Rail vehicle wheel diameter difference detection method, device, train, equipment and medium

Abstract

The present disclosure provides a method, apparatus, train, equipment, and medium for detecting wheel diameter differences of rail vehicles, which can be applied to the field of rail transportation technology. The method comprises: in response to receiving a signal indicating that the travel speed of a target rail vehicle is greater than a predetermined speed threshold, obtaining pulse signals of multiple wheels of the target rail vehicle in a t-th time period and first wheel diameter information of multiple wheels in a t-1th time period, where t is an integer greater than 1; processing the pulse signal of each wheel to generate a wheel diameter deviation index for each wheel; generating second wheel diameter information for each wheel in the t-th time period based on the wheel diameter deviation index of each wheel and the first wheel diameter information of each wheel; and generating wheel diameter difference information for multiple wheels in the t-th time period based on the second wheel diameter information of each wheel.

Description

Technical Field

[0001] The present disclosure relates to the field of rail transit technology, and in particular to a method, device, train, equipment and medium for detecting wheel diameter differences of rail vehicles. Background Art

[0002] As railways develop towards high-speed, heavy-load, and intensive transportation, the increased speeds and loads lead to increased wheel-rail forces, posing a high risk of abnormal wheel wear, which can impact the safety and smoothness of train operation. Wheel diameter variation is an indicator of wheel health. If the diameter variation between wheels on the same train, vehicle, or bogie exceeds the specified limit, it can affect train traction and braking control, reducing the safety and smoothness of train operation.

[0003] In the process of realizing the concept of the present disclosure, the inventors found that the related art mainly measures the wheel diameter difference by relying on regular measurements of ground equipment, which cannot achieve real-time detection, resulting in low detection efficiency, which in turn affects the safety and stability of train operation. Summary of the Invention

[0004] In view of the above problems, the present disclosure provides a method, device, train, equipment and medium for detecting wheel diameter differences of rail vehicles.

[0005] According to a first aspect of the present disclosure, a method for detecting wheel diameter differences of rail vehicles is provided, comprising: in response to receiving a signal that a traveling speed of a target rail vehicle is greater than a predetermined speed threshold, obtaining pulse signals of multiple wheels of the target rail vehicle in a t-th time period and first wheel diameter information of the multiple wheels in a t-1-th time period, where t is an integer greater than 1; processing the pulse signal of each wheel to generate a wheel diameter deviation index of each wheel; generating second wheel diameter information of each wheel in a t-th time period based on the wheel diameter deviation index of each wheel and the first wheel diameter information of each wheel; and generating wheel diameter difference information of the multiple wheels in a t-th time period based on the second wheel diameter information of each wheel.

[0006] According to an embodiment of the present disclosure, the above-mentioned processing of the pulse signal of each wheel to generate the wheel diameter deviation index of each wheel includes: generating the number of pulses of each wheel according to the changing trend of the pulse signal of each wheel; generating the average number of pulses of the above-mentioned multiple wheels according to each of the above-mentioned pulse numbers; and generating the wheel diameter deviation index of each wheel according to each of the above-mentioned pulse numbers and the above-mentioned average number of pulses.

[0007] According to an embodiment of the present disclosure, the above-mentioned t-th time period includes N collection moments, where N is an integer greater than 1; the above-mentioned generation of the number of pulses of each wheel based on the changing trend of the pulse signal of each wheel includes: in response to the i pulse signals before the n-th sampling moment being less than a first predetermined threshold, and the i-1 pulse signals after the above-mentioned n-th sampling moment being greater than a second predetermined threshold, determining that the pulse signal at the above-mentioned n-th sampling moment is the first pulse turning position of an upward trend, wherein 1<i<n≤N; and counting the number of the above-mentioned first pulse turning positions of each wheel in the above-mentioned t-th time period to generate the number of pulses of the above-mentioned wheels.

[0008] According to an embodiment of the present disclosure, the above-mentioned t-th time period includes N collection moments, where N is an integer greater than 1; the above-mentioned generation of the number of pulses of each wheel based on the changing trend of the pulse signal of each wheel includes: in response to the j pulse signals before the n-th sampling moment being greater than the second predetermined threshold, and the j-1 pulse signals after the above-mentioned n-th sampling moment being less than the first predetermined threshold, determining that the pulse signal at the above-mentioned n-th sampling moment is the second pulse turning position of the downward trend, wherein 1<j<n≤N; and counting the number of the above-mentioned second pulse turning positions of each wheel in the above-mentioned t-th time period to generate the above-mentioned number of pulses of each wheel.

[0009] According to an embodiment of the present disclosure, the above-mentioned changing trend includes an upward trend and a downward trend; the above-mentioned generating the number of pulses of each wheel according to the changing trend of the pulse signal of each wheel also includes: obtaining the number of first pulse turning positions of each wheel corresponding to the above-mentioned upward trend and the number of second pulse turning positions corresponding to the above-mentioned downward trend; and generating the number of pulses of each wheel according to the number of each of the above-mentioned first pulse turning positions and the number of each of the above-mentioned second pulse turning positions.

[0010] According to an embodiment of the present disclosure, the above-mentioned t-th time period includes Q sampling periods, where Q is an integer greater than 1; the above-mentioned second wheel diameter information of each wheel in the t-th time period is generated based on the above-mentioned wheel diameter deviation index of each wheel and the above-mentioned first wheel diameter information of each wheel, including: for the wheel diameter deviation index of each wheel in the Q sampling periods, calculating the wheel diameter deviation index error corresponding to each period; in response to the wheel diameter deviation index error of the q-th sampling period being less than a predetermined error threshold, determining that the wheel diameter deviation index of the q-th sampling period is the target wheel diameter deviation index; and generating the second wheel diameter information of each wheel in the t-th time period based on the above-mentioned target wheel diameter deviation index of each wheel and the above-mentioned first wheel diameter information of each wheel.

[0011] According to an embodiment of the present disclosure, the wheel diameter difference information of the above-mentioned multiple wheels in the t-1 period is generated based on the above-mentioned second wheel diameter information of each wheel, including: extracting the above-mentioned second wheel diameter information of at least two target wheels from the above-mentioned second wheel diameter information of each wheel, wherein the positional relationship between the above-mentioned at least two target wheels includes at least one of the following: being located on the same bogie of the above-mentioned target rail vehicle and being located on the same car of the above-mentioned target rail vehicle; generating the above-mentioned wheel diameter difference information based on the above-mentioned second wheel diameter information of the above-mentioned at least two target wheels.

[0012] According to an embodiment of the present disclosure, the above-mentioned rail vehicle wheel diameter difference detection method also includes: in response to the above-mentioned wheel diameter difference information exceeding a predetermined difference threshold, recording wheel diameter difference abnormality information; and in response to the number of the above-mentioned wheel diameter difference abnormality information exceeding a predetermined abnormality threshold, generating wheel diameter abnormality alarm information.

[0013] According to an embodiment of the present disclosure, the above-mentioned rail vehicle wheel diameter difference detection method also includes: obtaining historical wheel diameter difference information of the above-mentioned multiple wheels in the previous t-1 period and the operating parameter information of the above-mentioned target rail vehicle; and inputting the above-mentioned historical wheel diameter difference information, the above-mentioned operating parameter information and the wheel diameter difference information of the above-mentioned multiple wheels in the above-mentioned t-th period into a first target model, and outputting the wheel diameter difference prediction information of the above-mentioned multiple wheels in the t+1-th period; wherein the above-mentioned first target model is trained using the sample historical wheel diameter difference information within a predetermined historical period and the operating parameter information of the above-mentioned target rail vehicle.

[0014] According to an embodiment of the present disclosure, the above-mentioned rail vehicle wheel diameter difference detection method also includes: obtaining the historical wheel diameter information of the above-mentioned multiple wheels in the previous t-2 period and the operating parameter information of the above-mentioned target rail vehicle; and inputting the above-mentioned historical wheel diameter information and the above-mentioned operating parameter information into a second target model, and outputting the first wheel diameter information of the above-mentioned multiple wheels in the t-1 period; wherein the above-mentioned second target model is trained using the sample historical wheel diameter information within a predetermined historical period and the operating parameter information of the above-mentioned target rail vehicle.

[0015] A second aspect of the present disclosure provides a rail vehicle wheel diameter difference detection device, comprising: a first acquisition module, a processing module, a first generation module, and a second generation module.

[0016] a first acquisition module configured to acquire, in response to receiving a signal indicating that a traveling speed of a target rail vehicle is greater than a predetermined speed threshold, pulse signals of a plurality of wheels of the target rail vehicle within a t-th time period and first wheel diameter information of the plurality of wheels within the t-th time period, where t is an integer greater than 1;

[0017] A processing module, used to process the pulse signal of each wheel and generate a wheel diameter deviation index of each wheel;

[0018] a first generating module, configured to generate second wheel diameter information of each wheel in a t-th time period based on the wheel diameter deviation index of each wheel and the first wheel diameter information of each wheel; and

[0019] The second generating module is configured to generate wheel diameter difference information of the plurality of wheels in the t-1 period according to the second wheel diameter information of each wheel.

[0020] A third aspect of the present disclosure provides a train, comprising: a rail vehicle wheel diameter difference detection device configured on the above-mentioned train.

[0021] A fourth aspect of the present disclosure provides an electronic device, comprising: a storage device for storing one or more programs, wherein when the one or more programs are executed by one or more processors, the one or more processors execute the above-mentioned rail vehicle wheel diameter difference detection method.

[0022] A fifth aspect of the present disclosure further provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to execute the above-mentioned rail vehicle wheel diameter difference detection method.

[0023] A sixth aspect of the present disclosure further provides a computer program product, comprising a computer program, which implements the above-mentioned rail vehicle wheel diameter difference detection method when executed by a processor.

[0024] According to the rail vehicle wheel diameter difference detection method, device, train, equipment, medium and product provided by the present invention, during the operation of the target rail vehicle and when the operating speed is greater than a predetermined speed threshold, the wheel diameter deviation index of each wheel can be generated by processing the collected wheel pulse signal, and based on the wheel diameter deviation index of each wheel and the first wheel diameter information of multiple wheels in the t-1 period, the second wheel diameter information of each wheel in the t period can be generated, and then the wheel diameter difference information of multiple wheels in the t period is generated, thereby realizing real-time detection of the wheel diameter difference information of the wheels during the operation of the target rail vehicle, improving the detection efficiency, and thus improving the safety and stability of the train operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The above contents and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0026] Figure 1 A diagram schematically illustrates an application scenario of a method for detecting wheel diameter differences of rail vehicles according to an embodiment of the present disclosure;

[0027] Figure 2 The flowchart of the method for detecting wheel diameter differences of rail vehicles according to an embodiment of the present disclosure is schematically shown;

[0028] Figure 3 The following schematically shows an architecture diagram of a method for detecting wheel diameter differences of rail vehicles according to another embodiment of the present disclosure;

[0029] Figure 4 A schematic diagram schematically illustrates a pulse signal according to an embodiment of the present disclosure;

[0030] Figure 5 A schematic diagram illustrating an architecture for predicting wheel diameter difference information according to an embodiment of the present disclosure is shown;

[0031] Figure 6 Schematically shows an architecture diagram for predicting wheel diameter difference information according to another embodiment of the present disclosure;

[0032] Figure 7 A schematic block diagram of a device for detecting wheel diameter differences of rail vehicles according to an embodiment of the present disclosure is shown; and

[0033] Figure 8 A block diagram of an electronic device suitable for implementing a method for detecting wheel diameter differences of rail vehicles according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0034] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present disclosure. In the detailed description below, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0035] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise," "include," etc. used herein indicate the presence of the features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0036] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0037] When expressions such as "at least one of A, B, and C, etc." are used, they should generally be interpreted in accordance with the meaning commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0038] In the technical solutions disclosed herein, the user information (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0039] During the implementation of this disclosure, it was discovered that related technologies primarily measure wheel diameter differences through periodic measurements. For example, a train passes at low speed over a sensor-equipped track, where the sensors collect and detect wheel geometry and calculate wheel diameter differences. Alternatively, during vehicle maintenance, the train measures various parameters, such as diameter and roughness, using a specific wheel measuring device to calculate wheel diameter differences. However, these measurement methods cannot achieve real-time detection of wheel diameter differences and rely solely on periodic testing by ground-based equipment, resulting in low detection efficiency and, in turn, impacting the safety and stability of train operation.

[0040] In view of this, an embodiment of the present disclosure provides a method for detecting wheel diameter differences of rail vehicles, comprising: in response to receiving a signal that a traveling speed of a target rail vehicle is greater than a predetermined speed threshold, obtaining pulse signals of multiple wheels of the target rail vehicle in the tth time period and first wheel diameter information of multiple wheels in the t-1th time period, where t is an integer greater than 1; processing the pulse signal of each wheel to generate a wheel diameter deviation index of each wheel; generating second wheel diameter information of each wheel in the tth time period based on the wheel diameter deviation index of each wheel and the first wheel diameter information of each wheel; and generating wheel diameter difference information of multiple wheels in the tth time period based on the second wheel diameter information of each wheel.

[0041] Figure 1 The following schematically shows an application scenario diagram of the rail vehicle wheel diameter difference detection method according to an embodiment of the present disclosure.

[0042] like Figure 1 As shown, the application scenario 100 according to this embodiment may include a target rail vehicle 101 , a network 102 and a server 103 .

[0043] Network 102 is a medium used to provide a communication link between the target rail vehicle 101 and the server 103. Network 102 primarily comprises the train network system, responsible for transmitting data collected by the wheel speed sensors to the data analysis module of server 103. This data transmission can utilize the existing train network system or establish a dedicated fault diagnosis network. Network 102 can include various connection types, such as wired or wireless communication links or fiber optic cables. For example, data transmission can be carried out via wired transmission (such as RS232 or Ethernet) or wireless transmission (such as wireless Wi-Fi).

[0044] Target rail vehicle 101 interacts with server 103 via network 102 to receive or send messages, etc. Each wheel of target rail vehicle 101 is equipped with a data acquisition module, which primarily comprises a wheel speed sensor and a preprocessor. The wheel speed sensor is used to collect pulse signals, and the preprocessor is used to preprocess these pulse signals. Each vehicle must collect at least three independently rotating pulse signals, and each wheelset must be equipped with at least one wheel speed sensor. Real-time data enters the preprocessor, which performs data cleaning and digital-to-analog conversion. The digital signal is then transmitted via the network to the data analysis module in server 103.

[0045] Server 103 can be a server that provides various services. The data analysis module in server 103 primarily includes a vehicle-level data processor and a train-level data processor, responsible for analyzing and processing data collected by wheel speed sensors to detect and predict wheel diameter differences. Furthermore, the data analysis module includes data storage, responsible for centrally storing data processed by the train network system or preprocessor. This storage can be set up in vehicle-level and train-level memory, respectively. This stored historical data can be accessed and analyzed by the data processing module.

[0046] Server 103 may also include a results display module, primarily comprising a results display, which displays the analysis results of the data analysis module in server 103 and provides guidance to train operators. The results display module uses an interactive human-machine interface to visually display the wheel diameter difference information for multiple wheels in time period t and the predicted wheel diameter difference information for multiple wheels in time period t+1. It also allows for detailed parameter viewing and historical parameter review as needed.

[0047] It should be noted that the rail vehicle wheel diameter difference detection method provided in the embodiment of the present disclosure can generally be executed by the server 103. Accordingly, the rail vehicle wheel diameter difference detection device provided in the embodiment of the present disclosure can generally be set in the server 103. The rail vehicle wheel diameter difference detection method provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 103 and can communicate with the target rail vehicle 101 and / or the server 103. Accordingly, the rail vehicle wheel diameter difference detection device provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 103 and can communicate with the target rail vehicle 101 and / or the server 103.

[0048] It should be understood that Figure 1 The numbers of rail vehicles, networks, and servers shown in the figure are merely illustrative. Any number of rail vehicles, networks, and servers may be used depending on the implementation requirements.

[0049] The following will be based on Figure 1 The scene described by Figures 2 to 6 The method for detecting wheel diameter differences of rail vehicles according to an embodiment of the present disclosure is described in detail.

[0050] Figure 2 The flowchart of the method for detecting wheel diameter differences of rail vehicles according to an embodiment of the present disclosure is schematically shown.

[0051] like Figure 2 As shown, the rail vehicle wheel diameter difference detection method 200 of this embodiment includes operations S210 to S240.

[0052] In operation S210, in response to receiving that the running speed of the target rail vehicle is greater than a predetermined speed threshold, pulse signals of multiple wheels of the target rail vehicle in the tth time period and first wheel diameter information of multiple wheels in the t-1th time period are obtained, where t is an integer greater than 1.

[0053] In operation S220 , the pulse signal of each wheel is processed to generate a wheel diameter deviation index of each wheel.

[0054] In operation S230 , second wheel diameter information of each wheel in the t-th time period is generated based on the wheel diameter deviation index of each wheel and the first wheel diameter information of each wheel.

[0055] In operation S240 , wheel diameter difference information of the plurality of wheels in the t-th time period is generated based on the second wheel diameter information of each wheel.

[0056] According to an embodiment of the present disclosure, the target rail vehicle may be a rail train, which may include a plurality of carriages, and each carriage may include a plurality of wheels.

[0057] According to an embodiment of the present disclosure, the predetermined speed threshold may represent the minimum speed at which the wheel speed sensor can collect wheel pulse signals during the travel of the target rail vehicle. For example, if the predetermined speed threshold is 10 km / h, then when the speed of the target rail vehicle is greater than or equal to 10 km / h, such as when the speed of the target rail vehicle is 30 km / h, the wheel speed sensor can collect wheel pulse signals of the target rail vehicle.

[0058] According to an embodiment of the present disclosure, one wheel may be equipped with one wheel speed sensor or multiple wheel speed sensors. The wheel speed sensor of the target rail vehicle may collect multiple pulse signals within a period of time.

[0059] According to an embodiment of the present disclosure, the first wheel diameter information of multiple wheels in the t-1 period can represent the diameter information of the wheels of the target rail vehicle in the t-1 period collected when the target rail vehicle is stationary, or it can represent the diameter information of the wheels of the target rail vehicle in the t-1 period collected in real time when the target rail vehicle is in motion.

[0060] According to an embodiment of the present disclosure, the wheel diameter deviation index can represent the ratio of the number of pulses of the wheel within a fixed sampling time to the wheel diameter. By processing the pulse signal of each wheel, the wheel diameter deviation index of each wheel can be generated.

[0061] According to an embodiment of the present disclosure, the second wheel diameter information may represent the diameter information of the wheel in the tth period. The second wheel diameter information of each wheel in the tth period may be generated based on the wheel diameter deviation index of each wheel and the first wheel diameter information of each wheel.

[0062] According to an embodiment of the present disclosure, the wheel diameter difference information may represent diameter difference information of a plurality of wheels. The wheel diameter difference information of the plurality of wheels in the tth time period may be generated based on the second wheel diameter information of each wheel.

[0063] According to an embodiment of the present disclosure, wheel diameter difference information of multiple wheels can be generated by calculating wheel diameter difference information of multiple wheels of the same car, wheel diameter difference information of multiple wheels of the same bogie, or wheel diameter difference information of multiple wheels of the same target rail vehicle.

[0064] According to an embodiment of the present disclosure, during the operation of the target rail vehicle and when the operating speed is greater than a predetermined speed threshold, the wheel diameter deviation index of each wheel can be generated by processing the collected wheel pulse signals, and based on the wheel diameter deviation index of each wheel and the first wheel diameter information of multiple wheels in the t-1 period, the second wheel diameter information of each wheel in the t period can be generated, and then the wheel diameter difference information of multiple wheels in the t period can be generated, thereby realizing real-time detection of the wheel diameter difference information of the wheels during the operation of the target rail vehicle, improving the detection efficiency, and thus improving the safety and stability of the operation of the target rail vehicle.

[0065] According to the embodiment of the present disclosure, the historical wheel diameter difference information of multiple wheels in the t-1 period can be actually measured when the target rail vehicle is stationary, or it can be predicted in the t-2 period. Figure 3 An implementation method in which the historical wheel diameter difference information of the plurality of wheels in the t-1 period is actually measured when the target rail vehicle is in a stationary state is described in detail.

[0066] Figure 3 The following schematically shows an architecture diagram of a method for detecting wheel diameter differences of rail vehicles according to an embodiment of the present disclosure.

[0067] like Figure 3 As shown, when the running speed of the target rail vehicle is greater than the predetermined speed threshold, the pulse signals 311 of multiple wheels of the target rail vehicle in the t-th time period and the first wheel diameter information 312 of multiple wheels in the t-1th time period measured when the target rail vehicle is stationary can be obtained. By processing the pulse signals of each wheel, the wheel diameter deviation index 313 of each wheel can be generated. According to the wheel diameter deviation index 313 of each wheel and the first wheel diameter information 312 of each wheel, the second wheel diameter information 314 of each wheel in the t-th time period can be generated. Then, according to the second wheel diameter information 314 of each wheel in the t-th time period, the wheel diameter difference information 315 of multiple wheels in the t-th time period can be generated.

[0068] According to an embodiment of the present disclosure, the first wheel diameter information of the multiple wheels acquired in the t-1th time period is obtained by measuring the first wheel diameter information of the multiple wheels of the target rail vehicle based on sensors installed on the track when the target rail vehicle is stationary.

[0069] According to an embodiment of the present disclosure, the pulse signal of each wheel is processed to generate a wheel diameter deviation index of each wheel, including: generating the number of pulses of each wheel according to the changing trend of the pulse signal of each wheel; generating the average number of pulses of multiple wheels according to each pulse number; and generating the wheel diameter deviation index of each wheel according to each pulse number and the average pulse number.

[0070] According to an embodiment of the present disclosure, the wheel pulses are square waves with both rising and falling trends. The number of wheel pulses can be generated based on the changing trend of the pulse signal of each wheel. If a wheel speed sensor is installed on each wheel, the number of pulses for each wheel can be calculated by counting the number of pulses collected by the wheel speed sensor. If multiple wheel speed sensors are installed on each wheel, the number of pulses for each wheel can be calculated by calculating the sum of the number of pulses collected by each wheel speed sensor and the ratio of the number of wheel speed sensors.

[0071] According to an embodiment of the present disclosure, an average pulse number of multiple wheels may be generated based on the number of pulses. That is, the average pulse number of multiple wheels may be obtained by adding and averaging the pulse numbers of the respective wheels.

[0072] According to an embodiment of the present disclosure, a wheel diameter deviation index for each wheel can be generated based on the ratio of each pulse number to the average pulse number. For example, the pulse numbers of four wheels are L1, L2, L3, and L4, respectively, and the average pulse number Lnom = (L1 + L2 + L3 + L4) / 4. By calculating the ratio of the pulse number of each wheel to the average pulse number Lnom, the wheel diameter deviation index for each wheel can be generated. For example, the wheel diameter deviation index of the first wheel can be L1 / Lnom, the wheel diameter deviation index of the second wheel can be L2 / Lnom, the wheel diameter deviation index of the third wheel can be L3 / Lnom, and the wheel diameter deviation index of the fourth wheel can be L4 / Lnom.

[0073] According to an embodiment of the present disclosure, the number of pulses of each wheel can be generated according to the changing trend of the pulse signal of each wheel, so that the average number of pulses of multiple wheels can be calculated, and the wheel diameter deviation index of each wheel can be generated according to the ratio of each pulse number to the average pulse number, thereby improving the accuracy of the generated wheel diameter deviation index.

[0074] Figure 4 A schematic diagram of a pulse signal according to an embodiment of the present disclosure is schematically shown.

[0075] like Figure 4 Figure 2 shows a pulse signal diagram of a wheel speed sensor outputting a voltage signal, including a first predetermined threshold and a second predetermined threshold, where the second predetermined threshold is greater than the first predetermined threshold. The wheel speed sensor output voltage signal has voltage values ​​at multiple sampling moments that are all less than the first predetermined threshold or greater than the second predetermined threshold.

[0076] According to an embodiment of the present disclosure, the variation trend of the pulse signal may include an upward trend and a downward trend. The number of pulses of each wheel may be generated according to the variation trend of the pulse signal of each wheel.

[0077] For example, in response to the i pulse signals before the nth sampling moment being less than a first predetermined threshold and the i-1 pulse signals after the nth sampling moment being greater than a second predetermined threshold, the pulse signal at the nth sampling moment is determined to be the first pulse turning position of an upward trend; and the number of first pulse turning positions of each wheel in the tth time period is counted to generate the number of pulses of each wheel.

[0078] According to an embodiment of the present disclosure, the pulse signal can be a voltage signal or a current signal, and the wheel speed sensor can output a high voltage signal / high current signal and a low voltage signal / low current signal of distinguishable size. Taking the voltage signal output by the wheel speed sensor as an example, a first predetermined threshold and a second predetermined threshold can be set through statistical analysis of the high voltage signal and the low voltage signal output by the wheel speed sensor. When the second predetermined threshold is greater than the first predetermined threshold, all high voltage signals are higher than the second predetermined threshold, and all low voltage signals are lower than the first predetermined threshold.

[0079] According to an embodiment of the present disclosure, the t-th time period may include N acquisition moments, where N is an integer greater than 1, and 1<i<n≤N.

[0080] like Figure 4 As shown, in response to the three pulse signals before the 4th sampling moment being less than the first predetermined threshold, and the three pulse signals after the 4th sampling moment being greater than the second predetermined threshold, it can be determined that the pulse signal at the 4th sampling moment undergoes a large change, that is, changes from less than the first predetermined threshold to greater than the second predetermined threshold, and the pulse signal has an upward trend, so that the pulse signal at the 4th sampling moment can be determined to be the first pulse turning position of the upward trend.

[0081] According to an embodiment of the present disclosure, the number of first pulse turning points for each wheel during time period t can be counted to generate the pulse count for each wheel. If a wheel is equipped with a single wheel speed sensor during time period t, the wheel pulse count can be directly counted. For example, if the number of first pulse turning points for a wheel is NN, the wheel pulse count is NN. If a wheel is equipped with multiple wheel speed sensors during time period t, the wheel pulse count can be calculated by summing and averaging the pulse counts of each wheel speed sensor. For example, if the first pulse turning points for three wheel speed sensors are NN1, NN2, and NN3, the wheel pulse count is NN = (NN1 + NN2 + NN3) / 3.

[0082] According to the embodiment of the present disclosure, the number of pulses for each wheel can be generated according to the number of first pulse turning positions of the rising trend, thereby improving the flexibility of generating the number of pulses for each wheel.

[0083] For another example, in response to the j pulse signals before the nth sampling moment being greater than the second predetermined threshold and the j-1 pulse signals after the nth sampling moment being less than the first predetermined threshold, the pulse signal at the nth sampling moment is determined to be the second pulse turning position of the downward trend; and the number of the second pulse turning positions of each wheel in the tth time period is counted to generate the number of pulses of each wheel.

[0084] According to an embodiment of the present disclosure, the t-th time period includes N acquisition moments, where N is an integer greater than 1, and 1<j<n≤N.

[0085] like Figure 4 As shown, in response to the four pulse signals before the 8th sampling moment being greater than the second predetermined threshold, and the three pulse signals after the 8th sampling moment being less than the first predetermined threshold, it can be determined that the pulse signal undergoes a large change at the 8th sampling moment, that is, changes from greater than the second predetermined threshold to less than the first predetermined threshold, and the pulse signal has a downward trend, so that the pulse signal at the 8th sampling moment can be determined to be the second pulse turning position of the downward trend.

[0086] According to an embodiment of the present disclosure, the number of second pulse turning points for each wheel during time period t is counted to generate the pulse count for each wheel. If a wheel is equipped with a single wheel speed sensor during time period t, the wheel pulse count can be directly calculated. For example, if the number of second pulse turning points for a wheel is MM, the wheel pulse count is MM. If a wheel is equipped with multiple wheel speed sensors during time period t, the wheel pulse count can be calculated by summing and averaging the pulse counts of each wheel speed sensor. For example, if the number of second pulse turning points for three wheel speed sensors is MM1, MM2, and MM3, the wheel pulse count is MM = (MM1 + MM2 + MM3) / 3.

[0087] According to the embodiment of the present disclosure, the number of pulses for each wheel can be generated according to the number of second pulse turning positions of the downward trend, thereby improving the flexibility of generating the number of pulses for each wheel.

[0088] For another example, the number of first pulse turning positions corresponding to the upward trend and the number of second pulse turning positions corresponding to the downward trend of each wheel are obtained; and the number of pulses of each wheel is generated based on the number of each first pulse turning position and the number of each second pulse turning position.

[0089] According to an embodiment of the present disclosure, the number of first pulse turning positions corresponding to an upward trend for each wheel can be obtained by counting the number of first pulse turning positions at which the pulse signal at the nth sampling moment shows an upward trend. The number of second pulse turning positions corresponding to a downward trend can be obtained by counting the number of second pulse turning positions at which the pulse signal at the nth sampling moment shows a downward trend.

[0090] According to an embodiment of the present disclosure, the number of pulses of each wheel can be generated by averaging the number of first pulse turning positions and the number of second pulse turning positions. Figure 4 As shown, the number NN of the first pulse turning positions of a wheel is 1, and the number MM of the second pulse turning positions is 1, then the number of pulses of the wheel is L=(1+1) / 2.

[0091] According to an embodiment of the present disclosure, the accuracy of the number of pulses generated for each wheel can be improved based on the number of first pulse turning positions and the number of second pulse turning positions, and the flexibility of generating the number of pulses for each wheel can be further improved.

[0092] According to an embodiment of the present disclosure, the second wheel diameter information of each wheel in the t-th time period is generated based on the wheel diameter deviation index of each wheel and the first wheel diameter information of each wheel, including: for the wheel diameter deviation index of each wheel within Q sampling periods, calculating the wheel diameter deviation index error corresponding to each period; in response to the wheel diameter deviation index error of the q-th sampling period being less than a predetermined error threshold, determining the wheel diameter deviation index of the q-th sampling period as the target wheel diameter deviation index; and generating the second wheel diameter information of each wheel in the t-th time period based on the target wheel diameter deviation index of each wheel and the first wheel diameter information of each wheel.

[0093] According to an embodiment of the present disclosure, the tth time period may include Q sampling periods, where Q is an integer greater than 1. For example, the tth time period may include 10 sampling periods.

[0094] According to an embodiment of the present disclosure, the wheel diameter deviation in the qth sampling period can represent the average of multiple wheel diameter deviation indices in the sampling period. For each wheel's wheel diameter deviation index in Q sampling periods, the wheel diameter deviation index error corresponding to each period can be obtained.

[0095] According to an embodiment of the present disclosure, the predetermined error threshold can be set based on experience, for example, the predetermined error threshold can be 0.2%. If the wheel diameter deviation index error of the qth sampling period is less than the predetermined error threshold, the wheel diameter deviation index of the qth sampling period can be determined as the target wheel diameter deviation index.

[0096] According to an embodiment of the present disclosure, if the errors of multiple wheel diameter deviation indices in a sampling period are all less than a predetermined error threshold, the multiple wheel diameter deviation indices in the sampling period can be determined to be valid, and a wheel diameter deviation index exists in the sampling period. If at least one of the errors of multiple wheel diameter deviation indices in a sampling period is not less than the predetermined error threshold, the multiple wheel diameter deviation indices in the sampling period can be determined to be invalid, and no wheel diameter deviation index exists in the sampling period.

[0097] For example, in the qth sampling period, the wheel diameter deviation index errors of the p wheels can be determined by calculating the average of the wheel diameter deviation indices of the p wheels and combining them with the wheel diameter deviation indices of the p wheels. When the wheel diameter deviation index errors of the p wheels are all less than a predetermined error threshold, it can be determined that the multiple wheel diameter deviation indices of the sampling period are valid, and the wheel diameter deviation index of the qth sampling period can be determined as the target wheel diameter deviation index.

[0098] According to an embodiment of the present disclosure, the second wheel diameter information of each wheel in the t-th time period may be generated according to the target wheel diameter deviation index of each wheel and the first wheel diameter information of each wheel.

[0099] According to an embodiment of the present disclosure, by comparing the calculated relationship between the wheel diameter deviation index error corresponding to each period and a predetermined error threshold, if the wheel diameter deviation index error in the qth sampling period is less than the predetermined error threshold, the wheel diameter deviation index of the qth sampling period is determined to be the target wheel diameter deviation index, and then based on the target wheel diameter deviation index of each wheel and the first wheel diameter information of each wheel, the second wheel diameter information of each wheel in the tth time period can be generated, and the real-time second wheel diameter information of each wheel in the tth time period can be obtained, and the accuracy of the obtained second wheel diameter information of each wheel in the tth time period is improved.

[0100] According to an embodiment of the present disclosure, wheel diameter difference information of multiple wheels in the tth time period is generated based on the second wheel diameter information of each wheel, including: extracting the second wheel diameter information of at least two target wheels from the second wheel diameter information of each wheel; generating wheel diameter difference information based on the second wheel diameter information of at least two target wheels.

[0101] According to an embodiment of the present disclosure, the positional relationship between the at least two target wheels includes at least one of the following: being located on the same bogie of the target rail vehicle and being located on the same car of the target rail vehicle. In other words, the target wheels may be located on the same bogie of the target rail vehicle or on the same car of the target rail vehicle. Alternatively, the positional relationship between the at least two target wheels may further include being located on the same target rail vehicle.

[0102] According to an embodiment of the present disclosure, the second wheel diameter information of each wheel is obtained according to the product of the wheel diameter deviation index of each wheel and the first wheel diameter information of each wheel.

[0103] According to an embodiment of the present disclosure, the second wheel diameter information of at least two target wheels can be extracted from the second wheel diameter information of each wheel, and wheel diameter difference information can be generated based on the second wheel diameter information of at least two target wheels. For example, in the case where the second wheel diameter information of two target wheels is included on a bogie, the maximum and minimum values ​​of the second path difference information of the two target wheels are determined, and the wheel diameter difference information of the same bogie can be generated based on the maximum and minimum values ​​of the second path difference information of the two target wheels. Similarly, in the case where the second wheel diameter information of six target wheels is included on the same carriage, the maximum and minimum values ​​of the second path difference information of the six target wheels are determined, and the wheel diameter difference information of the same carriage can be generated based on the maximum and minimum values ​​of the second path difference information of the six target wheels.

[0104] According to an embodiment of the present disclosure, by extracting the second wheel diameter information of at least two target wheels from the second wheel diameter information of each wheel, the maximum and minimum values ​​can be determined from the extracted second wheel diameter information, thereby generating wheel diameter difference information under a variety of target wheel position relationships, thereby improving the diversity and accuracy of the wheel diameter difference information.

[0105] According to an embodiment of the present disclosure, the above-mentioned rail vehicle wheel diameter difference detection method also includes: recording wheel diameter difference abnormality information in response to the wheel diameter difference information exceeding a predetermined difference threshold; and generating wheel diameter abnormality alarm information in response to the number of wheel diameter difference abnormality information exceeding a predetermined abnormality threshold.

[0106] According to an embodiment of the present disclosure, the predetermined difference threshold can be set based on experience, and different predetermined difference thresholds can be set for the positional relationships between at least two target wheels. For example, the predetermined difference threshold of the same bogie can be set to DPbog-set, the predetermined difference threshold of the same carriage can be set to DPcoa-set, and the predetermined difference threshold of the same target rail vehicle can be set to DPtri-set.

[0107] According to an embodiment of the present disclosure, the predetermined abnormality threshold may represent the minimum number of times that wheel diameter difference information exceeds the predetermined difference threshold. For example, the predetermined abnormality threshold may be set to 10, and if the number of recorded wheel diameter difference abnormality information exceeds 10 times, a wheel diameter abnormality alarm message may be generated.

[0108] According to an embodiment of the present disclosure, a predetermined difference threshold can be set. When the wheel diameter abnormality information exceeds the predetermined difference threshold, the wheel diameter difference abnormality information is recorded, and when the number of wheel diameter abnormality information is greater than the predetermined abnormality threshold, the wheel diameter abnormality alarm information is generated, thereby realizing the generation of wheel diameter abnormality alarm information under different positional relationships between target wheels, thereby improving the safety of the target rail vehicle operation.

[0109] According to an embodiment of the present disclosure, the above-mentioned rail vehicle wheel diameter difference detection method also includes: obtaining historical wheel diameter information of multiple wheels in the previous t-2 period and operating parameter information of the target rail vehicle; and inputting the historical wheel diameter information and operating parameter information into the second target model, and outputting the first wheel diameter information of multiple wheels in the t-1 period.

[0110] According to an embodiment of the present disclosure, the second target model may be obtained by training using sample historical wheel diameter information within a predetermined historical period and operating parameter information of the target rail vehicle.

[0111] According to an embodiment of the present disclosure, when the prediction accuracy of the second target model on the test set is higher than a limit (e.g., 98%), the second target model can be considered valid. The second target model can also be a model built based on a machine learning method, such as multiple linear regression, ridge regression, least absolute shrinkage and selection operator (Lasso) regression, decision tree regression, random forest regression, gradient boosting regression, support vector regression, extreme gradient boosting (XGBoost) regression, LightGBM regression, neural network regression, etc.

[0112] According to an embodiment of the present disclosure, historical wheel diameter information and operating parameter information can be input into the second target model to predict the first wheel diameter information of multiple wheels in the next period, and the first wheel diameter information of multiple wheels in the t-1 period can be output.

[0113] According to an embodiment of the present disclosure, the above-mentioned rail vehicle wheel diameter difference detection method also includes: obtaining historical wheel diameter difference information of multiple wheels in the previous t-1 period and operating parameter information of the target rail vehicle; and inputting the historical wheel diameter difference information, operating parameter information and wheel diameter difference information of multiple wheels in the tth period into the first target model, and outputting the wheel diameter difference prediction information of multiple wheels in the t+1th period.

[0114] According to an embodiment of the present disclosure, the historical wheel diameter difference information of multiple wheels in the previous t-1 period can be obtained when the target rail vehicle is stationary or in motion. The operating parameter information of the target rail vehicle can represent train parameters related to wheel wear, such as mileage, speed, acceleration, air spring pressure, traction level, brake level, axle box bearing temperature, traction motor current, traction motor voltage, network current, network pressure, brake cylinder pressure, actual braking force, bogie dynamic load, idling, coasting, and other parameters.

[0115] According to an embodiment of the present disclosure, the first target model can be trained using historical wheel diameter difference information of samples within a predetermined historical period and operating parameter information of the target rail vehicle. When the prediction accuracy of the first target model on the test set exceeds a limit (e.g., 98%), the first target model can be considered effective. The first target model can be a model constructed based on machine learning methods, such as multiple linear regression, ridge regression, Lasso regression, decision tree regression, random forest regression, gradient boosting regression, support vector regression, XGBoost regression, LightGBM regression, neural network regression, etc.

[0116] According to an embodiment of the present disclosure, historical wheel diameter difference information, operating parameter information, and wheel diameter difference information for multiple wheels during period t can be input into a first target model to predict path difference information for multiple wheels during the next period, thereby outputting predicted wheel diameter difference information for multiple wheels during period t+1. The wheel diameter difference information for multiple wheels during period t can be output from a second target model.

[0117] According to the embodiments of the present disclosure, by inputting historical wheel diameter difference information, operating parameter information and wheel diameter difference information of multiple wheels in the t-th period into the first target model, the wheel diameter difference information of multiple wheels in the t+1-th period can be predicted, thereby outputting the wheel diameter difference prediction information of multiple wheels in the t+1-th period, and comparing the wheel diameter difference prediction information with a predetermined difference threshold, it can be predicted whether the wheel diameter difference information of multiple wheels in the t+1-th period exceeds the limit alarm, and a wheel turning and repair plan can be formulated in advance based on the prediction results, thereby realizing predictive maintenance of wheels, improving wheel utilization while ensuring the safety and availability of wheels, and achieving cost reduction and efficiency improvement.

[0118] According to an embodiment of the present disclosure, the historical wheel diameter difference information of multiple wheels in the t-1 period can be actually measured when the target rail vehicle is stationary, or it can be predicted in the t-2 period. In the case that the historical wheel diameter difference information of multiple wheels in the t-1 period is actually measured when the target rail vehicle is stationary, the wheel diameter difference information of multiple wheels in the t+1 period can be predicted based on the historical wheel diameter difference information of multiple wheels in the t-1 period, the wheel diameter difference information of multiple wheels in the t period, and the operating parameter information of the target rail vehicle, so as to obtain the wheel diameter difference prediction information of multiple wheels in the t+1 period. The following will be combined with Figure 5 The process is described in detail.

[0119] Figure 5 The following schematically shows an architecture diagram for predicting wheel diameter difference information according to an embodiment of the present disclosure.

[0120] like Figure 5As shown, the pulse signals 511 of the multiple wheels of the target rail vehicle obtained in the t-th time period are processed to generate the wheel diameter deviation index 513 of each wheel. The wheel diameter deviation index 513 of each wheel combined with the first wheel diameter information 512 of the multiple wheels obtained in the t-1th time period can generate the second wheel diameter information 514 of the multiple wheels in the t-th time period. According to the second wheel diameter information 514 of each wheel, the wheel diameter difference information 515 of the multiple wheels in the t-th time period is generated. The wheel diameter difference information 515 of the multiple wheels in the t-th time period, the operating parameter information 517 of the target rail vehicle and the historical wheel diameter difference information 518 of the multiple wheels in the t-1th time period are input into the first target model 516, so as to generate the wheel diameter difference prediction information 519 of the multiple wheels in the t+1th time period.

[0121] According to an embodiment of the present disclosure, when the historical wheel diameter difference information of multiple wheels in the t-1 period is predicted in the t-2 period, the historical wheel diameter difference information of multiple wheels in the t-1 period can be obtained by inputting the operating parameter information of the target rail vehicle, the historical wheel diameter difference information of multiple wheels in the t-2 period, and other information into the second target model. Figure 6 The process is described in detail.

[0122] Figure 6 The following schematically shows an architecture diagram for predicting wheel diameter difference information according to another embodiment of the present disclosure.

[0123] like Figure 6 As shown, the pulse signals 611 of the multiple wheels of the target rail vehicle obtained in the t-th time period are processed to generate the wheel diameter deviation index 613 of each wheel. The wheel diameter deviation index 613 of each wheel combined with the first wheel diameter information 612 of the multiple wheels obtained in the t-1th time period can generate the second wheel diameter information 614 of the multiple wheels in the t-th time period. According to the second wheel diameter information 614 of each wheel, the wheel diameter difference information 615 of the multiple wheels in the t-th time period is generated. The wheel diameter difference information 615 of the multiple wheels in the t-th time period, the operating parameter information 617 of the target rail vehicle and the historical wheel diameter difference information 618 of the multiple wheels in the t-1th time period are input into the first target model 616 to generate the wheel diameter difference prediction information 619 of the multiple wheels in the t+1th time period.

[0124] According to an embodiment of the present disclosure, the historical wheel diameter difference information 618 of multiple wheels in the t-1 period can be obtained by inputting the operating parameter information 617 of the target rail vehicle and the historical wheel diameter difference information 620 of multiple wheels in the t-2 period into the second target model 621 .

[0125] Based on the above-mentioned rail vehicle wheel diameter difference detection method, the present disclosure also provides a rail vehicle wheel diameter difference detection device. Figure 7 The device is described in detail.

[0126] Figure 7 The structural block diagram of the rail vehicle wheel diameter difference detection device according to an embodiment of the present disclosure is schematically shown.

[0127] like Figure 7 As shown, the rail vehicle wheel diameter difference detection device 700 of this embodiment includes a first acquisition module 710 , a processing module 720 , a first generation module 730 and a second generation module 740 .

[0128] The first acquisition module 710 is configured to, in response to receiving a signal indicating that the target rail vehicle's travel speed is greater than a predetermined speed threshold, acquire pulse signals from a plurality of wheels of the target rail vehicle during a time period t and first wheel diameter information of the plurality of wheels during the time period t, where t is an integer greater than 1. In one embodiment, the first acquisition module 710 may be configured to execute operation S210 described above, which will not be further described herein.

[0129] The processing module 720 is configured to process the pulse signal of each wheel and generate a wheel diameter deviation index of each wheel. In one embodiment, the processing module 720 may be configured to execute the operation S220 described above, which will not be described in detail here.

[0130] The first generating module 730 is configured to generate the second wheel diameter information of each wheel in the tth period based on the wheel diameter deviation index of each wheel and the first wheel diameter information of each wheel. In one embodiment, the first generating module 730 can be configured to perform the operation S230 described above, which will not be described in detail here.

[0131] The second generating module 740 is configured to generate wheel diameter difference information of the plurality of wheels in the tth period based on the second wheel diameter information of each wheel. In one embodiment, the second generating module 740 may be configured to execute the operation S240 described above, which will not be described in detail here.

[0132] According to an embodiment of the present disclosure, the processing module 720 includes:

[0133] A first processing submodule is configured to generate the number of pulses of each wheel according to a change trend of the pulse signal of each wheel;

[0134] A second processing submodule is configured to generate an average pulse number of the plurality of wheels according to the number of pulses; and

[0135] The third processing submodule is configured to generate a wheel diameter deviation index of each wheel according to the number of pulses and the average number of pulses.

[0136] According to an embodiment of the present disclosure, the tth time period includes N acquisition moments, where N is an integer greater than 1; the first processing submodule includes:

[0137] a first processing unit, configured to determine that the pulse signal at the nth sampling moment is a first pulse turning position of an upward trend in response to i pulse signals before the nth sampling moment being less than a first predetermined threshold and i-1 pulse signals after the nth sampling moment being greater than a second predetermined threshold, wherein 1<i<n≤N; and

[0138] The second processing unit is used to count the number of turning positions of each first pulse of each wheel in the t-th time period to generate the number of pulses of each wheel.

[0139] According to an embodiment of the present disclosure, the tth time period includes N acquisition moments, where N is an integer greater than 1; the first processing submodule includes:

[0140] a third processing unit, configured to determine that the pulse signal at the nth sampling moment is at a second pulse turning position of a downward trend in response to j pulse signals before the nth sampling moment being greater than a second predetermined threshold and j-1 pulse signals after the nth sampling moment being less than a first predetermined threshold, wherein 1<j<n≤N; and

[0141] The fourth processing unit is used to count the number of turning positions of the second pulses of each wheel in the t-th time period to generate the number of pulses of each wheel.

[0142] According to an embodiment of the present disclosure, the change trend includes an upward trend and a downward trend; the first processing submodule further includes:

[0143] A fifth processing unit is configured to obtain the number of first pulse turning positions corresponding to an upward trend and the number of second pulse turning positions corresponding to a downward trend for each wheel; and

[0144] The sixth processing unit is used to generate the number of pulses of each wheel according to the number of each first pulse turning position and the number of each second pulse turning position.

[0145] According to an embodiment of the present disclosure, the tth time period includes Q sampling periods, where Q is an integer greater than 1; the first generating module 730 includes:

[0146] The first generating submodule is used to calculate the wheel diameter deviation index of each wheel within Q sampling periods and obtain the wheel diameter deviation index error corresponding to each period;

[0147] a second generating submodule, configured to determine the wheel diameter deviation index of the qth sampling period as a target wheel diameter deviation index in response to the wheel diameter deviation index error of the qth sampling period being less than a predetermined error threshold; and

[0148] The third generating submodule is configured to generate the second wheel diameter information of each wheel in the tth time period according to the target wheel diameter deviation index of each wheel and the first wheel diameter information of each wheel.

[0149] According to an embodiment of the present disclosure, the second generation module 740 includes:

[0150] The fourth generating submodule is used to extract the second wheel diameter information of at least two target wheels from the second wheel diameter information of each wheel, wherein the positional relationship between the at least two target wheels includes at least one of the following: being located on the same bogie of the target rail vehicle and being located on the same carriage of the target rail vehicle.

[0151] The fifth generating submodule is configured to generate wheel diameter difference information according to the second wheel diameter information of at least two target wheels.

[0152] According to an embodiment of the present disclosure, the above-mentioned rail vehicle wheel diameter difference detection device further includes:

[0153] a recording module, configured to record wheel diameter difference abnormality information in response to the wheel diameter difference information exceeding a predetermined difference threshold; and

[0154] The third generating module is configured to generate wheel diameter abnormality alarm information in response to the number of wheel diameter difference abnormality information exceeding a predetermined abnormality threshold.

[0155] According to an embodiment of the present disclosure, the above-mentioned rail vehicle wheel diameter difference detection device further includes:

[0156] The second acquisition module is used to obtain historical wheel diameter difference information of multiple wheels in the previous t-1 period and operating parameter information of the target rail vehicle; and

[0157] a first output module, configured to input historical wheel diameter difference information, operating parameter information, and wheel diameter difference information of a plurality of wheels in a t-th period into a first target model, and output wheel diameter difference prediction information of a plurality of wheels in a t+1-th period;

[0158] The first target model is trained using sample historical wheel diameter difference information within a predetermined historical period and operating parameter information of the target rail vehicle.

[0159] According to an embodiment of the present disclosure, the above-mentioned rail vehicle wheel diameter difference detection device further includes:

[0160] A third acquisition module is used to acquire historical wheel diameter information of multiple wheels and operating parameter information of the target rail vehicle in the previous t-2 period; and

[0161] a second output module, configured to input historical wheel diameter information and operating parameter information into a second target model, and output first wheel diameter information of a plurality of wheels in a t-1 period;

[0162] The second target model is obtained by training using sample historical wheel diameter information within a predetermined historical period and operating parameter information of the target rail vehicle.

[0163] According to embodiments of the present disclosure, any multiple modules among the first acquisition module 710, the processing module 720, the first generation module 730, and the second generation module 740 may be combined into a single module, or any one of these modules may be split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of other modules and implemented in a single module. According to embodiments of the present disclosure, at least one of the first acquisition module 710, the processing module 720, the first generation module 730, and the second generation module 740 may be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or may be implemented in hardware or firmware through any other reasonable means of circuit integration or packaging, or may be implemented in any one of the three implementation methods of software, hardware, and firmware, or any appropriate combination of any of these. Alternatively, at least one of the first acquisition module 710 , the processing module 720 , the first generation module 730 , and the second generation module 740 may be at least partially implemented as a computer program module, which may perform corresponding functions when executed.

[0164] Based on the above-mentioned rail vehicle wheel diameter difference detection device, the present disclosure further provides a train, on which the rail vehicle wheel diameter difference detection device is configured.

[0165] Figure 8 A block diagram of an electronic device suitable for implementing a method for detecting wheel diameter differences of rail vehicles according to an embodiment of the present disclosure is schematically shown.

[0166] like Figure 8 As shown, the electronic device 800 according to an embodiment of the present disclosure includes a processor 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage unit 808 into a random access memory (RAM) 803. The processor 801 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 801 may also include onboard memory for caching purposes. The processor 801 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0167] Various programs and data required for the operation of the electronic device 800 are stored in the RAM 803. The processor 801, ROM 802, and RAM 803 are connected to each other via a bus 804. The processor 801 executes the various operations of the method flow according to the embodiment of the present disclosure by executing the programs in the ROM 802 and / or RAM 803. It should be noted that the programs may also be stored in one or more memories other than the ROM 802 and RAM 803. The processor 801 may also execute the various operations of the method flow according to the embodiment of the present disclosure by executing the programs stored in the one or more memories.

[0168] According to an embodiment of the present disclosure, electronic device 800 may further include an input / output (I / O) interface 805, which is also connected to bus 804. Electronic device 800 may also include one or more of the following components connected to I / O interface 805: an input section 806 including a keyboard, mouse, etc.; an output section 807 including devices such as a cathode ray tube (CRT), liquid crystal display (LCD), and speakers; a storage section 808 including a hard disk; and a communication section 809 including a network interface card such as a LAN card or modem. Communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to I / O interface 805 as needed. Removable media 811, such as a magnetic disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed in drive 810 as needed, so that computer programs read from the removable media can be installed into storage section 808 as needed.

[0169] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments, or may exist independently and not be incorporated into the device / apparatus / system. The computer-readable storage medium carries one or more programs, and when executed, implements the method according to the embodiments of the present disclosure.

[0170] According to an embodiment of the present disclosure, a computer-readable storage medium may be a non-volatile computer-readable storage medium, and may include, for example, but not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to an embodiment of the present disclosure, a computer-readable storage medium may include the ROM 802 and / or RAM 803 described above, and / or one or more memories other than ROM 802 and RAM 803.

[0171] The present disclosure also includes a computer program product comprising a computer program containing program code for executing the method shown in the flowchart. When the computer program product is executed in a computer system, the program code is used to cause the computer system to implement the rail vehicle wheel diameter difference detection method provided in the present disclosure.

[0172] The computer program executes the above functions defined in the system / device of the embodiment of the present disclosure when the computer program is executed by the processor 801. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0173] In one embodiment, the computer program may be stored on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may be transmitted and distributed in the form of a signal on a network medium, downloaded and installed via the communication portion 809, and / or installed from a removable medium 811. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0174] In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 809, and / or installed from a removable medium 811. When the computer program is executed by the processor 801, the above-described functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the systems, devices, means, modules, units, etc. described above can be implemented by computer program modules.

[0175] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computer programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C" or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect via the Internet).

[0176] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the above-mentioned module, program segment, or a part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0177] Those skilled in the art will appreciate that the features described in the various embodiments of the present disclosure may be combined and / or coupled in various ways, even if such combinations and / or couplings are not explicitly described in the present disclosure. In particular, the features described in the various embodiments of the present disclosure may be combined and / or coupled in various ways without departing from the spirit and teachings of the present disclosure. All such combinations and / or couplings fall within the scope of the present disclosure.

[0178] The above describes the embodiments of the present disclosure. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although each embodiment has been described separately above, this does not mean that the measures in each embodiment cannot be advantageously used in combination. Without departing from the scope of the present disclosure, those skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A method for detecting wheel diameter differences of rail vehicles, comprising: In response to receiving a signal indicating that the travel speed of the target rail vehicle is greater than a predetermined speed threshold, obtaining pulse signals of a plurality of wheels of the target rail vehicle in a t-th time period and first wheel diameter information of the plurality of wheels in a t-1-th time period, where t is an integer greater than 1; Generate a wheel diameter deviation index for each wheel based on the number of pulses corresponding to the pulse signal of each wheel; the wheel diameter deviation index for each vehicle represents the ratio of each pulse number to the average pulse number; generating second wheel diameter information of each wheel in time period t according to the wheel diameter deviation index of each wheel and the first wheel diameter information of each wheel; as well as Wheel diameter difference information of the plurality of wheels in the t-th time period is generated based on the second wheel diameter information of each wheel.

2. The method according to claim 1, wherein Generating the wheel diameter deviation index of each wheel based on the number of pulses corresponding to the pulse signal of each wheel includes: Generate the number of pulses for each wheel based on the changing trend of the pulse signal of each wheel; generating an average pulse number of the plurality of wheels based on each of the pulse numbers; and A wheel diameter deviation index of each wheel is generated based on the pulse numbers and the average pulse number.

3. The method according to claim 2, wherein: The t-th time period includes N collection moments, where N is an integer greater than 1; The step of generating the number of pulses of each wheel according to the change trend of the pulse signal of each wheel includes: In response to i pulse signals before the nth sampling moment being less than a first predetermined threshold and i-1 pulse signals after the nth sampling moment being greater than a second predetermined threshold, determining that the pulse signal at the nth sampling moment is a first pulse turning position of an upward trend, wherein 1<i<n≤N; and The number of turning positions of each of the first pulses of each wheel in the t-th time period is counted to generate the number of pulses of each wheel.

4. The method according to claim 2, wherein: The t-th time period includes N collection moments, where N is an integer greater than 1; The step of generating the number of pulses of each wheel according to the change trend of the pulse signal of each wheel includes: In response to j pulse signals before the nth sampling moment being greater than a second predetermined threshold and j-1 pulse signals after the nth sampling moment being less than a first predetermined threshold, determining that the pulse signal at the nth sampling moment is a second pulse turning position of a downward trend, wherein 1<j<n≤N; and The number of turning positions of each second pulse of each wheel in the t-th time period is counted to generate the number of pulses of each wheel.

5. The method according to claim 2, wherein: The changing trend includes an upward trend and a downward trend; The step of generating the number of pulses of each wheel according to the variation trend of the pulse signal of each wheel further includes: Obtaining the number of first pulse turning positions corresponding to the upward trend and the number of second pulse turning positions corresponding to the downward trend for each wheel; as well as The number of pulses for each wheel is generated according to the number of each of the first pulse turning positions and the number of each of the second pulse turning positions.

6. The method according to claim 1, wherein The t-th time period includes Q sampling periods, where Q is an integer greater than 1; generating the second wheel diameter information of each wheel in the t-th time period based on the wheel diameter deviation index of each wheel and the first wheel diameter information of each wheel, including: For each wheel's wheel diameter deviation index within Q sampling periods, the wheel diameter deviation index error corresponding to each period is calculated; In response to the wheel diameter deviation index error of the qth sampling period being less than a predetermined error threshold, determining the wheel diameter deviation index of the qth sampling period as a target wheel diameter deviation index; and The second wheel diameter information of each wheel in the t-th time period is generated according to the target wheel diameter deviation index of each wheel and the first wheel diameter information of each wheel.

7. The method according to claim 1, wherein Generating wheel diameter difference information of the plurality of wheels in time period t according to the second wheel diameter information of each wheel includes: Extracting the second wheel diameter information of at least two target wheels from the second wheel diameter information of each wheel, wherein the positional relationship between the at least two target wheels includes at least one of the following: being located on the same bogie of the target rail vehicle and being located on the same car of the target rail vehicle; The wheel diameter difference information is generated according to the second wheel diameter information of the at least two target wheels.

8. The method according to any one of claims 1 to 7, further comprising: In response to the wheel diameter difference information exceeding a predetermined difference threshold, recording wheel diameter difference abnormality information; as well as In response to the number of the wheel diameter difference abnormal information exceeding a predetermined abnormal threshold, wheel diameter abnormality alarm information is generated.

9. The method according to any one of claims 1 to 7, further comprising: Acquire historical wheel diameter difference information of the plurality of wheels and operating parameter information of the target rail vehicle in a previous t-1 period; as well as Inputting the historical wheel diameter difference information, the operating parameter information, and the wheel diameter difference information of the plurality of wheels in the t-th period into a first target model, and outputting wheel diameter difference prediction information of the plurality of wheels in the t+1-th period; The first target model is obtained by training using sample historical wheel diameter difference information within a predetermined historical period and operating parameter information of the target rail vehicle.

10. The method according to any one of claims 1 to 7, further comprising: Acquire historical wheel diameter information of the plurality of wheels and operating parameter information of the target rail vehicle in the previous t-2 period; as well as Inputting the historical wheel diameter information and the operating parameter information into a second target model, and outputting first wheel diameter information of the plurality of wheels in time period t-1; The second target model is obtained by training using sample historical wheel diameter information within a predetermined historical period and operating parameter information of the target rail vehicle.

11. A device for detecting wheel diameter differences of a railway vehicle, comprising: a first acquisition module configured to acquire, in response to receiving a signal indicating that a traveling speed of a target rail vehicle is greater than a predetermined speed threshold, pulse signals of a plurality of wheels of the target rail vehicle within a t-th time period and first wheel diameter information of the plurality of wheels within the t-th time period, where t is an integer greater than 1; a processing module, configured to generate a wheel diameter deviation index for each wheel based on the number of pulses corresponding to the pulse signal of each wheel; the wheel diameter deviation index for each vehicle representing a ratio of the number of pulses to the average number of pulses; a first generating module, configured to generate second wheel diameter information of each wheel in a t-th time period according to the wheel diameter deviation index of each wheel and the first wheel diameter information of each wheel; as well as The second generating module is configured to generate wheel diameter difference information of the plurality of wheels in the tth time period according to the second wheel diameter information of each wheel.

12. A train comprising: The train is equipped with the device according to claim 11.

13. An electronic device comprising: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors are enabled to execute the method according to any one of claims 1 to 10.

14. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to perform the method according to any one of claims 1 to 10.

15. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 10 is implemented.

Images