Method, device and circuit system for determining the operating state of a closing and opening spring

Abstract

The application provides a method and device for determining the working state of a closing and opening spring, and circuit system, the method comprising: acquiring a vibration signal of the spring in real time, and determining a first function according to the vibration signal, the first function being a function of the amplitude of the vibration signal changing with time; performing wavelet transform on the waveform corresponding to the first function to obtain a second function, the second function being a function of the output power of the vibration signal changing with time; determining a first characteristic value according to the second function, the first characteristic value including at least the maximum and minimum values of the output power; and inputting the first characteristic value into an internal characteristic parameter inversion model for analysis to obtain the working state of the spring. The method solves the problem that there is no mature reliability evaluation method and device for the closing and opening spring of a high-voltage circuit breaker in the prior art.

Description

Technical Field

[0001] This invention relates to the field of power systems, and more specifically, to a method, apparatus, computer-readable storage medium, and circuit system for determining the operating state of a closing spring. Background Technology

[0002] High-voltage circuit breakers are crucial control and protection units in power systems. The spring operating mechanism is the most widely used mechanism in high-voltage circuit breakers, and the opening and closing spring, as the core component of the spring operating mechanism, is critical to the safe and stable operation of the circuit breaker and even the power system. Due to factors such as materials, manufacturing processes, and operating conditions, the opening and closing springs in operation may experience stress relaxation or fracture, leading to circuit breaker failure and seriously affecting the safe and stable operation of the power grid. Based on fault data analysis from China Southern Power Grid since 2017, there are two failure modes for the opening and closing springs: 1) Stress relaxation (fatigue), accounting for 75%, the failure mechanism is: the opening and closing spring is under prolonged compression, resulting in slight plastic deformation and a decrease in stress over time, leading to stress relaxation. 2) Fracture or cracking, accounting for 25%, the failure mechanism is: improper heat treatment or manufacturing defects in the spring; cracks caused by these two reasons propagate under spring stress, eventually leading to spring fracture. Failure of the opening and closing spring directly leads to circuit breaker failure, seriously endangering the safe and stable operation of the power system.

[0003] The current status monitoring and diagnosis of circuit breaker spring mechanisms mainly suffers from the following problems:

[0004] 1) Mean and standard deviation method. This method can only reflect the average trend of the vibration signal and is not sensitive to local changes in the signal over time, thus failing to effectively reflect signal changes.

[0005] 2) Based on the χ² deviation test method. This method requires the establishment of a large test database and complex calculations. The determination of the average envelope of the signal is complicated, making it difficult to distinguish the fault type.

[0006] 3) Dynamic Time Warping-Based Method. This method uses Fourier transform to obtain the frequency distribution of the signal and extracts the numerical changes of specific frequencies or frequency bands as feature parameters. However, this method is only suitable for processing stationary random signals. The vibration signal generated when the opening and closing springs operate contains a large number of nonlinear components, such as spikes, harmonics, and discontinuities. These harmonics and discontinuities have wide frequency bands, distributed throughout the entire signal frequency band. Therefore, it is difficult to extract effective fault features using only time-domain and frequency-domain analysis. Windowed Fourier transforms use a fixed time-frequency window to decompose the signal into many fixed-length segments. The resulting feature parameters are only sensitive to faults such as time delays, but the analysis effect on the vibration signal of the opening and closing springs is not ideal. This is mainly due to the fixed time-frequency window of this method.

[0007] In summary, there is currently no technically mature method or device for assessing the reliability of the opening and closing springs of high-voltage circuit breakers. Existing data processing methods cannot reliably monitor the status of circuit breakers and diagnose faults through the vibration signals of the opening and closing springs.

[0008] Therefore, it is necessary to study the condition monitoring and fault diagnosis of the opening and closing springs in order to achieve fault early warning and improve the reliability of the spring mechanism and circuit breaker. Summary of the Invention

[0009] The main objective of this application is to provide a method, apparatus, computer-readable storage medium, and circuit system for determining the operating state of a circuit breaker opening and closing spring, so as to at least solve the problem that there is no technically mature method and apparatus for evaluating the reliability of high-voltage circuit breaker opening and closing springs in the prior art.

[0010] To achieve the above objectives, according to one aspect of this application, a method for determining the operating state of a closing / opening spring is provided. The method includes: acquiring a vibration signal of the spring in real time, and determining a first function based on the vibration signal, wherein the first function is a function of the amplitude of the vibration signal changing with time; performing wavelet transform on the waveform corresponding to the first function to obtain a second function, wherein the second function is a function of the output power of the vibration signal changing with time; determining a first characteristic value based on the second function, wherein the first characteristic value includes at least the maximum and minimum values ​​of the output power; inputting the first characteristic value into an internal characteristic parameter inversion model for analysis to obtain the operating state of the spring, wherein the operating state is a fault operating state or a non-fault operating state, wherein the fault operating state is one of stress relaxation, cracking, and fracture, and the internal characteristic parameter inversion model is obtained by training with historical first characteristic values ​​and the operating states corresponding to the historical first characteristic values.

[0011] Optionally, acquiring the vibration signal of the spring in real time and determining a first function based on the vibration signal includes: acquiring the vibration signal of the spring in real time and generating a first waveform based on the vibration signal, wherein the first waveform is a waveform showing the change of the amplitude of the vibration signal over time; determining the first function based on the first waveform and performing wavelet transform on the waveform corresponding to the first function to obtain a second function includes: performing wavelet transform on the first waveform corresponding to the first function to obtain a second waveform, wherein the second waveform is a waveform showing the change of the output power of the vibration signal over time; and determining the second function based on the second waveform.

[0012] Optionally, performing a wavelet transform on the first waveform corresponding to the first function to obtain a second waveform includes: determining the amplitude of all the vibration signals based on the first waveform, and calculating the instantaneous output power corresponding to all the amplitudes based on all the amplitudes and the shear modulus, spring wire diameter, spring mean diameter, effective number of turns, deformation, and instantaneous velocity of the spring, where the shear modulus is used to characterize the rigidity of the spring wire material, the spring mean diameter is the average of the inner and outer diameters of the spring, and the effective number of turns is the number of turns maintaining equal pitch; generating a third waveform based on all the instantaneous output power and the acquisition time of the corresponding vibration signal, where the third waveform is a waveform showing the change of the output power over time before the wavelet transform; and performing a wavelet transform on the third waveform to obtain the second waveform.

[0013] Optionally, determining the first characteristic value according to the second function includes: calculating a second characteristic value and a third characteristic value of the output power waveform according to the second function, wherein the second characteristic value is the difference between the output power at a first time point and the output power at a second time point in the second waveform diagram corresponding to the second function, and the third characteristic value is the difference between the output power at a first time point and the output power at a third time point in the second waveform diagram corresponding to the second function, wherein the first time point is any acquisition time in the second waveform diagram, the second time point is the previous acquisition time point of the first time point, and the third time point is the next acquisition time point of the first time point, and the acquisition time point is the time when the vibration signal is acquired; if both the second characteristic value and the third characteristic value are non-negative or both the second characteristic value and the third characteristic value are non-positive, the output power at the first time point is determined as the first characteristic value.

[0014] Optionally, before inputting the first feature value into the internal characteristic parameter inversion model for analysis, the method includes: establishing a standard feature value database, the standard feature value database including standard feature values ​​of the vibration signals of multiple first springs and the corresponding working states of the standard feature values, the standard feature values ​​corresponding one-to-one with the first springs, the standard feature values ​​being the first feature values ​​corresponding to the working states of the first springs when the working states are not faulty working states; establishing a fault feature value database, the fault feature value database including fault feature values ​​of the vibration signals of multiple second springs and the corresponding working states of the fault feature values, the fault feature values ​​corresponding one-to-one with the second springs, the fault feature values ​​being the first feature values ​​corresponding to the working states of the second springs when the working states are stress relaxation, cracks, or fractures, the fault feature values ​​being one-to-one with faulty working states; and training the neural network with the standard feature value database and the fault feature value database to obtain the internal characteristic parameter inversion model.

[0015] Optionally, training the neural network with the standard feature value database and the fault feature value database to obtain the internal characteristic parameter inversion model includes: inputting the standard feature values ​​and the fault feature values ​​into the neural network for analysis to obtain multiple result working states; performing residual analysis based on the training working states corresponding to the multiple result working states to obtain residual analysis results; and adjusting the parameters of the neural network based on the residual analysis results to obtain the internal characteristic parameter inversion model, wherein the training working states include the working states corresponding to the standard feature values ​​and the fault feature values.

[0016] According to another aspect of this application, a device for determining the operating state of a closing and opening spring is provided. The device includes: a first determining unit, configured to acquire the vibration signal of the spring in real time and determine a first function based on the vibration signal, wherein the first function is a function of the amplitude of the vibration signal changing with time; a calculation unit, configured to perform wavelet transform on the waveform corresponding to the first function to obtain a second function, wherein the second function is a function of the output power of the vibration signal changing with time; a second determining unit, configured to determine a first characteristic value based on the second function, wherein the first characteristic value includes at least the maximum and minimum values ​​of the output power; and a third determining unit, configured to input the first characteristic value into an internal characteristic parameter inversion model for analysis to obtain the operating state of the spring, wherein the operating state is a fault operating state or a non-fault operating state, wherein the fault operating state is one of stress relaxation, cracking, and fracture, and the internal characteristic parameter inversion model is obtained by training with historical first characteristic values ​​and the operating states corresponding to the historical first characteristic values.

[0017] According to another aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform any of the determination methods described above.

[0018] According to another aspect of this application, a circuit system is provided, comprising: a closing / opening spring, one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including methods for performing any of the aforementioned determination methods.

[0019] Optionally, the circuit system further includes: a signal acquisition module for acquiring vibration signals monitored by vibration sensors in real time; an output power waveform acquisition module for acquiring output power waveforms based on the vibration signal waveforms acquired by the signal acquisition module; a feature value database establishment module for establishing a standard feature value database and a fault feature value database based on historical data; and an inversion module for determining the fault type of the spring using a spring internal characteristic parameter inversion model trained through the standard feature value database and the fault feature value database.

[0020] Applying the technical solution of this application, in the above-mentioned method for determining the working state of the opening and closing spring, firstly, the vibration signal of the spring is acquired in real time, and a first function is determined based on the vibration signal, wherein the first function is a function of the amplitude of the vibration signal changing with time; then, wavelet transform is performed on the waveform corresponding to the first function to obtain a second function, wherein the second function is a function of the output power of the vibration signal changing with time; then, a first characteristic value is determined based on the second function, wherein the first characteristic value includes at least the maximum and minimum values ​​of the output power; finally, the first characteristic value is input into the internal characteristic parameter inversion model for analysis to obtain the working state of the spring, wherein the working state is a fault working state or a non-fault working state, wherein the fault working state is one of stress relaxation, cracking, and fracture, and the internal characteristic parameter inversion model is obtained by training through historical first characteristic values ​​and the working states corresponding to the historical first characteristic values. This method acquires vibration signals from the opening and closing springs during operation using a vibration sensor. Feature values ​​are then extracted from these signals via wavelet analysis. A standard feature value database and a fault feature value database are established to train a neural network model, resulting in an internal characteristic parameter inversion model. The feature values ​​are then input into this model to obtain the operating state of the opening and closing springs. This method addresses the lack of a mature reliability assessment method and device for high-voltage circuit breaker opening and closing springs in existing technologies. Attached Figure Description

[0021] Figure 1 A hardware structure block diagram of a mobile terminal for determining the operating state of a gate opening and closing spring, according to an embodiment of this application, is shown.

[0022] Figure 2 A flowchart illustrating a method for determining the operating state of a closing spring according to an embodiment of this application is shown.

[0023] Figure 3 A flowchart illustrating a specific method for determining the operating state of a closing and opening spring according to another embodiment of this application is shown.

[0024] Figure 4 A structural block diagram of a device for determining the operating state of a gate opening and closing spring according to an embodiment of this application is shown. Detailed Implementation

[0025] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0026] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] For ease of description, the following explains some of the nouns or terms used in the embodiments of this application:

[0029] Wavelet transform refers to the localization analysis of time and frequency of wavelet signals. Through scaling and translation operations, the wavelet signal is subdivided in time at high frequencies and in frequency at low frequencies. The wavelet signal is a signal with decay and oscillation mode with alternating positive and negative amplitudes.

[0030] As described in the background section, there is no technically mature method or device for evaluating the reliability of high-voltage circuit breaker opening and closing springs in the prior art. To address the problem of the lack of a technically mature method or device for evaluating the reliability of high-voltage circuit breaker opening and closing springs in the prior art, embodiments of this application provide a method, device, computer-readable storage medium, and circuit system for determining the operating state of the opening and closing springs.

[0031] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0032] The methods and embodiments provided in this application can be executed on a mobile terminal, a computer terminal, or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a method of determining the working state of a gate opening and closing spring according to an embodiment of the present invention. Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0033] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the device information display method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the aforementioned networks may include wireless networks provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0034] This embodiment provides a method for determining the operating state of a gate opening and closing spring that operates on a mobile terminal, computer terminal, or similar computing device. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0035] Figure 2 This is a flowchart of a method for determining the operating state of the opening and closing springs according to an embodiment of this application. Figure 2 As shown, the method includes the following steps:

[0036] Step S201: Acquire the vibration signal of the spring in real time, and determine the first function based on the vibration signal. The first function is a function of the amplitude of the vibration signal changing with time.

[0037] Specifically, a vibration sensor is installed at the opening and closing springs to monitor the vibration signals generated when the high-voltage circuit breaker operates and the opening and closing springs move.

[0038] Step S202: Perform wavelet transform on the waveform corresponding to the first function to obtain the second function, which is a function of the change of the output power of the vibration signal with time.

[0039] Specifically, the signals generated during spring vibration are irregular and difficult to analyze directly. Therefore, wavelet transform is required. Wavelet transform has good localization properties in the time and frequency domains, which can better reveal the details of the signal.

[0040] Step S203: Determine the first characteristic value according to the second function mentioned above. The first characteristic value includes at least the maximum and minimum values ​​of the output power.

[0041] Specifically, it is very difficult to analyze the function directly. Therefore, the working state of the opening and closing springs during the operation of the high-voltage circuit breaker is characterized by the eigenvalues ​​of the function. The first eigenvalues ​​mentioned above include the maximum and minimum values ​​of the output power corresponding to the second function mentioned above.

[0042] Step S204: Input the first feature value into the internal characteristic parameter inversion model for analysis to obtain the working state of the spring. The working state is either a faulty working state or a non-faulty working state. The faulty working state is one of stress relaxation, cracking, and fracture. The internal characteristic parameter inversion model is trained by the historical first feature value and the working state corresponding to the historical first feature value.

[0043] Specifically, a neural network model is trained using historical feature value data of different springs to obtain an internal characteristic parameter inversion model. By inputting these feature values ​​into the model, the internal characteristic parameter inversion model can determine the current state of the spring based on the detected feature values, including states such as stress relaxation, cracking, and breakage.

[0044] In the above embodiments, firstly, the vibration signal of the spring is acquired in real time, and a first function is determined based on the vibration signal. The first function is a function of the amplitude of the vibration signal changing with time. Then, wavelet transform is performed on the waveform corresponding to the first function to obtain a second function, which is a function of the output power of the vibration signal changing with time. Next, based on the second function, a first eigenvalue is determined. The first eigenvalue includes at least the maximum and minimum values ​​of the output power. Finally, the first eigenvalue is input into the internal characteristic parameter inversion model for analysis to obtain the working state of the spring. The working state is either a faulty working state or a non-faulty working state. The faulty working state is one of stress relaxation, cracking, or fracture. The internal characteristic parameter inversion model is obtained by training with historical first eigenvalues ​​and the corresponding working states. This method acquires the vibration signal of the opening and closing spring by controlling a vibration sensor, extracts the eigenvalues ​​of the vibration signal using wavelet analysis, establishes a standard eigenvalue database and a fault eigenvalue database to train a neural network model, obtains the internal characteristic parameter inversion model, and inputs the eigenvalues ​​into the internal characteristic parameter inversion model to obtain the working state of the opening and closing spring. This method solves the problem that there is no mature method and device for evaluating the reliability of high-voltage circuit breaker opening and closing springs in the existing technology.

[0045] In order to obtain the first function mentioned above, in an optional implementation, step S201 includes:

[0046] Step S2011: Acquire the vibration signal of the spring in real time, and generate a first waveform diagram based on the vibration signal. The first waveform diagram is a waveform diagram showing the change of the amplitude of the vibration signal over time.

[0047] Specifically, by using vibration sensors to monitor the vibration signals generated when the opening and closing springs of the high-voltage circuit breaker operate in real time, the monitored vibration signals can be output on the display screen in real time to form the corresponding first waveform diagram mentioned above.

[0048] Step S2012: Determine the first function based on the first waveform diagram.

[0049] Specifically, after obtaining the first waveform diagram, the amplitude of the vibration signal at any given time can be determined, and thus the function of the amplitude of the vibration signal changing with time can be determined.

[0050] In order to obtain the second function described above, in an optional implementation, step S202 includes:

[0051] Step S2023: Perform wavelet transform on the first waveform corresponding to the first function to obtain a second waveform, which is a waveform of the output power of the vibration signal changing with time.

[0052] Specifically, since the vibration signal monitored in real time contains noise, it is necessary to remove the noise through wavelet transform. Furthermore, since the waveform is cluttered and the mapping relationship between the first function and the second function cannot be directly established, it is necessary to convert the first waveform into the second waveform.

[0053] Step S2024: Determine the second function based on the second waveform diagram.

[0054] Specifically, after obtaining the first waveform diagram, the instantaneous output power of the vibration signal at any given time can be determined, and thus the function of the instantaneous output power of the vibration signal changing with time can be determined.

[0055] In order to obtain the second waveform, in one optional implementation, step S2021 above includes:

[0056] Step S20231: Based on the first waveform diagram, determine the amplitude of all the vibration signals, and calculate the instantaneous output power corresponding to all the amplitudes based on all the amplitudes, the shear modulus of the spring, the diameter of the spring wire, the mean diameter of the spring, the number of effective turns, the deformation, and the instantaneous velocity. The shear modulus is used to characterize the rigidity of the spring wire material, the mean diameter of the spring is the average of the inner and outer diameters of the spring, and the number of effective turns is the number of turns that maintain equal pitch.

[0057] Specifically, the waveforms of the vibration signals detected by the aforementioned vibration sensors are irregular vibration images, which are not conducive to analysis, and there is also a lack of methods for directly analyzing the vibration signals. Therefore, through the formula... The instantaneous output power at each point of the vibration signal can be calculated. In the above formula, G is the material shear modulus, d is the material diameter, D is the spring mean diameter, n is the effective number of spring coils, c is the deformation, and v is the instantaneous velocity of the spring when it moves.

[0058] Step S20232: Generate a third waveform diagram based on the acquisition time of all the above instantaneous output power and the corresponding vibration signal. The third waveform diagram is a waveform diagram of the change of the above output power with time before wavelet transform.

[0059] Specifically, the instantaneous output power corresponding to the vibration amplitude of each point in the first waveform can be calculated according to the above formula, and the waveform of the output power changing with time can be obtained.

[0060] Step S20233: Perform wavelet transform on the third waveform to obtain the second waveform.

[0061] Specifically, the third waveform obtained from the first waveform is still an irregular vibration image, but the output power waveform satisfies wavelet characteristics, that is, it has decay and the oscillation pattern is alternating positive and negative amplitudes. Therefore, wavelet transform can be performed on the output power waveform, that is, through the formula... By filtering the power waveform above and performing scaling and shift operations to subdivide the wavelet signal in time at high frequencies and in frequency at low frequencies, a second waveform can be obtained. This facilitates localized time and frequency analysis. Here, 'a' represents the scaling factor, and 'b' represents the shift factor. It is a basic wavelet.

[0062] In order to obtain the target feature value, in one optional implementation, step S203 above includes:

[0063] Step S2031: According to the second function, calculate the second characteristic value and the third characteristic value of the output power waveform. The second characteristic value is the difference between the output power at the first moment and the output power at the second moment in the second waveform diagram corresponding to the second function. The third characteristic value is the difference between the output power at the first moment and the output power at the third moment in the second waveform diagram corresponding to the second function. The first moment is any acquisition moment in the second waveform diagram. The second moment is the previous acquisition moment of the first moment. The third moment is the next acquisition moment of the first moment. The acquisition moment is the moment when the vibration signal is acquired.

[0064] Specifically, according to the formula Determine the i-th data point P of the second waveform above. i The second and third eigenvalues ​​of P. i The corresponding values ​​for each time point range from 0 to the current acquisition time, thus obtaining the second and third feature values ​​for each data point.

[0065] Step S2032: If both the second characteristic value and the third characteristic value are non-negative or both the second characteristic value and the third characteristic value are non-positive, determine the output power corresponding to the first moment as the first characteristic value.

[0066] Specifically, after obtaining the second and third eigenvalues, we can then use ΔP... i2 ≥0ΔP i1 A value ≥0 indicates a maximum point in the waveform graph; the amplitude of the power waveform corresponding to this data point is the first characteristic value P1. Simultaneously, ΔP can be used to determine the maximum value. i2 ≤0ΔPi1 ≤0 determines the minimum point in the waveform diagram, and the amplitude of the power waveform corresponding to this data point is the first characteristic value P2.

[0067] In order to obtain the correlation between the characteristic value and the working state of the spring, in an optional embodiment, before step S204 above, the method further includes:

[0068] Step S301: Establish a standard feature value database. The standard feature value database includes standard feature values ​​of the vibration signals of multiple first springs and the working states corresponding to the standard feature values. The standard feature values ​​correspond one-to-one with the first springs. The standard feature values ​​are the first feature values ​​corresponding to the working states of the first springs when the working states are not fault working states.

[0069] Specifically, based on historical data and experimental simulations, the first characteristic value of different springs in normal working state is obtained, and the above-mentioned standard characteristic value database is established based on the above-mentioned first characteristic value. In the above-mentioned standard characteristic value database, each first characteristic value has a corresponding working state.

[0070] Step S302: Establish a fault feature value database. The fault feature value database includes fault feature values ​​of the vibration signals of multiple second springs and the working states corresponding to the fault feature values. The fault feature values ​​correspond one-to-one with the second springs. The fault feature values ​​are the first feature values ​​corresponding to the working states of the second springs, such as stress relaxation, cracks, or fractures. The fault feature values ​​correspond one-to-one with the fault working states.

[0071] Specifically, based on historical data and experimental simulations, first characteristic values ​​of different springs in different fault working states are obtained. The above-mentioned fault characteristic value database is established based on the first characteristic values. Each first characteristic value in the above-mentioned standard characteristic value database has a corresponding working state. For example, characteristic value P1 is the first characteristic value obtained when a certain spring has a crack. In the above-mentioned fault characteristic value database, the working state corresponding to P1 is that a crack has appeared.

[0072] Step S303: Train the neural network with the above-mentioned standard feature value database and the above-mentioned fault feature value database to obtain the above-mentioned internal characteristic parameter inversion model.

[0073] Specifically, based on preset parameters, the neural network model is trained using the aforementioned standard feature value database and the aforementioned fault feature value database until the optimal internal characteristic parameter inversion model is obtained.

[0074] To ensure the accuracy of the aforementioned intrinsic characteristic parameter inversion model, in an optional implementation, step S303 includes:

[0075] Step S3031: Input the above standard feature values ​​and the above fault feature values ​​into the neural network for analysis to obtain multiple result working states;

[0076] Specifically, based on preset parameters, the feature values ​​from the aforementioned standard feature value database and the aforementioned fault feature value database are input into the aforementioned neural network to obtain the analysis working state corresponding to each feature value, which is the aforementioned result working state.

[0077] Step S3032: Perform residual analysis on the training working states corresponding to the multiple above-mentioned result working states to obtain residual analysis results, and adjust the parameters of the above-mentioned neural network according to the above-mentioned residual analysis results to obtain the above-mentioned internal characteristic parameter inversion model. The above-mentioned training working states include the above-mentioned working states corresponding to the above-mentioned standard feature values ​​and the above-mentioned fault feature values.

[0078] Specifically, the above-mentioned working status is compared with the working status stored in the database to perform residual analysis, and the residual analysis results are obtained. The preset parameters are adjusted according to the analysis results, and then the input is repeated to perform residual analysis again until the difference analysis results are lower than the value set by the staff, which means that the analysis accuracy of the internal characteristic parameter inversion model has met the standard.

[0079] To enable those skilled in the art to better understand the technical solution of this application, the implementation process of the method for determining the working state of the opening and closing spring of this application will be described in detail below with reference to specific embodiments.

[0080] This embodiment relates to a specific method for determining the working state of the opening and closing spring, such as... Figure 3 As shown, it includes the following steps:

[0081] Step S1: Use sensors to acquire the initial internal characteristic parameters of the opening and closing springs in real time. The internal characteristic parameters include the vibration signal when the spring moves.

[0082] Step S2: Use wavelet analysis to analyze the above vibration signal, obtain the output power waveform after wavelet transformation, and obtain the characteristic values ​​of the power waveform. Establish a standard characteristic value library and a fault simulation characteristic value library for the opening and closing springs of high-voltage circuit breakers.

[0083] Step S3: Use a neural network to process the above-mentioned standard feature value library and fault simulation feature value library to establish an inversion model of the internal characteristic parameters of the high-voltage circuit breaker opening and closing springs;

[0084] Step S4: Use the internal characteristic parameter inversion model to accurately identify the fault type of the opening and closing springs.

[0085] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0086] This application also provides a device for determining the operating state of a closing spring. It should be noted that this device can be used to execute the method for determining the operating state of a closing spring provided in this application. This device is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0087] The following describes the device for determining the working state of the opening and closing springs provided in the embodiments of this application.

[0088] Figure 4 This is a schematic diagram of a device for determining the working state of the opening and closing springs according to an embodiment of this application. Figure 4 As shown, the device includes:

[0089] The first determining unit 10 is used to acquire the vibration signal of the spring in real time and determine a first function based on the vibration signal. The first function is a function of the amplitude of the vibration signal changing with time.

[0090] Specifically, a vibration sensor is installed at the opening and closing springs to monitor the vibration signals generated when the high-voltage circuit breaker operates and the opening and closing springs move.

[0091] The calculation unit 20 is used to perform wavelet transform on the waveform corresponding to the first function to obtain a second function, wherein the second function is a function of the change of the output power of the vibration signal with time.

[0092] Specifically, the signals generated during spring vibration are irregular and difficult to analyze directly. Therefore, wavelet transform is required. Wavelet transform has good localization properties in the time and frequency domains, which can better reveal the details of the signal.

[0093] The second determining unit 30 is used to determine a first characteristic value according to the second function mentioned above, wherein the first characteristic value includes at least the maximum and minimum values ​​of the output power.

[0094] Specifically, it is very difficult to analyze the function directly. Therefore, the working state of the opening and closing springs during the operation of the high-voltage circuit breaker is characterized by the eigenvalues ​​of the function. The first eigenvalues ​​mentioned above include the maximum and minimum values ​​of the output power corresponding to the second function mentioned above.

[0095] The third determining unit 40 is used to input the first feature value into the internal characteristic parameter inversion model for analysis to obtain the working state of the spring. The working state is either a fault working state or a non-fault working state. The fault working state is one of stress relaxation, cracking, and fracture. The internal characteristic parameter inversion model is obtained by training the historical first feature value and the working state corresponding to the historical first feature value.

[0096] Specifically, a neural network model is trained using historical feature value data of different springs to obtain an internal characteristic parameter inversion model. By inputting these feature values ​​into the model, the internal characteristic parameter inversion model can determine the current state of the spring based on the detected feature values, including states such as stress relaxation, cracking, and breakage.

[0097] In the above embodiments, the first determining unit acquires the vibration signal of the spring in real time and determines a first function based on the vibration signal. The first function is a function of the amplitude of the vibration signal changing with time. The calculation unit performs wavelet transform on the waveform corresponding to the first function to obtain a second function. The second function is a function of the output power of the vibration signal changing with time. The second determining unit determines a first characteristic value based on the second function. The first characteristic value includes at least the maximum and minimum values ​​of the output power. The third determining unit inputs the first characteristic value into the internal characteristic parameter inversion model for analysis to obtain the working state of the spring. The working state is either a fault working state or a non-fault working state. The fault working state is one of stress relaxation, cracking, and fracture. The internal characteristic parameter inversion model is trained using historical first characteristic values ​​and the working states corresponding to the historical first characteristic values. This device acquires vibration signals from the opening and closing springs during operation by controlling vibration sensors. It then extracts feature values ​​from these vibration signals using wavelet analysis, establishes a standard feature value database and a fault feature value database, and trains a neural network model to obtain an internal characteristic parameter inversion model. The feature values ​​are then input into this model to determine the operating state of the opening and closing springs. This method addresses the lack of a mature reliability assessment method and device for high-voltage circuit breaker opening and closing springs in existing technologies.

[0098] In order to obtain the aforementioned first function, in one optional implementation, the first determining unit includes:

[0099] The acquisition module is used to acquire the vibration signal of the spring in real time and generate a first waveform based on the vibration signal. The first waveform is a waveform diagram showing the change of the amplitude of the vibration signal over time.

[0100] Specifically, by using vibration sensors to monitor the vibration signals generated when the opening and closing springs of the high-voltage circuit breaker operate in real time, the monitored vibration signals can be output on the display screen in real time to form the corresponding first waveform diagram mentioned above.

[0101] The first determining module is used to determine the first function based on the first waveform diagram.

[0102] Specifically, after obtaining the first waveform diagram, the amplitude of the vibration signal at any given time can be determined, and thus the function of the amplitude of the vibration signal changing with time can be determined.

[0103] To obtain the aforementioned second function, in one optional implementation, the computational unit includes:

[0104] The first calculation module is used to perform wavelet transform on the first waveform corresponding to the first function to obtain a second waveform, which is a waveform diagram of the output power of the vibration signal changing with time.

[0105] Specifically, since the vibration signal monitored in real time contains noise, it is necessary to remove the noise through wavelet transform. Furthermore, since the waveform is cluttered and the mapping relationship between the first function and the second function cannot be directly established, it is necessary to convert the first waveform into the second waveform.

[0106] The second determining module is used to determine the second function based on the second waveform diagram.

[0107] Specifically, after obtaining the first waveform diagram, the instantaneous output power of the vibration signal at any given time can be determined, and thus the function of the instantaneous output power of the vibration signal changing with time can be determined.

[0108] To obtain the second waveform, in one optional implementation, the first calculation module includes:

[0109] The first calculation submodule is used to determine the amplitude of all the above vibration signals according to the first waveform diagram, and to calculate the instantaneous output power corresponding to all the above amplitudes according to all the above amplitudes, the shear modulus of the spring, the diameter of the spring wire, the mean diameter of the spring, the number of effective turns, the deformation, and the instantaneous velocity. The shear modulus is used to characterize the rigidity of the material of the spring wire, the mean diameter of the spring is the average of the inner diameter and the outer diameter of the spring, and the number of effective turns is the number of turns that maintain equal pitch.

[0110] Specifically, the waveforms of the vibration signals detected by the aforementioned vibration sensors are irregular vibration images, which are not conducive to analysis, and there is also a lack of methods for directly analyzing the vibration signals. Therefore, through the formula... The instantaneous output power at each point of the vibration signal can be calculated. In the above formula, G is the material shear modulus, d is the material diameter, D is the spring mean diameter, n is the effective number of spring coils, c is the deformation, and v is the instantaneous velocity of the spring when it moves.

[0111] The generation submodule is used to generate a third waveform diagram based on the acquisition time of all the above instantaneous output power and the corresponding vibration signal. The third waveform diagram is the waveform diagram of the change of the above output power with time before wavelet transform.

[0112] Specifically, the instantaneous output power corresponding to the vibration amplitude of each point in the first waveform can be calculated according to the above formula, and the waveform of the output power changing with time can be obtained.

[0113] The second calculation submodule is used to perform wavelet transform on the third waveform to obtain the second waveform.

[0114] Specifically, the third waveform obtained from the first waveform is still an irregular vibration image, but the output power waveform satisfies wavelet characteristics, that is, it has decay and the oscillation pattern is alternating positive and negative amplitudes. Therefore, wavelet transform can be performed on the output power waveform, that is, through the formula... By filtering the power waveform above and performing scaling and shift operations to subdivide the wavelet signal in time at high frequencies and in frequency at low frequencies, a second waveform can be obtained. This facilitates localized time and frequency analysis. Here, 'a' represents the scaling factor, and 'b' represents the shift factor. It is a basic wavelet.

[0115] In order to obtain the target feature value, in one optional implementation, the second determining unit includes:

[0116] The second calculation module is used to calculate the second characteristic value and the third characteristic value of the output power waveform according to the second function. The second characteristic value is the difference between the output power at the first moment and the output power at the second moment in the second waveform diagram corresponding to the second function. The third characteristic value is the difference between the output power at the first moment and the output power at the third moment in the second waveform diagram corresponding to the second function. The first moment is any acquisition moment in the second waveform diagram. The second moment is the previous acquisition moment of the first moment. The third moment is the next acquisition moment of the first moment. The acquisition moment is the moment when the vibration signal is acquired.

[0117] Specifically, according to the formula Determine the i-th data point P of the second waveform above. i The second and third eigenvalues ​​of P. i The corresponding values ​​for each time point range from 0 to the current acquisition time, thus obtaining the second and third feature values ​​for each data point.

[0118] The third determining module is used to determine the output power corresponding to the first moment as the first characteristic value when both the second characteristic value and the third characteristic value are non-negative or when both the second characteristic value and the third characteristic value are non-positive.

[0119] Specifically, after obtaining the second and third eigenvalues, we can then use ΔP... i2 ≥0ΔP i1 A value ≥0 indicates a maximum point in the waveform graph; the amplitude of the power waveform corresponding to this data point is the first characteristic value P1. Simultaneously, ΔP can be used to determine the maximum value. i2 ≤0ΔP i1 ≤0 determines the minimum point in the waveform diagram, and the amplitude of the power waveform corresponding to this data point is the first characteristic value P2.

[0120] To obtain the correlation between the characteristic value and the working state of the spring, in an optional embodiment, the above-mentioned device further includes:

[0121] The first generation unit is used to establish a standard feature value database before inputting the first feature value into the internal characteristic parameter inversion model for analysis. The standard feature value database includes standard feature values ​​of the vibration signals of multiple first springs and the working states corresponding to the standard feature values. The standard feature values ​​correspond one-to-one with the first springs. The standard feature values ​​are the first feature values ​​corresponding to the working states of the first springs when the working states are not fault working states.

[0122] Specifically, based on historical data and experimental simulations, the first characteristic value of different springs in normal working state is obtained, and the above-mentioned standard characteristic value database is established based on the above-mentioned first characteristic value. In the above-mentioned standard characteristic value database, each first characteristic value has a corresponding working state.

[0123] The second generation unit is used to establish a fault feature value database. The fault feature value database includes fault feature values ​​of the vibration signals of multiple second springs and the working states corresponding to the fault feature values. The fault feature values ​​correspond one-to-one with the second springs. The fault feature values ​​are the first feature values ​​corresponding to the working states of the second springs, such as stress relaxation, cracks, or fractures. The fault feature values ​​correspond one-to-one with the fault working states.

[0124] Specifically, based on historical data and experimental simulations, first characteristic values ​​of different springs in different fault working states are obtained. The above-mentioned fault characteristic value database is established based on the first characteristic values. Each first characteristic value in the above-mentioned standard characteristic value database has a corresponding working state. For example, characteristic value P1 is the first characteristic value obtained when a certain spring has a crack. In the above-mentioned fault characteristic value database, the working state corresponding to P1 is that a crack has appeared.

[0125] The training unit is used to train the neural network with the aforementioned standard feature value database and the aforementioned fault feature value database to obtain the aforementioned internal characteristic parameter inversion model.

[0126] Specifically, based on preset parameters, the neural network model is trained using the aforementioned standard feature value database and the aforementioned fault feature value database until the optimal internal characteristic parameter inversion model is obtained.

[0127] To ensure the accuracy of the aforementioned intrinsic characteristic parameter inversion model, in one optional implementation, the training unit includes:

[0128] The input module is used to input the above standard feature values ​​and the above fault feature values ​​into the neural network for analysis, and obtain multiple result working states;

[0129] Specifically, based on preset parameters, the feature values ​​from the aforementioned standard feature value database and the aforementioned fault feature value database are input into the aforementioned neural network to obtain the analysis working state corresponding to each feature value, which is the aforementioned result working state.

[0130] The adjustment module is used to perform residual analysis on the training working states corresponding to the multiple above-mentioned result working states, obtain residual analysis results, and adjust the parameters of the above-mentioned neural network based on the above-mentioned residual analysis results to obtain the above-mentioned internal characteristic parameter inversion model. The above-mentioned training working states include the above-mentioned working states corresponding to the above-mentioned standard feature values ​​and the above-mentioned fault feature values.

[0131] Specifically, the above-mentioned working status is compared with the working status stored in the database to perform residual analysis, and the residual analysis results are obtained. The preset parameters are adjusted according to the analysis results, and then the input is repeated to perform residual analysis again until the difference analysis results are lower than the value set by the staff, which means that the analysis accuracy of the internal characteristic parameter inversion model has met the standard.

[0132] The aforementioned device for determining faults in the opening and closing springs includes a processor and a memory. The first determining unit, calculation unit, second determining unit, and third determining unit are all stored as program units in the memory. The processor executes these program units stored in the memory to achieve the corresponding functions. All of the above modules are located in the same processor; alternatively, the modules may be located in different processors in any combination.

[0133] The processor contains a kernel, which retrieves the corresponding program unit from memory. One or more kernels can be configured, and the operating state of the opening and closing springs is determined by adjusting the kernel parameters.

[0134] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0135] This invention provides a computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the method for determining the working state of the opening and closing spring.

[0136] Specifically, the methods for determining the working state of the opening and closing springs include:

[0137] Step S201: Acquire the vibration signal of the spring in real time, and determine the first function based on the vibration signal. The first function is a function of the amplitude of the vibration signal changing with time.

[0138] Specifically, a vibration sensor is installed at the opening and closing springs to monitor the vibration signals generated when the high-voltage circuit breaker operates and the opening and closing springs move.

[0139] Step S202: Perform wavelet transform on the waveform corresponding to the first function to obtain the second function, which is a function of the change of the output power of the vibration signal with time.

[0140] Specifically, the signals generated during spring vibration are irregular and difficult to analyze directly. Therefore, wavelet transform is required. Wavelet transform has good localization properties in the time and frequency domains, which can better reveal the details of the signal.

[0141] Step S203: Determine the first characteristic value according to the second function mentioned above. The first characteristic value includes at least the maximum and minimum values ​​of the output power.

[0142] Specifically, it is very difficult to analyze the function directly. Therefore, the working state of the opening and closing springs during the operation of the high-voltage circuit breaker is characterized by the eigenvalues ​​of the function. The first eigenvalues ​​mentioned above include the maximum and minimum values ​​of the output power corresponding to the second function mentioned above.

[0143] Step S204: Input the first feature value into the internal characteristic parameter inversion model for analysis to obtain the working state of the spring. The working state is either a faulty working state or a non-faulty working state. The faulty working state is one of stress relaxation, cracking, and fracture. The internal characteristic parameter inversion model is trained by the historical first feature value and the working state corresponding to the historical first feature value.

[0144] Specifically, a neural network model is trained using historical feature value data of different springs to obtain an internal characteristic parameter inversion model. By inputting these feature values ​​into the model, the internal characteristic parameter inversion model can determine the current state of the spring based on the detected feature values, including states such as stress relaxation, cracking, and breakage.

[0145] Optionally, in step S2011, the vibration signal of the spring is acquired in real time, and a first waveform is generated based on the vibration signal, wherein the first waveform is a waveform showing the change of the amplitude of the vibration signal over time; in step S2012, the first function is determined based on the first waveform; in step S2023, wavelet transform is performed on the first waveform corresponding to the first function to obtain a second waveform, wherein the second waveform is a waveform showing the change of the output power of the vibration signal over time; in step S2024, the second function is determined based on the second waveform.

[0146] Optionally, in step S20211, based on the first waveform diagram, the amplitude of all the vibration signals is determined, and the instantaneous output power corresponding to all the amplitudes is calculated based on all the amplitudes, the shear modulus of the spring, the diameter of the spring wire, the mean diameter of the spring, the number of effective turns, the deformation, and the instantaneous velocity. The shear modulus is used to characterize the rigidity of the spring wire material, the mean diameter of the spring is the average of the inner and outer diameters of the spring, and the number of effective turns is the number of turns that maintain equal pitch. In step S20212, a third waveform diagram is generated based on all the instantaneous output power and the acquisition time of the corresponding vibration signals. The third waveform diagram is a waveform diagram showing the change of the output power over time before wavelet transform. In step S2023, wavelet transform is performed on the third waveform diagram to obtain the second waveform diagram.

[0147] Optionally, in step S2031, according to the second function, calculate the second characteristic value and the third characteristic value of the output power waveform. The second characteristic value is the difference between the output power at the first moment and the output power at the second moment in the second waveform diagram corresponding to the second function. The third characteristic value is the difference between the output power at the first moment and the output power at the third moment in the second waveform diagram corresponding to the second function. The first moment is any acquisition moment in the second waveform diagram. The second moment is the previous acquisition moment of the first moment. The third moment is the next acquisition moment of the first moment. The acquisition moment is the moment when the vibration signal is acquired. In step S2032, if both the second characteristic value and the third characteristic value are non-negative or both are non-positive, determine the output power at the first moment as the first characteristic value.

[0148] Optionally, in step S301, a standard feature value database is established, which includes standard feature values ​​of the vibration signals of multiple first springs and the corresponding operating states of the standard feature values. The standard feature values ​​correspond one-to-one with the first springs, and the standard feature values ​​are the first feature values ​​corresponding to the first springs when their operating states are not faulty operating states. In step S302, a fault feature value database is established, which includes fault feature values ​​of the vibration signals of multiple second springs and the corresponding operating states of the fault feature values. The fault feature values ​​correspond one-to-one with the second springs, and the fault feature values ​​are the first feature values ​​corresponding to the second springs when their operating states are stress relaxation, cracks, or fractures. The fault feature values ​​correspond one-to-one with faulty operating states. In step S303, the standard feature value database and the fault feature value database are used to train a neural network to obtain the internal characteristic parameter inversion model.

[0149] Optionally, in step S3031, the above-mentioned standard feature values ​​and the above-mentioned fault feature values ​​are input into the neural network for analysis to obtain multiple result working states; in step S3032, residual analysis is performed on the training working states corresponding to the multiple result working states to obtain residual analysis results, and the parameters of the above-mentioned neural network are tuned according to the above-mentioned residual analysis results to obtain the above-mentioned internal characteristic parameter inversion model, wherein the above-mentioned training working states include the above-mentioned working states corresponding to the above-mentioned standard feature values ​​and the above-mentioned fault feature values.

[0150] This invention provides a processor for running a program, wherein the program executes the method for determining the working state of the opening and closing springs.

[0151] Specifically, the methods for determining the working state of the opening and closing springs include:

[0152] Step S201: Acquire the vibration signal of the spring in real time, and determine the first function based on the vibration signal. The first function is a function of the amplitude of the vibration signal changing with time.

[0153] Specifically, a vibration sensor is installed at the opening and closing springs to monitor the vibration signals generated when the high-voltage circuit breaker operates and the opening and closing springs move.

[0154] Step S202: Perform wavelet transform on the waveform corresponding to the first function to obtain the second function, which is a function of the change of the output power of the vibration signal with time.

[0155] Specifically, the signals generated during spring vibration are irregular and difficult to analyze directly. Therefore, wavelet transform is required. Wavelet transform has good localization properties in the time and frequency domains, which can better reveal the details of the signal.

[0156] Step S203: Determine the first characteristic value according to the second function mentioned above. The first characteristic value includes at least the maximum and minimum values ​​of the output power.

[0157] Specifically, it is very difficult to analyze the function directly. Therefore, the working state of the opening and closing springs during the operation of the high-voltage circuit breaker is characterized by the eigenvalues ​​of the function. The first eigenvalues ​​mentioned above include the maximum and minimum values ​​of the output power corresponding to the second function mentioned above.

[0158] Step S204: Input the first feature value into the internal characteristic parameter inversion model for analysis to obtain the working state of the spring. The working state is either a faulty working state or a non-faulty working state. The faulty working state is one of stress relaxation, cracking, and fracture. The internal characteristic parameter inversion model is trained by the historical first feature value and the working state corresponding to the historical first feature value.

[0159] Specifically, a neural network model is trained using historical feature value data of different springs to obtain an internal characteristic parameter inversion model. By inputting these feature values ​​into the model, the internal characteristic parameter inversion model can determine the current state of the spring based on the detected feature values, including states such as stress relaxation, cracking, and breakage.

[0160] Optionally, in step S2011, the vibration signal of the spring is acquired in real time, and a first waveform is generated based on the vibration signal, wherein the first waveform is a waveform showing the change of the amplitude of the vibration signal over time; in step S2012, the first function is determined based on the first waveform; in step S2023, wavelet transform is performed on the first waveform corresponding to the first function to obtain a second waveform, wherein the second waveform is a waveform showing the change of the output power of the vibration signal over time; in step S2024, the second function is determined based on the second waveform.

[0161] Optionally, in step S20211, based on the first waveform diagram, the amplitude of all the vibration signals is determined, and the instantaneous output power corresponding to all the amplitudes is calculated based on all the amplitudes, the shear modulus of the spring, the diameter of the spring wire, the mean diameter of the spring, the number of effective turns, the deformation, and the instantaneous velocity. The shear modulus is used to characterize the rigidity of the spring wire material, the mean diameter of the spring is the average of the inner and outer diameters of the spring, and the number of effective turns is the number of turns that maintain equal pitch. In step S20212, a third waveform diagram is generated based on all the instantaneous output power and the acquisition time of the corresponding vibration signals. The third waveform diagram is a waveform diagram showing the change of the output power over time before wavelet transform. In step S2023, wavelet transform is performed on the third waveform diagram to obtain the second waveform diagram.

[0162] Optionally, in step S2031, according to the second function, calculate the second characteristic value and the third characteristic value of the output power waveform. The second characteristic value is the difference between the output power at the first moment and the output power at the second moment in the second waveform diagram corresponding to the second function. The third characteristic value is the difference between the output power at the first moment and the output power at the third moment in the second waveform diagram corresponding to the second function. The first moment is any acquisition moment in the second waveform diagram. The second moment is the previous acquisition moment of the first moment. The third moment is the next acquisition moment of the first moment. The acquisition moment is the moment when the vibration signal is acquired. In step S2032, if both the second characteristic value and the third characteristic value are non-negative or both are non-positive, determine the output power at the first moment as the first characteristic value.

[0163] Optionally, in step S301, a standard feature value database is established, which includes standard feature values ​​of the vibration signals of multiple first springs and the corresponding operating states of the standard feature values. The standard feature values ​​correspond one-to-one with the first springs, and the standard feature values ​​are the first feature values ​​corresponding to the first springs when their operating states are not faulty operating states. In step S302, a fault feature value database is established, which includes fault feature values ​​of the vibration signals of multiple second springs and the corresponding operating states of the fault feature values. The fault feature values ​​correspond one-to-one with the second springs, and the fault feature values ​​are the first feature values ​​corresponding to the second springs when their operating states are stress relaxation, cracks, or fractures. The fault feature values ​​correspond one-to-one with faulty operating states. In step S303, the standard feature value database and the fault feature value database are used to train a neural network to obtain the internal characteristic parameter inversion model.

[0164] Optionally, in step S3031, the above-mentioned standard feature values ​​and the above-mentioned fault feature values ​​are input into the neural network for analysis to obtain multiple result working states; in step S3032, residual analysis is performed on the training working states corresponding to the multiple result working states to obtain residual analysis results, and the parameters of the above-mentioned neural network are tuned according to the above-mentioned residual analysis results to obtain the above-mentioned internal characteristic parameter inversion model, wherein the above-mentioned training working states include the above-mentioned working states corresponding to the above-mentioned standard feature values ​​and the above-mentioned fault feature values.

[0165] This invention provides a circuit system, including: a signal acquisition module for acquiring vibration signals monitored by a vibration sensor in real time; an output power waveform acquisition module for acquiring an output power waveform based on the vibration signal waveform acquired by the signal acquisition module; a feature value database establishment module for establishing a standard feature value database and a fault feature value database based on historical data; and an inversion module for determining the working state of the spring using a spring internal characteristic parameter inversion model trained through the standard feature value database and the fault feature value database.

[0166] The circuit system for the operation of a closing and opening spring provided in this embodiment of the invention further includes the closing and opening spring, a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs at least the following steps:

[0167] Step S201: Acquire the vibration signal of the spring in real time, and determine the first function based on the vibration signal. The first function is a function of the amplitude of the vibration signal changing with time.

[0168] Step S202: Perform wavelet transform on the waveform corresponding to the first function to obtain the second function, which is a function of the change of the output power of the vibration signal with time.

[0169] Step S203: Determine the first characteristic value according to the second function mentioned above. The first characteristic value includes at least the maximum and minimum values ​​of the output power.

[0170] Step S204: Input the first feature value into the internal characteristic parameter inversion model for analysis to obtain the working state of the spring. The working state is either a faulty working state or a non-faulty working state. The faulty working state is one of stress relaxation, cracking, and fracture. The internal characteristic parameter inversion model is trained by the historical first feature value and the working state corresponding to the historical first feature value.

[0171] Optionally, in step S2011, the vibration signal of the spring is acquired in real time, and a first waveform is generated based on the vibration signal, wherein the first waveform is a waveform showing the change of the amplitude of the vibration signal over time; in step S2012, the first function is determined based on the first waveform. In step S2023, wavelet transform is performed on the first waveform corresponding to the first function to obtain a second waveform, wherein the second waveform is a waveform showing the change of the output power of the vibration signal over time; in step S2024, the second function is determined based on the second waveform.

[0172] Optionally, in step S20211, based on the first waveform diagram, the amplitude of all the vibration signals is determined, and the instantaneous output power corresponding to all the amplitudes is calculated based on all the amplitudes, the shear modulus of the spring, the diameter of the spring wire, the mean diameter of the spring, the number of effective turns, the deformation, and the instantaneous velocity. The shear modulus is used to characterize the rigidity of the spring wire material, the mean diameter of the spring is the average of the inner and outer diameters of the spring, and the number of effective turns is the number of turns that maintain equal pitch. In step S20212, a third waveform diagram is generated based on all the instantaneous output power and the acquisition time of the corresponding vibration signals. The third waveform diagram is a waveform diagram showing the change of the output power over time before wavelet transform. In step S2023, wavelet transform is performed on the third waveform diagram to obtain the second waveform diagram.

[0173] Optionally, in step S2031, according to the second function, calculate the second characteristic value and the third characteristic value of the output power waveform. The second characteristic value is the difference between the output power at the first moment and the output power at the second moment in the second waveform diagram corresponding to the second function. The third characteristic value is the difference between the output power at the first moment and the output power at the third moment in the second waveform diagram corresponding to the second function. The first moment is any acquisition moment in the second waveform diagram. The second moment is the previous acquisition moment of the first moment. The third moment is the next acquisition moment of the first moment. The acquisition moment is the moment when the vibration signal is acquired. In step S2032, if both the second characteristic value and the third characteristic value are non-negative or both are non-positive, determine the output power at the first moment as the first characteristic value.

[0174] Optionally, in step S301, a standard feature value database is established, which includes standard feature values ​​of the vibration signals of multiple first springs and the corresponding operating states of the standard feature values. The standard feature values ​​correspond one-to-one with the first springs, and the standard feature values ​​are the first feature values ​​corresponding to the first springs when their operating states are not faulty operating states. In step S302, a fault feature value database is established, which includes fault feature values ​​of the vibration signals of multiple second springs and the corresponding operating states of the fault feature values. The fault feature values ​​correspond one-to-one with the second springs, and the fault feature values ​​are the first feature values ​​corresponding to the second springs when their operating states are stress relaxation, cracks, or fractures. The fault feature values ​​correspond one-to-one with faulty operating states. In step S303, the standard feature value database and the fault feature value database are used to train a neural network to obtain the internal characteristic parameter inversion model.

[0175] Optionally, in step S3031, the above-mentioned standard feature values ​​and the above-mentioned fault feature values ​​are input into the neural network for analysis to obtain multiple result working states; in step S3032, residual analysis is performed on the training working states corresponding to the multiple result working states to obtain residual analysis results, and the parameters of the above-mentioned neural network are tuned according to the above-mentioned residual analysis results to obtain the above-mentioned internal characteristic parameter inversion model, wherein the above-mentioned training working states include the above-mentioned working states corresponding to the above-mentioned standard feature values ​​and the above-mentioned fault feature values.

[0176] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having at least the following method steps:

[0177] Step S201: Acquire the vibration signal of the spring in real time, and determine the first function based on the vibration signal. The first function is a function of the amplitude of the vibration signal changing with time.

[0178] Step S202: Perform wavelet transform on the waveform corresponding to the first function to obtain the second function, which is a function of the change of the output power of the vibration signal with time.

[0179] Step S203: Determine the first characteristic value according to the second function mentioned above. The first characteristic value includes at least the maximum and minimum values ​​of the output power.

[0180] Step S204: Input the first feature value into the internal characteristic parameter inversion model for analysis to obtain the working state of the spring. The working state is either a faulty working state or a non-faulty working state. The faulty working state is one of stress relaxation, cracking, and fracture. The internal characteristic parameter inversion model is trained by the historical first feature value and the working state corresponding to the historical first feature value.

[0181] Optionally, in step S2011, the vibration signal of the spring is acquired in real time, and a first waveform is generated based on the vibration signal, wherein the first waveform is a waveform showing the change of the amplitude of the vibration signal over time; in step S2012, the first function is determined based on the first waveform. In step S2023, wavelet transform is performed on the first waveform corresponding to the first function to obtain a second waveform, wherein the second waveform is a waveform showing the change of the output power of the vibration signal over time; in step S2024, the second function is determined based on the second waveform.

[0182] Optionally, in step S20211, based on the first waveform diagram, the amplitude of all the vibration signals is determined, and the instantaneous output power corresponding to all the amplitudes is calculated based on all the amplitudes, the shear modulus of the spring, the diameter of the spring wire, the mean diameter of the spring, the number of effective turns, the deformation, and the instantaneous velocity. The shear modulus is used to characterize the rigidity of the spring wire material, the mean diameter of the spring is the average of the inner and outer diameters of the spring, and the number of effective turns is the number of turns that maintain equal pitch. In step S20212, a third waveform diagram is generated based on all the instantaneous output power and the acquisition time of the corresponding vibration signals. The third waveform diagram is a waveform diagram showing the change of the output power over time before wavelet transform. In step S2023, wavelet transform is performed on the third waveform diagram to obtain the second waveform diagram.

[0183] Optionally, in step S2031, according to the second function, calculate the second characteristic value and the third characteristic value of the output power waveform. The second characteristic value is the difference between the output power at the first moment and the output power at the second moment in the second waveform diagram corresponding to the second function. The third characteristic value is the difference between the output power at the first moment and the output power at the third moment in the second waveform diagram corresponding to the second function. The first moment is any acquisition moment in the second waveform diagram. The second moment is the previous acquisition moment of the first moment. The third moment is the next acquisition moment of the first moment. The acquisition moment is the moment when the vibration signal is acquired. In step S2032, if both the second characteristic value and the third characteristic value are non-negative or both are non-positive, determine the output power at the first moment as the first characteristic value.

[0184] Optionally, in step S301, a standard feature value database is established, which includes standard feature values ​​of the vibration signals of multiple first springs and the corresponding operating states of the standard feature values. The standard feature values ​​correspond one-to-one with the first springs, and the standard feature values ​​are the first feature values ​​corresponding to the first springs when their operating states are not faulty operating states. In step S302, a fault feature value database is established, which includes fault feature values ​​of the vibration signals of multiple second springs and the corresponding operating states of the fault feature values. The fault feature values ​​correspond one-to-one with the second springs, and the fault feature values ​​are the first feature values ​​corresponding to the second springs when their operating states are stress relaxation, cracks, or fractures. The fault feature values ​​correspond one-to-one with faulty operating states. In step S303, the standard feature value database and the fault feature value database are used to train a neural network to obtain the internal characteristic parameter inversion model.

[0185] Optionally, in step S3031, the above-mentioned standard feature values ​​and the above-mentioned fault feature values ​​are input into the neural network for analysis to obtain multiple result working states; in step S3032, residual analysis is performed on the training working states corresponding to the multiple result working states to obtain residual analysis results, and the parameters of the above-mentioned neural network are tuned according to the above-mentioned residual analysis results to obtain the above-mentioned internal characteristic parameter inversion model, wherein the above-mentioned training working states include the above-mentioned working states corresponding to the above-mentioned standard feature values ​​and the above-mentioned fault feature values.

[0186] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0187] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0188] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0189] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0190] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0191] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0192] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0193] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, 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, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0194] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0195] As can be seen from the above description, the embodiments of this application achieve the following technical effects:

[0196] 1) The method for determining the working state of the opening and closing spring of this application firstly acquires the vibration signal of the spring in real time, and determines a first function based on the vibration signal. The first function is a function of the amplitude of the vibration signal changing with time. Then, a wavelet transform is performed on the waveform corresponding to the first function to obtain a second function. The second function is a function of the output power of the vibration signal changing with time. Afterwards, a first characteristic value is determined based on the second function. The first characteristic value includes at least the maximum and minimum values ​​of the output power. Finally, the first characteristic value is input into the internal characteristic parameter inversion model for analysis to obtain the working state of the spring. The working state is either a fault working state or a non-fault working state. The fault working state is one of stress relaxation, cracking, and fracture. The internal characteristic parameter inversion model is obtained by training with historical first characteristic values ​​and the working states corresponding to the historical first characteristic values. This method acquires vibration signals from the opening and closing springs during operation using a vibration sensor. Feature values ​​are then extracted from these signals via wavelet analysis. A standard feature value database and a fault feature value database are established to train a neural network model, resulting in an internal characteristic parameter inversion model. The feature values ​​are then input into this model to obtain the operating state of the opening and closing springs. This method addresses the lack of a mature reliability assessment method and device for high-voltage circuit breaker opening and closing springs in existing technologies.

[0197] 2) The device for determining the working state of the opening and closing spring of this application comprises: a first determining unit acquiring the vibration signal of the spring in real time and determining a first function based on the vibration signal, wherein the first function is a function of the amplitude of the vibration signal changing with time; a calculation unit performing wavelet transform on the waveform corresponding to the first function to obtain a second function, wherein the second function is a function of the output power of the vibration signal changing with time; a second determining unit determining a first characteristic value based on the second function, wherein the first characteristic value includes at least the maximum and minimum values ​​of the output power; and a third determining unit inputting the first characteristic value into an internal characteristic parameter inversion model for analysis to obtain the working state of the spring, wherein the working state is a fault working state or a non-fault working state, wherein the fault working state is one of stress relaxation, cracking, and fracture, and the internal characteristic parameter inversion model is obtained by training with historical first characteristic values ​​and the working states corresponding to the historical first characteristic values. This device acquires vibration signals from the opening and closing springs during operation by controlling vibration sensors. It then extracts feature values ​​from these vibration signals using wavelet analysis, establishes a standard feature value database and a fault feature value database, and trains a neural network model to obtain an internal characteristic parameter inversion model. The feature values ​​are then input into this model to determine the operating state of the opening and closing springs. This method addresses the lack of a mature reliability assessment method and device for high-voltage circuit breaker opening and closing springs in existing technologies.

[0198] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for determining the working state of a closing / opening spring, characterized in that, The method includes: The vibration signal of the spring is acquired in real time, and a first function is determined based on the vibration signal, wherein the first function is a function of the change of the amplitude of the vibration signal over time. Perform wavelet transform on the waveform corresponding to the first function to obtain the second function, which is a function of the change of the output power of the vibration signal with time; Based on the second function, a first characteristic value is determined, wherein the first characteristic value includes at least the maximum and minimum values ​​of the output power; The first feature value is input into the internal characteristic parameter inversion model for analysis to obtain the working state of the spring. The working state is either a fault working state or a non-fault working state. The fault working state is one of stress relaxation, cracking, and fracture. The internal characteristic parameter inversion model is trained by the historical first feature value and the working state corresponding to the historical first feature value. Performing wavelet transform on the waveform corresponding to the first function to obtain the second function includes: performing wavelet transform on the first waveform corresponding to the first function to obtain the second waveform, wherein the second waveform is a waveform diagram of the output power of the vibration signal changing with time; and determining the second function based on the second waveform. Performing a wavelet transform on the first waveform corresponding to the first function to obtain a second waveform includes: determining the amplitude of all vibration signals based on the first waveform, and calculating the instantaneous output power corresponding to all amplitudes based on all amplitudes, the shear modulus of the spring, the diameter of the spring wire, the mean diameter of the spring, the number of effective turns, the deformation, and the instantaneous velocity. The shear modulus is used to characterize the rigidity of the spring wire material, the mean diameter of the spring is the average of the inner and outer diameters of the spring, and the number of effective turns is the number of turns maintaining equal pitch. Generating a third waveform based on all the instantaneous output power and the acquisition time of the corresponding vibration signal, the third waveform is a waveform showing the change of the output power over time before the wavelet transform. Performing a wavelet transform on the third waveform to obtain the second waveform.

2. The determination method according to claim 1, characterized in that, Real-time acquisition of the spring's vibration signal, and determination of a first function based on the vibration signal, including: The vibration signal of the spring is acquired in real time, and a first waveform is generated based on the vibration signal. The first waveform is a waveform diagram showing the change of the amplitude of the vibration signal over time. The first function is determined based on the first waveform diagram.

3. The determination method according to claim 2, characterized in that, The first eigenvalue is determined based on the second function, including: According to the second function, the second characteristic value and the third characteristic value of the output power waveform are calculated. The second characteristic value is the difference between the output power at the first time and the output power at the second time in the second waveform diagram corresponding to the second function. The third characteristic value is the difference between the output power at the first time and the output power at the third time in the second waveform diagram corresponding to the second function. The first time is any acquisition time in the second waveform diagram. The second time is the previous acquisition time of the first time. The third time is the next acquisition time of the first time. The acquisition time is the time when the vibration signal is acquired. If both the second feature value and the third feature value are non-negative or both the second feature value and the third feature value are non-positive, the output power corresponding to the first moment is determined to be the first feature value.

4. The determination method according to claim 1, characterized in that, Before inputting the first eigenvalue into the intrinsic characteristic parameter inversion model for analysis, the method includes: A standard feature value database is established, which includes standard feature values ​​of vibration signals of multiple first springs and the corresponding working states of the standard feature values. The standard feature values ​​correspond one-to-one with the first springs, and the standard feature values ​​are the first feature values ​​corresponding to the working states of the first springs when the working states are not faulty working states. A fault feature value database is established, which includes fault feature values ​​of vibration signals of multiple second springs and the corresponding working states of the fault feature values. The fault feature values ​​correspond one-to-one with the second springs. The fault feature values ​​are the first feature values ​​corresponding to the working states of the second springs when they are in stress relaxation, cracks or fractures. The fault feature values ​​correspond one-to-one with the fault working states. The neural network is trained using the standard feature value database and the fault feature value database to obtain the internal characteristic parameter inversion model.

5. The determination method according to claim 4, characterized in that, The internal characteristic parameter inversion model is obtained by training a neural network with the standard feature value database and the fault feature value database, including: The standard feature values ​​and the fault feature values ​​are input into a neural network for analysis to obtain multiple result working states; Residual analysis is performed on the training working states corresponding to the multiple result working states to obtain residual analysis results. The neural network is then tuned based on the residual analysis results to obtain the internal characteristic parameter inversion model. The training working states include the working states corresponding to the standard feature values ​​and the fault feature values.

6. A device for determining the working state of a closing / opening spring, characterized in that, The determining device includes: The first determining unit is used to acquire the vibration signal of the spring in real time and determine a first function based on the vibration signal, wherein the first function is a function of the amplitude of the vibration signal changing with time. The calculation unit is used to perform wavelet transform on the waveform corresponding to the first function to obtain a second function, wherein the second function is a function of the change of the output power of the vibration signal over time. The second determining unit is configured to determine a first characteristic value based on the second function, wherein the first characteristic value includes at least the maximum and minimum values ​​of the output power; The third determining unit is used to input the first feature value into the internal characteristic parameter inversion model for analysis to obtain the working state of the spring. The working state is either a fault working state or a non-fault working state. The fault working state is one of stress relaxation, cracking, and fracture. The internal characteristic parameter inversion model is trained by the historical first feature value and the working state corresponding to the historical first feature value. The calculation unit includes: a first calculation module, used to perform wavelet transform on the first waveform corresponding to the first function to obtain a second waveform, the second waveform being a waveform of the output power of the vibration signal changing with time; and a second determination module, used to determine the second function based on the second waveform. The first calculation module includes: a first calculation submodule, used to determine the amplitude of all the vibration signals based on the first waveform diagram, and to calculate the instantaneous output power corresponding to all the amplitudes based on all the amplitudes and the shear modulus, spring wire diameter, spring mean diameter, effective number of turns, deformation, and instantaneous velocity of the spring, wherein the shear modulus is used to characterize the rigidity of the spring wire material, the spring mean diameter is the average of the inner and outer diameters of the spring, and the effective number of turns is the number of turns maintaining equal pitch; a generation submodule, used to generate a third waveform diagram based on all the instantaneous output power and the acquisition time of the corresponding vibration signals, wherein the third waveform diagram is a waveform diagram showing the change of the output power over time before wavelet transform; and a second calculation submodule, used to perform wavelet transform on the third waveform diagram to obtain the second waveform diagram.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the determination method according to any one of claims 1 to 5.

8. A circuit system, characterized in that, include: The system includes a closing / opening spring, one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include methods for performing the determination method according to any one of claims 1 to 5.

9. The circuit system according to claim 8, characterized in that, The circuit system also includes: The signal acquisition module is used to acquire the vibration signals monitored by the vibration sensor in real time. An output power waveform acquisition module is used to acquire an output power waveform based on the vibration signal waveform acquired by the signal acquisition module. The feature value database creation module establishes a standard feature value database and a fault feature value database based on historical data. The inversion module uses a spring internal characteristic parameter inversion model trained by the standard feature value database and the fault feature value database to determine the working state of the spring.

Images