Evaluation System and Method for Locomotive Automatic Driving

Abstract

The present invention provides an evaluation system and method for locomotive automatic driving. The evaluation system comprises: an automatic driving locomotive system for providing operational data of the automatic driving locomotive, a big data platform including a database and data analysis and evaluation devices, and a dynamics simulation system. The big data platform is connected to the automatic driving locomotive system and the dynamics simulation system. The dynamics simulation system is configured to perform dynamics simulation based on the operational data and obtain a locomotive coupler force variation curve. The data analysis and evaluation device is configured to perform safety and rationality evaluations based on safety evaluation criteria, rationality evaluation criteria, and operational data, and to perform stability evaluations based on stability evaluation rules and the coupler force variation curve to obtain evaluation results. The database is configured to store the operational data and evaluation results. The present invention enables comprehensive and all-round analysis of the operational status of the automatic driving locomotive system from both macro and micro perspectives and has broad application prospects.

Description

Technical Field

[0001] The present invention belongs to the field of big data technology, and specifically relates to an evaluation system and method suitable for automatic driving of a locomotive. Background Art

[0002] With the development of big data technology and the continuous advancement of modern information technology, the world has entered the Internet + Big Data era. Big data is profoundly changing people's thinking, production, and lifestyles, and is about to usher in a new round of industrial and technological revolution. The deep integration of big data with various industries will generate unprecedented social and commercial value. Coupled with the rapid development of the national big data industry, it will play a significant role in forming a complete big data industry innovation chain and promoting the rapid and stable growth of the big data industry. With the further development of big data cloud computing technology, its application areas will surely expand in an orderly manner in the future, bringing a new look to human production and life. The rapid progress of artificial intelligence is undoubtedly due to the rapid development of big data in recent years. The essence of big data is massive, multi-dimensional, and multi-format data. Thanks to the development of various sensors and data collection technologies, we are now able to obtain previously unimaginable amounts of data, and at the same time, we are also gaining in-depth and detailed data in certain fields. Big data is also influencing the development of accompanying systems for the emerging field of autonomous locomotive driving. The evaluation system is a system based on the big data technology platform and is used to serve autonomous locomotive driving.

[0003] There are no clear standards for the technical indicators related to automated locomotive operation. Field trials often rely on manual analysis and data collection. This requires significant manpower to assess test scenario coverage, vehicle control rates, energy consumption, impulse response, comfort, and efficiency. Furthermore, manual verification of issues and statistical analysis of relevant indicators cannot guarantee data accuracy, completeness, or consistency. Currently, railway bureaus lack ground-based systems to support data analysis and statistics on the quality of automated locomotive operation. This lack of a relevant data foundation for data verification and analysis in subsequent projects hinders their validation and promotion. Summary of the Invention

[0004] The present invention provides an evaluation system and method for locomotive automatic driving, so as to solve the problem that the existing automatic driving evaluation is manually performed and cannot guarantee the accuracy, integrity and uniformity of the data.

[0005] Based on the above-mentioned purpose, an embodiment of the present invention provides an evaluation system suitable for locomotive automatic driving, comprising: a locomotive automatic driving system for providing operating data of locomotive automatic driving, a big data platform including a database and a data analysis and evaluation device, and a dynamic simulation system, wherein the big data platform is connected to the locomotive automatic driving system and the dynamic simulation system; the database includes at least a data storage library and an evaluation criteria library; the dynamic simulation system is used to perform dynamic simulation based on the operating data to obtain the coupler force change curve of the locomotive; the evaluation criteria library includes: safety evaluation criteria, stability evaluation rules and rationality evaluation criteria; the data analysis and evaluation device is used to perform safety and rationality evaluation based on the safety evaluation criteria, the rationality evaluation criteria and the operating data, and perform stability evaluation based on the stability evaluation rules and the coupler force change curve to obtain evaluation results; the database is used to store the operating data and the evaluation results.

[0006] Optionally, the database further includes a data analysis configuration library, and the data analysis and evaluation device applies a data analysis and evaluation software method to perform data analysis on the operating data according to the preset data analysis configuration library, and stores the data in the data storage library.

[0007] Optionally, the data analysis and evaluation device is also used to: program and digitize according to railway specifications to generate the safety evaluation criteria; apply intelligent algorithm software methods and standard train intelligent software methods to obtain the speed operation curve of the standard train operation model as the rationality evaluation criteria.

[0008] Optionally, the data analysis and evaluation device is used to: generate the standard train operation model by applying an intelligent algorithm software method based on the manual driving operation data of excellent drivers stored in the database; obtain a simulation curve of the standard train operation model operating in a real environment using the standard train intelligent software method as the speed operation curve of the standard train operation model.

[0009] Optionally, the dynamic simulation system is used to: extract operating parameters related to coupler force calculation based on the operating data, and the operating parameters related to coupler force calculation include at least: air braking amount, slope data, curve data, tunnel data, train formation data and operating speed; perform dynamic simulation and coupler force calculation based on the operating parameters to obtain the coupler force change curve of the locomotive.

[0010] Optionally, the big data platform also includes a statistical display module, which is used to: count the evaluation results of one or more locomotives in different time periods from the time dimension; count the evaluation results of each locomotive in each railway bureau, line or each section from the location dimension; and count the precise parking position distribution and interval time distribution of the automatic driving system of a single track from the accuracy probability distribution.

[0011] Optionally, the statistical display module is further used to: receive a query request input by a user; respond to the query request, and statistically analyze and display the evaluation results of one or more locomotives from the time dimension, location dimension or accuracy probability distribution.

[0012] Optionally, the evaluation system further includes a transmission system connected to the automatic driving system and the big data platform, for transmitting the operating data of the locomotive automatic driving system to the big data platform.

[0013] Based on the same inventive concept, an embodiment of the present invention also proposes an evaluation method suitable for locomotive automatic driving, which is applied to the aforementioned evaluation system suitable for locomotive automatic driving, and the method includes: receiving operating data obtained during the locomotive automatic driving process transmitted by the locomotive automatic driving system; performing dynamic simulation based on the operating data to obtain the coupler force change curve of the locomotive; performing safety and rationality evaluation based on the safety evaluation criteria, rationality evaluation criteria in the evaluation criteria library and the operating data, and performing stability evaluation based on the stability evaluation rules in the evaluation criteria library and the coupler force change curve to obtain an evaluation result.

[0014] Optionally, the method further includes: counting the evaluation results of one or more locomotives in different time periods from the time dimension; counting the evaluation results of each locomotive in each railway bureau, line or each section from the location dimension; and counting the precise parking position distribution and interval time distribution of the automatic driving system of a single track from the accuracy probability distribution.

[0015] The beneficial effects of the present invention are as follows: as can be seen from the above description, an evaluation system and method suitable for locomotive automatic driving provided by an embodiment of the present invention, the evaluation system comprising: a locomotive automatic driving system for providing operating data of the locomotive automatic driving, a big data platform comprising a database and a data analysis and evaluation device, and a dynamic simulation system, wherein the big data platform is connected to the locomotive automatic driving system and the dynamic simulation system; the database comprises at least a data storage library and an evaluation criteria library; the dynamic simulation system is used to perform dynamic simulation according to the operating data to obtain the coupler force change curve of the locomotive; the evaluation criteria library comprises: safety evaluation criteria, stability evaluation rules, and rationality evaluation criteria; the data analysis and evaluation device is used to perform safety and rationality evaluation according to the safety evaluation criteria, the rationality evaluation criteria, and the operating data, and to perform stability evaluation according to the stability evaluation rules and the coupler force change curve to obtain an evaluation result; the database is used to store the operating data and the evaluation results, and can perform a comprehensive and all-round analysis of the operating conditions of the locomotive automatic driving system in both macro and micro aspects, and has broad application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 Schematic diagram of the structure of an evaluation system applicable to automatic driving of a locomotive in an embodiment of the present invention;

[0018] Figure 2 A schematic diagram for generating a standard train operation curve in an embodiment of the present invention;

[0019] Figure 3 is a schematic diagram of a running speed curve of a locomotive in an embodiment of the present invention;

[0020] Figure 4 Schematic diagram of a coupler force variation curve in an embodiment of the present invention;

[0021] Figure 5 Schematic diagram of an evaluation method of an evaluation system in an embodiment of the present invention;

[0022] Figure 6 4 is a flow chart of an evaluation method applicable to automatic driving of a locomotive in an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to make the objectives, technical solutions and advantages of the present disclosure more clearly understood, the present disclosure is further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

[0024] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present invention should have the usual meanings understood by people with ordinary skills in the field to which the present disclosure belongs. The "first", "second" and similar words used in the embodiments of the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0025] The embodiment of the present invention provides an evaluation system suitable for automatic driving of a locomotive. Figure 1 As shown, the evaluation system suitable for locomotive automatic driving includes: a locomotive automatic driving system for providing operating data of the locomotive automatic driving, a big data platform including a database and a data analysis and evaluation device, and a dynamic simulation system, wherein the big data platform is connected to the locomotive automatic driving system and the dynamic simulation system; the database includes at least a data storage library and an evaluation criteria library.

[0026] The dynamic simulation system is used to perform dynamic simulation based on the operating data to obtain the coupler force change curve of the locomotive; the evaluation criteria library includes: safety evaluation criteria, stability evaluation rules and rationality evaluation criteria; the data analysis and evaluation device is used to perform safety and rationality evaluation based on the safety evaluation criteria, the rationality evaluation criteria and the operating data, and perform stability evaluation based on the stability evaluation rules and the coupler force change curve to obtain evaluation results; the database is used to store the operating data and the evaluation results.

[0027] The evaluation system analyzes data sent by the locomotive's automatic driving system using a configurable data parsing configuration library. The data is then stored in a data repository using either regularized or irregular storage methods, providing a data source for subsequent statistics and evaluation. The evaluation system is a specialized application system developed based on a big data cluster / platform and can be divided into an evaluation system and a statistical system. The locomotive automatic driving evaluation system covers all driver-operated time periods, including but not limited to four phases: in-depot preparation, outbound shunting, mainline operation, and inbound shunting. Each operational division item is assigned an evaluation point, and each evaluation point is further subdivided into evaluation items and evaluation criteria. The evaluation criteria measure the item's correctness based on the dimensions of action (whether it occurs), magnitude (speed, torque, position), and time (duration). The collection of evaluation points, items, and criteria is called the evaluation criteria. Items are categorized into three levels: critical, warning, and advisory, depending on the importance of the issue being evaluated. The evaluation system should categorize safety, rationality, and stability based on the item information.

[0028] Continue to see Figure 1 The evaluation system also includes a transmission system connected to the automatic driving system and the big data platform, and is used to transmit the operating data of the locomotive automatic driving system to the big data platform.

[0029] The evaluation system for locomotive autonomous driving, according to the embodiment of the present invention, can be divided into online and offline evaluation, depending on the data source of the locomotive autonomous driving system. Offline evaluation utilizes recorded data from the locomotive autonomous driving system's field operation. Online evaluation, primarily used for laboratory testing, utilizes real-time laboratory data from the locomotive autonomous driving system. Its principles and functions are consistent with offline evaluation, differing in the real-time nature of data processing and the partitioned storage of evaluation results. The embodiment of the present invention utilizes a big data cluster / platform to build the locomotive autonomous driving evaluation system, developing corresponding software and databases on the big data cluster to accommodate locomotive autonomous driving system evaluation applications. The evaluation system consists of system hardware, a database, and software. The evaluation system implements the entire evaluation process according to the basic process of "data input - data storage - driving evaluation - statistical display." The evaluation system software is divided into software modules, including data analysis, evaluation software, standard train intelligent software, intelligent algorithm software, and evaluation system display. The locomotive autonomous driving system includes both onboard and laboratory locomotive autonomous driving systems. It serves as the brain of the locomotive autonomous driving control system, providing online and offline recorded data to the evaluation system and serving as the data source for the evaluation system. The dynamics simulation system calculates the longitudinal, lateral, and vertical coupler forces acting on the locomotive's automated driving system, providing a basis for stability evaluation. The big data platform is the foundational hardware and system architecture for the locomotive's automated driving evaluation system. The evaluation criteria library is a collection of criteria used in evaluating automated locomotive driving.

[0030] In an embodiment of the present invention, the database also includes a data analysis configuration library. The data analysis and evaluation device applies data analysis and evaluation software methods to perform data analysis on the operating data according to the pre-set data analysis configuration library and stores the data in the data storage library. The data analysis and evaluation device is further configured to program and digitize the operating data according to railway specifications to generate the safety evaluation criteria. This is primarily achieved by programing and digitizing national railway operating regulations, business regulations, technical regulations, and other rules and regulations, and evaluating them through software rules. This allows for the detection and evaluation of violations during the operation of the locomotive automatic driving system. For example, the "Railway Locomotive Operating Regulations" stipulates that "freight trains should not release brakes when their speed is below 15 km / h; heavy-load freight trains should not release brakes when their speed is below 30 km / h" as evaluation criteria. The evaluation system sets two evaluation points and items: "normal load + release speed limit" and "heavy load + release speed limit." If the speed of the locomotive automatic driving system during parking is lower than the release speed limit, the locomotive automatic driving system is judged to have experienced a serious safety incident.

[0031] The data analysis and evaluation device also applies intelligent algorithm software methods and standard train intelligent software methods to obtain a speed curve for the standard train operation model as the rationality evaluation criterion. Rationality includes, but is not limited to, whether the control speed, the starting process, and the stopping process are reasonable. Optionally, the data analysis and evaluation device is configured to: generate the standard train operation model using intelligent algorithm software methods based on manual driving operation data of excellent drivers stored in a database; and obtain a simulated curve of the standard train operation model using the standard train intelligent software methods in a real-world environment as the speed curve for the standard train operation model. For example, by using the manual driving operation data of excellent drivers stored in the big data platform and artificial intelligence (AI) algorithms such as machine learning and model training, basic resistance operation parameters (A, B, C values) and air brake force parameters are corrected. The parameters and formulas obtained by correction and training using the AI algorithm constitute a standard train model. The simulated curve of the standard train model running in the real environment is used as the standard train operation curve. This curve is used as the evaluation standard for train operation, and then the actual automatic driving operation curve is compared to see whether it is reasonable (including interval time, speed efficiency, etc.), thereby guiding the improvement of automatic driving technology. Figure 2 Based on the multiple speed curves of manual driving by excellent drivers stored in the big data platform, AI algorithms are used to correct basic resistance operating parameters and air brake force parameters to build a standard train model. The standard train model includes a basic resistance model and an air brake force model. The basic resistance model is w′0=A+Bv+Cv 2 , the air braking force model is Among them, A, B, C are weights, v is the running speed, b c is the commonly used unit braking force of trains, β c is the common braking coefficient, To convert the friction coefficient, θ h is the train braking rate, and b is the train unit braking force during emergency braking. A standard train model is used to simulate the real environment, and a simulation curve, namely the standard train operation curve, is obtained. This curve is used as the rationality evaluation criterion for rationality evaluation.

[0032] In an embodiment of the present invention, the dynamic simulation system is used to: extract the operating parameters related to the coupler force calculation based on the operating data, and the operating parameters related to the coupler force calculation include at least: air braking amount, slope data, curve data, tunnel data, train formation data and operating speed; perform dynamic simulation and coupler force calculation based on the operating parameters to obtain the coupler force change curve of the locomotive. Finally, a stability evaluation is performed based on the coupler force change curve and the stability evaluation rules. For example, using the actual operation data of the autonomous driving on the big data platform, such as Figure 3 The running speed curve in the train is used to extract the running parameters related to the coupler force calculation and transmit them to the power car simulation system. The coupler force calculation is performed to obtain the coupler force change curve of a single train. The train stability is evaluated by comparing and calculating the coupler force curve value with the standard limit value. Figure 4 As shown, the obtained coupler force variation curve is compared with the coupler force limit value to evaluate the stability. The evaluation results can be divided into: whether there is an over-limit; the maximum coupler force of a single trip; the maximum coupler force variation per unit time, etc. Among them, the coupler force limit value includes an upper limit and a lower limit. Figure 4 The upper limit is 900kN, and the lower limit is -900kN. In the embodiment of the present invention, the coupler force limit value can be set as needed without specific restrictions. For example, it can be set according to national standards. The general entry for the coupler force limit value is "longitudinal coupler force safety control limit value". The operating parameters related to the coupler force calculation include traction / electric braking force, air braking amount, slope data, curve data, tunnel data, train formation data, operating speed, etc., and the train formation data includes locomotive model, number of vehicles, formation length, load, total weight, etc. The embodiment of the present invention can also compare the coupler force data of multiple locomotives, mainly comparing the maximum value and the maximum value of variation. By analyzing the coupler force of multiple locomotive operating data, the best control curve can be screened out to guide the improvement of automatic driving system technology.

[0033] In an embodiment of the present invention, the big data platform also includes a statistical display module, which is used to: count the evaluation results of one or more locomotives in different time periods from the time dimension; count the evaluation results of each locomotive in each railway bureau, line or each section from the location dimension; and count the precise parking position distribution and interval time distribution of the automatic driving system of a single track from the accuracy probability distribution.

[0034] The evaluation system should aggregate and summarize evaluation results, efficiency, benefits, coverage, and other indicators according to time, location, and accuracy probability distribution for user presentation. The statistical system encompasses all aspects of the operational process, primarily used to assess whether all indicators of the locomotive automated driving system meet customer (railway bureau, technical, after-sales), design, and management requirements. Statistical information should be calculated based on different dimensions. From a time perspective, statistics should be collected for single trips, multiple trips, a week, multiple weeks, a month, multiple months, a year, multiple years, and custom time periods. From a location perspective, statistics should be collected for each railway bureau, locomotive depot, line, upstream and downstream lines, signal rooms, station sections, station interiors (entry and exit signals), phased areas, through-test areas, and temporary speed restriction areas. For evaluation systems, statistics should be collected for number, distribution, coverage, cumulative, and time, and displayed using curves, pie charts, bar charts, timelines, and electronic maps. From an accuracy probability distribution perspective, statistics can be collected for the precise stopping location distribution and interval time distribution of the locomotive automated driving system on a single track. The users of the statistical system include railway bureaus, after-sales service, technical personnel, etc. Different access rights need to be set for each type of personnel and the access rights are configurable.

[0035] The statistical display module is also used to receive user-input query requests and, in response to these queries, generate and display statistical evaluation results for one or more locomotive trips based on time, location, or accuracy probability distribution. The evaluation system organizes the contents of the data repository based on, but not limited to, train number, locomotive model, time, route, and railway bureau, compiles statistical data from the evaluation results, and displays the results via a web or client for user access. These users can include railway bureau managers, locomotive autonomous driving operators, and locomotive autonomous driving developers.

[0036] Evaluation methods for evaluation systems refer to Figure 5The database includes a data parsing configuration library, a data repository, and an evaluation rule library. Operational data from the locomotive automatic driving system is processed by data analysis and evaluation software and stored in the data repository. Evaluation items and standards are set according to railway specifications, programmed and digitized, and safety evaluation criteria are obtained and stored in the evaluation rule library. Intelligent algorithm software is applied to the manual driving operation data of excellent drivers stored in the data repository to generate a standard train operation model. Based on the standard train operation model, the standard train intelligent software is used to operate in real-world conditions. The speed curve of the standard train operation model is obtained and used as the rationality evaluation criterion and stored in the evaluation rule library. A dynamic simulation system is used to extract data related to coupler force from the operation data and calculate the coupler force variation curve. The optimal curve is selected based on multiple trips of coupler force variation curves as a guide to obtain stability evaluation criteria and store them in the evaluation rule library. When evaluating the operation data of any locomotive, the data analysis and evaluation software is used to analyze and process the operation data. Safety, stability, and rationality are then evaluated according to the evaluation rules in the evaluation rule library, and the evaluation results are stored in the data repository. When railway bureau personnel or designers need to view the evaluation results, they use the evaluation system display software to respond to the viewing request and obtain the evaluation results from the data repository for statistics and display.

[0037] The evaluation system for locomotive autonomous driving, according to embodiments of the present invention, analyzes and organizes locomotive autonomous driving operational data to form a data repository for evaluating the quality of locomotive autonomous driving operations. It then integrates ground-based big data intelligent analysis and other methods to develop evaluation rules. This system comprehensively evaluates the safety, rationality, and stability of locomotive autonomous driving system operations. It also compiles statistics for various evaluation indicators, including but not limited to trip times, energy consumption, vehicle control rate, mileage, and station coverage, and displays the statistical and evaluation results. The development of this locomotive autonomous driving evaluation system can completely replace manual data parsing and analysis, generating statistical data reports and displaying them via a web client or dedicated client. This lays the foundation for rapid rollout of subsequent project trials. Upon successful development, the system can be promoted and applied to ground-based railway authorities. The evaluation system provides comprehensive, all-encompassing analysis and assessment of locomotive autonomous driving system operations at both macro and micro levels, providing data support for locomotive autonomous driving system developers and managers. This is the first development of a system specifically designed for locomotive autonomous driving system evaluation and is forward-looking with broad application prospects. The evaluation method includes both online real-time and offline evaluation. It can utilize recorded data for offline evaluation and statistical analysis of field locomotive automated driving operations, and real-time data for real-time evaluation of laboratory locomotive automated driving performance. This system covers virtually all applications of locomotive automated driving and offers significant practical value. The evaluation system comprehensively analyzes locomotive automated driving systems from the perspectives of safety, stability, and rationality, and designs evaluation criteria and effectiveness for each of these key areas. Safety evaluation primarily involves programmable and digitized national railway operating regulations, business rules, and technical regulations, and software-based evaluation of these regulations. This system can identify and assess any operational violations of the locomotive automated driving system, providing guidance for locomotive automated driving system developers and depot operations management units on potential improvements. For stability evaluation, dynamics software is integrated to evaluate whether the lateral and longitudinal impulses exceed standard values using a dynamics model. For rationality evaluation, a standard train operation model (model driver model) is generated using a big data platform and machine learning methods. The operating results of the standard train operation model serve as the basic standard for the evaluation system, and statistical distribution is used as the standard evaluation basis, with a high degree of confidence. The evaluation system also designs a statistical system (method) for the locomotive automatic driving system. The statistical items cover indicators for various scenario controls of the locomotive automatic driving system, such as parking position, interval technical speed, interval operation scale, and operation route map. Evaluation statistical reports for different periods such as single trips, weekly, monthly, and annual evaluation results can be generated. Through the evaluation statistical reports, locomotive automatic driving manufacturers can intuitively experience the application of the locomotive automatic driving system. The application of the locomotive automatic driving system can also be displayed through the web / client.The embodiment of the present invention utilizes a big data platform to construct an autonomous driving system evaluation system, making the autonomous driving system visual, manageable, searchable, and configurable. This is an application of the big data platform in the field of "locomotive autonomous driving," providing a complete locomotive autonomous driving system evaluation method and related algorithms, creating an evaluation system that integrates AI, Big Data, and other technologies. On the one hand, it allows users involved in locomotive autonomous driving to understand and summarize the autonomous driving system from a micro / macro perspective; on the other hand, the evaluation system functions to serve the locomotive autonomous driving system in terms of statistical information and control models. During the operation of the locomotive autonomous driving system, locomotive autonomous driving system developers and operation unit managers can use this evaluation system to fully understand the various functions and performance indicators of the locomotive autonomous driving system, providing guidance for improving the locomotive autonomous driving system's functions and enhancing its own control performance, while also having good promotional significance.

[0038] An evaluation system suitable for locomotive automatic driving of an embodiment of the present invention includes: a locomotive automatic driving system for providing operating data of locomotive automatic driving, a big data platform including a database and a data analysis and evaluation device, and a dynamic simulation system, wherein the big data platform is connected to the locomotive automatic driving system and the dynamic simulation system; the database includes at least a data storage library and an evaluation criteria library; the dynamic simulation system is used to perform dynamic simulation based on the operating data to obtain the coupler force change curve of the locomotive; the evaluation criteria library includes: safety evaluation criteria, stability evaluation rules and rationality evaluation criteria; the data analysis and evaluation device is used to perform safety and rationality evaluation based on the safety evaluation criteria, the rationality evaluation criteria and the operating data, and perform stability evaluation based on the stability evaluation rules and the coupler force change curve to obtain evaluation results; the database is used to store the operating data and the evaluation results, and can perform comprehensive and all-round analysis of the operating conditions of the locomotive automatic driving system in macro and micro aspects, and has broad application prospects.

[0039] For the convenience of description, the above devices are described as being divided into various modules according to their functions. Of course, when implementing the embodiments of the present invention, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0040] Based on the same concept, the embodiment of the present invention also provides an evaluation method applicable to automatic driving of a locomotive. Applicable to the aforementioned evaluation system applicable to automatic driving of a locomotive. Figure 6 As shown in Figure 2, the evaluation methods applicable to automatic driving of locomotives include:

[0041] Step S11: receiving the operation data acquired during the locomotive automatic driving process transmitted by the locomotive automatic driving system.

[0042] In this embodiment of the present invention, the operating data can be actual operating data acquired during the locomotive's automated driving process, or it can be operating data acquired in the laboratory. The former is used to conduct offline evaluation and statistical analysis of the on-site operational status of the locomotive's automated driving using recorded actual operating data. The latter is used to conduct real-time evaluation of the laboratory performance of the locomotive's automated driving using real-time operating data.

[0043] Step S12: Perform dynamic simulation based on the operating data to obtain a coupler force variation curve of the locomotive.

[0044] Optionally, a dynamics simulation system extracts operating parameters relevant to coupler force calculation based on the operating data; dynamics simulation and coupler force calculation are performed based on the operating parameters to obtain a coupler force variation curve for the locomotive. The operating parameters relevant to coupler force calculation include at least: air braking amount, slope data, curve data, tunnel data, train formation data, and operating speed.

[0045] Step S13: Perform safety and rationality evaluation according to the safety evaluation criteria, rationality evaluation criteria in the evaluation criteria library and the operating data, and perform smoothness evaluation according to the smoothness evaluation rules in the evaluation criteria library and the coupler force change curve to obtain evaluation results.

[0046] Data analysis and evaluation software is used to analyze operational data based on a pre-configured data analysis configuration library and store it in a data repository. This data is then programmed and digitized according to railway specifications to generate safety evaluation criteria. Safety evaluation is then conducted based on these criteria and operational data.

[0047] The intelligent algorithm software method and the standard train intelligent software method are applied to obtain a speed operation curve of the standard train operation model, which is used as a rationality evaluation criterion, and then a rationality evaluation is performed based on the rationality evaluation criterion and the operation data. Optionally, the intelligent algorithm software method is applied to generate the standard train operation model based on manual driving and operation data of excellent drivers stored in a database; and a simulation curve of the standard train operation model using the standard train intelligent software method in a real environment is obtained as the speed operation curve of the standard train operation model.

[0048] The dynamic simulation system is used to evaluate the stability based on the coupler force variation curve and stability evaluation rules.

[0049] In an embodiment of the present invention, it also includes: counting the evaluation results of one or more locomotives in different time periods from the time dimension; counting the evaluation results of each locomotive in each railway bureau, line or each section from the position dimension; and counting the precise parking position distribution and interval time distribution of the automatic driving system of a single track from the accuracy probability distribution.

[0050] The foregoing description is of specific embodiments of the present invention. In some cases, the actions or steps described in the embodiments of the present invention may be performed in an order different from that shown in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0051] The method of the above embodiment is applied to the corresponding system in the above embodiment and has the beneficial effects of the corresponding system embodiment, which will not be described in detail here.

[0052] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application is limited to these examples. Within the scope of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the present application as described above, which are not provided in detail for the sake of simplicity.

[0053] This application is intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the embodiments of the present invention. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present invention should be included in the scope of protection of this application.

Claims

1. An evaluation system for automatic driving of a locomotive, characterized in that: The evaluation system includes: a locomotive automatic driving system for providing operation data of the locomotive automatic driving system, a big data platform including a database and a data analysis and evaluation device, and a dynamics simulation system, wherein the big data platform is connected to the locomotive automatic driving system and the dynamics simulation system; the database includes at least a data storage library and an evaluation criteria library; The dynamic simulation system is used to perform dynamic simulation based on the operating data to obtain a coupler force variation curve of the locomotive; The evaluation criteria library includes: safety evaluation criteria, stability evaluation rules, and rationality evaluation criteria; the data analysis and evaluation device is used to perform safety and rationality evaluations based on the safety evaluation criteria, the rationality evaluation criteria, and the operating data, and to perform stability evaluations based on the stability evaluation rules and the coupler force variation curve to obtain evaluation results; the database is used to store the operating data and the evaluation results; the data analysis and evaluation device is further used to: program and digitize the data according to railway specifications to generate the safety evaluation criteria; and apply intelligent algorithm software methods and standard train intelligent software methods to obtain a speed operation curve of a standard train operation model as the rationality evaluation criteria; The data analysis and evaluation device is used to: generate the standard train operation model by applying an intelligent algorithm software method based on manual driving operation data of excellent drivers stored in a database; obtain a simulation curve of the standard train operation model operating in a real environment by applying the standard train intelligent software method as the speed operation curve of the standard train operation model; The method of applying an intelligent algorithm software method to generate the standard train operation model based on the manual driving operation data of excellent drivers stored in the database includes: applying an AI algorithm to correct basic resistance operation parameters and air braking force parameters based on multiple operation speed curves of manual driving operation of excellent drivers stored in the big data platform to construct a standard train operation model; wherein, the standard train operation model includes a basic resistance model and an air braking force model, and the basic resistance model is , the air braking force model is , where A, B, C are weights, and v is the running speed. is the commonly used unit braking force of trains, is the common braking coefficient, To convert the friction coefficient, is the train braking rate, b is the train unit braking force during emergency braking; The method of obtaining the simulation curve of the standard train operation model using the standard train intelligent software method in accordance with the real environment, as the speed operation curve of the standard train operation model, includes: applying the standard train operation model to simulate in accordance with the real environment to obtain a simulation curve, namely the standard train operation curve, and using this as a rationality evaluation criterion for rationality evaluation.

2. The evaluation system according to claim 1, wherein: The database also includes a data analysis configuration library. The data analysis and evaluation device applies a data analysis and evaluation software method to perform data analysis on the operating data according to the preset data analysis configuration library and stores the data in the data storage library.

3. The evaluation system according to claim 1, wherein: The dynamics simulation system is used for: Extracting operating parameters related to coupler force calculation based on the operating data, the operating parameters related to coupler force calculation including at least: air braking amount, slope data, curve data, tunnel data, train formation data, and operating speed; Dynamic simulation and coupler force calculation are performed according to the operating parameters to obtain a coupler force variation curve of the locomotive.

4. The evaluation system according to claim 1, wherein: The big data platform also includes a statistical display module for: Counting the evaluation results of one or more locomotives in different time periods from a time dimension; Counting the evaluation results of each locomotive in each railway bureau, line or section from the location dimension; The precise parking position distribution and interval time distribution of the automatic driving system on a single track are statistically analyzed based on the accuracy probability distribution.

5. The evaluation system according to claim 4, wherein: The statistical display module is also used for: Receive query requests input by users; In response to the query request, the evaluation results of one or more locomotives are statistically analyzed and displayed from the time dimension, location dimension or accuracy probability distribution.

6. The evaluation system according to claim 1, wherein: The evaluation system also includes a transmission system connected to the automatic driving system and the big data platform, and is used to transmit the operating data of the locomotive automatic driving system to the big data platform.

7. An evaluation method for automatic driving of a locomotive, characterized in that: Applied to the evaluation system for automatic driving of a locomotive according to any one of claims 1 to 6, the method comprising: receiving operation data acquired during the locomotive automatic driving process transmitted by the locomotive automatic driving system; Performing dynamic simulation based on the operating data to obtain a coupler force variation curve of the locomotive; Safety and rationality evaluations are performed based on the safety evaluation criteria, rationality evaluation criteria in the evaluation criteria library and the operating data, and stability evaluations are performed based on the stability evaluation rules in the evaluation criteria library and the coupler force change curve to obtain evaluation results.

8. The method according to claim 7, wherein: The method further comprises: Counting the evaluation results of one or more locomotives in different time periods from a time dimension; Counting the evaluation results of each locomotive in each railway bureau, line or section from the location dimension; The precise parking position distribution and interval time distribution of the automatic driving system on a single track are statistically analyzed based on the accuracy probability distribution.

Images