Multi-point Calibration Method for Illuminance Sensors Based on Big Data

Abstract

The present invention discloses a multi-point calibration method for illuminance sensors based on big data, specifically relating to the technical field of illuminance sensor calibration. Faulty illuminance sensors are screened out based on the transmittance, time zero drift, and zero point temperature drift of the illuminance sensors and excluded from subsequent calibrations, which can effectively save the calibration cost of the illuminance sensors; by analyzing big data, a correlation coefficient set of the illuminance sensors is obtained, and the illuminance sensors are calibrated based on the correlation coefficient set, which can calibrate the illuminance sensors more scientifically, improve the measurement accuracy and stability of the illuminance sensors; more calibration times are set for the illuminance sensors with a large comprehensive quality coefficient, and more resources can be used for the sensors with better performance, which is beneficial to the scientific management of the illuminance sensors; it solves the problems of high calibration cost of illuminance sensors and inability to calibrate illuminance sensors scientifically in the prior art.

Description

Technical Field

[0001] The present invention relates to the technical field of illuminance sensor calibration, and more specifically, to a multi-point calibration method for illuminance sensors based on big data. Background Art

[0002] With the increase of the usage time, the performance of the electronic components inside the illuminance sensor will gradually degrade, resulting in a decrease in the stability of the output signal; long-term exposure to certain specific environments (such as high temperature, high humidity, strong magnetic field, etc.) may also accelerate the aging process of the components, thus affecting the zero-point stability of the sensor; the components and materials inside the sensor will be affected by temperature changes, generating thermal expansion and contraction effects, resulting in slight changes in the internal structure of the sensor, thereby affecting the zero-point position of the output signal.

[0003] However, in actual use, there are still many disadvantages, such as the high calibration cost of the illuminance sensor and the problem that the illuminance sensor cannot be calibrated scientifically. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, the present invention provides a multi-point calibration method for illuminance sensors based on big data to solve the problems proposed in the above background art.

[0005] To achieve the above object, the present invention provides the following technical solution: A multi-point calibration method for illuminance sensors based on big data, including the following steps:

[0006] Step 1, collect the transmittance, average time zero drift and average zero temperature drift of the illuminance sensor;

[0007] Step 2, when the transmittance, average time zero drift and average zero temperature drift meet the preset standards, enter the next step; otherwise, mark it as a faulty illuminance sensor, do not enter the next step, and output the set of illuminance sensors to be calibrated;

[0008] Step 3, based on big data, establish a set of correlation coefficients for the illuminance sensors to be calibrated; the acquisition method of the set of correlation coefficients is: use statistical methods and machine learning algorithms to calculate the correlation coefficients between each feature dimension and the illuminance sensor; each feature dimension and the corresponding correlation coefficient form a set of correlation coefficients of the illuminance sensor; through linear normalization processing of the set of correlation coefficients, a set of correlation coefficients is obtained;

[0009] Step 4. Calibrate the illuminance sensor based on the correlation coefficient set and output the calibrated illuminance sensor, including: converting the non-linear relationship into a linear relationship through a data conversion variable and outputting each feature dimension after the conversion variable; using a linear regression model as the calibration model, where the linear regression model is expressed as y = β0 + β1 * x1 + β2 * x2 + … + βs * xs; here, y is the calibrated value of the illuminance, x1, x2, …, xs are each feature dimension after the conversion variable, and β0, β1, …, βs are the parameters of the calibration model; using an optimization algorithm to determine the parameters of the calibration model until the difference between the predicted value and the standard value meets the requirements, complete the calibration of the illuminance sensor, and output the calibrated illuminance sensor.

[0010] Preferably, in Step 1, use a transmittance measuring instrument to test the transmittance of the optical element of the illuminance sensor; the transmittance refers to the ratio of the transmitted light intensity to the incident light intensity, expressed as a percentage; measure the time zero drift and zero temperature drift of the illuminance sensor, and calculate the average value of the time zero drift and the average value of the zero temperature drift of the illuminance sensor; in Step 2, when the transmittance, time zero drift, and zero temperature drift of the illuminance sensor all meet the preset thresholds or requirements, it is considered that the illuminance sensor can be calibrated and proceed to the next calibration process; otherwise, mark it as a faulty illuminance sensor and exclude it from subsequent calibrations.

[0011] Preferably, based on the transmittance, the average value of the time zero drift, and the average value of the zero temperature drift, analyze and obtain the comprehensive quality coefficient of the illuminance sensor, and take corresponding measures based on the comprehensive quality coefficient, including the following steps:

[0012] Step S11. When the transmittance, time zero drift, and zero temperature drift of the illuminance sensor all meet the preset thresholds or requirements, mark it as the illuminance sensor to be calibrated, output the set of illuminance sensors to be calibrated, and record the transmittance, time zero drift, and average value of the zero temperature drift of the illuminance sensor to be calibrated.

[0013] Step S12. Calculate the zero temperature drift quality index based on the average value of the time zero drift and the average value of the zero temperature drift of the illuminance sensor.

[0014] Step S13. Under standard environmental conditions, uniformly set different gradient light intensities, record the error ratios of the illuminance sensor facing different gradient light intensities, and calculate the average value of the error ratios.

[0015] Step S14. Jointly analyze the average value of the error ratios, transmittance, average value of the time zero drift, and average value of the zero temperature drift to obtain the comprehensive quality coefficient of the illuminance sensor; take corresponding measures based on the comprehensive quality coefficient, including:

[0016] Allocate calibration resources, where the calibration resources include: a calibration times threshold; that is, the illuminance sensors with a larger comprehensive quality coefficient have more calibration times. The more calibration times, the better the calibration effect on the illuminance sensors. For illuminance sensors with a relatively low comprehensive quality coefficient, due to reasons such as hardware aging, damage, or design defects, the room for performance improvement is limited. Therefore, fewer calibration times are allocated, and more resources are used for the illuminance sensors with better performance.

[0017] Sort the illuminance sensors to be calibrated in descending order according to the comprehensive quality coefficient, and preferentially calibrate the illuminance sensors with high comprehensive quality coefficient values; or divide the set of illuminance sensors to be calibrated into several levels, and preferentially calibrate the levels with good quality; for example, the higher the comprehensive quality coefficient, the better the quality of the illuminance sensor, and the illuminance sensors with good quality are calibrated first.

[0018] Preferably, the method for obtaining the comprehensive quality coefficient is as follows:

[0019] Denote the average error ratio, transmittance, average time zero drift, and average zero temperature drift as Er, Tm, TZDa, and TZDb respectively;

[0020] Through the formula Calculate the zero temperature drift quality index ZQI, where TZDa T , TZDb T Represent the thresholds of time zero drift and zero temperature drift respectively;

[0021] Through the formula Calculate the comprehensive quality coefficient Zp, where α1, α2, and α3 are positive real number exponents set according to the importance of each parameter to the comprehensive quality.

[0022] Preferably, before constructing the set of correlation coefficients, perform data preprocessing on the measurement data of the illuminance sensors and environmental characteristic parameters, including:

[0023] Data cleaning and denoising processing to ensure the accuracy and reliability of the data;

[0024] Feature dimension parameter selection: Feature dimension parameters include environmental characteristic parameters (such as temperature, humidity, air pressure, etc.) and spatio-temporal characteristic parameters (such as time, geographical location, etc.);

[0025] Correlation analysis: Use statistical methods (such as Pearson correlation coefficient, Spearman rank correlation coefficient) and machine learning algorithms (such as random forest, gradient boosting tree, etc.) to accurately calculate the correlation coefficients of each dimension with the illuminance sensor to improve the accuracy and robustness of the set of correlation coefficients;

[0026] Dynamic adjustment: The construction of the correlation coefficient set should support dynamic updates. As new data is added, the correlation coefficients are recalculated and the correlation coefficient set is adjusted to adapt to factors such as environmental changes and equipment aging.

[0027] Preferably, the multi-point calibration method for the illuminance sensor further includes:

[0028] Step Five: Based on the correlation coefficient set or the updated correlation coefficient set, build a verification environment. Place the illuminance sensor in the verification environment with a known standard illuminance value and output the calibration value corresponding to the illuminance value.

[0029] Step Six: Compare the gap between the calibration value and the standard value of the illuminance value of the illuminance sensor in the verification environment, and take measures based on the relationship between the gap and the threshold.

[0030] Preferably, in Step Five, the building of the verification environment includes:

[0031] Set the number of gradients for each feature dimension based on the correlation coefficient set, fluctuate up and down centered on the standard environment, and output several gradient data for each feature dimension with the upper and lower limits of each feature dimension of the illuminance sensor as constraints.

[0032] Based on the several gradient data of each feature dimension, arrange and combine to obtain several groups of verification environment feature parameters, output the verification environment feature parameters, and build a verification environment based on the verification environment feature parameters.

[0033] Preferably, use the calibration quality index JQI to represent the gap, and determine whether the calibration quality index exceeds the corresponding calibration quality index threshold; if so, it indicates that the calibration is successful; otherwise, determine whether the number of calibration times reaches the calibration times threshold. If the calibration times threshold is not reached, recalibrate, obtain the correlation coefficient set based on the new data analysis, denoted as the updated correlation coefficient set, until the calibration times threshold is reached; if the requirement is still not met when the calibration times threshold is reached, mark it as a faulty illuminance sensor and terminate the calibration.

[0034] Through the formula where yi is the standard value of the illuminance value, y is the calibration value of the illuminance value, n represents the number of verification times, and i represents the serial number of the verification times.

[0035] Preferably, the multi-point calibration method for the illuminance sensor further includes a calibration quality management step. The calibration quality management step is used to jointly analyze to obtain the average value of the calibration quality index, the calibration consumption time fluctuation coefficient, and the calibration success rate, obtain the calibration operation reliability coefficient, and take measures based on the calibration operation reliability coefficient.

[0036] Denote the average value of the calibration quality index, the calibration consumption time fluctuation coefficient σ T and the calibration success rate Jc as JQIa, σT , Jc;

[0037] The calibration operation reliability coefficient RJ is calculated through the formula where ∈ is a very small positive number used to prevent the denominator from being zero; ∈ is adjusted according to the actual situation; if RJ is high, it indicates that the calibration operation is reliable, and only routine maintenance and monitoring are required; if RJ is low, it indicates that there are problems with the calibration operation, and the calibration process should be optimized, more accurate calibration equipment should be replaced, and the operators should be trained.

[0038] Technical effects and advantages of the present invention:

[0039] (1) The multi-point calibration method for illuminance sensors provided by the present invention screens out faulty illuminance sensors based on the transmittance, time zero drift, and zero temperature drift of the illuminance sensors and excludes them from subsequent calibrations, which can effectively save the calibration cost of illuminance sensors; by analyzing big data, a set of correlation coefficients of the illuminance sensors is obtained; the illuminance sensors are calibrated based on the set of correlation coefficients, which calibrates the illuminance sensors more scientifically, improves the measurement accuracy and stability of the illuminance sensors, and ensures that reliable data can be provided under different environments and different lighting conditions; more calibration times are set for illuminance sensors with a large comprehensive quality coefficient, which can allocate more resources to illuminance sensors with better performance, facilitating the scientific management of illuminance sensors; it solves the problems of high calibration cost of illuminance sensors and inability to calibrate illuminance sensors scientifically in the prior art.

[0040] (2) The multi-point calibration method for illuminance sensors provided by the present invention builds a verification environment based on the set of correlation coefficients of the illuminance sensors to be calibrated; it can effectively ensure that abnormal illuminance sensors are effectively calibrated, solving the problem of unscientific calibration quality verification in the prior art. Description of the Drawings

[0041] Figure 1 is the flowchart of the multi-point calibration method for illuminance sensors of the present invention.

[0042] Figure 2 is the flowchart of the multi-point calibration method for illuminance sensors based on the comprehensive quality coefficient of the present invention.

[0043] Figure 3 is the flowchart of the calibration quality verification of the present invention. Detailed Embodiments

[0044] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art.

[0045] Meanwhile, it should be understood that, for the sake of convenience of description, the sizes of the respective parts shown in the drawings are not drawn in actual proportional relationship.

[0046] The following description of at least one exemplary embodiment is merely illustrative in nature and in no way serves as a limitation to the present application and its application or use.

[0047] Technologies, methods, and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, the said technologies, methods, and devices should be regarded as part of the specification.

[0048] Background Art: Time zero drift refers to the situation where the output zero point of a light intensity sensor drifts with time, that is, when there is no light input (i.e., the ideal zero state), the output signal of the sensor may also shift over time; zero temperature drift refers to the situation where the output zero point of a light intensity sensor drifts with temperature changes, that is, when the ambient temperature changes, the output signal of the sensor also shifts at the zero point position. Time zero drift will cause the accuracy of the measurement results of the sensor to gradually decrease during long-term use, thus affecting the overall performance of the system; zero temperature drift will cause deviations in the measurement results of the sensor at different temperatures, affecting the measurement accuracy and reliability of the system. Abnormalities in time zero drift and zero temperature drift are often caused by reasons such as design defects of the sensor, problems in the manufacturing process, or irreversible damage caused by long-term use, and it is difficult to restore performance through calibration.

[0049] Embodiment 1, referring to Figure 1 the flowchart of the multi-point calibration method for a light intensity sensor, the present invention provides a Figure 1 multi-point calibration method for a light intensity sensor based on big data as shown in

[0050] Step 1: Collect the transmittance, average time zero drift, and average zero temperature drift of the light intensity sensor;

[0051] Step 2: When the transmittance, average time zero drift, and average zero temperature drift meet the preset criteria, proceed to the next step; otherwise, mark it as a faulty light intensity sensor, do not proceed to the next step, and output the set of light intensity sensors to be calibrated;

[0052] In the embodiments of the present invention, it should be explained that a transmittance measuring instrument (such as a spectrophotometer) is used to test the transmittance of the optical element of the illuminance sensor; the transmittance refers to the ratio of the transmitted light intensity to the incident light intensity, expressed as a percentage, and a high transmittance means high transparency; the time zero drift and zero temperature drift of the illuminance sensor are measured, and the average value of the time zero drift and the average value of the zero temperature drift of the illuminance sensor are calculated; it is explained that when the transmittance, time zero drift, and zero temperature drift of the illuminance sensor all meet the preset thresholds or requirements, the illuminance sensor is considered calibratable and proceeds to the next calibration process; otherwise, it is marked as a faulty illuminance sensor and excluded from subsequent calibrations;

[0053] Step 3: Based on big data, establish an association coefficient set for the illuminance sensor to be calibrated; the acquisition method of the association coefficient set is: using statistical methods and machine learning algorithms to calculate the correlation coefficients of each feature dimension with the illuminance sensor; each feature dimension and the corresponding correlation coefficients form the correlation coefficient set of the illuminance sensor; through linear normalization processing of the correlation coefficient set, the association coefficient set is obtained;

[0054] It is explained that the statistical method may be the Pearson correlation coefficient or the Spearman rank correlation coefficient; the machine learning algorithms may be decision trees, random forests, gradient boosting machines, neural networks, and the feature dimensions may include environmental feature parameters and spatio-temporal feature parameters; linear normalization processing is used to make the values of the correlation coefficients in the correlation coefficient set range from 0 to 1.

[0055] Step 4: Calibrate the illuminance sensor based on the association coefficient set and output the calibrated illuminance sensor; including: converting the non-linear relationship into a linear relationship through data conversion variables (such as logarithmic conversion, square root conversion, polynomial conversion, etc.) and outputting each feature dimension after passing through the conversion variable; using a linear regression model as the calibration model, and the linear regression model is expressed as y = β0 + β1 * x1 + β2 * x2 + … + βs * xs; where y is the calibrated value of the illuminance value, x1, x2, …, xs are each feature dimension (such as temperature, humidity, etc.) after passing through the conversion variable, and β0, β1, …, βs are the parameters of the calibration model; using an optimization algorithm to determine the parameters of the calibration model (such as the β parameters in the linear regression model) until the difference between the predicted value and the standard value meets the requirements, completing the calibration of the illuminance sensor and outputting the calibrated illuminance sensor; the standard value refers to the standard value of the illuminance, that is, the true value.

[0056] It is explained that the correlation coefficient can be linear or non-linear; if there is a non-linear relationship between the feature dimension parameters and the measured values, a polynomial regression model or a neural network model is selected as the calibration model; the optimization algorithms include the least squares method and the gradient descent method:

[0057] Least squares method: Using a linear regression model as the calibration model, the least squares method is selected as the optimization algorithm to find the optimal parameters by minimizing the sum of squared residuals; Gradient descent method: For more complex models, such as neural network models, the gradient descent method (or its variants, such as stochastic gradient descent, batch gradient descent, Adam, etc.) is used to minimize the loss function by iteratively adjusting the model parameters; In the embodiments of the present invention, the loss function refers to the difference between the predicted value and the standard value.

[0058] In the embodiments of the present invention, it is further designed that, referring to Figure 2 the flowchart of the multi-point calibration method for illuminance sensors based on the comprehensive quality coefficient. Based on the transmittance, the average value of zero drift over time, and the average value of zero temperature drift, the comprehensive quality coefficient of the illuminance sensor is analyzed, and corresponding measures are taken based on the comprehensive quality coefficient, including the following steps:

[0059] Step S11: When the transmittance, zero drift over time, and zero temperature drift of the illuminance sensor all meet the preset thresholds or requirements, mark the illuminance sensor to be calibrated, output the set of illuminance sensors to be calibrated, and record the average values of the transmittance, zero drift over time, and zero temperature drift of the illuminance sensor to be calibrated;

[0060] Step S12: Calculate the zero temperature drift quality index based on the average value of zero drift over time and the average value of zero temperature drift of the illuminance sensor;

[0061] Step S13: In a standard environment, uniformly set different gradient illumination intensities, record the error ratios of the illuminance sensor facing different gradient illumination intensities, and calculate the average value of the error ratios;

[0062] Step S14: Jointly analyze the average value of the error ratios, the transmittance, the average value of zero drift over time, and the average value of zero temperature drift to obtain the comprehensive quality coefficient of the illuminance sensor; Corresponding measures are taken based on the comprehensive quality coefficient, including:

[0063] Allocate calibration resources, and the calibration resources include: the calibration times threshold; that is, the illuminance sensor with a larger comprehensive quality coefficient has more calibration times, and the more calibration times, the better the calibration effect on the illuminance sensor; For the illuminance sensor with a relatively low comprehensive quality coefficient, due to reasons such as hardware aging, damage, or design defects, its performance improvement space is limited. Therefore, fewer calibration times are allocated, and more resources are used for the illuminance sensor with better performance;

[0064] Sort the illuminance sensors to be calibrated in descending order of the comprehensive quality coefficient, and preferentially calibrate the illuminance sensors with high comprehensive quality coefficient values; or divide the set of illuminance sensors to be calibrated into several levels, and preferentially calibrate the levels with good quality; for example, the higher the comprehensive quality coefficient, the better the quality of the illuminance sensor, and the illuminance sensor with good quality is calibrated first.

[0065] In the embodiment of the present invention, it is further designed that the acquisition method of the comprehensive quality coefficient is as follows:

[0066] Denote the average error ratio, transmittance, average zero drift over time, and average zero drift over temperature as Er, Tm, TZDa, and TZDb respectively;

[0067] Through the formula Calculate the zero temperature drift quality index ZQI, where TZDa T , TZDb T Represent the thresholds of zero drift over time and zero drift over temperature respectively;

[0068] Through the formula Calculate the comprehensive quality coefficient Zp, where α1, α2, and α3 are positive real number exponents set according to the importance of the influence of each parameter on the comprehensive quality.

[0069] In the embodiment of the present invention, it needs to be explained that before constructing the correlation coefficient set, data preprocessing is performed on the measurement data of the illuminance sensor and the environmental characteristic parameters, including:

[0070] Data cleaning and denoising processing to ensure the accuracy and reliability of the data;

[0071] Feature dimension parameter selection: The feature dimension parameters include environmental characteristic parameters (such as temperature, humidity, air pressure, etc.) and spatio-temporal characteristic parameters (such as time, geographical location, etc.);

[0072] Correlation analysis: Statistical methods (such as Pearson correlation coefficient, Spearman rank correlation coefficient) and machine learning algorithms (such as random forest, gradient boosting tree, etc.) are used to accurately calculate the correlation coefficients between each dimension and the illuminance sensor to improve the accuracy and robustness of the correlation coefficient set;

[0073] Dynamic adjustment: The construction of the correlation coefficient set should support dynamic update. As new data is added, the correlation coefficients are recalculated and the correlation coefficient set is adjusted to adapt to factors such as environmental changes and equipment aging.

[0074] Summary: Faulty illuminance sensors are screened out based on the transmittance, zero drift over time, and zero temperature drift of the illuminance sensors and excluded from subsequent calibrations, effectively saving the calibration cost of illuminance sensors. A calibration times threshold is set based on the comprehensive quality coefficient. By analyzing big data, a correlation coefficient set of illuminance sensors is obtained. The illuminance sensors are calibrated based on the correlation coefficient set, calibrating the illuminance sensors more scientifically, improving the measurement accuracy and stability of the illuminance sensors, and ensuring that reliable data can be provided under different environments and different lighting conditions. More calibration times are set for illuminance sensors with a large comprehensive quality coefficient, enabling more resources to be used on illuminance sensors with better performance, which is conducive to the scientific management of illuminance sensors.

[0075] Example 2. Refer to Figure 3 the calibration quality verification flowchart. The difference between the embodiment of the present invention and Embodiment 1 is that the multi-point calibration method for illuminance sensors of the present invention further includes:

[0076] Step Five: Based on the correlation coefficient set or the updated correlation coefficient set, build a verification environment, place the illuminance sensor in a verification environment with a known standard illuminance value, and output the calibration value corresponding to the illuminance value.

[0077] Step Six: Compare the gap between the calibration value and the standard value of the illuminance value of the illuminance sensor in the verification environment, and take measures based on the relationship between the gap and the corresponding threshold.

[0078] It should be explained in the embodiment of the present invention that the building of the verification environment includes:

[0079] Set the gradient number of each feature dimension based on the correlation coefficient set, fluctuate up and down centered on the standard environment, and output several gradient data of each feature dimension with the upper and lower limits of each feature dimension of the illuminance sensor as constraints.

[0080] When setting the gradient number of each feature dimension, the gradient density should be allocated based on the size of the correlation coefficient, that is, more gradient points are set for dimensions with high correlation to more carefully examine its influence. At the same time, consider the feasibility of actual operation and cost-effectiveness.

[0081] Based on the several gradient data of each feature dimension, arrange and combine to obtain several groups of verification environment characteristic parameters, output the verification environment characteristic parameters, and build a verification environment based on the verification environment characteristic parameters.

[0082] In the embodiments of the present invention, it should be noted that during the verification process, high-precision environmental control equipment (such as a thermo-hygrostat, a light simulator, etc.) is used to accurately simulate the change in illuminance under different environmental conditions, ensuring the accuracy and repeatability of the verification environment, realizing the automatic control and data collection of the verification environment, reducing human errors, and improving the verification efficiency and accuracy.

[0083] In the further design of the embodiments of the present invention, the gap is represented by the calibration quality index JQI, and it is determined whether the calibration quality index exceeds the corresponding calibration quality index threshold; if so, it indicates that the calibration is successful; otherwise, it is determined whether the number of calibration times reaches the calibration times threshold. If the calibration times threshold is not reached, recalibration is performed, and a set of correlation coefficients is obtained based on the analysis of the new data, denoted as the updated set of correlation coefficients, until the calibration times threshold is reached; if the requirements are still not met after reaching the calibration times threshold, the illuminance sensor is marked as faulty, and the calibration is terminated.

[0084] Through the formula where yi is the standard value of the illuminance value, y is the calibrated value of the illuminance value, n represents the number of verification times, and i represents the order number of the verification times.

[0085] In the further design of the embodiments of the present invention, the multi-point calibration method for the illuminance sensor further includes a calibration quality management step, and the calibration quality management step is used to jointly analyze to obtain the average value of the calibration quality index, the calibration consumption time fluctuation coefficient, and the calibration success rate, obtain the calibration operation reliability coefficient, and take measures based on the calibration operation reliability coefficient.

[0086] The average value of the calibration quality index, the calibration consumption time fluctuation coefficient σ T and the calibration success rate Jc are respectively denoted as JQIa, σ T , Jc;

[0087] Through the formula The calibration operation reliability coefficient RJ is calculated, where ∈ is a very small positive number used to prevent the denominator from being zero; ∈ is adjusted according to the actual situation; if RJ is high, it indicates that the calibration operation reliability is good, and only routine maintenance and monitoring are required; if RJ is low, it indicates that there are problems with the calibration operation, and the calibration process is optimized, more accurate calibration equipment is replaced, and the operators are trained.

[0088] Summary: In the prior art, the method of verifying the calibration quality is often not scientific enough, and the verification is carried out based on the subjective awareness of users and fixed processes; as a result, it is impossible to ensure that the abnormal illuminance sensor is effectively calibrated; the embodiments of the present invention provide a verification method after calibration, and a verification environment is built based on the set of correlation coefficients of the illuminance sensor to be calibrated; it can effectively ensure that the abnormal illuminance sensor is effectively calibrated.

[0089] Finally, the above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A multi-point calibration method for an illuminance sensor based on big data, characterized in that: include: Step 1, collecting the transmittance, time zero drift average value and zero temperature drift average value of the light intensity sensor; Step 2: When the transmittance, the time zero drift average value and the zero temperature drift average value meet the preset standard, proceed to the next step; otherwise, mark it as a faulty light sensor, do not proceed to the next step, and output the light sensor set to be calibrated; Step 3: Establish a correlation coefficient set of the light sensor to be calibrated based on big data; the correlation coefficient set is obtained by: using statistical methods and machine learning algorithms to calculate the correlation coefficients of each feature dimension and the light sensor; each feature dimension and the corresponding correlation coefficient constitute the correlation coefficient set of the light sensor; and the correlation coefficient set is processed by linear normalization to obtain the correlation coefficient set; Step 4, calibrate the light sensor based on the correlation coefficient set, and output the calibrated light sensor; including: converting the nonlinear relationship into a linear relationship through data conversion variables, and outputting the characteristic dimensions of the converted variables; using a linear regression model as a calibration model, the linear regression model is expressed as y=β0+β1*x1+β2*x2+…+βs*xs; wherein y is the calibration value of the light value, x1, x2,…, xs are the characteristic dimensions of the converted variables, and β0, β1,…, βs are the parameters of the calibration model; using an optimization algorithm to determine the parameters of the calibration model until the difference between the predicted value and the standard value meets the requirements, completing the calibration of the light sensor, and outputting the calibrated light sensor.

2. The multi-point calibration method of an illuminance sensor based on big data according to claim 1, characterized in that: Use a transmittance measuring instrument to test the transmittance of the optical element of the light sensor; transmittance refers to the ratio of the transmitted light intensity to the incident light intensity, expressed as a percentage; measure the time zero drift and zero temperature drift of the light sensor; calculate the average time zero drift and zero temperature drift of the light sensor; when the transmittance, time zero drift, and zero temperature drift of the light sensor meet the preset thresholds or requirements, the light sensor is considered calibrable and enters the next calibration process; otherwise, it is marked as a faulty light sensor and excluded from subsequent calibration.

3. The multi-point calibration method of an illuminance sensor based on big data according to claim 1, characterized in that: Based on the transmittance, the time zero drift average value and the zero temperature drift average value, the comprehensive quality coefficient of the light intensity sensor is analyzed and obtained, and corresponding measures are taken based on the comprehensive quality coefficient, including the following steps: Step S11: When the transmittance, time zero drift and zero temperature drift of the light sensor meet the preset threshold or requirement, the light sensor is marked as the light sensor to be calibrated, the light sensor set to be calibrated is output, and the transmittance, time zero drift and zero temperature drift average values ​​of the light sensor to be calibrated are recorded; Step S12, calculating a zero temperature drift quality index based on the time zero drift average value and the zero temperature drift average value of the light intensity sensor; Step S13, under a standard environment, evenly set different gradient light intensities, record the error ratios of the light sensor facing different gradient light intensities, and calculate the average error ratio; Step S14, jointly analyzing the error ratio average value, transmittance, time zero drift average value and zero temperature drift average value to obtain a comprehensive quality coefficient of the light intensity sensor; Take corresponding measures based on the comprehensive quality coefficient, including: Allocate correction resources, the correction resources include: a calibration times threshold Tha; that is, light sensors with a large comprehensive quality coefficient have more calibration times; sort the light sensors to be calibrated from high to low according to the comprehensive quality coefficient, and give priority to calibrating light sensors with high comprehensive quality coefficient values.

4. The multi-point calibration method of an illuminance sensor based on big data according to claim 3 is characterized in that: The comprehensive quality coefficient is obtained as follows: The error ratio average, transmittance, time zero drift average and zero temperature drift average are recorded as Er, Tm, TZDa, TZDb respectively; By formula The zero temperature drift quality index ZQI is calculated, where TZDa T ,TZDb T Respectively represent the thresholds of time zero drift and zero temperature drift; By formula The comprehensive quality coefficient Zp is calculated, where α1, α2, and α3 are positive real number exponents set according to the importance of each parameter on the comprehensive quality.

5. The multi-point calibration method of an illuminance sensor based on big data according to claim 1, characterized in that: The multi-point calibration method of the light intensity sensor also includes: Step 5: Based on the correlation coefficient set or the updated correlation coefficient set, a verification environment is built, the light sensor is placed in the verification environment with a known standard light value, and a calibration value corresponding to the light value is output; Step 6: Compare the difference between the calibration value of the illuminance value of the illuminance sensor in the verification environment and the standard value, and take measures based on the relationship between the difference and the threshold.

6. The multi-point calibration method of an illuminance sensor based on big data according to claim 5, characterized in that: The verification environment construction includes: The number of gradients of each feature dimension is set based on the correlation coefficient set, fluctuates up and down with the standard environment as the center, and the upper and lower limits of each feature dimension of the light sensor are used as constraints to output a number of gradient data of each feature dimension; Based on a number of gradient data of each feature dimension, a number of groups of verification environment feature parameters are obtained by arrangement and combination, the verification environment feature parameters are output, and the verification environment is built based on the verification environment feature parameters.

7. The multi-point calibration method of an illuminance sensor based on big data according to claim 6, characterized in that: The calibration quality index JQI is used to represent the gap, and it is determined whether the calibration quality index exceeds the corresponding calibration quality index threshold; if so, it indicates that the calibration is successful; otherwise, it is determined whether the calibration times have reached the calibration times threshold. If it has not reached the calibration times threshold, recalibrate, and obtain a set of correlation coefficients based on new data analysis, which is recorded as the updated correlation coefficient set, until the calibration times threshold is reached; if the calibration times threshold is reached but still does not meet the requirements, it is marked as a faulty light sensor and the calibration is terminated; By formula Among them, yi is the standard value of the illuminance value, y is the calibration value of the illuminance value, n represents the number of verifications, and i represents the sequential number of verifications.

8. The multi-point calibration method of an illuminance sensor based on big data according to claim 6, characterized in that: The multi-point calibration method for the illuminance sensor further comprises a calibration quality management step, wherein the calibration quality management step is used to jointly analyze and obtain a calibration quality index average value, a calibration consumption time fluctuation coefficient and a calibration success rate, obtain a calibration operation reliability coefficient, and take measures based on the calibration operation reliability coefficient; The average value of the calibration quality index and the fluctuation coefficient of the calibration time σ T and calibration success rate Jc, denoted as JQIa, σ T , Jc; By formula The calibration operation reliability coefficient RJ is calculated, where ∈ is a small positive number to prevent the denominator from being zero; ∈ is adjusted according to the actual situation; If RJ is high, it indicates that the calibration operation is reliable and only routine maintenance and monitoring are required. If RJ is low, it indicates that there are problems with the calibration operation and the calibration process needs to be optimized, more accurate calibration equipment needs to be replaced, and operators need to be trained.

Images