Piezoelectric vibration sensor residual life prediction method and system based on digital twinning

Abstract

The embodiment of the invention provides a piezoelectric vibration sensor residual life prediction method and system based on digital twinning, and the method is realized based on a digital twinning system, and comprises the steps: respectively providing a vibration condition and a temperature condition for a piezoelectric vibration sensor through a vibration source and a temperature source at a test time, the piezoelectric vibration sensor outputs a corresponding vibration signal; processing the vibration signal by using a sensitivity analysis service to obtain a sensitivity parameter, and performing simulation by using a thermal response model of a finite element simulation service to obtain a piezoelectric patch pressure parameter; calculating a residual life value according to the test time acquired by the data acquisition service and the failure time of the piezoelectric vibration sensor; and constructing a training data sample based on the parameters and the residual life value obtained under the vibration condition, the temperature condition and the test time, training the residual life prediction model by using the training data sample, and predicting the residual life of the piezoelectric vibration sensor to be tested by using the trained residual life prediction model.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of sensors, in particular to a piezoelectric vibration sensor residual life prediction method and system based on digital twinning. BACKGROUND

[0002] Vibration sensors are sensors that convert vibration signals into electrical signals. Due to their high temperature resistance, small size, and other characteristics, they play an important role in vibration monitoring in high-temperature environments such as aircraft engines and industrial control scenarios. The failure of piezoelectric vibration sensors can cause the failure of state monitoring and control, resulting in serious consequences. Therefore, it is necessary to predict the residual life of piezoelectric vibration sensors to replace the devices that will be damaged in advance and ensure the stability of the system.

[0003] Piezoelectric vibration sensors have complex structures and internal stress changes. The pressure and charge of the piezoelectric sheet change under thermal stress, and various parameters are coupled with degradation phenomena that change over time. A single failure physical model cannot accurately describe its working state. At the same time, due to commercial confidentiality, it is difficult to carry out life prediction in the absence of accurate parameters of device materials and a large number of failure case statistics. Life prediction based on artificial intelligence models is currently a hot topic of research. The key to predicting residual life using artificial intelligence models is to provide accurate and effective training data samples. Some characteristic parameters that affect the residual life of piezoelectric vibration sensors cannot be directly measured, and multiple characteristic parameters with coupling relationships cannot be obtained at the same time. SUMMARY

[0004] In view of the above, the purpose of the embodiments of the present application is to provide a piezoelectric vibration sensor residual life prediction method and system based on digital twinning.

[0005] To achieve the above purpose, the embodiments of the present application provide a piezoelectric vibration sensor residual life prediction method based on digital twinning, which is implemented based on a digital twinning system. The digital twinning system includes a sensor virtual model, a sensitivity analysis service, a finite element simulation service, a data acquisition service, and a residual life prediction model. The sensor virtual model is a mapping of the physical entity of the piezoelectric vibration sensor. The method includes:

[0006] At a test time, a vibration source and a temperature source are used to provide vibration conditions and temperature conditions for the piezoelectric vibration sensor, respectively, and the piezoelectric vibration sensor outputs corresponding vibration signals;

[0007] The sensitivity analysis service is used to process the vibration signals and the vibration signals output by a standard piezoelectric vibration sensor under the vibration conditions and temperature conditions, to obtain sensitivity parameters of the sensor virtual model;

[0008] simulate the piezoelectric sheet pressure parameter of the sensor virtual model under the vibration condition and the temperature condition by using the finite element simulation service;

[0009] calculate a residual life value according to the test time and the failure time of the piezoelectric vibration sensor;

[0010] construct a training data sample based on the sensitivity parameter, the piezoelectric sheet pressure parameter and the residual life value obtained under the vibration condition, the temperature condition and the test time;

[0011] train the residual life prediction model by using the training data sample to obtain a trained residual life prediction model.

[0012] Optionally, the digital twin system further comprises a vibration analysis service, and the method further comprises:

[0013] perform noise reduction processing on the vibration signal output by the piezoelectric vibration sensor by using the vibration analysis service to obtain a noise-reduced vibration signal;

[0014] calculate vibration acceleration according to the noise-reduced vibration signal.

[0015] Optionally, the piezoelectric sheet pressure parameter of the sensor virtual model under the vibration condition and the temperature condition is simulated by using the finite element simulation service, and the piezoelectric sheet pressure parameter comprises:

[0016] the piezoelectric sheet pressure parameter of the sensor virtual model under the vibration condition and the temperature condition is simulated by using a finite element force response model and a finite element thermal response model.

[0017] Optionally, the method further comprises:

[0018] obtain a current vibration signal output by the piezoelectric vibration sensor to be tested under a current vibration condition and a current temperature condition during a degradation process of the piezoelectric vibration sensor to be tested;

[0019] perform processing on the current vibration signal and a vibration signal output by a standard piezoelectric vibration sensor under the current vibration condition and the current temperature condition by using the sensitivity analysis service to obtain a current sensitivity parameter of a sensor virtual model to be tested; wherein the sensor virtual model to be tested is a mapping of a physical entity of the piezoelectric vibration sensor to be tested;

[0020] simulate the current piezoelectric sheet pressure parameter of the sensor virtual model to be tested under the current vibration condition and the current temperature condition by using the finite element simulation service;

[0021] inputting the current sensitivity parameter, the current piezoelectric sheet pressure parameter obtained under the current vibration condition, the current temperature condition, and the current time into the trained remaining life prediction model, and outputting a predicted remaining life from the trained remaining life prediction model.

[0022] Optionally, after calculating the remaining life value according to the test time and the failure time of the piezoelectric vibration sensor collected by the data collection service, the method further includes:

[0023] dividing a remaining life interval according to the value of the remaining life value.

[0024] outputting the predicted remaining life from the trained remaining life prediction model.

[0025] outputting a predicted remaining life interval from the trained remaining life prediction model.

[0026] Embodiments of the present application also provide a piezoelectric vibration sensor remaining life prediction system based on digital twinning, including:

[0027] a physical entity of a piezoelectric vibration sensor, configured to provide a vibration condition and a temperature condition to the piezoelectric vibration sensor by using a vibration source and a temperature source respectively at a test time, and output a corresponding vibration signal from the piezoelectric vibration sensor;

[0028] a sensitivity analysis service, configured to process the vibration signal and a vibration signal output by a standard piezoelectric vibration sensor under the vibration condition and the temperature condition, to obtain a sensitivity parameter of a sensor virtual model; wherein the sensor virtual model is a mapping of the physical entity of the piezoelectric vibration sensor;

[0029] a finite element force simulation service, configured to obtain a piezoelectric sheet pressure parameter of the sensor virtual model by simulation under the vibration condition and the temperature condition;

[0030] a data collection service, configured to calculate a remaining life value according to the test time and the failure time of the piezoelectric vibration sensor collected.

[0031] a remaining life prediction model, configured to be trained based on training data samples constructed based on the sensitivity parameter, the piezoelectric sheet pressure parameter, and the remaining life value obtained under the vibration condition, the temperature condition, and the test time, to obtain a trained remaining life prediction model.

[0032] Optionally, the system further includes:

[0033] a vibration analysis service, configured to perform noise reduction processing on the vibration signal output by the piezoelectric vibration sensor to obtain a noise-reduced vibration signal, and calculate a vibration acceleration according to the noise-reduced vibration signal.

[0034] Optionally, the finite element simulation service is configured to simulate, under the vibration condition and the temperature condition, a piezoelectric sheet pressure parameter of the sensor virtual model in thermal and force responses by using a finite element force response model and a finite element thermal response model.

[0035] Optionally, the system further comprises:

[0036] a physical entity of the to-be-tested piezoelectric vibration sensor, configured to obtain a current vibration signal output by the to-be-tested piezoelectric vibration sensor under a current vibration condition and a current temperature condition in a degradation process of the to-be-tested piezoelectric vibration sensor;

[0037] the sensitivity analysis service is configured to process the current vibration signal and a vibration signal output by a standard piezoelectric vibration sensor under the current vibration condition and the current temperature condition to obtain a current sensitivity parameter of a to-be-tested sensor virtual model; the to-be-tested sensor virtual model is a mapping of the physical entity of the to-be-tested piezoelectric vibration sensor;

[0038] the finite element simulation service is configured to simulate, under the current vibration condition and the current temperature condition, a current piezoelectric sheet pressure parameter of the to-be-tested sensor virtual model;

[0039] the trained remaining life prediction model is configured to output a predicted remaining life when the current sensitivity parameter and the current piezoelectric sheet pressure parameter obtained under the current vibration condition, the current temperature condition and a current time are input.

[0040] Optionally, the data collection service is further configured to divide a remaining life interval according to a value of the remaining life value.

[0041] the trained remaining life prediction model is configured to output a predicted remaining life interval.

[0042] It can be seen from the above that the piezoelectric vibration sensor residual life prediction method and system based on digital twinning provided by the embodiments of the application provide vibration conditions and temperature conditions for the piezoelectric vibration sensor by using vibration sources and temperature sources respectively under test time, output corresponding vibration signals from the piezoelectric vibration sensor, process the vibration signals by using sensitivity analysis services to obtain sensitivity parameters, simulate piezoelectric sheet pressure parameters by using finite element simulation services, calculate residual life values according to test time and failure time of the piezoelectric vibration sensor collected by data collection services, construct training data samples based on various parameters obtained under vibration conditions, temperature conditions and test time, train the residual life prediction model by using the training data samples, and predict the residual life of the piezoelectric vibration sensor to be tested by using the trained residual life prediction model. The application can obtain multiple degradation characteristics that affect the service life of the piezoelectric vibration sensor, predict the residual life of the piezoelectric vibration sensor based on the multiple degradation characteristics, improve the accuracy and reliability of the prediction results, and improve the prediction efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0044] Figure 1 The method flowchart of the embodiments of the application is shown in the figure.

[0045] Figure 2 The process diagram of constructing training data samples by the embodiments of the application is shown in the figure.

[0046] Figure 3 The system block diagram of the embodiments of the application is shown in the figure.

[0047] Figure 4 The structure block diagram of the electronic device of the embodiments of the application is shown in the figure. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solutions and advantages of the present disclosure clearer, the present disclosure will be further described in detail below with reference to specific embodiments and drawings.

[0049] It should be noted that the technical terms or scientific terms used in the embodiments of the present application should be understood as the general meaning understood by those skilled in the art to which the present disclosure belongs, unless otherwise defined. The terms "first", "second", and similar terms used in the embodiments of the present application do not represent any order, quantity or importance, but are only used to distinguish different components. The terms "include" or "contain" and similar terms mean that the elements or objects before the terms cover the elements or objects listed after the terms and their equivalents, and do not exclude other elements or objects. The terms "connected" or "connected" and similar terms are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to represent relative positional relationships, which may change accordingly when the absolute position of the described object changes.

[0050] In the related art, the piezoelectric vibration sensor converts the change of force on the piezoelectric sheet into the change of electric charge at both ends through the piezoelectric effect. When the piezoelectric vibration sensor vibrates, the stress on the surface of the piezoelectric sheet pressed by the pre-tightening force will change, causing the electric charge at both ends to change, thereby converting the mechanical signal into an electrical signal. Therefore, there is a non-tight mechanical structure in the piezoelectric vibration sensor, and it is made of multiple materials, and the piezoelectric vibration sensor's electromechanical signal conversion function is easily affected by factors such as material pressure, mechanical force, thermal stress, etc. That is, the sensitivity of the piezoelectric vibration sensor is affected by multiple factors such as vibration acceleration, vibration frequency, temperature, piezoelectric sheet pressure, etc., and the coupling effect of each factor directly affects the remaining life of the sensor. Among them, the piezoelectric sheet pressure cannot be directly measured, and the influence degree of the coupling effect of each factor on the remaining life at the same time cannot be accurately evaluated.

[0051] Therefore, the embodiments of the present application provide a piezoelectric vibration sensor remaining life prediction method based on digital twinning. A sensor virtual model corresponding to the piezoelectric vibration sensor is realized based on a digital twinning system, finite element force response models, finite element thermal response models, etc. are established, and an accelerated degradation experiment of the piezoelectric vibration sensor is carried out using the digital twinning system. Under specific vibration conditions and temperature conditions, the sensitivity parameters, piezoelectric sheet pressure parameters, etc. of the sensor are obtained by simulation using each model, and the training data samples are constructed based on the vibration conditions, temperature conditions and the corresponding obtained parameters. The remaining life prediction model is trained using the training data samples, so as to obtain the remaining life prediction model which can predict the remaining life of the piezoelectric vibration sensor.

[0052] In the following, the technical solutions of the present application are further described in detail through specific embodiments.

[0053] Digital Twin (DT) is a technology that integrates multi-physical, multi-scale and multi-disciplinary attributes, and has the characteristics of real-time synchronization, faithful mapping and high fidelity. Based on the real-time interaction between virtual entities and physical entities, the target system can be effectively deduced and evaluated, especially the degradation of sensors.

[0054] The remaining life prediction method of the embodiment is realized based on a digital twin system. The digital twin system includes a physical entity PE, a virtual model VE, a service Ss, a twin data DD, a connection CN, etc. The virtual model includes a sensor virtual model, a sensor structure model, a finite element force response model, and a finite element thermal response model. The sensor virtual model is a mapping of the physical entity of the piezoelectric vibration sensor, which describes the relationship between the input and output of the piezoelectric vibration sensor under specific vibration and temperature conditions. The sensor structure model is constructed according to the geometric structure information of the internal components of the piezoelectric vibration sensor. It can be constructed according to the design drawings of the sensor, or it can be constructed by the actual size parameters of the sensor obtained through structural analysis. The sensor structure model is the basis for the simulation of the finite element force response model and the finite element thermal response model.

[0055] The finite element force response model is obtained by simulating the piezoelectric vibration sensor under specific vibration and temperature conditions and setting force simulation conditions. The simulation results include modal parameters and internal stress deformation distribution. The internal forces mainly include the bolt pre-tightening force of the sensor and the pressure generated by the expansion of the piezoelectric material at different temperatures. The external force mainly includes the mechanical force transmitted through the base of the vibration sensor.

[0056] The finite element thermal response model is obtained by simulating the piezoelectric vibration sensor under specific vibration and temperature conditions and setting thermal simulation conditions. The simulation results include the pressure change of the piezoelectric sheet of the piezoelectric vibration sensor, i.e. the thermal stress change of the piezoelectric material.

[0057] The service Ss includes sensitivity analysis service, finite element simulation service, vibration analysis service, data acquisition service, auxiliary service, etc. Among them, the sensitivity analysis service processes the vibration signal output by the sensor virtual model and the vibration signal output by the standard piezoelectric vibration sensor under the same vibration condition and temperature condition to obtain the sensitivity parameter of the sensor virtual model. In some ways, the sensitivity s = output charge q / input acceleration a, a = q / s can be obtained, and when the specific piezoelectric vibration sensor and the standard piezoelectric vibration sensor are tested, the accelerations of the two are consistent, that is, a = q1 / s1 = q2 / s2, so under the condition that the sensitivity s1 of the standard piezoelectric vibration sensor is known, the output charges q1 and q2 of the two sensors are obtained by testing, and the sensitivity s2 of the specific piezoelectric vibration sensor can be obtained.

[0058] The vibration analysis service is used for denoising processing of the vibration signal output by the sensor virtual model to obtain the denoised vibration signal. In some ways, the denoising processing of the vibration signal includes converting the time domain vibration signal into the frequency domain vibration signal, denoising processing the frequency domain vibration signal, and calculating the vibration acceleration according to the denoised vibration signal.

[0059] The auxiliary service includes a remaining life prediction model, a hardware device control service, an extensible interface service, a data storage and management service, a model management and application service, a visualization service, etc. Among them, the remaining life prediction model is used to output the predicted remaining life of the piezoelectric vibration sensor according to the input degradation characteristics of the piezoelectric vibration sensor. In the training phase of the remaining life prediction model, it is necessary to construct a training data sample of the degradation characteristics of the piezoelectric vibration sensor. The degradation characteristics are the characteristics that affect the service life of the piezoelectric vibration sensor. Considering that the sensitivity parameters, piezoelectric sheet pressure parameters, etc. of the piezoelectric vibration sensor under different vibration conditions and temperature conditions are all characteristics that affect its service life, it is necessary to construct a training data sample including the corresponding sensitivity parameters, piezoelectric sheet pressure parameters and corresponding remaining life values under different vibration conditions and temperature conditions, that is, to construct a training data sample including the characteristic values (t, T, P, f, a, s). The training data sample is the piezoelectric sheet pressure parameter P and the sensitivity parameter s of the sensor under the condition of time point t, temperature T, vibration frequency f and vibration acceleration a. Among them, the vibration frequency is the vibration frequency of the vibration source and can be directly obtained, and the vibration acceleration is obtained by processing the vibration signal output by the sensor by the vibration analysis service.

[0060] In some modes, the remaining life prediction model can be implemented based on the statistical method of Wiener random process, or based on the neural network model of deep learning. Optionally, the remaining life prediction model is constructed based on the LTSM network model. In the training stage, the input of the model is the training data sample of a period of time obtained by using the digital twin system to perform the accelerated degradation experiment on the sensor.

[0061] In some modes, the control service of the hardware device is used to control and manage the hardware devices such as the vibration source, the physical entity of the piezoelectric vibration sensor, the temperature sensor, the temperature source, and the like. The extensible interface service is used to provide the management of the extensible hardware interface and software interface. The data storage and management service is used to provide the storage and management of the input and output data of the modules in the system such as the virtual model, the service, the hardware device, and the remaining life prediction model. The model management and application service is used to manage the virtual model and the remaining life prediction model. The visualization service is used to provide the visualization display of the data such as the vibration signal, the vibration condition, the temperature condition, and the corresponding sensitivity parameter, the piezoelectric sheet pressure parameter, and the like.

[0062] In some embodiments, the twin data DD is the data basis of the digital twin system, including design data, knowledge data, historical data, real-time data, and other data. The design data includes the physical parameters and working parameters of the piezoelectric vibration sensor such as the material, size, working temperature range, frequency range, and range of the device, which is the data basis for constructing the simulation models such as the virtual model, the finite element force response model, and the finite element thermal response model. The knowledge data is the principle of the piezoelectric vibration sensor and the basic principle of the related analysis method, which also belongs to the data basis for constructing the simulation models such as the virtual model, the finite element force response model, and the finite element thermal response model. The historical data is the existing degradation characteristic data of the piezoelectric vibration sensor that can be collected, which can be used to train the remaining life prediction model. The real-time data is the vibration signal, the sensitivity parameter, and the piezoelectric sheet pressure parameter of the virtual model of the to-be-tested sensor generated in real time during the degradation experiment of the to-be-tested piezoelectric vibration sensor by using the digital twin system. The real-time data is input into the trained remaining life prediction model, and the trained remaining life prediction model is used to predict the remaining life of the to-be-tested piezoelectric vibration sensor. The other data is the data generated during the operation of the services in the system.

[0063] In some embodiments, the connection CN includes six bidirectional links between the service Ss and the twin data DD, the physical entity PE and the twin data DD, the virtual model VE and the twin data DD, the physical entity PE and the service Ss, the virtual model VE and the service Ss, and the physical entity PE and the virtual model VE. The signal output end of the physical entity is connected to the digital twin system through the data acquisition device DAQ, and provides the vibration frequency, vibration acceleration of the vibration source, the collected temperature value, the vibration signal of the standard piezoelectric vibration sensor, and other data to the service, virtual model and other modules of the digital twin system, to realize data interaction between the physical entity and each module. The input and output data of the virtual model and the service are connected to the storage module, and the storage module is used to store the input and output data. The sensitivity parameters generated by the virtual model and the piezoelectric sheet pressure parameters, the vibration frequency, vibration acceleration and temperature value provided by the physical entity are collectively input into the remaining life prediction model, the remaining life prediction model is trained, and the trained remaining life prediction model is used to predict the remaining life of the piezoelectric vibration sensor to be tested.

[0064] As shown in Figure 1 , 2 The embodiment of the present application provides a piezoelectric vibration sensor remaining life prediction method based on digital twinning, which is realized based on a digital twin system, and the method comprises the following steps:

[0065] S101: At a test time, a vibration source and a temperature source are used to provide vibration conditions and temperature conditions for a piezoelectric vibration sensor, and the piezoelectric vibration sensor outputs corresponding vibration signals;

[0066] In this embodiment, the digital twin system is used to perform a degradation experiment on the piezoelectric vibration sensor, an external vibration generating device is used to provide different vibration conditions, and vibration under different combinations of vibration frequencies and vibration accelerations is generated. An external high-temperature test box is used to provide different temperature conditions, and the piezoelectric vibration sensor (PVS) outputs corresponding vibration signals under different vibration conditions and temperature conditions.

[0067] S102: The sensitivity analysis service is used to process the vibration signals and the vibration signals output by the standard piezoelectric vibration sensor under the vibration conditions and the temperature conditions, to obtain sensitivity parameters of a sensor virtual model;

[0068] In this embodiment, the sensitivity analysis service calculates the sensitivity parameters of the piezoelectric vibration sensor according to the vibration signals output by the piezoelectric vibration sensor and the vibration signals output by the standard piezoelectric vibration sensor, and the standard sensitivity parameters of the standard piezoelectric vibration sensor.

[0069] S103: Obtain piezoelectric sheet pressure parameters of the sensor virtual model by using a finite element analysis service to simulate under vibration conditions and temperature conditions;

[0070] In this embodiment, under vibration conditions, temperature conditions, and set force and thermal simulation conditions, piezoelectric sheet pressure parameters of the sensor virtual model are obtained by using a finite element force response model and a finite element thermal simulation model based on the sensor virtual model and the sensor structure model, including material pressure change parameters, mechanical force change parameters, and thermal stress change parameters suffered by the piezoelectric sheet. In some modes, the set force simulation conditions include pre-tightening force, vibration acceleration, and vibration frequency inside the sensor, and the thermal simulation conditions include temperature.

[0071] S104: Calculate the remaining useful life value according to the test time collected by the data collection service and the failure time of the piezoelectric vibration sensor;

[0072] In this embodiment, the current test time t collected by the data collection service and the failure time t 失效 of the piezoelectric vibration sensor are used to calculate the remaining useful life value RUL(t) = t 失效 -t of the piezoelectric vibration sensor, and the remaining useful life value corresponding to the test time is used as a degradation feature for training the remaining useful life model.

[0073] In some embodiments, according to the calculated remaining useful life value, different remaining useful life intervals can be further divided, and the remaining useful life interval corresponding to the test time is used as a degradation feature for training the classification task of the remaining useful life model, and different maintenance suggestions are provided in different remaining useful life intervals. For example, according to the remaining useful life value, three intervals of RUL < 100h, 100h ≤ RUL < 500h, and RUL ≥ 500h are divided, when the prediction result is the interval RUL < 100h, it is recommended to replace the sensor, and when the prediction result is 100h ≤ RUL < 500h, it is recommended to focus on maintenance.

[0074] S105: Construct training data samples based on the sensitivity parameters, piezoelectric sheet pressure parameters, and remaining useful life values obtained under vibration conditions, temperature conditions, and test time.

[0075] S106: Train the remaining useful life prediction model by using the training data samples to obtain the trained remaining useful life prediction model.

[0076] In this embodiment, based on the digital twin system, the piezoelectric vibration sensor is subjected to degradation experiment, and after obtaining the sensitivity parameters, piezoelectric sheet pressure parameters and residual life values obtained under test time, vibration conditions and temperature conditions, training data samples are constructed based on the test time, vibration conditions (vibration frequency, vibration acceleration), temperature value, sensitivity parameters, piezoelectric sheet pressure parameters, residual life values and other parameters. The training data sample set is constructed by the corresponding sensitivity parameters, piezoelectric sheet pressure parameters and residual life values under different test time, vibration conditions and temperature conditions. The residual life prediction model is trained based on the training data sample set, and the trained residual life prediction model is obtained.

[0077] In some embodiments, the residual life prediction method further comprises:

[0078] In the degradation process of the piezoelectric vibration sensor to be tested, the current vibration signal output by the piezoelectric vibration sensor to be tested under the current vibration condition and the current temperature condition is obtained.

[0079] The current vibration signal and the vibration signal output by the standard piezoelectric vibration sensor under the current vibration condition and the current temperature condition are processed by using the sensitivity analysis service to obtain the current sensitivity parameters of the virtual model of the sensor to be tested; wherein the virtual model of the sensor to be tested is a mapping of the physical entity of the piezoelectric vibration sensor to be tested.

[0080] Under the current vibration condition and the current temperature condition, the current piezoelectric sheet pressure parameters of the virtual model of the sensor to be tested are simulated by using the finite element simulation service.

[0081] The current sensitivity parameters and the current piezoelectric sheet pressure parameters obtained under the current vibration condition, the current temperature condition and the current time are input into the trained residual life prediction model, and the predicted residual life is output by the trained residual life prediction model.

[0082] In this embodiment, after the trained residual life prediction model is obtained through training, the residual life of the piezoelectric vibration sensor to be tested can be predicted based on the digital twin system. The virtual model of the sensor to be tested is constructed, the vibration source and the temperature source are used to provide vibration conditions and temperature conditions for the piezoelectric vibration sensor to be tested, the current sensitivity parameters of the virtual model of the sensor to be tested are determined by using the sensitivity analysis service under the current vibration condition and the current temperature condition provided at the current time, the current piezoelectric sheet pressure parameters of the virtual model of the sensor to be tested are simulated by using the finite element simulation model, the current sensitivity parameters and the current piezoelectric sheet pressure parameters obtained under the current vibration condition, the current temperature condition and the current time are input into the trained residual life prediction model, and the predicted residual life value or residual life interval of the piezoelectric vibration sensor to be tested is output by the trained residual life prediction model, so that the piezoelectric vibration sensor to be tested can be effectively maintained in combination with the prediction result.

[0083] The method for predicting the residual life of the piezoelectric vibration sensor based on digital twinning provided by the embodiment of the application constructs a digital twinning system, which integrates multiple functions such as data collection, data analysis, model simulation, model training, and model prediction, can obtain multiple degradation characteristics affecting the service life of the piezoelectric vibration sensor, predicts the residual life of the piezoelectric vibration sensor based on the multiple degradation characteristics, and can improve the accuracy and reliability of the prediction result and improve the prediction efficiency.

[0084] It should be noted that the method of the embodiment of the application can be executed by a single device, such as a computer or a server. The method of the embodiment can also be applied to a distributed scenario and completed by multiple devices cooperating with each other. In this distributed scenario, one of the multiple devices can only execute one or more steps in the method of the embodiment of the application, and the multiple devices can interact with each other to complete the method.

[0085] It should be noted that the above describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be executed in an order different than the order in which they are recited in the embodiments, and still achieve the desired result. In addition, the processes depicted in the figures do not necessarily require the particular order shown, or sequential order, to achieve the desired results. In certain implementations, multitasking and parallel processing can be advantageous.

[0086] As shown in Figure 3 The embodiment of the application provides a piezoelectric vibration sensor residual life prediction system based on digital twinning, which comprises:

[0087] The physical entity of the piezoelectric vibration sensor is used to provide vibration conditions and temperature conditions for the piezoelectric vibration sensor by using a vibration source and a temperature source respectively at a test time, and output corresponding vibration signals from the piezoelectric vibration sensor;

[0088] The sensitivity analysis service is used to process the vibration signals and the vibration signals output by the standard piezoelectric vibration sensor under the vibration conditions and the temperature conditions, to obtain the sensitivity parameters of the sensor virtual model; wherein the sensor virtual model is a mapping of the physical entity of the piezoelectric vibration sensor;

[0089] The finite element simulation service is used to obtain the piezoelectric sheet pressure parameters of the sensor virtual model by simulation under the vibration conditions and the temperature conditions;

[0090] The data collection service is used to calculate the residual life value according to the collected test time and the failure time of the piezoelectric vibration sensor;

[0091] The remaining life prediction model is trained based on training data samples constructed based on sensitivity parameters, piezoelectric sheet pressure parameters and remaining life values obtained under vibration conditions, temperature conditions and test time, to obtain the trained remaining life prediction model; wherein the remaining life value is calculated according to the test time and the failure time of the piezoelectric vibration sensor.

[0092] For the convenience of description, the above system is described in various modules in terms of functions. Of course, the functions of each module can be implemented in one or more software and / or hardware when implementing the embodiments of the present application.

[0093] The system of the above embodiments is used to implement the corresponding method in the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be described here.

[0094] Figure 4 A more specific electronic device hardware structure schematic diagram provided by the embodiment is shown, which can include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040 and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030 and the communication interface 1040 are connected to each other in the device through the bus 1050.

[0095] The processor 1010 can be implemented in the form of a general-purpose CPU (Central Processing Unit, central processor), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., for executing related programs to implement the technical solutions provided by the embodiments of the present specification.

[0096] The memory 1020 can be implemented in the form of a ROM (Read Only Memory, read-only memory), a RAM (Random Access Memory, random access memory), a static storage device, a dynamic storage device, etc. The memory 1020 can store an operating system and other application programs, and when the technical solutions provided by the embodiments of the present specification are implemented by software or firmware, the related program codes are saved in the memory 1020 and called and executed by the processor 1010.

[0097] The input / output interface 1030 is configured to connect an input / output module to realize information input and output. The input / output module can be configured as a component in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. The input device can include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device can include a display, a speaker, a vibrator, an indicator light, etc.

[0098] The communication interface 1040 is configured to connect a communication module (not shown in the figure) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired manner (such as a USB, a network cable, etc.) or a wireless manner (such as a mobile network, WIFI, Bluetooth, etc.).

[0099] The bus 1050 includes a channel to transmit information between various components (such as the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040) of the device.

[0100] It should be noted that although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040, and the bus 1050, in the specific implementation process, the device can also include other components necessary for normal operation. In addition, those skilled in the art can understand that the above device can also only contain components necessary for implementing the embodiments of the present specification, and does not have to contain all the components shown in the figure.

[0101] The electronic device of the above embodiment is used to realize the corresponding method in the above embodiment, and has the beneficial effects of the corresponding method embodiment, which will not be described here.

[0102] The computer readable medium of the embodiment includes permanent and non-permanent, removable and non-removable media, which can be realized by any method or technology to store information. The information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device.

[0103] Those of ordinary skill in the art will realize that the foregoing discussion of any of the embodiments has been presented for the purpose of illustration and description and is not intended to be exhaustive or to limit the scope of the disclosure to the precise embodiments discussed. Many modifications and variations will be apparent to those of ordinary skill in the art upon reading this disclosure. For example, embodiments can be practiced in conjunction with a variety of storage architectures (e.g., dynamic RAM (DRAM)). It is intended that the embodiments described herein be considered in a descriptive sense only and not for purposes of limitation. Therefore, obvious modifications should be presumed to be within the scope of the disclosure.

[0104] In addition, for simplicity and clarity of illustration, power supply / ground connections to integrated circuit (IC) chips and other components can or can not be shown in the provided figures. Further, as will be appreciated by those skilled in the art, the various features and processes described herein can be implemented in hardware, software or a combination thereof. In the case of a software implementation, the functionality traditionally associated with various features and processes can be

[0105] Although the present disclosure has been described in connection with certain specific embodiments, numerous alternatives, modifications, and variations will be apparent to those skilled in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) can use the embodiments discussed.

[0106] Embodiments of the present disclosure are intended to cover all such alternatives, modifications, and variations as falling within the scope of the appended claims. Accordingly, any omission, modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present disclosure should be included in the protection scope of the present disclosure.

Claims

1. A piezoelectric vibration sensor residual life prediction method based on digital twinning, based on a digital twinning system, characterized in that, The digital twin system comprises a sensor virtual model, a sensitivity analysis service, a finite element simulation service, a data acquisition service, and a residual life prediction model, wherein the sensor virtual model is a mapping of a physical entity of a piezoelectric vibration sensor, and the method comprises the following steps: At a test time, a vibration condition and a temperature condition are provided to the piezoelectric vibration sensor by using a vibration source and a temperature source respectively, and a corresponding vibration signal is output by the piezoelectric vibration sensor; The vibration signal and a vibration signal output by a standard piezoelectric vibration sensor under the vibration condition and the temperature condition are processed by using the sensitivity analysis service to obtain a sensitivity parameter of the sensor virtual model; Under the vibration condition and the temperature condition, a piezoelectric sheet pressure parameter of the sensor virtual model is simulated by using the finite element simulation service; A residual life value is calculated according to a test time and a failure time of the piezoelectric vibration sensor collected by the data acquisition service; Based on the sensitivity parameter, the piezoelectric sheet pressure parameter, and the residual life value obtained under the vibration condition, the temperature condition, and the test time, a training data sample is constructed; The residual life prediction model is trained by using the training data sample to obtain a trained residual life prediction model.

2. The method of claim 1, wherein, The digital twin system further comprises a vibration analysis service, and the method further comprises the following steps: The vibration signal output by the piezoelectric vibration sensor is denoised by using the vibration analysis service to obtain a denoised vibration signal; Vibration acceleration is calculated according to the denoised vibration signal.

3. The method of claim 1, wherein, Under the vibration condition and the temperature condition, a piezoelectric sheet pressure parameter of the sensor virtual model is simulated by using the finite element simulation service, which comprises the following steps: Under the vibration condition and the temperature condition, a piezoelectric sheet pressure parameter of the sensor virtual model under thermal and force responses is simulated by using a finite element force response model and a finite element thermal response model.

4. The method of claim 1, wherein, Further comprising the following steps: During a degradation process of a to-be-tested piezoelectric vibration sensor, a current vibration signal output by the to-be-tested piezoelectric vibration sensor under a current vibration condition and a current temperature condition is obtained; The current vibration signal and a vibration signal output by a standard piezoelectric vibration sensor under the current vibration condition and the current temperature condition are processed by using the sensitivity analysis service to obtain a current sensitivity parameter of a to-be-tested sensor virtual model; wherein the to-be-tested sensor virtual model is a mapping of a physical entity of the to-be-tested piezoelectric vibration sensor; Under the current vibration condition and the current temperature condition, a current piezoelectric sheet pressure parameter of the to-be-tested sensor virtual model is simulated by using the finite element simulation service; The current sensitivity parameter and the current piezoelectric sheet pressure parameter obtained under the current vibration condition, the current temperature condition, and a current time are input into the trained residual life prediction model, and a predicted residual life is output by the trained residual life prediction model.

5. The method of claim 1, wherein, After calculating the residual life value according to the test time and the failure time of the piezoelectric vibration sensor collected by the data acquisition service, the following steps are further included: According to a value of the residual life value, a residual life interval is divided. outputting, by the trained remaining useful life prediction model, a predicted remaining useful life, comprising: outputting, by the trained remaining useful life prediction model, a predicted remaining useful life interval.

6. A piezoelectric vibration sensor residual life prediction system based on digital twinning, characterized by, comprising: a physical entity of a piezoelectric vibration sensor, configured to provide vibration conditions and temperature conditions to the piezoelectric vibration sensor by using a vibration source and a temperature source respectively at a test time, and output a corresponding vibration signal from the piezoelectric vibration sensor; a sensitivity analysis service, configured to process the vibration signal and a vibration signal output by a standard piezoelectric vibration sensor under the vibration conditions and the temperature conditions to obtain a sensitivity parameter of a sensor virtual model; wherein the sensor virtual model is a mapping of the physical entity of the piezoelectric vibration sensor; a finite element force simulation service, configured to obtain, by simulation, a piezoelectric patch pressure parameter of the sensor virtual model under the vibration conditions and the temperature conditions; a data collection service, configured to calculate a remaining useful life value according to a collection of the test time and a failure time of the piezoelectric vibration sensor; a remaining useful life prediction model, configured to train a training data sample constructed based on the sensitivity parameter, the piezoelectric patch pressure parameter, and the remaining useful life value obtained under the vibration conditions, the temperature conditions, and the test time, to obtain a trained remaining useful life prediction model.

7. The system of claim 6, wherein, further comprising: a vibration analysis service, configured to perform noise reduction processing on the vibration signal output by the piezoelectric vibration sensor to obtain a noise-reduced vibration signal, and calculate vibration acceleration according to the noise-reduced vibration signal.

8. The system of claim 6, wherein: the finite element simulation service is configured to obtain, by simulation, the piezoelectric patch pressure parameter of the sensor virtual model under thermal and force responses by using a finite element force response model and a finite element thermal response model under the vibration conditions and the temperature conditions.

9. The system of claim 6, wherein, further comprising: a physical entity of a to-be-tested piezoelectric vibration sensor, configured to obtain a current vibration signal output by the to-be-tested piezoelectric vibration sensor under current vibration conditions and current temperature conditions in a degradation process of the to-be-tested piezoelectric vibration sensor; the sensitivity analysis service is configured to process the current vibration signal and a vibration signal output by a standard piezoelectric vibration sensor under the current vibration conditions and the current temperature conditions to obtain a current sensitivity parameter of a to-be-tested sensor virtual model; wherein the to-be-tested sensor virtual model is a mapping of the physical entity of the to-be-tested piezoelectric vibration sensor; the finite element simulation service is configured to simulate a current piezoelectric patch pressure parameter of the to-be-tested sensor virtual model under the current vibration conditions and the current temperature conditions; the trained remaining useful life prediction model is configured to output a predicted remaining useful life when the current sensitivity parameter and the current piezoelectric patch pressure parameter obtained under the current vibration conditions, the current temperature conditions, and a current time are input.

10. The system of claim 6, wherein: the data collection service is further configured to divide a remaining useful life interval according to a value of the remaining useful life value; the trained remaining useful life prediction model is configured to output a predicted remaining useful life interval.

Images