Train operation and maintenance data processing method and device and electronic equipment

Abstract

The application discloses a train operation and maintenance data processing method and device and electronic equipment, and relates to the technical field of train intelligent operation and maintenance. The train operation and maintenance data processing method comprises the following steps: receiving train operation and maintenance data, wherein the train operation and maintenance data is data generated by a train, a station and equipment on the train; classifying the train operation and maintenance data through a preset train standard protocol model; and predicting the classification result by using a preset intelligent analysis model corresponding to the classification result to obtain a target fault type. The application does not need to specially analyze and process each data format and protocol, but uniformly classifies, analyzes and processes the train operation and maintenance data, thereby improving efficiency and accurately analyzing complex data simply. In addition, the train operation and maintenance data processing method can accurately identify the meaning represented by the data and improve operation and maintenance efficiency and accuracy.

Description

Technical Field

[0001] This invention relates to the field of intelligent train operation and maintenance technology, and in particular to a train operation and maintenance data processing method, device and electronic equipment. Background Technology

[0002] In the operation and maintenance of urban rail transit, it is necessary to collect, transmit, store, and analyze various operation and maintenance monitoring data. These data sources are complex, including signaling systems, station control systems, train operation data, and equipment operating status. In practice, this data is collected, stored, and transmitted in different formats, protocols, and granularities. To conduct effective data analysis and decision-making, extensive parsing and integration of this diverse data is required.

[0003] In the prior art, patent CN115884421A discloses a 5G message sending method and sending device. Specifically, it discloses that by classifying the messages to be sent, a classifier is used to divide the messages into signaling messages, VoNR messages, and ordinary data messages, and the priority of these three message types is determined. Then, the messages are sent in order according to their priority, so that high-priority messages can occupy more bandwidth resources and ensure that high-priority messages receive better network speed configuration, thereby meeting the needs of users for different types of networks.

[0004] Patent CN115879891A discloses a subway nighttime control system and method. Specifically, it discloses that the model layer provides candidate control models for different subway scene equipment. Upon receiving a first control command, the system can determine the corresponding target control model from the candidate control models based on the equipment identifier, and send a second control command carrying the equipment identifier and the target control model to the logic layer. The logic layer can then control the subway scene equipment corresponding to the equipment identifier based on the target control model. It can be seen that in this subway nighttime control system, the control process model for different subway scene equipment is modeled into candidate control models and deployed in the model layer. These candidate control models can be triggered by the presentation layer based on the detected first control command, and ultimately executed by the logic layer, thereby achieving automated control of various subway scene equipment. This significantly reduces the daily maintenance workload of subway staff during non-operating hours, thus greatly improving the efficiency of subway nighttime maintenance.

[0005] Patent CN115048374A also discloses an edge data processing method and platform based on a time-series database, and a storage medium. Specifically, it discloses, according to the first aspect of this application, an edge data processing method based on a time-series database, comprising: collecting a first type of monitoring data and a second type of monitoring data of an object to be monitored; uploading the first type of monitoring data to a cloud platform in real time, enabling the cloud platform to display and analyze the first type of monitoring data; and writing the second type of monitoring data into a time-series database intermittently; in response to the arrival of a diagnostic analysis cycle, acquiring the second type of monitoring data related to the object to be monitored within a set time period in the time-series database; performing diagnostic analysis on the object to be monitored based on the acquired second type of monitoring data to obtain diagnostic analysis results; and outputting the diagnostic analysis results through the cloud platform.

[0006] In summary, the current approach of requiring specialized parsing and processing for each data format and protocol is inefficient and struggles to accurately parse complex data; no effective solution has yet been proposed. Summary of the Invention

[0007] Purpose of the invention: To provide a train operation and maintenance data processing method, device, and electronic equipment to solve the above-mentioned problems existing in the prior art.

[0008] Technical solution: A train operation and maintenance data processing method, comprising the following steps: receiving train operation and maintenance data, wherein the train operation and maintenance data is data generated by the train, station and equipment on the train; classifying the train operation and maintenance data through a preset train standard protocol model; and using a preset intelligent analysis model corresponding to the classification result to predict the classification result and obtain the target fault type.

[0009] Preferably, the pre-setting of the intelligent parsing model includes: encoding, serializing, and mapping the train operation and maintenance sample data using an adaptive code table allocation method to complete the training of the machine learning model.

[0010] Preferably, the pre-setting of the intelligent analysis model further includes: receiving model parameters configured by the user in the type-parameter configuration interface of the terminal; wherein, the fault type and the trained machine learning model have a first mapping relationship; and allocating the corresponding model parameters to the corresponding trained machine learning model according to the first mapping relationship to obtain the intelligent analysis model.

[0011] Preferably, the pre-setting of the intelligent parsing model further includes: receiving the operating mechanism rules configured by the user in the type-rule configuration interface of the terminal; wherein the rule type has a second mapping relationship with the trained machine learning model; and allocating the corresponding operating mechanism rules to the corresponding trained machine learning model according to the second mapping relationship.

[0012] Preferably, the machine learning model is a multi-class decision tree model or a convolutional neural network model.

[0013] Preferably, the pre-setting of the train standard protocol model includes: receiving standard protocol signal data configured by the user on the terminal and reading basic train data from the database; constructing a third mapping relationship between the standard protocol signal data and the basic train data, and constructing a fourth mapping relationship between the standard protocol signal data and the preset intelligent parsing model; and generating the train standard protocol model based on the third and fourth mapping relationships.

[0014] As a preferred option, when using a preset intelligent parsing model corresponding to the classification results to predict the classification results, the data batch processing program, the aggregation program, and the scheduled service are started.

[0015] Preferably, after predicting the classification results using a preset intelligent parsing model corresponding to the classification results and obtaining the target fault type, the method further includes: storing the train operation and maintenance data and the target fault type in a structured manner according to different data types.

[0016] To achieve the above objectives, according to another aspect of this application, a train operation and maintenance data processing device is provided.

[0017] The train operation and maintenance data processing device according to this application includes: a receiving module for receiving train operation and maintenance data, wherein the train operation and maintenance data is data generated by trains, stations and equipment on trains; a classification module for classifying the train operation and maintenance data through a preset train standard protocol model; and a parsing module for predicting the classification results using a preset intelligent parsing model corresponding to the classification results to obtain the target fault type.

[0018] To achieve the above objectives, according to another aspect of this application, an electronic device is provided, the electronic device comprising:

[0019] At least one processor; and

[0020] A memory communicatively connected to the at least one processor; wherein,

[0021] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the train operation and maintenance data processing method.

[0022] Beneficial Effects: In this embodiment, a train operation and maintenance data processing method is adopted. This involves receiving train operation and maintenance data, which is generated by the train, station, and equipment on the train; classifying the train operation and maintenance data using a preset train standard protocol model; and predicting the classification results using a preset intelligent analysis model corresponding to the classification results to obtain the target fault type. This achieves the goal of unified classification, analysis, and processing of train operation and maintenance data, thereby improving efficiency and providing a simple and accurate analysis of complex data. It also solves the technical problems of low efficiency and difficulty in accurately analyzing complex data caused by requiring specialized analysis and processing for each data format and protocol. Attached Figure Description

[0023] Figure 1 This is a flowchart illustrating the train operation and maintenance data processing method according to an embodiment of this application;

[0024] Figure 2 This is a flowchart illustrating a train operation and maintenance data processing device according to an embodiment of this application;

[0025] Figure 3 This is a schematic diagram of the structure of a train operation and maintenance data processing method and apparatus according to a preferred embodiment of this application;

[0026] Figure 4 This is a schematic diagram of the structure of a train operation and maintenance data processing method and apparatus according to another preferred embodiment of this application;

[0027] Figure 5 This is a schematic diagram of the structure of a train operation and maintenance data processing method and apparatus according to another preferred embodiment of this application. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] Furthermore, the terms "installation," "setup," "equipped with," "connection," "linking," and "socketing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral structure; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium, or an internal connection between two devices, components, or parts. Those skilled in the art can understand the specific meaning of these terms in this invention based on the specific circumstances.

[0031] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0032] According to embodiments of the present invention, a train operation and maintenance data processing method is provided, such as... Figure 1 As shown, the method includes the following steps S101 to S103:

[0033] Step S101: Receive train operation and maintenance data, wherein the train operation and maintenance data is data generated by the train, station and equipment on the train;

[0034] Trains generate operational and maintenance data during daily operation, primarily from the train itself, stations, and onboard equipment.

[0035] Specifically, train operation and maintenance data can come from multiple sources, including train signaling systems, station control systems, train operation data, onboard equipment, and train subsystems. These data are generally collected, stored, and transmitted in different formats, protocols, and granularities.

[0036] In this embodiment, a server or local mainframe computer may periodically or manually receive train operation and maintenance data for subsequent classification, analysis, and processing. The receiving method can be a wireless network, wired network, etc., and is not limited thereto; however, given that the train is in motion for extended periods, a 5G wireless network is preferred for data reception.

[0037] It is important to understand that different systems and equipment on a train use different protocols, and the protocol signals often describe different systems and equipment differently. Therefore, these protocols can be used as identification tags for data association.

[0038] Step S102: Classify the train operation and maintenance data using a preset train standard protocol model;

[0039] The pre-defined train standard protocol model can divide train operation and maintenance data into multiple categories of datasets according to standard protocols, with each dataset corresponding to a standard protocol. At the same time, the pre-defined train standard protocol model also describes different systems and equipment differently through protocol signals, which is linked to the corresponding intelligent parsing model for subsequent prediction. In this way, the protocol parsing rules can be automatically adjusted based on the model.

[0040] It is known that datasets with the same protocol indicate that they can be parsed using the same parsing method; thus, the datasets corresponding to that category can be parsed through the associated intelligent parsing model.

[0041] It should be understood that the data in each dataset consists of different train models and trainsets using the same protocol (or equipment).

[0042] It's important to understand that other types of datasets are associated and parsed in the same way, which will not be elaborated upon here.

[0043] Step S103: Use a preset intelligent analysis model corresponding to the classification result to predict the classification result and obtain the target fault type.

[0044] The classification result is predicted by associating it with the intelligent parsing model corresponding to the dataset of a certain category. Since the intelligent parsing model is pre-set, it has the function of predicting the type of fault.

[0045] Specifically, a machine model, known as the intelligent analysis model, was trained for each type of fault.

[0046] Preferably, an adaptive code table is used to encode, serialize, and map the train operation and maintenance sample data to complete the training of the machine learning model.

[0047] Furthermore, the machine learning model is a multi-class decision tree model or a convolutional neural network model.

[0048] The trained model specifies the initial parameters, rules, and data types required for prediction. Thus, the intelligent parsing model can extract the data required for parsing from a dataset of a certain category based on the data type, calculate the original parameter scores, make a threshold judgment based on the original operating mechanism rules, and finally determine the target fault type based on the threshold judgment result.

[0049] It is important to understand that the target fault type can be the fault usage rate, current fault, historical fault, vehicle life prediction, fault warning, etc.

[0050] It is also necessary to understand how the intelligent parsing model decodes and restores the data after encoding and deserialization.

[0051] In this embodiment, the intelligent parsing model supports online parsing and offline analysis of operation and maintenance data, which can meet the needs of real-time operation and maintenance and historical data analysis.

[0052] In this embodiment, the training and updating of the intelligent parsing model improves the parsing accuracy and stability by continuously learning and optimizing the intelligent parsing algorithm.

[0053] In some embodiments, a unified protocol standard can also be adopted to make data exchange between devices more convenient and efficient, while also protecting data security and privacy.

[0054] The train operation and maintenance data processing method of this application eliminates the need for specialized parsing and processing for each data format and protocol. Instead, it uniformly classifies, parses, and processes train operation and maintenance data, thereby improving efficiency and simplifying the accurate parsing of complex data.

[0055] In addition, the train operation and maintenance data processing method of this application can accurately identify the meaning of the data, thereby improving operation and maintenance efficiency and accuracy.

[0056] According to an embodiment of the present invention, preferably, the pre-setting of the intelligent parsing model further includes:

[0057] Receive model parameters configured by the user in the type-parameter configuration interface of the terminal; wherein, the fault type has a first mapping relationship with the trained machine learning model;

[0058] Based on the first mapping relationship, the corresponding model parameters are assigned to the corresponding trained machine learning model to obtain the intelligent parsing model.

[0059] In this embodiment, the user is an administrator. The administrator first accesses the type-parameter configuration interface on the terminal, and then sets the parameters by inputting the corresponding information, i.e., the original parameters or modified model parameters, into the type-parameter configuration interface on the terminal according to the actual situation. The modified model parameters are the original parameters, i.e., the original parameters are updated with the modified model parameters. For example, a table of the original parameters or modified model parameters is given below:

[0060]

[0061] It should be noted that the intelligent parsing model in this embodiment has default original parameters, but it is not excluded that the original parameters can also be set in the manner described above.

[0062] For example, as can be seen from the table above, the data types of the dataset required for the calculations involved in the intelligent analysis model for fault type utilization are time range and full-score mileage.

[0063] For example, as can be seen from the table above, the data types of the datasets required for the calculations involved in the intelligent analysis model for fault types of historical faults are severe, event, moderate, and minor.

[0064] Clearly, the above methods allow for the allocation of weight values ​​(model parameters) as needed to adapt to different situations; this improves configuration flexibility, eliminates the need for reprogramming to modify and adjust parameters, saves costs, and reduces the workload of data development.

[0065] According to embodiments of the present invention, preferably, such as Figure 3 As shown, the pre-settings of the intelligent parsing model also include:

[0066] It receives the operating mechanism rules configured by the user in the type-rule configuration interface of the terminal; wherein, the rule type has a second mapping relationship with the trained machine learning model;

[0067] Based on the second mapping relationship, the corresponding operating mechanism rules are assigned to the corresponding trained machine learning models.

[0068] In this embodiment, the user is an administrator. The administrator first accesses the type-rule configuration interface on the terminal, and then sets the relevant information by selecting the original operating mechanism rule or the modified operating mechanism rule (multiple rule templates are provided for selection) in the type-rule configuration interface on the terminal according to the actual situation. The modified operating mechanism rule is to modify the original operating mechanism rule, that is, to update the original operating mechanism rule with the modified operating mechanism rule.

[0069] It is important to understand that the intelligent parsing model in this embodiment has default original operating mechanism rules, but it is not excluded that the original operating mechanism rules can also be set in the manner described above.

[0070] Clearly, the above methods enable the use of a visual functional block diagram language to edit train operation mechanism rules. These rules can be set or modified as needed to adapt to different situations, improving configuration flexibility and eliminating the need for reprogramming to adjust operation mechanism rules, thus saving costs and reducing the workload of data development.

[0071] It is also important to understand that by configuring the operating mechanism rules, fault warning functions for the whole vehicle, system and components can be realized; furthermore, by using a custom rule tree diagram, the conversion between analog and digital quantities can be realized, any non-zero analog quantity can be equivalent to the digital quantity 1, otherwise it can be equivalent to the digital quantity 0; thus, fault warning can be realized.

[0072] According to an embodiment of the present invention, preferably, the pre-setting of the train standard protocol model includes:

[0073] It receives standard protocol signal data configured by the user on the terminal and reads basic train data from the database.

[0074] Construct a third mapping relationship between the standard protocol signal data and the train basic data, and construct a fourth mapping relationship between the standard protocol signal data and the preset intelligent parsing model;

[0075] The train standard protocol model is generated based on the third association relationship and the fourth mapping relationship.

[0076] In this embodiment, the user is an administrator. The administrator first accesses the standard protocol configuration interface on the terminal, and then inputs the corresponding information, namely standard protocol signal data or added / reduced standard protocol signals, into the standard protocol configuration interface according to the actual situation; adding / reducing standard protocol signals involves increasing or decreasing the standard protocol signal dataset. An example is provided in the table below, showing the configured standard protocol signal data:

[0077]

[0078]

[0079] For example, as can be seen from the table above, referring to the signal description can identify the train's subsystems, equipment on the train, etc., and thus the association between standard protocol signal data and the preset intelligent analysis model can be constructed (the fourth mapping relationship). Referring to the signal carriage can identify a series of related data such as the line, train, type, formation, fault dictionary, etc., and thus the association between standard protocol signal data and basic train data can be constructed (the third mapping relationship).

[0080] Thus, the train standard protocol model can be determined based on the third and fourth mapping relationships; this model can be used for the classification of subsequent train operation and maintenance data.

[0081] Clearly, the above methods allow for the addition or removal of standard protocol signal data to adapt to different situations; this improves configuration flexibility and eliminates the need for reprogramming to set, add, or remove standard protocol signal data, saving costs and reducing the workload of data development.

[0082] According to embodiments of the present invention, preferably, such as Figure 4 and 5 As shown, when using a preset intelligent parsing model corresponding to the classification result to predict the classification result, the data batch processing program, the aggregation program, and the scheduled service are started.

[0083] In this embodiment, a data batch processing program and an aggregation program are initiated. Data is processed in batches, using different pipelines and threshold conditions to create various data types as needed. Furthermore, batch processing is enabled, and storage types are set based on the data's symbol type. The system dynamically determines whether the type and threshold conditions match, temporarily storing any intermediate differences. By integrating and analyzing the data and storing it differently according to different data types, the efficiency of data storage is improved.

[0084] According to an embodiment of the present invention, preferably, after predicting the classification result using a preset intelligent analysis model corresponding to the classification result to obtain the target fault type, the method further includes:

[0085] The train operation and maintenance data and the target fault types are stored in a structured manner according to different data types.

[0086] After obtaining the target fault type, the server can further structure and store the data according to different format requirements, such as subsystems, time, train number, fault type, etc., based on the page display and functional requirements. This allows users to easily retrieve the relevant data through the interface by searching according to different data types.

[0087] like Figure 2 As shown, one embodiment of this application also provides a train operation and maintenance data processing device, including:

[0088] The receiving module 10 is used to receive train operation and maintenance data, wherein the train operation and maintenance data is data generated by the train, the station and the equipment on the train;

[0089] Trains generate operational and maintenance data during daily operation, primarily from the train itself, stations, and onboard equipment.

[0090] Specifically, train operation and maintenance data can come from multiple sources, including train signaling systems, station control systems, train operation data, onboard equipment, and train subsystems. These data are generally collected, stored, and transmitted in different formats, protocols, and granularities.

[0091] In this embodiment, a server or local mainframe computer may periodically or manually receive train operation and maintenance data for subsequent classification, analysis, and processing. The receiving method can be a wireless network, wired network, etc., and is not limited thereto; however, given that the train is in motion for extended periods, a 5G wireless network is preferred for data reception.

[0092] It is important to understand that different systems and equipment on a train use different protocols, and the protocol signals often describe different systems and equipment differently. Therefore, these protocols can be used as identification tags for data association.

[0093] The classification module 20 is used to classify the train operation and maintenance data according to a preset train standard protocol model;

[0094] The pre-defined train standard protocol model can divide train operation and maintenance data into multiple categories of datasets according to standard protocols, with each dataset corresponding to a standard protocol. At the same time, the pre-defined train standard protocol model also describes different systems and equipment differently through protocol signals, which is linked to the corresponding intelligent parsing model for subsequent prediction. In this way, the protocol parsing rules can be automatically adjusted based on the model.

[0095] It is known that datasets with the same protocol indicate that they can be parsed using the same parsing method; thus, the datasets corresponding to that category can be parsed through the associated intelligent parsing model.

[0096] It should be understood that the data in each dataset consists of different train models and trainsets using the same protocol (or equipment).

[0097] It's important to understand that other types of datasets are associated and parsed in the same way, which will not be elaborated upon here.

[0098] The parsing module 30 is used to predict the classification results using a preset intelligent parsing model corresponding to the classification results, so as to obtain the target fault type.

[0099] The classification result is predicted by associating it with the intelligent parsing model corresponding to the dataset of a certain category. Since the intelligent parsing model is pre-set, it has the function of predicting the type of fault.

[0100] Specifically, a machine model, known as the intelligent analysis model, was trained for each type of fault.

[0101] Preferably, an adaptive code table is used to encode, serialize, and map the train operation and maintenance sample data to complete the training of the machine learning model.

[0102] Furthermore, the machine learning model is a multi-class decision tree model or a convolutional neural network model.

[0103] The trained model specifies the initial parameters, rules, and data types required for prediction. Thus, the intelligent parsing model can extract the data required for parsing from a dataset of a certain category based on the data type, calculate the original parameter scores, make a threshold judgment based on the original operating mechanism rules, and finally determine the target fault type based on the threshold judgment result.

[0104] It is important to understand that the target fault type can be the fault usage rate, current fault, historical fault, vehicle life prediction, fault warning, etc.

[0105] It is also necessary to understand how the intelligent parsing model decodes and restores the data after encoding and deserialization.

[0106] In this embodiment, the intelligent parsing model supports online parsing and offline analysis of operation and maintenance data, which can meet the needs of real-time operation and maintenance and historical data analysis.

[0107] In this embodiment, the training and updating of the intelligent parsing model improves the parsing accuracy and stability by continuously learning and optimizing the intelligent parsing algorithm.

[0108] In some embodiments, a unified protocol standard can also be adopted to make data exchange between devices more convenient and efficient, while also protecting data security and privacy.

[0109] The train operation and maintenance data processing method of this application eliminates the need for specialized parsing and processing for each data format and protocol. Instead, it uniformly classifies, parses, and processes train operation and maintenance data, thereby improving efficiency and simplifying the accurate parsing of complex data.

[0110] In addition, the train operation and maintenance data processing method of this application can accurately identify the meaning of the data, thereby improving operation and maintenance efficiency and accuracy.

[0111] According to an embodiment of the present invention, preferably, the pre-setting of the intelligent parsing model further includes:

[0112] Receive model parameters configured by the user in the type-parameter configuration interface of the terminal; wherein, the fault type has a first mapping relationship with the trained machine learning model;

[0113] Based on the first mapping relationship, the corresponding model parameters are assigned to the corresponding trained machine learning model to obtain the intelligent parsing model.

[0114] In this embodiment, the user is an administrator. The administrator first accesses the type-parameter configuration interface on the terminal, and then sets the parameters by inputting the corresponding information, i.e., the original parameters or modified model parameters, into the type-parameter configuration interface on the terminal according to the actual situation. The modified model parameters are the original parameters, i.e., the original parameters are updated with the modified model parameters. For example, a table of the original parameters or modified model parameters is given below:

[0115]

[0116] It should be noted that the intelligent parsing model in this embodiment has default original parameters, but it is not excluded that the original parameters can also be set in the manner described above.

[0117] For example, as can be seen from the table above, the data types of the dataset required for the calculations involved in the intelligent analysis model for fault type utilization are time range and full-score mileage.

[0118] For example, as can be seen from the table above, the data types of the datasets required for the calculations involved in the intelligent analysis model for fault types of historical faults are severe, event, moderate, and minor.

[0119] Clearly, the above methods allow for the allocation of weight values ​​(model parameters) as needed to adapt to different situations; this improves configuration flexibility, eliminates the need for reprogramming to modify and adjust parameters, saves costs, and reduces the workload of data development.

[0120] According to embodiments of the present invention, preferably, such as Figure 3 As shown, the pre-settings of the intelligent parsing model also include:

[0121] It receives the operating mechanism rules configured by the user in the type-rule configuration interface of the terminal; wherein, the rule type has a second mapping relationship with the trained machine learning model;

[0122] Based on the second mapping relationship, the corresponding operating mechanism rules are assigned to the corresponding trained machine learning models.

[0123] In this embodiment, the user is an administrator. The administrator first accesses the type-rule configuration interface on the terminal, and then sets the relevant information by selecting the original operating mechanism rule or the modified operating mechanism rule (multiple rule templates are provided for selection) in the type-rule configuration interface on the terminal according to the actual situation. The modified operating mechanism rule is to modify the original operating mechanism rule, that is, to update the original operating mechanism rule with the modified operating mechanism rule.

[0124] It is important to understand that the intelligent parsing model in this embodiment has default original operating mechanism rules, but it is not excluded that the original operating mechanism rules can also be set in the manner described above.

[0125] Clearly, the above methods enable the use of a visual functional block diagram language to edit train operation mechanism rules. These rules can be set or modified as needed to adapt to different situations, improving configuration flexibility and eliminating the need for reprogramming to adjust operation mechanism rules, thus saving costs and reducing the workload of data development.

[0126] It is also important to understand that by configuring the operating mechanism rules, fault warning functions for the whole vehicle, system and components can be realized; furthermore, by using a custom rule tree diagram, the conversion between analog and digital quantities can be realized, any non-zero analog quantity can be equivalent to the digital quantity 1, otherwise it can be equivalent to the digital quantity 0; thus, fault warning can be realized.

[0127] According to an embodiment of the present invention, preferably, the pre-setting of the train standard protocol model includes:

[0128] It receives standard protocol signal data configured by the user on the terminal and reads basic train data from the database.

[0129] Construct a third mapping relationship between the standard protocol signal data and the train basic data, and construct a fourth mapping relationship between the standard protocol signal data and the preset intelligent parsing model;

[0130] The train standard protocol model is generated based on the third association relationship and the fourth mapping relationship.

[0131] In this embodiment, the user is an administrator. The administrator first accesses the standard protocol configuration interface on the terminal, and then inputs the corresponding information, namely standard protocol signal data or added / reduced standard protocol signals, into the standard protocol configuration interface according to the actual situation; adding / reducing standard protocol signals involves increasing or decreasing the standard protocol signal dataset. An example is provided in the table below, showing the configured standard protocol signal data:

[0132]

[0133]

[0134] For example, as can be seen from the table above, referring to the signal description can identify the train's subsystems, equipment on the train, etc., and thus the association between standard protocol signal data and the preset intelligent analysis model can be constructed (the fourth mapping relationship). Referring to the signal carriage can identify a series of related data such as the line, train, type, formation, fault dictionary, etc., and thus the association between standard protocol signal data and basic train data can be constructed (the third mapping relationship).

[0135] Thus, the train standard protocol model can be determined based on the third and fourth mapping relationships; this model can be used for the classification of subsequent train operation and maintenance data.

[0136] Clearly, the above methods allow for the addition or removal of standard protocol signal data to adapt to different situations; this improves configuration flexibility and eliminates the need for reprogramming to set, add, or remove standard protocol signal data, saving costs and reducing the workload of data development.

[0137] According to embodiments of the present invention, preferably, such as Figure 4 and 5 As shown, when using a preset intelligent parsing model corresponding to the classification result to predict the classification result, the data batch processing program, the aggregation program, and the scheduled service are started.

[0138] In this embodiment, a data batch processing program and an aggregation program are initiated. Data is processed in batches, using different pipelines and threshold conditions to create various data types as needed. Furthermore, batch processing is enabled, and storage types are set based on the data's symbol type. The system dynamically determines whether the type and threshold conditions match, temporarily storing any intermediate differences. By integrating and analyzing the data and storing it differently according to different data types, the efficiency of data storage is improved.

[0139] According to an embodiment of the present invention, preferably, after predicting the classification result using a preset intelligent analysis model corresponding to the classification result to obtain the target fault type, the method further includes:

[0140] The train operation and maintenance data and the target fault types are stored in a structured manner according to different data types.

[0141] After obtaining the target fault type, the server can further structure and store the data according to different format requirements, such as subsystems, time, train number, fault type, etc., based on the page display and functional requirements. This allows users to easily retrieve the relevant data through the interface by searching according to different data types.

[0142] One embodiment of this application also provides an electronic device, including:

[0143] At least one processor; and

[0144] A memory communicatively connected to the at least one processor; wherein,

[0145] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the train operation and maintenance data processing method.

[0146] If the modules integrated into the terminal device are implemented as software functional units and sold or used as independent products, they can be stored in the memory of an electronic device. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a memory, and when the computer program is executed by a processor, it can implement the above-mentioned steps of displaying memory power consumption optimization and processing memory power consumption optimization.

[0147] Computer programs include computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. Computer-readable media can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in computer-readable media can be appropriately added to or subtracted according to the requirements of legislation and patent practice in a jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0148] Obviously, those skilled in the art will understand that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device, or fabricating them separately as individual integrated circuit modules, or fabricating multiple modules or steps as a single integrated circuit module. Thus, the present invention is not limited to any particular hardware and software combination.

[0149] The preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the present invention is not limited to the specific details of the above embodiments. Within the scope of the technical concept of the present invention, various equivalent transformations can be made to the technical solutions of the present invention, and all such equivalent transformations fall within the protection scope of the present invention.

Claims

1. A method for processing train operation and maintenance data, characterized in that, The steps include the following: Receive train operation and maintenance data, wherein the train operation and maintenance data is data generated by the train, the station and the equipment on the train; The train operation and maintenance data are classified using a pre-defined train standard protocol model; The pre-settings of the train standard protocol model include: It receives standard protocol signal data configured by the user on the terminal and reads basic train data from the database. Construct a third mapping relationship between the standard protocol signal data and the train basic data, and construct a fourth mapping relationship between the standard protocol signal data and the preset intelligent parsing model; A train standard protocol model is generated based on the third and fourth mapping relationships; The target fault type is obtained by using a pre-set intelligent analysis model corresponding to the classification results to predict the classification results; The pre-settings of the intelligent parsing model include: The train operation and maintenance sample data is encoded, serialized, and mapped using an adaptive code table allocation method to complete the training of the machine learning model. The pre-settings for the intelligent parsing model also include: Receive model parameters configured by the user in the type-parameter configuration interface of the terminal; wherein, the fault type has a first mapping relationship with the trained machine learning model; Based on the first mapping relationship, the corresponding model parameters are assigned to the corresponding trained machine learning model to obtain the intelligent parsing model; The pre-settings for the intelligent parsing model also include: It receives the operating mechanism rules configured by the user in the type-rule configuration interface of the terminal; wherein, the rule type has a second mapping relationship with the trained machine learning model; Based on the second mapping relationship, the corresponding operating mechanism rules are assigned to the corresponding trained machine learning models.

2. The method according to claim 1, characterized in that, The machine learning model is a multi-class decision tree model or a convolutional neural network model.

3. The method according to claim 1, characterized in that, When using a preset intelligent parsing model corresponding to the classification results to predict the classification results, the data batch processing program, the aggregation program, and the scheduled service are started.

4. The method according to claim 1, characterized in that, After predicting the classification results using a pre-defined intelligent analysis model corresponding to the classification results and obtaining the target fault type, the following steps are also included: The train operation and maintenance data and the target fault types are stored in a structured manner according to different data types.

5. A train operation and maintenance data processing device, characterized in that, include: A receiving module is used to receive train operation and maintenance data, wherein the train operation and maintenance data is data generated by the train, the station and the equipment on the train; The classification module is used to classify the train operation and maintenance data according to a preset train standard protocol model; The pre-settings of the train standard protocol model include: It receives standard protocol signal data configured by the user on the terminal and reads basic train data from the database. Construct a third mapping relationship between the standard protocol signal data and the train basic data, and construct a fourth mapping relationship between the standard protocol signal data and the preset intelligent parsing model; A train standard protocol model is generated based on the third and fourth mapping relationships; The parsing module is used to predict the classification results using a preset intelligent parsing model corresponding to the classification results, and to obtain the target fault type. The pre-settings of the intelligent parsing model include: The train operation and maintenance sample data is encoded, serialized, and mapped using an adaptive code table allocation method to complete the training of the machine learning model. The pre-settings for the intelligent parsing model also include: Receive model parameters configured by the user in the type-parameter configuration interface of the terminal; wherein, the fault type has a first mapping relationship with the trained machine learning model; Based on the first mapping relationship, the corresponding model parameters are assigned to the corresponding trained machine learning model to obtain the intelligent parsing model; The pre-settings for the intelligent parsing model also include: It receives the operating mechanism rules configured by the user in the type-rule configuration interface of the terminal; wherein, the rule type has a second mapping relationship with the trained machine learning model; Based on the second mapping relationship, the corresponding operating mechanism rules are assigned to the corresponding trained machine learning models.

6. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the train operation and maintenance data processing method according to any one of claims 1-4.

Images