Bolt shaft fatigue test method and device under multi-mode perception and medium

Abstract

The invention discloses a bolt shaft fatigue test method and device under multi-modal sensing and a medium, and relates to the related field of mechanical structure fatigue tests.The method comprises the steps that a multi-modal sensing layer is deployed on a bolt shaft, multi-modal sensing monitoring is executed, and a multi-modal sensing monitoring data set is established; a periodic ultrasonic sensing signal is extracted, signal feature extraction is executed, a signal feature extraction result and an acquisition period are sent to a fatigue recognition main channel, and a fatigue damage evolution baseline is established; extracting a strain sensing time sequence signal and an acceleration sensing time sequence signal; carrying out additional damage analysis, and establishing a time sequence additional damage factor; and performing time sequence superposition fitting of the fatigue damage evolution baseline by using the time sequence additional damage factor, and updating the fatigue damage state of the bolt shaft by using a time sequence superposition fitting result. The technical problem that the damage identification sensitivity is low in existing bolt shaft fatigue monitoring is solved, and the technical effect of improving the bolt shaft fatigue damage identification sensitivity is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of mechanical structure fatigue test, in particular to a bolt shaft fatigue test method and device under multi-modal perception and a medium. BACKGROUND

[0002] As a key mechanical connection component, the precise monitoring of the fatigue damage of the bolt shaft is of great significance to the operation safety of major equipment. If early fatigue damage cannot be identified in time, it is easy to cause catastrophic structural failure accidents. At present, the mainstream method for bolt shaft fatigue monitoring is to collect signals through a single modal sensor (such as an ultrasonic probe or a strain gauge), and to identify damage based on time domain / frequency domain feature analysis. Since the single modal sensor can only obtain local damage information, and is easily disturbed by environmental noise, load fluctuations and other factors, the existing method has the problems of incomplete damage feature extraction, inaccurate evolution law representation, low early damage identification sensitivity, and is difficult to meet the dynamic evaluation needs of the fatigue state of the bolt shaft under complex working conditions.

[0003] In the related art at present, the bolt shaft fatigue monitoring has the technical problem of low damage identification sensitivity. SUMMARY

[0004] The present application provides a bolt shaft fatigue test method and device under multi-modal perception and a medium. A multi-modal perception layer is formed by arranging a coupling probe, a strain sensing washer and an acceleration sensor on the bolt shaft. The multi-modal perception monitoring data set is monitored and established. The periodic ultrasonic perception signal is extracted from the data set. The signal feature extraction is performed. The results and the collection period are transmitted to the fatigue identification main channel. The fatigue damage evolution baseline is established. The strain perception time series signal and the acceleration perception time series signal are extracted from the data set. The additional damage analysis is performed by using the two kinds of time series signals. The time series additional damage factor is constructed. The time series additional damage factor is used for time series superposition fitting of the fatigue damage evolution baseline. The bolt shaft fatigue damage state is updated. The technical problem of low damage identification sensitivity of the existing bolt shaft fatigue monitoring is solved. The technical effect of improving the fatigue damage identification sensitivity of the bolt shaft is achieved.

[0005] The application provides a bolt shaft fatigue test method under multi-modal perception, including: deploying a multi-modal perception layer on a bolt shaft, performing multi-modal perception monitoring, establishing a multi-modal perception monitoring dataset, the multi-modal perception layer including a coupling probe, a strain perception washer, and an acceleration sensor; extracting a periodic ultrasonic perception signal in the multi-modal perception monitoring dataset, performing signal feature extraction of the periodic ultrasonic perception signal, sending the signal feature extraction result and a collection period to a fatigue identification main channel, and establishing a fatigue damage evolution baseline; extracting a strain perception time series signal and an acceleration perception time series signal in the multi-modal perception monitoring dataset; performing additional damage analysis using the strain perception time series signal and the acceleration perception time series signal, establishing a time series additional damage factor; performing time series superposition fitting of the fatigue damage evolution baseline using the time series additional damage factor, and updating a bolt shaft fatigue damage state using a time series superposition fitting result.

[0006] In a possible implementation, the signal feature extraction of the periodic ultrasonic perception signal, the sending of the signal feature extraction result and the collection period to the fatigue identification main channel, the establishment of the fatigue damage evolution baseline, and the following processing are performed: the signal feature extraction includes echo time delay increment extraction, echo amplitude attenuation rate extraction, and echo waveform offset extraction; the collection period is used to initialize an independent identification channel and a cumulative damage channel in the fatigue identification main channel; after the independent identification channel receives the signal feature extraction result, transient fatigue state analysis of each period node is performed to establish a period fatigue state with period node identification; after the cumulative damage channel receives the signal feature extraction result and the period fatigue state, period signal change rate calculation is performed, and a fatigue damage evolution baseline is generated using a period signal change rate calculation result and the period fatigue state.

[0007] In a possible implementation, after the cumulative damage channel receives the signal feature extraction result and the period fatigue state, the period signal change rate calculation is performed, and the following processing is performed: a calibration fatigue period of the bolt shaft is established; node segmentation of the calibration fatigue period is performed using the period fatigue state, a node segmentation result is established, and a dynamic weight coefficient is configured using the node segmentation result; during the period signal change rate calculation, multi-feature damage weighted calculation is performed through the dynamic weight coefficient, the period fatigue state is corrected according to the multi-feature damage weighted calculation result, and a fatigue damage evolution baseline is generated.

[0008] In a possible implementation, the time sequence superposition fitting of the fatigue damage evolution baseline with the time sequence additional damage factors updates the bolt shaft fatigue damage state by using the time sequence superposition fitting result, and the following processing is performed: a backtracking time window is configured, and a time sequence decreasing weight is set according to a window length of the backtracking time window; impact jump identification is performed according to the time sequence additional damage factors, and an impact jump identification result is configured; and the time sequence superposition fitting of the fatigue damage evolution baseline with the time sequence additional damage factors is performed by using the impact jump identification result and the time sequence decreasing weight.

[0009] In a possible implementation, the time sequence superposition fitting of the fatigue damage evolution baseline with the time sequence additional damage factors updates the bolt shaft fatigue damage state by using the time sequence superposition fitting result, and the following processing is performed: when any time sequence additional damage factor is an impact jump identification result, a time node compensation of the fatigue damage corresponding to the time sequence additional damage factor is performed; when any time sequence additional damage factor is a non-impact jump identification result, weighted superposition of the plurality of time sequence additional damage factors is performed based on the time sequence decreasing weight; and the time sequence superposition fitting is completed by using the time node compensation and / or the weighted superposition.

[0010] In a possible implementation, the time sequence superposition fitting of the fatigue damage evolution baseline with the time sequence additional damage factors updates the bolt shaft fatigue damage state by using the time sequence superposition fitting result, and the following processing is performed: fatigue early warning trigger analysis is performed by using the updated bolt shaft fatigue damage state, a first early warning result is established; fatigue abnormal impact identification is performed according to the strain sensing time sequence signal and the acceleration sensing time sequence signal, a second early warning result is established; and early warning is reported by using the first early warning result and the second early warning result.

[0011] In a possible implementation, the multi-modal sensing monitoring establishes a multi-modal sensing monitoring data set, and the following processing is performed: historical fatigue test data is acquired, and a collection period of the coupled probe is set according to the historical fatigue test data; under the collection period, the coupled probe emits an ultrasonic signal, and a signal echo is received, and a periodic ultrasonic sensing signal is established; the strain sensing gasket and the acceleration sensor are activated to perform time sequence data collection, and a strain sensing time sequence signal and an acceleration sensing time sequence signal are established; and the multi-modal sensing monitoring data set is established according to the periodic ultrasonic sensing signal, the strain sensing time sequence signal, and the acceleration sensing time sequence signal.

[0012] In a possible implementation, the time sequence superposition fitting of the fatigue damage evolution baseline with the time sequence additional damage factors updates the bolt shaft fatigue damage state by using the time sequence superposition fitting result, and the following processing is performed: a backtracking time window is configured, and a time sequence decreasing weight is set according to a window length of the backtracking time window; impact jump identification is performed according to the time sequence additional damage factors, and an impact jump identification result is configured; and the time sequence superposition fitting of the fatigue damage evolution baseline with the time sequence additional damage factors is performed by using the impact jump identification result and the time sequence decreasing weight.

[0013] The application also provides an electronic device, comprising: a memory for storing executable instructions; and a processor for executing the executable instructions stored in the memory to implement the bolt shaft fatigue test method under multi-modal perception.

[0014] The application also provides a computer-readable storage medium, comprising: a computer program stored thereon, which is executed by a processor to implement the bolt shaft fatigue test method under multi-modal perception.

[0015] The bolt shaft fatigue test method under multi-modal perception, the device and the medium provided by the application first deploy a multi-modal perception layer on a bolt shaft, perform multi-modal perception monitoring, and establish a multi-modal perception monitoring dataset, the multi-modal perception layer comprises a coupling probe, a strain perception gasket and an acceleration sensor, then periodic ultrasonic perception signals in the multi-modal perception monitoring dataset are extracted, signal feature extraction of the periodic ultrasonic perception signals is performed, the signal feature extraction results and a collection period are sent to a fatigue identification main channel, a fatigue damage evolution baseline is established, strain perception time series signals and acceleration perception time series signals in the multi-modal perception monitoring dataset are extracted, additional damage analysis is performed by using the strain perception time series signals and the acceleration perception time series signals, a time series additional damage factor is established, and finally time series superposition fitting of the fatigue damage evolution baseline is performed by using the time series additional damage factor, and the bolt shaft fatigue damage state is updated by using the time series superposition fitting result. The technical effect of improving the fatigue damage identification sensitivity of the bolt shaft is achieved. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the application, the drawings of the embodiments of the application will be briefly introduced below, and a flowchart is used in the application to illustrate the operations performed by the system according to the embodiments of the application. It should be understood that the foregoing or the following operations are not necessarily performed in sequence. On the contrary, various steps can be processed in reverse order or at the same time according to needs. Meanwhile, other operations can be added to these processes, or one or more steps of operations can be removed from these processes.

[0017] Figure 1 A flowchart of the bolt shaft fatigue test method under multi-modal perception provided by the embodiments of the application is shown.

[0018] Figure 2 A structural schematic diagram of an electronic device provided by the embodiments of the application is shown.

[0019] Explanation of reference signs: input device 201, processor 202, memory 203, output device 204. DETAILED DESCRIPTION

[0020] The above description is only a summary of the technical solutions of the present application. In order to make the technical means of the present application more clear, the present application can be implemented according to the content of the description, and in order to make the above and other purposes, characteristics and advantages of the present application more obvious and easy to understand, the following specific embodiments of the present application are described.

[0021] In order to make the purposes, technical solutions and advantages of the present application more clear, the present application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0022] In the following description, "some embodiments" are related to a subset of all possible embodiments, but it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. The term "first\second" is only to distinguish similar objects, and does not represent the specific order of the objects. The terms "include" and "have" and any variations, are intended to cover non-exclusive inclusion, for example, a process, method, system, product or server including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or modules not clearly listed or inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as understood by those skilled in the art to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application.

[0023] The embodiments of the present application provide a bolt shaft fatigue test method under multi-modal perception, as shown in Figure 1 The method comprises the following steps: Step S100, deploying a multi-modal perception layer on a bolt shaft, performing multi-modal perception monitoring, establishing a multi-modal perception monitoring data set, the multi-modal perception layer comprising a coupling probe, a strain perception washer and an acceleration sensor.

[0024] Specifically, the multi-modal perception layer refers to a monitoring system integrating multiple sensors (such as ultrasonic probes, strain sensors, and acceleration sensors) for simultaneously collecting signals of multiple physical quantities. Specifically, the bolt shaft surface is cleaned to ensure that the installation location is free of impurities. According to design requirements, an ultrasonic coupling probe is used, which is fixed at a designated position of the bolt shaft. Through ultrasonic emission and reception devices, non-destructive testing of the internal structure of the bolt shaft is achieved. A strain perception gasket is installed between the bolt and the connected part. The gasket has a built-in strain sensor that can monitor the axial and circumferential strain of the bolt shaft in real time. An acceleration sensor is installed at an appropriate position of the bolt shaft to monitor the vibration acceleration signal of the bolt shaft during operation. Through a data acquisition card (such as an NI data acquisition card), the above sensors are connected, and the sampling frequency (such as 10 kHz) and sampling time (such as 10 seconds) are set. The data acquisition system is started, and multi-modal perception data of the bolt shaft under different working conditions are collected and stored as a multi-modal perception monitoring data set.

[0025] For example, for a bolt shaft used for bridge connection, when installing the coupling probe, a special ultrasonic coupling agent is used to ensure good contact between the probe and the surface of the bolt shaft; when installing the strain perception gasket, ensure that the gasket is tightly attached to the bolt and the connected part to avoid signal interference; when installing the acceleration sensor, use screws to fix the sensor to ensure that it does not loosen during vibration.

[0026] In one possible implementation, the step S100 of performing multi-modal perception monitoring and establishing a multi-modal perception monitoring data set further includes a step S110 of obtaining historical fatigue test data and setting the acquisition period of the coupling probe based on the historical fatigue test data. Specifically, fatigue test data similar to the current bolt shaft is obtained from a database or historical test records, including ultrasonic signal characteristics, strain data, and acceleration data. The fatigue damage evolution law in the historical fatigue test data is analyzed, and the acquisition period of the coupling probe is set based on the analysis results. For example, suppose the historical fatigue test data shows that the fatigue damage of the bolt shaft grows slowly within the first 100 hours, with a damage growth of about 10% every 100 hours, and after 100 hours, the damage growth is about 5% every 10 hours. Therefore, the acquisition period of the coupling probe can be set as follows: within the first 100 hours, collect data every 20 hours; after 100 hours, collect data every 10 hours.

[0027] Step S120, under the acquisition period, the coupling probe emits ultrasonic signals and receives signal echoes to establish a periodic ultrasonic perception signal. Specifically, the transmission frequency (such as 1 MHz) and pulse width (such as 10 μs) of the ultrasonic signal are set in the coupling probe. When the acquisition period arrives, the coupling probe is triggered to emit ultrasonic signals, receive reflected echo signals, and extract periodic signal characteristics through filtering and amplification processing.

[0028] Step S130, activate the strain sensing gasket, acceleration sensor to execute timing data collection, establish strain sensing timing signal, acceleration sensing timing signal. Specifically, activate the strain sensing gasket and acceleration sensor. Collect strain data of strain sensing gasket and acceleration data of acceleration sensor. The collected timing signal is low-pass filtered to remove high-frequency noise. The filtered signal is normalized to adjust the signal amplitude to 0-1.

[0029] Step S140, according to the periodic ultrasonic sensing signal, strain sensing timing signal, acceleration sensing timing signal, establish multi-modal sensing monitoring data set. Specifically, the signal data collected in steps S120 and S130 are integrated into a data set. The data set is stored in the database, including timestamp, ultrasonic signal feature, strain data and acceleration data. This implementation mode analyzes the historical fatigue test data, reasonably sets the acquisition period of the coupling probe, and ensures that data can be collected more frequently in the rapid evolution stage of fatigue damage, thereby improving the richness and effectiveness of the data.

[0030] Step S200, extract the periodic ultrasonic sensing signal in the multi-modal sensing monitoring data set, perform signal feature extraction of the periodic ultrasonic sensing signal, and send the signal feature extraction result and the acquisition period to the fatigue identification main channel to establish a fatigue damage evolution baseline.

[0031] Specifically, the periodic ultrasonic sensing signals are selected from the multi-modal sensing monitoring data set. These signals are collected by the coupling probe and reflect the ultrasonic echo characteristics of the internal structure of the bolt shaft. Digital signal processing techniques such as band-pass filters are used to remove noise and other non-periodic components, and pure periodic ultrasonic sensing signals are extracted. The extracted periodic ultrasonic sensing signals are subjected to fast Fourier transform (FFT) to convert time-domain signals to frequency-domain signals. The amplitude, frequency and phase of the frequency-domain signal are extracted. For example, the main frequency, amplitude maximum and phase offset of the signal are calculated. The extracted signal features (such as amplitude, frequency, phase) and acquisition period are sent to the fatigue identification main channel through a communication interface (such as Ethernet or USB). In the fatigue identification main channel, a fatigue damage evolution baseline is established according to the initial signal features. The fatigue damage evolution baseline is a reference curve used to describe the fatigue damage evolution process. For example, the initial ultrasonic signal amplitude, frequency and phase are used as baseline parameters.

[0032] In a possible implementation, the step S200 further includes a step S210 of performing signal feature extraction on the periodic ultrasonic sensing signals, and sending the signal feature extraction result and the collection period to the fatigue identification main channel to establish a fatigue damage evolution baseline. Specifically, the signal feature extraction includes echo time delay increment extraction, echo amplitude decay rate extraction, and echo waveform offset extraction. Specifically, time delay analysis is performed on the ultrasonic signals of each collection period to calculate the echo time delay increment, which is calculated by measuring the time delay change of the ultrasonic signal echo. Amplitude analysis is performed on the ultrasonic signals of each collection period to calculate the echo amplitude decay rate, which is calculated by analyzing the amplitude change of the ultrasonic signal echo. Waveform comparison is performed on the ultrasonic signals of each collection period to calculate the echo waveform offset, which is calculated by comparing the difference between the standard waveform and the actual waveform.

[0033] In the step S220, the independent identification channel and the cumulative damage channel in the fatigue identification main channel are initialized by using the collection period. Specifically, according to the collection period, an independent identification channel is set for each period node to analyze the transient fatigue state. According to the collection period, a cumulative damage channel is set to calculate the period signal change rate and generate the fatigue damage evolution baseline. The initial values of the independent identification channel and the cumulative damage channel are set to 0.

[0034] Step S230, after receiving the signal feature extraction results by the independent identification channel, the transient fatigue state of each cycle node is analyzed, and the cycle fatigue state with cycle node identification is established. Specifically, in each independent identification channel, the signal feature extraction results (echo time delay increment, echo amplitude attenuation rate, echo waveform offset) are received. According to the change of signal feature, the transient fatigue state is analyzed. The cycle fatigue state with identification is generated for each cycle node. Specifically, the threshold range can be set for the echo time delay increment, echo amplitude attenuation rate and echo waveform offset according to historical data or experimental results. These thresholds are used to judge the severity of the transient fatigue state. For example, the time delay increment threshold is set to 2 μs, the amplitude attenuation rate threshold is set to 0.02 V, and the waveform offset threshold is set to 2°. According to the change range of signal feature, the transient fatigue state is divided into "normal state", "slight damage", "moderate damage" and "severe damage". For example: if the time delay increment < 2 μs, the amplitude attenuation rate < 0.02 V, and the waveform offset < 2°, it is "normal state"; if the time delay increment is between 2-4 μs, the amplitude attenuation rate is between 0.02-0.04 V, and the waveform offset is between 2-4°, it is "slight damage"; if the time delay increment is between 4-6 μs, the amplitude attenuation rate is between 0.04-0.06 V, and the waveform offset is between 4-6°, it is "moderate damage"; if the time delay increment > 6 μs, the amplitude attenuation rate > 0.06 V, and the waveform offset > 6°, it is "severe damage". Using logical judgment or rule-based algorithm, the transient fatigue state is judged according to the signal feature extraction results.

[0035] Step S240, after receiving the signal feature extraction results and the cycle fatigue state by the cumulative damage channel, the cycle signal change rate is calculated, and the fatigue damage evolution baseline is generated by using the cycle signal change rate calculation result and the cycle fatigue state. Specifically, the cycle signal change rate refers to the change rate of signal features (such as echo time delay increment, echo amplitude attenuation rate, echo waveform offset) between adjacent collection cycles. For each signal feature, the change amount between adjacent cycles is calculated and standardized as a change rate. For example, for the echo time delay increment, the change rate can be expressed as the ratio of the time delay increment change amount between adjacent cycles to the collection cycle. The fatigue damage evolution baseline is a reference curve for describing the evolution process of fatigue damage over time. Based on the cycle signal change rate and the cycle fatigue state, the fatigue damage evolution baseline is generated by a cumulative damage model (such as a linear cumulative damage model). This implementation can realize short-term and long-term fatigue monitoring through independent identification channel and cumulative damage channel, which can capture transient changes and evaluate cumulative damage, thereby providing more comprehensive and accurate data support for bolt shaft fatigue monitoring.

[0036] In one possible implementation, after the cumulative damage channel is used to receive the signal feature extraction result and the cycle fatigue state, a cycle signal change rate is calculated, and step S240 further includes step S241 of establishing a calibration fatigue cycle of the bolt shaft. Specifically, historical fatigue test data is analyzed to determine the fatigue characteristics of the bolt shaft at different stages. According to the evolution law of fatigue damage, the entire fatigue test process is divided into three stages of initial stage, middle stage and final stage, and a calibration fatigue cycle is set for each stage. For example, the initial stage is 0-50 hours (the amplitude attenuation rate is more sensitive, the time delay increment and the waveform shift change less, but gradually increase); the middle stage is 50-100 hours (the amplitude attenuation rate and the time delay increment are sensitive, the waveform shift starts to change significantly, and the fatigue damage gradually accumulates); and the final stage is 100-150 hours (the time delay increment and the waveform shift are more sensitive, the amplitude attenuation rate changes tend to be stable, and the fatigue damage accumulates rapidly).

[0037] Step S242, node segmentation of the calibration fatigue cycle is performed using the cycle fatigue state to establish a node segmentation result, and a dynamic weight coefficient is configured by using the node segmentation result. Specifically, according to the calibration fatigue cycle, the collected cycle fatigue state data is segmented into different nodes, and each node corresponds to a specific time range and fatigue stage. According to the fatigue stage characteristics of each node, different weight coefficients are assigned to different signal features (amplitude attenuation rate, time delay increment, and waveform shift). The assignment of the weight coefficients is based on the sensitive features of each stage. For example, the amplitude attenuation rate weight is higher in the initial stage, and the time delay increment and the waveform shift weight are lower; the amplitude attenuation rate and the time delay increment weight are similar in the middle stage, and the waveform shift weight is moderate; and the time delay increment and the waveform shift weight are higher in the final stage, and the amplitude attenuation rate weight is lower.

[0038] Step S243, during the cycle signal change rate calculation process, multi-feature damage weighted calculation is performed by using the dynamic weight coefficient, the cycle fatigue state is corrected according to the multi-feature damage weighted calculation result, and a fatigue damage evolution baseline is generated. Specifically, according to the dynamic weight coefficient, the change rate of each signal feature is weighted and calculated, and the total weighted value is (amplitude attenuation rate change rate × amplitude attenuation rate weight) + (time delay increment change rate × time delay increment weight) + (waveform shift change rate × waveform shift weight). According to the multi-feature damage weighted calculation result, the fatigue state of each cycle is corrected, and the corrected fatigue state more accurately reflects the actual fatigue damage degree. The corrected fatigue state of each cycle is accumulated to form a complete fatigue damage evolution baseline. This implementation adjusts the weight of the signal feature according to the fatigue characteristics of different stages through the dynamic weight coefficient, which can more accurately reflect the evolution process of the fatigue damage. Through the multi-feature damage weighted calculation, the fatigue state of each cycle is corrected, which avoids the limitation of a single feature and improves the accuracy of the fatigue state evaluation.

[0039] In a possible implementation, the step S200 of sending the signal feature extraction result and the collection period to the fatigue identification main channel and establishing a fatigue damage evolution baseline further includes a step S250 of establishing an aging fitting of the coupling probe and configuring a drift correction factor using the aging fitting. Specifically, signal feature data of the coupling probe at different use times (such as 0 hours, 50 hours, 100 hours, 150 hours, etc.) are collected, including amplitude, time delay, waveform, etc., for analyzing the aging trend of the coupling probe. Mathematical modeling methods (such as linear regression, polynomial fitting, etc.) are used to fit the aging data of the coupling probe, to establish an aging model for describing the change law of the coupling probe performance over time. According to the aging model, a drift correction factor for each collection period is calculated, which is used to correct the drift of the coupling probe signal and ensure the accuracy of the signal feature.

[0040] After the step S260 of performing periodic parameter drift correction of the fatigue identification main channel using the drift correction factor, the fatigue damage evolution baseline is established. Specifically, the signal feature of each collection period is corrected using the drift correction factor, and the corrected signal feature more accurately reflects the actual fatigue state. Based on the corrected signal feature, the fatigue state of each period is calculated, the fatigue state of each period is accumulated, and a complete fatigue damage evolution baseline is generated. This implementation can effectively correct the drift of the signal by establishing an aging fitting model of the coupling probe and configuring a drift correction factor, and ensure the accuracy of the signal feature. The corrected signal feature can more accurately reflect the actual fatigue state, thereby improving the reliability of the fatigue damage evolution baseline.

[0041] In step S300, strain perception time series signals and acceleration perception time series signals in the multi-modal perception monitoring data set are extracted.

[0042] Specifically, the data screening algorithm is used to extract the preprocessed strain perception time series signals and acceleration perception time series signals from the multi-modal perception monitoring data set.

[0043] In step S400, additional damage analysis is performed using the strain perception time series signals and the acceleration perception time series signals, and a time series additional damage factor is established.

[0044] Specifically, the time-series additional damage factor refers to a factor for quantifying the influence of additional damage obtained by analyzing time-series signals. The pre-processed strain sensing time-series signals and acceleration sensing time-series signals are analyzed using a machine learning algorithm (such as a support vector machine, SVM) to identify additional damage features. For example, the SVM model is trained using labeled training data, and the pre-processed strain sensing time-series signals and acceleration sensing time-series signals are input into the SVM model to identify additional damage features. According to the identification result, the time-series additional damage factor is established to quantify the influence of additional damage on fatigue damage. For example, the additional damage factor is defined as the ratio of the additional damage feature to the normal state feature. For example, assuming that the SVM model identifies an additional damage feature in the strain sensing time-series signal with an amplitude of 0.2, while the amplitude in the normal state is 0.1, the additional damage factor can be defined as 0.2 / 0.1 = 2.

[0045] Step S500, time-series superposition fitting of the fatigue damage evolution baseline is performed with the time-series additional damage factor, and the bolt shaft fatigue damage state is updated using the time-series superposition fitting result.

[0046] Specifically, time-series superposition fitting refers to mathematically fitting the additional damage factor with the time-series fatigue damage evolution baseline to update the fatigue damage state. The time-series additional damage factor is superposition fitted with the time-series fatigue damage evolution baseline using a mathematical modeling method (such as linear regression or nonlinear regression). The fatigue damage state of the bolt shaft is updated according to the fitting result, and the updated fatigue damage state is displayed through a visualization tool (such as a plotting library in Matlab or Python).

[0047] For example, assuming that the fatigue damage evolution baseline is a linearly increasing curve with a slope of 0.1, and the additional damage factor is 2, the slope of the updated fatigue damage state curve is 0.1 x 2 = 0.2. The fatigue damage state curve plotted by Matlab can intuitively show the fatigue damage evolution process of the bolt shaft.

[0048] In a possible implementation, the time series superposition fitting of the fatigue damage evolution baseline with the time series additional damage factor further comprises the following step S510: configuring a backtracking time window and setting a time series decreasing weight according to the window length of the backtracking time window. Specifically, a backtracking time window is defined to consider the influence of additional damage in the past on the current fatigue state. The length of the backtracking time window can be set according to actual requirements, for example, 30 hours, 50 hours or 100 hours. According to the length of the backtracking time window, a decreasing weight is set for each time point to reflect the characteristic that the influence of additional damage on the current state decreases with time. The decreasing weight can adopt linear decrease, exponential decrease or other suitable decreasing functions.

[0049] In step S520, impact jump identification is performed according to the time series additional damage factor, and an impact jump identification result is configured. Specifically, the time series additional damage factor is analyzed to identify damage that increases significantly in a short time (i.e., impact jump). Impact jump represents rapid accumulation of fatigue damage or sudden damage. For example, the change amount of the additional damage factor between adjacent time points is calculated, and the time point at which the change amount exceeds a threshold is marked as an impact jump. The identified impact jump is marked, and the time point and amplitude at which it occurs are recorded.

[0050] In step S530, the time series superposition fitting of the fatigue damage evolution baseline with the time series additional damage factor is performed by using the impact jump identification result and the time series decreasing weight. Specifically, during the time series superposition fitting process, special attention is paid to the impact jump identification result. For the identified impact jump point, a higher weight or special processing is given to reflect its significant influence on the fatigue damage state. The impact jump point is an acceleration stage of fatigue damage, and its influence needs to be highlighted in the fitting process. For non-impact jump points, the time series decreasing weight is applied to reflect the characteristic that the influence of additional damage on the current state decreases with time. By combining the impact jump identification result and the time series decreasing weight, the time series additional damage factor is superposed and fitted with the fatigue damage evolution baseline, and the fitting result is used to update the fatigue damage state of the bolt shaft. This implementation can dynamically adjust the fatigue damage state by combining the time series decreasing weight and the impact jump identification result, and ensure the accuracy and real-time performance of the fatigue damage evolution baseline.

[0051] In a possible implementation, the step S530 of performing the time series superposition fitting of the time series additional damage factors on the fatigue damage evolution baseline by using the impact jump identification result and the time series decreasing weight further includes a step S531 of performing time node compensation of the fatigue damage according to the corresponding time series additional damage factor when the time series additional damage factor is the impact jump identification result. Specifically, according to the impact jump identification result, it is determined which time points are impact jump points. For each impact jump point, the fatigue damage evolution baseline is compensated at the time node according to the amplitude of the additional damage factor of the impact jump point, so that the impact of the impact jump is directly reflected on the fatigue damage evolution baseline. For example, if the additional damage factor of the impact jump point is 0.2, the value is directly added to the fatigue damage evolution baseline at the current time node.

[0052] The step S532 includes a step of performing weighted superposition of the multiple time series additional damage factors based on the time series decreasing weight when the time series additional damage factor is the non-impact jump identification result. Specifically, for the non-impact jump point, the additional damage factors are weighted and superposed according to the time series decreasing weight. The superposition strategy can be adjusted according to actual needs, for example, linear superposition or nonlinear superposition.

[0053] The step S533 includes a step of completing the time series superposition fitting through the time node compensation and / or the weighted superposition. Specifically, the results of the time node compensation and / or the weighted superposition are combined to complete the time series superposition fitting. According to the fitting result, the fatigue damage state of the bolt shaft is dynamically updated. This implementation can more comprehensively reflect the evolution process of the fatigue damage by comprehensively considering the additional damage factor, the time series decreasing weight and the impact jump identification result, and can improve the reliability of the fatigue monitoring. Through the time node compensation, the rapid accumulation or sudden damage of the fatigue damage can be highlighted, so that the updating of the fatigue damage state is more sensitive and accurate.

[0054] In a possible implementation, the step S500 of updating the fatigue damage state of the bolt shaft by using the time series superposition fitting result further includes a step S540 of performing fatigue warning triggering analysis by using the updated fatigue damage state of the bolt shaft to establish a first warning result. Specifically, according to historical data, experimental results or industry standards, a warning threshold of the fatigue damage is set. For example, it is set that the warning is triggered when the fatigue damage degree reaches 0.8. According to the updated fatigue damage state, it is analyzed whether the preset fatigue damage threshold is reached. If the fatigue damage state exceeds the preset threshold, the fatigue warning is triggered, and warning information is recorded. The warning information includes a time point, a fatigue damage degree, a warning level and the like.

[0055] Step S550, according to the strain sensing time sequence signal, the acceleration sensing time sequence signal, fatigue abnormal impact recognition is carried out, and the second early warning result is established. Specifically, the strain sensing time sequence signal and the acceleration sensing time sequence signal are analyzed, and whether abnormal impact exists is identified. Abnormal impact can be identified by mutation, peak value or frequency change of the signal. For example, it is considered that abnormal impact exists when the strain signal exceeds a certain threshold or the peak value of the acceleration signal exceeds a certain threshold. If abnormal impact is identified, fatigue abnormal impact early warning is triggered, and early warning information is recorded. The early warning information includes the time point, the abnormal impact amplitude and the early warning level.

[0056] Step S560, the first early warning result, the second early warning result is used for early warning. Specifically, the first early warning result (fatigue damage state) and the second early warning result (fatigue abnormal impact) are combined to carry out comprehensive early warning. According to the early warning level and the early warning type, a suitable alarm mode is selected, such as audible and visual alarm, short message notification, system prompt, etc. All early warning information is recorded in the system log for subsequent analysis and tracing. This implementation mode realizes multi-dimensional early warning analysis by combining fatigue damage state and fatigue abnormal impact, and improves the accuracy and reliability of early warning.

[0057] The embodiment of the application adopts a multi-modal sensing layer composed of a coupling probe, a strain sensing gasket and an acceleration sensor arranged on the bolt shaft to carry out monitoring and establish a multi-modal sensing monitoring data set. Periodic ultrasonic sensing signals are extracted from the data set, signal feature extraction is carried out, and the results and the collection period are transmitted to the fatigue identification main channel to establish a fatigue damage evolution baseline. Strain sensing time sequence signals and acceleration sensing time sequence signals are extracted from the data set, additional damage analysis is carried out using the two kinds of time sequence signals, a time sequence additional damage factor is constructed, the fatigue damage evolution baseline is time sequence superposition fitted using the time sequence additional damage factor, and the fatigue damage state of the bolt shaft is updated. Technical means solve the technical problem of low damage identification sensitivity of the existing bolt shaft fatigue monitoring, and achieve the technical effect of improving the fatigue damage identification sensitivity of the bolt shaft.

[0058] Based on the foregoing embodiments, the embodiment of the application also provides an electronic device and a computer readable storage medium, the computer readable storage medium stores a computer program, and the computer program is executed by a processor of the electronic device to realize the method according to any one of the foregoing embodiments.

[0059] Figure 2 FIG. 1 is a structural schematic diagram of an electronic device provided by an embodiment of the application, which shows a block diagram of an exemplary electronic device suitable for implementing the embodiments of the application. Figure 2The electronic device shown is merely an example and should not bring any limitation to the function and use range of the embodiments of the present application. The electronic device is in the form of a general computing device, and its components can include, but are not limited to, an input device 201, a processor 202, a memory 203, and an output device 204. The processor 202 can be one or more; the memory 203 can include a computer readable medium and at least one program product having a set of (at least one) program modules configured to perform the functions of the embodiments of the present application.

[0060] The memory 203 shown in the embodiments of the present application can employ any combination of one or more computer readable media; the computer readable storage media can be, but is not limited to, an infrared ray, a semiconductor system, a device, or a component, or a combination of any of the above, for storing software programs, computer executable programs, and modules, such as the program instructions / modules corresponding to the bolt shaft fatigue test method under multi-modal perception in the embodiments of the present application. The processor 202 executes various function applications and data processing of the computer device by running the software programs, instructions, and modules stored in the memory 203, that is, implements the bolt shaft fatigue test method under multi-modal perception as described above.

[0061] The above specific embodiments do not constitute a limitation to the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution, and improvement made within the spirit and principle of the present application should be included in the protection scope of the present application. In some cases, the actions or steps described in the present application can be executed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are possible or can be advantageous.

Claims

1. A method for bolt shaft fatigue testing under multi-modal perception, characterized in that, The method comprises: Deploying a multi-modal sensing layer on the bolt shaft, performing multi-modal sensing monitoring, establishing a multi-modal sensing monitoring dataset, the multi-modal sensing layer comprising a coupling probe, a strain sensing gasket, and an acceleration sensor; Extracting periodic ultrasonic sensing signals in the multi-modal sensing monitoring dataset, performing signal feature extraction of the periodic ultrasonic sensing signals, sending the signal feature extraction results and the collection period to a fatigue identification main channel, and establishing a fatigue damage evolution baseline; Extracting strain sensing time series signals and acceleration sensing time series signals in the multi-modal sensing monitoring dataset; Performing additional damage analysis using the strain sensing time series signals and the acceleration sensing time series signals, and establishing a time series additional damage factor; Performing time series superposition fitting of the fatigue damage evolution baseline using the time series additional damage factor, and updating the fatigue damage state of the bolt shaft using the time series superposition fitting result.

2. The bolt shaft fatigue testing method under multi-modal perception as claimed in claim 1, wherein, The signal feature extraction of the periodic ultrasonic sensing signals, the sending of the signal feature extraction results and the collection period to the fatigue identification main channel, and the establishment of the fatigue damage evolution baseline comprise: The signal feature extraction comprises echo time delay increment extraction, echo amplitude decay rate extraction, and echo waveform offset extraction; The collection period is used to initialize independent identification channels and cumulative damage channels in the fatigue identification main channel; After the independent identification channels receive the signal feature extraction results, transient fatigue state analysis of each period node is performed, and a period fatigue state with period node identification is established; After the cumulative damage channels receive the signal feature extraction results and the period fatigue state, period signal change rate calculation is performed, and a fatigue damage evolution baseline is generated using the period signal change rate calculation result and the period fatigue state.

3. The bolt shaft fatigue testing method under multi-modal perception as claimed in claim 2, wherein, The period signal change rate calculation performed after the cumulative damage channels receive the signal feature extraction results and the period fatigue state comprises: A calibration fatigue period of the bolt shaft is established; Node segmentation of the calibration fatigue period is performed using the period fatigue state, a node segmentation result is established, and a dynamic weight coefficient is configured based on the node segmentation result; During the period signal change rate calculation, multi-feature damage weighted calculation is performed through the dynamic weight coefficient, the period fatigue state is corrected based on the multi-feature damage weighted calculation result, and a fatigue damage evolution baseline is generated.

4. The bolt shaft fatigue testing method under multi-modal perception as claimed in claim 1, wherein, The time series superposition fitting of the fatigue damage evolution baseline using the time series additional damage factor comprises: A backtracking time window is configured, and a time series decreasing weight is set according to the window length of the backtracking time window; Impact jump identification is performed according to the time series additional damage factor, and an impact jump identification result is configured; The time series superposition fitting of the fatigue damage evolution baseline using the time series additional damage factor is performed using the impact jump identification result and the time series decreasing weight.

5. The bolt shaft fatigue testing method under multi-modal perception as claimed in claim 4, wherein, The time series superposition fitting of the fatigue damage evolution baseline using the time series additional damage factor comprises: When any time sequence additional damage factor is an impact jump identification result, time node compensation corresponding to the fatigue damage is performed according to the corresponding time sequence additional damage factor; When any time sequence additional damage factor is a non-impact jump identification result, the weighted superposition of multiple time sequence additional damage factors is performed based on time sequence decreasing weights; The time sequence superposition fitting is completed by time node compensation and / or weighted superposition.

6. The bolt shaft fatigue testing method under multi-modal sensing as claimed in claim 1, wherein, The bolt shaft fatigue damage state is updated by using the time sequence superposition fitting result, including: Fatigue early warning trigger analysis is performed by using the updated bolt shaft fatigue damage state, and a first early warning result is established; Fatigue abnormal impact identification is performed according to the strain sensing time sequence signal and the acceleration sensing time sequence signal, and a second early warning result is established; The first early warning result and the second early warning result are used for early warning.

7. The bolt shaft fatigue testing method under multi-modal perception as claimed in claim 1, wherein, The multi-modal sensing monitoring is performed, and a multi-modal sensing monitoring data set is established, including: Historical fatigue test data is acquired, and a collection period of the coupled probe is set according to the historical fatigue test data; Under the collection period, the coupled probe emits an ultrasonic signal and receives a signal echo, and a periodic ultrasonic sensing signal is established; The strain sensing gasket and the acceleration sensor are activated to perform time sequence data acquisition, and strain sensing time sequence signals and acceleration sensing time sequence signals are established; A multi-modal sensing monitoring data set is established according to the periodic ultrasonic sensing signal, the strain sensing time sequence signal, and the acceleration sensing time sequence signal.

8. The bolt shaft fatigue testing method under multi-modal perception as claimed in claim 1, wherein, The signal feature extraction result and the collection period are sent to a fatigue identification main channel to establish a fatigue damage evolution baseline, and the method further includes: An aging fitting of the coupled probe is established, and a drift correction factor is configured by using the aging fitting; After periodic parameter drift correction of the fatigue identification main channel is performed by using the drift correction factor, the fatigue damage evolution baseline is established.

9. An electronic device, comprising: The electronic device includes: A memory for storing executable instructions; A processor for executing the executable instructions stored in the memory, realizing the bolt shaft fatigue test method under multi-modal sensing according to any one of claims 1 to 8.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to realize the bolt shaft fatigue test method under multi-modal sensing according to any one of claims 1 to 8.

Images