TWDS online wheel set detection data acquisition system and equipment

Abstract

The invention discloses a TWDS online wheel set detection data acquisition system and equipment, and particularly relates to the technical field of data processing, the data acquisition system comprises a position control module, an identification module, a protection module, a measurement module and a management and operation module; the position control module is used for monitoring the position of a train on a track through an inductive sensor; the identification module is used for carrying out serial number identification on the compartment and the wheel set and sending a confirmation signal to the protection module after identification is completed; after receiving the confirmation signal sent by the identification module, the protection module controls a mechanical protection device of the laser scanner and keeps the temperature stable; the measuring module is used for acquiring geometric data of a wheel set by using a laser scanner and transmitting the data to the management and operation module for processing; the management and operation module is used for analyzing a data change trend according to the scanning data and generating a measurement report; the data acquisition device comprises an inductive sensor, a laser scanner, a measuring unit, a data processing server and a communication module.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and more specifically to a TWDS online wheelset detection data acquisition system and equipment. Background Art

[0002] With the rapid development of the railway transportation industry, the safety, reliability and operation efficiency of trains have received increasing attention. As an important part of the train, the performance of wheelsets is directly related to the safety, comfort and operating costs of the train. Especially in high-speed railway and heavy-load railway systems, the health of wheelsets has a vital impact on safety and operational stability.

[0003] Traditional wheelset detection methods mostly rely on manual inspection and periodic maintenance, which not only has high labor and time costs, but is also easily affected by human factors, resulting in incomplete and timely inspections, and may even ignore potential safety hazards. Therefore, the development of an efficient, accurate, and real-time wheelset online detection system has become an urgent need to improve the safety and efficiency of railway transportation. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a TWDS online wheelset detection data acquisition system and device to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solution: a TWDS online wheelset detection data acquisition system, comprising a position control module, an identification module, a protection module, a measurement module, and a management and calculation module;

[0006] The position control module monitors the position of the train on the track through an inductive sensor, and sends a signal to the identification module and the protection module when confirming that the train enters the measurement area;

[0007] After receiving the signal sent by the position control module, the identification module performs number identification on the carriage and the wheelset, and sends a confirmation signal to the protection module after the identification is completed;

[0008] After receiving the confirmation signal sent by the identification module, the protection module controls the mechanical protection device of the laser scanner and keeps the temperature stable;

[0009] After receiving the signal sent by the position control module, the measuring module uses a laser scanner to collect geometric data of the wheelset and transmits the data to the management and calculation module for processing;

[0010] The management and calculation module analyzes the data change trend according to the scan data and generates a measurement report.

[0011] In a preferred embodiment, the position control module monitors the position of the train on the track through an inductive sensor, and sends a signal to the measurement module, the identification module and the protection module when confirming that the train enters the measurement area. The specific steps include: installing 4 inductive sensors on the track, marked as sensors 1, 2, 3 and 4 respectively, to determine whether the train enters the measurement area; when sensor 1 detects the train, it indicates that the train has entered the measurement area, and sends an identification signal to the identification module, the signal content includes the timestamp of the train entering the measurement area and the current position of the train;

[0012] When sensor No. 2 detects a train, it indicates that the train has entered the scanning area, and sends a start signal to the measurement module to collect geometric data of the wheelset. When sensor No. 3 detects that the train has left the scanning area, it indicates that the scanning process of the measurement module has been completed, and sends an end signal to the measurement module to confirm that the scanning is completed.

[0013] When the train is traveling in the reverse direction, sensor No. 4 is enabled and used as a sensor to sense the approaching train, sensor No. 3 is used as a start signal sensor for the scanning area, and sensor No. 2 is used as an end signal sensor for the scanning area.

[0014] In a preferred embodiment, after the identification module receives the identification signal sent by the position control module, it identifies the carriage and the wheelset by number, and sends a confirmation signal to the protection module after the identification is completed. The specific steps are as follows:

[0015] Step B1, car number identification: after receiving the identification signal from sensor No. 1, the car and wheels entering the measurement area are numbered and identified, the car number image is automatically captured by the camera, and the image acquisition start time is recorded, the car number is extracted from the image using an image recognition algorithm, and the identified car number is compared with the registration information in the vehicle registration database to determine the unique identification of the car, further comprising the following steps:

[0016] Step B101, image preprocessing: converting the acquired image into a grayscale image and removing noise from the image, converting the image into a binary image through threshold processing, and dividing the carriage number area;

[0017] Step B102, feature extraction: Use the convolutional neural network algorithm to extract features from the preprocessed binary image, and obtain the position and character of the car number through convolution and pooling operations on the feature map. The convolution operation is to slide the convolution kernel on the input feature map, and generate the output feature map by calculating the weighted sum of each position. The specific formula is: Among them, F out (x, y) is the pixel value of the output feature map at position (x, y), k is the radius of the convolution kernel, and F in(x, y) is the pixel value of the input feature map, K(i, j) is the weight of the convolution kernel at position (i, j);

[0018] The pooling operation is to use the maximum pooling operation after each convolution layer to reduce the size of the feature map. The specific calculation formula is: Among them, F pool (x, y) is the pixel value of the feature map at position (x, y) after pooling, p is the size of the pooling window, and F out (x, y) is the pixel value of the output feature map at position (x+i, y+j), and max means selecting the maximum value in the pooling window;

[0019] After multiple layers of convolution and pooling, the feature map after the pooling operation is flattened into a one-dimensional vector F flatten And input to the fully connected layer for classification, y = f (W·F flatten +b), where y is the classification output, representing the category vector of the car number, W is the weight matrix, b is the bias, and f is the activation function;

[0020] Step B2, wheelset number identification: According to the relative position between the carriage and the wheelset, the geometric parameters of the carriage and the wheelset are obtained by the measurement module, and the wheelset number is extracted and identified, further comprising the following steps:

[0021] Step B201, geometric feature matching: by comparing the geometric features of the predetermined wheelset inside the carriage with the wheelset geometric features obtained in the measurement module, it is determined that the wheelset belongs to the position inside the carriage;

[0022] Step B202: When the geometric features of the matched wheelset match the predetermined g-th wheelset in the carriage, the wheelset is numbered as g and associated with the carriage number;

[0023] Step B3: Confirm the accuracy of identification by comparing the geometric parameters of the car and wheelset, as well as the number matching. When the car and wheelset numbers are identified and confirmed to be correct, the identification module sends a confirmation signal to the protection module, indicating that the car number and wheelset number have been successfully identified. The confirmation signal includes the car number, wheelset number, and confirmation status information.

[0024] In a preferred embodiment, after the measurement module receives the start signal sent by the position control module, it uses a laser scanner to collect geometric data of the wheelset and transmits the data to the management and operation module for processing. The specific steps are as follows:

[0025] Step C1: After receiving the start signal from sensor No. 2, the measurement module starts the laser scanner to perform geometric measurement on the wheelset of the train and collects the geometric data of the wheelset, including the wheel rim height, wheel rim thickness, wheel rim slope value, wheel rim width and thickness, wheel diameter and wheelset inner distance; after receiving the end signal sent by sensor No. 3, the scanning is stopped;

[0026] The wheel rim height is obtained by measuring the height difference of the outer surface of the wheel with a laser scanner. The specific formula is: h r =z top -z contact , where h r is the rim height, z top is the height of the top of the wheel, z contact is the height of the surface where the wheel contacts the track;

[0027] The rim thickness is calculated by a laser scanner by scanning the rim surface and measuring the laser reflection points at different positions. The specific formula is: r =d outside -d inside , where t r is the rim thickness, d outside is the distance from the outer side of the wheel rim to the laser instrument, d inside is the distance from the inner side of the wheel rim to the laser instrument;

[0028] The rim slope value is obtained by measuring the inclination angle of the rim surface, and the specific formula is: Where QR is the rim slope value, h r is the rim height, r base is the radius of the wheel rim;

[0029] The rim width is the lateral width of the wheel rim, and the rim thickness is the vertical thickness of the rim from the wheel flange to the inner ring. The rim width and thickness are obtained by scanning the inner and outer contours of the wheel rim. The specific formula is: b =d flange -d web , t b =d rim-top -d rim-bottom , where w b is the rim width, d flange is the distance from the outermost side of the wheel rim to the laser instrument, d web is the distance from the rim centerline to the laser instrument, t b is the rim thickness, d rim-top is the distance from the top of the rim to the laser instrument, d rim_bottom is the distance from the bottom of the rim to the laser instrument;

[0030] The wheel diameter is measured from the highest point to the lowest point of the outer edge of the wheel, expressed as D, and the inner distance of the wheelset is obtained by scanning the laser point on the inner side of the wheel, expressed as L;

[0031] Step C2, data transmission: the collected geometric data is organized into a structured data packet and transmitted to the management and operation module, wherein the data packet includes {h r ,t r ,QR,w b ,t b ,D,L,t start ,t end}, where h r is the rim height, t r is the rim thickness, QR is the rim slope value, w b is the rim width, t b is the rim thickness, D is the wheel diameter, L is the inside distance of the wheelset, t start and t end are the start and end time of data collection.

[0032] In a preferred embodiment, after receiving the confirmation signal sent by the identification module, the protection module controls the mechanical protection device of the laser scanner and keeps the temperature stable. The specific steps are as follows:

[0033] Step D1, check the status information in the confirmation signal, confirm that the carriage and wheelset have been successfully identified, start the mechanical protection device of the laser scanner, including controlling the stepper motor to open the protection gate, and start the air knife protection device of the window, and use the built-in temperature sensor to monitor the temperature of the scanner working area, denoted as T env , and set a temperature threshold T min =15℃, the temperature value T fed back by the temperature sensor env and the set temperature threshold T min Dynamically adjust the working status of heaters and fans to control the temperature of the working area;

[0034] Step D2: The power of the heater is expressed as P heater , the fan power is expressed as P fan , calculate the power of the heater and fan by the thermodynamic formula: P heater =αC p ΔT,P fan =βC p ΔT, where ΔT = |T min -T env | is the temperature difference, C p is the specific heat capacity of air, α is the air flow rate controlled by the heater, and β is the air flow rate controlled by the fan;

[0035] The current temperature is lower than the set temperature threshold: T env <T min , start the heater and use a certain power P heater Continue heating until the temperature reaches the set value;

[0036] The current temperature exceeds the set temperature threshold: T env ≥T min , start the fan and set it to power P fan Air is drawn in for cooling.

[0037] In a preferred embodiment, the management and calculation module analyzes the data change trend according to the scan data and generates a measurement report. The specific steps are as follows:

[0038] Step S1: Receive the geometric parameter data of the carriage and wheelset from the measurement module, and perform data verification and time verification on the received data. The data verification includes checking whether all fields in the data packet are in the correct format and whether each parameter value is within a reasonable range. The time verification is whether there are overlapping collection time periods, and t end >t start ;

[0039] Step S2: Analyze the received geometric parameter data, perform time series analysis on it, calculate the parameter change rate, and express the measured value of a certain geometric parameter at time t as V(1), V(2), .., V(z). The specific formula of the parameter change rate is: Among them, R V (t) is the rate of change, V q+1 and V q Indicates that at time point t q+1 and t q When the geometric parameter measurement value is corresponding, for each geometric parameter time series data, the least squares method is used to fit the data, and the change trend diagram of each geometric parameter is drawn using the data visualization tool, and the maximum allowable change rate of each parameter is set. When the change rate of the parameter within a certain period of time exceeds the maximum allowable change rate, it means that the parameter is detected to be abnormal, and the abnormal parameter is marked in red. According to the results of data analysis, a detailed measurement report is automatically generated, including: the collection time period, the original measurement values ​​of each geometric parameter, and the change trend diagram of each geometric parameter. According to the parameter change trend, the health status of the equipment is evaluated and maintenance suggestions are provided.

[0040] In a preferred embodiment, the communication interaction module,

[0041] The present application also provides a TWDS online wheelset detection data acquisition device, the device specifically comprising: an inductive sensor, a laser scanner, a measuring unit, a data processing server, and a communication module;

[0042] The inductive sensor is used to monitor the real-time position of the train on the track;

[0043] The laser scanner is used to accurately collect geometric data of the train wheelset;

[0044] The measuring unit is used to obtain scanning data from the laser scanner and transmit the data to the data processing server;

[0045] The data processing server receives data from the measuring unit, analyzes and calculates the data, and generates a measurement report;

[0046] The communication module uploads the processed data to the client application and database for storage.

[0047] The beneficial effects of the present invention are as follows: by collecting geometric data through inductive sensors and laser scanners, the geometric parameters of the wheels can be measured with high precision, ensuring the accuracy of the test data; the data is transmitted to the client and the database in real time through the communication module; the management personnel can view the test results through the remote monitoring system, conduct data analysis and make decisions, and reduce the dependence on on-site inspections; the present invention supports online detection and can perform wheelset detection without stopping the train, which greatly improves the operating efficiency of the train and avoids the time waste caused by stopping for inspection. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 The sensor position layout diagram of the position control module of the present invention;

[0049] Figure 2 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0051] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0052] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0053] Example 1

[0054] This embodiment provides Figure 1 A TWDS online wheelset detection data acquisition system is shown, which specifically includes a position control module, an identification module, a protection module, a measurement module, and a management and calculation module;

[0055] The position control module monitors the position of the train on the track through an inductive sensor, and sends a signal to the identification module and the protection module when confirming that the train enters the measurement area;

[0056] After receiving the signal sent by the position control module, the identification module performs number identification on the carriage and the wheelset, and sends a confirmation signal to the protection module after the identification is completed;

[0057] After receiving the confirmation signal sent by the identification module, the protection module controls the mechanical protection device of the laser scanner and keeps the temperature stable;

[0058] After receiving the signal sent by the position control module, the measuring module uses a laser scanner to collect geometric data of the wheelset and transmits the data to the management and calculation module for processing;

[0059] The management and calculation module analyzes the data change trend according to the scan data and generates a measurement report.

[0060] In this embodiment, the position control module specifically needs to be explained. The position control module monitors the train position on the track through an inductive sensor. When confirming that the train enters the measurement area, it sends a signal to the measurement module, the identification module and the protection module. The specific steps include: installing 4 inductive sensors on the track, marked as sensors 1, 2, 3 and 4 respectively, such as Figure 1 As shown, it is determined whether the train enters the measurement area, wherein sensor No. 1 is 10 meters away from the measurement unit and is used to sense the approach of the train; sensor No. 2 is located 1.5 meters in front of the measurement unit; sensor No. 3 is in front of the measurement unit and is in the scanning area, and sensor No. 4 is located 10 meters away from the measurement unit and is used to be enabled when the train is traveling in the reverse direction. At this time, sensor No. 4 completes the function of sensor No. 1, sensor No. 3 replaces sensor No. 2, and sensor No. 2 replaces sensor No. 3; when sensor No. 1 detects a train, it indicates that the train has entered the measurement area, and sends an identification signal to the identification module, the signal content includes the timestamp of the train entering the measurement area and the current position of the train;

[0061] When sensor No. 2 detects a train, it indicates that the train has entered the scanning area, and sends a start signal to the measurement module to collect geometric data of the wheelset. When sensor No. 3 detects that the train has left the scanning area, it indicates that the scanning process of the measurement module has been completed, and sends an end signal to the measurement module to confirm that the scanning is completed.

[0062] When the train is traveling in the reverse direction, sensor No. 4 is enabled and used as a sensor to sense the approaching train, sensor No. 3 is used as a start signal sensor for the scanning area, and sensor No. 2 is used as an end signal sensor for the scanning area.

[0063] In this embodiment, it is necessary to explain the identification module in detail. After receiving the identification signal sent by the position control module, the identification module identifies the carriage and the wheel pair by number, and sends a confirmation signal to the protection module after the identification is completed. The specific steps are as follows:

[0064] Step B1, car number identification: after receiving the identification signal from sensor No. 1, the car and wheels entering the measurement area are numbered and identified, the car number image is automatically captured by the camera, and the image acquisition start time is recorded, the car number is extracted from the image using an image recognition algorithm, and the identified car number is compared with the registration information in the vehicle registration database to determine the unique identification of the car, further comprising the following steps:

[0065] Step B101, image preprocessing: converting the acquired image into a grayscale image and removing noise from the image, converting the image into a binary image through threshold processing, and dividing the carriage number area;

[0066] Step B102, feature extraction: Use the convolutional neural network algorithm to extract features from the preprocessed binary image, and obtain the position and character of the car number through convolution and pooling operations on the feature map. The convolution operation is to slide the convolution kernel on the input feature map, and generate the output feature map by calculating the weighted sum of each position. The specific formula is: Among them, F out (x, y) is the pixel value of the output feature map at position (x, y), k is the radius of the convolution kernel, and F in (x, y) is the pixel value of the input feature map, K(i, j) is the weight of the convolution kernel at position (i, j);

[0067] The pooling operation is to use the maximum pooling operation after each convolution layer to reduce the size of the feature map. The specific calculation formula is: Among them, F pool (x, y) is the pixel value of the feature map at position (x, y) after pooling, p is the size of the pooling window, and F out (x, y) is the pixel value of the output feature map at position (x+i, y+j), and max means selecting the maximum value in the pooling window;

[0068] After multiple layers of convolution and pooling, the feature map after the pooling operation is flattened into a one-dimensional vector F flatten And input to the fully connected layer for classification, y = f (W·F flatten +b), where y is the classification output, representing the category vector of the car number, W is the weight matrix, b is the bias, and f is the activation function;

[0069] Step B2, wheelset number identification: According to the relative position between the carriage and the wheelset, the geometric parameters of the carriage and the wheelset are obtained by the measurement module, and the wheelset number is extracted and identified, further comprising the following steps:

[0070] Step B201, geometric feature matching: by comparing the geometric features of the predetermined wheelset inside the carriage with the wheelset geometric features obtained in the measurement module, it is determined that the wheelset belongs to the position inside the carriage;

[0071] Step B202: When the geometric features of the matched wheelset match the predetermined g-th wheelset in the carriage, the wheelset is numbered as g and associated with the carriage number;

[0072] Step B3: Confirm the accuracy of identification by comparing the geometric parameters of the car and wheelset, as well as the number matching. When the car and wheelset numbers are identified and confirmed to be correct, the identification module sends a confirmation signal to the protection module, indicating that the car number and wheelset number have been successfully identified. The confirmation signal includes the car number, wheelset number, and confirmation status information.

[0073] In this embodiment, it is specifically necessary to explain the measurement module. After receiving the start signal sent by the position control module, the measurement module uses a laser scanner to collect geometric data of the wheelset and transmits the data to the management and operation module for processing. The specific steps are as follows:

[0074] Step C1: After receiving the start signal from sensor No. 2, the measurement module starts the laser scanner to perform geometric measurement on the wheelset of the train and collects the geometric data of the wheelset, including the wheel rim height, wheel rim thickness, wheel rim slope value, wheel rim width and thickness, wheel diameter and wheelset inner distance; after receiving the end signal sent by sensor No. 3, the scanning is stopped;

[0075] The wheel rim height is the vertical distance from the wheel contact surface to the top of the wheel. The laser scanner measures the height difference of the outer surface of the wheel. The specific formula is: h r =z top -z contact , where h r is the rim height, z top is the height of the top of the wheel, z contact is the height of the surface where the wheel contacts the track;

[0076] The rim thickness is the width of the rim on the horizontal plane. The laser scanner calculates the thickness by scanning the rim surface and measuring the laser reflection points at different positions. The specific formula is: r =d outside -d inside , where t r is the rim thickness, d outside is the distance from the outer side of the wheel rim to the laser instrument, d inside is the distance from the inner side of the wheel rim to the laser instrument;

[0077] The rim slope value is the angle of the rim surface relative to the wheel rim, which is obtained by measuring the inclination angle of the rim surface. The specific formula is: Where QR is the rim slope value, h r is the rim height, r base is the radius of the wheel rim;

[0078] The rim width is the lateral width of the wheel rim, and the rim thickness is the vertical thickness of the rim from the wheel flange to the inner ring. The rim width and thickness are obtained by scanning the inner and outer contours of the wheel rim. The specific formula is: b =d flange -d web , t b =d rim-top -d rim-bottom , where w b is the rim width, d flangeis the distance from the outermost side of the wheel rim to the laser instrument, d web is the distance from the rim centerline to the laser instrument, t b is the rim thickness, d rim-top is the distance from the top of the rim to the laser instrument, d rim_bottom is the distance from the bottom of the rim to the laser instrument;

[0079] The wheel diameter is measured from the highest point to the lowest point of the outer edge of the wheel, expressed as D, and the inner distance of the wheelset is obtained by scanning the laser point on the inner side of the wheel, expressed as L;

[0080] Step C2, data transmission: The collected geometric data is organized into a structured data packet and transmitted to the management and operation module. The data packet includes {h r ,t r ,QR,w b ,t b ,D,L,t start ,t end}, where h r is the rim height, t r is the rim thickness, QR is the rim slope value, w b is the rim width, t b is the rim thickness, D is the wheel diameter, L is the inside distance of the wheelset, t start and t end are the start and end time of data collection.

[0081] In this embodiment, it is specifically necessary to explain the protection module. After receiving the confirmation signal sent by the identification module, the protection module controls the mechanical protection device of the laser scanner and keeps the temperature stable. The specific steps are as follows:

[0082] Step D1, check the status information in the confirmation signal, confirm that the carriage and wheelset have been successfully identified, start the mechanical protection device of the laser scanner, including controlling the stepper motor to open the protection gate, and start the air knife protection device of the window, and use the built-in temperature sensor to monitor the temperature of the scanner working area, denoted as T env , and set a temperature threshold T min =15℃, the temperature value T fed back by the temperature sensor env and the set temperature threshold T min Dynamically adjust the working status of heaters and fans to control the temperature of the working area;

[0083] Step D2: The power of the heater is expressed as P heater , the fan power is expressed as P fan , calculate the power of the heater and fan by the thermodynamic formula: P heater =αC p ΔT,Pfan =βC p ΔT, where ΔT = |T min -T env | is the temperature difference, C p is the specific heat capacity of air, α is the air flow rate controlled by the heater, and β is the air flow rate controlled by the fan;

[0084] The current temperature is lower than the set temperature threshold: T env <T min , start the heater and use a certain power P heater Continue heating until the temperature reaches the set value;

[0085] The current temperature exceeds the set temperature threshold: T env ≥T min , start the fan and set it to power P fan Air is drawn in for cooling.

[0086] In this embodiment, the management and calculation module specifically needs to be explained. The management and calculation module analyzes the data change trend according to the scan data and generates a measurement report. The specific steps are as follows:

[0087] Step S1: Receive the geometric parameter data of the carriage and wheelset from the measurement module, and perform data verification and time verification on the received data. The data verification includes checking whether all fields in the data packet are in the correct format and whether each parameter value is within a reasonable range. The time verification is whether there are overlapping collection time periods, and t end >t start ;

[0088] Step S2: Analyze the received geometric parameter data, perform time series analysis on it, calculate the parameter change rate, and express the measured value of a certain geometric parameter at time t as V(1), V(2), .., V(z). The specific formula of the parameter change rate is: Among them, R V (t) is the rate of change, which indicates the degree of change of the geometric parameter V(t) in each time interval. q+1 and V q Indicates that at time point t q+1 and t qWhen the geometric parameter measurement value is corresponding, for each geometric parameter time series data, the least squares method is used to fit the data, and the change trend diagram of each geometric parameter is drawn using the data visualization tool, and the maximum allowable change rate of each parameter is set. When the change rate of the parameter within a certain period of time exceeds the maximum allowable change rate, it means that the parameter is detected to be abnormal, and the abnormal parameter is marked in red. According to the results of data analysis, a detailed measurement report is automatically generated, including: the collection time period, the original measurement values ​​of each geometric parameter, and the change trend diagram of each geometric parameter. According to the parameter change trend, the health status of the equipment is evaluated and maintenance suggestions are provided.

[0089] Example 2

[0090] This embodiment provides a TWDS online wheelset detection data acquisition device, the device specifically includes: an induction sensor, a laser scanner, a measurement unit, a data processing server, and a communication module;

[0091] The inductive sensor is used to monitor the real-time position of the train on the track;

[0092] The laser scanner is used to accurately collect geometric data of the train wheelset;

[0093] The measuring unit is used to obtain scanning data from the laser scanner and transmit the data to the data processing server;

[0094] The data processing server receives data from the measuring unit, analyzes and calculates the data, and generates a measurement report;

[0095] The communication module uploads the processed data to the client application and database for subsequent analysis and storage.

[0096] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0097] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0098] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0099] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0100] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0101] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0102] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A TWDS online wheelset detection data acquisition system, characterized by: It includes position control module, identification module, protection module, measurement module, and management and calculation module; The position control module monitors the position of the train on the track through an inductive sensor, and sends a signal to the identification module and the protection module when confirming that the train enters the measurement area; After receiving the signal sent by the position control module, the identification module performs number identification on the carriage and the wheelset, and sends a confirmation signal to the protection module after the identification is completed; After receiving the confirmation signal sent by the identification module, the protection module controls the mechanical protection device of the laser scanner and keeps the temperature stable; After receiving the signal sent by the position control module, the measuring module uses a laser scanner to collect geometric data of the wheelset and transmits the data to the management and calculation module for processing; The management and calculation module analyzes the data change trend according to the scan data and generates a measurement report.

2. A TWDS online wheelset detection data acquisition system according to claim 1, characterized in that: The position control module monitors the position of the train on the track through the inductive sensor, and sends a signal to the measurement module, the identification module and the protection module when confirming that the train enters the measurement area. The specific steps include: installing 4 inductive sensors on the track, marked as sensors 1, 2, 3 and 4 respectively, to determine whether the train enters the measurement area; When sensor 1 detects a train, it indicates that the train has entered the measurement area, and sends an identification signal to the identification module. The signal content includes the timestamp of the train entering the measurement area and the current position of the train; When sensor No. 2 detects a train, it indicates that the train has entered the scanning area, and sends a start signal to the measurement module to collect geometric data of the wheelset. When sensor No. 3 detects that the train has left the scanning area, it indicates that the scanning process of the measurement module has been completed, and sends an end signal to the measurement module to confirm that the scanning is completed. When the train is traveling in the reverse direction, sensor No. 4 is enabled and used as a sensor to sense the approaching train, sensor No. 3 is used as a start signal sensor for the scanning area, and sensor No. 2 is used as an end signal sensor for the scanning area.

3. A TWDS online wheelset detection data acquisition system according to claim 1, characterized in that: After receiving the identification signal sent by the position control module, the identification module performs number identification on the carriage and the wheelset, and sends a confirmation signal to the protection module after the identification is completed. The specific steps are as follows: Step B1, car number identification: after receiving the identification signal from sensor No. 1, the car and wheels entering the measurement area are numbered and identified, the car number image is automatically captured by the camera, and the image acquisition start time is recorded, the car number is extracted from the image using the image recognition algorithm, and the identified car number is compared with the registration information in the vehicle registration database to determine the unique identification of the car; Step B2, wheelset number identification: According to the relative position between the carriage and the wheelset, the geometric parameters of the carriage and the wheelset are obtained by the measurement module, and the wheelset number is extracted and identified, further comprising the following steps: Step B201, geometric feature matching: by comparing the geometric features of the predetermined wheelset inside the carriage with the wheelset geometric features obtained in the measurement module, it is determined that the wheelset belongs to the position inside the carriage; Step B202: When the geometric features of the matched wheelset match the predetermined g-th wheelset in the carriage, the wheelset is numbered as g and associated with the carriage number; Step B3: Confirm the accuracy of identification by comparing the geometric parameters of the car and wheelset, as well as the number matching. When the car and wheelset numbers are identified and confirmed to be correct, the identification module sends a confirmation signal to the protection module, indicating that the car number and wheelset number have been successfully identified. The confirmation signal includes the car number, wheelset number, and confirmation status information.

4. A TWDS online wheelset detection data acquisition system according to claim 3, characterized in that: In the carriage number recognition step B1, the carriage number image is automatically captured by a camera, and the image acquisition start time is recorded, the carriage number is extracted from the image using an image recognition algorithm, and the recognized carriage number is compared with the registration information in the vehicle registration database to determine the unique identification of the carriage, further comprising the following steps: Step B101, image preprocessing: converting the acquired image into a grayscale image and removing noise from the image, converting the image into a binary image through threshold processing, and dividing the carriage number area; Step B102, feature extraction: Use the convolutional neural network algorithm to extract features from the preprocessed binary image, and obtain the position and character of the car number through convolution and pooling operations on the feature map. The convolution operation is to slide the convolution kernel on the input feature map, and generate the output feature map by calculating the weighted sum of each position. The specific formula is: Among them, F out (x, y) is the pixel value of the output feature map at position (x, y), k is the radius of the convolution kernel, and F in (x, y) is the pixel value of the input feature map, K(i, j) is the weight of the convolution kernel at position (i, j); The pooling operation is to use the maximum pooling operation after each convolution layer to reduce the size of the feature map. The specific calculation formula is: Among them, F pool (x, y) is the pixel value of the feature map at position (x, y) after pooling, p is the size of the pooling window, and F out (x, y) is the pixel value of the output feature map at position (x+i, y+j), and max means selecting the maximum value in the pooling window; After multiple layers of convolution and pooling, the feature map after the pooling operation is flattened into a one-dimensional vector F flatten And input to the fully connected layer for classification, y = f (W·F flatten +b), where y is the classification output, representing the category vector of the car number, W is the weight matrix, b is the bias, and f is the activation function.

5. The TWDS online wheelset detection data acquisition system according to claim 1 is characterized in that: After the measurement module receives the start signal sent by the position control module, it uses a laser scanner to collect the geometric data of the wheelset and transmits the data to the management and calculation module for processing. The specific steps are as follows: Step C1: After receiving the start signal from sensor No. 2, the measurement module starts the laser scanner to perform geometric measurement on the wheelset of the train and collects the geometric data of the wheelset, including the wheel rim height, wheel rim thickness, wheel rim slope value, wheel rim width and thickness, wheel diameter and wheelset inner distance; after receiving the end signal sent by sensor No. 3, the scanning is stopped; The wheel rim height is obtained by measuring the height difference of the outer surface of the wheel with a laser scanner. The specific formula is: h r =z top -z contact , where h r is the rim height, z top is the height of the top of the wheel, z contact is the height of the surface where the wheel contacts the track; The rim thickness is calculated by a laser scanner by scanning the rim surface and measuring the laser reflection points at different positions. The specific formula is: r =d outside -d inside , where t r is the rim thickness, d outside is the distance from the outer side of the wheel rim to the laser instrument, d inside is the distance from the inner side of the wheel rim to the laser instrument; The rim slope value is obtained by measuring the inclination angle of the rim surface, and the specific formula is: Where QR is the rim slope value, h r is the rim height, r base is the radius of the wheel rim; The rim width is the lateral width of the wheel rim, and the rim thickness is the vertical thickness of the rim from the wheel flange to the inner ring. The rim width and thickness are obtained by scanning the inner and outer contours of the wheel rim. The specific formula is: b =d flange -d web , t b =d rim-top -d rim-bottom , where w b is the rim width, d flange is the distance from the outermost side of the wheel rim to the laser instrument, d web is the distance from the rim centerline to the laser instrument, t b is the rim thickness, d rim-top is the distance from the top of the rim to the laser instrument, d rim_bottom is the distance from the bottom of the rim to the laser instrument; The wheel diameter is measured from the highest point to the lowest point of the outer edge of the wheel, expressed as D, and the inner distance of the wheelset is obtained by scanning the laser point on the inner side of the wheel, expressed as L; Step C2, data transmission: The collected geometric data is organized into a structured data packet and transmitted to the management and operation module. The data packet includes {h r ,t r ,QR,w b ,t b ,D,L,t start ,t end }, where h r is the rim height, t r is the rim thickness, QR is the rim slope value, w b is the rim width, t b is the rim thickness, D is the wheel diameter, L is the inside distance of the wheelset, t start and t end are the start and end time of data collection.

6. The TWDS online wheelset detection data acquisition system according to claim 1 is characterized in that: After receiving the confirmation signal sent by the identification module, the protection module controls the mechanical protection device of the laser scanner and keeps the temperature stable. The specific steps are as follows: Step D1, check the status information in the confirmation signal, confirm that the carriage and wheelset have been successfully identified, start the mechanical protection device of the laser scanner, including controlling the stepper motor to open the protection gate, and start the air knife protection device of the window, and use the built-in temperature sensor to monitor the temperature of the scanner working area, denoted as T env , and set a temperature threshold T min =15℃, the temperature value T fed back by the temperature sensor env and the set temperature threshold T min Dynamically adjust the working status of heaters and fans to control the temperature of the working area; Step D2: The power of the heater is expressed as P heater , the fan power is expressed as P fan , calculate the power of the heater and fan by the thermodynamic formula: P heater =αC p ΔT,P fan =βC p ΔT, where ΔT = |T min -T env | is the temperature difference, C p is the specific heat capacity of air, α is the air flow rate controlled by the heater, and β is the air flow rate controlled by the fan; The current temperature is lower than the set temperature threshold: T env <T min , start the heater and heater Continue heating until the temperature reaches the set value; The current temperature exceeds the set temperature threshold: T env ≥T min , start the fan and set it to power P fan Air is drawn in for cooling.

7. The TWDS online wheelset detection data acquisition system according to claim 1 is characterized in that: The management and calculation module analyzes the data change trend according to the scan data and generates a measurement report. The specific steps are as follows: Step S1: Receive the geometric parameter data of the carriage and wheelset from the measurement module, and perform data verification and time verification on the received data. The data verification includes checking whether all fields in the data packet are in the correct format and whether each parameter value is within a reasonable range. The time verification is whether there are overlapping collection time periods, and t end >t start ; Step S2: Analyze the received geometric parameter data, perform time series analysis on it, calculate the parameter change rate, and express the measured value of a certain geometric parameter at time t as V(1), V(2), .., V(z). The specific formula of the parameter change rate is: Among them, R V (t) is the rate of change, V q+1 and V q Indicates that at time point t q+1 and t q When the geometric parameter measurement value is corresponding, for each geometric parameter time series data, the least squares method is used to fit the data, and the change trend diagram of each geometric parameter is drawn using the data visualization tool, and the maximum allowable change rate of each parameter is set. When the change rate of the parameter within a certain period of time exceeds the maximum allowable change rate, it means that the parameter is detected to be abnormal, and the abnormal parameter is marked in red. According to the results of data analysis, a detailed measurement report is automatically generated, including: the collection time period, the original measurement values ​​of each geometric parameter, and the change trend diagram of each geometric parameter. According to the parameter change trend, the health status of the equipment is evaluated and maintenance suggestions are provided.

8. A TWDS online wheelset detection data acquisition device is applied to a TWDS online wheelset detection data acquisition system as claimed in any one of claims 1 to 7, characterized in that: Specifically include: The inductive sensor is used to monitor the real-time position of the train on the track; The laser scanner is used to accurately collect geometric data of the train wheelset; The measuring unit is used to obtain scanning data from the laser scanner and transmit the data to the data processing server; The data processing server receives data from the measuring unit, analyzes and calculates the data, and generates a measurement report; The communication module uploads the processed data to the client application and database for storage.

Images