Driving system detection method, device and equipment, storage medium and vehicle

Abstract

The invention discloses a detection method, device and equipment of a driving system, a storage medium and a vehicle, and relates to the technical field of vehicles. The method comprises the following steps: acquiring measurement data and working condition data of a target object; the measurement data and the working condition data are input into a digital twinborn model to be processed, at least one crack feature is obtained, and the digital twinborn model is obtained by training historical measurement data and historical working condition data; inputting the at least one crack feature into a crack detection reference model for detection to obtain a first amplitude vector; the crack index value is compared with a first preset threshold value, the detection result of the driving system is obtained, the crack index value is the absolute value of the difference value of the first amplitude vector and the second amplitude vector, and the second amplitude vector is obtained through calculation of the measurement data and the working condition data. According to the embodiment of the invention, the detection period of the driving system can be shortened, and the detection efficiency of the driving system is improved.

Description

Technical Field

[0001] The present application belongs to the field of vehicle technology, and in particular, relates to a detection method, device, equipment, storage medium and vehicle for a drive system. Background Art

[0002] Powertrain is the general term for the components and systems responsible for providing power in a car. It is composed of the engine, transmission system and drive system, and is the core part of the car. In order to meet the life extension and life determination requirements of the drive system in the powertrain, the powertrain needs to be tested.

[0003] Related technologies usually test the drive system through a variety of complex durability tests, which has a long testing cycle and low testing efficiency. Summary of the invention

[0004] The embodiment of the present application provides a detection method for a drive system, which can solve the problems of long detection cycle and low detection efficiency of the drive system in the prior art, shorten the detection cycle of the drive system, and improve the detection efficiency of the drive system.

[0005] In a first aspect, an embodiment of the present application provides a detection method for a drive system, the detection method for a drive system comprising:

[0006] Obtain measurement data and working condition data of the target object;

[0007] The measurement data and the operating condition data are input into the digital twin model for processing to obtain at least one crack feature, wherein the digital twin model is trained by the historical measurement data and the historical operating condition data, and the digital twin model obtains at least one crack feature by extracting crack features from the measurement data and the operating condition data;

[0008] Inputting at least one crack feature into a crack detection benchmark model for detection to obtain a first amplitude vector, the crack detection model calculates at least one crack input feature to obtain a depth value and a normalization coefficient, and corrects a third amplitude vector using the depth value and the normalization coefficient to obtain a first amplitude vector, wherein the third amplitude vector is obtained by processing the measurement data and the working condition data by the crack detection model;

[0009] The crack index value is compared with the first preset threshold value to obtain the detection result of the drive system. The crack index value is the absolute value of the difference between the first amplitude vector and the second amplitude vector. The second amplitude vector is calculated from the measurement data.

[0010] In some optional implementations of the first aspect, when the detection result is that the drive system is abnormal,

[0011] After comparing the crack index value with the first preset threshold value to obtain the detection result of the drive system, the method further includes:

[0012] When the crack fault joint file includes the second amplitude vector, the preset crack position and the preset crack size corresponding to the second amplitude vector are respectively searched from the crack fault joint file to obtain the corresponding target crack position and the target crack size. The crack fault joint file includes a mapping relationship between multiple preset amplitude vectors and multiple preset crack positions, and a mapping relationship between multiple preset amplitude vectors and multiple preset crack sizes. The preset amplitude vectors correspond to the preset crack positions one by one, and the preset amplitude vectors correspond to the preset crack sizes one by one.

[0013] In some optional implementations of the first aspect, when the detection result is that the drive system is abnormal,

[0014] After comparing the crack index value with the first preset threshold value to obtain the detection result of the drive system, the method further includes:

[0015] When the second amplitude vector is not included in the crack fault joint file, the preset crack position and the preset crack size corresponding to the third amplitude vector are respectively searched from the crack fault joint file to obtain the corresponding target crack position and the target crack size. The crack fault joint file includes a mapping relationship between multiple preset amplitude vectors and multiple preset crack positions, and a mapping relationship between multiple preset amplitude vectors and multiple preset crack sizes. The preset amplitude vectors correspond to the preset crack positions one-to-one, and the preset amplitude vectors correspond to the preset crack sizes one-to-one. The third amplitude vector is the amplitude vector with the smallest difference from the second amplitude vector among the multiple preset amplitude vectors.

[0016] In some optional embodiments of the first aspect, the crack detection benchmark model includes a personalized characterization sub-model, a finite element sub-model and a crack axis dynamics sub-model.

[0017] Inputting at least one crack feature into a crack detection benchmark model for detection to obtain a first amplitude vector, including:

[0018] Inputting the target commonality characterization vector and the target individuality characterization vector into the individuality characterization sub-model for processing to obtain a third amplitude vector, wherein the target commonality characterization vector and the target individuality characterization vector are both obtained from the measurement data and the working condition data;

[0019] Inputting at least one crack feature into a finite element sub-model for calculation to obtain shaft parameters, the shaft parameters including rotation speed, output torque and temperature;

[0020] The shaft parameters are input into the crack shaft dynamics sub-model for calculation to obtain the depth value and normalization coefficient;

[0021] The third amplitude vector is corrected by the depth value and the normalization coefficient to obtain the first amplitude vector.

[0022] In some optional implementations of the first aspect, the crack detection benchmark model includes a personalized characterization sub-model, and the training process of the personalized characterization sub-model includes:

[0023] Acquire a first training sample set, the first training sample set comprising a plurality of first training samples, each of the plurality of first training samples comprising a historical commonality characterization vector, a historical commonality characterization vector and a historical amplitude vector;

[0024] Using the first training sample set to train the first preset model to obtain a personalized representation sub-model;

[0025] And / or, the crack detection benchmark model includes a finite element sub-model, and the training process of the finite element sub-model includes:

[0026] Acquire a second training sample set, the second training sample set includes a plurality of second training samples, each of the plurality of second training samples includes a historical crack feature and a historical axis parameter corresponding to the historical crack feature;

[0027] The second preset model is trained using the second training sample set to obtain a finite element sub-model.

[0028] In some optional implementations of the first aspect, the crack detection benchmark model includes a crack axis dynamics sub-model, and the crack axis dynamics sub-model includes:

[0029]

[0030] Wherein, Md represents the total mass of the target object; x represents the velocity of the target object; ω represents the rotational speed of the target object; Gd represents the rotational inertia of the target object; Fd represents the tangential force of the target object; and Fc represents the tangential force at the crack position in the target object.

[0031] In some optional implementations of the first aspect, comparing the crack index value with the first preset threshold value to obtain a detection result of the drive system includes:

[0032] When the crack index value is greater than or equal to the first preset threshold, determining that the detection result of the drive system is that the drive system is abnormal;

[0033] When the crack index value is less than the first preset threshold value, it is determined that the detection result is that the drive system is normal.

[0034] Based on the same inventive concept, in a second aspect, an embodiment of the present application provides a detection device for a drive system, the device comprising:

[0035] An acquisition module, used to acquire measurement data and working condition data of a target object;

[0036] A processing module, used for inputting the measurement data and the working condition data into the digital twin model for processing to obtain at least one crack feature, wherein the digital twin model is trained by the historical measurement data and the historical working condition data, and the digital twin model obtains at least one crack feature by extracting crack features from the measurement data and the working condition data;

[0037] A detection module, used for inputting at least one crack feature into a crack detection benchmark model for detection to obtain a first amplitude vector, the crack detection model calculates at least one crack input feature to obtain a depth value and a normalization coefficient, and uses the depth value and the normalization coefficient to correct a third amplitude vector to obtain a first amplitude vector, and the third amplitude vector is obtained by the crack detection model processing measurement data and working condition data;

[0038] The comparison module is used to compare the crack index value with a first preset threshold value to obtain the detection result of the drive system. The crack index value is the absolute value of the difference between the first amplitude vector and the second amplitude vector. The second amplitude vector is calculated from the measurement data and the working condition data.

[0039] Based on the same inventive concept, in a third aspect, an embodiment of the present application provides an electronic device, the electronic device comprising a processor and a memory storing computer program instructions;

[0040] The processor reads and executes computer program instructions to implement the detection method of the drive system as described in the first aspect.

[0041] Based on the same inventive concept, in a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the detection method of the drive system of the first aspect is implemented.

[0042] Based on the same inventive concept, in the fifth aspect, an embodiment of the present application provides a computer program product. An embodiment of the present application provides a computer program product, and the computer program product includes computer program instructions. When the computer program instructions are executed by a processor, the detection method of the drive system of the first aspect is implemented.

[0043] Based on the same inventive concept, in a sixth aspect, an embodiment of the present application provides a vehicle, including at least one of the following:

[0044] A detection device for a drive system according to the second aspect;

[0045] Such as the electronic device of the third aspect.

[0046] According to the detection method, device, equipment, storage medium and vehicle of the drive system provided in the embodiment of the present application, firstly, the measurement data and working condition data are obtained, and then the measurement data and working condition data are input into the digital twin model for processing to obtain at least one crack feature, and then at least one crack feature is input into the crack detection benchmark model for detection to obtain the first amplitude vector, and finally the crack index value can be compared with the first preset threshold value to obtain the detection result of the drive system. That is to say, in the embodiment of the present application, the drive system is detected by the digital twin model, the crack detection benchmark model and the first preset threshold value, and the detection result of the drive system can be obtained without conducting multiple complex endurance tests, which can shorten the detection cycle of the drive system and improve the detection efficiency of the drive system. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0048] Figure 1 It is a flow chart of a detection method of a drive system provided in an embodiment of the present application;

[0049] Figure 2 is a schematic diagram of at least one crack feature provided in an embodiment of the present application;

[0050] Figure 3 is a cross-sectional schematic diagram of a target object provided in an embodiment of the present application;

[0051] Figure 4 is a structural schematic diagram of a detection device for a drive system provided in an embodiment of the present application;

[0052] Figure 5 It is a schematic diagram of the structure of an embodiment of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0053] In order to more clearly understand the above-mentioned purposes, features and advantages of the present application, the scheme of the present application will be further described below. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0054] In the following description, many specific details are set forth to facilitate a full understanding of the present application, but the present application may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only part of the embodiments of the present application, rather than all of the embodiments.

[0055] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0056] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0057] Before describing the technical solutions provided by the embodiments of the present application, in order to facilitate the understanding of the embodiments of the present application, the present application first specifically describes the problems existing in the related art:

[0058] Components such as the gear shaft and the center shaft in the differential are key components for determining the health and life of the vehicle's drive system. Related technologies usually test the system through a variety of composite durability tests, which has a long detection cycle and low detection efficiency. In addition, regular manual maintenance is required for after-sales maintenance, which has the problems of high cost and low accuracy.

[0059] The inventors have found that most of the failures of the differential are caused by cracks in the gear shaft or the middle shaft in the differential, and the cracks gradually expand until the gear shaft or the middle shaft is completely disconnected. Therefore, the drive system can be detected by detecting whether there are cracks in the gear shaft or the middle shaft in the differential.

[0060] In order to solve the problems of long detection cycle and low detection efficiency of the drive system in the related art, the embodiments of the present application provide a detection method, device, equipment, storage medium and vehicle for the drive system. The detection method for the drive system provided by the embodiments of the present application is first introduced below.

[0061] Figure 1 It is a flow chart of a detection method of a drive system provided in an embodiment of the present application.

[0062] like Figure 1As shown, the detection method of the drive system provided in the embodiment of the present application can be applied to the detection device and electronic equipment of the drive system, and the embodiment of the present application is described by taking the electronic equipment as an example. The detection method of the drive system provided in the embodiment of the present application can include the following S110 to S140.

[0063] S110: Acquire measurement data and operating condition data of the target object.

[0064] S120. Input the measurement data and the operating condition data into the digital twin model for processing to obtain at least one crack feature. The digital twin model is trained by historical measurement data and historical operating condition data. The digital twin model obtains at least one crack feature by extracting crack features from the measurement data and the operating condition data.

[0065] S130. Input at least one crack feature into a crack detection benchmark model for detection to obtain a first amplitude vector. The crack detection model calculates at least one crack input feature to obtain a depth value and a normalization coefficient. The depth value and the normalization coefficient are used to correct a third amplitude vector to obtain a first amplitude vector. The third amplitude vector is obtained by processing the measurement data and the operating condition data by the crack detection model.

[0066] S140. Compare the crack index value with the first preset threshold value to obtain a detection result of the drive system, wherein the crack index value is the absolute value of the difference between the first amplitude vector and the second amplitude vector, and the second amplitude vector is calculated from the measurement data.

[0067] According to the detection method of the drive system provided in the embodiment of the present application, the measurement data and the operating data are first obtained, and then the measurement data and the operating data are input into the digital twin model for processing to obtain at least one crack feature, and then at least one crack feature is input into the crack detection benchmark model for detection to obtain a first amplitude vector, and finally the crack index value can be compared with the first preset threshold value to obtain the detection result of the drive system. That is to say, in the embodiment of the present application, the drive system is detected by the digital twin model, the crack detection benchmark model and the first preset threshold value, and the detection result of the drive system can be obtained without conducting multiple complex endurance tests, which can shorten the detection cycle of the drive system and improve the detection efficiency of the drive system.

[0068] The specific implementation methods of the above steps are introduced below.

[0069] In S110, the target object may be a device in which cracks occur in the differential, causing the differential to fail. For example, the target object may be a gear shaft or a center shaft in the differential.

[0070] The measurement data may include output torque, rotational speed of the target object, and temperature of the target object. Output torque can be measured by torque sensors such as strain gauge sensors, magnetic sensors, and optical sensors. Rotational speed can be measured by photoelectric encoders, magnetic sensors, resonance sensors, and sound sensors. Temperature can be measured by thermocouples, thermistors, temperature sensors, and the like.

[0071] The operating condition data may include vehicle acceleration, vehicle speed, accelerator pedal request, brake pedal request, front and rear torque distribution ratio and wheel speed, etc.

[0072] Acceleration can be measured by accelerometers, global positioning systems (GPS), inertial measurement units (IMU), etc.

[0073] The front-to-rear torque distribution ratio may be the ratio of the torque output by the engine to be distributed between the front wheels and the rear wheels of the vehicle. The front-to-rear torque distribution ratio may be obtained through the power distribution system of the vehicle.

[0074] Wheel speed is the linear speed of the vehicle tire when it is in contact with the ground, usually expressed as the number of revolutions of the wheel per unit time. The wheel speed can be measured by a wheel speed sensor.

[0075] In S120, after acquiring the measurement data and operating condition data of the target object, the electronic device may also input the measurement data and operating condition data into the digital twin model for processing to obtain at least one crack feature.

[0076] The type of crack feature can be set according to actual conditions and is not limited here. Figure 2 As shown, at least one crack feature may include three crack features, namely crack feature 1, crack feature 2 and crack feature 3. Among them, crack feature 1 may represent a fine crack, crack feature 2 may represent a crack with a width greater than a width threshold, and crack feature 3 may represent an irregular crack. Each crack feature may include at least one of crack morphology, crack length, crack width, etc.

[0077] Acquire a common characterization vector and an individual characterization vector from the historical measurement data and the historical operating condition data;

[0078] When the monitoring indicator value is within a preset range, the monitoring indicator value is classified to obtain at least one degradation state, and the monitoring indicator value is the absolute value of the difference between the common characterization vector and the individual characterization vector.

[0079] The training process of the digital twin model may include:

[0080] Acquire a third training sample set, the third training sample set comprising a plurality of third training samples, each of the plurality of third training samples comprising historical measurement data, historical operating condition data and historical crack characteristics;

[0081] The third preset model is trained using the third training sample set to obtain a digital twin model.

[0082] The third preset model may include a neural network.

[0083] Exemplarily, historical measurement data and historical operating condition data of vehicles with different crack characteristics can be fed to a third preset model in a time series, so that the generated digital twin model can identify at least one crack feature in the crack generation process in a time series.

[0084] The historical measurement data may include historical output torque, historical rotation speed of the target object, historical temperature of the target object, and the like.

[0085] The historical operating condition data may include the vehicle's historical acceleration, historical vehicle speed, historical accelerator pedal requests, historical brake pedal requests, historical front and rear torque distribution ratios, and historical wheel speeds.

[0086] The historical crack characteristics may include at least one of historical crack morphology, historical crack length, and historical crack width.

[0087] The process of acquiring the historical measurement data and the historical operating condition data may be the same as the process of acquiring the measurement data and the operating condition data described above, and will not be described in detail here.

[0088] The digital twin model can sequentially perform signal preprocessing, deviation calculation, membership classification, model correction, unified physical model input and simulation prediction. Among them, signal preprocessing may include sliding smoothing, which can reduce the direct impact of the signal-to-noise ratio; deviation calculation can be to convert the time domain signal into the frequency domain signal using the short-time Fourier algorithm, and capture the difference between the characteristics of the frequency performance and the expected performance characteristics of the simulation prediction; membership classification can calculate the deviation and the actual health status of the target object to achieve classification and membership; model correction can be adjusted according to the latest parameters or thresholds used for classification and membership, and the adjustment results are input into the unified physical model for correction of the parameters in the unified physical model; the unified physical model can be a model used to characterize different target objects with different parameters, and the target objects have similarities; simulation prediction, that is, the unified physical model is based on mechanical theory and data science and has a certain predictiveness. Optionally, the results of simulation prediction can be subjected to deviation calculation.

[0089] In S130, after the electronic device inputs the measurement data and the operating condition data into the digital twin model for processing to obtain at least one crack feature, it may also input at least one crack feature into the crack detection reference model for detection to obtain a first amplitude vector.

[0090] The first magnitude vector may be a magnitude vector sorted by frequency for reference. The magnitudes in the first magnitude vector, and the second magnitude vector and the third magnitude vector described below may be magnitudes after the output torque is transformed in the frequency domain.

[0091] In some optional embodiments, the crack detection benchmark model may include a personalized characterization sub-model, a finite element sub-model, and a crack axis dynamics sub-model.

[0092] Inputting at least one crack feature into a crack detection benchmark model for detection to obtain a first amplitude vector may include:

[0093] Inputting the target commonality characterization vector and the target individuality characterization vector into the individuality characterization sub-model for processing to obtain a third amplitude vector, wherein the target commonality characterization vector and the target individuality characterization vector are both obtained from the measurement data and the working condition data;

[0094] Inputting at least one crack feature into a finite element sub-model for calculation to obtain shaft parameters, the shaft parameters including rotation speed, output torque and temperature;

[0095] The shaft parameters are input into the crack shaft dynamics sub-model for calculation to obtain the depth value and normalization coefficient;

[0096] The third amplitude vector is corrected by the depth value and the normalization coefficient to obtain the first amplitude vector.

[0097] In this embodiment, the target common characterization vector and the target individual characterization vector are processed through the personalized characterization sub-model, so that the details of the frequency and amplitude can be calculated; the third amplitude vector can be corrected through the finite element sub-model and the crack dynamics sub-model, thereby improving the accuracy of the first amplitude vector, thereby improving the accuracy of the detection results of the drive system.

[0098] The target commonality representation vector may be a vector representing the similarity of features in the frequency domain.

[0099] The target personality representation vector may be a vector representing unique fluctuations of performance characteristics in the frequency domain.

[0100] The personalized characterization sub-model may be a model capable of calculating details of the frequency and magnitude of the output torque.

[0101] The finite element sub-model may be a model capable of calculating an on-axis parameter according to at least one crack characteristic.

[0102] The crack shaft dynamics sub-model is a model that can calculate the depth value and normalization coefficient based on the shaft parameters.

[0103] The third amplitude vector may be an amplitude vector obtained after calculating the details of the frequency and the amplitude.

[0104] The depth value may be the depth of the crack on the target object.

[0105] Optionally, inputting the target common characterization vector and the target individual characterization vector into the personalized characterization sub-model for processing to obtain the third amplitude vector may include: using the personalized characterization sub-model to calculate the absolute value of the difference between the target common characterization vector and the target common characterization vector, and when the absolute value is within a preset range, classifying the absolute value to obtain the third amplitude vector. The preset range can be set according to actual conditions and is not limited here.

[0106] After feature extraction and quantitative diagnosis of the measured data, the third amplitude vector can be obtained through the personalized characterization sub-model. After the depth value and normalization coefficient are obtained using the finite element sub-module and the crack axis dynamics sub-model, the third amplitude vector can be corrected by the depth value and the normalization coefficient to obtain the first amplitude vector, and then whether cracks appear in the drive system can be predicted based on the first amplitude vector.

[0107] In some optional implementations, the crack detection benchmark model includes a personalized characterization sub-model, and the training process of the personalized characterization sub-model includes:

[0108] Acquire a first training sample set, the first training sample set comprising a plurality of first training samples, each of the plurality of first training samples comprising a historical commonality characterization vector, a historical commonality characterization vector and a historical amplitude vector;

[0109] The first preset model is trained using the first training sample set to obtain a personalized representation sub-model.

[0110] In this embodiment, the first preset model is trained using the first training sample set to obtain a personalized characterization sub-model, which provides a basis for subsequent detection of at least one crack feature.

[0111] The first preset model may include a neural network.

[0112] In some optional embodiments, the crack detection benchmark model includes a finite element sub-model, and the training process of the finite element sub-model includes:

[0113] Acquire a second training sample set, the second training sample set includes a plurality of second training samples, each of the plurality of second training samples includes a historical crack feature and a historical axis parameter corresponding to the historical crack feature;

[0114] The second preset model is trained using the second training sample set to obtain a finite element sub-model.

[0115] In this embodiment, the second preset model is trained using the second training sample set to obtain a finite element sub-model, which provides a basis for subsequent detection of at least one crack feature.

[0116] The second preset model may include a neural network.

[0117] The second training samples in the second training sample set can be obtained by changing the crack size by changing the crack length, crack width and radial position, or by changing the crack morphology, or by changing the number of cracks, wherein the crack morphology may include circumferential cracks, radial cracks, center hole cracks, tooth cracks and bottom cracks, and the number of cracks may include single cracks and multiple cracks.

[0118] The crack detection benchmark model includes a crack axis dynamics sub-model, which includes:

[0119]

[0120] Wherein, Md represents the total mass of the target object; x represents the acceleration of the target object; ω represents the rotational speed of the target object; Gd represents the rotational inertia of the target object; Fd represents the tangential force of the target object; and Fc represents the tangential force at the crack position in the target object. Represents the second derivative of the velocity of the target object, that is, the acceleration of the target object; Indicates the speed of the target object.

[0121] In this embodiment, the crack axis dynamics submodule is used to provide a basis for the subsequent correction of the third amplitude vector.

[0122] Alternatively, if Figure 3 As shown, the mass m lost at the crack position in the target object c Formula (2) can be satisfied.

[0123]

[0124] Wherein, δ represents the normalization coefficient; a represents the depth of the crack on the target object, that is, the depth value mentioned above; h represents the axial length of the target object; and ρ represents the density of the target object.

[0125] Optionally, the unbalanced force F at the crack location in the target object c It can satisfy formula (3)

[0126]

[0127] Wherein, R represents the radius of the target object; ω represents the rotation speed of the target object.

[0128] In S140, after the electronic device inputs at least one crack feature into the crack detection reference model for detection and obtains the first amplitude vector, it can also compare the crack index value with the first preset threshold to obtain the detection result of the drive system.

[0129] The second amplitude vector may be an amplitude vector actually extracted and sorted by frequency. The second amplitude vector may be understood as a feature sparse coding.

[0130] The calculation process of the second amplitude vector may include: performing sliding smoothing processing on the measurement data to obtain a processing result; performing deviation calculation on the processing result to obtain a calculation result of the deviation calculation, and performing membership classification on the calculation result to obtain the second amplitude vector.

[0131] The crack index value MQF can satisfy formula (4).

[0132] MQF=|FW| Formula (4)

[0133] Wherein, W represents the first magnitude vector; F represents the second magnitude vector.

[0134] In some optional implementations, the crack index value is compared with the first preset threshold value to obtain a detection result of the drive system, including:

[0135] When the crack index value is greater than or equal to the first preset threshold, determining that the detection result of the drive system is that the drive system is abnormal;

[0136] When the crack index value is less than the first preset threshold value, it is determined that the detection result is that the drive system is normal.

[0137] In this implementation, the detection result of the driving system can be determined quickly and accurately according to the first preset threshold.

[0138] When the crack index value is greater than or equal to the first preset threshold value, it can be considered that there is a crack in the drive system, and therefore, the detection result of the drive system is determined to be abnormal; when the crack index value is less than the first preset threshold value, it is considered that there is no crack in the drive system, and therefore, the detection result is determined to be normal.

[0139] The first preset threshold value may be set according to actual conditions and is not limited here. For example, the setting of the first preset threshold value may satisfy the 3σ principle, and the first preset threshold value may include θ±3σ, where σ represents the standard deviation and θ may be set according to actual conditions and is not limited here.

[0140] In some optional implementations, when the detection result is that the drive system is abnormal,

[0141] After comparing the crack index value with the first preset threshold value to obtain the detection result of the drive system, the method further includes:

[0142] When the crack fault joint file includes the second amplitude vector, the preset crack position and the preset crack size corresponding to the second amplitude vector are respectively searched from the crack fault joint file to obtain the corresponding target crack position and the target crack size. The crack fault joint file includes a mapping relationship between multiple preset amplitude vectors and multiple preset crack positions, and a mapping relationship between multiple preset amplitude vectors and multiple preset crack sizes. The preset amplitude vectors correspond to the preset crack positions one by one, and the preset amplitude vectors correspond to the preset crack sizes one by one.

[0143] In this embodiment, when the second amplitude vector is included in the crack fault joint file, the target crack location and target crack size can be quickly and accurately determined based on the crack fault joint file, providing a basis for accurately predicting the remaining life of the drive system and providing maintenance recommendations and decisions for the drive system.

[0144] The target crack size may include a target crack length and width.

[0145] Exemplarily, the crack fault joint file may be a crack fault joint dictionary argmin{(t-Dy) 2 +λ|y|}, where t represents the axial length of the differential center shaft or gear shaft, y represents the axial position information of the differential center shaft or gear shaft, Dy represents the differential of the axial position information of the differential center shaft or gear shaft, and λ represents a characteristic parameter that can correct the calculation result. Of course, the crack fault joint file can also be a file in other forms such as a list.

[0146] It is understandable that when cracks occur in the differential shaft or gear shaft, the characteristics of the long-term performance are sparse. In order to reduce the complexity of the digital twin model, a large number of samples are converted into sparse representations to form a joint file of crack faults, which improves the search efficiency.

[0147] In some optional implementations, when the detection result is that the drive system is abnormal,

[0148] After comparing the crack index value with the first preset threshold value to obtain the detection result of the drive system, the method further includes:

[0149] When the second amplitude vector is not included in the crack fault joint file, the preset crack position and the preset crack size corresponding to the third amplitude vector are respectively searched from the crack fault joint file to obtain the corresponding target crack position and the target crack size. The crack fault joint file includes a mapping relationship between multiple preset amplitude vectors and multiple preset crack positions, and a mapping relationship between multiple preset amplitude vectors and multiple preset crack sizes. The preset amplitude vectors correspond to the preset crack positions one-to-one, and the preset amplitude vectors correspond to the preset crack sizes one-to-one. The third amplitude vector is the amplitude vector with the smallest difference from the second amplitude vector among the multiple preset amplitude vectors.

[0150] In this embodiment, when the second amplitude vector is not included in the crack fault joint file, the target crack position and target crack size can be quickly determined based on the crack fault joint file, providing a basis for predicting the remaining life of the drive system and providing maintenance recommendations and decisions for the drive system.

[0151] That is to say, when the crack fault joint file does not include the second amplitude vector, the target crack position and the target crack size can be determined from the crack fault joint file according to the minimum residual principle.

[0152] Based on the same inventive concept as the above-mentioned detection method of the drive system, the embodiment of the present application further provides a detection device of the drive system. The detection device of the drive system is described in detail below.

[0153] Figure 4 It is a structural schematic diagram of a detection device for a drive system provided in an embodiment of the present application.

[0154] like Figure 4 As shown, the detection device 400 of the driving system provided in the embodiment of the present application can be applied to a vehicle. The detection device 400 of the driving system can include an acquisition module 410, a processing module 420, a detection module 430 and a comparison module 440.

[0155] Wherein, the acquisition module 410 is used to acquire the measurement data and working condition data of the target object;

[0156] A processing module 420 is used to input the measurement data and the operating condition data into the digital twin model for processing to obtain at least one crack feature, the digital twin model is trained by historical measurement data and historical operating condition data, and the digital twin model obtains at least one crack feature by extracting crack features from the measurement data and the operating condition data;

[0157] A detection module 430 is used to input at least one crack feature into a crack detection benchmark model for detection to obtain a first amplitude vector, the crack detection model calculates at least one crack input feature to obtain a depth value and a normalization coefficient, and uses the depth value and the normalization coefficient to correct a third amplitude vector to obtain a first amplitude vector, and the third amplitude vector is obtained by the crack detection model processing the measurement data and the working condition data;

[0158] The comparison module 440 is used to compare the crack index value with the first preset threshold value to obtain the detection result of the drive system. The crack index value is the absolute value of the difference between the first amplitude vector and the second amplitude vector. The second amplitude vector is calculated from the measurement data and the working condition data.

[0159] According to the detection device of the drive system provided in the embodiment of the present application, the measurement data and the operating data are first obtained, and then the measurement data and the operating data are input into the digital twin model for processing to obtain at least one crack feature, and then at least one crack feature is input into the crack detection benchmark model for detection to obtain a first amplitude vector, and finally the crack index value can be compared with the first preset threshold value to obtain the detection result of the drive system. That is to say, in the embodiment of the present application, the drive system is detected by the digital twin model, the crack detection benchmark model and the first preset threshold value, and the detection result of the drive system can be obtained without conducting multiple complex endurance tests, which can shorten the detection cycle of the drive system and improve the detection efficiency of the drive system.

[0160] In some optional implementations, when the detection result is that the drive system is abnormal,

[0161] The detection device 400 of the drive system further includes:

[0162] The first determination module is used to search for preset crack positions and preset crack sizes corresponding to the second amplitude vector from the crack fault joint file when the second amplitude vector is included in the crack fault joint file, and obtain the corresponding target crack position and target crack size. The crack fault joint file includes a mapping relationship between multiple preset amplitude vectors and multiple preset crack positions, and a mapping relationship between multiple preset amplitude vectors and multiple preset crack sizes. The preset amplitude vectors correspond to the preset crack positions one by one, and the preset amplitude vectors correspond to the preset crack sizes one by one.

[0163] If the detection result is that the drive system is abnormal,

[0164] The detection device 400 of the drive system further includes:

[0165] The second determination module is used to search for preset crack positions and preset crack sizes corresponding to the third amplitude vector from the crack fault joint file respectively when the second amplitude vector is not included in the crack fault joint file, so as to obtain the corresponding target crack position and target crack size. The crack fault joint file includes a mapping relationship between multiple preset amplitude vectors and multiple preset crack positions, and a mapping relationship between multiple preset amplitude vectors and multiple preset crack sizes. The preset amplitude vectors correspond to the preset crack positions one-to-one, and the preset amplitude vectors correspond to the preset crack sizes one-to-one. The third amplitude vector is the amplitude vector with the smallest difference from the second amplitude vector among the multiple preset amplitude vectors.

[0166] In some optional embodiments, the crack detection benchmark model includes a personalized characterization sub-model, a finite element sub-model, and a crack axis dynamics sub-model.

[0167] The detection module 430 includes:

[0168] An input submodule, used for inputting a target common characterization vector and a target individual characterization vector into a personalized characterization submodel for processing to obtain a third amplitude vector, wherein the target common characterization vector and the target individual characterization vector are both obtained from measurement data and working condition data;

[0169] A first calculation submodule is used to input at least one crack feature into a finite element submodel for calculation to obtain shaft parameters, where the shaft parameters include rotation speed, output torque and temperature;

[0170] The second calculation submodule is used to input the shaft parameters into the crack shaft dynamics submodel for calculation to obtain the depth value and normalization coefficient;

[0171] The correction submodule is used to correct the third amplitude vector by using the depth value and the normalization coefficient to obtain the first amplitude vector.

[0172] In some optional implementations, the crack detection benchmark model includes a personalized characterization sub-model, and the detection device 400 of the drive system further includes:

[0173] The acquisition module 410 is further used to acquire a first training sample set, the first training sample set includes a plurality of first training samples, each of the plurality of first training samples includes a historical commonality characterization vector, a historical commonality characterization vector and a historical amplitude vector;

[0174] A first training module, used to train the first preset model using the first training sample set to obtain a personalized representation sub-model;

[0175] And / or, the crack detection benchmark model includes a finite element sub-model, and the detection device 400 of the drive system further includes:

[0176] The acquisition module 410 is further used to acquire a second training sample set, where the second training sample set includes a plurality of second training samples, each of the plurality of second training samples includes a historical crack feature and a historical axis parameter corresponding to the historical crack feature;

[0177] A second training module, used to train the second preset model using a second training sample set to obtain a finite element sub-model;

[0178] And / or, the crack detection benchmark model includes a crack axis dynamics sub-model, and the crack axis dynamics sub-model includes:

[0179]

[0180] Wherein, Md represents the total mass of the target object; x represents the velocity of the target object; ω represents the rotational speed of the target object; Gd represents the rotational inertia of the target object; Fd represents the tangential force of the target object; and Fc represents the tangential force at the crack position in the target object.

[0181] In some optional implementations, the comparison module 440 includes:

[0182] A first determination submodule, configured to determine that the detection result of the drive system is an abnormality of the drive system when the crack index value is greater than or equal to a first preset threshold value;

[0183] The second determination submodule is used to determine that the detection result is that the drive system is normal when the crack index value is less than the first preset threshold.

[0184] Regarding the detection device of the driving system in the above embodiment, the specific manner in which each module performs operations and the beneficial effects have been described in detail in the embodiment of the method, and will not be elaborated here.

[0185] Figure 5 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application is shown.

[0186] The electronic device may include a processor 501 and a memory 502 storing computer program instructions.

[0187] Specifically, the processor 501 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0188] The memory 502 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 502 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 502 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 502 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 502 is a non-volatile solid-state memory.

[0189] The memory may include read-only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical or other physical / tangible memory storage devices. Thus, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to one aspect of the present application.

[0190] The processor 501 implements any one of the drive system detection methods in the above embodiments by reading and executing computer program instructions stored in the memory 502 .

[0191] In one example, the electronic device may further include a communication interface 503 and a bus 510. Figure 5 As shown, the processor 501, the memory 502, and the communication interface 503 are connected via a bus 510 and communicate with each other.

[0192] The communication interface 503 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0193] Bus 510 includes hardware, software or both, and the parts of online data flow billing equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-end bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Epress (PCI-) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 510 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.

[0194] In addition, in combination with the detection method of the drive system in the above embodiment, the embodiment of the present application can provide a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when the computer program instructions are executed by the processor, the detection method of the drive system provided in the embodiment of the present application is implemented.

[0195] An embodiment of the present application also provides a computer program product. When instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes a detection method for a drive system as provided in an embodiment of the present application.

[0196] The present application also provides a vehicle, the vehicle comprising at least one of the following:

[0197] A detection device for a drive system as in the above-mentioned embodiment;

[0198] Such as the electronic device in the above embodiment.

[0199] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0200] The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to execute the required commands. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0201] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0202] The present application is described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present application.It should be understood that each square block in the flowchart and / or block diagram and the combination of each square block in the flowchart and / or block diagram can be realized by computer program instructions.These computer program instructions can be provided to the processor of the detection device of a general-purpose computer, a special-purpose computer or other programmable drive system, to produce a kind of machine, so that these instructions executed by the processor of the detection device of the computer or other programmable drive system enable the realization of the function / action specified in one or more square blocks of the flowchart and / or block diagram.Such a processor can be but is not limited to a general-purpose processor, a special-purpose processor, a special application processor or a field programmable logic circuit.It can also be understood that each square block in the block diagram and / or the flowchart and the combination of the square blocks in the block diagram and / or the flowchart can also be realized by the dedicated hardware that performs the specified function or action, or can be realized by the combination of dedicated hardware and computer instructions.

[0203] The above are only specific implementation methods of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

[0204] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprises" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

Claims

1. A method for detecting a drive system, characterized in that: include: Obtain measurement data and working condition data of the target object; Inputting the measurement data and the operating condition data into a digital twin model for processing to obtain at least one crack feature, wherein the digital twin model is trained by historical measurement data and historical operating condition data, and the digital twin model extracts crack features from the measurement data and the operating condition data to obtain the at least one crack feature; Inputting the at least one crack feature into a crack detection benchmark model for detection to obtain a first amplitude vector, the crack detection model calculating the at least one crack input feature to obtain a depth value and a normalization coefficient, and using the depth value and the normalization coefficient to correct a third amplitude vector to obtain the first amplitude vector, the third amplitude vector being obtained by the crack detection model processing the measurement data and the operating condition data; The crack index value is compared with a first preset threshold value to obtain a detection result of the drive system, wherein the crack index value is an absolute value of a difference between a first amplitude vector and a second amplitude vector, and the second amplitude vector is calculated from the measurement data.

2. The detection method of the driving system according to claim 1, characterized in that: When the detection result is that the drive system is abnormal, After comparing the crack index value with the first preset threshold value to obtain the detection result of the drive system, the method further includes: When the second amplitude vector is included in the crack fault joint file, the preset crack position and the preset crack size corresponding to the second amplitude vector are respectively searched from the crack fault joint file to obtain the corresponding target crack position and the target crack size. The crack fault joint file includes a mapping relationship between multiple preset amplitude vectors and multiple preset crack positions, and a mapping relationship between multiple preset amplitude vectors and multiple preset crack sizes. The preset amplitude vectors correspond to the preset crack positions one-to-one, and the preset amplitude vectors correspond to the preset crack sizes one-to-one.

3. The detection method of the driving system according to claim 1, characterized in that: When the detection result is that the drive system is abnormal, After comparing the crack index value with the first preset threshold value to obtain the detection result of the drive system, the method further includes: When the second amplitude vector is not included in the crack fault joint file, the preset crack position and the preset crack size corresponding to the third amplitude vector are respectively searched from the crack fault joint file to obtain the corresponding target crack position and the target crack size. The crack fault joint file includes a mapping relationship between multiple preset amplitude vectors and multiple preset crack positions, and a mapping relationship between multiple preset amplitude vectors and multiple preset crack sizes. The preset amplitude vectors correspond to the preset crack positions one-to-one, and the preset amplitude vectors correspond to the preset crack sizes one-to-one. The third amplitude vector is the amplitude vector with the smallest difference from the second amplitude vector among the multiple preset amplitude vectors.

4. The detection method of the driving system according to claim 1, characterized in that: The crack detection benchmark model includes a personalized characterization sub-model, a finite element sub-model and a crack shaft dynamics sub-model. The step of inputting the at least one crack feature into a crack detection benchmark model for detection to obtain a first amplitude vector comprises: Inputting a target common characterization vector and a target individual characterization vector into the individual characterization sub-model for processing to obtain the third amplitude vector, wherein the target common characterization vector and the target individual characterization vector are both obtained from the measurement data and the operating condition data; Inputting the at least one crack feature into the finite element sub-model for calculation to obtain shaft parameters, wherein the shaft parameters include rotation speed, output torque and temperature; Inputting the on-axis parameters into the crack axis dynamics sub-model for calculation to obtain the depth value and the normalization coefficient; The third amplitude vector is corrected by using the depth value and the normalization coefficient to obtain a first amplitude vector.

5. The detection method of the driving system according to claim 1, characterized in that: The crack detection benchmark model includes a personalized characterization sub-model, and the training process of the personalized characterization sub-model includes: Acquire a first training sample set, the first training sample set comprising a plurality of first training samples, each of the plurality of first training samples comprising a historical commonality characterization vector, the historical commonality characterization vector and a historical amplitude vector; Using the first training sample set to train the first preset model to obtain the personalized representation sub-model; And / or, the crack detection benchmark model includes a finite element sub-model, and the training process of the finite element sub-model includes: Acquire a second training sample set, where the second training sample set includes a plurality of second training samples, and each second training sample in the plurality of second training samples includes a historical crack feature and a historical axis parameter corresponding to the historical crack feature; The second preset model is trained using the second training sample set to obtain the finite element sub-model.

6. The detection method of the driving system according to claim 1, characterized in that: The crack detection benchmark model includes a crack axis dynamics sub-model, and the crack axis dynamics sub-model includes: Wherein, Md represents the total mass of the target object; x represents the speed of the target object; ω represents the rotational speed of the target object; Gd represents the rotational inertia of the target object; Fd represents the tangential force of the target object; and Fc represents the tangential force at the crack position in the target object.

7. The detection method of a driving system according to any one of claims 1 to 6, characterized in that: The step of comparing the crack index value with the first preset threshold value to obtain a detection result of the drive system includes: When the crack index value is greater than or equal to the first preset threshold, determining that the detection result of the drive system is that the drive system is abnormal; When the crack index value is less than the first preset threshold, it is determined that the detection result is that the drive system is normal.

8. A detection device for a drive system, characterized in that: include: An acquisition module, used to acquire measurement data and working condition data of a target object; A processing module, used for inputting the measurement data and the operating condition data into a digital twin model for processing to obtain at least one crack feature, wherein the digital twin model is trained by historical measurement data and historical operating condition data, and the digital twin model obtains the at least one crack feature by extracting crack features from the measurement data and the operating condition data; a detection module, configured to input the at least one crack feature into a crack detection benchmark model for detection to obtain a first amplitude vector, the crack detection model calculates the at least one crack input feature to obtain a depth value and a normalization coefficient, and uses the depth value and the normalization coefficient to correct a third amplitude vector to obtain the first amplitude vector, the third amplitude vector being obtained by the crack detection model processing the measurement data and the operating condition data; A comparison module is used to compare the crack index value with a first preset threshold value to obtain a detection result of the drive system, wherein the crack index value is the absolute value of the difference between the first amplitude vector and the second amplitude vector, and the second amplitude vector is calculated from the measurement data.

9. An electronic device, characterized in that: The electronic device comprises a processor and a memory storing computer program instructions; The processor reads and executes the computer program instructions to implement the detection method of the drive system according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the detection method of the drive system according to any one of claims 1 to 7 is implemented.

11. A vehicle, characterized in that: Include at least one of the following: The detection device of the drive system according to claim 8; The electronic device as claimed in claim 9.

Images