Intelligent self-adaptive calibration method and calibration system of sensor

Abstract

The invention relates to the technical field of sensor calibration, and discloses an intelligent self-adaptive calibration method and calibration system of a sensor. The self-adaptive calibration method is applied to a sensor monitoring unit and specifically comprises the following steps that S101, a calibration request of a sensor is received, and the calibration request comprises a time sequence of the sensor in stage time, a sensor frequency spectrum and a sensor wavelet transformation state; according to the method, the time sequence, the frequency spectrum and the wavelet transformation state data of the sensor are collected, transformation is realized based on a data correction method, then a preset mathematical model is utilized to predict the matching option of the sensor, and whether the specified matching option has a matching request corresponding to an actual output value is detected; and the actual output value of the sensor in the matching request is determined to be compared with the output value of the predicted sensor, so that accurate duplicate checking calibration is realized, the precision of the calibration value is improved, and the precision of subsequent acquisition data of the sensor is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of sensor calibration. Specifically, it relates to an intelligent adaptive calibration method and a calibration system for sensors. Background Art

[0002] In the fields of industrial automation technology, detection technology, information processing, etc., sensors have been widely used. Sensors can be directly used to measure current, magnetic induction intensity, magnetic field direction (angle), etc.

[0003] However, due to the hardware errors existing in the sensors themselves and the hardware errors also existing in other hardware systems used in conjunction with them, parameter calibration is generally required in actual applications to ensure the detection accuracy. Traditional calibration methods have disadvantages such as expensive calibration tooling, risk of matching errors, long time required for overall parameter calibration, many manual links, and low overall efficiency. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent adaptive calibration method and a calibration system for sensors, which determine the comparison between the actual output value of the sensor in the matching request and the output value of the predicted sensor, so as to achieve accurate duplicate checking and calibration, improve the accuracy of the calibration value, and aim to solve the problems in the prior art.

[0005] The present invention is implemented as follows. The intelligent adaptive calibration method for sensors is applied to a sensor monitoring unit and specifically includes the following steps: S101: Receive a calibration request for the sensor, where the calibration request includes the time series, sensor spectrum, and sensor wavelet transform state of the sensor within a stage time; S102: Obtain the spectrum state and wavelet transform state data of the sensor in the time series, input the spectrum state and wavelet transform state data of the sensor in the time series into a preset data classification model, and obtain a classification result output based on the spectrum state and wavelet transform state data of the sensor in the time series; S103: Obtain the classification result output from the spectrum state and wavelet transform state data of the sensor in the time series, place the classification result in an adjustment unit to complete data comparison, and obtain the deviation error of the reference feature data; S104: Place the deviation error of the reference feature data in the adjustment unit to perform sensor deviation adjustment, and obtain a deviation identifier. After the sensor deviation adjustment, obtain the spectrum state and wavelet transform state data of the adjusted sensor in the time series again; S105: Identify the spectral state and wavelet transform state data of the adjusted sensor in the time series, place them in a preset mathematical model, use the preset mathematical model to predict the matching options of the sensor, and detect whether there is a matching request corresponding to the actual output value for the specified matching option; S106: If there is a corresponding matching request for the specified matching option, determine the comparison between the actual output value of the sensor in the matching request and the output value of the predicted sensor. If the calibration condition is met, compensate and correct the sensor data again according to the current actual output value.

[0006] Further, in S101, receiving the calibration request of the sensor includes: Receiving the connection request sent by the sensor through a preset network, where the connection request is used to request to establish a connection with the sensor monitoring unit; Detect the sending path of the connection request to determine the characteristic parameters of the sensor to be calibrated; After obtaining the sending path of the sensor, connect to the sensor according to the connection request. After the connection is completed, receive the calibration request of the sensor.

[0007] Further, the calibration request includes the time series, sensor spectrum, and sensor wavelet transform state of the sensor within a stage time. The stage time includes: At least two cycle segments are retained for the time series data sampling of the sensor; The sensor spectrum is at least intercepted with multiple frequency bands, and the multiple frequency bands are a set of point differences recorded by the time series data of the sensor on the spectrum; The sensor wavelet transform state is at least intercepted to gradually perform multi-scale refinement on the signal to meet the requirements of time subdivision at high frequencies, frequency subdivision at low frequencies, and automatic adaptation to time-frequency signal analysis, and can focus on any details of the signal.

[0008] Further, the preset network includes one or a combination of 3G network, 4G network, 5G network, and WIFI network.

[0009] Further, in S102, obtaining the spectral state and wavelet transform state data of the sensor in the time series and inputting the spectral state and wavelet transform state data of the sensor in the time series into a preset data classification model includes: Obtain multiple data classification models and sort the types of the multiple data classification models in sequence; Obtain the content text of the spectral state and wavelet transform state data of the sensor in the time series, and input the spectral state and wavelet transform state data of the sensor in the time series into the data classification model ranked first.

[0010] Further, in S104, place the offset error of the reference feature data in the adjustment unit for sensor offset adjustment, and obtain an offset identifier, including: The adjustment unit obtains the offset error of the reference feature data based on the classification result of the data output, and then identifies the feature data parameters of the current sensor; Superimpose the offset error of the reference feature data on the identified feature data parameters. The offset error of the reference feature data is provided with a phase feature. The adjustment unit first identifies the phase feature, and then determines the numerical adjustment phase of the feature data parameters.

[0011] Further, in S105, use a preset mathematical model to predict the matching options of the sensor, and detect whether there is a matching request corresponding to the actual output value for the specified matching option, including: Establish a mathematical model to describe the error characteristics of the sensor, and then use the mathematical model to predict the parameter output value of the sensor; Obtain the parameter output value predicted by the mathematical model for the sensor, and arrange the parameter output values according to the preset parameter arrangement method to form matching options; Detect the actual output numerical path and data integrity of the spectral state and wavelet transform state data of the adjusted sensor in the time series; If it is checked that the actual output numerical path and data of the spectral state and wavelet transform state data of the sensor in the time series are complete, then establish a corresponding matching request for the specified matching option.

[0012] Further, in S106, if there is no corresponding matching request for the specified matching option, output a feedback signal to the adjustment unit to determine whether the actual output numerical path and data of the spectral state and wavelet transform state data of the adjusted sensor are incomplete; If the actual output numerical path and data of the spectral state and wavelet transform state data of the adjusted sensor are incomplete, continue to request to establish a corresponding matching request within the cycle time until the matching request corresponding to the specified matching option is established.

[0013] Compared with the prior art, the intelligent adaptive calibration method and calibration system for the sensor provided by the present invention have the following beneficial effects: 1. By collecting the time series, spectrum, and wavelet transform state data of the sensor, first perform a transformation based on the data correction method. Place the offset error of the reference feature data in the adjustment unit for sensor offset adjustment, obtain the offset identifier, record the content of the adjustment data, and then generate a preset mathematical model through the preset functional parameters. Use the preset mathematical model to predict the matching options of the sensor, and detect whether there is a matching request corresponding to the actual output value for the specified matching option. Compare the actual output value of the sensor in the matching request with the output value of the predicted sensor, thereby achieving accurate duplicate checking and calibration, improving the accuracy of the calibration value, and ensuring the accuracy of the data collected by the sensor subsequently; 2. At least two cycle segments should be retained for the time series data sampling of the sensor; the sensor spectrum should be intercepted with at least multiple frequency bands, and the multiple frequency bands are the set of point differences recorded by the time series data of the sensor in the spectrum; the sensor wavelet transform state should be intercepted with at least the requirement of gradually performing multi-scale refinement on the signal to achieve time subdivision at high frequencies, frequency subdivision at low frequencies, and automatic adaptation to time-frequency signal analysis, and can focus on any detail of the signal. Thus, when performing this data comparison, the data acquisition deviation can be repeated multiple times to facilitate maximizing the acquisition of the offset error of the reference feature data, and then place the offset error of the reference feature data in the adjustment unit for sensor offset adjustment, which is conducive to obtaining the best data offset error and improving the sensor monitoring accuracy rate.

[0014] The intelligent adaptive calibration system of the sensor is applied to the above intelligent adaptive calibration method. The system includes: The receiving and recognition module is used to receive the calibration request of the sensor and input the data into the preset data classification model to obtain the classification result output based on the spectrum state and wavelet transform state data of the sensor in the time series; The data analysis module is used to place the classification result of the spectrum state and wavelet transform state data of the sensor in the time series in the adjustment unit to complete data comparison and obtain the offset error of the reference feature data; The calibration and acquisition module is used to place the offset error of the reference feature data in the adjustment unit for sensor offset adjustment and obtain the offset identifier; The model matching module is used to identify the spectrum state and wavelet transform state data of the adjusted sensor in the time series and place them in the preset mathematical model, and use the preset mathematical model to predict the matching options of the sensor; The prediction and comparison module is used to determine whether there is a corresponding matching request for the matching option. If it exists, compare the actual output value of the sensor in the matching request with the output value of the predicted sensor; The compensation module is used to compensate and correct the sensor data again according to the current actual output value.

[0015] Specifically, the model matching module includes: A model generation unit, configured to obtain function parameters preset by the system, and generate a preset mathematical model through the preset function parameters; An output matching unit, configured to predict matching options of the sensor by using the preset mathematical model, and detect whether there is a matching request corresponding to the actual output value of the specified matching option; A request obtaining unit, configured to determine that when there is a corresponding matching request for the specified matching option, compare the actual output value of the sensor in the matching request with the output value of the predicted sensor. Description of the Drawings

[0016] Figure 1 It is a schematic flowchart of the intelligent adaptive calibration method for the sensor proposed by the present invention; Figure 2 It is a schematic flowchart of receiving a calibration request for the sensor in the intelligent adaptive calibration method for the sensor proposed by the present invention; Figure 3 It is a schematic structural diagram of the intelligent adaptive calibration system for the sensor proposed by the present invention; Figure 4 It is a schematic structural diagram of the model matching module in the intelligent adaptive calibration system for the sensor proposed by the present invention. Detailed Embodiment

[0017] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention.

[0018] The implementation of the present invention will be described in detail below with reference to specific embodiments.

[0019] In the drawings of this embodiment, the same or similar reference numerals correspond to the same or similar components; in the description of the present invention, it should be understood that if there are terms such as "upper", "lower", "left", "right", etc. indicating the orientation or positional relationship, they are based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, the terms describing the positional relationship in the drawings are only used for exemplary illustration and cannot be understood as limiting the present invention. For those of ordinary skill in the art, the specific meanings of the above terms can be understood according to specific circumstances.

[0020] Referring to Figure 1-2 As shown, the intelligent adaptive calibration method for the sensor is applied to the sensor monitoring unit, and specifically includes the following steps: S101: Receive the calibration request of the sensor. The calibration request includes the time series, sensor spectrum, and sensor wavelet transform state of the sensor within a stage time; Among them, receiving the calibration request of the sensor includes: Receive the connection request sent by the sensor through a preset network. The connection request is used to request to establish a connection with the sensor monitoring unit; Detect the sending path of the connection request and determine the characteristic parameters of the sensor to be calibrated; After obtaining the sending path of the sensor, connect to the sensor according to the connection request. After the connection is completed, receive the calibration request of the sensor; S102: Obtain the spectrum state and wavelet transform state data of the sensor in the time series, input the spectrum state and wavelet transform state data of the sensor in the time series into a preset data classification model, and obtain the classification result output based on the spectrum state and wavelet transform state data of the sensor in the time series; Among them, obtaining the spectrum state and wavelet transform state data of the sensor in the time series and inputting the spectrum state and wavelet transform state data of the sensor in the time series into a preset data classification model includes: Obtain multiple data classification models and sort the types of the multiple data classification models in sequence; Obtain the content text of the spectrum state and wavelet transform state data of the sensor in the time series, and input the spectrum state and wavelet transform state data of the sensor in the time series into the data classification model ranked first; S103: Obtain the classification result output from the spectrum state and wavelet transform state data of the sensor in the time series, place the classification result in the adjustment unit to complete data comparison, and obtain the deviation error of the reference feature data; S104: Place the deviation error of the reference feature data in the adjustment unit to perform sensor deviation adjustment, and obtain a deviation identifier. After the sensor deviation adjustment, obtain the spectrum state and wavelet transform state data of the adjusted sensor in the time series again; Among them, placing the deviation error of the reference feature data in the adjustment unit to perform sensor deviation adjustment and obtaining a deviation identifier includes: The adjustment unit obtains the deviation error of the reference feature data based on the classification result output from the data, and then identifies the characteristic data parameters of the current sensor; Superimpose the deviation error of the reference feature data on the identified characteristic data parameters. The deviation error of the reference feature data is provided with a direction feature. The adjustment unit first identifies the direction feature and then determines the numerical adjustment direction of the characteristic data parameters; S105: Identify the spectral state and wavelet transform state data of the adjusted sensor in the time series, place them in a preset mathematical model, use the preset mathematical model to predict the matching options of the sensor, and detect whether there is a matching request corresponding to the actual output value for the specified matching option; Among them, using the preset mathematical model to predict the matching options of the sensor and detecting whether there is a matching request corresponding to the actual output value for the specified matching option includes: Establish a mathematical model to describe the error characteristics of the sensor, and then use the mathematical model to predict the parameter output value of the sensor; Obtain the parameter output value predicted by the mathematical model for the sensor, and arrange the parameter output values according to the preset parameter arrangement method to form matching options; Detect the actual output numerical path and data integrity of the spectral state and wavelet transform state data of the adjusted sensor in the time series; If it is checked that the actual output numerical path and data integrity of the spectral state and wavelet transform state data of the sensor in the time series are complete, then a corresponding matching request is established for the specified matching option; S106: If there is a corresponding matching request for the specified matching option, determine the comparison between the actual output value of the sensor in the matching request and the output value of the predicted sensor. If the calibration condition is met, compensate and correct the sensor data again according to the current actual output value. By collecting the time series of the sensor, the sensor spectrum, and the sensor wavelet transform state data, first attempt to implement the transformation based on the data correction method, place the reference feature data offset error in the adjustment unit for sensor offset adjustment, and obtain the offset identifier, record the content of the adjustment data. Then, through the system preset function parameters, generate a preset mathematical model through the preset function parameters, use the preset mathematical model to predict the matching options of the sensor, and detect whether there is a matching request corresponding to the actual output value for the specified matching option, determine the comparison between the actual output value of the sensor in the matching request and the output value of the predicted sensor, so as to achieve accurate duplicate checking and calibration, improve the accuracy of the calibration value, and ensure the accuracy of the subsequent collected data of the sensor.

[0021] Specifically, the model-based automatic calibration method of the sensor automatically calibrates the sensor through the model. The core of this method is to compare with the actual output value, so as to adjust the model parameters to achieve automatic calibration. Commonly used models include linear models, non-linear models, and neural network models.

[0022] In this embodiment, the calibration request includes the time series of the sensor, the sensor spectrum, and the sensor wavelet transform state within the stage time. The stage time includes: At least two cycle segments are retained for the time series data sampling of the sensor; The sensor spectrum is at least intercepted with multiple frequency bands. The multiple frequency bands are a set of point differences recorded by the time series data of the sensor in the spectrum, so that when comparing the data, the data acquisition deviation can be repeated multiple times, which is convenient for maximizing the acquisition of the offset error of the reference feature data. Then, the offset error of the reference feature data is placed in the adjustment unit for sensor offset adjustment, so as to obtain the best data offset error and improve the monitoring accuracy of the sensor; The wavelet transform state of the sensor is at least intercepted to gradually perform multi-scale refinement on the signal to meet the requirements of time subdivision at high frequencies, frequency subdivision at low frequencies, and automatic adaptation to time-frequency signal analysis, and can focus on any details of the signal.

[0023] In this embodiment, the preset network includes one or a combination of 3G network, 4G network, 5G network, and WIFI network.

[0024] In S106 of this embodiment, if there is no corresponding matching request for the specified matching option, a feedback signal is output to the adjustment unit to determine whether the actual output value path of the spectrum state and wavelet transform state data of the adjusted sensor in the time series is incomplete with the data; If the actual output value path of the spectrum state and wavelet transform state data of the adjusted sensor in the time series is incomplete with the data, continue to request to establish a corresponding matching request within the cycle time until the matching request corresponding to the specified matching option is established.

[0025] Refer to Figure 3-4 As shown, the intelligent adaptive calibration system of the sensor is applied to the above intelligent adaptive calibration method. The system includes: a receiving and identifying module, which is used to receive the calibration request of the sensor and input the data into a preset data classification model to obtain a classification result based on the spectrum state and wavelet transform state data output of the sensor in the time series; a data analysis module, which is used to analyze the classification result of the spectrum state and wavelet transform state data output of the sensor in the time series, place the classification result in the adjustment unit to complete data comparison, and obtain the offset error of the reference feature data; a calibration and acquisition module, which is used to place the offset error of the reference feature data in the adjustment unit for sensor offset adjustment and obtain an offset identifier; a model matching module, which is used to identify the spectrum state and wavelet transform state data of the adjusted sensor in the time series and place them in a preset mathematical model, and use the preset mathematical model to predict the matching option of the sensor; a prediction and comparison module, which is used to determine whether there is a corresponding matching request for the matching option. If so, it determines the comparison between the actual output value of the sensor in the matching request and the output value of the predicted sensor; a compensation module, which is used to compensate and correct the sensor data again according to the current actual output value; Specifically, at least two cycle segments are retained in the time series data sampling of the sensor; the sensor spectrum is at least intercepted with multiple frequency bands, and the multiple frequency bands are a set of point differences recorded by the time series data of the sensor in the spectrum; the sensor wavelet transform state is at least intercepted to meet the requirements of gradually performing multi-scale refinement on the signal to achieve time subdivision at high frequencies, frequency subdivision at low frequencies, and automatic adaptation to time-frequency signal analysis, and can focus on any details of the signal. Thus, when comparing this data, the data acquisition deviation can be repeated multiple times to facilitate maximizing the acquisition of the deviation error of the reference feature data. Then, the deviation error of the reference feature data is placed in the adjustment unit for sensor deviation adjustment, which is convenient for obtaining the best data deviation error and improving the monitoring accuracy of the sensor.

[0026] In this embodiment, the model matching module includes: a model generation unit for obtaining the function parameters preset by the system and generating a preset mathematical model through the preset function parameters; an output matching unit for predicting the matching options of the sensor using the preset mathematical model and detecting whether there is a matching request corresponding to the actual output value for the specified matching option; a request acquisition unit for determining that there is a corresponding matching request for the specified matching option, then comparing the actual output value of the sensor in the matching request with the output value of the predicted sensor. By collecting the time series, spectrum, and wavelet transform state data of the sensor, first, based on the data correction method, an attempt is made to achieve the transformation. The deviation error of the reference feature data is placed in the adjustment unit for sensor deviation adjustment, and a deviation identifier is obtained, recording the content of the adjusted data. Then, through the function parameters preset by the system, a preset mathematical model is generated through the preset function parameters, the matching options of the sensor are predicted using the preset mathematical model, and it is detected whether there is a matching request corresponding to the actual output value for the specified matching option. The actual output value of the sensor in the matching request is compared with the output value of the predicted sensor, thereby achieving precise duplicate checking and calibration, improving the accuracy of the calibration value, and ensuring the accuracy of the subsequent data collected by the sensor.

[0027] For the sensor wavelet transform state, it corresponds to a signal with finite energy, and its amplitude is an oscillating form with positive and negative phases. Wavelet transform is a local analysis of time and frequency. It gradually performs multi-scale refinement on the signal through stretching and translation operations, and finally achieves time subdivision at high frequencies and frequency subdivision at low frequencies, and can automatically adapt to the requirements of time-frequency signal analysis, so that it can focus on any details of the signal; The process of wavelet transform: ① Select a wavelet basis function and initialize the scale factor and translation factor; ② Multiply the signal by the wavelet and integrate to obtain the wavelet coefficients at the corresponding moments; ③ Move the translation factor until the end of the signal; ④ Change the scale factor and repeat steps 2 and 3 to complete the wavelet transform.

[0028] In this embodiment, the entire operation process can be controlled by a computer, and in each operation link, sensors can be set to perform signal feedback to achieve sequential execution of steps. These are all common knowledge of current automatic control and will not be elaborated one by one in this embodiment.

[0029] The above are only the preferred embodiments of the present invention, and are not intended to limit the present invention. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. An intelligent adaptive calibration method for a sensor, characterized in that Applied to the sensor monitoring unit, specifically including the following steps: S101: Receive the calibration request of the sensor, where the calibration request includes the time series, sensor spectrum, and sensor wavelet transform state of the sensor within a stage time; S102: Obtain the spectrum state and wavelet transform state data of the sensor in the time series, input the spectrum state and wavelet transform state data of the sensor in the time series into a preset data classification model, and obtain the classification result output based on the spectrum state and wavelet transform state data of the sensor in the time series; S103: Obtain the classification result output from the spectrum state and wavelet transform state data of the sensor in the time series, place the classification result in the adjustment unit to complete data comparison, and obtain the offset error of the reference feature data; S104: Place the offset error of the reference feature data in the adjustment unit to perform sensor offset adjustment, and obtain an offset identifier. After the sensor offset adjustment, obtain the spectrum state and wavelet transform state data of the adjusted sensor in the time series again; S105: Identify the spectrum state and wavelet transform state data of the adjusted sensor in the time series, place it in a preset mathematical model, use the preset mathematical model to predict the matching options of the sensor, and detect whether there is a matching request corresponding to the actual output value of the specified matching option; S106: If there is a corresponding matching request for the specified matching option, determine the comparison between the actual output value of the sensor in the matching request and the output value of the predicted sensor. If the calibration condition is met, compensate and correct the sensor data again according to the current actual output value.

2. The intelligent adaptive calibration method of the sensor according to claim 1, characterized in that, In S101, receiving the calibration request of the sensor includes: Receive the connection request sent by the sensor through a preset network, where the connection request is used to request to establish a connection with the sensor monitoring unit; Detect the sending path of the connection request and determine the characteristic parameters of the sensor to be calibrated; After obtaining the sending path of the sensor, connect to the sensor according to the connection request. After the connection is completed, receive the calibration request of the sensor.

3. The intelligent adaptive calibration method of the sensor according to claim 2, wherein, Among the time series, sensor spectrum, and sensor wavelet transform state of the sensor in the calibration request, the stage time includes: At least two cycle segments are retained in the time series data sampling of the sensor; The sensor spectrum is at least intercepted with multiple frequency bands, and the multiple frequency bands are a set of point differences recorded on the spectrum of the time series data of the sensor; The sensor wavelet transform state is at least intercepted to gradually perform multi-scale refinement on the signal to meet the requirements of time subdivision at high frequencies, frequency subdivision at low frequencies, and automatic adaptation to time-frequency signal analysis, and can focus on any detail of the signal.

4. The intelligent adaptive calibration method of the sensor according to claim 3, characterized in that, The preset network includes one or a combination of 3G network, 4G network, 5G network, and WIFI network.

5. The intelligent adaptive calibration method of the sensor according to claim 4, characterized in that, In S102, obtaining the spectrum state and wavelet transform state data of the sensor in the time series and inputting the spectrum state and wavelet transform state data of the sensor in the time series into a preset data classification model includes: Obtain multiple data classification models, and sort the types of the multiple data classification models in sequence according to the order. Obtain the content text of the spectrum state and wavelet transform state data of the sensor in the time series, and input the spectrum state and wavelet transform state data of the sensor in the time series into the first sorted data classification model.

6. The intelligent adaptive calibration method of the sensor according to claim 5, characterized in that, In S104, place the offset error of the reference feature data in the adjustment unit for sensor offset adjustment, and obtain an offset identifier, including: The adjustment unit obtains the offset error of the reference feature data based on the classification result of the data output, and then identifies the feature data parameters of the current sensor. Superimpose the offset error of the reference feature data on the identified feature data parameters. The offset error of the reference feature data is provided with a phase feature. The adjustment unit first identifies the phase feature, and then determines the numerical adjustment phase of the feature data parameters.

7. The intelligent adaptive calibration method of the sensor according to claim 6, characterized in that, In S105, use a preset mathematical model to predict the matching options of the sensor, and detect whether there is a matching request corresponding to the actual output value for the specified matching option, including: Establish a mathematical model to describe the error characteristics of the sensor, and then use the mathematical model to predict the parameter output value of the sensor. Obtain the parameter output value predicted by the mathematical model for the sensor, and arrange the parameter output value according to the preset parameter arrangement method to form matching options. Detect the actual output numerical path and data integrity of the spectrum state and wavelet transform state data of the adjusted sensor in the time series. If it is checked that the actual output numerical path and data of the spectrum state and wavelet transform state data of the sensor in the time series are complete, then establish a corresponding matching request for the specified matching option.

8. The intelligent adaptive calibration method of the sensor according to claim 7, characterized in that, In S106, if there is no corresponding matching request for the specified matching option, output a feedback signal to the adjustment unit to determine whether the actual output numerical path and data of the spectrum state and wavelet transform state data of the adjusted sensor in the time series are incomplete. If the actual output numerical path and data of the spectrum state and wavelet transform state data of the adjusted sensor in the time series are incomplete, then continue to request to establish a corresponding matching request within the cycle time until the matching request corresponding to the specified matching option is established.

9. The intelligent adaptive calibration system of the sensor, characterized in that, Applied to the intelligent adaptive calibration method described in any one of claims 1-8, the system includes: A receiving and identifying module, configured to receive a calibration request of the sensor, and input data into a preset data classification model to obtain a classification result based on the spectrum state and wavelet transform state data output of the sensor in the time series. A data analysis module, configured to perform data comparison on the classification result of the spectrum state and wavelet transform state data output of the sensor in the time series, place the classification result in the adjustment unit to obtain the offset error of the reference feature data. A calibration obtaining module, configured to place the offset error of the reference feature data in the adjustment unit for sensor offset adjustment, and obtain an offset identifier. A model matching module, which is used to identify the spectrum state and wavelet transform state data of the adjusted sensor in the time series, place them in a preset mathematical model, and use the preset mathematical model to predict the matching options of the sensor; A prediction comparison module, which is used to determine whether there is a corresponding matching request for the matching option. If so, it determines the comparison between the actual output value of the sensor in the matching request and the output value of the predicted sensor; A compensation module, which is used to compensate and correct the sensor data again according to the current actual output value.

10. The intelligent adaptive calibration system of the sensor according to claim 9, characterized in that, The model matching module includes: A model generation unit, which is used to obtain the function parameters preset by the system and generate a preset mathematical model through the preset function parameters; An output matching unit, which is used to predict the matching options of the sensor by using the preset mathematical model and detect whether there is a matching request corresponding to the specified matching option; A request acquisition unit, which is used to determine that there is a corresponding matching request for the specified matching option, and then determine the comparison between the actual output value of the sensor in the matching request and the output value of the predicted sensor.

Images