal technical operations to generate the optimal scheduling solution.

[0031] In the example, a simulation computing experimental environment for the railway transportation operation process can be constructed based on multi-agent reinforcement learning technology. Based on the different command and dispatch scenarios of each technical operation, controllable factors (for example, transportation task priority, number of trains, line status, etc.) and random disturbance factors (for example, natural disasters, failure of operating equipment, human errors, etc.) are comprehensively considered. With human personnel, human vehicles, human facilities and equipment, human technical operations, artificial environments, and rule bases as inputs, the algorithms in the technical operation optimization algorithm library are matched, and corresponding computational experiments are performed. Through continuous iterative optimization, multiple optimal optimization models for technical operations are trained, thereby generating the optimal dispatching plan and the overall technical operation command and dispatch plan. For example, by establishing a mathematical model of the operation process, the various operation tasks of the railway technical operation station can be simulated; the equipment signals within the railway technical operation station (including equipment status monitoring, fault diagnosis, equipment operating parameter adjustment and other functions) can be simulated; various data of the railway technical operation station (including real-time operation data, equipment operation data, operation plan data, etc.) can be managed; the experimental plan of the railway technical operation station can be designed and planned, including formulating computational experimental processes and steps, selecting experimental objects and variables, and determining experimental parameters and conditions; using deep learning, parallel computing and other methods to achieve parameter optimization and model correction, and through analysis and learning of experimental data, parameters can be automatically or manually adjusted and models can be improved, and different optimization model algorithms can be switched for computational experimental testing; the computational experimental results of the railway technical operation station can be analyzed and evaluated (including statistical analysis of the experimental results, data mining and model establishment), and the effectiveness and feasibility of the experiment can be evaluated, and improvement suggestions and optimization plans can be put forward.

[0032] In step S204, based on the optimal scheduling solution, the scheduling operations of the technical operation stations are controlled.

[0033] In this example, a stable and reliable real-time feedback mechanism can be established between the manual scheduling system and the physical scheduling system based on cloud-edge collaboration and model adaptive matching technology (including real-time collection of data generated by the physical scheduling system and outputting and applying scheduling solutions and plans generated by computational experiments to the physical scheduling system). In this example, the operational status of technical operation stations can be predicted based on transportation operation-related data. In this example, the prediction time period for the operational status of the technical operation station is determined based on the minimum difference between the time when each incoming train's status changes and the current time. The time when each incoming train's status changes is determined based on the current position of each incoming train and the optimal scheduling solution.

[0034] For example, based on cloud-edge collaboration and model adaptive matching technology, real-time data interaction and information transmission between the parallel scheduling system and the physical scheduling system (including personnel data synchronization, train data synchronization, equipment data synchronization, scheduling plan synchronization, and plan updates) can be achieved; based on real-time data and historical data, data analysis and model prediction technology can be used to deduce and predict the operating status of the technical operation station; the operation status of the railway operation station can be monitored in real time, and possible problems and bottlenecks can be predicted, so that measures can be taken in advance to adjust and optimize. In the process of deducing and predicting the operating status of the technical operation station, a rolling prediction method can be used for deduction and prediction. For example, each time t is predicted, stage (t stage is a variable value) during the state change period, t stage The calculation method is as follows: 1) Take the current time t current As a time reference; 2) Based on the current position of each incoming train and the current scheduling strategy, calculate the time t when each train status changes change ;3) Calculate t stage =min(t change t current ); 4) Input the prediction results of the period operation status into the operation status simulation part. The operation status simulation part updates the period operation station and train group status based on the prediction results, and uses the simulation results as the input of the operation status prediction part, that is, as the initial state information for the next prediction; 5) With t current For variable step lengths, operational situation prediction and operational status simulation achieve rolling interactive output until the scheduling strategy is verified; 6) In the above process, the operating environment status is changed to achieve sudden changes in the operating environment and further failure of some environments to verify the scheduling effect of the current scheduling strategy; 7) Based on the daily shift plan, the operating status of the train group after the simulation is evaluated to achieve an overall evaluation of the scheduling strategy; 8) Output the evaluation results.

[0035] By adopting the technical operation station scheduling method disclosed in the present invention, it is possible to solve the problems of complicated technical operation processes of railway technical operation stations, numerous interference factors, and reliance on manual scheduling, enhance the scheduling and management capabilities of railway technical operation stations for a large number of complex operation plans, and improve the quality and efficiency of railway freight transportation production.

[0036] Figure 3 4 is a flowchart illustrating a method for compiling basic data for a parallel scheduling system according to an exemplary embodiment of the present disclosure.

[0037] like Figure 3As shown, in step S301, data is collected. In the intelligent parallel scheduling system for railway technical operation stations, the data collection stage provides raw information for subsequent data processing and decision support. The types of data collected may include station information, train information, route information, equipment and facility information, and operation plan information, and the collected data can be organized and categorized.

[0038] For example, information about a particular station can be collected (including the station's name, geographic location, and surrounding infrastructure; the number and length of platforms, their capacity to accommodate trains; the conditions of the loading and unloading yard facilities; the configuration of signaling and communication equipment; information on train arrival and departure lines, marshalling lines, and other line information, as well as station operating hours and relevant operating regulations). For example, information about trains at a station during a certain time period can be collected (e.g., train type, train formation information, train operation plan, and train status). Specifically, the following train information can be collected: train number (passenger and freight trains each have a corresponding train number); train type, such as passenger cars, freight cars, or special vehicles; train formation information, such as the number of vehicles, vehicle type, and load capacity (where vehicle types are mainly collected for freight use, including open cars, flat cars, covered cars, tank cars, and insulated cars; and for passenger use, mainly including hard seat cars, hard sleeper cars, soft sleeper cars, dining cars, and luggage cars); train operation plan, such as train arrival and departure times, stop times, and operation routes; train status, such as whether it is on time, whether it is late and the reason for the delay, and whether it has a malfunction. For example, line information can be collected (for example, technical parameters such as railway line name, mileage, speed limit, etc.; line occupancy, construction and maintenance information; technical conditions and restrictions of key nodes, such as switches, culverts, bridges, tunnels, etc.). For example, equipment and facility information can be collected (including real-time status and performance parameters of systems such as signals, communications, and power supply, as well as maintenance and inspection records, service life, failure rate, and other data). For example, operation plan information can be collected (including, for example, global or local train operation diagrams, transportation task arrangements for special periods, and emergency plans and special driving organization plans). For example, information such as the local weather environment can be collected, including but not limited to real-time weather forecasts and temperature and humidity reminders, natural disaster warnings, surrounding public facilities, entertainment facilities, and catering and accommodation. These data are usually collected through the integration of railway internal information systems, real-time monitoring of sensor networks, manual entry and updates, etc.

[0039] In step S302, the collected data is sorted and preprocessed. Through data sorting and preprocessing, the original disorganized and uneven data can be converted into high-quality basic data suitable for use in the intelligent parallel scheduling system.

[0040] In this example, data can be cleansed. For example, duplicate data can be removed (for example, large amounts of collected data can be deduplicated to ensure the uniqueness of each record), missing values can be filled (for example, gaps or incomplete information in the data can be filled with reasonable values based on business logic, historical data, or predictive models), and erroneous data can be corrected (for example, data anomalies caused by data entry errors, sensor false alarms, etc. can be detected and corrected).

[0041] In this example, the cleaned data can be transformed, for example, to unify the format (for example, converting data from different source systems into a unified format to facilitate subsequent integration and analysis), and to convert data types (for example, converting text-type date and time into a standard date and time format, or converting category labels into numerical codes, etc.).

[0042] In the example, data integration can be performed (including, for example, associative integration (for example, associating independent data sets based on key fields such as train number, train number, timestamp, etc. to form a complete business view) and dimensional modeling (for example, building a star or snowflake data warehouse model to facilitate multi-dimensional and multi-level data analysis and query)). In this example, the final data can be standardized. For example, data with different dimensions can be standardized (e.g., unifying the units of distance, speed, time, etc.), and categorical data can be encoded (e.g., using one-hot encoding or label encoding). For example, continuous variables can be normalized (min-max scaling) or standardized (z-score standardization) to make different indicators comparable, which facilitates the training and optimization of machine learning algorithms.

[0043] In step S303, the sorted and pre-processed data is compiled. The main function of this step is to integrate the sorted and pre-processed data and construct a database structure suitable for system use based on the ACP theory.

[0044] In this example, a database model can be designed. For example, a database table structure (including, for example, a station information table, a train information table, a route information table, an equipment and facility table, an operation schedule table, etc.) that meets the requirements (e.g., 3NF (Third Normal Form) or other suitable normal forms) can be designed based on business needs and system functions.

[0045] In this example, data is entered and stored. For example, various pre-processed basic data is entered according to the designed database structure and stored in the corresponding database tables. At this point, data consistency, integrity, and correctness must be ensured. For example, transactions can be used to ensure the security of data updates.

[0046] In this example, you can further establish data associations. For example, you can integrate data according to certain key constraints; establish associations between different tables by setting primary and foreign keys, such as linking trains with train numbers, stations with routes, and equipment with maintenance records; and create views or intermediate tables to simplify complex queries or support data display and analysis needs for specific business scenarios.

[0047] In addition, for databases, appropriate security considerations can be taken into account and reasonable user permissions can be set to effectively protect data security and prevent illegal access and tampering. Sensitive data should be further encrypted to prevent data leakage and ensure information security. In addition, database data can be backed up and recovered in the event of data loss due to unexpected circumstances (for example, a data backup plan can be developed to regularly back up basic data to cope with possible system failures or disasters; appropriate data recovery mechanisms can be set up to ensure that data services can be quickly restored in emergency situations). For example, when processing time series data, for real-time dynamic data (for example, the real-time location of trains, arrival and departure times, etc.), considering how to efficiently record and retrieve time series data, a special time series data table structure can be created, or a time series database can be used for management.

[0048] In step S304, the compiled data is verified. Verification can include the following: content completeness; logical consistency; data accuracy; real-time dynamic data; and whether the system detects and corrects any anomalies. In the basic data compilation method for the intelligent parallel scheduling system of the railway technical operation station, the data verification stage is a key step in ensuring data quality and accuracy.

[0049] In this example, the completeness of the content can be verified. For example, the data records in each table can be checked to see if they are complete and if there is any missing or omitted information, to ensure that each train, station, line, equipment, and other information contains all the necessary fields.

[0050] In this example, the content can be verified for logical consistency. For example, the data can be verified to match the actual situation (for example, checking whether the train's origin and destination stations match the actual route) and whether there are any theoretical conflicts in the arrival and departure times of trains. Furthermore, the rationality of time series data can be ensured. For example, the chronological order of the train operation plan should be consistent with the actual situation, and there should be no logical conflicts between previous and subsequent events. Furthermore, the logical relationship between equipment and facility status and maintenance records can be verified, for example, whether the status of equipment has been updated after maintenance.

[0051] In this example, data accuracy can be verified. For example, data accuracy can be checked, whether numerical data exceeds a reasonable range (for example, train speed, weight, length, etc.), whether the data matches the actual situation, and the correctness of date and time data (for example, whether future dates or invalid date formats appear). Business rules can also be used to validate data, such as whether the actual travel time of a train on a certain line exceeds the maximum allowed value. In addition, range checks can be performed on numerical data, such as ensuring that train speed, weight, length, etc. should not exceed a reasonable range.

[0052] In this example, real-time verification can be performed. For real-time dynamic data, verification can be performed periodically or based on event-triggered mechanisms to ensure that the data used for scheduling decisions is up-to-date. For example, a reasonable data refresh cycle can be set, and newly collected data can be compared and verified for consistency with historical data. For dynamic data, data verification should be performed periodically to ensure it is up-to-date. In addition, statistical analysis, machine learning algorithms and other means can be used to detect anomalies and promptly discover potential data errors or anomalies. When anomalies are discovered, corresponding repair measures can be taken and fed back to the data collection stage for source investigation and improvement.

[0053] In step 305, the system data is updated and maintained irregularly. In the basic data compilation method of the intelligent parallel dispatching system of the railway technical operation station, the data update and maintenance stage is an important link to continuously ensure the timeliness and accuracy of the data.

[0054] In this example, data can be updated regularly. For example, based on actual business needs and the frequency of data changes, regular data collection and update tasks can be set up (for example, daily, weekly, or monthly updates of static data such as station facility information and train formation information). For real-time dynamic data (such as train operation status and equipment monitoring data), real-time synchronous updates can be achieved through real-time data interfaces or message queues.

[0055] In this example, dynamic real-time updates are possible. For example, interfaces are established with various information systems (e.g., train dispatching and control systems, equipment monitoring systems, and weather information systems) to obtain the latest data changes in real time and immediately update them to the database. For example, when receiving notification of an emergency such as a train delay or equipment failure, relevant data can be quickly adjusted to ensure that scheduling decisions are based on the latest conditions.

[0056] In this example, data quality monitoring and exception handling can be performed. By implementing a data quality monitoring mechanism, newly entered or updated data can be automatically verified to promptly detect and correct errors. Furthermore, abnormal data can be tracked and analyzed to identify the source of the problem and provide feedback for rectification. Abnormal events and their handling results can also be recorded for reference in future optimization efforts.

[0057] In this example, data backup and recovery can be performed. For example, during data updates, regular full and incremental backups can be implemented to prevent data loss due to hardware failure or other reasons. Furthermore, for situations where data is frequently modified, logging or snapshot technology can be used to quickly restore the data state to a specific point in time when needed.

[0058] In this example, data archiving and cleanup can be performed. For example, outdated and unused information can be cleaned up to improve system performance. Furthermore, a reasonable data retention policy can be established based on regulatory requirements and business needs, and data that has exceeded its retention period can be securely destroyed or anonymized.

[0059] In this example, system upgrades and adaptive adjustments can be performed. When system functionality is upgraded or business rules are changed, the underlying data structure and content are updated and maintained accordingly to ensure data compatibility with the system. This data update and maintenance phase effectively ensures that the Railway Technical Operations Station's intelligent parallel scheduling system always uses the latest and most accurate data to support its efficient and stable operation.

[0060] Figure 4 2 is a block diagram illustrating a technical work station scheduling device according to an exemplary embodiment of the present disclosure.

[0061] like Figure 4 As shown, the technical operation station scheduling device 400 according to an exemplary embodiment of the present disclosure includes: a data acquisition unit 401, configured to acquire transportation operation related data from the technical operation station; a manual scheduling unit 402, configured to generate a manual scheduling system based on the transportation operation related data to simulate the operation mechanism of the technical operation station; a computational experiment unit 403, configured to determine the optimal scheduling plan for the transportation operation process based on the manual scheduling system; and a parallel execution unit 404, configured to control the scheduling operation of the technical operation station based on the optimal scheduling plan.

[0062] In the example, the transportation operation related data includes station information, train information, line information, equipment and facility information, and operation plan information.

[0063] In the example, the manual scheduling system includes manual personnel, manual vehicles, manual facilities and equipment, manual technical operations, artificial environment and a rule base, wherein the manual personnel, manual vehicles, manual facilities and equipment, manual technical operations and artificial environment respectively simulate the actual personnel, vehicles, facilities and equipment, technical operations and environmental factors involved in the scheduling operations of the technical operation station, and the rule base indicates the relationship between manual personnel, manual vehicles, manual facilities and equipment, manual technical operations and artificial environment as well as their respective operating standards.

[0064] In the example, the computational experiment unit 403 is further configured to: based on human personnel, human vehicles, human facilities and equipment, human technical operations, artificial environment and rule base, use the algorithms in the technical operation optimization algorithm library to perform corresponding computational experiments and train the optimal optimization model for technical operations to generate the optimal scheduling plan.

[0065] In this example, the computational experiment unit 403 is further configured to predict the operational status of the technical operation station based on the transport operation-related data. In this example, the prediction time period for predicting the operational status of the technical operation station is determined based on the minimum difference between the time when each incoming train's status changes and the current time, wherein the time when each incoming train's status changes is determined based on the current location of each incoming train and the optimal scheduling solution.

[0066] In the example, the data acquisition unit 401 is further configured to: clean, convert, integrate and standardize the transportation operation related data.

[0067] Combination of the above Figures 1 to 3 The specific operations shown are respectively Figure 4 The operations are executed by corresponding units in the technical operation station scheduling device 400 shown in the figure. Here, the specific operation details will not be repeated.

[0068] By adopting the technical operation station scheduling device according to the exemplary embodiment of the present disclosure, the command and scheduling capabilities of the technical operation station can be improved, and intelligent and integrated operation management can be achieved.

[0069] Figure 5 is a block diagram illustrating a computing system including at least one computing device and at least one storage device storing instructions according to an exemplary embodiment of the present disclosure.

[0070] like Figure 5 As shown, the computing system 500 according to an exemplary embodiment of the present invention includes a computing device 501 and a storage device 502, wherein the storage device 502 stores computer executable instructions. When the computer executable instructions are executed by the computing device 501, the technical operation station scheduling method described in any of the aforementioned embodiments is executed.

[0071] The computing device 501 is deployed in a server or client, or can be deployed on a node device in a distributed network environment. In addition, the computing device 501 can be a PC, tablet device, personal digital assistant, smartphone, web application, or other device capable of executing the above-mentioned instruction set. Here, the computing device does not necessarily have to be a single computing device, but can also be any collection of devices or circuits that can execute the above-mentioned instructions (or instruction sets) individually or in combination. The computing device can also be part of an integrated control system or system manager, or can be configured as a portable electronic device that is interconnected with an interface locally or remotely (for example, via wireless transmission). In the computing device, the processor includes a central processing unit (CPU), a graphics processing unit (GPU), a programmable logic device, a dedicated processor system, a microcontroller, or a microprocessor. By way of example and not limitation, the processor also includes an analog processor, a digital processor, a microprocessor, a multi-core processor, a processor array, a network processor, etc.

[0072] According to another aspect of the present disclosure, a computer-readable storage medium storing instructions is provided. When the instructions are executed by at least one computing device, the at least one computing device is prompted to execute the technical work station scheduling method described in any of the aforementioned embodiments. Computer-readable storage media include magnetic media such as floppy disks and magnetic tapes, optical media (including compact disc (CD) ROMs and DVD ROMs), magneto-optical media such as floppy disks, and hardware devices designed to store and execute program commands, such as ROMs, RAMs, and flash memories. The instructions may include language codes executable by a computer using an interpreter, as well as machine language codes generated by a compiler.

[0073] By adopting the present disclosure, based on the construction of a manual scheduling system and optimizing various technical operations and the overall operation process through computational experiments, parallel execution between the actual scheduling system and the manual scheduling system is achieved, thereby improving the command and scheduling capabilities of the technical operation station, realizing intelligent and integrated operation management, and providing a more efficient and intelligent scheduling solution for rail transportation.

[0074] The processes, methods, or algorithms disclosed herein may be transmitted to or implemented by a processing device, controller, or computer, which may include any existing programmable electronic control unit or a dedicated electronic control unit. Similarly, the processes, methods, or algorithms may be stored as data and instructions executable by a controller or computer in a variety of forms, including but not limited to permanent storage of information on non-writable storage media (such as ROM devices) and mutably storage of information on writable storage media (such as floppy disks, magnetic tapes, CDs, RAM devices, and other magnetic and optical media). The processes, methods, or algorithms may also be implemented in a software executable object. Alternatively, the processes, methods, or algorithms may be implemented in whole or in part using suitable hardware components (such as ASICs, FPGAs, state machines, controllers, or other hardware components or devices) or a combination of hardware, software, and firmware components.

[0075] Although the present disclosure includes specific examples, it will be apparent to those skilled in the art that various changes in form and detail may be made in these examples without departing from the spirit and scope of the claims and their equivalents. The examples described herein are to be considered in a descriptive sense only and not for purposes of limitation. The description of features or aspects in each example is to be considered applicable to similar features or aspects in other examples. Suitable results may be obtained if the described techniques are performed in a different order, and / or if the components of the described systems, architectures, devices, or circuits are combined in a different manner and / or replaced or supplemented with other components or their equivalents. Therefore, the scope of the present disclosure is not limited by the specific embodiments, but by the claims and their equivalents, and all variations within the scope of the claims and their equivalents are to be construed as included in the present disclosure.

Claims

1. A method for scheduling a technical operation station, characterized in that: The technical operation station scheduling method includes: Obtain transportation operation related data from technical operation stations; Based on the transport operation related data, a manual scheduling system is generated to simulate the operation mechanism of the technical operation station; Determine the optimal scheduling plan for the transportation operation process based on the manual scheduling system; Based on the optimal scheduling plan, the scheduling operations of the technical operation station are controlled.

2. The method for scheduling technical work stations according to claim 1, characterized in that: The transportation operation related data includes station information, train information, line information, equipment and facility information and operation plan information.

3. The method for scheduling technical work stations according to claim 1, characterized in that: The manual scheduling system includes manual personnel, manual vehicles, manual facilities and equipment, manual technical operations, artificial environment and a rule base, wherein the manual personnel, manual vehicles, manual facilities and equipment, manual technical operations and artificial environment respectively simulate the actual personnel, vehicles, facilities and equipment, technical operations and environmental factors involved in the scheduling operations of the technical operation station, and the rule base indicates the relationship between manual personnel, manual vehicles, manual facilities and equipment, manual technical operations and artificial environment and their respective operating standards.

4. The method for scheduling technical work stations according to claim 3, characterized in that: Based on the manual scheduling system, determining the optimal scheduling plan for the transportation operation process includes: based on manual personnel, manual vehicles, manual facilities and equipment, manual technical operations, artificial environment and rule base, using the algorithms in the technical operation optimization algorithm library to perform corresponding computational experiments and train the optimal optimization model for technical operations to generate the optimal scheduling plan.

5. The method for scheduling technical work stations according to claim 1, characterized in that: The technical operation station scheduling method further includes: predicting the operation status of the technical operation station based on the transportation operation related data.

6. The method for scheduling technical work stations according to claim 5, characterized in that: The predicted time period for predicting the operation status of the technical operation station is determined based on the minimum value of the difference between the moment when the status of each incoming train changes and the current moment, wherein the moment when the status of each incoming train changes is determined based on the current position of each incoming train and the optimal scheduling plan.

7. The method for scheduling technical work stations according to claim 1, characterized in that: The technical operation station scheduling method also includes: cleaning, format conversion, integration and standardization of the transportation operation related data.

8. A technical operation station scheduling device, characterized in that: The technical operation station scheduling device includes: a data acquisition unit configured to acquire transport operation related data from a technical operation station; a manual scheduling unit configured to generate a manual scheduling system based on the transport operation related data to simulate the operation mechanism of the technical operation station; a computational experiment unit configured to determine an optimal scheduling solution for a transportation operation process based on the manual scheduling system; The parallel execution unit is configured to control the scheduling operations of the technical operation station based on the optimal scheduling solution.

9. A computing system comprising at least one computing device and at least one storage device storing instructions, characterized in that: When the instructions are executed by the at least one computing device, the at least one computing device is prompted to perform the technical work station scheduling method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing instructions, characterized in that: When the instructions are executed by at least one computing device, the at least one computing device is prompted to execute the technical work station scheduling method according to any one of claims 1 to 7.

Images