CN116106738A - Method, device, equipment and medium for detecting performance offline of electric drive system - Google Patents
Method, device, equipment and medium for detecting performance offline of electric drive system Download PDFInfo
- Publication number
- CN116106738A CN116106738A CN202310050265.1A CN202310050265A CN116106738A CN 116106738 A CN116106738 A CN 116106738A CN 202310050265 A CN202310050265 A CN 202310050265A CN 116106738 A CN116106738 A CN 116106738A
- Authority
- CN
- China
- Prior art keywords
- vibration
- performance
- drive system
- electric drive
- historical
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/34—Testing dynamo-electric machines
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/72—Electric energy management in electromobility
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Algebra (AREA)
- Control Of Electric Motors In General (AREA)
Abstract
The invention provides a method, a device, equipment and a medium for detecting the performance offline of an electric drive system, wherein the method comprises the following steps: obtaining vibration data to be measured of a plurality of measuring points of an electric driving system to be measured; performing order analysis on vibration data to be detected to obtain a vibration waterfall diagram to be detected, and generating a matrix tensor to be detected based on the vibration waterfall diagram to be detected to obtain an input data set to be detected; invoking a performance offline detection model to perform performance offline detection on the input data set to be detected, and obtaining a performance offline evaluation result; the performance offline detection model is obtained through historical vibration data and historical evaluation label training, and the performance offline detection model obtained through the historical vibration data and the historical evaluation label training can be used for performing performance offline detection on the electric drive system to be tested with multiple components, objectively evaluating the performance offline of the electric drive system to be tested, and improving the accuracy of the performance offline evaluation result.
Description
Technical Field
The invention relates to the technical field of new energy automobiles, in particular to a method, a device, equipment and a medium for detecting performance offline of an electric drive system.
Background
The electric drive system is a power source of a new energy automobile, the new energy automobile comprises a pure electric automobile, a range-extended automobile, a hydrogen fuel automobile and other automobiles, and comprises main components such as a motor, a speed reducer, a controller and other auxiliary components such as a charger and a DC-DC (direct current-direct current) converter. When power is transmitted, the electric drive system can generate various noises, such as motor electromagnetic noise, gear meshing noise of a speed reducer, pulse width modulation noise, abnormal sound of a bearing and the like, and the noises exceeding the design boundary can seriously reduce the driving experience of a user and even cause safety accidents. Therefore, performance offline detection of the electric drive system, that is, performance offline detection of noise, vibration and harshness NVH (Noise, vibration, harshness), is required, and failed electric drive systems are intercepted in advance.
For example, CN104792519a discloses a method for detecting the NVH of an automobile gearbox off line, which comprises an off line analyzer, a control unit, a data acquisition system, a loading system, a driving system and a gearbox. The off-line analyzer adopts an advanced order analysis algorithm to perform off-line analysis, and the gearbox is used as an off-line detection object and is provided with a vibration noise pickup sensor. The invention uses the reference spectrum as an objective standard by a method of generating an order spectrum according to vibration noise, calculating the standard deviation of each order spectrum and adjusting the offset of the whole reference spectrum relative to a zero line. However, the application scene of taking the reference spectral line obtained by the standard deviation of the order spectral line as an objective standard is limited, and the method is especially not suitable for performing performance offline detection on an electric drive system with multiple components, and the objective standard is not objective to the electric drive system, namely, the detection standard still has subjective problem when performing the performance offline detection on the electric drive system.
Disclosure of Invention
In view of the above-mentioned drawbacks of the prior art, the present invention provides a method, apparatus, device and medium for detecting performance offline of an electric drive system, so as to solve the above-mentioned technical problems of low applicability of performance offline detection of an electric drive system with multiple components, and subjectivity of detection standards.
The invention provides a method for detecting the performance offline of an electric drive system, which comprises the following steps: obtaining vibration data to be measured of a plurality of measuring points of an electric driving system to be measured; performing order analysis on the vibration data to be tested to obtain a vibration waterfall diagram to be tested, and generating a matrix tensor to be tested based on the vibration waterfall diagram to be tested to obtain an input data set to be tested; invoking a performance offline detection model to perform performance offline detection on the input data set to be detected to obtain a performance offline evaluation result; the performance offline detection model is obtained through historical vibration data and historical evaluation label training.
In one embodiment of the invention, historical vibration data and a historical evaluation tag are obtained; performing order analysis on the historical vibration data to obtain a historical vibration waterfall diagram, and generating a training matrix tensor based on the historical vibration waterfall diagram; and inputting the training matrix tensor and the historical evaluation label as a historical input data set into a first offline detection model for training to obtain a performance offline detection model.
In one embodiment of the invention, initial vibration data and initial evaluation labels of a plurality of measuring points of a historical electric drive system are obtained; matching the initial evaluation label with a preset evaluation label to determine a missing evaluation label; constructing abnormal characteristics for the initial vibration data based on the missing evaluation tag and the initial evaluation tag to obtain missing vibration data; and determining the initial vibration data and the missing vibration data as historical vibration data, and determining the initial evaluation tag and the missing evaluation tag as historical evaluation tags.
In an embodiment of the present invention, the historical input data set is subjected to data enhancement to obtain an enhanced input data set; dividing the enhanced input data set into a training set and a verification set according to a preset distribution proportion; performing initial training on the first offline detection model based on the training set to obtain a second offline detection model; and carrying out optimization training on the second offline detection model based on the verification set to obtain a performance offline detection model.
In one embodiment of the present invention, the historical input data set is at least one of replicated, rotated, amplified, noisy, and counter-generated to obtain an enhanced input data set.
In an embodiment of the invention, identity information of an electric drive system to be tested is received; generating a performance offline detection report based on the identity information and the performance offline evaluation result; if the performance offline detection report contains an unqualified electric drive system to be detected, displaying a preset normal vibration waterfall diagram and the vibration waterfall diagram to be detected in the performance offline detection report.
The invention provides an electric drive system performance off-line detection device, comprising: the system comprises a to-be-measured data acquisition module, a test module and a test module, wherein the to-be-measured data acquisition module is configured to acquire to-be-measured vibration data of a plurality of measuring points of an to-be-measured electric drive system; the input data set determining module is configured to analyze the vibration data to be detected in order to obtain a vibration waterfall diagram to be detected, and generate a matrix tensor to be detected based on the vibration waterfall diagram to be detected to obtain an input data set to be detected; the evaluation result determining module is configured to call a performance offline detection model to perform performance offline detection on the input data set to be detected to obtain a performance offline evaluation result; the performance offline detection model is obtained through historical vibration data and historical evaluation label training.
In an embodiment of the present invention, the electric driving system includes a speed reducer, a controller, and a motor, where the industrial personal computer is connected to the controller, the dynamometer, and the data acquisition card, the dynamometer is further connected to the speed reducer through a power output interface, each vibration sensor is respectively installed on a measuring point of the speed reducer, a measuring point of the controller, and a measuring point of the motor, and the data acquisition card is respectively connected to each vibration sensor; the industrial personal computer is used for sending control instructions to the electric driving system and the dynamometer; the electric drive system and the dynamometer are used for executing the control instruction, and the speed is controlled by controlling the torque and the rotating speed; the dynamometer is also used for feeding back the execution conditions of the torque and the rotating speed to the industrial personal computer; the vibration sensor is used for sensing vibration conditions of a plurality of measuring points of the electric drive system to obtain vibration data to be measured; the data acquisition card is used for acquiring the vibration data to be detected and transmitting the vibration data to be detected to the data acquisition module to be detected.
The invention also provides an electronic device comprising: one or more processors; a storage means for storing one or more programs that, when executed by the one or more processors, cause the electronic device to implement the electric drive system performance offline detection method of any of the embodiments described above.
The present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor of a computer, causes the computer to perform the electric drive system performance offline detection method according to any one of the embodiments described above.
The invention has the beneficial effects that: the invention provides a method, a device, equipment and a medium for detecting performance offline of an electric drive system, wherein the performance offline detection model is used for detecting the performance offline of vibration data to be detected of a plurality of measuring points of the electric drive system to be detected, and the performance offline detection of the electric drive system to be detected with multiple components can be realized; because the performance offline detection model is obtained through the training of the historical vibration data and the historical evaluation label, the performance offline evaluation result can be objectively obtained through the performance offline detection model, and the accuracy of the performance offline evaluation result is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application. It is apparent that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art. In the drawings:
FIG. 1 shows a schematic diagram of an exemplary system architecture to which the technical solution of an embodiment of the invention may be applied;
FIG. 2 illustrates a flow diagram of an electric drive system performance offline detection method according to one embodiment of the invention;
FIG. 3 illustrates a flow diagram of an electric drive system performance offline detection implementation method according to one embodiment of the present invention;
FIG. 4 illustrates a block diagram of an electric drive system performance offline detection apparatus, according to one embodiment of the present invention;
FIG. 5 illustrates a schematic detection of an electric drive system performance offline detection device according to one embodiment of the present invention;
fig. 6 shows a schematic diagram of a computer system suitable for use in implementing an embodiment of the invention.
Detailed Description
Further advantages and effects of the present invention will become readily apparent to those skilled in the art from the disclosure herein, by referring to the accompanying drawings and the preferred embodiments. The invention may be practiced or carried out in other embodiments that depart from the specific details, and the details of the present description may be modified or varied from the spirit and scope of the present invention. It should be understood that the preferred embodiments are presented by way of illustration only and not by way of limitation.
It should be noted that the illustrations provided in the following embodiments merely illustrate the basic concept of the present invention by way of illustration, and only the components related to the present invention are shown in the drawings and are not drawn according to the number, shape and size of the components in actual implementation, and the form, number and proportion of the components in actual implementation may be arbitrarily changed, and the layout of the components may be more complicated.
In the following description, numerous details are set forth in order to provide a more thorough explanation of embodiments of the present invention, it will be apparent, however, to one skilled in the art that embodiments of the present invention may be practiced without these specific details, in other embodiments, well-known structures and devices are shown in block diagram form, rather than in detail, in order to avoid obscuring the embodiments of the present invention.
It should be noted that NVH is an english abbreviation of noise, vibration and harshness (Noise, vibration, harshness), and is a comprehensive problem for measuring the quality of automobile manufacturing. The electric drive system is a power source of a new energy automobile, and can generate various noises when transmitting power, and the noises exceeding the design boundary can seriously reduce the driving experience of users and even cause safety accidents. The method for detecting the offline of the performance of the electric drive system provided by the invention is used for detecting the offline of the performance of the NVH of the electric drive system, and intercepting the electric drive system with the unacceptable performance of the NVH in advance.
The order analysis may relate the frequency spectrum and time history to the rotational speed of the rotating component, revealing the vibration and noise mechanisms. The vibration noise signal of the structure, such as the vibration noise of the engine, can be analyzed by the order, and the order relationship between the rotational components of the engine and the rotational speed of the crankshaft is determined prior to testing. When actually testing, if the response of a certain order is found to be large, the position where the engine component generates the response can be determined through the order relation.
The waterfall diagram obtained through order analysis is composed of frequency spectrum curves generated according to smaller rotation speed increment along a rotation speed shaft, each curve along the frequency shaft is a single instantaneous spectrum under a specific rotation speed step length, and the spectrum lines are stacked together according to the rotation speed sequence to form the waterfall diagram.
Referring to fig. 1, fig. 1 shows a schematic diagram of an exemplary system architecture to which the technical solution of the embodiment of the present invention may be applied. As shown in fig. 1, the system architecture may include a computer device 101 and an electric drive system performance offline detection apparatus 102. The computer device may be at least one of a general-purpose computer, a neural network computer, and the like. The related technician can use the computer equipment 101 to detect the vibration data to be detected of a plurality of measuring points of the electric driving system to be detected, and obtain the performance offline evaluation result. The electric drive system performance off-line detection device 101 is used for collecting vibration data to be detected and providing the vibration data to the computer equipment 101 for processing.
Illustratively, after the computer device 101 obtains vibration data to be measured of a plurality of measuring points of the electric drive system to be measured, performing order analysis on the vibration data to be measured to obtain a vibration waterfall diagram to be measured, and generating a matrix tensor to be measured based on the vibration waterfall diagram to be measured to obtain an input data set to be measured; invoking a performance offline detection model to perform performance offline detection on the input data set to be detected, and obtaining a performance offline evaluation result; the performance offline detection model is obtained through historical vibration data and historical evaluation label training. In one embodiment of the invention, the objective performance offline evaluation result of the electric drive system to be tested can be obtained through the performance offline detection model, and the accuracy of the performance offline evaluation result is improved.
In order to solve the technical problems, the invention provides a method, a device, equipment and a medium for detecting the performance of an electric drive system in an offline manner, and the implementation details of the technical scheme of the embodiment of the invention are explained in detail below.
Referring to fig. 2, fig. 2 is a flow chart illustrating a method for detecting performance of an electric drive system in a offline state according to an embodiment of the invention. As shown in fig. 2, in an exemplary embodiment, the method for detecting the performance of the electric drive system includes at least steps S210 to S230, which are described in detail as follows:
step S210, obtaining vibration data to be measured of a plurality of measuring points of the electric drive system to be measured.
In one embodiment of the invention, the electric drive system comprises a speed reducer, a motor, a controller and other main components, and vibration conditions of the electric drive system during operation are sensed through a plurality of vibration sensors arranged on a measuring point of the speed reducer, a measuring point of the motor and a measuring point of the controller in the electric drive system in a pressing mode, and vibration data to be measured of the plurality of measuring points are collected by the data collecting card. Under the condition that the normal operation of the electric drive system is not affected, the number of the measuring points on the main component can be multiple, namely, the vibration condition of one main component can be sensed through a plurality of vibration sensors.
Step S220, performing order analysis on the vibration data to be detected to obtain a vibration waterfall diagram to be detected, and generating a matrix tensor to be detected based on the vibration waterfall diagram to be detected to obtain an input data set to be detected.
In one embodiment of the invention, the vibration data to be measured is subjected to order analysis to obtain a vibration waterfall diagram to be measured, the frequency spectrum of which changes along with the rotation speed, and the vibration data to be measured of one measuring point can generate a vibration waterfall diagram to be measured. The predetermined matrix tensor dimension is determined from the predetermined data input structure, and may be one-dimensional or two-dimensional or three-dimensional or higher. And combining the vibration waterfalls to be measured of each measuring point to generate a matrix tensor to be measured of a preset matrix tensor dimension, and obtaining an input data set to be measured.
And step S230, calling a performance offline detection model to perform performance offline detection on the input data set to be detected, and obtaining a performance offline evaluation result.
The performance offline detection model is obtained through historical vibration data and historical evaluation label training.
In one embodiment of the invention, a machine learning model, namely a first offline detection model, is built, and a preset input data structure, the types of anomalies to be detected and the number of categories are determined. Determining a preset matrix tensor dimension when determining a preset input data structure; the type of the abnormality to be detected is preset evaluation labels, such as motor bearing abnormality, gear bump abnormality, motor electromagnetic order vibration abnormality and the like. In the present invention, the machine learning model may use a conventional machine learning model such as a support vector machine (SupportVectorMachine, SVM), logistic regression, naive bayes, an extreme learning machine, etc.; deep learning models that are popular today, such as convolutional neural networks (ConvolutionalNeuralNetworks, CNN), recurrent Neural Networks (RNNs), long short-term memory models (LSTM), deep residual error networks (Deep ResidualNetwork, resNet), auto encoders, deep belief networks, dense networks, or variations and combinations of the above, may also be used.
In one embodiment of the invention, historical vibration data and a historical evaluation tag are obtained; performing order analysis on the historical vibration data to obtain a historical vibration waterfall diagram with the frequency spectrum changing along with the rotating speed, and combining the historical vibration waterfall diagrams of a plurality of measuring points based on the preset matrix tensor dimension to generate a training matrix tensor. And combining the training matrix tensor and the history evaluation label to generate a history input data set, and inputting the history input data set into the first offline detection model for training to obtain the performance offline detection model.
In one embodiment of the present invention, initial vibration data of a plurality of measuring points of the historical electric drive system and an initial evaluation tag are obtained, wherein the initial vibration data is collected by the electric drive system performance offline detection device provided by the present invention, and the initial evaluation tag can be obtained by evaluating the historical electric drive system manually, which is only an example, and the present invention is not limited in any way. And performing order analysis on the initial vibration data to obtain an initial vibration waterfall diagram. Considering that the vibration data of part of abnormal categories is missing at an early stage, the initial evaluation tag and the preset evaluation tag can be matched, and the missing evaluation tag can be determined. According to development experience, constructing abnormal characteristics on an initial vibration waterfall diagram based on the missing evaluation label and the initial evaluation label, for example, aiming at abnormal motor bearings and abnormal gear collisions, specific abnormal characteristics of the abnormal motor bearings and the abnormal gear collisions can be constructed on the initial vibration waterfall diagram aiming at the characteristics of the abnormal motor bearings and the abnormal gear collisions; for another example, aiming at the fact that the electromagnetic order vibration of the motor is larger, the larger electromagnetic order characteristic of the motor can be constructed on the initial vibration waterfall diagram, and missing vibration data corresponding to the missing evaluation tag can be supplemented through the mode. The initial vibration data and the missing vibration data are determined as historical vibration data, and the initial evaluation tag and the missing evaluation tag are determined as historical evaluation tags.
In one embodiment of the invention, in order to achieve the purpose of preventing the machine learning model from being over fitted and improving the robustness of the performance offline detection model, an equilibrium enhanced input data set is obtained by data enhancement to a historical input data set. Data enhancement is the processing of raw data by techniques including, but not limited to, copying, rotation, amplification, noise addition, countermeasure generation, etc., to generate more enhanced data without materially adding data, the enhanced data being more balanced than the type of raw data.
In one embodiment of the present invention, the enhanced input data set is divided into a training set and a verification set according to a preset allocation ratio, and in the present invention, the preset allocation ratio may be set to 7:3, that is, seven of the total number of the enhanced input data sets is occupied by the training set, three of the total number of the enhanced input data sets is occupied by the verification set, and this preset allocation ratio is only an example, and the present invention does not limit the preset allocation ratio. Performing initial training on the first offline detection model based on the training set to obtain a second offline detection model; and carrying out optimization training on the second offline detection model based on the verification set to obtain the performance offline detection model.
In one embodiment of the invention, the first offline detection model learns the mapping rule of a plurality of training sets of each category by using a gradient descent method or other updating iterative methods in the traditional machine learning model or the deep learning model, optimizes the parameters of the first offline detection model, and adaptively forms an inherent objective evaluation standard, wherein the objective evaluation standard is a performance offline evaluation result obtained when performance offline detection is carried out on vibration data to be detected, namely, an abnormal category. And carrying out optimization training on the second offline detection model based on the verification set, improving the detection precision, and obtaining the offline detection model with excellent detection precision.
In one embodiment of the present invention, identity information of an electric drive system to be measured is received, and the identity information of the electric drive system to be measured may be a number of the electric drive system to be measured. And the performance offline evaluation result gives out an abnormal class, and the qualification condition of the electric drive system to be tested is determined according to the identity information and the abnormal class, so that a performance offline detection report is generated. If the disqualified electric driving system to be tested exists, the preset normal vibration waterfall and the vibration waterfall diagram to be tested are displayed in the performance offline detection report as comparison of the normal state and the abnormal state.
Referring to fig. 3, fig. 3 is a flow chart illustrating a method for implementing performance offline detection of an electric drive system according to an embodiment of the present invention. As shown in fig. 3, steps 301 to 307 are model training phases, and steps 308 to 312 are model application phases. Step S301, a first offline detection model is built: the first offline detection model can be a traditional machine learning model or a deep learning model, and is used for determining a preset input data structure, an abnormal category to be detected and a category number; step S302, acquiring historical vibration data and a historical evaluation tag: the method comprises the steps that vibration conditions of a plurality of measuring points of a historical electric drive system perceived by a vibration sensor are collected through a data collection card, historical vibration data are obtained, and vibration conditions corresponding to the historical vibration data are evaluated to obtain a historical evaluation label; step S303, obtaining a historical vibration waterfall diagram: obtaining a historical vibration waterfall diagram through order analysis; step S304, generating a history input data set: combining the historical vibration waterfall graphs according to a preset input data structure to generate training matrix tensors, and taking the historical vibration waterfall graphs and the historical evaluation labels as a historical input data set; step S305, performing data enhancement on the historical input data set: in order to prevent the machine learning model from being over fitted, the historical input data set is subjected to data enhancement through data enhancement technologies such as copying, rotation, amplification, noise adding, countermeasure generation and the like, so that an enhanced input data set is obtained; step S306, dividing the training set and the verification set: based on a preset distribution ratio: dividing the enhanced input data set into a training set and a verification set, wherein the preset allocation proportion can be 7:3, and the invention does not limit the preset allocation proportion; step S307, training the first offline detection model based on the training set and the verification set to obtain a performance offline detection model: performing initial training on the first offline detection model based on the training set to obtain a second offline detection model, and performing optimization training on the second offline detection model based on the verification set to obtain a performance offline detection model; step S308, obtaining vibration data to be measured: obtaining vibration data to be measured of a plurality of measuring points of an electric driving system to be measured; step S309, obtaining a vibration waterfall diagram to be measured: obtaining a vibration waterfall diagram to be tested by performing order analysis on the vibration data to be tested; step S310, generating an input data set to be tested: combining the vibration waterfall patterns to be tested according to a preset input data structure to generate a matrix tensor to be tested, so as to obtain an input data set to be tested; step S311, calling a performance offline detection model to obtain a performance offline evaluation result: inputting the input data set to be tested into a performance offline detection model to perform performance offline detection, and obtaining a performance offline evaluation result, namely an abnormal class; step S312, generating a performance offline detection report: receiving identity information of the electric drive system to be tested, generating a performance offline detection report according to the identity information and a performance offline evaluation result, displaying the qualification condition and the abnormal category of the electric drive system to be tested on the performance offline detection report, and displaying the comparison of a preset normal vibration waterfall and a vibration waterfall diagram to be tested in the performance offline detection report if the unqualified electric drive system to be tested exists.
Referring to fig. 4, fig. 4 is a block diagram illustrating an electric drive system performance offline detection apparatus according to one embodiment of the present invention. The apparatus may be applied in the implementation environment shown in fig. 1 and is specifically configured in the computer device 101. The apparatus may also be adapted to other exemplary implementation environments and may be specifically configured in other devices, and the present embodiment is not limited to the implementation environments to which the apparatus is adapted.
As shown in fig. 4, an electric drive system performance offline detection apparatus 400 according to an embodiment of the present invention includes: a data to be measured acquisition module 401, an input data set determination module 402 and an evaluation result determination module 403.
The to-be-measured data acquisition module 401 is configured to acquire to-be-measured vibration data of a plurality of measuring points of the to-be-measured electric drive system; the input data set determining module 402 is configured to perform order analysis on vibration data to be detected to obtain a vibration waterfall diagram to be detected, and generate a matrix tensor to be detected based on the vibration waterfall diagram to be detected to obtain an input data set to be detected; the evaluation result determining module 403 is configured to invoke a performance offline detection model to perform performance offline detection on the input data set to be detected, so as to obtain a performance offline evaluation result; the performance offline detection model is obtained through historical vibration data and historical evaluation label training.
In one embodiment of the invention, the electric driving system comprises a speed reducer, a controller and a motor, the industrial personal computer is respectively connected with the controller, the dynamometer and the data acquisition card, the dynamometer is also connected with the speed reducer through a power output interface, each vibration sensor is respectively arranged on a measuring point of the speed reducer, a measuring point of the controller and a measuring point of the motor, and the data acquisition card is respectively connected with each vibration sensor; the industrial personal computer is used for sending control instructions to the electric driving system and the dynamometer; the electric drive system and the dynamometer are used for executing control instructions, and controlling the speed by controlling the torque and the rotating speed; the dynamometer is also used for feeding back the execution conditions of the torque and the rotating speed to the industrial personal computer; the vibration sensor is used for sensing vibration conditions of a plurality of measuring points of the electric driving system to obtain vibration data to be measured; the data acquisition card is used for acquiring vibration data to be detected and transmitting the vibration data to the data acquisition module to be detected.
In one embodiment of the present invention, please refer to fig. 5, fig. 5 shows a schematic diagram of detection of an electric drive system performance offline detection device according to one embodiment of the present invention. As shown in fig. 5, the electric driving system 530 includes a speed reducer 531, a motor 532 and a controller 533, the industrial personal computer 520 is respectively connected with the controller 533, a dynamometer a542, a dynamometer B541 and a data acquisition card 510, the dynamometer a542 and the dynamometer B541 are also respectively connected to a power output interface of the electric driving system through self-carrying keys, namely connected with the speed reducer 531, the vibration sensor 551 is pressed on a measuring point of the motor 532, the vibration sensor 552 is pressed on a measuring point of the controller 533, the vibration sensor 553 is pressed on a measuring point of the speed reducer 531, and the data acquisition card 510 is respectively connected with the vibration sensor 551, the vibration sensor 552 and the vibration sensor 553. The industrial personal computer 520 sends control instructions including rotation speed and torque to the controller 533, the dynamometer a542 and the dynamometer B541, and in order to balance the torque of the on-line detection device for the performance of the electric drive system, the dynamometer a542 and the dynamometer B541 also need to execute the control instructions. The rotation speed and torque are controlled by the control command to control the electric driving system 530, the dynamometer a542 and the dynamometer B541 to perform acceleration, deceleration and uniform speed work, and the actually executed rotation speed and torque are fed back to the industrial personal computer 520 by the dynamometer a542 and the dynamometer B541. Vibration data to be detected sensed by the vibration sensor 551, the vibration sensor 552 and the vibration sensor 553 are collected by the data collection card 510 and then transmitted to the industrial personal computer 520 for analysis, detection and storage.
It should be noted that, the device for detecting the performance of the electric drive system in the above embodiment and the method for detecting the performance of the electric drive system in the above embodiment belong to the same concept, and the specific manner in which each module and unit perform the operation has been described in detail in the method embodiment, which is not repeated here. In practical application, the device for detecting the performance of the electric drive system provided by the embodiment can distribute the functions by different functional modules according to the needs, namely, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above, which is not limited herein.
The embodiment of the invention also provides electronic equipment, which comprises: one or more processors; and a storage device for storing one or more programs, which when executed by the one or more processors, cause the electronic device to implement the electric drive system performance offline detection method provided in the above embodiments.
Fig. 6 shows a schematic diagram of a computer system suitable for use in implementing an embodiment of the invention. It should be noted that, the computer system 600 of the electronic device shown in fig. 6 is only an example, and should not impose any limitation on the functions and the application scope of the embodiments of the present invention.
As shown in fig. 6, the computer system 600 includes a central processing unit (CentralProcessingUnit, CPU) 601, which can perform various appropriate actions and processes, such as performing the methods provided by the above-described embodiments, according to a program stored in a Read-only memory (ROM) 602 or a program loaded from a storage section 608 into a random access memory (RandomAccessMemory, RAM) 603. In the RAM603, various programs and data required for system operation are also stored. The CPU601, ROM602, and RAM603 are connected to each other through a bus 604. An Input/Output (I/O) interface 605 is also connected to bus 604.
The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, mouse, etc.; an output portion 607 including a cathode ray tube (CathodeRayTube, CRT), a liquid crystal display (LiquidCrystalDisplay, LCD), and the like, a speaker, and the like; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN (Local AreaNetwork ) card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The drive 610 is also connected to the I/O interface 605 as needed. Removable media 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is installed as needed on drive 610 so that a computer program read therefrom is installed as needed into storage section 608.
In particular, according to embodiments of the present invention, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising a computer program for performing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication portion 609, and/or installed from the removable medium 611. When executed by a Central Processing Unit (CPU) 601, performs the various functions defined in the system of the present invention.
It should be noted that, the computer readable medium shown in the embodiments of the present invention may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium may be, for example, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-Only Memory (ROM), an erasable programmable read-Only Memory (ErasableProgrammableReadOnlyMemory, EPROM), a flash Memory, an optical fiber, a portable compact disk read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer-readable signal medium may comprise a data signal propagated in baseband or as part of a carrier wave, with a computer-readable computer program embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. A computer program embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. Where each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units involved in the embodiments of the present invention may be implemented by software, or may be implemented by hardware, and the described units may also be provided in a processor. Wherein the names of the units do not constitute a limitation of the units themselves in some cases.
Another aspect of the present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor of a computer, causes the computer to perform the electric drive system performance offline detection method as provided in the respective embodiments described above. The computer-readable storage medium may be included in the electronic device described in the above embodiment or may exist alone without being incorporated in the electronic device.
The above embodiments are merely illustrative of the principles of the present invention and its effectiveness, and are not intended to limit the invention. Modifications and variations may be made to the above-described embodiments by those skilled in the art without departing from the spirit and scope of the invention. It is therefore intended that all equivalent modifications and changes made by those skilled in the art without departing from the spirit and technical spirit of the present invention shall be covered by the appended claims.
Claims (10)
1. The method for detecting the performance offline of the electric drive system is characterized by comprising the following steps of:
obtaining vibration data to be measured of a plurality of measuring points of an electric driving system to be measured;
performing order analysis on the vibration data to be tested to obtain a vibration waterfall diagram to be tested, and generating a matrix tensor to be tested based on the vibration waterfall diagram to be tested to obtain an input data set to be tested;
invoking a performance offline detection model to perform performance offline detection on the input data set to be detected to obtain a performance offline evaluation result;
the performance offline detection model is obtained through historical vibration data and historical evaluation label training.
2. The method for detecting the performance offline of the electric drive system according to claim 1, wherein before the performance offline evaluation result is obtained by calling a performance offline detection model to perform performance offline detection on the input data set to be detected, the method for detecting the performance offline of the electric drive system further comprises:
acquiring historical vibration data and a historical evaluation tag;
performing order analysis on the historical vibration data to obtain a historical vibration waterfall diagram, and generating a training matrix tensor based on the historical vibration waterfall diagram;
and inputting the training matrix tensor and the historical evaluation label as a historical input data set into a first offline detection model for training to obtain a performance offline detection model.
3. The electric drive system performance offline detection method according to claim 2, characterized in that before acquiring the historical vibration data and the historical evaluation tag, the electric drive system performance offline detection method further comprises:
acquiring initial vibration data and initial evaluation labels of a plurality of measuring points of a historical electric drive system;
matching the initial evaluation label with a preset evaluation label to determine a missing evaluation label;
constructing abnormal characteristics for the initial vibration data based on the missing evaluation tag and the initial evaluation tag to obtain missing vibration data;
and determining the initial vibration data and the missing vibration data as historical vibration data, and determining the initial evaluation tag and the missing evaluation tag as historical evaluation tags.
4. The method for detecting the performance offline of the electric drive system according to claim 2, wherein inputting the training matrix tensor and the history evaluation tag as a history input data set into a first offline detection model for training, to obtain the performance offline detection model, comprises:
performing data enhancement on the historical input data set to obtain an enhanced input data set;
dividing the enhanced input data set into a training set and a verification set according to a preset distribution proportion;
performing initial training on the first offline detection model based on the training set to obtain a second offline detection model;
and carrying out optimization training on the second offline detection model based on the verification set to obtain a performance offline detection model.
5. The method of claim 4, wherein data enhancing the historical input data set to obtain an enhanced input data set comprises:
at least one of copying, rotating, amplifying, noise adding and countermeasure generating is performed on the historical input data set to obtain an enhanced input data set.
6. The method for detecting the performance offline of the electric drive system according to any one of claims 1 to 5, wherein after the performance offline evaluation result is obtained by calling a performance offline detection model to perform performance offline detection on the input data set to be detected, the method for detecting the performance offline of the electric drive system further comprises:
receiving identity information of an electric drive system to be tested;
generating a performance offline detection report based on the identity information and the performance offline evaluation result;
if the performance offline detection report contains an unqualified electric drive system to be detected, displaying a preset normal vibration waterfall diagram and the vibration waterfall diagram to be detected in the performance offline detection report.
7. An electric drive system performance offline detection device, characterized in that the electric drive system performance offline detection device comprises:
the to-be-measured data acquisition module is used for acquiring to-be-measured vibration data of a plurality of measuring points of the to-be-measured electric drive system;
the input data set determining module is used for carrying out order analysis on the vibration data to be detected to obtain a vibration waterfall diagram to be detected, and generating a matrix tensor to be detected based on the vibration waterfall diagram to be detected to obtain an input data set to be detected;
the evaluation result determining module is used for calling a performance offline detection model to perform performance offline detection on the input data set to be detected to obtain a performance offline evaluation result;
the performance offline detection model is obtained through historical vibration data and historical evaluation label training.
8. The device for detecting the performance of the electric drive system on-line according to claim 7, wherein the device for detecting the performance of the electric drive system on-line further comprises an electric drive system, an industrial personal computer, a dynamometer, a plurality of vibration sensors and a data acquisition card;
the electric driving system comprises a speed reducer, a controller and a motor, the industrial personal computer is respectively connected with the controller, the dynamometer and the data acquisition card, the dynamometer is also connected with the speed reducer through a power output interface, each vibration sensor is respectively arranged on a measuring point of the speed reducer, a measuring point of the controller and a measuring point of the motor, and the data acquisition card is respectively connected with each vibration sensor;
the industrial personal computer is used for sending control instructions to the electric driving system and the dynamometer;
the electric drive system and the dynamometer are used for executing the control instruction, and the speed is controlled by controlling the torque and the rotating speed;
the dynamometer is also used for feeding back the execution conditions of the torque and the rotating speed to the industrial personal computer;
the vibration sensor is used for sensing vibration conditions of a plurality of measuring points of the electric drive system to obtain vibration data to be measured;
the data acquisition card is used for acquiring the vibration data to be detected and transmitting the vibration data to be detected to the data acquisition module to be detected.
9. An electronic device, the electronic device comprising:
one or more processors;
storage means for storing one or more programs that, when executed by the one or more processors, cause the electronic device to implement the electric drive system performance offline detection method of any one of claims 1-6.
10. A computer-readable storage medium, having stored thereon a computer program which, when executed by a processor of a computer, causes the computer to perform the electric drive system performance offline detection method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310050265.1A CN116106738A (en) | 2023-02-01 | 2023-02-01 | Method, device, equipment and medium for detecting performance offline of electric drive system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310050265.1A CN116106738A (en) | 2023-02-01 | 2023-02-01 | Method, device, equipment and medium for detecting performance offline of electric drive system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116106738A true CN116106738A (en) | 2023-05-12 |
Family
ID=86259350
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310050265.1A Pending CN116106738A (en) | 2023-02-01 | 2023-02-01 | Method, device, equipment and medium for detecting performance offline of electric drive system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116106738A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116910495A (en) * | 2023-09-13 | 2023-10-20 | 江西五十铃汽车有限公司 | Method and system for detecting off-line of automobile, readable storage medium and automobile |
-
2023
- 2023-02-01 CN CN202310050265.1A patent/CN116106738A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116910495A (en) * | 2023-09-13 | 2023-10-20 | 江西五十铃汽车有限公司 | Method and system for detecting off-line of automobile, readable storage medium and automobile |
| CN116910495B (en) * | 2023-09-13 | 2024-01-26 | 江西五十铃汽车有限公司 | Method and system for detecting off-line of automobile, readable storage medium and automobile |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Minhas et al. | A novel method to classify bearing faults by integrating standard deviation to refined composite multi-scale fuzzy entropy | |
| Chen et al. | Fault diagnosis method for machinery in unsteady operating condition by instantaneous power spectrum and genetic programming | |
| Lobato et al. | An integrated approach to rotating machinery fault diagnosis using, EEMD, SVM, and augmented data | |
| CN116106738A (en) | Method, device, equipment and medium for detecting performance offline of electric drive system | |
| US11933838B2 (en) | Managing health condition of a rotating system | |
| Espinoza Sepúlveda et al. | Blind application of developed smart vibration-based machine learning (SVML) model for machine faults diagnosis to different machine conditions | |
| JP2017094403A (en) | Processing program machine learning device, processing and assembling system provided with the machine learning device, and processing program machine learning method | |
| CN113125135A (en) | Fault diagnosis method for rotary machine, storage medium, and electronic device | |
| CN107491374A (en) | A kind of determination methods and computing device of equipment downtime state | |
| CN114443483A (en) | Test method and device of artificial intelligence system, electronic equipment and medium | |
| Ekwaro-Osire et al. | Incipient Fault Point Detection Based on Multiscale Diversity Entropy | |
| Mutra et al. | Signal-based parameter and fault identification in roller bearings using adaptive neuro-fuzzy inference systems | |
| CN109032853B (en) | Method and device for controlling FPGA card group | |
| CN113168739B (en) | Method for checking at least one vehicle and electronic computing device | |
| Wang et al. | Transfer learning based deep learning model and control chart for bearing useful life prediction | |
| Agarwal et al. | Proposal and validation of usability model for component based software system | |
| Hao et al. | Research on Fault Diagnosis Method Based on Improved CNN | |
| Ibryaeva et al. | A novel hybrid method for fault diagnosis of two rolling bearings mounted on the same shaft | |
| Yang et al. | Improving rolling bearing online fault diagnostic performance based on multi-dimensional characteristics | |
| Cheng et al. | Development of autoencoder-based status diagnosis method for ball bearing tribology status monitoring | |
| US11422062B2 (en) | Method for predicting damage to a component of a roller bearing | |
| CN116430160B (en) | Device and method for testing shell stress of electric drive system | |
| CN111507639B (en) | Financing risk analysis method and device | |
| CN115791171A (en) | Bearing fault diagnosis method, storage medium and electronic device | |
| CN114486135A (en) | Box vibration contribution amount testing method and device, testing equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |