Bridge boom pin sensor for health monitoring and method of use

Abstract

The application relates to a bridge suspender pin shaft sensor for health monitoring and a use method thereof, the bridge suspender pin shaft sensor for health monitoring comprising a pin shaft body, a plurality of eddy current sensors for detecting deformation displacement and a plurality of corresponding temperature sensors for detecting temperature, the pin shaft body being provided with a plurality of annular grooves, the eddy current sensors and the temperature sensors being integrally arranged in the annular grooves, each of the eddy current sensors and the corresponding temperature sensor forming a sensor group, and the detection data of the eddy current sensors and the temperature sensors being combined to infer a pin shaft stress value. The application provides a sensor capable of directly measuring the mechanical condition of a suspender pin shaft, and capable of long-time monitoring of the mechanical state of a bridge suspender and a pin shaft, improves the clarity of bridge suspender pin shaft monitoring, and enhances the stability and anti-interference capability of the monitoring sensor.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of pin shaft monitoring, and in particular to a bridge suspender pin shaft sensor for health monitoring and a use method thereof. BACKGROUND

[0002] At present, large bridges such as arch bridges and suspension bridges often have suspender components. These large bridges are statically indeterminate structures, and the local mechanical conditions are affected by the overall stress conditions. In these large bridges, the suspender transmits the load of the bridge deck girder to the support body such as the suspension cable and the arch, and these support bodies are key load transmission components. The pin shafts on the bridge suspender and the suspender provide stable support for the components such as the suspender and the suspender.

[0003] In related technologies, the vibration or strain sensor for monitoring the vibration or strain of the pin shaft establishes a correlation with the health condition of the bridge, and uses the correlation and the monitoring data of the sensor to monitor the pin shaft, but generally the correlation is relatively complex, which leads to unclear monitoring of the pin shaft, and only when the pin shaft structure deteriorates to a high degree can there be a more obvious feature. SUMMARY

[0004] In order to provide a sensor that can directly measure the mechanical condition of the suspender pin shaft, and can monitor the mechanical state of the pin shaft of the bridge suspender and the suspender for a long time, improve the clarity of monitoring the bridge suspender pin shaft, and enhance the stability and anti-interference ability of the monitoring sensor, the present application provides a bridge suspender pin shaft sensor for health monitoring and a use method thereof.

[0005] In a first aspect, the above application purpose is achieved by the following technical solution:

[0006] A bridge suspender pin shaft sensor for health monitoring, the bridge suspender pin shaft sensor for health monitoring comprising: a pin shaft body, a plurality of eddy current sensors for detecting deformation displacement, and a plurality of temperature sensors corresponding to the eddy current sensors for detecting temperature, the pin shaft body is provided with a plurality of annular grooves, the eddy current sensors and the temperature sensors are integrally arranged in the annular grooves, each of the eddy current sensors and the corresponding temperature sensor forms a sensor group, and the detection data of the eddy current sensors and the temperature sensors are combined to infer the pin shaft stress value.

[0007] By adopting the technical scheme, the bridge suspender pin shaft sensor for health monitoring comprises a pin shaft body and a plurality of sensors, the sensors comprise a plurality of eddy current sensors for detecting deformation displacement and a corresponding plurality of temperature sensors for detecting temperature, and the sensors are installed on the pin shaft through a plurality of annular grooves arranged on the pin shaft body, so that the mechanical state of the pin shaft can be more accurately and directly measured, and the interference of other factors on the sensors is reduced, the probability of damage or falling of the sensors is reduced due to the integration of the sensors in the annular grooves of the pin shaft, the service life of the sensors is prolonged, and the sensors can monitor the mechanical state of the pin shaft of the bridge suspender and rod for a long time. In addition, the eddy current sensor is mainly used for non-contact measurement of the displacement of the pin shaft. When the pin shaft vibrates or deforms during work, the eddy current sensor can accurately capture the displacement change. This displacement change is an important manifestation of the mechanical state of the pin shaft, and can reflect whether the pin shaft is subjected to excessive external force and whether there are problems such as wear or fatigue. The temperature sensor can measure the temperature of the pin shaft in real time. The temperature change is closely related to the mechanical state of the pin shaft. For example, when the pin shaft is subjected to excessive friction or load, the temperature of the pin shaft may rise, thereby indirectly reflecting the stress condition, friction state and potential damage risk of the pin shaft. In addition, there is a more prominent correlation between the monitoring data of the eddy current sensor and the temperature sensor. For example, when the pin shaft is subjected to excessive friction, the monitoring data of the eddy current sensor and the temperature sensor will both rise. Therefore, the eddy current sensor and the temperature sensor are used in combination to improve the clarity of the monitoring of the bridge suspender pin shaft. In addition, the mechanical state of the pin shaft can be more comprehensively understood by comprehensively analyzing the displacement and temperature information, the measurement accuracy and reliability are improved, and potential problems of the pin shaft can be found in time, thereby providing an important basis for preventing and solving pin shaft failures.

[0008] In a preferred example, the temperature sensor is a thermocouple sensor, and each eddy current sensor is integrated with a corresponding thermocouple sensor and arranged in the annular groove.

[0009] By adopting the technical scheme, the temperature sensor is a thermocouple sensor, and the thermocouple directly contacts the measured object, avoiding the influence of intermediate media on the measurement result, thereby ensuring high measurement accuracy. The thermocouple sensor can continuously measure in a very wide temperature range, from very low temperature to very high temperature, and can maintain good performance, so that the thermocouple can adapt to various complex and extreme working environments. In addition, the thermal mass of the thermocouple sensor is low, so it can respond to temperature changes faster. In addition, each eddy current sensor is integrated with a corresponding thermocouple sensor, so that each eddy current sensor and the corresponding thermocouple sensor can detect at the same time, ensuring the accuracy and synchronization of the detection data.

[0010] The application can be further configured in a preferred example that: the annular groove is provided with a plurality of eddy current sensors and thermocouple sensors on both sides, the eddy current sensors provided on both sides of the annular groove are staggered, a metal shell is arranged in the annular groove, and the metal shell is used for covering the eddy current sensors and the thermocouple sensors.

[0011] By adopting the above technical scheme, the annular groove on the pin shaft surrounds the pin shaft, the annular groove is provided with a plurality of eddy current sensors and thermocouple sensors on both sides, the eddy current sensors and the corresponding thermocouple sensors are uniformly arranged in the entire annular groove, the sensors are arranged on the free surface of the groove side, the influence of the creep of the main stress part of the pin shaft on the sensor reading can be avoided, and the pin shaft can be monitored in all directions, the displacement or temperature change of different parts of the pin shaft can be captured in time by the eddy current sensors and the corresponding thermocouple sensors, so that the comprehensive detection of the mechanical state of the pin shaft is ensured, the uniform distribution of the multiple sensors makes it possible to obtain data from multiple angles and positions, which helps to reduce the error of a single sensor, thereby improving the accuracy of the overall measurement, and the arrangement of multiple sensors provides data redundancy, thereby ensuring the reliability of the entire monitoring system. In addition, the metal shell arranged in the annular groove is used for covering the eddy current sensors and the thermocouple sensors, which further reduces the interference of external environmental factors on the detection of the sensors, thereby further improving the accuracy of the overall measurement.

[0012] The application can be further configured in a preferred example that: the eddy current sensors and the thermocouple sensors of the same sensor group simultaneously read, and the eddy current sensors and the thermocouple sensors of each sensor group read in turn in a scanning mode.

[0013] By adopting the above technical scheme, the eddy current sensors and the thermocouple sensors simultaneously read, so that the displacement and temperature data of the pin shaft can be obtained at the same time point, the data synchronization helps to more accurately analyze the working state of the pin shaft, avoids the error caused by the time difference, and since the eddy current and thermocouple data obtained at the same time are paired, data analysis and comparison can be conveniently performed, the correlation between the detection data of the eddy current sensors and the thermocouple sensors can be found, and more details and characteristics of the working state of the pin shaft can be found.

[0014] In the second aspect, the above application purpose is achieved by the following technical scheme:

[0015] A use method of a bridge suspender pin shaft sensor for health monitoring, the use method of the bridge suspender pin shaft sensor for health monitoring comprises the following steps:

[0016] acquire eddy current detection data and corresponding temperature detection data;

[0017] perform initial value processing on the eddy current detection data and the corresponding temperature detection data to obtain initial value eddy current detection data and initial value temperature detection data;

[0018] input the initial value eddy current detection data and the initial value temperature detection data into a preset neural network model, and obtain a plurality of model output values based on the neural network model;

[0019] perform calculation in combination with the plurality of model output values to obtain a sensor test result.

[0020] By adopting the above technical solution, the eddy current detection data of each eddy current sensor and the temperature detection data of the corresponding thermocouple sensor are acquired, and the eddy current detection data of each eddy current sensor and the temperature detection data of the corresponding thermocouple sensor are subjected to initial value processing. The initial value processing refers to calibration processing of the eddy current detection data and the temperature detection data. For example, the eddy current data and the temperature detection data measured when the pin shaft is in a stationary or known state and is stable without external heat source influence are subtracted from the acquired eddy current detection data and temperature detection data to perform initial value processing, thereby ensuring the accuracy of detection. The preset neural network model refers to a model for analyzing the eddy current detection data and the temperature detection data to further judge the bearing force value of the pin shaft. For example, the neural network algorithm is used to analyze the correlation between the eddy current detection data and the temperature detection data and the mechanical state of the pin shaft. In addition, since the eddy current detection data and the temperature detection data include detection data of a plurality of groups of eddy current sensors and temperature sensors in a plurality of annular grooves on the pin shaft, different positions on the pin shaft may affect each other. Therefore, the neural network model performs multiple analyses, inputs multiple results, and then performs average value calculation on a plurality of output values of the neural network model to obtain a final test result, thereby improving the accuracy of the test.

[0021] In a preferred example, the neural network model is obtained by the following manner: acquiring initial detection data of the eddy current sensor and initial detection data of the temperature sensor under no load action, and acquiring a plurality of sets of training data sets under calibration test conditions, wherein each set of the training data set includes calibration detection data of each eddy current sensor, corresponding calibration detection data of each temperature sensor, and a corresponding pin shaft bearing force value, and each set of the training data set is sorted according to a calibration test sequence of each set of the training data set, and the calibration detection data of each eddy current sensor and the corresponding temperature sensor in each set of the training data set are sorted according to a preset sensor sequence;

[0022] initializing calibration detection data of each eddy current sensor and calibration detection data of each temperature sensor in each training data set based on the initial detection data of the eddy current sensor and the initial detection data of the temperature sensor under no load;

[0023] training the neural network based on each training data set to generate a neural network model.

[0024] By adopting the above technical solution, the neural network model is the main means for analyzing the mechanical state of the pin shaft, and the prediction accuracy of the neural network model determines the accuracy of the test result. Therefore, it is necessary to improve the robustness of the neural network model. Based on this, the initial detection data of the eddy current sensor and the initial detection data of the temperature sensor under no load are obtained. The initial detection data is the recorded reading of each sensor when it is set at the factory under no load. The initial detection data is used as the value of the initialization process. Since the initial detection data is recorded at the factory under no load, it directly reflects the initial state of the sensor on the pin shaft, so that the initial detection data can more accurately represent the actual initial conditions of the sensor on the pin shaft. Compared with the commonly used detection data under standard conditions as the value of the initialization process, the error caused by the difference between the standard conditions and the actual working conditions can be avoided. In this way, the accuracy of the training sample is improved to improve the accuracy of the neural network training. In addition, each training data set is sorted according to the calibration test sequence of each training data set, and each eddy current sensor in each training data set and the corresponding temperature sensor are sorted according to the preset sensor sequence. This facilitates the search for abnormal data during neural network training.

[0025] In a preferred example, the application can be further configured as follows: the neural network is trained based on each training data set to generate a neural network model, specifically including:

[0026] Each time the neural network is trained based on each training data set, the calibration detection data of any eddy current sensor and the calibration detection data of the corresponding temperature sensor in the training data set are randomly selected;

[0027] The calibration detection data of the randomly selected eddy current sensor and the calibration detection data of the corresponding temperature sensor are excluded from the training data set in the current neural network training, and the neural network is trained based on the remaining data in the training data set to generate a neural network model.

[0028] By adopting the technical scheme, in order to improve the robustness and anti-interference ability of the neural network model, the neural network model needs to be improved, each set of training data set represents the data obtained by testing under the calibration test condition, in each neural network training based on each set of training data set, the calibration detection data of any eddy current sensor and the calibration detection data of the corresponding temperature sensor in the training data set are randomly selected, and the selected calibration detection data of the eddy current sensor and the calibration detection data of the corresponding temperature sensor are excluded in the training data set of the current neural network training, that is, by using the random truncation method, the data of a group of eddy current sensors and temperature sensors are randomly frozen in the data obtained by testing under the calibration test condition, and then training is performed, in this way, by randomly truncating each set of training data set, the robustness and anti-interference ability of the neural network model are improved.

[0029] In a preferred example, the application can be further configured to: the initial value processing of the eddy current detection data and the temperature detection data obtains the initial value eddy current detection data and the initial value temperature detection data, and specifically includes: based on the initial detection data of the eddy current sensor and the initial detection data of the temperature sensor under the no-load action, the initial value processing of the eddy current detection data and the temperature detection data obtains the initial value eddy current detection data and the initial value temperature detection data.

[0030] By adopting the technical scheme, since the training samples of the neural network model are also processed by the initial detection data of the eddy current sensor and the initial detection data of the temperature sensor under the no-load action, the initial value processing of the eddy current detection data and the temperature detection data based on the initial detection data of the eddy current sensor and the initial detection data of the temperature sensor under the no-load action enables the current actual detection data to correspond to the training data of the neural network model, avoids the model prediction result from being wrong due to the difference in data format, and guarantees the accuracy of detection.

[0031] In a preferred example, the application can be further configured to: the initial value processing of the eddy current detection data and the temperature detection data obtains the initial value eddy current detection data and the initial value temperature detection data, and specifically includes: based on the initial detection data of the eddy current sensor and the initial detection data of the temperature sensor under the no-load action, the initial value processing of the eddy current detection data and the temperature detection data obtains the initial value eddy current detection data and the initial value temperature detection data.

[0032] Based on the sensor sequence, the initial value eddy current detection data and the corresponding initial value temperature detection data are excluded in sequence, and the remaining initial value eddy current detection data and initial value temperature detection data are collected to generate a plurality of detection data groups corresponding to the sensor sequence;

[0033] The plurality of detection data groups are input into a preset neural network model, and a plurality of model output values are obtained based on the neural network model.

[0034] By adopting the technical scheme, since the training of the neural network model is performed after randomly freezing the data of a group of eddy current sensors and temperature sensors in the data obtained by testing under the calibration test condition each time, so as to improve the anti-interference ability of the neural network model, similarly, in order to reduce the interference possibly existing in the initialized eddy current detection data and the corresponding initialized temperature detection data as much as possible, one initialized eddy current detection data and the corresponding initialized temperature detection data in the actually detected data are frozen, and each initialized eddy current detection data and the corresponding initialized temperature detection data are sequentially frozen in accordance with the sensor sequence, to obtain a plurality of detection data groups with frozen partial data, the number of the detection data groups corresponds to the number of the sensor groups formed by the eddy current sensors and the temperature sensors, through the analysis of the neural network model on the plurality of detection data groups, a plurality of model output values are obtained, so as to ensure the correspondence between the detection data and the model analysis mode, thereby ensuring the accuracy of the detection.

[0035] In a preferred example, the application can be further configured to: the calculation combined with a plurality of model output values obtains a sensor test result, specifically including:

[0036] The average value calculation and the standard deviation calculation combined with a plurality of model output values obtain an average value calculation result and a standard deviation calculation result;

[0037] The sensor test result includes the average value calculation result and the standard deviation calculation result

[0038] By adopting the technical scheme, after obtaining a plurality of model output values, the average value calculation and the standard deviation calculation combined with each model output value obtain the final test result, and high-accuracy measurement of the pin shaft mechanical state is realized.

[0039] In summary, the application includes at least one of the following beneficial technical effects:

[0040] 1. A bridge suspender pin shaft sensor for health monitoring, comprising a pin shaft body and a plurality of sensors, the sensors comprising a plurality of eddy current sensors for detecting deformation displacement and a corresponding plurality of temperature sensors for detecting temperature, the sensors being mounted on the pin shaft through a plurality of annular grooves provided on the pin shaft body, so as to more accurately and directly measure the mechanical state of the pin shaft, reduce the interference of other factors on the sensors, and reduce the probability of damage or falling of the sensors due to the integration of the sensors in the annular grooves of the pin shaft, prolong the service life of the sensors, and enable the sensors to monitor the mechanical state of the bridge suspender and the pin shaft for a long time. In addition, the eddy current sensors are mainly used for non-contact measurement of the displacement of the pin shaft, and when the pin shaft vibrates or deforms during operation, the eddy current sensors can accurately capture the displacement change, which is an important manifestation of the mechanical state of the pin shaft and can reflect whether the pin shaft is subjected to excessive external force and whether there are problems such as wear or fatigue. The temperature sensor can measure the temperature of the pin shaft in real time, and the temperature change is closely related to the mechanical state of the pin shaft. For example, when the pin shaft is subjected to excessive friction or load, its temperature may rise, thereby indirectly reflecting the stress condition, friction state and potential damage risk of the pin shaft. In addition, there is a more prominent correlation between the monitoring data of the eddy current sensors and the temperature sensors. For example, when the pin shaft is subjected to excessive friction, the monitoring data of the eddy current sensors and the temperature sensors will both rise. Therefore, the use of the eddy current sensors and the temperature sensors in combination improves the clarity of the monitoring of the bridge suspender pin shaft, and comprehensive analysis of the displacement and temperature information can provide a more comprehensive understanding of the mechanical state of the pin shaft, improve the accuracy and reliability of the measurement, and enable the pin shaft to be found in time. The problems that may exist provide an important basis for preventing and solving the pin shaft failure.

[0041] 2、obtain the eddy current detection data of each eddy current sensor and the temperature detection data of the corresponding thermocouple sensor, and perform initial value processing on the eddy current detection data of each eddy current sensor and the temperature detection data of the corresponding thermocouple sensor. The initial value processing refers to the calibration processing of the eddy current detection data and the temperature detection data. For example, the initial value processing is performed by subtracting the eddy current data and the temperature detection data measured when the pin shaft is at rest or in a known state and is stable without external heat source from the obtained eddy current detection data and temperature detection data, so as to ensure the accuracy of the detection. The preset neural network model refers to a model for analyzing the eddy current detection data and the temperature detection data and then judging the bearing force value of the pin shaft. For example, the neural network algorithm is used to analyze the correlation between the eddy current detection data, the temperature detection data and the mechanical state of the pin shaft. In addition, since the eddy current detection data and the temperature detection data include the detection data of multiple groups of eddy current sensors and temperature sensors in multiple annular grooves on the pin shaft, different positions on the pin shaft may affect each other. Therefore, the neural network model performs multiple analyses, inputs multiple results, and then calculates the average value of multiple output values of the neural network model to obtain the final test result, thereby improving the accuracy of the test.

[0042] 3、The neural network model is a main means for analyzing the mechanical state of the pin shaft, and the prediction accuracy of the neural network model determines the accuracy of the test result. Therefore, it is necessary to improve the robustness of the neural network model. Based on this, the initial detection data of the eddy current sensor and the initial detection data of the temperature sensor under no load are obtained. The initial detection data is the recorded reading of each sensor when it is set at the factory under no load. The initial detection data is used as the initial value processing value. Since the initial detection data is recorded when the sensor is set at the factory under no load, it directly reflects the initial state of the sensor on the pin shaft, so that the initial detection data can more accurately represent the actual initial condition of the sensor on the pin shaft. Compared with the commonly used detection data under standard conditions as the initial value processing value, the error caused by the difference between the standard conditions and the actual working conditions can be avoided. In this way, the accuracy of the training sample is improved to improve the accuracy of the neural network training. In addition, each training data set is sorted according to the calibration test sequence of each training data set, and each eddy current sensor in each training data set and the corresponding temperature sensor are sorted according to the preset sensor sequence, so as to facilitate the search for abnormal data in the neural network training process. BRIEF DESCRIPTION OF DRAWINGS

[0043] Figure 1 is a schematic view of the annular groove of the bridge boom pin shaft sensor for health monitoring in the embodiment of the present application.

[0044] Figure 2This is a schematic diagram of the eddy current sensor and temperature sensor of the bridge hanger pin sensor used for health monitoring in the embodiments of this application.

[0045] Figure 3 This is a flowchart illustrating an implementation method of using a bridge hanger pin sensor for health monitoring in an embodiment of this application.

[0046] Figure 4 This is a flowchart illustrating the implementation of the method for obtaining the neural network model in this application embodiment.

[0047] Figure 5 This is a schematic diagram of the training method of the neural network model in the embodiments of this application.

[0048] Figure 6 This is a flowchart illustrating the implementation of step S03 of the method for using a bridge hanger pin sensor for health monitoring in an embodiment of this application.

[0049] Figure 7 This is a flowchart illustrating the implementation of step S20 of the method for using a bridge hanger pin sensor for health monitoring in an embodiment of this application.

[0050] Figure 8 This is a flowchart illustrating the implementation of step S30 of the method for using a bridge hanger pin sensor for health monitoring in an embodiment of this application.

[0051] Figure 9 This is a flowchart illustrating the implementation of step S40 of the method for using a bridge hanger pin sensor for health monitoring in an embodiment of this application.

[0052] Figure 10 This is a schematic diagram of a device for using a bridge hanger pin sensor for health monitoring, as described in this application. Detailed Implementation

[0053] The following is in conjunction with the appendix Figures 1-10 This application will be described in further detail.

[0054] In one embodiment, such as Figure 1 and Figure 2 As shown, this application discloses a bridge gantry pin sensor for health monitoring. The bridge gantry pin sensor for health monitoring includes: a pin body, several eddy current sensors for detecting deformation displacement, and several corresponding temperature sensors for detecting temperature. The pin body is provided with several annular grooves. In this embodiment, the pin body is a cylinder, and the annular grooves surround the outer surface of the pin body. The probes of the eddy current sensors and the temperature sensors are disposed within the annular grooves. Preferably, the eddy current sensors can also be used to measure parameters such as the vibration, velocity, and density of the pin. The number of annular grooves is preferably set to two.

[0055] Each eddy current sensor forms a sensor group with a corresponding temperature sensor, multiple eddy current sensors form multiple sensor groups with multiple corresponding temperature sensors, each sensor group includes one eddy current sensor and one temperature sensor, and the eddy current sensor and the temperature sensor in the same sensor group are integrally arranged, in this embodiment, the integration of the eddy current sensor and the temperature sensor means that the two sensors are combined or integrated in the same system or device to realize the functions of eddy current measurement and temperature measurement using one system or device, in this embodiment, the pin shaft body is also provided or connected with a data transmission interface for transmitting the detection data of the eddy current sensor and the temperature sensor to an external monitoring system, the measurement range, accuracy and output signal type (such as voltage, current or digital signal) of the eddy current sensor and the temperature sensor meet the predetermined standard requirements, the eddy current sensor and the temperature sensor are connected to the same external monitoring system or controller, in addition, the electromagnetic compatibility of the eddy current sensor and the temperature sensor in the same sensor group meets the predetermined standard requirements.

[0056] The detection data of the eddy current sensor and the temperature sensor can be used to infer the force value of the pin shaft, because the eddy current sensor and the temperature sensor have complementary measurement and their provided information can jointly reflect the mechanical properties of the pin shaft. Specifically, the eddy current sensor is mainly used for non-contact measurement of the displacement of the pin shaft, when the pin shaft vibrates or deforms during work, the eddy current sensor can accurately capture the displacement change, which is an important manifestation of the mechanical state of the pin shaft, and can reflect whether the pin shaft is subjected to excessive external force, whether there is wear or fatigue, etc., while the temperature sensor can measure the temperature of the pin shaft in real time, the temperature change is closely related to the mechanical state of the pin shaft, for example, when the pin shaft is subjected to excessive friction or load, its temperature may rise, and this temperature change can indirectly reflect the force condition, friction state and potential damage risk of the pin shaft;

[0057] Therefore, the influence of temperature on the displacement of the pin shaft can be analyzed by judging the correlation between the displacement change and the temperature, for example, by machine learning model analysis, or calculating the correlation coefficient or covariance between the displacement and temperature data, and based on the pre-prepared evaluation indicators and thresholds, such as the displacement range, temperature change range, maximum allowed deviation between displacement and temperature, etc., the mechanical state of the pin shaft can be detected; or the working state of the pin shaft can be judged by analyzing the change trend of the displacement and temperature data through a machine learning model, whether there is overload, wear or thermal expansion, etc.

[0058] In an embodiment, the temperature sensor is a thermocouple sensor, and each eddy current sensor is integrated with a corresponding thermocouple sensor and arranged in the annular groove. Preferably, the probe of the thermocouple sensor and the probe of the eddy current sensor can be integrated together to realize the cooperation of the two.

[0059] In an embodiment, a plurality of eddy current sensors and thermocouple sensors are arranged on both sides of the annular groove, the number of the eddy current sensors and thermocouple sensors on both sides of the annular groove is the same, the interval between the integrated eddy current sensors and thermocouple sensors on the same side of the annular groove is the same, in this embodiment, the two sides of the annular groove refer to the two faces of the annular groove that face each other in the length direction of the pin shaft body, that is, when the pin shaft body is placed vertically with the length direction of the pin shaft body, the annular groove includes two side faces and a covering face surrounding the inner core of the pin shaft body, the covering face is located between the upper and lower side faces, the eddy current sensors arranged on both sides of the same annular groove are staggered, that is, the sensor groups formed by the eddy current sensors and thermocouple sensors arranged on both sides of the same annular groove are staggered, so that the detection area of each eddy current sensor and thermocouple sensor on both sides of the same annular groove is different, realizing more accurate and comprehensive monitoring of the pin shaft with a larger area.

[0060] A metal shell is arranged in the annular groove, and the metal shell is used to cover the integrated eddy current sensors and thermocouple sensors to further reduce the interference of external environmental factors on the detection of the sensors, thereby further improving the accuracy of the overall measurement.

[0061] In an embodiment, the eddy current sensors and thermocouple sensors of the same sensor group read at the same time, and the eddy current sensors and thermocouple sensors of each sensor group read in turn in a scanning manner, that is, after the eddy current sensors and thermocouple sensors in the same sensor group complete reading, the eddy current sensors and thermocouple sensors in the next sensor group in the order read again, in this embodiment, the order of reading of the eddy current sensors and thermocouple sensors of each sensor group in a scanning manner is set in advance, for example, the reading detection order of any sensor group on one side of the annular groove can be set as first, and the reading detection order of the sensor group adjacent to the sensor group ranked first on the other side of the annular groove can be set as second, and the scanning reading order is set according to the positional relationship.

[0062] In an embodiment, as shown in Figure 3 Fig. 6, the application discloses a use method of the bridge suspender pin shaft sensor for health monitoring, and the use method of the bridge suspender pin shaft sensor for health monitoring includes:

[0063] S10: Obtain the eddy current detection data and the corresponding temperature detection data.

[0064] In the embodiment, the eddy current detection data refers to the detection data actually obtained by the eddy current sensor on the pin shaft body. The temperature detection data refers to the detection data actually obtained by the temperature sensor on the pin shaft body.

[0065] Specifically, in the use and operation process of the bridge suspender pin shaft sensor for health monitoring, when the bearing force value of the bridge suspender pin shaft needs to be detected, the detection data actually obtained by each eddy current sensor, i.e., the eddy current detection data, and the detection data actually obtained by each temperature sensor, i.e., the temperature detection data, are obtained.

[0066] S20: Perform initial value processing on the eddy current detection data and the corresponding temperature detection data to obtain initial value eddy current detection data and initial value temperature detection data.

[0067] Specifically, the initial value processing on the eddy current detection data and the corresponding temperature detection data includes subtracting a preset initial value from the eddy current detection data and the corresponding temperature detection data at the same time. The preset initial value can refer to the detection data under standard conditions, historical average or median data, or calibration data. Based on this, after the initial value processing on the eddy current detection data and the corresponding temperature detection data is completed, the initial value eddy current detection data and the initial value temperature detection data are obtained.

[0068] S30: Input the initial value eddy current detection data and the initial value temperature detection data into a preset neural network model, and obtain a plurality of model output values based on the neural network model.

[0069] Specifically, the initialized eddy current detection data and the initialized temperature detection data are input into a preset neural network model, the neural network model refers to a model for analyzing the eddy current detection data and the temperature detection data and then judging the bearing force value of the pin shaft, the training sample of the neural network model can be detection data actually obtained by the eddy current sensor and the temperature sensor on the historical pin shaft body or test data under standard test conditions, therefore, the initialized eddy current detection data and the initialized temperature detection data are analyzed multiple times by the neural network model, thereby obtaining multiple model output values, the model output values represent the bearing force value of the pin shaft. In the embodiment, the initialized eddy current detection data and the initialized temperature detection data include multiple sets of detection data of the eddy current sensor and the temperature sensor in the multiple annular grooves on the pin shaft. Due to factors such as the possibility of mutual influence of different positions on the pin shaft leading to a decrease in detection data accuracy, the aging of some sensors leading to a decrease in detection data accuracy, and insufficient robustness of the neural network model, the accuracy of the output values of the model can be reduced, therefore, multiple analyses are performed based on the neural network model to obtain multiple model output values, thereby facilitating the judgment of whether these factors exist according to the multiple model output values, and further improving the accuracy of the test results.

[0070] S40: Calculate based on the multiple model output values to obtain a sensor test result.

[0071] Specifically, the multiple model output values output by the neural network model are analyzed, for example, whether the difference between each two model output values is greater than a preset deviation threshold is calculated, if the result is yes, the larger model output value is removed, and then the average value of the remaining model output values is calculated to obtain the final sensor test result representing the bearing force value of the pin shaft; if the result is no, the average value of all model output values can be directly calculated to obtain the sensor test result.

[0072] In an embodiment, as shown in Figure 4 , the neural network model is obtained in the following manner:

[0073] S01: Obtain initial detection data of the eddy current sensor and initial detection data of the temperature sensor under no load action, and obtain multiple sets of training data sets under calibration test conditions, wherein each set of training data set includes calibration detection data of each eddy current sensor, corresponding calibration detection data of each temperature sensor, and corresponding bearing force value of the pin shaft, each set of training data set is sorted according to the calibration test sequence of each set of training data set, and the calibration detection data of each eddy current sensor and the calibration detection data of the corresponding temperature sensor in each set of training data set are sorted according to a preset sensor sequence.

[0074] Specifically, initial detection data of the eddy current sensors and initial detection data of the temperature sensors under no load are acquired, the initial detection data being recorded readings of the sensors when they are set at the factory under no load, and a plurality of sets of training data sets under calibration test conditions are acquired, i.e., a plurality of calibration tests are performed, and training data sets of each calibration test are acquired, wherein each set of training data sets includes calibration detection data of each eddy current sensor, calibration detection data of each corresponding temperature sensor, and a corresponding pin bearing force value, each set of training data sets is sorted according to a calibration test order of the set of training data sets, and calibration detection data of each eddy current sensor and calibration detection data of each corresponding temperature sensor in each set of training data sets are sorted according to a preset sensor order, i.e., the calibration detection data of any eddy current sensor and the calibration detection data of the corresponding temperature sensor in the training data set are sorted in the same order

[0075] For example, the data in each set of training data sets can be represented in the following manner:

[0076] XF j , wx ij , Tx ij ,...., i = 1, 2, 3,...., n, j = 1, 2, 3,...., m,

[0077] wherein j is the serial number of the calibration test order, XF j is the pin bearing force value in the jth test; wx ij is the reading of the ith eddy current sensor in the jth test; Tx ij is the reading of the ith temperature sensor in the jth test, and the serial number i is the preset sensor order;

[0078] In addition, the eddy current detection data actually detected by the eddy current sensors on the pin shaft body and the temperature detection data actually detected by the temperature sensors on the pin shaft body can be represented in the following manner:

[0079] w i , T i ,...., i = 1, 2, 3,...., n, wherein w i is the eddy current detection data actually detected by the ith eddy current sensor, and T i is the temperature detection data actually detected by the ith temperature sensor, and the serial number i is the preset sensor order.

[0080] S02: Based on the initial detection data of the eddy current sensors and the initial detection data of the temperature sensors under no load, the calibration detection data of each eddy current sensor and the calibration detection data of each temperature sensor in each set of training data sets are initialized.

[0081] Specifically, based on the initial detection data of the eddy current sensor and the initial detection data of the temperature sensor under no load, the calibration detection data of each eddy current sensor and the calibration detection data of each temperature sensor in each training data set are initialized. In this embodiment, the initialization method is that the calibration detection data of each eddy current sensor in each training data set is subtracted by the initial detection data of the eddy current sensor to obtain first initialization data, the calibration detection data of each temperature sensor is subtracted by the initial detection data of the temperature sensor to obtain second initialization data, and then the first initialization data is divided by the second initialization data to obtain third initialization data. In this way, the final initialization processing of each training data set includes the third initialization data and the corresponding pin bearing force value.

[0082] For example, the recorded readings of each sensor when factory-set under no load can be represented as follows: w0 i , T0 i ,..., i = 1, 2, 3,..., n,

[0083] where w0 i is the initial detection data of the eddy current sensor, T0 i is the initial detection data of the temperature sensor.

[0084] The input training data set of the neural network model can be represented as follows:

[0085] XF j , (wx ij -w0 i ) / (Tx ij -T0 i ),..., i = 1, 2, 3,..., n, j = 1, 2, 3,..., m, where (wx ij -w0 i ) is the first initialization data, (Tx ij -T0 i ) is the second initialization data, and (wx ij -w0 i ) / (Tx ij -T0 i ) is the third initialization data.

[0086] S03: Perform neural network training based on each training data set to generate a neural network model.

[0087] Specifically, the neural network is trained using each training data set, and after the training is completed, a neural network model is obtained.

[0088] In the embodiment, as shown in Figure 5 The training mode of the neural network model is performed through the training data set after the initial value processing is completed.

[0089] In an embodiment, as shown in Figure 6 In step S03, the neural network training is performed based on each set of training data set, and the neural network model is generated, specifically including:

[0090] S031: Each time the neural network training is performed based on each set of training data set, the calibration detection data of any eddy current sensor and the calibration detection data of the corresponding temperature sensor in the training data set are randomly selected.

[0091] Specifically, in order to improve the robustness and anti-interference ability of the neural network model, the neural network model needs to be improved, therefore, based on the random truncation method, each time the neural network training is performed based on each set of training data set, the calibration detection data of any eddy current sensor and the calibration detection data of the corresponding temperature sensor in the training data set are randomly selected.

[0092] For example, when the jth training data set is input, the input training data set of the neural network model includes XF j , (wx ij -w0 i ) / (Tx ij -T0 i ),..., i = 1, 2, 3,..., n, j = 1, 2, 3,..., m, and the random number randomly selected from i = 1, 2, 3,..., n is k, then the randomly selected data is (wx kj -w0 k ) / (Tx kj -T0 k ).

[0093] S032: Exclude the calibration detection data of the randomly selected eddy current sensor and the calibration detection data of the corresponding temperature sensor in the training data set of the current neural network training, and perform neural network training based on the remaining data in the training data set to generate a neural network model.

[0094] Specifically, after the random selection of data is completed, the calibration detection data of the randomly selected eddy current sensor and the calibration detection data of the corresponding temperature sensor are excluded in the training data set of the current neural network training, and then the neural network training is performed based on the remaining data in the training data set to generate a neural network model.

[0095] For example, the remaining data in the training data set includes XF j , (wx ij -w0 i) / (Tx ij -T0 i ),...., i = 1, 2, 3,...., n, j = 1, 2, 3,...., m, i≠k.

[0096] In an embodiment, as shown in FIG. 2, the initial value processing of the eddy current detection data and the temperature detection data is performed in step S20 to obtain the initial value eddy current detection data and the initial value temperature detection data, which specifically includes: Figure 7

[0097] S21: Based on the initial detection data of the eddy current sensor and the initial detection data of the temperature sensor under no load, the initial value processing of the eddy current detection data and the temperature detection data is performed to obtain the initial value eddy current detection data and the initial value temperature detection data.

[0098] Specifically, since the training samples of the neural network model are also processed by the initial detection data of the eddy current sensor and the initial detection data of the temperature sensor under no load, based on the initial detection data of the eddy current sensor and the initial detection data of the temperature sensor under no load, the initial value processing of the eddy current detection data and the temperature detection data is performed, so that the current actual detection data can correspond to the training data of the neural network model, thereby obtaining the initial value eddy current detection data and the initial value temperature detection data.

[0099] For example, the recorded readings of each sensor when factory-set under no load can be represented in the following manner: w0 i , T0 i ,...., i = 1, 2, 3,...., n,

[0100] wherein w0 i is the initial detection data of the eddy current sensor, T0 i is the initial detection data of the temperature sensor;

[0101] The eddy current detection data and the temperature detection data can be represented in the following manner:

[0102] cx i , cT i ,...., i = 1, 2, 3,...., n,

[0103] wherein cx i is the eddy current detection data, cT i is the temperature detection data;

[0104] The initial value eddy current detection data and the initial value temperature detection data can be represented in the following manner:

[0105] cx i ​-w0 i ,cT i -w0 i , ..., i = 1, 2, 3, ..., n, where cx i -w0 i To initialize eddy current detection data, cT i -w0 i This is the initial value of the temperature detection data.

[0106] Furthermore, since it is necessary to ensure that the actual detection data corresponds to the training data of the neural network model, the initialized eddy current detection data and the initialized temperature detection data are further processed. That is, the initialized eddy current detection data is divided by the initialized temperature detection data. The data input into the neural network model is the data after the initialized eddy current detection data is divided by the initialized temperature detection data.

[0107] For example, the data obtained by dividing the initial eddy current detection data by the initial temperature detection data can be represented as follows:

[0108] (cx i -w0 i ) / (cT i -w0 i ), ...., i=1, 2, 3, ...., n.

[0109] In one embodiment, such as Figure 8 As shown, in step S30, the initialized eddy current detection data and the initialized temperature detection data are input into a preset neural network model. Based on the neural network model, several model output values ​​are obtained. Specifically, this includes: S31: Based on the sensor order, one initialized eddy current detection data and the corresponding initialized temperature detection data are excluded in sequence, and the remaining initialized eddy current detection data and initialized temperature detection data are combined to generate several detection data groups corresponding to the sensor order.

[0110] Specifically, since the training of the neural network model is performed by randomly freezing the data of a group of eddy current sensors and temperature sensors in the data obtained by testing under the calibration test condition each time, so as to improve the anti-interference ability of the neural network model, and similarly, in order to reduce the interference that may exist in the initialized eddy current detection data and the corresponding initialized temperature detection data as much as possible, based on the sensor sequence, the initialized eddy current detection data and the corresponding initialized temperature detection data with the first serial number are excluded, the remaining initialized eddy current detection data and the initialized temperature detection data are taken as the first detection data group, the initialized eddy current detection data and the corresponding initialized temperature detection data with the second serial number are excluded, and the remaining initialized eddy current detection data and the initialized temperature detection data are taken as the second detection data group, and the exclusion is performed based on the sensor sequence to obtain a plurality of detection data groups.

[0111] For example, the data in the detection data group can be represented in the following manner:

[0112] The first detection data group: (cxi-w0) / (cTi-w0), i=1, 2, 3,..., n. i -w0 i ) / (cTi-w0), i=1, 2, 3,..., n. i -w0 i ) / (cTi-w0), i=1, 2, 3,..., n.

[0113] The second detection data group: (cxi-w0) / (cTi-w0), i=1, 3, 4,..., n. i -w0 i ) / (cTi-w0), i=1, 3, 4,..., n. i -w0 i ) / (cTi-w0), i=1, 3, 4,..., n.

[0114] The n-th detection data group: (cxi-w0) / (cTi-w0), i=1, 2, 3,..., n-1. i -w0 i ) / (cTi-w0), i=1, 2, 3,..., n-1. i -w0 i ) / (cTi-w0), i=1, 2, 3,..., n-1.

[0115] S32: inputting a plurality of detection data groups into a preset neural network model, and obtaining a plurality of model output values based on the neural network model.

[0116] Specifically, each detection data group is inputted into a preset neural network model, and a plurality of model output values corresponding to each detection data group are obtained based on the analysis of the neural network model.

[0117] For example, the model output value can be represented in the following manner:

[0118] cxi, i=1, 2, 3,..., n. i

[0119] ​In one embodiment, such as Figure 9 As shown, in step S40, the sensor test results include the average value calculation result and the standard deviation calculation result. These are combined with several model output values ​​to calculate the sensor test results, specifically including:

[0120] S41: Combine the output values ​​of several models to calculate the mean and standard deviation, and obtain the result of the mean calculation and the result of the standard deviation calculation.

[0121] Specifically, the average value and standard deviation are calculated by combining the output values ​​of several models to obtain the average value and standard deviation results. Both the average value and standard deviation results are sensor test results.

[0122] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0123] In one embodiment, a device for using a bridge suspender pin sensor for health monitoring is provided, and this device corresponds one-to-one with the method of using the bridge suspender pin sensor for health monitoring in the above embodiments. For example... Figure 10 As shown, the device for using the bridge hanger pin sensor for health monitoring includes a data acquisition module, an initial value processing module, a model output module, and a statistical analysis module. Detailed descriptions of each functional module are as follows:

[0124] The data acquisition module is used to acquire eddy current detection data and corresponding temperature detection data;

[0125] The initialization processing module is used to perform initialization processing on the eddy current detection data and the corresponding temperature detection data to obtain initialized eddy current detection data and initialized temperature detection data.

[0126] The model output module is used to input the initialized eddy current detection data and the initialized temperature detection data into a preset neural network model, and obtain several model output values ​​based on the neural network model.

[0127] The statistical analysis module is used to combine the output values ​​of several models to perform calculations and obtain sensor test results.

[0128] Optionally, the device for using bridge hanger pin sensors for health monitoring also includes:

[0129] The data collection module is configured to acquire initial detection data of the eddy current sensors and initial detection data of the temperature sensors under no load, and acquire a plurality of sets of training data under calibration test conditions, wherein each set of training data includes calibration detection data of each eddy current sensor, calibration detection data of each corresponding temperature sensor, and a corresponding pin bearing force value, each set of training data is sorted according to a calibration test sequence of each set of training data, and the calibration detection data of each eddy current sensor and the calibration detection data of each corresponding temperature sensor in each set of training data are sorted according to a preset sensor sequence.

[0130] The initial initialization module is configured to initialize the calibration detection data of each eddy current sensor and the calibration detection data of each temperature sensor in each set of training data based on the initial detection data of the eddy current sensors and the initial detection data of the temperature sensors under no load.

[0131] The model generation module is configured to generate a neural network model based on each set of training data.

[0132] Optionally, the model generation module includes:

[0133] The random selection sub-module is configured to randomly select calibration detection data of any eddy current sensor and calibration detection data of a corresponding temperature sensor in each set of training data each time the neural network is trained based on each set of training data.

[0134] The training sub-module is configured to exclude the calibration detection data of the randomly selected eddy current sensor and the calibration detection data of the corresponding temperature sensor in the training data of the current time neural network training, and generate a neural network model based on the remaining data in the training data.

[0135] Optionally, the initialization processing module includes:

[0136] The initialization processing sub-module is configured to initialize the eddy current detection data and the temperature detection data based on the initial detection data of the eddy current sensors and the initial detection data of the temperature sensors under no load, to obtain initialized eddy current detection data and initialized temperature detection data.

[0137] Optionally, the model output module includes:

[0138] The exclusion sub-module is configured to exclude the initialized eddy current detection data and the corresponding initialized temperature detection data in sequence based on the sensor sequence, and generate a plurality of detection data groups in the corresponding sensor sequence by collecting the remaining initialized eddy current detection data and the initialized temperature detection data.

[0139] The model analysis submodule is configured to input the plurality of detection data sets into a preset neural network model, and obtain a plurality of model output values based on the neural network model.

[0140] Optionally, the sensor test result includes an average value calculation result and a standard deviation calculation result, and the statistical analysis module includes:

[0141] The statistical analysis submodule is configured to perform average value calculation and standard deviation calculation on the plurality of model output values, and obtain the average value calculation result and the standard deviation calculation result.

[0142] For specific limitations of the device for using the bridge suspender pin shaft sensor for health monitoring, refer to the limitations of the method for using the bridge suspender pin shaft sensor for health monitoring described above, which will not be repeated here. Each module in the device for using the bridge suspender pin shaft sensor for health monitoring described above can be realized by software, hardware, or a combination thereof, in whole or in part. The above-mentioned modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to each module.

[0143] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units or modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above.

[0144] The above-described embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A bridge boom pin sensor for health monitoring, characterized by, The sensor comprises a pin shaft body, a plurality of eddy current sensors for detecting deformation displacement, and a corresponding plurality of temperature sensors for detecting temperature, the pin shaft body is provided with a plurality of annular grooves, the eddy current sensors and the temperature sensors are integrally arranged in the annular grooves, each of the eddy current sensors and the corresponding temperature sensor forms a sensor group, and the detection data of the eddy current sensor and the temperature sensor are combined to infer the stress value of the pin shaft; The use method of the sensor is as follows: Obtain eddy current detection data and corresponding temperature detection data; Perform initial value processing on the eddy current detection data and the corresponding temperature detection data to obtain initial value eddy current detection data and initial value temperature detection data; Input the initial value eddy current detection data and the initial value temperature detection data into a preset neural network model, obtain a plurality of model output values based on the neural network model, and the neural network model is obtained by the following method: Obtain initial detection data of the eddy current sensor and initial detection data of the temperature sensor under no load action, obtain a plurality of sets of training data sets under calibration test conditions, sort each set of training data set according to the calibration test sequence of each set of training data set, and sort the calibration detection data of each eddy current sensor and the calibration detection data of the corresponding temperature sensor in each set of training data set according to the preset sensor sequence; Perform initial value processing on the calibration detection data of each eddy current sensor and the calibration detection data of each temperature sensor in each set of training data set based on the initial detection data of the eddy current sensor and the initial detection data of the temperature sensor under no load action; Perform neural network training based on each set of training data set to generate a neural network model, specifically including: Randomly select calibration detection data of any eddy current sensor and calibration detection data of the corresponding temperature sensor in the training data set each time the neural network training is performed based on each set of training data set; Freeze the randomly selected calibration detection data of the eddy current sensor and the calibration detection data of the corresponding temperature sensor in the training data set of the current neural network training, freeze a group of data of the eddy current sensor and the temperature sensor in the data obtained by testing under the calibration test condition each time by the random truncation method, and then perform neural network training based on the remaining data in the training data set to generate a neural network model; Combine a plurality of model output values to obtain a sensor test result, specifically including: Combine a plurality of model output values to obtain average value calculation results and standard deviation calculation results; The sensor test result includes the average value calculation result and the standard deviation calculation result.

2. The bridge boom pin sensor for health monitoring of claim 1, wherein, The temperature sensor is a thermocouple sensor, and each eddy current sensor and the corresponding thermocouple sensor are integrally arranged in the annular groove.

3. The bridge boom pin sensor for health monitoring of claim 2, wherein, The electric eddy current sensors and the thermocouple sensors arranged on both sides of the annular groove are staggered with each other, and a metal shell is arranged in the annular groove, which is used for covering the electric eddy current sensors and the thermocouple sensors.

4. The bridge boom pin sensor for health monitoring of claim 2, wherein, The electric eddy current sensors and the thermocouple sensors of the same sensor group simultaneously read, and the electric eddy current sensors and the thermocouple sensors of each sensor group read in turn in a scanning mode.

5. The method of using a bridge boom pin sensor for health monitoring of claim 1, wherein, The initial value processing of the electric eddy current detection data and the temperature detection data to obtain initial value electric eddy current detection data and initial value temperature detection data specifically includes: Based on the initial detection data of the electric eddy current sensor and the initial detection data of the temperature sensor under the action of no load, the initial value processing of the electric eddy current detection data and the temperature detection data to obtain initial value electric eddy current detection data and initial value temperature detection data.

6. The method of using a bridge boom pin sensor for health monitoring of claim 1, wherein, The initial value electric eddy current detection data and the initial value temperature detection data are input into a preset neural network model, and based on the neural network model, a plurality of model output values are obtained, specifically including: Based on the sensor sequence, a initial value electric eddy current detection data and a corresponding initial value temperature detection data are sequentially excluded, and a plurality of detection data groups corresponding to the sensor sequence are generated by collecting the remaining initial value electric eddy current detection data and initial value temperature detection data. A plurality of detection data groups are input into a preset neural network model, and based on the neural network model, a plurality of model output values are obtained.

Images