Locomotive vibration mode identification method and system based on machine learning

Abstract

The invention relates to the technical field of locomotive vibration mode recognition, in particular to a locomotive vibration mode recognition method and system based on machine learning, and the method comprises the steps: obtaining the real-time vibration acceleration of a target locomotive, calculating a real-time deviation angle according to an induction inclination angle and the real-time vibration acceleration, judging whether the real-time deviation angle is larger than a deviation threshold value or not, and if yes, judging whether the real-time deviation angle is larger than the deviation threshold value; if yes, carrying out vibration adjustment on the real-time vibration acceleration to obtain a target vibration acceleration, and if not, taking the real-time vibration acceleration as the target vibration acceleration, carrying out machine learning on the original vibration recognition model through the historical vibration data set to obtain a target vibration recognition model, and according to the target vibration acceleration, carrying out vibration adjustment on the target vibration recognition model; and carrying out locomotive vibration mode identification on the target locomotive by using the target vibration identification model. According to the invention, manpower resource consumption in the locomotive vibration mode identification process can be reduced, and the accuracy of locomotive vibration mode identification is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of locomotive vibration pattern recognition, and in particular to a locomotive vibration pattern recognition method, system, electronic equipment and computer-readable storage medium based on machine learning. Background Art

[0002] The locomotive vibration generated during the operation of the locomotive is one of the main factors affecting the safety performance of the locomotive. The locomotive vibration will not only accelerate the wear of parts and shorten the maintenance cycle, but also excessive vibration may lead to driving safety accidents. Therefore, the rapid and accurate identification of the locomotive vibration mode during the operation of the locomotive is important for ensuring the safety of passengers and staff and improving the efficiency of locomotive maintenance.

[0003] The current method for identifying locomotive vibration patterns is usually to first obtain the vibration data of the locomotive during driving, and then have experts in related fields manually identify the vibration pattern of the locomotive based on the vibration data. Although this method can achieve the purpose of identifying the vibration pattern of the locomotive, it requires a lot of human resources, and human judgment is prone to subjective bias, which reduces the accuracy of locomotive vibration pattern recognition. Summary of the invention

[0004] The present invention provides a locomotive vibration pattern recognition method based on machine learning and a computer-readable storage medium, the main purpose of which is to reduce the human resource consumption in the locomotive vibration pattern recognition process and improve the accuracy of locomotive vibration pattern recognition.

[0005] To achieve the above object, the present invention provides a locomotive vibration pattern recognition method based on machine learning, comprising: Using a pre-built acceleration sensor to collect real-time vibration signals of the target locomotive, wherein the real-time vibration signals include: lateral vibration signals, longitudinal vibration signals and vertical vibration signals; Performing analog-to-digital conversion and error processing on the real-time vibration signal to obtain real-time vibration acceleration, wherein the real-time vibration acceleration includes: real-time lateral acceleration, real-time longitudinal acceleration and real-time vertical acceleration; Using a pre-built gravity sensing device to obtain a sensed tilt angle of the target locomotive, calculating a vibration tilt angle according to the real-time vibration acceleration, and calculating a real-time deviation angle of the target locomotive according to the sensed tilt angle and the vibration tilt angle; Determining whether the real-time deviation angle is greater than a preset deviation threshold; If the real-time deviation angle is greater than the deviation threshold, vibration adjustment is performed on the real-time vibration acceleration according to the real-time deviation angle to obtain a target vibration acceleration; If the real-time deviation angle is not greater than the deviation threshold, taking the real-time vibration acceleration as the target vibration acceleration; Acquire a historical vibration data set of the target locomotive, and set an original vibration value range of the target locomotive according to the historical vibration data set, wherein the original vibration value range includes: a lateral vibration value range, a longitudinal vibration value range, and a vertical vibration value range; According to the original vibration value range and the pre-constructed convolutional neural network, an original vibration recognition model is constructed, and the original vibration recognition model is machine-learned using the historical vibration data set to obtain a target vibration recognition model; According to the target vibration acceleration, a target vibration recognition model is used to perform locomotive vibration pattern recognition on the target locomotive.

[0006] Optionally, performing analog-to-digital conversion and error processing on the real-time vibration signal to obtain real-time vibration acceleration includes: Performing analog-to-digital conversion on the real-time vibration signal to obtain original vibration acceleration; The lateral zero offset, longitudinal zero offset and vertical zero offset of the acceleration sensor are obtained, and the original vibration acceleration is error processed according to the lateral zero offset, longitudinal zero offset and vertical zero offset to obtain the real-time vibration acceleration, wherein the real-time vibration acceleration is expressed as: ; in, represents the real-time lateral acceleration, represents the original lateral acceleration, Indicates the lateral zero point offset, represents the real-time longitudinal acceleration, represents the original longitudinal acceleration, Indicates the longitudinal zero point offset, represents the real-time vertical acceleration, represents the original vertical acceleration, Indicates the vertical zero offset.

[0007] Optionally, the calculating the vibration tilt angle according to the real-time vibration acceleration, and the calculating the real-time deviation angle of the target locomotive according to the induced tilt angle and the vibration tilt angle, comprises: According to the real-time vibration acceleration, the vibration tilt angle is calculated using the following formula: ; in, represents the vibration tilt angle, represents the inverse tangent function, represents the lateral acceleration, represents the longitudinal acceleration, represents the vertical acceleration; According to the sensing tilt angle and the vibration tilt angle, the real-time deviation angle is calculated using the following formula: ; in, Indicates the real-time deviation angle, Indicates the sensing tilt angle.

[0008] Optionally, the performing vibration adjustment on the real-time vibration acceleration according to the real-time deviation angle to obtain a target vibration acceleration includes: The following real-time rotation matrix is ​​constructed according to the real-time deviation angle: ; in, represents the real-time rotation formula, represents the cosine function, represents the sine function; According to the real-time rotation matrix, the real-time vibration acceleration is rotationally adjusted using the following formula to obtain the target vibration acceleration, wherein the target vibration acceleration includes: target lateral acceleration, target longitudinal acceleration and target vertical acceleration: ; ; ; ; in, represents the target lateral acceleration, represents the target longitudinal acceleration, Indicates the target vertical acceleration.

[0009] Optionally, setting the original vibration value range of the target locomotive according to the historical vibration data set includes: Acquire historical vibration peak values ​​of the historical vibration data set, wherein the historical vibration data set is a plurality of groups of acceleration data with vibration mode labels, and the historical vibration peak values ​​include: a lateral vibration peak value, a longitudinal vibration peak value, and a vertical vibration peak value; The lateral vibration peak value, the longitudinal vibration peak value and the vertical vibration peak value are respectively used as the original maximum lateral value, the original maximum longitudinal value and the original maximum vertical value to obtain the original maximum vibration value; According to a preset selection range, an original minimum vibration value is selected in the historical vibration data set, wherein the original minimum vibration value includes: an original minimum lateral value, an original minimum longitudinal value, and an original minimum vertical value; According to the original maximum vibration value and the original minimum vibration value, an original vibration value range is constructed, wherein the original vibration value range includes: a lateral vibration value range, a longitudinal vibration value range and a vertical vibration value range.

[0010] Optionally, the using the historical vibration data set to perform machine learning on the original vibration recognition model to obtain a target vibration recognition model includes: Randomly dividing the historical vibration data set into a vibration training data set and a vibration verification data set; Extracting vibration training data in sequence from the vibration training data set; Inputting the vibration training data into the original vibration recognition model to obtain a model recognition result; Identifying a vibration pattern label of the vibration training data, and determining whether the model recognition result is consistent with the vibration pattern label of the vibration training data; If the model recognition result is consistent with the vibration mode label of the vibration training data, the original vibration value range is used as the target vibration value range; If the model recognition result is inconsistent with the vibration mode label of the vibration training data, adjusting the original vibration value range according to the vibration training data to obtain a target vibration value range; Constructing a verification vibration recognition model according to the convolutional neural network and the target vibration value range; Extracting vibration verification data in sequence from the vibration verification data set, inputting the vibration verification data into a verification vibration identification model, and obtaining a model verification result; Identify the vibration pattern label of the vibration verification data, and determine whether the model verification result is consistent with the vibration pattern label of the vibration verification data: If the model verification result is inconsistent with the vibration pattern label of the vibration verification data, obtaining the inconsistent data in the vibration verification data, using the inconsistent data as vibration training data, using the verification vibration recognition model as the original vibration recognition model, and returning to the step of inputting the vibration training data into the original vibration recognition model; If the model verification result is consistent with the vibration pattern label of the vibration verification data, the verification vibration recognition model is used as the target vibration recognition model.

[0011] Optionally, adjusting the original vibration value range according to the vibration training data to obtain the target vibration value range includes: The vibration training data is expressed as: ; in, represents the vibration training data, represents the training lateral acceleration, represents the training longitudinal acceleration, Indicates training vertical acceleration; The original vibration range is expressed as: ; in, represents the original horizontal range, represents the original minimum horizontal value, represents the original maximum horizontal value, represents the original vertical value range, represents the original minimum vertical value, represents the original maximum vertical value, represents the original vertical range, Represents the original minimum vertical value, Indicates the original maximum vertical value; Determine the model verification result and the vibration difference type of the vibration mode label, wherein the vibration difference type includes: abnormal vibration of the label and normal vibration of the label; If the vibration difference type is label abnormal vibration, the original vibration value range is expanded according to the vibration training data to obtain the target vibration value range; If the vibration difference type is labeled normal vibration, the original vibration value range is reduced according to the vibration training data to obtain the target vibration value range.

[0012] Optionally, the determination of the model verification result and the vibration difference type of the vibration pattern label includes: Obtaining a training vibration pattern of a vibration pattern label and an identification vibration pattern of a model recognition result, wherein the training vibration pattern and the identification vibration pattern both include: a horizontal vibration pattern, a longitudinal vibration pattern, a vertical vibration pattern and a normal vibration pattern; determining whether the training vibration pattern appears in the identification vibration pattern; If the training vibration pattern does not appear in the identification vibration pattern, the vibration difference type is set as label abnormal vibration; If the training vibration pattern appears in the identification vibration pattern, the vibration difference type is set to the normal vibration of the tag.

[0013] Optionally, the performing locomotive vibration pattern recognition on the target locomotive using a target vibration recognition model according to the target vibration acceleration includes: Inputting the target vibration acceleration into a target vibration recognition model to obtain a predicted vibration value; The predicted vibration value is numerically compared with the target vibration value range to obtain the locomotive vibration mode, wherein the locomotive vibration mode includes: lateral vibration mode, longitudinal vibration mode, vertical vibration mode and normal vibration mode.

[0014] To achieve the above object, the present invention also provides a locomotive vibration pattern recognition system based on machine learning, comprising: A vibration data acquisition module is used to collect real-time vibration signals of a target locomotive using a pre-built acceleration sensor, wherein the real-time vibration signals include: lateral vibration signals, longitudinal vibration signals and vertical vibration signals, and perform analog-to-digital conversion and error processing on the real-time vibration signals to obtain real-time vibration acceleration, wherein the real-time vibration acceleration includes: real-time lateral acceleration, real-time longitudinal acceleration and real-time vertical acceleration; An angle error calculation module, used to obtain the sensed tilt angle of the target locomotive using a pre-built gravity sensing device, calculate the vibration tilt angle according to the real-time vibration acceleration, and calculate the real-time deviation angle of the target locomotive according to the sensed tilt angle and the vibration tilt angle; An angle error elimination module, used to determine whether the real-time deviation angle is greater than a preset deviation threshold, if the real-time deviation angle is greater than the deviation threshold, then vibration adjustment is performed on the real-time vibration acceleration according to the real-time deviation angle to obtain a target vibration acceleration, if the real-time deviation angle is not greater than the deviation threshold, then the real-time vibration acceleration is used as the target vibration acceleration, a historical vibration data set of a target locomotive is obtained, and an original vibration value range of the target locomotive is set according to the historical vibration data set, wherein the original vibration value range includes: a lateral vibration value range, a longitudinal vibration value range and a vertical vibration value range; The vibration pattern recognition module is used to construct an original vibration recognition model according to the original vibration value range and the pre-constructed convolutional neural network, perform machine learning on the original vibration recognition model using the historical vibration data set to obtain a target vibration recognition model, and perform locomotive vibration pattern recognition on the target locomotive using the target vibration recognition model according to the target vibration acceleration.

[0015] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising: a memory storing at least one instruction; and The processor executes the instructions stored in the memory to implement the locomotive vibration pattern recognition method based on machine learning.

[0016] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the above-mentioned locomotive vibration pattern recognition method based on machine learning.

[0017] The present invention is to solve the problem described in the background technology. The present invention uses an acceleration sensor to collect the real-time vibration signal of the target locomotive, and realizes the intelligent real-time acquisition of the vibration acceleration of the locomotive. The real-time vibration signal is converted into analog-to-digital conversion and error processing to obtain the real-time vibration acceleration, which converts the acquired electrical signal of the locomotive vibration into a real-time vibration acceleration value. The induced tilt angle of the target locomotive is obtained by using a gravity sensing device, and the contactless acquisition of the induced tilt angle of the target locomotive is completed, which provides a basis for the subsequent calculation of the direction offset error of the acceleration sensor. The vibration tilt angle is calculated according to the real-time vibration acceleration, and the vibration tilt angle indirectly calculated based on the real-time vibration acceleration is obtained, which provides conditions for the subsequent calculation of the direction offset error of the acceleration sensor. By calculating the real-time deviation angle of the target locomotive according to the induced tilt angle and the vibration tilt angle, the numerical representation of the direction offset error of the acceleration sensor is realized. Since the real-time deviation angle has an acceptable range, that is, there is no need to eliminate the deviation of all real-time deviation angles, so it is judged whether the real-time deviation angle is greater than the deviation threshold, and the real-time deviation angle within the deviation threshold can be screened. If the real-time deviation angle is greater than the deviation threshold, it means that the real-time deviation angle is not within the acceptable range, so the real-time vibration acceleration should be adjusted according to the real-time deviation angle to obtain the target vibration acceleration and eliminate the real-time deviation angle of the target locomotive. If the real-time deviation angle is not greater than the deviation threshold, it means that the real-time deviation angle is within the acceptable range. By taking the real-time vibration acceleration as the target vibration acceleration, unnecessary real-time deviation angle elimination can be skipped, which speeds up the entire locomotive vibration pattern recognition process. By obtaining the historical vibration data set of the target locomotive and setting the original vibration value range of the target locomotive according to the historical vibration data set, the basis for locomotive vibration pattern recognition is obtained. Further, according to the original vibration value range and convolutional neural network, the original vibration recognition model is constructed, and the original vibration recognition model is machine-learned using the historical vibration data set to obtain the target vibration recognition model. This step uses the characteristics of deep learning of convolutional neural networks to construct a model that can intelligently identify locomotive vibration patterns. The target vibration recognition model is not interfered by human subjective factors and has high accuracy. Finally, by inputting the target vibration acceleration into the target vibration recognition model, the locomotive vibration pattern recognition of the target locomotive is completed. Since this process does not require a large amount of manual participation, the consumption of human resources is reduced. Therefore, the present invention can reduce the consumption of human resources in the process of locomotive vibration pattern recognition and improve the accuracy of locomotive vibration pattern recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic diagram of a flow chart of a locomotive vibration pattern recognition method based on machine learning provided by an embodiment of the present invention; Figure 2A functional module diagram of a locomotive vibration pattern recognition system based on machine learning provided by one embodiment of the present invention; Figure 3 A schematic diagram of the structure of an electronic device for implementing the locomotive vibration pattern recognition method based on machine learning provided in one embodiment of the present invention.

[0019] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0020] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0021] The embodiment of the present application provides a locomotive vibration pattern recognition method based on machine learning. The execution subject of the locomotive vibration pattern recognition method based on machine learning includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the locomotive vibration pattern recognition method based on machine learning can be executed by software or hardware installed in a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0022] Reference Figure 1 FIG. 1 is a flow chart of a locomotive vibration pattern recognition method based on machine learning provided by an embodiment of the present invention. In this embodiment, the locomotive vibration pattern recognition method based on machine learning includes: S1. Using a pre-built acceleration sensor to collect real-time vibration signals of a target locomotive, wherein the real-time vibration signals include: a lateral vibration signal, a longitudinal vibration signal, and a vertical vibration signal.

[0023] It should be explained that the acceleration sensor refers to a three-axis acceleration sensor that can measure the acceleration in three directions during the travel of the locomotive. When setting the acceleration sensor, the travel direction of the locomotive is taken as the lateral direction, the direction perpendicular to the lateral direction but in the same plane as the travel direction is taken as the longitudinal direction, and the direction perpendicular to the plane formed by the lateral direction and the longitudinal direction is taken as the vertical direction. The target locomotive refers to the locomotive for which locomotive vibration mode identification is to be performed, for example: a heavy-load electric locomotive.

[0024] It is understandable that the locomotive engine is the main power source of the car. The piston movement and crankshaft rotation inside it will cause the locomotive to vibrate. Therefore, the locomotive vibration intensity generated inside the locomotive engine is relatively high. When the locomotive vibration is transmitted to the car body, it will become less obvious due to the effect of the vibration reduction device. Therefore, in order to fully identify and understand the locomotive vibration, the acceleration sensor should be installed at the locomotive engine.

[0025] It can be understood that the lateral vibration signal refers to the lateral electrical signal when the locomotive vibrates in the lateral direction, wherein the lateral electrical signal indicates the magnitude of the acceleration in the lateral direction of the locomotive. The longitudinal electrical signal refers to the longitudinal electrical signal when the locomotive vibrates in the longitudinal direction, wherein the longitudinal electrical signal indicates the magnitude of the acceleration in the longitudinal direction of the locomotive. The vertical vibration signal refers to the vertical electrical signal when the locomotive vibrates in the vertical direction, wherein the vertical electrical signal indicates the magnitude of the acceleration in the vertical direction of the locomotive.

[0026] It should be noted that the real-time vibration signal collected by the acceleration sensor should be based on the locomotive as a whole as a reference system, that is, the running acceleration of the locomotive itself will not affect the real-time vibration signal.

[0027] S2 performs analog-to-digital conversion and error processing on the real-time vibration signal to obtain real-time vibration acceleration, wherein the real-time vibration acceleration includes: real-time lateral acceleration, real-time longitudinal acceleration and real-time vertical acceleration.

[0028] It should be explained that the real-time vibration signal is a continuously changing voltage signal, not a specific acceleration value, so the real-time vibration signal needs to be converted into an analog-to-digital conversion to convert the voltage signal into an acceleration value. The analog-to-digital conversion refers to a technology that can convert a voltage signal into an acceleration value.

[0029] It is understandable that the acceleration sensor will produce a zero point offset due to locomotive vibration during operation. The zero point offset refers to the phenomenon that the reading of the acceleration sensor is not zero when the locomotive does not vibrate. This phenomenon will cause the acceleration sensor to produce errors when collecting real-time vibration signals, so error processing is required for this zero point offset.

[0030] It can be understood that the real-time vibration acceleration refers to the acceleration values ​​in the lateral, longitudinal and vertical directions obtained by converting the original vibration acceleration into digital form and processing the error.

[0031] In detail, the performing analog-to-digital conversion and error processing on the real-time vibration signal to obtain the real-time vibration acceleration includes: Performing analog-to-digital conversion on the real-time vibration signal to obtain original vibration acceleration; The lateral zero offset, longitudinal zero offset and vertical zero offset of the acceleration sensor are obtained, and the original vibration acceleration is error processed according to the lateral zero offset, longitudinal zero offset and vertical zero offset to obtain the real-time vibration acceleration, wherein the real-time vibration acceleration is expressed as: ; in, represents the real-time lateral acceleration, represents the original lateral acceleration, Indicates the lateral zero point offset, represents the real-time longitudinal acceleration, represents the original longitudinal acceleration, Indicates the longitudinal zero point offset, represents the real-time vertical acceleration, represents the original vertical acceleration, Indicates the vertical zero offset.

[0032] It is understandable that the original vibration acceleration refers to the acceleration with a specific value obtained through analog-to-digital conversion, but the original vibration acceleration has not been processed for error. The lateral zero offset refers to the zero offset occurring in the lateral direction. The longitudinal zero offset refers to the zero offset occurring in the longitudinal direction. The vertical zero offset refers to the zero offset occurring in the vertical direction.

[0033] S3. Using a pre-built gravity sensing device to obtain a sensed tilt angle of the target locomotive, calculating a vibration tilt angle according to the real-time vibration acceleration, and calculating a real-time deviation angle of the target locomotive according to the sensed tilt angle and the vibration tilt angle.

[0034] It should be explained that the gravity sensing device refers to a device that measures the induced tilt angle of the locomotive by the locomotive's own gravity, such as an optical sensor or a gyroscope. The induced tilt angle refers to the angle between the locomotive's driving direction and the horizontal plane measured directly by the gravity sensing device. The vibration tilt angle refers to the angle between the locomotive's driving direction and the horizontal plane calculated indirectly. The real-time deviation angle refers to the difference between the induced tilt angle and the vibration tilt angle.

[0035] It should be noted that the acceleration sensor is completely fitted to the locomotive engine. Therefore, when the locomotive vibrates, the acceleration sensor may become loose due to the vibration of the locomotive, resulting in a slight change in the direction measured by the acceleration sensor. This will cause a large angle error in subsequent calculations, so a gravity sensing device is introduced to calculate the angle error.

[0036] It can be understood that the gravity sensing device does not need to have direct contact with the locomotive, so the sensed tilt angle measured by the gravity sensing device will be minimally affected by the vibration of the locomotive. Therefore, the sensed tilt angle can be considered as a more accurate angle between the locomotive's travel direction and the horizontal plane. Therefore, the real-time deviation angle can be used to represent the measurement error of the acceleration sensor.

[0037] In detail, the step of calculating the vibration tilt angle according to the real-time vibration acceleration and calculating the real-time deviation angle of the target locomotive according to the induced tilt angle and the vibration tilt angle includes: According to the real-time vibration acceleration, the vibration tilt angle is calculated using the following formula: ; in, represents the vibration tilt angle, represents the inverse tangent function, represents the lateral acceleration, represents the longitudinal acceleration, represents the vertical acceleration; According to the sensing tilt angle and the vibration tilt angle, the real-time deviation angle is calculated using the following formula: ;

[0038] in, Indicates the real-time deviation angle, Indicates the sensing tilt angle.

[0039] S4. Determine whether the real-time deviation angle is greater than a preset deviation threshold.

[0040] It can be understood that the deviation threshold refers to a deviation angle set manually, and the deviation threshold can be obtained by querying relevant literature.

[0041] If the real-time deviation angle is greater than the deviation threshold, S5 is executed to perform vibration adjustment on the real-time vibration acceleration according to the real-time deviation angle to obtain a target vibration acceleration.

[0042] It is understandable that when the real-time deviation angle is greater than the deviation threshold, it means that the real-time vibration acceleration at this time has a large deviation from the actual vibration acceleration of the target locomotive, so the real-time vibration acceleration of the target locomotive needs to be adjusted.

[0043] In detail, the vibration adjustment of the real-time vibration acceleration according to the real-time deviation angle to obtain the target vibration acceleration includes: The following real-time rotation matrix is ​​constructed according to the real-time deviation angle: ; in, represents the real-time rotation formula, represents the cosine function, represents the sine function; According to the real-time rotation matrix, the real-time vibration acceleration is rotationally adjusted using the following formula to obtain the target vibration acceleration, wherein the target vibration acceleration includes: target lateral acceleration, target longitudinal acceleration and target vertical acceleration: ; ; ; ; in, represents the target lateral acceleration, represents the target longitudinal acceleration, Indicates the target vertical acceleration.

[0044] It should be explained that the real-time rotation matrix refers to the conversion of the original coordinate axes measured by the acceleration sensor into actual coordinate axes representing the actual situation, wherein the original coordinate axes refer to the three measurement directions initially set by the acceleration sensor, namely the horizontal direction, the longitudinal direction and the vertical direction, and the actual coordinate axes refer to the three directions actually measured when the acceleration sensor is offset in direction.

[0045] If the real-time deviation angle is not greater than the deviation threshold, S6 is executed to use the real-time vibration acceleration as the target vibration acceleration.

[0046] It is understandable that when the real-time deviation angle is not greater than the deviation threshold, it means that there is only a small deviation between the real-time vibration acceleration at this time and the actual vibration acceleration of the target locomotive, and this deviation has little effect on subsequent calculations. In order to speed up the process of vibration pattern recognition of the entire locomotive, the real-time vibration acceleration is not adjusted.

[0047] S7. Obtain a historical vibration data set of the target locomotive, and set an original vibration value range of the target locomotive according to the historical vibration data set, wherein the original vibration value range includes: a lateral vibration value range, a longitudinal vibration value range, and a vertical vibration value range.

[0048] It should be explained that the historical vibration data set refers to multiple groups of historical vibration accelerations about the target locomotive collected in the past, and the historical vibration accelerations include: historical lateral acceleration, historical longitudinal acceleration and historical vertical acceleration, wherein each group of historical vibration accelerations is manually detected to obtain the locomotive vibration mode corresponding to the vibration acceleration, and the locomotive vibration mode is affixed as a vibration label to the corresponding historical vibration data, wherein the locomotive vibration mode includes: lateral vibration, longitudinal vibration, vertical vibration and normal vibration.

[0049] It should be noted that the vibration label does not only include one vibration mode, it may include multiple locomotive vibration modes. If it is manually determined that a set of historical vibration accelerations does not have any vibration, the set of historical vibration accelerations will be labeled with a vibration label of normal vibration.

[0050] It is understandable that the historical vibration data set may include multiple historical lateral accelerations, multiple historical longitudinal accelerations, and multiple historical vertical accelerations. The lateral vibration value range refers to a lateral acceleration range selected from multiple historical lateral accelerations, the longitudinal vibration value range refers to a longitudinal acceleration range selected from multiple historical longitudinal accelerations, and the vertical vibration value range refers to a vertical acceleration range selected from multiple historical vertical accelerations.

[0051] For example, the historical lateral accelerations in a historical data set are: 1 , 7 , 4 , the preset selection range is 2, then the original maximum lateral value is the maximum value of the historical lateral acceleration, which is 7 , with the historical lateral acceleration 7 As the starting point, select an original minimum horizontal value of 4 with a distance of 2 in the direction of decreasing value. , so the original horizontal range is (4 7 ).

[0052] In detail, the setting of the original vibration value range of the target locomotive according to the historical vibration data set includes: Acquire historical vibration peak values ​​of the historical vibration data set, wherein the historical vibration data set is a plurality of groups of acceleration data with vibration mode labels, and the historical vibration peak values ​​include: a lateral vibration peak value, a longitudinal vibration peak value, and a vertical vibration peak value; The lateral vibration peak value, the longitudinal vibration peak value and the vertical vibration peak value are respectively used as the original maximum lateral value, the original maximum longitudinal value and the original maximum vertical value to obtain the original maximum vibration value; According to a preset selection range, an original minimum vibration value is selected in the historical vibration data set, wherein the original minimum vibration value includes: an original minimum lateral value, an original minimum longitudinal value, and an original minimum vertical value; According to the original maximum vibration value and the original minimum vibration value, an original vibration value range is constructed, wherein the original vibration value range includes: a lateral vibration value range, a longitudinal vibration value range and a vertical vibration value range.

[0053] It is understandable that the historical vibration data set may include multiple historical lateral accelerations, multiple historical longitudinal accelerations, and multiple historical vertical accelerations. The lateral vibration peak value refers to the historical lateral acceleration with the largest value among multiple historical lateral accelerations. The longitudinal vibration peak value refers to the historical longitudinal acceleration with the largest value among multiple historical longitudinal accelerations. The vertical vibration peak value refers to the historical vertical acceleration with the largest value among multiple historical vertical accelerations. Selecting the minimum vibration value refers to taking the original maximum vibration value as the starting point and determining a minimum vibration value in the direction of decreasing values ​​according to the selection range.

[0054] Exemplarily, there are five groups of historical vibration data in a certain historical vibration data set, wherein the first group of historical vibration data is: , the second set of historical vibration data is , the third set of historical vibration data is , where the subscript x represents the lateral direction, the subscript y represents the longitudinal direction, and the subscript z represents the vertical direction. The multiple historical lateral accelerations are: , and , from which the lateral vibration peak is selected as , multiple historical longitudinal accelerations are: , and , from which the longitudinal vibration peak is selected , multiple historical vertical accelerations are: , and , from which the vertical vibration peak is selected as .

[0055] For example, the historical lateral accelerations in a historical data set are: 1 , 7 , 4 , the preset selection range is 2, then the original maximum lateral value is the maximum value of the historical lateral acceleration, which is 7 , with the historical lateral acceleration 7 As the starting point, select an original minimum horizontal value of 4 with a distance of 2 in the direction of decreasing value. , so the original horizontal range is (4 7 ).

[0056] S8. Construct an original vibration recognition model according to the original vibration value range and the pre-constructed convolutional neural network, and use the historical vibration data set to perform machine learning on the original vibration recognition model to obtain a target vibration recognition model.

[0057] It should be explained that the convolutional neural network refers to a deep learning model, which can be used to extract data features of real-time vibration acceleration, and perform deep learning on real-time vibration acceleration according to the data features, and output predicted vibration values ​​based on real-time vibration acceleration, wherein the predicted vibration values ​​include: predicted lateral acceleration, predicted longitudinal acceleration and predicted vertical acceleration. The original vibration recognition model refers to a recognition model that uses the deep learning ability of the convolutional neural network to identify the vibration pattern of the locomotive. The machine learning refers to the process of training the original vibration recognition model through historical vibration data sets to make it have stronger locomotive vibration recognition capabilities. The target vibration recognition model refers to a recognition model with stronger locomotive vibration recognition capabilities.

[0058] It is understandable that since the vibration labels in the historical vibration data sets are obtained by manual subjective judgment, the vibration labels of the historical vibration data sets have strong human subjectivity. The vibration labels of these historical vibration data sets can represent human feelings about locomotive vibration, but since there is no unified standard, there will be a large number of vibration differences in actual locomotive pattern recognition. Therefore, these historical vibration data sets can be used to perform machine learning on the convolutional neural network to obtain a target vibration recognition model that can uniformly describe locomotive vibration.

[0059] Specifically, the historical vibration data set is used to perform machine learning on the original vibration recognition model to obtain a target vibration recognition model, including: Randomly dividing the historical vibration data set into a vibration training data set and a vibration verification data set; Extracting vibration training data in sequence from the vibration training data set; Inputting the vibration training data into the original vibration recognition model to obtain a model recognition result; Identifying a vibration pattern label of the vibration training data, and determining whether the model recognition result is consistent with the vibration pattern label of the vibration training data; If the model recognition result is consistent with the vibration mode label of the vibration training data, the original vibration value range is used as the target vibration value range; If the model recognition result is inconsistent with the vibration mode label of the vibration training data, adjusting the original vibration value range according to the vibration training data to obtain a target vibration value range; Constructing a verification vibration recognition model according to the convolutional neural network and the target vibration value range; Extracting vibration verification data in sequence from the vibration verification data set, inputting the vibration verification data into a verification vibration identification model, and obtaining a model verification result; Identify the vibration pattern label of the vibration verification data, and determine whether the model verification result is consistent with the vibration pattern label of the vibration verification data: If the model verification result is inconsistent with the vibration pattern label of the vibration verification data, obtaining the inconsistent data in the vibration verification data, using the inconsistent data as vibration training data, using the verification vibration recognition model as the original vibration recognition model, and returning to the step of inputting the vibration training data into the original vibration recognition model; If the model verification result is consistent with the vibration pattern label of the vibration verification data, the verification vibration recognition model is used as the target vibration recognition model.

[0060] It should be explained that the vibration training data set refers to a data set for model training of the original vibration recognition model. The vibration verification data set refers to a data set for accuracy verification of the verification vibration recognition model. The model recognition result refers to the locomotive vibration pattern output after recognition by the original vibration recognition model. The verification vibration recognition model refers to the recognition model obtained after the original vibration recognition model is trained with the vibration training data set. The model verification result refers to the locomotive vibration pattern output after recognition by the verification vibration recognition model. The inconsistent data refers to the vibration verification data whose model verification result is inconsistent with the vibration pattern label.

[0061] Specifically, the original vibration value range is adjusted according to the vibration training data to obtain the target vibration value range, including: The vibration training data is expressed as: ; in, represents the vibration training data, represents the training lateral acceleration, represents the training longitudinal acceleration, Indicates training vertical acceleration; The original vibration range is expressed as: ;

[0062] in, represents the original horizontal range, represents the original minimum horizontal value, represents the original maximum horizontal value, represents the original vertical value range, represents the original minimum vertical value, represents the original maximum vertical value, represents the original vertical range, Represents the original minimum vertical value, Indicates the original maximum vertical value; Determine the model verification result and the vibration difference type of the vibration mode label, wherein the vibration difference type includes: abnormal vibration of the label and normal vibration of the label; If the vibration difference type is label abnormal vibration, the original vibration value range is expanded according to the vibration training data to obtain the target vibration value range; If the vibration difference type is labeled normal vibration, the original vibration value range is reduced according to the vibration training data to obtain the target vibration value range.

[0063] It should be explained that the vibration difference type refers to the type in which the vibration recognition result is inconsistent with the vibration pattern label. The label abnormal vibration refers to the situation where the abnormal vibration label in the vibration pattern label is inconsistent with the vibration recognition result, that is, the vibration pattern label shows that the target locomotive has generated a certain abnormal vibration, but the vibration recognition result does not show the abnormal vibration, wherein the abnormal vibration may include: lateral vibration, longitudinal vibration and vertical vibration. The label normal vibration refers to the situation where the normal vibration label in the vibration pattern label is consistent with the vibration recognition result, that is, the vibration pattern label does not show that the target locomotive has generated a certain abnormal vibration, but the model recognition result shows that the target locomotive has generated the abnormal vibration.

[0064] It is understandable that when the vibration difference type is abnormal vibration of the label, it means that the vibration prediction value output by the original vibration recognition model exceeds the range of the original vibration value range, and the original vibration value range needs to be expanded, and the expansion process refers to using the vibration prediction value as the target vibration maximum value or the target vibration maximum value to replace the original vibration maximum value or the original vibration minimum value. When the vibration difference type is normal vibration of the label, it means that the vibration prediction value output by the original vibration recognition model is within the original vibration value range, and the original vibration value range needs to be reduced, and the reduction process refers to inserting the vibration prediction value into the original vibration value range, and using the vibration prediction value as the target vibration maximum value or the target vibration maximum value to replace the original vibration maximum value or the original vibration minimum value, wherein the replacement result is determined according to the distance between the vibration prediction value and the original vibration maximum value and the original vibration minimum value.

[0065] In detail, the judgment model verification result and the vibration difference type of the vibration mode label include: Obtaining a training vibration pattern of a vibration pattern label and an identification vibration pattern of a model recognition result, wherein the training vibration pattern and the identification vibration pattern both include: a horizontal vibration pattern, a longitudinal vibration pattern, a vertical vibration pattern and a normal vibration pattern; determining whether the training vibration pattern appears in the identification vibration pattern; If the training vibration pattern does not appear in the identification vibration pattern, the vibration difference type is set as label abnormal vibration; If the training vibration pattern appears in the identification vibration pattern, the vibration difference type is set to the normal vibration of the tag.

[0066] For example, the original vibration ranges of a certain original vibration recognition model are: the original lateral range is (4 7 ), the original vertical range is (1 6 ), the original vertical range is (2 8 ), Xiao Zhang inputs the following set of vibration training data into the original vibration recognition model: The historical lateral acceleration is 3 , the historical longitudinal acceleration is 5 , the historical vertical acceleration is 9 The vibration mode labels of the vibration training data are: lateral vibration and vertical vibration. The original vibration recognition model returns a set of vibration prediction values: the predicted lateral acceleration is 3 , the predicted longitudinal acceleration is 4 , the predicted vertical acceleration is 9 , the vibration prediction value is compared with the original vibration range, and the model recognition result is: longitudinal vibration. Among them, the vibration mode label has lateral vibration and vertical vibration, but the model recognition result does not have lateral vibration and vertical vibration. Therefore, the original lateral range and the original vertical range should be expanded, and the predicted lateral acceleration is used as the target lateral minimum value instead of the original lateral minimum value. The target lateral range is (3 7 ), the predicted vertical acceleration is used as the target vertical maximum value instead of the original vertical maximum value, and the target vertical value range is (2 9 ), the vibration mode label does not show longitudinal vibration, but longitudinal vibration appears in the model recognition result, so the original longitudinal value range should be reduced, and the predicted longitudinal acceleration is inserted into the original longitudinal value range to replace the original longitudinal maximum value as the target longitudinal maximum value, and the target longitudinal value range is (1 4 ).

[0067] S9. According to the target vibration acceleration, a target vibration recognition model is used to perform locomotive vibration pattern recognition on the target locomotive.

[0068] In detail, the target vibration acceleration is used to identify the vibration pattern of the target locomotive using the target vibration identification model, including: Inputting the target vibration acceleration into a target vibration recognition model to obtain a predicted vibration value; The predicted vibration value is numerically compared with the target vibration value range to obtain the locomotive vibration mode, wherein the locomotive vibration mode includes: lateral vibration mode, longitudinal vibration mode, vertical vibration mode and normal vibration mode.

[0069] It is understandable that the numerical comparison refers to the action of determining whether the predicted vibration value is within the target vibration value range. The locomotive vibration mode obtained by numerical comparison can be a plurality of abnormal vibration modes, wherein the abnormal vibration mode includes: lateral vibration, longitudinal vibration and vertical vibration.

[0070] The present invention is to solve the problem described in the background technology. The present invention uses an acceleration sensor to collect the real-time vibration signal of the target locomotive, and realizes the intelligent real-time acquisition of the vibration acceleration of the locomotive. The real-time vibration signal is converted into analog-to-digital conversion and error processing to obtain the real-time vibration acceleration, which converts the acquired electrical signal of the locomotive vibration into a real-time vibration acceleration value. The induced tilt angle of the target locomotive is obtained by using a gravity sensing device, and the contactless acquisition of the induced tilt angle of the target locomotive is completed, which provides a basis for the subsequent calculation of the direction offset error of the acceleration sensor. The vibration tilt angle is calculated according to the real-time vibration acceleration, and the vibration tilt angle indirectly calculated based on the real-time vibration acceleration is obtained, which provides conditions for the subsequent calculation of the direction offset error of the acceleration sensor. By calculating the real-time deviation angle of the target locomotive according to the induced tilt angle and the vibration tilt angle, the numerical representation of the direction offset error of the acceleration sensor is realized. Since the real-time deviation angle has an acceptable range, that is, there is no need to eliminate the deviation of all real-time deviation angles, so it is judged whether the real-time deviation angle is greater than the deviation threshold, and the real-time deviation angle within the deviation threshold can be screened. If the real-time deviation angle is greater than the deviation threshold, it means that the real-time deviation angle is not within the acceptable range, so the real-time vibration acceleration should be adjusted according to the real-time deviation angle to obtain the target vibration acceleration and eliminate the real-time deviation angle of the target locomotive. If the real-time deviation angle is not greater than the deviation threshold, it means that the real-time deviation angle is within the acceptable range. By taking the real-time vibration acceleration as the target vibration acceleration, unnecessary real-time deviation angle elimination can be skipped, which speeds up the entire locomotive vibration pattern recognition process. By obtaining the historical vibration data set of the target locomotive and setting the original vibration value range of the target locomotive according to the historical vibration data set, the basis for locomotive vibration pattern recognition is obtained. Further, according to the original vibration value range and convolutional neural network, the original vibration recognition model is constructed, and the original vibration recognition model is machine-learned using the historical vibration data set to obtain the target vibration recognition model. This step uses the characteristics of deep learning of convolutional neural networks to construct a model that can intelligently identify locomotive vibration patterns. The target vibration recognition model is not interfered by human subjective factors and has high accuracy. Finally, by inputting the target vibration acceleration into the target vibration recognition model, the locomotive vibration pattern recognition of the target locomotive is completed. Since this process does not require a large amount of manual participation, the consumption of human resources is reduced. Therefore, the present invention can reduce the consumption of human resources in the process of locomotive vibration pattern recognition and improve the accuracy of locomotive vibration pattern recognition.

[0071] like Figure 2 , which is a functional module diagram of a locomotive vibration pattern recognition system based on machine learning provided in one embodiment of the present invention.

[0072] The locomotive vibration pattern recognition system 100 based on machine learning of the present invention can be installed in an electronic device. According to the functions to be implemented, the locomotive vibration pattern recognition system 100 based on machine learning can include a vibration data acquisition module 101, an angle error calculation module 102, an angle error elimination module 103 and a vibration pattern recognition module 104. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0073] The vibration data acquisition module 101 is used to collect the real-time vibration signal of the target locomotive using a pre-built acceleration sensor, wherein the real-time vibration signal includes: a lateral vibration signal, a longitudinal vibration signal and a vertical vibration signal, and perform analog-to-digital conversion and error processing on the real-time vibration signal to obtain real-time vibration acceleration, wherein the real-time vibration acceleration includes: real-time lateral acceleration, real-time longitudinal acceleration and real-time vertical acceleration; The angle error calculation module 102 is used to obtain the sensed tilt angle of the target locomotive using a pre-built gravity sensing device, calculate the vibration tilt angle according to the real-time vibration acceleration, and calculate the real-time deviation angle of the target locomotive according to the sensed tilt angle and the vibration tilt angle; The angle error elimination module 103 is used to determine whether the real-time deviation angle is greater than a preset deviation threshold. If the real-time deviation angle is greater than the deviation threshold, the real-time vibration acceleration is vibration-adjusted according to the real-time deviation angle to obtain a target vibration acceleration. If the real-time deviation angle is not greater than the deviation threshold, the real-time vibration acceleration is used as the target vibration acceleration, a historical vibration data set of the target locomotive is obtained, and an original vibration value range of the target locomotive is set according to the historical vibration data set, wherein the original vibration value range includes: a lateral vibration value range, a longitudinal vibration value range and a vertical vibration value range; The vibration pattern recognition module 104 is used to construct an original vibration recognition model according to the original vibration value range and the pre-constructed convolutional neural network, perform machine learning on the original vibration recognition model using the historical vibration data set to obtain a target vibration recognition model, and perform locomotive vibration pattern recognition on the target locomotive using the target vibration recognition model according to the target vibration acceleration.

[0074] In detail, each module in the locomotive vibration pattern recognition system 100 based on machine learning in the embodiment of the present invention is used in the same manner as described above. Figure 1 The same technical means as the locomotive vibration pattern recognition method based on machine learning described in the text and can produce the same technical effects are used, which will not be repeated here.

[0075] like Figure 3 , is a schematic diagram of the structure of an electronic device for implementing a locomotive vibration pattern recognition method based on machine learning provided by an embodiment of the present invention.

[0076] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a locomotive vibration pattern recognition method program based on machine learning.

[0077] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory 11 may be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 may also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Further, the memory 11 also includes an internal storage unit of the electronic device 1 and an external storage device. The memory 11 can not only be used to store application software and various types of data installed in the electronic device 1, such as the code of the locomotive vibration pattern recognition method program based on machine learning, but also can be used to temporarily store data that has been output or is to be output.

[0078] The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules (such as a locomotive vibration pattern recognition method program based on machine learning, etc.) stored in the memory 11, and calls data stored in the memory 11 to execute various functions of the electronic device 1 and process data.

[0079] The bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 may be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0080] Figure 3 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0081] For example, although not shown, the electronic device 1 may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0082] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0083] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.

[0084] The locomotive vibration pattern recognition method program based on machine learning stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve: Using a pre-built acceleration sensor to collect real-time vibration signals of the target locomotive, wherein the real-time vibration signals include: lateral vibration signals, longitudinal vibration signals and vertical vibration signals; Performing analog-to-digital conversion and error processing on the real-time vibration signal to obtain real-time vibration acceleration, wherein the real-time vibration acceleration includes: real-time lateral acceleration, real-time longitudinal acceleration and real-time vertical acceleration; Using a pre-built gravity sensing device to obtain a sensed tilt angle of the target locomotive, calculating a vibration tilt angle according to the real-time vibration acceleration, and calculating a real-time deviation angle of the target locomotive according to the sensed tilt angle and the vibration tilt angle; Determining whether the real-time deviation angle is greater than a preset deviation threshold; If the real-time deviation angle is greater than the deviation threshold, vibration adjustment is performed on the real-time vibration acceleration according to the real-time deviation angle to obtain a target vibration acceleration; If the real-time deviation angle is not greater than the deviation threshold, taking the real-time vibration acceleration as the target vibration acceleration; Acquire a historical vibration data set of the target locomotive, and set an original vibration value range of the target locomotive according to the historical vibration data set, wherein the original vibration value range includes: a lateral vibration value range, a longitudinal vibration value range, and a vertical vibration value range; According to the original vibration value range and the pre-constructed convolutional neural network, an original vibration recognition model is constructed, and the original vibration recognition model is machine-learned using the historical vibration data set to obtain a target vibration recognition model; According to the target vibration acceleration, a target vibration recognition model is used to perform locomotive vibration pattern recognition on the target locomotive.

[0085] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figures 1 to 3 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0086] Furthermore, if the module / unit integrated in the electronic device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0087] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement: Using a pre-built acceleration sensor to collect real-time vibration signals of the target locomotive, wherein the real-time vibration signals include: lateral vibration signals, longitudinal vibration signals and vertical vibration signals; Performing analog-to-digital conversion and error processing on the real-time vibration signal to obtain real-time vibration acceleration, wherein the real-time vibration acceleration includes: real-time lateral acceleration, real-time longitudinal acceleration and real-time vertical acceleration; Using a pre-built gravity sensing device to obtain a sensed tilt angle of the target locomotive, calculating a vibration tilt angle according to the real-time vibration acceleration, and calculating a real-time deviation angle of the target locomotive according to the sensed tilt angle and the vibration tilt angle; Determining whether the real-time deviation angle is greater than a preset deviation threshold; If the real-time deviation angle is greater than the deviation threshold, vibration adjustment is performed on the real-time vibration acceleration according to the real-time deviation angle to obtain a target vibration acceleration; If the real-time deviation angle is not greater than the deviation threshold, taking the real-time vibration acceleration as the target vibration acceleration; Acquire a historical vibration data set of the target locomotive, and set an original vibration value range of the target locomotive according to the historical vibration data set, wherein the original vibration value range includes: a lateral vibration value range, a longitudinal vibration value range, and a vertical vibration value range; According to the original vibration value range and the pre-constructed convolutional neural network, an original vibration recognition model is constructed, and the original vibration recognition model is machine-learned using the historical vibration data set to obtain a target vibration recognition model; According to the target vibration acceleration, a target vibration recognition model is used to perform locomotive vibration pattern recognition on the target locomotive.

[0088] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only illustrative, and actual implementation may have other division methods.

[0089] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0090] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0091] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0092] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A locomotive vibration pattern recognition method based on machine learning, characterized in that: The method comprises: Using a pre-built acceleration sensor to collect real-time vibration signals of the target locomotive, wherein the real-time vibration signals include: lateral vibration signals, longitudinal vibration signals and vertical vibration signals; Performing analog-to-digital conversion and error processing on the real-time vibration signal to obtain real-time vibration acceleration, wherein the real-time vibration acceleration includes: real-time lateral acceleration, real-time longitudinal acceleration and real-time vertical acceleration; Using a pre-built gravity sensing device to obtain a sensed tilt angle of the target locomotive, calculating a vibration tilt angle according to the real-time vibration acceleration, and calculating a real-time deviation angle of the target locomotive according to the sensed tilt angle and the vibration tilt angle; Determining whether the real-time deviation angle is greater than a preset deviation threshold; If the real-time deviation angle is greater than the deviation threshold, vibration adjustment is performed on the real-time vibration acceleration according to the real-time deviation angle to obtain a target vibration acceleration; If the real-time deviation angle is not greater than the deviation threshold, taking the real-time vibration acceleration as the target vibration acceleration; Acquire a historical vibration data set of the target locomotive, and set an original vibration value range of the target locomotive according to the historical vibration data set, wherein the original vibration value range includes: a lateral vibration value range, a longitudinal vibration value range, and a vertical vibration value range; According to the original vibration value range and the pre-constructed convolutional neural network, an original vibration recognition model is constructed, and the original vibration recognition model is machine-learned using the historical vibration data set to obtain a target vibration recognition model; According to the target vibration acceleration, a target vibration recognition model is used to perform locomotive vibration pattern recognition on the target locomotive.

2. The locomotive vibration pattern recognition method based on machine learning as claimed in claim 1, characterized in that: The step of performing analog-to-digital conversion and error processing on the real-time vibration signal to obtain real-time vibration acceleration includes: Performing analog-to-digital conversion on the real-time vibration signal to obtain original vibration acceleration; The lateral zero offset, longitudinal zero offset and vertical zero offset of the acceleration sensor are obtained, and the original vibration acceleration is error processed according to the lateral zero offset, longitudinal zero offset and vertical zero offset to obtain the real-time vibration acceleration, wherein the real-time vibration acceleration is expressed as: ； in, represents the real-time lateral acceleration, represents the original lateral acceleration, Indicates the lateral zero point offset, represents the real-time longitudinal acceleration, represents the original longitudinal acceleration, Indicates the longitudinal zero point offset, represents the real-time vertical acceleration, represents the original vertical acceleration, Indicates the vertical zero offset.

3. The locomotive vibration pattern recognition method based on machine learning as claimed in claim 2, characterized in that: The step of calculating the vibration tilt angle according to the real-time vibration acceleration and calculating the real-time deviation angle of the target locomotive according to the induced tilt angle and the vibration tilt angle comprises: According to the real-time vibration acceleration, the vibration tilt angle is calculated using the following formula: ； in, represents the vibration tilt angle, represents the inverse tangent function, represents the lateral acceleration, represents the longitudinal acceleration, represents the vertical acceleration; According to the sensing tilt angle and the vibration tilt angle, the real-time deviation angle is calculated using the following formula: ； in, Indicates the real-time deviation angle, Indicates the sensing tilt angle.

4. The locomotive vibration pattern recognition method based on machine learning as claimed in claim 3, characterized in that: The step of performing vibration adjustment on the real-time vibration acceleration according to the real-time deviation angle to obtain a target vibration acceleration includes: The following real-time rotation matrix is ​​constructed according to the real-time deviation angle: ； in, represents the real-time rotation formula, represents the cosine function, represents the sine function; According to the real-time rotation matrix, the real-time vibration acceleration is rotationally adjusted using the following formula to obtain the target vibration acceleration, wherein the target vibration acceleration includes: target lateral acceleration, target longitudinal acceleration and target vertical acceleration: ； ； ； ； in, represents the target lateral acceleration, represents the target longitudinal acceleration, Indicates the target vertical acceleration.

5. The locomotive vibration pattern recognition method based on machine learning as claimed in claim 1, characterized in that: The step of setting the original vibration value range of the target locomotive according to the historical vibration data set includes: Acquire historical vibration peak values ​​of the historical vibration data set, wherein the historical vibration data set is a plurality of groups of acceleration data with vibration mode labels, and the historical vibration peak values ​​include: a lateral vibration peak value, a longitudinal vibration peak value, and a vertical vibration peak value; The lateral vibration peak value, the longitudinal vibration peak value and the vertical vibration peak value are respectively used as the original maximum lateral value, the original maximum longitudinal value and the original maximum vertical value to obtain the original maximum vibration value; According to a preset selection range, an original minimum vibration value is selected in the historical vibration data set, wherein the original minimum vibration value includes: an original minimum lateral value, an original minimum longitudinal value, and an original minimum vertical value; According to the original maximum vibration value and the original minimum vibration value, an original vibration value range is constructed, wherein the original vibration value range includes: a lateral vibration value range, a longitudinal vibration value range and a vertical vibration value range.

6. The locomotive vibration pattern recognition method based on machine learning as claimed in claim 5, characterized in that: The method of using the historical vibration data set to perform machine learning on the original vibration recognition model to obtain a target vibration recognition model includes: Randomly dividing the historical vibration data set into a vibration training data set and a vibration verification data set; Extracting vibration training data in sequence from the vibration training data set; Inputting the vibration training data into the original vibration recognition model to obtain a model recognition result; Identifying a vibration pattern label of the vibration training data, and determining whether the model recognition result is consistent with the vibration pattern label of the vibration training data; If the model recognition result is consistent with the vibration mode label of the vibration training data, the original vibration value range is used as the target vibration value range; If the model recognition result is inconsistent with the vibration mode label of the vibration training data, adjusting the original vibration value range according to the vibration training data to obtain a target vibration value range; Constructing a verification vibration recognition model according to the convolutional neural network and the target vibration value range; Extracting vibration verification data in sequence from the vibration verification data set, inputting the vibration verification data into a verification vibration identification model, and obtaining a model verification result; Identify the vibration pattern label of the vibration verification data, and determine whether the model verification result is consistent with the vibration pattern label of the vibration verification data: If the model verification result is inconsistent with the vibration pattern label of the vibration verification data, obtaining the inconsistent data in the vibration verification data, using the inconsistent data as vibration training data, using the verification vibration recognition model as the original vibration recognition model, and returning to the step of inputting the vibration training data into the original vibration recognition model; If the model verification result is consistent with the vibration pattern label of the vibration verification data, the verification vibration recognition model is used as the target vibration recognition model.

7. The locomotive vibration pattern recognition method based on machine learning as claimed in claim 6, characterized in that: The step of adjusting the original vibration value range according to the vibration training data to obtain the target vibration value range includes: The vibration training data is expressed as: ； in, represents the vibration training data, represents the training lateral acceleration, represents the training longitudinal acceleration, Indicates training vertical acceleration; The original vibration range is expressed as: ； in, represents the original horizontal range, represents the original minimum horizontal value, represents the original maximum horizontal value, represents the original vertical value range, represents the original minimum vertical value, represents the original maximum vertical value, represents the original vertical range, Represents the original minimum vertical value, Indicates the original maximum vertical value; Determine the model verification result and the vibration difference type of the vibration mode label, wherein the vibration difference type includes: abnormal vibration of the label and normal vibration of the label; If the vibration difference type is label abnormal vibration, the original vibration value range is expanded according to the vibration training data to obtain the target vibration value range; If the vibration difference type is labeled normal vibration, the original vibration value range is reduced according to the vibration training data to obtain the target vibration value range.

8. The locomotive vibration pattern recognition method based on machine learning as claimed in claim 7, characterized in that: The judgment model verification result and the vibration difference type of the vibration mode label include: Obtaining a training vibration pattern of a vibration pattern label and an identification vibration pattern of a model recognition result, wherein the training vibration pattern and the identification vibration pattern both include: a horizontal vibration pattern, a longitudinal vibration pattern, a vertical vibration pattern and a normal vibration pattern; determining whether the training vibration pattern appears in the identification vibration pattern; If the training vibration pattern does not appear in the identification vibration pattern, the vibration difference type is set as label abnormal vibration; If the training vibration pattern appears in the identification vibration pattern, the vibration difference type is set to the normal vibration of the tag.

9. The locomotive vibration pattern recognition method based on machine learning as claimed in claim 7, characterized in that: The method of performing locomotive vibration pattern recognition on a target locomotive using a target vibration recognition model according to the target vibration acceleration includes: Inputting the target vibration acceleration into a target vibration recognition model to obtain a predicted vibration value; The predicted vibration value is numerically compared with the target vibration value range to obtain the locomotive vibration mode, wherein the locomotive vibration mode includes: lateral vibration mode, longitudinal vibration mode, vertical vibration mode and normal vibration mode.

10. A locomotive vibration pattern recognition system based on machine learning, characterized in that: The system comprises: A vibration data acquisition module is used to collect real-time vibration signals of a target locomotive using a pre-built acceleration sensor, wherein the real-time vibration signals include: lateral vibration signals, longitudinal vibration signals and vertical vibration signals, and perform analog-to-digital conversion and error processing on the real-time vibration signals to obtain real-time vibration acceleration, wherein the real-time vibration acceleration includes: real-time lateral acceleration, real-time longitudinal acceleration and real-time vertical acceleration; An angle error calculation module, used to obtain the sensed tilt angle of the target locomotive using a pre-built gravity sensing device, calculate the vibration tilt angle according to the real-time vibration acceleration, and calculate the real-time deviation angle of the target locomotive according to the sensed tilt angle and the vibration tilt angle; An angle error elimination module, used to determine whether the real-time deviation angle is greater than a preset deviation threshold, if the real-time deviation angle is greater than the deviation threshold, then vibration adjustment is performed on the real-time vibration acceleration according to the real-time deviation angle to obtain a target vibration acceleration, if the real-time deviation angle is not greater than the deviation threshold, then the real-time vibration acceleration is used as the target vibration acceleration, a historical vibration data set of a target locomotive is obtained, and an original vibration value range of the target locomotive is set according to the historical vibration data set, wherein the original vibration value range includes: a lateral vibration value range, a longitudinal vibration value range and a vertical vibration value range; The vibration pattern recognition module is used to construct an original vibration recognition model according to the original vibration value range and the pre-constructed convolutional neural network, perform machine learning on the original vibration recognition model using the historical vibration data set to obtain a target vibration recognition model, and perform locomotive vibration pattern recognition on the target locomotive using the target vibration recognition model according to the target vibration acceleration.

Images