A method for monitoring the running status of a high-speed train

Abstract

The present invention provides a method for monitoring the running status of a high-speed train, comprising: responding to a status monitoring instruction, receiving basic vehicle body attributes uploaded by a management end, and acquiring a standard running model; receiving vibration-temperature combination data acquired by each sensing sensor, and acquiring characteristic diagnosis data of different carriages based on the vibration-temperature combination data; obtaining a customized diagnosis model based on the characteristic diagnosis data of different carriages, comparing the standard running model with the customized diagnosis model, and acquiring a first running deviation data set; acquiring dynamic riding data of different carriages, determining characteristic diagnosis data corresponding to an associated carriage based on the dynamic riding data, and obtaining a second running deviation data set by performing correlation comparison based on the characteristic diagnosis data corresponding to the associated carriage; calling a preset diagnosis strategy based on the first running deviation data set and the second running deviation data set, acquiring a running diagnosis result, generating warning information according to the running diagnosis result, and sending the running diagnosis result and the warning information to a management end.

Description

Technical Field

[0001] The invention relates to the field of transportation technology, and in particular to a method for monitoring the running status of a high-speed train. Background Art

[0002] With the rapid development of modern railway transportation, high-speed trains have become an important part of modern urbanization. The safety of high-speed trains not only affects the life safety of passengers and train operators, but also directly affects the stability of urban transportation and the development of the economy and society. Therefore, it is necessary to ensure the safe operation of high-speed trains.

[0003] Traditional methods to ensure the safe operation of high-speed trains usually rely on manual inspections and regular maintenance, which is time-consuming, inefficient, and can only be performed when the train is stopped. It is impossible to monitor the operating status of the train in real time. Trains that have been maintained may also have various faults and abnormal conditions during operation, such as severe wheel wear, overheating of bearings, etc., leading to train operation accidents and affecting the safety of railway transportation.

[0004] Therefore, how to conduct real-time monitoring and diagnosis of high-speed trains and provide early warning of potential failures has become an urgent problem to be solved. Summary of the invention

[0005] The present invention provides a method for monitoring the running status of a high-speed train, which can monitor and diagnose the high-speed train in real time and give early warning of potential faults.

[0006] According to a first aspect of the present invention, a method for monitoring the operation status of a high-speed train is provided, comprising: responding to a status monitoring instruction, receiving basic vehicle body attributes uploaded by a management terminal, acquiring a standard operation model based on the basic vehicle body attributes, receiving vibration-temperature combination data acquired by each sensing sensor, calling a preset screening strategy based on the vibration-temperature combination data, removing error data from the vibration-temperature combination data according to the preset screening strategy, acquiring characteristic diagnosis data of different carriages, updating the standard operation model based on the characteristic diagnosis data of different carriages to obtain a customized diagnosis model, comparing the standard operation model with the customized diagnosis model, acquiring a first operation deviation data set, acquiring dynamic riding data of different carriages, determining characteristic diagnosis data corresponding to an associated carriage based on the dynamic riding data, performing correlation comparison based on the characteristic diagnosis data corresponding to the associated carriage to obtain a second operation deviation data set, calling a preset diagnosis strategy based on the first operation deviation data set and the second operation deviation data set, acquiring an operation diagnosis result, generating warning information based on the operation diagnosis result, and sending the operation diagnosis result and the warning information to the management terminal.

[0007] Optionally, in response to a status monitoring instruction, basic vehicle body attributes uploaded by a management terminal are received, and a standard operation model is obtained based on the basic vehicle body attributes, including: in response to the status monitoring instruction, a property editing interface is called, and basic vehicle body attributes of a high-speed train are obtained based on the property editing interface; a basic vehicle body model and basic configuration data are retrieved based on the basic vehicle body attributes, wherein the basic configuration data includes target monitoring component characteristics; a standard operation record table is called, and data is extracted from the standard operation record table according to the target monitoring component characteristics to obtain standard operation data corresponding to each target monitoring component; the basic vehicle body model is updated based on the standard operation data to obtain a standard operation model.

[0008] Optionally, vibration-temperature combination data acquired by each perception sensor is received, a preset screening strategy is called based on the vibration-temperature combination data, error data is removed from the vibration-temperature combination data according to the preset screening strategy, and characteristic diagnostic data of different compartments is obtained, including: receiving the vibration-temperature combination data acquired by each perception sensor according to a preset monitoring time, identifying the vibration-temperature combination data, obtaining diagnostic correlation data, constructing a status monitoring mapping table according to the diagnostic correlation data, obtaining a monitoring type and one or more vibration-temperature combination data corresponding to a current target monitoring component based on the status monitoring mapping table, calling the corresponding preset screening strategy according to the monitoring type, removing error data from one or more vibration-temperature combination data based on the preset screening strategy, obtaining characteristic diagnostic data corresponding to the current target monitoring component, and repeating the above steps of obtaining characteristic diagnostic data until the characteristic diagnostic data corresponding to all target monitoring components in different compartments are respectively obtained.

[0009] Optionally, the vibration-temperature combination data includes bearing vibration-temperature combination data, and the corresponding preset screening strategy is called according to the monitoring type, and error data is removed from one or more vibration-temperature combination data based on the preset screening strategy to obtain characteristic diagnostic data corresponding to the current target monitoring component, including: when the monitoring type is bearing status monitoring, calling the first preset screening strategy, the first preset screening strategy includes a bearing vibration data screening strategy and a bearing temperature data screening strategy, calling a preset identification rule to identify the bearing vibration-temperature combination data, obtaining bearing vibration data and bearing temperature data, removing errors from the bearing vibration data according to the bearing vibration data screening strategy to obtain bearing vibration characteristic data, removing errors from the bearing temperature data according to the bearing temperature data screening strategy to obtain bearing temperature characteristic data, combining the bearing vibration characteristic data and the bearing temperature characteristic data to obtain bearing characteristic diagnostic data.

[0010] Optionally, the vibration-temperature combination data also includes wheel vibration-temperature combination data, and the corresponding preset screening strategy is called according to the monitoring type, and error data is removed from one or more vibration-temperature combination data based on the preset screening strategy to obtain characteristic diagnostic data corresponding to the current target monitoring component, and also includes: when the monitoring type is wheel status monitoring, calling a second preset screening strategy, the second preset screening strategy includes a wheel vibration data screening strategy and a wheel temperature data screening strategy, calling the preset identification rule to identify the wheel vibration-temperature combination data, obtaining wheel vibration data and wheel temperature data, removing errors from the wheel vibration data according to the wheel vibration data screening strategy to obtain wheel vibration characteristic data, removing errors from the wheel temperature data according to the wheel temperature data screening strategy to obtain wheel temperature characteristic data, combining the wheel vibration characteristic data and the wheel temperature characteristic data to obtain wheel characteristic diagnostic data.

[0011] Optionally, the vibration-temperature combination data also includes rail vibration-temperature combination data, and the corresponding preset screening strategy is called according to the monitoring type, and error data is removed from one or more vibration-temperature combination data based on the preset screening strategy to obtain characteristic diagnostic data corresponding to the current target monitoring component, and also includes: when the monitoring type is rail status monitoring, calling a third preset screening strategy, the third preset screening strategy includes a rail vibration data screening strategy and a rail temperature data screening strategy, calling the preset identification rule to identify the rail vibration-temperature combination data, obtaining rail vibration data and rail temperature data, removing errors from the rail vibration data according to the rail vibration data screening strategy to obtain rail vibration characteristic data, removing errors from the rail temperature data according to the rail temperature data screening strategy to obtain rail temperature characteristic data, combining the rail vibration characteristic data and the rail temperature characteristic data to obtain rail characteristic diagnostic data.

[0012] Optionally, the standard operation model is updated based on the characteristic diagnostic data of different carriages to obtain a customized diagnostic model, and the standard operation model is compared with the customized diagnostic model to obtain first operation deviation data, including: combining the bearing characteristic diagnostic data, the wheel characteristic diagnostic data and the rail characteristic diagnostic data of different carriages to obtain a characteristic diagnostic data set, extracting the corresponding target synchronous operation data in the standard operation model based on the characteristic diagnostic data set, generating a target update data set according to the multiple target synchronous operation data, and updating each target synchronous operation data of the standard operation model one by one based on each characteristic diagnostic data of the characteristic diagnostic data set to obtain a customized diagnostic model, and comparing the customized diagnostic model with the operation status data corresponding to each target monitoring component in the standard operation model to obtain a first operation deviation data set.

[0013] Optionally, the acquisition of dynamic occupancy data of different carriages, determining characteristic diagnostic data corresponding to associated carriages based on the dynamic occupancy data, and performing correlation comparison based on the characteristic diagnostic data corresponding to the associated carriages to obtain a second operation deviation data set includes: locating the current operating section of the train based on the current operating position of the train, each model of train has a preset current operating section at different current operating positions, determining the passenger information of each carriage in the current operating section based on the ticket sales information corresponding to the train, collecting cargo information of the corresponding carriage based on an image acquisition device preset by the train, obtaining dynamic occupancy data of the corresponding carriage based on the passenger information and cargo information of each carriage, determining the characteristic diagnostic data corresponding to the associated carriage based on the dynamic occupancy data, and obtaining a differentiated interval of the characteristic diagnostic data based on the difference between the dynamic occupancy data, and determining the associated carriage that does not meet the requirements based on the differentiated interval to obtain a second operation deviation data set.

[0014] Optionally, the method of determining the passenger information of each carriage in the current travel section based on the ticket sales information corresponding to the train, collecting the cargo information of the corresponding carriage based on the image acquisition device preset by the train, and obtaining the dynamic riding data of the corresponding carriage based on the passenger information and cargo information of each carriage includes: obtaining the number and age group of the passenger information of each carriage in each current travel section, adding different first mass coefficients for each passenger based on the age group, and different age groups have different first mass coefficients, obtaining the luggage rack identification area of ​​each carriage, performing segmented identification processing on the luggage rack identification area based on the seat number in the carriage to obtain the corresponding luggage interval segment, performing horizontal coordinate processing on the image of each luggage interval segment, obtaining each pixel point different from the preset pixel value of the luggage interval segment to obtain a luggage identification pixel point, obtaining a second mass coefficient based on the horizontal coordinate ratio of the luggage identification pixel point to the total number of pixel points of the corresponding luggage interval segment, and each horizontal coordinate ratio has a preset second mass coefficient, and calculating the dynamic riding data based on the number of passenger information, the first mass coefficient, the number of luggage interval segments, and the second mass coefficient.

[0015] Optionally, the obtaining of dynamic riding data based on the number of passenger information, the first quality coefficient, the number of luggage sections, and the second quality coefficient includes:

[0016] The first dynamic sub-information is obtained by calculating based on the number of passenger information and the first quality coefficient, and the second dynamic sub-information is obtained by calculating based on the number of baggage sections and the second quality coefficient;

[0017] The first dynamic sub-information and the second dynamic sub-information are added together to obtain dynamic riding data, and the dynamic riding data is calculated by the following formula:

[0018] in, For dynamic riding data, is the number of passengers on board, is the passenger weight coefficient, For the The first quality coefficient of the passenger information, is the upper limit of the number of passengers on board, is the weight value of the first quality coefficient, is the normalized value of passengers, is the number of baggage sections with bags, is the weight coefficient of the baggage interval, For the The second mass coefficient in the baggage section, is the upper limit of the number of baggage sections, is the weight coefficient of the baggage interval, is the baggage normalization value.

[0019] Optionally, the method of determining characteristic diagnostic data corresponding to an associated car based on the dynamic riding data, and obtaining a differentiated interval of characteristic diagnostic data based on the difference between the dynamic riding data, and determining the output display of an associated car that does not meet the requirements based on the differentiated interval, includes: sorting all cars in descending order based on the dynamic riding data to obtain a car descending sequence, traversing the dynamic riding data of each car in the car descending sequence in turn and determining the closest dynamic riding data, using the dynamic riding data of the traversed car and the closest dynamic riding data as the characteristic diagnostic data corresponding to the associated car, calculating the difference in the dynamic riding data to obtain a differentiated riding value, obtaining a standard data difference between the characteristic diagnostic data corresponding to the associated cars based on the differentiated riding value, calculating the diagnostic data difference of the information feature data of each dimension, if the diagnostic data difference is less than or equal to the standard data difference, the associated car meets the requirements, and if the diagnostic data difference is greater than the standard data difference, the associated car does not meet the requirements.

[0020] Optionally, the calculating of the difference in the dynamic riding data to obtain a differentiated riding value, and obtaining a standard data difference between characteristic diagnostic data corresponding to the associated carriages based on the differentiated riding value, comprises:

[0021] Acquire information feature data of each dimension in each feature diagnostic data and a corresponding feature weight, wherein the information feature data at least includes rail vibration data and rail temperature data;

[0022] The standard data difference is calculated based on the differentiated occupancy values ​​of the associated carriages and the feature weights of the information feature data of each dimension. The standard data difference is calculated using the following formula:

[0023] in, For the The standard deviation of the dimensions, It is the characteristic diagnostic data of the first car in the two associated cars. The characteristic diagnostic data of the second car in the two associated cars, For the The feature weight of each dimension.

[0024] Different from the prior art, the present invention provides a method for monitoring the operation status of a high-speed train. By receiving the basic attributes of the vehicle body uploaded by the management end, a standard operation model is generated, and then the vibration-temperature combination data collected by each sensing sensor is obtained. The preset screening strategy is used to remove the error data to obtain characteristic diagnosis data. The standard operation model is updated based on the characteristic diagnosis data to generate a customized diagnosis model. The standard operation model is compared with the customized diagnosis model to obtain the operation deviation data, and the preset diagnosis strategy is called to diagnose the operation deviation data to obtain the diagnosis result. According to the operation diagnosis result, early warning information is generated and sent to the management end. Through the above method, high-speed trains can be monitored and diagnosed in real time, potential faults can be warned, and train management personnel can quickly take early warning measures and maintenance operations, reducing the risk of sudden failures and improving the safety and reliability of high-speed train operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a flow chart of a method for monitoring the running status of a high-speed train provided in an embodiment of the present application;

[0026] Figure 2 is a schematic diagram of a luggage rack identification area provided in an embodiment of the present application;

[0027] Figure 3 is a schematic diagram of obtaining a second quality coefficient provided in an embodiment of the present application;

[0028] Figure 4 It is a structural schematic diagram of a high-speed train operation status monitoring device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0030] It should be noted that, if there is no conflict, the various features in the embodiments of the present invention can be combined with each other, and all are within the protection scope of the present invention. In addition, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in a different order from the module division in the device schematic diagram or the order in the flow chart.

[0031] The terms "first", "second", "third", "fourth", etc. (if any) in the description and claims of the present invention and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in sequences other than those illustrated or described herein.

[0032] It should be understood that in the present invention, "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising 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 these processes, methods, products or apparatuses.

[0033] Unless otherwise defined, all technical and scientific terms used in this specification have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0034] See also Figure 1 , Figure 1 : is a flow chart of a method for monitoring the running status of a high-speed train provided in an embodiment of the present application, including steps S1 to S4, which are specifically as follows:

[0035] S1. Respond to the status monitoring instruction, receive the basic attributes of the vehicle body uploaded by the management end, and obtain the standard operation model based on the basic attributes of the vehicle body.

[0036] Among them, the status monitoring instruction represents the instruction issued by the train management personnel for monitoring the operating status of the high-speed train; the management end represents the management platform for monitoring the operating status of the high-speed train, including but not limited to the monitoring workbench (computer terminal) installed on the high-speed train, and mobile management devices such as mobile phones, computers, and tablets used by train management personnel; the basic attributes of the vehicle body are the basic attributes of the high-speed train, including but not limited to the manufacturer, model, etc.; the standard operating model represents a digital model used to describe the ideal operating state of the high-speed train.

[0037] It is understandable that the different configurations and characteristics of each high-speed train result in different operating states. The manufacturer and model of high-speed trains are unique. A standard operating model of the high-speed train to be monitored can be generated by receiving the manufacturer and model of the high-speed train to be monitored input by the train management personnel. The standard operating model serves as a benchmark for the operating state and can be used for subsequent operating state monitoring and diagnosis of the high-speed train to be monitored.

[0038] In some embodiments, step S1 (responding to the status monitoring instruction, receiving the basic attributes of the vehicle body uploaded by the management end, and obtaining the standard operation model based on the basic attributes of the vehicle body) specifically includes steps S11 to S13:

[0039] S11. In response to a status monitoring instruction, a property editing interface is called, and basic properties of a high-speed train body are obtained based on the property editing interface.

[0040] Among them, the attribute editing interface represents a management interface for train management personnel to input basic attributes of high-speed trains, and the attribute editing interface can be displayed on the management end; the high-speed train refers to a train system used for high-speed travel, which can specifically be an EMU.

[0041] S12. Retrieving a vehicle body basic model and basic configuration data based on the basic attributes of the vehicle body, wherein the basic configuration data includes target monitoring component characteristics.

[0042] Among them, the basic car body model represents a digital model used to describe the basic characteristics of the high-speed train, including but not limited to the structure, size, weight, power system, control system, etc. of the high-speed train, which is consistent with the static characteristics of the high-speed train; the basic configuration data represents component type, component quantity and other data related to component configuration; the target monitoring component characteristics represent the type, number, location and specifications of key components that affect the running status of the train.

[0043] S13, calling a standard operation record table, extracting data from the standard operation record table according to the characteristics of the target monitoring component, obtaining standard operation data corresponding to each target monitoring component, and updating the vehicle body basic model based on the standard operation data to obtain a standard operation model.

[0044] Among them, the standard operation record table is a database or table containing the relevant operation data of each component of all high-speed trains under ideal operating conditions; the target monitoring component represents the key component that needs to be paid special attention or monitored when monitoring the operating status of the high-speed train; the standard operation data represents the relevant operation data of each key component of the high-speed train when the high-speed train is in an ideal operating state.

[0045] Specifically, the standard operation record table contains the relevant operation data of all components of the high-speed train under the ideal operation state, and the target monitoring component characteristics indicate which key components of the high-speed train need to be monitored. Therefore, the relevant operation data of irrelevant components in the standard operation record table can be removed according to the labels of the key components in the target monitoring component characteristics, and the relevant operation data of each key component of the high-speed train under the ideal operation state can be screened out to complete the data extraction. The relevant operation data of the key components obtained are the standard operation data; the standard operation data are integrated into the vehicle body basic model to update the vehicle body basic model based on the standard operation data, and the new model obtained is the standard operation model.

[0046] S2. Receive vibration-temperature combination data acquired by each sensing sensor, call a preset screening strategy based on the vibration-temperature combination data, remove error data from the vibration-temperature combination data according to the preset screening strategy, and acquire characteristic diagnostic data of different compartments.

[0047] Among them, the perception sensor represents a vibration-temperature composite sensor installed on a key component; the vibration-temperature combination data represents a collection of vibration data and temperature data, which can reflect the status of the corresponding key component during the operation of the high-speed train, the vibration data can reveal the vibration condition of this key component, and the temperature data can reveal the temperature change of this key component; the preset screening strategy represents a set of pre-set rules for screening and cleaning noise and error data in the vibration-temperature combination data, and the error data removal represents the process of removing noise and error data from the vibration-temperature combination data based on the preset screening strategy; the characteristic diagnostic data represents the key characteristic data with diagnostic significance obtained after the error is removed.

[0048] It should be noted that in order to monitor the operating status of high-speed trains, corresponding vibration-temperature composite sensors may be pre-installed on key components of different carriages of high-speed trains, and one or more vibration-temperature composite sensors may be installed on each key component. Each vibration-temperature composite sensor may collect relevant operating data on the corresponding key component, and the relevant operating data is vibration-temperature combination data. Error data or irrelevant data such as noise in the vibration-temperature combination data may cause deviations in the diagnosis process. The preset screening strategy is called to identify and eliminate irrelevant data in the vibration-temperature combination data, thereby improving the overall quality of the data and providing a reliable data basis for subsequent diagnosis.

[0049] In some embodiments, step S2 (receiving vibration-temperature combination data acquired by each sensing sensor, calling a preset screening strategy based on the vibration-temperature combination data, performing error data removal on the vibration-temperature combination data according to the preset screening strategy, and acquiring characteristic diagnostic data of different compartments) specifically includes steps S21 to S24:

[0050] S21. Receive vibration-temperature combination data acquired by each sensing sensor according to a preset monitoring time, identify the vibration-temperature combination data, acquire diagnosis-related data, and construct a status monitoring mapping table according to the diagnosis-related data.

[0051] Among them, the preset monitoring time represents the relevant time parameters pre-set for collecting vibration-temperature combination data, including but not limited to the start time of data collection, the time interval for continuous data collection and the end time of data collection. The start time of data collection can specifically be the time when the high-speed train starts to run, the end time of data collection can specifically be the time when the high-speed train ends to run, and the time interval for continuous data collection is 500 milliseconds; the diagnostic associated data represents the data that links the vibration-temperature combination data with the corresponding monitoring type and the label of the target monitoring component, that is, the diagnostic associated data reveals which monitoring type each vibration-temperature combination data belongs to, and which key component of the high-speed train the vibration-temperature combination data corresponds to; the state monitoring mapping table is a data table, which records the relationship between the monitoring type, the target monitoring component label and the corresponding vibration-temperature combination data.

[0052] It should be noted that, through the diagnosis of associated data, it is possible to understand the relationship between each vibration-temperature combination data and the operating status of specific components in specific structural parts of high-speed trains (such as wheels, bearings, etc.). Constructing a condition monitoring mapping table can provide a basis for the subsequent rapid retrieval and analysis of the vibration-temperature combination data related to each target monitoring component in each specific monitoring type, thereby effectively performing condition monitoring and diagnosis on each target monitoring component.

[0053] S22. Acquire the monitoring type and one or more vibration-temperature combination data corresponding to the current target monitoring component based on the status monitoring mapping table.

[0054] The monitoring type indicates a specific monitoring task category, including but not limited to bearing condition monitoring, wheel condition monitoring and rail condition monitoring; the current target monitoring component indicates a key component being analyzed.

[0055] Specifically, the number of the current target monitoring component is obtained, and the monitoring type and one or more vibration-temperature combination data corresponding to the number of the current target monitoring component are searched in the state monitoring mapping table.

[0056] It can be understood that, since one or more vibration-temperature composite sensors are provided on each key component, each vibration-temperature composite sensor will perform synchronous data acquisition, so each target monitoring component corresponds to one or more vibration-temperature combination data.

[0057] S23. Calling a corresponding preset screening strategy according to the monitoring type, removing error data from one or more vibration-temperature combination data based on the preset screening strategy, and acquiring characteristic diagnostic data corresponding to the current target monitoring component.

[0058] It is understandable that the preset screening strategies corresponding to different monitoring types are different, that is, the vibration-temperature combination data corresponding to different monitoring types have different characteristics and diagnostic requirements. Therefore, it is necessary to select appropriate preset screening strategies according to the monitoring type to effectively remove noise and error data. This differentiated processing method can better meet the needs of high-speed train operation status monitoring and realize accurate monitoring and timely early warning.

[0059] In some embodiments, the vibration-temperature combination data includes bearing vibration-temperature combination data, and step S23 (calling the corresponding preset screening strategy according to the monitoring type, removing error data from one or more vibration-temperature combination data based on the preset screening strategy, and obtaining characteristic diagnostic data corresponding to the current target monitoring component) includes:

[0060] When the monitoring type is bearing status monitoring, a first preset screening strategy is called, and the first preset screening strategy includes a bearing vibration data screening strategy and a bearing temperature data screening strategy.

[0061] Among them, the bearing vibration-temperature combination data represents a collection of vibration data and temperature data obtained for monitoring the bearing state; the bearing state monitoring represents a monitoring task category, which evaluates the health state and operating performance of the target monitoring component by monitoring and analyzing the operating parameters of the bearing (such as vibration data and temperature data); the first preset screening strategy represents a specific data screening strategy designed for bearing state monitoring; the bearing vibration data screening strategy is a preprocessing method designed for vibration data for removing noise and error data and extracting characteristic information closely related to the bearing vibration state; the bearing temperature data screening strategy is a preprocessing method designed for temperature data for removing noise and error data and extracting characteristic information closely related to the bearing thermal state.

[0062] The preset identification rules are called to identify the bearing vibration-temperature combination data to obtain the bearing vibration data and the bearing temperature data.

[0063] Among them, the preset identification rules include pre-set rules for classifying bearing vibration and temperature combination data, which can distinguish and extract bearing vibration data and bearing temperature data from bearing vibration and temperature data; the bearing vibration data is a numerical set of mechanical vibration information generated by the target monitoring component during operation; the bearing temperature data is a numerical set of temperature changes of the target monitoring component during operation.

[0064] The bearing vibration data is subjected to error removal according to the bearing vibration data screening strategy to obtain bearing vibration characteristic data, wherein the bearing vibration characteristic data represents the vibration data characteristics after error removal and reflects the vibration state of the target monitoring component.

[0065] The bearing temperature data is subjected to error removal according to the bearing temperature data screening strategy to obtain bearing temperature characteristic data, wherein the bearing temperature characteristic data represents the temperature data characteristics after error removal and reflects the temperature change of the target monitoring component.

[0066] The bearing vibration characteristic data and the bearing temperature characteristic data are combined to obtain bearing characteristic diagnosis data, wherein the bearing characteristic diagnosis data represents comprehensive characteristic data obtained by combining the bearing vibration characteristic data and the bearing temperature characteristic data.

[0067] In some embodiments, the vibration-temperature combination data also includes wheel vibration-temperature combination data, and step S23 (calling the corresponding preset screening strategy according to the monitoring type, removing error data from one or more vibration-temperature combination data based on the preset screening strategy, and obtaining characteristic diagnostic data corresponding to the current target monitoring component) also includes:

[0068] When the monitoring type is wheel status monitoring, a second preset screening strategy is called, and the second preset screening strategy includes a wheel vibration data screening strategy and a wheel temperature data screening strategy.

[0069] Among them, wheel state monitoring means monitoring the polygonal state of the wheel, and the wheel vibration-temperature combination data represents a collection of vibration data and temperature data obtained for monitoring the wheel state; the wheel state monitoring represents a monitoring task category, which evaluates the health state and operating performance of the target monitoring component by monitoring and analyzing the operating parameters of the wheel (such as vibration data and temperature data); the second preset screening strategy represents a specific data screening strategy designed for wheel state monitoring; the wheel vibration data screening strategy is a preprocessing method designed for vibration data for removing noise and error data and extracting feature information closely related to the vibration state of the wheel; the wheel temperature data screening strategy is a preprocessing method designed for temperature data for removing noise and error data and extracting feature information closely related to the thermal state of the wheel.

[0070] The preset identification rule is called to identify the wheel vibration-temperature combination data to obtain wheel vibration data and wheel temperature data.

[0071] Among them, the preset identification rules also include pre-set rules for classifying wheel vibration and temperature combination data, which can distinguish and extract wheel vibration data and wheel temperature data from the wheel vibration and temperature data; the wheel vibration data is a numerical set of mechanical vibration information generated by the target monitoring component during operation; the wheel temperature data is a numerical set of temperature changes of the target monitoring component during operation.

[0072] The wheel vibration data is subjected to error removal according to the wheel vibration data screening strategy to obtain wheel vibration characteristic data, wherein the wheel vibration characteristic data represents the vibration data characteristics after error removal and reflects the vibration state of the wheel.

[0073] The wheel temperature data is subjected to error removal according to the wheel temperature data screening strategy to obtain wheel temperature characteristic data, wherein the wheel temperature characteristic data represents the temperature data characteristics after error removal and reflects the temperature change of the wheel.

[0074] The wheel vibration characteristic data and the wheel temperature characteristic data are combined to obtain wheel characteristic diagnosis data, wherein the wheel characteristic diagnosis data represents comprehensive characteristic data obtained by combining the wheel vibration characteristic data and the wheel temperature characteristic data.

[0075] In some embodiments, the vibration-temperature combination data includes rail vibration-temperature combination data, and step S23 (calling the corresponding preset screening strategy according to the monitoring type, removing error data from one or more vibration-temperature combination data based on the preset screening strategy, and obtaining characteristic diagnostic data corresponding to the current target monitoring component) also includes:

[0076] When the monitoring type is rail status monitoring, a third preset screening strategy is called, and the third preset screening strategy includes a rail vibration data screening strategy and a rail temperature data screening strategy.

[0077] Among them, rail condition monitoring is to monitor the corrugation state of the rail, and the rail vibration-temperature combination data represents a collection of vibration data and temperature data obtained for monitoring the rail condition; the rail condition monitoring represents a monitoring task category, which evaluates the health status and operating performance of the target monitoring component by monitoring and analyzing the operating parameters of the rail (such as vibration data and temperature data); the third preset screening strategy represents a specific data screening strategy designed for rail condition monitoring; the rail vibration data screening strategy is a preprocessing method designed for vibration data for removing noise and error data and extracting characteristic information closely related to the vibration state of the rail; the rail temperature data screening strategy is a preprocessing method designed for temperature data for removing noise and error data and extracting characteristic information closely related to the thermal state of the rail.

[0078] The preset identification rule is called to identify the rail vibration-temperature combination data to obtain rail vibration data and rail temperature data.

[0079] Among them, the preset identification rules also include pre-set rules for data classification of rail vibration and temperature combination data, which can distinguish and extract rail vibration data and rail temperature data from the rail vibration and temperature data; the rail vibration data is a numerical set of mechanical vibration information generated by the target monitoring component during operation; the rail temperature data is a numerical set of temperature changes of the target monitoring component during operation.

[0080] The rail vibration data is subjected to error removal according to the rail vibration data screening strategy to obtain rail vibration characteristic data, wherein the rail vibration characteristic data represents the vibration data characteristics after error removal and reflects the vibration state of the target monitoring component.

[0081] The rail temperature data is subjected to error removal according to the rail temperature data screening strategy to obtain rail temperature characteristic data, wherein the rail temperature characteristic data represents the temperature data characteristics after error removal and reflects the temperature change of the target monitoring component.

[0082] The rail vibration characteristic data and the rail temperature characteristic data are combined to obtain rail characteristic diagnosis data, wherein the rail characteristic diagnosis data represents comprehensive characteristic data obtained by combining the rail vibration characteristic data and the rail temperature characteristic data.

[0083] Through the above method, key components such as axle box bearings, gear box bearings, motor bearings, etc. of the running gear of high-speed trains can be monitored in real time. At the same time, the polygonal status of wheels, corrugation status of tracks, etc. can be monitored in real time.

[0084] S24. Repeat the above steps of obtaining characteristic diagnostic data until characteristic diagnostic data corresponding to all target monitoring components in different compartments are obtained respectively.

[0085] Specifically, as long as the characteristic diagnostic data corresponding to a target monitoring component has not been acquired, the above steps of acquiring the characteristic diagnostic data are repeated until the characteristic diagnostic data corresponding to all target monitoring components in different compartments are acquired.

[0086] For example: If a certain carriage needs to obtain characteristic diagnostic data of 100 target monitoring components, and the characteristic diagnostic data corresponding to the first 60 target monitoring components have been obtained, then repeat the above steps of obtaining characteristic diagnostic data, and continue to obtain the characteristic diagnostic data corresponding to the 61st target monitoring component, until the characteristic diagnostic data corresponding to all 100 target monitoring components are obtained, and then continue to obtain the characteristic diagnostic data corresponding to the next carriage, until the characteristic diagnostic data corresponding to all target monitoring components in different carriages are obtained.

[0087] S3. Update the standard operation model based on the characteristic diagnostic data of different carriages to obtain a customized diagnostic model, compare the standard operation model with the customized diagnostic model, and obtain a first operation deviation data set.

[0088] Among them, the customized diagnostic model represents the model obtained after updating the standard operation model based on the characteristic diagnostic data, which reflects the actual operation status of the high-speed train; the operation data related to the same target monitoring components in the standard operation model and the customized diagnostic model are identified, and the deviation data corresponding to each target monitoring component is obtained. The set of deviation data corresponding to all target monitoring components obtained is the first operation deviation data set.

[0089] In some embodiments, step S3 (updating the standard operation model based on characteristic diagnostic data of different carriages to obtain a customized diagnostic model, comparing the standard operation model with the customized diagnostic model to obtain a first operation deviation data set) specifically includes steps S31 to S34:

[0090] S31, combining the bearing characteristic diagnosis data, the wheel characteristic diagnosis data and the rail characteristic diagnosis data of different carriages to obtain a characteristic diagnosis data set.

[0091] Among them, the bearing characteristic diagnostic data, the wheel characteristic diagnostic data and the rail characteristic diagnostic data are all characteristic diagnostic data. The three are aggregated together to form a comprehensive data set, which is the characteristic diagnostic data set.

[0092] S32: extracting corresponding target synchronous operation data in the standard operation model based on the characteristic diagnosis data set, and generating a target update data set according to the multiple target synchronous operation data.

[0093] Among them, the target synchronous operation data represents the operation data corresponding to each target monitoring component in the characteristic diagnosis data set at a specific time point or time period extracted from the standard operation data; the target update data set represents a data set composed of multiple target synchronous operation data.

[0094] For example, if the characteristic diagnosis data set contains the temperature data of component 1 of a bearing in a specific time period, then the target synchronous operation data is the temperature data of component 1 of the bearing in the same time period in the standard operation data.

[0095] S33. Based on each characteristic diagnosis data of the characteristic diagnosis data set, each target synchronous operation data of the standard operation model is updated one by one to obtain a customized diagnosis model.

[0096] Among them, each bearing characteristic diagnostic data, wheel characteristic diagnostic data, and rail characteristic diagnostic data is a characteristic diagnostic data.

[0097] Specifically, for each characteristic diagnosis data in the characteristic diagnosis data set, the corresponding target synchronization operation data in the standard operation model is found, and each characteristic diagnosis data is used to replace and update the corresponding target synchronization operation data.

[0098] For example: The feature diagnosis data set contains the temperature data of component 1 of a bearing in a specific time period, marked as data 1. Find the corresponding temperature data of component 1 of the bearing in the standard operation model, marked as data 2, and replace data 2 with data 1.

[0099] S34: Compare the operation status data corresponding to each target monitoring component in the customized diagnosis model with that in the standard operation model to obtain a first operation deviation data set.

[0100] The operating status data includes standard operating data of a standard operating model and actual operating data of a customized diagnosis model.

[0101] S4. Acquire dynamic riding data of different carriages, determine characteristic diagnostic data corresponding to associated carriages based on the dynamic riding data, and perform correlation comparison based on the characteristic diagnostic data corresponding to the associated carriages to obtain a second operation deviation data set.

[0102] Among them, the dynamic riding data represents the real-time load condition of the car during operation; the associated cars represent a group of cars with the closest real-time load conditions, which can be compared horizontally. If the temperature and vibration between the two cars differ too much, it means that one of the cars is seriously aged or needs maintenance; the characteristic diagnostic data includes vibration data and temperature data; the second operation deviation data set represents a data set used to identify the potential damage risks of each car, which is helpful for early warning and maintenance.

[0103] It should be noted that passengers getting on and off the train, luggage handling, etc. during train operation will affect the load of the carriage, so the load of the carriage changes in real time during operation. If the real-time load conditions in two different carriages of the same train are the same, their temperature and vibration frequency do not exceed the threshold range (not damaged), but the temperature and / or vibration frequency of the two carriages are different, then one of the carriages may have a tendency to be damaged, such as severe aging or needing maintenance.

[0104] In some embodiments, step S4 (obtaining dynamic riding data of different carriages, determining characteristic diagnostic data corresponding to the associated carriages based on the dynamic riding data, and performing correlation comparison based on the characteristic diagnostic data corresponding to the associated carriages to obtain a second operation deviation data set) specifically includes steps S41 to S43:

[0105] S41. Locate the current travel section of the train based on the current travel position of the train. Each model of train has a preset current travel section at different current travel positions.

[0106] The current travel position indicates the specific geographical location of the train at a certain moment; the current travel section indicates the section from one station to another station of the train.

[0107] It should be noted that when each model of train is in operation, the entire route will be divided into several sections according to its operation plan and route. Each section is called a driving section. These driving sections are pre-set to facilitate the management and monitoring of the operating status of the train. The distance between the departure of a high-speed train from one station and the arrival at another station can be divided into a driving section.

[0108] For example: Train A's route is Beijing South Station - Jinan West Station - Nanjing South Station - Shanghai Hongqiao Station, then Beijing South Station - Jinan West Station is driving section 1, Jinan West Station - Nanjing South Station is driving section 2, Nanjing South Station - Shanghai Hongqiao Station is driving section 3. If Train A passes through the GPS positioning system at 10:30 Beijing time and its position is determined to be a, a is between Beijing and Jinan, then the current driving section of Train A is Beijing South Station - Jinan West Station, that is, driving section 1.

[0109] S42. Determine the passenger information of each carriage in the current travel section based on the ticket sales information corresponding to the train, collect the cargo information of the corresponding carriage based on the image acquisition device preset by the train, and obtain the dynamic occupancy data of the corresponding carriage based on the passenger information and cargo information of each carriage.

[0110] Among them, the ticket sales information represents detailed information about passengers purchasing tickets, including carriage number, seat number, number of passengers, etc.; the passenger information represents detailed information about passengers currently riding the train, including number of passengers, age group, etc.; the image acquisition device represents a device installed on the train for capturing images inside the carriage, which can specifically be a camera; the cargo information includes detailed information on luggage and cargo carried on the train.

[0111] It should be noted that the ticket sales information can be obtained from the background of the ticket purchasing platform. The number of passengers and the weight of cargo will directly affect the load condition of the carriage.

[0112] In some embodiments, step S42 (determining the passenger information of each carriage in the current travel section based on the ticket sales information corresponding to the train, collecting the cargo information of the corresponding carriage based on the image acquisition device preset by the train, and obtaining the dynamic riding data of the corresponding carriage based on the passenger information and cargo information of each carriage) specifically includes steps S421 to S424:

[0113] S421. Obtain the number and age group of passengers in each carriage in each current travel segment, and add a different first mass coefficient to each passenger based on the age group. Different age groups have different first mass coefficients.

[0114] Among them, the number of passenger information represents the total number of passengers actually in the current carriage; the age group represents the age classification of the passengers, such as under 12 years old is one age group; the first quality coefficient represents different weight coefficients assigned according to the age group of the passengers, such as the quality coefficient of children may be lower, and the quality coefficient of adults is higher.

[0115] For example: The current travel section of train A is Beijing South Station-Jinan West Station. There are 10 children, 5 teenagers, 20 adults and 2 senior citizens in carriage 1. Among them, 0-12 years old (children) is the first age group, and the first mass coefficient added is 0.5, 13-17 years old (teenagers) is the second age group, and the first mass coefficient added is 0.8, 18-64 years old (adults) is the third age group, and the first mass coefficient added is 1.0, 65 years old and above (seniors) is the fourth age group, and the first mass coefficient added is 0.7.

[0116] S422, obtaining the luggage rack identification area of ​​each carriage, and performing segmented identification processing on the luggage rack identification area based on the seat number in the carriage to obtain the corresponding luggage compartment segment.

[0117] Among them, the luggage rack identification area represents the area in the car for storing luggage, which is usually set above the car; the seat number represents the seat number of each passenger, which can determine the position of the passenger and luggage; the segmented identification processing means dividing the luggage rack identification area according to the seat number, and the luggage interval segment represents the luggage rack area divided by seat number, and each luggage interval segment corresponds to the luggage placement area of ​​one or more seats.

[0118] See also Figure 2 , Figure 2 1F, 2F, and 3F represent seat numbers. The luggage identification area is identified according to 1F, 2F, and 3F and divided into three areas, f1, f2, and f3. These three areas are luggage sections. f1 is the luggage section corresponding to 1F, f2 is the luggage section corresponding to 2F, and f3 is the luggage section corresponding to 3F.

[0119] S423, performing coordinate processing of the horizontal coordinate of the image of each baggage section, obtaining each pixel point different from the preset pixel value of the baggage section to obtain a baggage identification pixel point, and obtaining a second quality coefficient based on the horizontal coordinate ratio of the baggage identification pixel point to the total number of pixel points of the corresponding baggage section, and each horizontal coordinate ratio has a preset second quality coefficient.

[0120] The image represents a photograph of a luggage section in a carriage acquired by an image acquisition device; the coordinate processing of the horizontal axis represents processing of the luggage section in the image, and converting the horizontal position of the luggage in the image into a specific coordinate value; the preset pixel value represents a preset reference pixel value, which is usually an image pixel value without luggage; pixels in the image that are different from the preset pixel value may indicate the presence of luggage, and the luggage identification pixel points represent the pixels representing luggage; the total number of pixels in the luggage section represents the total number of all pixels in the luggage section; the horizontal axis ratio represents the ratio of the luggage identification pixel points to the total number of pixels in the luggage section, which is used to determine the quantity and distribution of the luggage; the second quality coefficient represents a weight coefficient allocated based on the horizontal axis ratio of the luggage identification pixel points, which can be used to estimate the luggage weight of each section.

[0121] Example: See Figure 3 , Figure 3: is a schematic diagram of obtaining a second quality coefficient provided by an embodiment of the present invention. The color on each baggage segment is fixed. If the preset pixel value is the pixel value corresponding to silver, the pixel points in the b1, b2, b3, and b4 areas are different from the preset pixel values, indicating that they are not silver and luggage has been placed. Therefore, the pixel points corresponding to the b1, b2, b3, and b4 areas are baggage identification pixels. The horizontal coordinate ratio of the baggage identification pixel points corresponding to the f1 area to the total number of pixel points in the corresponding baggage segment is (x1+x2) / x, the horizontal coordinate ratio of the baggage identification pixel points corresponding to the f2 area to the total number of pixel points in the corresponding baggage segment is x3 / x, and the horizontal coordinate ratio of the baggage identification pixel points corresponding to the f3 area to the total number of pixel points in the corresponding baggage segment is x4 / x. Each baggage identification pixel point has a corresponding second quality coefficient for the horizontal coordinate ratio of the total number of pixel points in the corresponding baggage segment. For example, if the horizontal coordinate ratio is one-tenth, there is a corresponding second quality coefficient, and if the horizontal coordinate ratio is one-half, there is also a corresponding second quality coefficient. The preset second quality coefficient can be adjusted according to actual conditions.

[0122] S424. Calculate dynamic riding data based on the number of passenger information, the first quality coefficient, the number of luggage sections, and the second quality coefficient.

[0123] The number of luggage interval segments refers to the number of luggage storage areas obtained after segment identification processing in each carriage. For example, if the number of luggage storage areas obtained after segment identification processing in each carriage is 16, then the number of luggage interval segments is 16.

[0124] In some embodiments, step S424 (calculating dynamic riding data based on the number of passenger information, the first quality coefficient, the number of luggage sections, and the second quality coefficient) specifically includes steps S4241 to S4242:

[0125] S4241. Calculate the first dynamic sub-information based on the number of passenger information and the first quality coefficient, and calculate the second dynamic sub-information based on the number of luggage sections and the second quality coefficient.

[0126] The first dynamic sub-information represents information reflecting the passenger load condition in the carriage; the second dynamic sub-information represents information reflecting the luggage load condition in the carriage.

[0127] S4242: Add the first dynamic sub-information and the second dynamic sub-information to obtain dynamic riding data, and calculate the dynamic riding data using the following formula:

[0128] in, For dynamic riding data, is the number of passengers on board, is the passenger weight coefficient, For the The first quality coefficient of the passenger information, is the upper limit of the number of passengers on board, is the weight value of the first quality coefficient, is the normalized value of passengers, is the number of baggage sections with bags, is the weight coefficient of the baggage interval, For the The second mass coefficient in the baggage section, is the upper limit of the number of baggage sections, is the weight coefficient of the baggage interval, is the baggage normalization value.

[0129] The upper limit value of the passenger information indicates the maximum number of passengers that can be accommodated in each carriage; the passenger normalization value and the luggage normalization value respectively indicate the values ​​obtained by converting the passenger mass and the luggage mass into the same standard scale; the number of luggage sections with luggage indicates the number of luggage sections actually storing luggage in each carriage; the upper limit value of the number of luggage sections indicates the maximum number of luggage sections in each carriage.

[0130] Specifically, Reflects the impact of passengers on the carriage load, It is the sum of the mass coefficients of all passengers multiplied by the weight coefficient, reflecting the accumulation of passenger mass. Reflects the impact of luggage on carriage load, It means the sum of the mass coefficients of all the luggage multiplied by the weight coefficient, reflecting the accumulation of the luggage mass.

[0131] It should be noted that in order to perform normalized calculations, the mass of passengers and the mass of luggage need to be normalized, and the units of the two need to be converted into the same numerical coefficients to facilitate calculations.

[0132] S43. Determine characteristic diagnostic data corresponding to the associated car based on the dynamic riding data, obtain differentiated intervals of the characteristic diagnostic data based on the differences between the dynamic riding data, and obtain a second operating deviation data set based on the associated car that does not meet the requirements determined based on the differentiated intervals.

[0133] Among them, the differentiation interval represents the interval used to determine whether the car meets the standards; failure to meet the requirements means deviation from the standards, exceeding the differentiation interval; the second operation deviation data set represents a collection of cars that deviate from the standards and their related characteristic data.

[0134] It should be noted that the characteristic diagnostic data includes vibration diagnostic data and temperature diagnostic data. A standardized difference interval, namely the differentiation interval, is defined based on the difference in dynamic riding data of two cars in the associated cars. Based on the defined differentiation interval, it is determined which cars' characteristic diagnostic data exceed the interval, thereby determining that these cars do not meet the requirements. The above-mentioned cars that do not meet the requirements and their related characteristic data are grouped together to form a second operating deviation data set.

[0135] In some embodiments, step S43 (obtaining a differentiated interval of characteristic diagnostic data based on the difference between the dynamic riding data, and determining the associated carriage that does not meet the requirements based on the differentiated interval to obtain a second operation deviation data set) specifically includes steps S431 to S434:

[0136] S431. Sort all the carriages in descending order based on the dynamic riding data to obtain a descending sequence of carriages, traverse the dynamic riding data of each carriage in the descending sequence of carriages in turn and determine the closest dynamic riding data.

[0137] Among them, the descending sorting means arranging in order from large to small; the car descending sequence means a car sequence sorted from high to low according to the passenger and luggage load conditions; traversal means checking the data of each car in the car descending sequence in turn; the closest dynamic riding data means the dynamic riding data of other cars in the car descending sequence that are closest to the dynamic riding data of the currently traversed car.

[0138] Specifically, the total weight of the objects and people on each car is calculated, and the real-time load weights of all cars are arranged in descending order, that is, the higher the weight, the lower the weight. Each car is taken as the main body, and its closest dynamic riding data is determined. If the dynamic riding data of two cars have the same difference with the current car, the dynamic riding data corresponding to one car can be arbitrarily selected as the dynamic riding data closest to the dynamic riding data of the current car.

[0139] For example: after descending sorting, the descending sequence of the carriages is A, C, D, B, and E. The dynamic riding data corresponding to carriage A is 9, the dynamic riding data corresponding to carriage C is 8, the dynamic riding data corresponding to carriage D is 7.5, the dynamic riding data corresponding to carriage B is 6, and the dynamic riding data corresponding to carriage E is 5.

[0140] First, determine that the dynamic riding data closest to the dynamic riding data 9 corresponding to car A is 8, then determine that the dynamic riding data closest to the dynamic riding data 8 corresponding to car C is 7.5, determine that the dynamic riding data closest to the dynamic riding data 7.5 corresponding to car D is 8, then determine that the dynamic riding data closest to the dynamic riding data 6 corresponding to car B is 5, and finally determine that the dynamic riding data closest to the dynamic riding data 5 corresponding to car E is 6.

[0141] S432. Use the dynamic riding data of the traversed carriage and the closest dynamic riding data as characteristic diagnostic data corresponding to the associated carriage.

[0142] For example: Carriage A and Carriage C are associated cars, Carriage C and Carriage D are associated cars, and Carriage B and Carriage E are associated cars. Dynamic riding data 9 and dynamic riding data 8 are characteristic diagnostic data corresponding to the associated cars (Carriage A and Carriage C), dynamic riding data 8 and dynamic riding data 7.5 are characteristic diagnostic data corresponding to the associated cars (Carriage C and Carriage D), and dynamic riding data 6 and dynamic riding data 5 are characteristic diagnostic data corresponding to the associated cars (Carriage B and Carriage E).

[0143] S433, calculating the difference in the dynamic riding data to obtain a differentiated riding value, and obtaining the standard data difference between the characteristic diagnostic data corresponding to the associated cars based on the differentiated riding value.

[0144] Among them, the differentiated occupancy value represents the difference between the dynamic occupancy data of two associated carriages; the standard data difference represents the standardized difference between the characteristic diagnostic data of two associated carriages, which is used to measure the degree of difference in the characteristic diagnostic data between the carriages to determine whether there is a trend of damage to the train.

[0145] For example: the difference between dynamic riding data 9 and dynamic riding data 8 is 1, that is, the differentiated riding value is 1. The standard data difference between the characteristic diagnostic data corresponding to the associated cars (carriage A and car C) can be obtained based on the differentiated riding value 1, such as the standard data difference of temperature is 2°C, and the standard data difference of vibration is 0.2Hz.

[0146] It should be noted that, generally speaking, when the load of the train increases, the friction between the wheels and the rails will increase, resulting in heat accumulation and temperature increase on the friction surface. The weight borne by the wheels increases with the load, so the contact pressure with the ground also increases, causing the wheels and rails to generate more vibrations when moving.

[0147] In some embodiments, step S433 (the step of calculating the difference in the dynamic riding data to obtain a differentiated riding value, and obtaining the standard data difference between the characteristic diagnostic data corresponding to the associated carriages based on the differentiated riding value) specifically includes steps S4331 to S4332:

[0148] S4331. Obtain information feature data and corresponding feature weights of each dimension in each feature diagnostic data, wherein the information feature data at least includes rail vibration data and rail temperature data.

[0149] The dimensions represent various categories of feature diagnostic data, such as vibration data, temperature data, etc., and each dimension represents a specific feature data type; the information feature data represents various types of data describing the running status of the carriage; the feature weight represents the relative importance of each information feature data in calculating the standard data difference; the rail vibration data represents data measuring the vibration condition of the track where the carriage is located, and the rail temperature data represents data measuring the temperature condition of the track where the carriage is located.

[0150] S4332: Based on the differentiated occupancy values ​​of the associated carriages and the feature weights of the information feature data of each dimension, a standard data difference is calculated by the following formula:

[0151] in, For the The standard deviation of the dimensions, It is the characteristic diagnostic data of the first car in the two associated cars. The characteristic diagnostic data of the second car in the two associated cars, For the The feature weight of each dimension.

[0152] It should be noted that the features of each dimension (such as vibration, temperature, etc.) have different importance in the overall diagnosis, so it is necessary to configure feature weights for each dimension, and different dimensions correspond to different feature weights. The rail vibration data of each carriage can be obtained by the average value of the rail vibration data of all target monitoring components corresponding to the carriage, and the rail temperature data of each carriage can be obtained by the average value of the rail temperature data of all target monitoring components corresponding to the carriage.

[0153] S434, calculating the diagnostic data difference of the information feature data of each dimension, if the diagnostic data difference is less than or equal to the standard data difference, the associated car meets the requirements, if the diagnostic data difference is greater than the standard data difference, the associated car does not meet the requirements.

[0154] The diagnostic data difference represents the actual difference between the characteristic diagnostic data, and is used to evaluate the specific differences in the characteristic data between the carriages to determine whether there is an abnormal situation.

[0155] For example, if the rail vibration data of car No. 1 is 0.75Hz, the rail temperature data is 35℃, and the rail vibration data of car No. 2 is 0.65, the rail temperature data is 30℃, the standard data difference of vibration data is 0.2Hz, and the standard data difference of temperature data is 2℃. The difference of vibration data between car No. 1 and car No. 2 is 0.1Hz, which is less than the standard data difference of vibration data, so the vibration conditions of car No. 1 and car No. 2 meet the requirements; the difference of temperature data between car No. 1 and car No. 2 is 5℃, which is greater than the standard data difference of temperature data, so the temperature conditions of car No. 1 and car No. 2 do not meet the requirements.

[0156] S5. Call a preset diagnosis strategy based on the first operation deviation data set and the second operation deviation data set to obtain an operation diagnosis result, generate warning information according to the operation diagnosis result, and send the operation diagnosis result and the warning information to the management end.

[0157] Among them, the preset diagnostic strategy represents a pre-defined judgment rule for predicting the operating status based on the first operating deviation data set and the second operating deviation data set, which can determine whether the carriage of the high-speed train is in a normal state or has a damage trend; the operating diagnosis result represents the evaluation result obtained after diagnosing the operating status of each target monitoring component; the early warning information represents relevant information generated based on the abnormal operation diagnosis result for reminding train management personnel of possible abnormal conditions or potential faults.

[0158] For the first operation deviation data set, if the actual operation data exceeds the maximum value or is less than the minimum value, it means that the vibration data or temperature data of the carriage exceeds the safety threshold and the carriage is abnormal; for the second operation deviation data set, the associated carriage that does not meet the requirements may have a tendency to be damaged. Call the preset diagnostic strategy, conduct a comprehensive analysis of the two types of deviation data, generate a comprehensive operation diagnosis result, generate warning information based on the diagnosis result, prompt the management end of possible risks and abnormalities, and send the operation diagnosis result and warning information to the management end to ensure that the corresponding maintenance and correction measures are taken in time.

[0159] It should be noted that the first operation deviation data set is obtained by comparing the standard operation model with the customized diagnosis model, and the deviation is found by comparing the actual operation data of the carriage with the limit value (such as the maximum or minimum value) of the standard operation model; the second operation deviation data set is obtained based on the correlation comparison between the dynamic riding data of different carriages, and the carriages with damage trends are obtained. The two methods realize comprehensive monitoring and timely warning of the train operation status to ensure the safe operation of the train.

[0160] In this embodiment, a method for monitoring the running status of a high-speed train is provided. By receiving the basic attributes of the vehicle body uploaded by the management end, a standard running model is generated, and then the vibration and temperature combination data collected by each sensing sensor is obtained. The error data is removed by using a preset screening strategy to obtain characteristic diagnostic data. The standard running model is updated based on the characteristic diagnostic data to generate a customized diagnostic model. The standard running model is compared with the customized diagnostic model to obtain the running deviation data, and the preset diagnostic strategy is called to diagnose the running deviation data to obtain the diagnostic results. According to the running diagnostic results, early warning information is generated and sent to the management end. In the above manner, high-speed trains can be monitored and diagnosed in real time, potential faults can be warned, and train management personnel can quickly take early warning measures and maintenance operations, reducing the risk of sudden failures and improving the safety and reliability of high-speed train operation.

[0161] See also Figure 4 , Figure 4 1 is a schematic diagram of the structure of a high-speed train running status monitoring device provided by an embodiment of the present invention, the high-speed train running status monitoring device comprising:

[0162] The attribute editing module is used to respond to the status monitoring instruction, receive the basic attributes of the vehicle body uploaded by the management end, and obtain the standard operation model based on the basic attributes of the vehicle body.

[0163] The data acquisition module is used to receive the vibration-temperature combination data acquired by each perception sensor, call a preset screening strategy based on the vibration-temperature combination data, remove error data from the vibration-temperature combination data according to the preset screening strategy, and acquire characteristic diagnostic data of different compartments.

[0164] The model comparison module is used to update the standard operation model based on the characteristic diagnostic data of different carriages to obtain a customized diagnostic model, compare the standard operation model with the customized diagnostic model, and obtain a first operation deviation data set.

[0165] The correlation comparison module is used to obtain dynamic riding data of different carriages, determine characteristic diagnostic data corresponding to the associated carriage based on the dynamic riding data, and perform correlation comparison based on the characteristic diagnostic data corresponding to the associated carriage to obtain a second operation deviation data set.

[0166] The result acquisition module is used to call the preset diagnosis strategy based on the first operation deviation data set and the second operation deviation data set, obtain the operation diagnosis result, generate warning information according to the operation diagnosis result, and send the operation diagnosis result and the warning information to the management end.

[0167] It should be noted that the above-mentioned high-speed train operation status monitoring device can execute the high-speed train operation status monitoring method provided by the embodiment of the present invention. For technical details and beneficial effects that are not fully described in the embodiment of the high-speed train operation status monitoring device, refer to the high-speed train operation status monitoring method provided by the embodiment of the present invention.

[0168] It should be noted that the above-mentioned half-high container trading system can execute the half-high container trading method provided in the embodiment of the present invention. For technical details and beneficial effects that are not fully described in the embodiment of the half-high container trading system, refer to the half-high container trading method provided in the embodiment of the present invention.

[0169] Through the description of the above embodiments, it can be clearly understood by those skilled in the art that each embodiment can be implemented by means of software plus a general hardware platform, or by hardware. It can be understood by those skilled in the art that all or part of the processes in the above embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0170] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for monitoring the running status of a high-speed train, characterized in that: include: In response to the status monitoring instruction, receiving the basic attributes of the vehicle body uploaded by the management end, and obtaining the standard operation model based on the basic attributes of the vehicle body; Receiving vibration-temperature combination data acquired by each sensing sensor, calling a preset screening strategy based on the vibration-temperature combination data, removing error data from the vibration-temperature combination data according to the preset screening strategy, and acquiring characteristic diagnostic data of different compartments; The standard operation model is updated based on characteristic diagnostic data of different carriages to obtain a customized diagnostic model, and the standard operation model is compared with the customized diagnostic model to obtain a first operation deviation data set; Acquiring dynamic riding data of different carriages, determining characteristic diagnostic data corresponding to associated carriages based on the dynamic riding data, and performing correlation comparison based on the characteristic diagnostic data corresponding to the associated carriages to obtain a second operation deviation data set; calling a preset diagnosis strategy based on the first operation deviation data set and the second operation deviation data set, obtaining an operation diagnosis result, generating warning information according to the operation diagnosis result, and sending the operation diagnosis result and the warning information to the management end; Receiving vibration-temperature combination data acquired by each sensing sensor, calling a preset screening strategy based on the vibration-temperature combination data, removing error data from the vibration-temperature combination data according to the preset screening strategy, and acquiring characteristic diagnostic data of different compartments, including: Receiving vibration-temperature combination data acquired by each sensing sensor according to a preset monitoring time, identifying the vibration-temperature combination data, acquiring diagnosis-related data, and constructing a state monitoring mapping table according to the diagnosis-related data; Based on the state monitoring mapping table, obtain the monitoring type and one or more vibration-temperature combination data corresponding to the current target monitoring component; Calling a corresponding preset screening strategy according to the monitoring type, removing error data from one or more vibration-temperature combination data based on the preset screening strategy, and acquiring characteristic diagnostic data corresponding to the current target monitoring component; Repeat the above steps of obtaining characteristic diagnostic data until characteristic diagnostic data corresponding to all target monitoring components in different compartments are obtained respectively; The vibration-temperature combination data includes bearing vibration-temperature combination data. The corresponding preset screening strategy is called according to the monitoring type. Error data is removed from one or more vibration-temperature combination data based on the preset screening strategy to obtain characteristic diagnostic data corresponding to the current target monitoring component, including: When the monitoring type is bearing status monitoring, calling a first preset screening strategy, the first preset screening strategy includes a bearing vibration data screening strategy and a bearing temperature data screening strategy; Calling preset identification rules to identify the bearing vibration-temperature combination data, and obtaining bearing vibration data and bearing temperature data; Performing error removal on the bearing vibration data according to the bearing vibration data screening strategy to obtain bearing vibration characteristic data; Perform error removal on the bearing temperature data according to the bearing temperature data screening strategy to obtain bearing temperature characteristic data; Combining the bearing vibration characteristic data and the bearing temperature characteristic data to obtain bearing characteristic diagnosis data; The vibration-temperature combination data also includes wheel vibration-temperature combination data, calling a corresponding preset screening strategy according to the monitoring type, removing error data from one or more vibration-temperature combination data based on the preset screening strategy, and obtaining characteristic diagnosis data corresponding to the current target monitoring component, further comprising: When the monitoring type is wheel status monitoring, calling a second preset screening strategy, the second preset screening strategy includes a wheel vibration data screening strategy and a wheel temperature data screening strategy; Calling the preset recognition rule to recognize the wheel vibration and temperature combination data, and obtaining wheel vibration data and wheel temperature data; Performing error removal on the wheel vibration data according to the wheel vibration data screening strategy to obtain wheel vibration characteristic data; performing error removal on the wheel temperature data according to the wheel temperature data screening strategy to obtain wheel temperature characteristic data; combining the wheel vibration characteristic data and the wheel temperature characteristic data to obtain wheel characteristic diagnosis data; The vibration-temperature combination data also includes rail vibration-temperature combination data, calling a corresponding preset screening strategy according to the monitoring type, removing error data from one or more vibration-temperature combination data based on the preset screening strategy, and obtaining characteristic diagnostic data corresponding to the current target monitoring component, further comprising: When the monitoring type is rail condition monitoring, calling a third preset screening strategy, the third preset screening strategy includes a rail vibration data screening strategy and a rail temperature data screening strategy; Calling the preset recognition rule to recognize the rail vibration-temperature combination data, and obtaining rail vibration data and rail temperature data; Perform error removal on the rail vibration data according to the rail vibration data screening strategy to obtain rail vibration characteristic data; Perform error removal on the rail temperature data according to the rail temperature data screening strategy to obtain rail temperature characteristic data; Combining the rail vibration characteristic data and the rail temperature characteristic data to obtain rail characteristic diagnosis data; The acquiring of dynamic riding data of different carriages, determining characteristic diagnostic data corresponding to the associated carriages based on the dynamic riding data, and performing correlation comparison based on the characteristic diagnostic data corresponding to the associated carriages to obtain a second operation deviation data set includes: Locating the current driving section of the train based on the current driving position of the train, each model of train has a preset current driving section at different current driving positions; Determine the passenger information of each carriage in the current travel section based on the ticket sales information corresponding to the train, collect the cargo information of the corresponding carriage based on the image acquisition device preset by the train, and obtain the dynamic riding data of the corresponding carriage based on the passenger information and cargo information of each carriage; Determine characteristic diagnostic data corresponding to the associated car based on the dynamic riding data, obtain a differential interval of the characteristic diagnostic data based on the difference between the dynamic riding data, and obtain a second operation deviation data set based on the associated car that does not meet the requirements determined by the differential interval; The method of determining the passenger information of each carriage in the current travel section based on the ticket sales information corresponding to the train, collecting the cargo information of the corresponding carriage based on the image acquisition device preset by the train, and obtaining the dynamic riding data of the corresponding carriage based on the passenger information and cargo information of each carriage includes: Obtaining the number and age group of passengers in each carriage in each current travel segment, and adding a different first mass coefficient to each passenger based on the age group, where different age groups have different first mass coefficients; Obtain the luggage rack identification area of ​​each carriage, and obtain the corresponding luggage compartment segment after segmentation recognition processing of the luggage rack identification area based on the seat number in the carriage; Performing coordinate processing of the horizontal coordinate on the image of each baggage section, obtaining each pixel point different from the preset pixel value of the baggage section to obtain a baggage identification pixel point, and obtaining a second quality coefficient based on the horizontal coordinate ratio of the baggage identification pixel point to the total number of pixel points of the corresponding baggage section, wherein each horizontal coordinate ratio has a preset second quality coefficient; Dynamic riding data is calculated based on the number of passenger information, the first quality coefficient, the number of luggage sections, and the second quality coefficient; The dynamic riding data is calculated based on the number of passenger information, the first quality coefficient, the number of luggage sections, and the second quality coefficient, including: The first dynamic sub-information is obtained by calculating based on the number of passenger information and the first quality coefficient, and the second dynamic sub-information is obtained by calculating based on the number of baggage sections and the second quality coefficient; The first dynamic sub-information and the second dynamic sub-information are added together to obtain dynamic riding data, and the dynamic riding data is calculated by the following formula: in, For dynamic riding data, is the number of passengers on board, is the passenger weight coefficient, For the The first quality coefficient of the passenger information, is the upper limit of the number of passengers on board, is the weight value of the first quality coefficient, is the normalized value of passengers, is the number of baggage sections with bags, is the weight coefficient of the baggage interval, For the The second mass coefficient in the baggage section, is the upper limit of the number of baggage sections, is the weight coefficient of the baggage interval, is the baggage normalization value; The determining of characteristic diagnostic data corresponding to the associated carriage based on the dynamic riding data, obtaining a differentiated interval of the characteristic diagnostic data based on a difference between the dynamic riding data, and determining an output display of the associated carriage that does not meet the requirements based on the differentiated interval, includes: Based on the dynamic riding data, all carriages are sorted in descending order to obtain a carriage descending sequence, and the dynamic riding data of each carriage in the carriage descending sequence is traversed in turn to determine the closest dynamic riding data. The two characteristic diagnosis data corresponding to the dynamic riding data of the traversed car and the closest dynamic riding data are used as the characteristic diagnosis data corresponding to the associated car; Calculating the difference in the dynamic riding data to obtain a differentiated riding value, and obtaining a standard data difference between the characteristic diagnostic data corresponding to the associated vehicle compartments based on the differentiated riding value; Calculate the diagnostic data difference of the information feature data of each dimension, if the diagnostic data difference is less than or equal to the standard data difference, the associated car meets the requirements, if the diagnostic data difference is greater than the standard data difference, the associated car does not meet the requirements; The calculating of the difference in the dynamic riding data to obtain a differentiated riding value, and obtaining a standard data difference between characteristic diagnostic data corresponding to the associated carriages based on the differentiated riding value, comprises: Acquire information feature data of each dimension in each feature diagnostic data and a corresponding feature weight, wherein the information feature data at least includes rail vibration data and rail temperature data; The standard data difference is calculated based on the differentiated occupancy values ​​of the associated carriages and the feature weights of the information feature data of each dimension. The standard data difference is calculated using the following formula: in, For the The standard deviation of the dimensions, is the dynamic riding data of the first car in the two associated cars, The dynamic riding data of the second car in the two associated cars, For the The feature weight of each dimension.

2. The method for monitoring the running status of a high-speed train according to claim 1, characterized in that: In response to the status monitoring instruction, the basic attributes of the vehicle body uploaded by the management end are received, and the standard operation model is obtained based on the basic attributes of the vehicle body, including: In response to the status monitoring instruction, calling the attribute editing interface, and obtaining the basic attributes of the body of the high-speed train based on the attribute editing interface; Retrieving a vehicle body basic model and basic configuration data based on the basic attributes of the vehicle body, wherein the basic configuration data includes target monitoring component features; Call the standard operation record table, extract data from the standard operation record table according to the characteristics of the target monitoring component, obtain standard operation data corresponding to each target monitoring component, update the vehicle body basic model based on the standard operation data, and obtain a standard operation model.

3. The method for monitoring the running status of a high-speed train according to claim 1, characterized in that: The standard operation model is updated based on characteristic diagnostic data of different carriages to obtain a customized diagnostic model, and the standard operation model is compared with the customized diagnostic model to obtain a first operation deviation data set, including: Combining the bearing characteristic diagnosis data, the wheel characteristic diagnosis data and the rail characteristic diagnosis data of different carriages to obtain a characteristic diagnosis data set; Extracting the corresponding target synchronous operation data in the standard operation model based on the characteristic diagnosis data set, and generating a target update data set according to the plurality of target synchronous operation data; Based on each characteristic diagnosis data of the characteristic diagnosis data set, each target synchronous operation data of the standard operation model is updated one by one to obtain a customized diagnosis model; The customized diagnostic model is compared with the operating status data corresponding to each target monitoring component in the standard operating model to obtain a first operating deviation data set.

Images