Temperature compensation algorithm-based intelligent monitor temperature drift correction method and system

Abstract

The embodiment of the present application relates to the technical field of data processing, and particularly relates to a temperature drift correction method and system of an intelligent monitor based on a temperature compensation algorithm, which comprises the following steps: collecting environment temperature data of an environment where the intelligent monitor is located in real time, and obtaining a sensor aging factor preset in the intelligent monitor; based on the environment temperature data and a preset temperature-drift characteristic model, extracting temperature drift characteristics of the intelligent monitor, and dynamically generating a nonlinear compensation curve matched with the temperature drift characteristics; using an adaptive compensation parameter optimization algorithm, iteratively optimizing and processing compensation parameters of the nonlinear compensation curve, and dynamically correcting the compensation parameters by fusing the sensor aging factor in the iterative optimization and processing process, so as to obtain an optimized compensation parameter set; according to the optimized compensation parameter set, performing real-time correction processing on original measurement data of the intelligent monitor, and outputting target measurement results after suppressing temperature drift noise.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for correcting temperature drift of an intelligent monitoring instrument based on a temperature compensation algorithm. Background Art

[0002] In the field of industrial monitoring, temperature drift correction is a key technology for ensuring sensor measurement accuracy. Because temperature changes can alter the physical properties of sensor components, leading to drift errors in the output signal, traditional methods often use fixed compensation coefficients or linear temperature compensation models for correction. These techniques typically establish a linear relationship between temperature and drift based on laboratory calibration data, and then modify the measurement results using preset compensation parameters.

[0003] However, existing compensation models mostly use ideal linear assumptions, which cannot accurately characterize the nonlinear drift characteristics of sensors under complex temperature gradients, resulting in increased compensation residuals in high and low temperature alternating scenarios. In addition, the compensation parameters of existing technologies are fixed for a long time and do not take into account the time-varying drift characteristics caused by component aging during the actual operation of the sensor. As the service time increases, the initial calibration parameters gradually mismatch the actual characteristics. To address this situation, current solutions mostly rely on regular manual calibration and maintenance, which is difficult to meet the needs of industrial sites for continuous and stable measurements. It can be seen that existing technologies have defects such as rapid attenuation of compensation accuracy and poor long-term stability. How to build a coordinated compensation mechanism that dynamically adapts to ambient temperature changes and device aging processes is a technical barrier that urgently needs to be overcome. Summary of the Invention

[0004] In order to at least overcome the above-mentioned deficiencies in the prior art, one of the objectives of the present invention is to provide a method and system for correcting temperature drift of an intelligent monitoring instrument based on a temperature compensation algorithm.

[0005] An embodiment of the present invention provides a method for correcting temperature drift of an intelligent monitoring instrument based on a temperature compensation algorithm, comprising:

[0006] Collecting ambient temperature data of the environment in which the intelligent monitor is located in real time, and obtaining a sensor aging factor preset in the intelligent monitor;

[0007] Extracting the temperature drift characteristics of the intelligent monitor based on the ambient temperature data and a preset temperature-drift characteristic model, and dynamically generating a nonlinear compensation curve matching the temperature drift characteristics;

[0008] Adopting an adaptive compensation parameter optimization algorithm to iteratively optimize the compensation parameters of the nonlinear compensation curve, and integrating the sensor aging factor in the iterative optimization process to dynamically correct the compensation parameters to obtain an optimized compensation parameter set;

[0009] The original measurement data of the intelligent monitor is corrected in real time according to the optimized compensation parameter set, and a target measurement result with temperature drift noise suppressed is output.

[0010] In one implementation, extracting the temperature drift characteristic of the intelligent monitor based on the ambient temperature data and a preset temperature-drift characteristic model includes:

[0011] Dividing the ambient temperature data into multiple temperature data segments according to a preset time window, and performing temperature fluctuation trend analysis on each temperature data segment to obtain the temperature change rate and temperature fluctuation amplitude of each temperature data segment;

[0012] The temperature-drift characteristic model is called to perform nonlinear correlation mapping processing on the temperature change rate and the temperature fluctuation amplitude to generate the temperature drift characteristic of the intelligent monitor; the temperature drift characteristic includes a first mapping relationship between the temperature change rate and the drift amount, and a second mapping relationship between the temperature fluctuation amplitude and the drift amount.

[0013] In one implementation, dynamically generating a nonlinear compensation curve that matches the temperature drift characteristic includes:

[0014] According to the first mapping relationship, the temperature change rate is mapped to a corresponding first drift component, and according to the second mapping relationship, the temperature fluctuation amplitude is mapped to a corresponding second drift component; wherein the first drift component and the second drift component are dimensionless relative change rates obtained after normalization;

[0015] Inputting the first drift component and the second drift component into a preset compensation curve generation function, and obtaining initial compensation parameters through nonlinear weighted fusion calculation;

[0016] Dynamically adjusting the initial compensation parameters according to the model parameters in the temperature-drift characteristic model to generate adjusted compensation parameters;

[0017] A piecewise continuous nonlinear compensation curve is constructed based on the adjusted compensation parameters, and the nonlinear compensation curve is used to provide differentiated compensation amounts in different temperature fluctuation ranges.

[0018] In one implementation, the updating process of the preset compensation curve generating function includes:

[0019] monitoring an average correction error of the nonlinear compensation curve within a preset time period, and determining whether the average correction error exceeds a dynamic adjustment threshold;

[0020] If it exceeds, adjusting the coefficients of the nonlinear relationship expression in the compensation curve generating function according to the distribution characteristics of the average correction error;

[0021] The adjusted compensation curve generating function is reapplied to subsequent temperature drift characteristic processing to achieve adaptive updating of the nonlinear compensation curve.

[0022] In one implementation, obtaining a sensor aging factor preset in the intelligent monitoring instrument includes:

[0023] Obtaining a historical operating time and sensor aging weight distribution table of the intelligent monitoring instrument; wherein the sensor aging weight distribution table includes aging impact weights corresponding to different operating time intervals;

[0024] According to the historical working hours, a corresponding aging impact weight is matched from the sensor aging weight allocation table, and a reference aging factor is weighted based on the aging impact weight to generate a dynamically updated sensor aging factor.

[0025] In one implementation, the process of generating the sensor aging weight distribution table includes:

[0026] Acquire historical data of multiple reference intelligent monitors during an aging test phase, wherein the historical data includes sensor performance degradation indicators at different operating times;

[0027] According to the correlation between the sensor performance degradation index and the temperature drift correction error, the impact level corresponding to different working time intervals is divided;

[0028] A corresponding aging impact weight is allocated to each working time interval based on the impact level, and the sensor aging weight allocation table is generated.

[0029] In one implementation, the iterative optimization process of the compensation parameters of the nonlinear compensation curve using an adaptive compensation parameter optimization algorithm includes:

[0030] Obtaining a temperature drift correction error in a current iteration cycle, and comparing the temperature drift correction error with a preset error threshold;

[0031] If the temperature drift correction error is greater than the preset error threshold, adjusting the parameter values ​​in the compensation parameter set according to the error gradient direction to generate an updated compensation parameter set;

[0032] The updated compensation parameter set is re-input into the nonlinear compensation curve for parameter verification until the temperature drift correction error is less than or equal to the preset error threshold.

[0033] In one implementation, dynamically correcting the compensation parameters by integrating the sensor aging factor during the iterative optimization process includes:

[0034] Divide the preset sensor aging factor value intervals according to the value of the sensor aging factor, and configure a corresponding compensation parameter correction weight for each sensor aging factor value interval;

[0035] Extracting an offset compensation parameter and a temperature drift slope compensation parameter in a current iteration cycle from the compensation parameter set, and decomposing the offset compensation parameter and the temperature drift slope compensation parameter into independent parameter components according to parameter type; wherein the independent parameter components are dimensionless standardized parameter components obtained after dedimensionalization processing;

[0036] Matching a corresponding compensation parameter correction weight according to the sensor aging factor value interval in which the sensor aging factor is located, and allocating the compensation parameter correction weight to each independent parameter component;

[0037] Based on the parameter change direction of each independent parameter component, a directional weighted operation is performed on the allocated compensation parameter correction weight to generate an aging correction component corresponding to each independent parameter component;

[0038] adding the aging correction component to the corresponding independent parameter component to generate a corrected offset compensation parameter component and a corrected temperature drift slope compensation parameter component;

[0039] Recombining the corrected offset compensation parameter component and the corrected temperature drift slope compensation parameter component according to parameter type to generate a dynamically corrected compensation parameter set;

[0040] Inputting the dynamically corrected compensation parameter set into the nonlinear compensation curve for parameter verification, and obtaining a verified temperature drift correction error;

[0041] According to the error distribution characteristics of the verified temperature drift correction error, reversely adjust the compensation parameter correction weight corresponding to the sensor aging factor value interval to generate an updated compensation parameter correction weight table;

[0042] Based on the updated compensation parameter correction weight table, dynamic correction weight distribution is performed on the independent parameter components of the next iteration cycle to generate an optimized compensation parameter set.

[0043] In one implementation, performing real-time correction processing on the original measurement data of the intelligent monitor according to the optimized compensation parameter set and outputting a target measurement result after suppressing temperature drift noise includes:

[0044] Dividing the original measurement data into a plurality of time-synchronized measurement data segments according to the acquisition timestamp, wherein the time range of each measurement data segment corresponds one-to-one with the time range of the ambient temperature data segment;

[0045] matching a corresponding compensation parameter group from the optimized compensation parameter set according to the time range of the ambient temperature data segment, and assigning the compensation parameter group to the time-synchronized measurement data segment;

[0046] performing a linear compensation operation on each measurement value in the time-synchronized measurement data segment based on the offset correction coefficient and the temperature drift slope in the compensation parameter group to generate a compensated measurement data sequence;

[0047] Performing sliding window mean filtering on the compensated measurement data sequence, calculating the average value of the measurement data in each window according to a preset window length and overlapping step length, and generating a filtered measurement data sequence;

[0048] The filtered measurement data sequences are merged in the order of timestamps, and the measurement data corresponding to duplicate timestamps are removed to generate the target measurement result after suppressing the temperature drift noise.

[0049] In a non-limiting implementation, after outputting the target measurement result after suppressing temperature drift noise, the method further includes:

[0050] Retrieve a historical temperature drift correction data set that matches the current ambient temperature data from the historical database, and extract the corresponding historical compensation parameter set and historical correction results;

[0051] Comparing the historical compensation parameter set with the optimized compensation parameter set for parameter differences, and identifying abnormal compensation parameter components that deviate from a preset reference range;

[0052] Based on the residual distribution characteristics of the historical correction results and the target measurement results, a parameter error transmission link is constructed to locate the error source direction of the abnormal compensation parameter component;

[0053] Performing a gradient descent compensation operation on the abnormal compensation parameter component according to the direction of the error source to generate a reversely corrected compensation parameter component;

[0054] The compensation parameter components after the reverse correction are refitted with the current ambient temperature data to generate a compensation parameter set after feedback correction and update the set to the nonlinear compensation curve.

[0055] In a non-limiting implementation, after outputting the target measurement result after suppressing temperature drift noise, the method further includes:

[0056] Real-time monitoring of the instantaneous change gradient of subsequent ambient temperature data, and generating a temperature transition event identifier when the instantaneous change gradient exceeds a mutation threshold;

[0057] Extracting the temperature mean difference between the steady-state interval before the temperature transition and the steady-state interval after the transition corresponding to the temperature transition event identifier, and determining the product of the temperature mean difference and a preset transition temperature difference compensation coefficient;

[0058] Dynamically adjusting the temperature drift slope parameter in the optimized compensation parameter set according to the multiplication result to generate a pre-adjusted compensation parameter group;

[0059] Loading the pre-adjustment compensation parameter group in the pre-transition phase of the steady-state interval after the temperature jump, and collecting the measurement data fluctuation characteristics in the transition phase in real time;

[0060] The pre-adjusted compensation parameter set is fine-tuned based on the fluctuation characteristics of the measurement data to generate a steady-state compensation parameter set and lock it to the nonlinear compensation curve.

[0061] An embodiment of the present invention also provides a temperature drift correction system for an intelligent monitoring instrument, comprising a processor, a memory connected to the processor, and a bus; wherein the processor and the memory communicate with each other via the bus; the processor is used to call program instructions in the memory to execute the above-mentioned temperature drift correction method for an intelligent monitoring instrument based on a temperature compensation algorithm.

[0062] An embodiment of the present invention further provides a computer-readable storage medium storing a program, which, when executed by a processor, implements the above-mentioned temperature drift correction method for an intelligent monitor based on a temperature compensation algorithm.

[0063] The embodiment of the present invention provides a temperature drift correction method and system for an intelligent monitoring instrument based on a temperature compensation algorithm, which achieves precise suppression of temperature drift noise and improvement of long-term stability through a multi-dimensional dynamic compensation mechanism. First, based on the real-time collected ambient temperature data and the preset temperature-drift characteristic model, the temperature drift characteristics of the sensor under the current working conditions are dynamically analyzed, and a nonlinear compensation curve adapted to the corresponding temperature distribution is generated, breaking through the linearization limitations of the traditional fixed compensation model. Secondly, an adaptive compensation parameter optimization algorithm is adopted to continuously iteratively optimize the compensation parameters so that the nonlinear compensation curve can dynamically track ambient temperature fluctuations and realize the adaptive evolution of the compensation strategy. In addition, the sensor aging factor is innovatively integrated into the parameter optimization process, and the characteristic deviation caused by device aging is synchronously compensated in the iterative correction, thereby constructing a synergistic suppression system for the dual interference of temperature drift and device aging. Through real-time correction processing, the optimized compensation parameter set is dynamically integrated with the original measurement data, effectively eliminating the nonlinear interference of temperature drift noise on the measurement results. At the same time, it overcomes the long-term compensation failure problem caused by ignoring device aging in traditional methods. Such a design can build a collaborative compensation mechanism that dynamically adapts to ambient temperature changes and device aging processes, significantly improving the measurement accuracy and stability in complex temperature field environments, avoiding the compensation lag caused by parameter solidification in conventional temperature drift correction technology, and realizing adaptive compensation calibration throughout the life cycle. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0065] Figure 1 The present invention provides a flow chart of a method for correcting temperature drift of an intelligent monitoring instrument based on a temperature compensation algorithm.

[0066] Figure 2 The present invention provides a block diagram of a temperature drift correction system for an intelligent monitoring instrument.

[0067] icon:

[0068] 100-Intelligent monitor temperature drift correction system;

[0069] 101 - processor; 102 - memory; 103 - bus. DETAILED DESCRIPTION

[0070] The exemplary embodiments disclosed herein will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0071] In order to better understand the above technical solution, the technical solution of the present invention is described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. In the absence of conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

[0072] Figure 1 This is a flow chart of a method for correcting temperature drift of an intelligent monitor based on a temperature compensation algorithm according to an embodiment of the present invention, which is applied to a temperature drift correction system of an intelligent monitor, and includes steps 101 to 104 .

[0073] Step 101: collecting ambient temperature data of the environment in which the intelligent monitor is located in real time, and obtaining a sensor aging factor preset in the intelligent monitor.

[0074] In an embodiment of the present invention, the intelligent monitor can be used in an industrial production workshop to monitor the equipment status. The operation of the equipment in this workshop is affected by the ambient temperature, so real-time ambient temperature data collection is required. The intelligent monitor is equipped with a high-precision temperature sensor that collects ambient temperature data every 10 seconds. For example, at a certain moment, the collected ambient temperature data may be 25°C, 25.2°C, 25.5°C, and so on, which constitutes an ambient temperature data sequence.

[0075] At the same time, the intelligent monitoring instrument is pre-installed with information related to the sensor aging factor. In an optional embodiment, obtaining the sensor aging factor pre-installed in the intelligent monitoring instrument includes:

[0076] Step 1011: Obtain the historical working hours and sensor aging weight distribution table of the intelligent monitoring instrument; wherein the sensor aging weight distribution table includes aging impact weights corresponding to different working time intervals, and the generation process of the sensor aging weight distribution table includes: obtaining historical data of multiple reference intelligent monitoring instruments during the aging test phase, the historical data including sensor performance attenuation indicators under different working hours; dividing the impact levels corresponding to different working time intervals according to the correlation between the sensor performance attenuation indicators and the temperature drift correction error; and allocating a corresponding aging impact weight to each working time interval based on the impact level to generate the sensor aging weight distribution table.

[0077] In the aforementioned industrial production workshop scenario, the smart monitor has been in use for a long time. The device management system can access the monitor's historical operating hours. For example, to generate a sensor aging weight distribution table, R&D personnel selected 10 reference smart monitors of the same model as the smart monitor and conducted aging tests. During the aging test, the sensor performance degradation indicators of these reference smart monitors were recorded at different operating times. For example, after 1000 hours of operation, the sensor measurement accuracy of one reference smart monitor decreased by 0.5%, while after 2000 hours of operation, the sensor response time of another reference smart monitor increased by 10%. Based on extensive experimental data and analysis, it was found that the greater the sensor performance degradation indicator, the greater the temperature drift correction error. Based on this correlation, different operating hours were defined, such as 0-1000 hours, 1001-2000 hours, and 2001-3000 hours. The impact level (low, medium, or high) was determined based on the degree of impact of sensor performance degradation on the temperature drift correction error within each interval. Finally, a corresponding aging impact weight is assigned to each working time interval. For example, the aging impact weight corresponding to 0-1000 hours is 0.1, the aging impact weight corresponding to 1001-2000 hours is 0.3, the aging impact weight corresponding to 2001-3000 hours is 0.5, and so on, thereby generating a sensor aging weight distribution table.

[0078] Optionally, in the actual application of intelligent monitoring instruments, the sensor aging weight allocation table is crucial for accurately evaluating and compensating for the impact of sensor aging on measurement results. It records in detail the aging impact weights corresponding to different working time intervals. These weights provide a key basis for subsequent accurate correction of sensor data under complex working conditions.

[0079] Generating a sensor aging weight distribution table first requires selecting multiple reference smart monitors of the same model as the actual smart monitors for aging testing. The purpose of selecting devices of the same model is to maximize the relevance and accuracy of the test results with actual applications. During the aging testing phase, these reference smart monitors are monitored over a long period of time, and detailed records of sensor performance degradation indicators at different operating times are recorded. These indicators cover multiple aspects, such as the decline in sensor measurement accuracy, which may manifest as a gradually increasing deviation between the measured value and the true value as the operating time increases; and the increase in sensor response time, which is the time from input signal to the sensor providing a valid output signal. For example, after 1000 hours of operation, the sensor measurement accuracy of a reference smart monitor decreased by 0.5%; after 2000 hours of operation, the sensor response time of another reference smart monitor increased by 10%.

[0080] After obtaining sensor performance degradation index data, we can identify the inherent correlation between the sensor performance degradation index and the temperature drift correction error: the greater the sensor performance degradation index, the greater the temperature drift correction error. Based on this, we can classify different operating time intervals into impact levels. This classification comprehensively considers the degree to which sensor performance degradation affects the temperature drift correction error, dividing the operating time interval into multiple levels. For example, 0-1000 hours may correspond to a low impact level, because at this stage, sensor performance degradation is relatively small, and the impact on the temperature drift correction error is also weak. 1001-2000 hours corresponds to a medium impact level, at which sensor performance degradation increases, and the impact on the temperature drift correction error is more significant. 2001-3000 hours and above correspond to a high impact level. As operating time increases, sensor performance degradation becomes more severe, and the impact on the temperature drift correction error becomes more prominent.

[0081] Finally, an aging impact weight is assigned based on the impact level corresponding to each operating time interval. The weighting principle is that the higher the impact level, the greater the weight. For example, the aging impact weight for 0-1000 hours might be 0.1, indicating that within this operating time interval, sensor aging has a relatively small impact on temperature drift correction. The aging impact weight for 1001-2000 hours is 0.3, indicating that the impact of sensor aging on temperature drift correction increases during this period. The aging impact weight for 2001-3000 hours is 0.5, reflecting the significant impact of sensor aging on temperature drift correction within this range. This allows the generation of a comprehensive and accurate sensor aging weight assignment table.

[0082] Step 1012: Match the corresponding aging impact weight from the sensor aging weight allocation table according to the historical working hours, and perform weighted processing on the baseline aging factor based on the aging impact weight to generate a dynamically updated sensor aging factor.

[0083] For example, in this embodiment of the present invention, if the intelligent monitoring instrument has a historical operating time of 5000 hours, the sensor aging weight distribution table shows that it is in the operating time range of "4001-5000 hours", and the corresponding aging impact weight for this range is 0.8. For example, if the baseline aging factor is 0.5, then through weighted processing, that is, multiplying the aging impact weight by the baseline aging factor, the dynamically updated sensor aging factor is 0.8 × 0.5 = 0.4.

[0084] Step 102: Based on the ambient temperature data and a preset temperature-drift characteristic model, the temperature drift characteristic of the intelligent monitor is extracted, and a nonlinear compensation curve matching the temperature drift characteristic is dynamically generated.

[0085] In the scenario of an industrial production workshop, the ambient temperature data collected by the intelligent monitor is constantly changing. In an optional embodiment, based on the ambient temperature data and a preset temperature-drift characteristic model, the temperature drift characteristics of the intelligent monitor are extracted, including:

[0086] Step 1021: Divide the ambient temperature data into multiple temperature data segments according to a preset time window, and perform temperature fluctuation trend analysis on each temperature data segment to obtain the temperature change rate and temperature fluctuation amplitude of each temperature data segment.

[0087] If the preset time window is set to 60 seconds, the collected ambient temperature data will be divided into multiple 60-second temperature data segments. For example, the data collected in the first temperature data segment is 25°C, 25.2°C, 25.5°C, 25.8°C, and 26°C. To calculate the temperature change rate, subtract the first temperature value from the last temperature value in the data segment, and then divide it by the 60-second time interval, that is, (26-25) ÷ 60 ≈ 0.0167°C / second, to obtain the temperature change rate for the temperature data segment. The temperature fluctuation amplitude is calculated by subtracting the lowest temperature value from the highest temperature value in the data segment, that is, 26-25 = 1°C, to obtain the temperature fluctuation amplitude. Similar calculations are performed for each temperature data segment divided in this way, resulting in a series of temperature change rates and temperature fluctuation amplitudes.

[0088] Step 1022: Call the temperature-drift characteristic model, perform nonlinear correlation mapping processing on the temperature change rate and the temperature fluctuation amplitude, and generate the temperature drift characteristic of the intelligent monitor; the temperature drift characteristic includes a first mapping relationship between the temperature change rate and the drift amount, and a second mapping relationship between the temperature fluctuation amplitude and the drift amount.

[0089] Optionally, the temperature-drift characteristic model is established based on a large amount of experimental data and analysis. In an embodiment of the present invention, the calculated temperature change rate and temperature fluctuation amplitude of each temperature data segment are input into the model. For example, for a data segment with a temperature change rate of 0.0167°C / second and a temperature fluctuation amplitude of 1°C, the first mapping relationship between the temperature change rate and the drift amount is obtained through the nonlinear association mapping processing of the model. For example, under this model, when the temperature change rate is 0.0167°C / second, the corresponding drift amount is 0.05; at the same time, the second mapping relationship between the temperature fluctuation amplitude and the drift amount is obtained. When the temperature fluctuation amplitude is 1°C, the corresponding drift amount is 0.1. These mapping relationships together constitute the temperature drift characteristics of the intelligent monitor.

[0090] In an optional embodiment, the dynamically generating a nonlinear compensation curve matching the temperature drift characteristic includes:

[0091] Step 1023: According to the first mapping relationship, map the temperature change rate into a corresponding first drift component, and according to the second mapping relationship, map the temperature fluctuation amplitude into a corresponding second drift component; wherein the first drift component and the second drift component are dimensionless relative change rates obtained after normalization processing.

[0092] For the previously obtained temperature change rate of 0.0167°C / second, the corresponding drift is 0.05. For example, if the maximum temperature change rate during the entire monitoring process is 0.1°C / second and the minimum is 0°C / second, then through normalization, the first drift component = (0.0167-0) ÷ (0.1-0) = 0.167. For a temperature fluctuation amplitude of 1°C, the corresponding drift is 0.1. For example, if the maximum temperature fluctuation amplitude is 3°C and the minimum is 0°C, then the second drift component = (1-0) ÷ (3-0) = 0.333. This gives the dimensionless first and second drift components after normalization.

[0093] Step 1024: Input the first drift component and the second drift component into a preset compensation curve generation function, and obtain initial compensation parameters through nonlinear weighted fusion calculation.

[0094] The preset compensation curve generation function takes into account the different degrees of influence of the first and second drift components, setting the weight of the first drift component to 0.4 and the weight of the second drift component to 0.6. In the nonlinear weighted fusion calculation, the first drift component of 0.167 and the second drift component of 0.333 are first multiplied by their respective weights: 0.167 × 0.4 = 0.0668 and 0.333 × 0.6 = 0.1998, respectively. These two results are then added together: 0.0668 + 0.1998 = 0.2666, to obtain the initial compensation parameters.

[0095] Among them, the updating process of the preset compensation curve generating function includes: monitoring the average correction error of the nonlinear compensation curve within a preset time period, and judging whether the average correction error exceeds the dynamic adjustment threshold; if it exceeds, adjusting the coefficient of the nonlinear relationship expression in the compensation curve generating function according to the distribution characteristics of the average correction error; and reapplying the adjusted compensation curve generating function to the subsequent temperature drift characteristic processing to achieve adaptive updating of the nonlinear compensation curve.

[0096] In an embodiment of the present invention, the preset time period is set to 1 hour. The average correction error of the nonlinear compensation curve within the time period is calculated once every hour. For example, within a certain hour, after the measurement data of the intelligent monitor is corrected by the nonlinear compensation curve, the average correction error is calculated to be 0.2. For example, the dynamic adjustment threshold is 0.15. Since 0.2 exceeds 0.15, the distribution characteristics of the average correction error are analyzed at this time, and it is found that the error is mainly concentrated in the area with a large temperature change rate. Based on this characteristic, the coefficients of the nonlinear relationship expression related to the temperature change rate in the compensation curve generation function are adjusted. For example, the coefficient related to the first drift component is increased to enhance the compensation capability for the case of a large temperature change rate. After the adjustment, the new compensation curve generation function is applied to the subsequent processing of temperature drift characteristics.

[0097] In more detail, the updating process of the preset compensation curve generation function is a dynamic and adaptive mechanism designed to ensure that the nonlinear compensation curve can always accurately adapt to the temperature drift characteristics of the smart monitor in different environments, thereby improving the accuracy and stability of the measurement data.

[0098] Firstly, the system continuously and accurately monitors the average correction error of the nonlinear compensation curve within a preset time period. The setting of the preset time period needs to consider various factors, such as the frequency of change of measurement data, the stability of environmental temperature, and the requirements of actual application on measurement accuracy, etc. In the embodiment of the present application, the preset time period is set to 1 hour (which can timely capture the change of correction effect of the compensation curve, and does not perform calculation and adjustment too frequently). Every 1 hour, the system automatically collects all error data of the measurement data of the intelligent monitor corrected by the nonlinear compensation curve in the time period, and calculates the average correction error, which reflects the average deviation degree between the measurement data and the true value after the temperature drift is compensated by the nonlinear compensation curve in the time period.

[0099] Then, the calculated average correction error is compared with the dynamic adjustment threshold value. The dynamic adjustment threshold value is not a fixed value, and it is dynamically adjusted according to the use environment of the intelligent monitor, the measurement requirements, and the long-term monitoring data feedback, etc. For example, in the industrial production scene with high requirements on measurement accuracy, the dynamic adjustment threshold value may be set relatively low to ensure the high accuracy of measurement data; and in some scenes with relatively loose requirements on accuracy, the threshold value can be appropriately increased. If the average correction error exceeds the dynamic adjustment threshold value, it indicates that the nonlinear compensation curve generated by the current compensation curve generation function may not be able to effectively compensate the temperature drift, and the error of the measurement data exceeds the acceptable range, so the compensation curve generation function needs to be adjusted.

[0100] When the average correction error exceeds the dynamic adjustment threshold value, the system analyzes the distribution characteristics of the average correction error, for example, by classifying and counting the error data according to factors such as temperature change rate and temperature fluctuation amplitude, to find out in which areas or situations the error is mainly concentrated. If it is determined that the error is mainly concentrated in the area with large temperature change rate, it indicates that the current compensation curve generation function is insufficient in compensating the temperature drift caused by rapid temperature change; or the error is concentrated in the area with large temperature fluctuation amplitude, which indicates that the compensation curve is not good at dealing with large amplitude temperature fluctuation.

[0101] According to the distribution characteristics of the average correction error, the system adjusts the coefficients of the nonlinear relationship expression in the compensation curve generation function, which determines the sensitivity and compensation ability of the compensation curve generation function to different factors. For example, if it is found that the error is mainly concentrated in the area with large temperature change rate, then the coefficient of the nonlinear relationship expression related to temperature change rate is increased, so as to enhance the compensation ability of the compensation curve generation function to the case with large temperature change rate, so that the generated nonlinear compensation curve can more effectively correct the measurement data when facing rapid temperature change, and reduce the error.

[0102] Furthermore, the adjusted compensation curve generation function will be reapplied to the subsequent processing of temperature drift characteristics. During the subsequent processing, the new compensation curve generation function will generate a nonlinear compensation curve that is more in line with the actual situation based on the real-time collected ambient temperature data and the temperature drift characteristics obtained from the latest analysis. This new nonlinear compensation curve will provide more accurate differentiated compensation amounts within different temperature fluctuation ranges, thereby achieving adaptive updating of the nonlinear compensation curve. For example, in a range with relatively gentle temperature fluctuations, the compensation curve may use a relatively gentle function relationship for compensation; while in a range with drastic temperature fluctuations, the compensation curve will use a more aggressive function relationship based on the adjusted coefficient to enhance the compensation effect. Through the above-mentioned adaptive update mechanism, the nonlinear compensation curve can better adapt to the ever-changing ambient temperature, effectively suppress the impact of temperature drift on the measurement data, and ensure that the intelligent monitor can always provide accurate and stable measurement results in complex temperature environments, meeting the strict measurement accuracy requirements of actual application scenarios such as industrial production.

[0103] Step 1025: Dynamically adjust the initial compensation parameters according to the model parameters in the temperature-drift characteristic model to generate adjusted compensation parameters.

[0104] The temperature-drift characteristic model has some fixed parameters, such as the model's scaling factor. In this embodiment of the present invention, for example, a scaling factor of 1.2 is used. The initial compensation parameter, 0.2666, is multiplied by this scaling factor (0.2666 × 1.2 = 0.31992), yielding the adjusted compensation parameter.

[0105] Step 1026: constructing a piecewise continuous nonlinear compensation curve based on the adjusted compensation parameters, wherein the nonlinear compensation curve is used to provide differentiated compensation amounts within different temperature fluctuation ranges.

[0106] Within the ambient temperature range of an industrial production workshop, different temperature ranges are divided according to temperature fluctuations, such as 20-25°C and 25-30°C. Based on the adjusted compensation parameter of 0.31992 and the characteristics of different temperature ranges, a piecewise continuous nonlinear compensation curve is constructed. For example, within the 20-25°C range, the compensation amount corresponding to different temperature points within the range is calculated based on the compensation parameter according to a preset functional relationship (such as a quadratic function). Within the 25-30°C range, another functional relationship (such as an exponential function) is used to calculate the compensation amount, thus constructing a nonlinear compensation curve that provides differentiated compensation amounts within different temperature fluctuation ranges.

[0107] Step 103: Adopting an adaptive compensation parameter optimization algorithm, performing iterative optimization processing on the compensation parameters of the nonlinear compensation curve, and integrating the sensor aging factor in the iterative optimization process to dynamically correct the compensation parameters to obtain an optimized compensation parameter set.

[0108] In this industrial monitoring scenario, the adaptive compensation parameter optimization algorithm continuously adjusts the compensation parameters. In an optional embodiment, the adaptive compensation parameter optimization algorithm is used to iteratively optimize the compensation parameters of the nonlinear compensation curve, including:

[0109] Step 1031: Obtain a temperature drift correction error in a current iteration cycle, and compare the temperature drift correction error with a preset error threshold.

[0110] For example, the current iteration cycle is the fifth iteration. During this cycle, after correcting the measurement data of the intelligent monitor using the nonlinear compensation curve, the calculated temperature drift correction error is 0.18. The preset error threshold is 0.15.

[0111] Step 1032: If the temperature drift correction error is greater than the preset error threshold, adjust the parameter values ​​in the compensation parameter set according to the error gradient direction to generate an updated compensation parameter set.

[0112] Since 0.18 is greater than 0.15, the parameter values ​​in the compensation parameter set are adjusted based on the direction of the error gradient, that is, the direction of increasing error. For example, if the compensation parameter set contains parameters a, b, and c, analyzing the error gradient reveals that parameter a has a greater impact on the error and needs to be increased as the error increases. For another example, if the original value of a is 0.5, the error gradient calculation will increase the value of a to 0.6, thus generating an updated compensation parameter set.

[0113] Step 1033: re-input the updated compensation parameter set into the nonlinear compensation curve for parameter verification until the temperature drift correction error is less than or equal to the preset error threshold.

[0114] Input the updated compensation parameter set into the nonlinear compensation curve and calibrate the intelligent monitor's measurement data again to calculate the new temperature drift correction error. If the new error is still greater than the preset error threshold, continue adjusting the parameters according to the above steps until the temperature drift correction error is less than or equal to 0.15.

[0115] In an optional embodiment, the sensor aging factor is integrated into the iterative optimization process to dynamically modify the compensation parameters to obtain an optimized compensation parameter set, including:

[0116] Step 10341: Divide the preset sensor aging factor value intervals according to the value of the sensor aging factor, and configure a corresponding compensation parameter correction weight for each sensor aging factor value interval.

[0117] In the embodiment of the present invention, the sensor aging factor is 0.4. According to pre-settings, the sensor aging factor value intervals are divided into 0-0.2, 0.2-0.4, 0.4-0.6, etc. For the 0.2-0.4 interval, the configured compensation parameter correction weight is 0.3.

[0118] Step 10342: Extract the offset compensation parameters and temperature drift slope compensation parameters in the current iteration cycle from the compensation parameter set, and decompose the offset compensation parameters and temperature drift slope compensation parameters into independent parameter components according to parameter type; wherein the independent parameter components are dimensionless standardized parameter components obtained after completing the dedimensionalization processing.

[0119] Optionally, the compensation parameter set includes an offset compensation parameter x and a temperature drift slope compensation parameter y. x is decomposed into independent parameter components such as x1 and x2 according to parameter type, and y is decomposed into independent parameter components such as y1 and y2. For example, if the original value of x is 10 (in the unit of a certain physical quantity), through dedimensionalization, the maximum value of the physical quantity is set to 100 and the minimum value is set to 0. Then, the standardized value x1 = (10-0) ÷ (100-0) = 0.1, and similar processing is performed on x2 and other parameters. If the original value of y is 0.5 (in the unit of another physical quantity), the maximum value of the physical quantity is set to 1 and the minimum value is set to 0. Then, the standardized value y1 = (0.5-0) ÷ (1-0) = 0.5, and similar processing is performed on y2 and other parameters.

[0120] Step 10343: Match the corresponding compensation parameter correction weight according to the sensor aging factor value interval in which the sensor aging factor is located, and distribute the compensation parameter correction weight to each independent parameter component.

[0121] Since the sensor aging factor of 0.4 is in the range of 0.2-0.4, the corresponding compensation parameter correction weight in this range is 0.3. This weight is distributed to each independent parameter component, that is, the correction weight of x1 is 0.3, the correction weight of x2 is 0.3, the correction weight of y1 is 0.3, the correction weight of y2 is 0.3, and so on.

[0122] Step 10344: Based on the parameter change direction of each independent parameter component, perform a directional weighted operation on the allocated compensation parameter correction weight to generate an aging correction component corresponding to each independent parameter component.

[0123] For example, if the parameter x1 changes in an increasing direction and the parameter y1 changes in a decreasing direction, the aging correction component for x1 = 0.3 × 1 (the weight in the increasing direction is set to 1) = 0.3; the aging correction component for y1 = 0.3 × (-1) (the weight in the decreasing direction is set to -1) = -0.3.

[0124] Step 10345: Add the aging correction component to the corresponding independent parameter component to generate a corrected offset compensation parameter component and a corrected temperature drift slope compensation parameter component.

[0125] For x1, the corrected x1=0.1+0.3=0.4; for y1, the corrected y1=0.5-0.3=0.2. And so on, all the corrected offset compensation parameter components and corrected temperature drift slope compensation parameter components are obtained.

[0126] Step 10346: Recombining the corrected offset compensation parameter component and the corrected temperature drift slope compensation parameter component according to parameter type to generate a dynamically corrected compensation parameter set.

[0127] The corrected x1, x2, etc. are recombined into offset compensation parameters, and the corrected y1, y2, etc. are recombined into temperature drift slope compensation parameters, thereby generating a dynamically corrected compensation parameter set.

[0128] Step 10347: Input the dynamically corrected compensation parameter set into the nonlinear compensation curve for parameter verification, and obtain the verified temperature drift correction error.

[0129] The dynamically corrected compensation parameter set is input into the nonlinear compensation curve, and the measurement data of the intelligent monitor is corrected to calculate and obtain a verified temperature drift correction error, for example, 0.12.

[0130] Step 10348: According to the error distribution characteristics of the verified temperature drift correction error, reversely adjust the compensation parameter correction weight corresponding to the sensor aging factor value interval to generate an updated compensation parameter correction weight table.

[0131] Analysis of the error distribution characteristics of the verified temperature drift correction error of 0.12 revealed that while adjustments to all parameters produced good results, adjustments to other parameters produced poor results. Based on this information, the compensation parameter correction weights corresponding to the sensor aging factor range were adjusted in the opposite direction. For example, for the 0.2-0.4 range, the compensation parameter correction weight was adjusted from 0.3 to 0.4, generating an updated compensation parameter correction weight table.

[0132] Step 10349: Dynamically revise the weight distribution of the independent parameter components of the next iteration cycle based on the updated compensation parameter correction weight table to generate an optimized compensation parameter set.

[0133] In the next iteration cycle, the compensation parameter correction weight table is updated, the correction weights are reallocated to the independent parameter components, and the parameter adjustment is continued to generate the optimized compensation parameter set.

[0134] Step 104: performing real-time correction processing on the original measurement data of the intelligent monitoring instrument according to the optimized compensation parameter set, and outputting a target measurement result after suppressing temperature drift noise.

[0135] In industrial production workshops, smart monitors continuously collect various data from equipment. These raw measurement data are affected by temperature drift. In an optional embodiment, the raw measurement data of the smart monitor is corrected in real time according to the optimized compensation parameter set, and the target measurement result with temperature drift noise suppressed is output, including:

[0136] Step 1041: Divide the original measurement data into multiple time-synchronized measurement data segments according to the acquisition timestamp, and the time range of each measurement data segment corresponds to the time range of the ambient temperature data segment one by one.

[0137] The raw measurement data collected by the smart monitor involves multiple parameters such as the vibration amplitude and current intensity of the equipment. For example, the data collected about the vibration amplitude is a series of values, such as 10 (unit: mm), 10.2, 10.5, etc., and the acquisition timestamp of each data is recorded. These raw measurement data are divided into multiple measurement data segments according to the same time window (such as 60 seconds) as the ambient temperature data segment. The first measurement data segment contains the vibration amplitude data 10, 10.2, and 10.5 collected within a certain 60 seconds. The second measurement data segment contains the data collected within the next 60 seconds, and so on. The time range of each measurement data segment strictly corresponds to the time range of the previously divided ambient temperature data segment.

[0138] Step 1042: Match a corresponding compensation parameter group from the optimized compensation parameter set according to the time range of the ambient temperature data segment, and assign the compensation parameter group to the time-synchronized measurement data segment.

[0139] For a specific time range of ambient temperature data, such as the time range from 10:00:00 to 10:01:00, a corresponding compensation parameter set is found from the optimized compensation parameter set. For example, a compensation parameter set containing an offset correction factor of 0.5 and a temperature drift slope of 0.2 is assigned to the corresponding time range of the measurement data segment, namely, the raw measurement data segment of vibration amplitude, collected from 10:00:00 to 10:01:00.

[0140] Step 1043: Based on the offset correction coefficient and the temperature drift slope in the compensation parameter group, perform a linear compensation operation on each measurement value in the time-synchronized measurement data segment to generate a compensated measurement data sequence.

[0141] For each vibration amplitude measurement value in a measurement data segment assigned to a compensation parameter group, for example, a measurement value of 10 (unit: mm), a linear compensation operation is performed. The compensation formula is: Compensated value = measured value + offset correction factor + temperature drift slope × (current ambient temperature - reference temperature). For example, if the current ambient temperature is 25°C and the reference temperature is 20°C, then for a measurement value of 10, the compensated value = 10 + 0.5 + 0.2 × (25 - 20) = 10 + 0.5 + 1 = 11.5 (unit: mm). This operation is performed on each measurement value in this measurement data segment to generate a compensated measurement data sequence, such as 11.5, 11.7, 12, and so on.

[0142] Step 1044: Perform sliding window mean filtering on the compensated measurement data sequence, calculate the average value of the measurement data in each window according to the preset window length and overlapping step length, and generate a filtered measurement data sequence.

[0143] The preset window length is 5, and the overlap step is 2. For the compensated measurement data sequence 11.5, 11.7, 12, 12.2, 12.5, 12.8, ..., the first window includes 11.5, 11.7, 12, 12.2, and 12.5, and the average is calculated as (11.5 + 11.7 + 12 + 12.2 + 12.5) ÷ 5 = 12. The second window, starting from the second data point, includes 11.7, 12, 12.2, 12.5, and 12.8, and the average is calculated as (11.7 + 12 + 12.2 + 12.5 + 12.8) ÷ 5 = 12.24. This sliding window mean filtering process generates filtered measurement data sequences such as 12, 12.24, and 12.48.

[0144] Step 1045: Merge the filtered measurement data sequences in the order of timestamps, remove measurement data corresponding to duplicate timestamps, and generate the target measurement result after suppressing temperature drift noise.

[0145] The filtered measurement data sequences are merged in the order of their acquisition timestamps. During the merging process, if duplicate timestamps are found, only one is retained. For example, if two measurement data with the timestamp 10:00:30 are found during the merging process, only one is retained. This process ultimately generates the target measurement results after suppressing temperature drift noise. These results more accurately reflect the actual device status and reduce the impact of temperature drift on the measurement data.

[0146] In a non-limiting embodiment, after outputting the target measurement result after suppressing temperature drift noise, the method further includes:

[0147] Step 201: Retrieve a historical temperature drift correction data set that matches the current ambient temperature data from a historical database, extract the corresponding historical compensation parameter set and historical correction results, compare the parameter differences between the historical compensation parameter set and the optimized compensation parameter set, identify abnormal compensation parameter components that deviate from a preset reference range, and construct a parameter error transmission link based on the residual distribution characteristics of the historical correction results and the target measurement results to locate the error source direction of the abnormal compensation parameter component.

[0148] In an industrial production workshop scenario, a historical database stores temperature drift correction data for different ambient temperatures over a period of time. Based on the current ambient temperature data, for example, 25°C, a historical temperature drift correction dataset for ambient temperatures between 24°C and 26°C is retrieved from the historical database. A historical compensation parameter set is extracted from this dataset. For example, a parameter in the historical compensation parameter set is 0.4, while the corresponding parameter in the optimized compensation parameter set is 0.6. A comparison reveals that this parameter deviates from the preset reference range, which is set to 0.3-0.5. Simultaneously, historical correction results are extracted and compared with the current target measurement results to calculate residual distribution characteristics. For example, if large residuals are found at some measurement points, the residual distribution is analyzed, combined with historical data and current compensation parameter settings, and a parameter error transmission chain is constructed. It is determined that the error in this abnormal compensation parameter component may be due to inaccurate parameter adjustment of the temperature-drift characteristic model in the current temperature range.

[0149] Step 202: Perform a gradient descent compensation operation on the abnormal compensation parameter component according to the direction of the error source to generate a reverse-corrected compensation parameter component, re-fit the reverse-corrected compensation parameter component with the current ambient temperature data, generate a feedback-corrected compensation parameter set, and update it to the nonlinear compensation curve.

[0150] Based on the direction of the previously located error source, a gradient descent compensation operation is performed on the abnormal compensation parameter component. For example, for a deviated compensation parameter of 0.6, the gradient descent algorithm is used to calculate the gradient direction, which indicates that the parameter needs to be reduced. Using a preset step size (set to 0.1), the parameter is reduced to 0.6 - 0.1 = 0.5. This reverse-corrected compensation parameter component 0.5 is refitted to the current ambient temperature data of 25°C, taking into account factors such as the temperature change rate and the temperature fluctuation amplitude to generate a feedback-corrected compensation parameter set. For example, after fitting, a new set of compensation parameters is obtained, which is then updated to the nonlinear compensation curve, making the nonlinear compensation curve more adaptable to actual conditions and improving the ability to correct temperature drift.

[0151] In a non-limiting embodiment, after outputting the target measurement result after suppressing temperature drift noise, the method further includes:

[0152] Step 301: monitor the instantaneous change gradient of subsequent ambient temperature data in real time, generate a temperature transition event identifier when the instantaneous change gradient exceeds a mutation threshold, extract the temperature mean difference between the steady-state interval before the temperature transition and the steady-state interval after the transition corresponding to the temperature transition event identifier, and determine the product result of the temperature mean difference and the preset transition temperature difference compensation coefficient, dynamically adjust the temperature drift slope parameter in the optimized compensation parameter set according to the product result, and generate a pre-adjusted compensation parameter group.

[0153] In industrial production workshops, the instantaneous gradient of ambient temperature data is continuously monitored in real time. For example, if the ambient temperature data is 25°C, 25.2°C, 25.5°C, 26°C, 28°C, 30°C, etc., the gradient of two adjacent temperature values ​​is calculated, such as (25.2-25) ÷ (measurement interval time), (25.5-25.2) ÷ (measurement interval time), etc. For example, the mutation threshold is 0.5°C / minute. When the instantaneous gradient at a certain moment exceeds this threshold, such as a rapid increase from 26°C to 28°C with a gradient exceeding 0.5°C / minute, a temperature jump event flag is generated. Next, the temperature difference between the steady-state interval before the temperature transition (for example, 25°C-26°C) and the steady-state interval after the transition (for example, 28°C-30°C) corresponding to the temperature transition event identifier is extracted. The mean temperature of the steady-state interval before the transition is (25 + 26) ÷ 2 = 25.5°C, and the mean temperature of the steady-state interval after the transition is (28 + 30) ÷ 2 = 29°C, resulting in a mean temperature difference of 29 - 25.5 = 3.5°C. The preset transition temperature difference compensation coefficient is set to 0.2, and the calculated product is 3.5 × 0.2 = 0.7. Based on this product, the temperature drift slope parameter in the optimized compensation parameter set is dynamically adjusted. For example, if the original temperature drift slope parameter is 0.3, it will be adjusted to 0.3 + 0.7 = 1, thus generating the pre-adjusted compensation parameter set.

[0154] Step 302: Load the pre-adjustment compensation parameter group in the pre-transition stage of the steady-state interval after the temperature jump, and collect the measurement data fluctuation characteristics of the transition stage in real time, fine-tune the pre-adjustment compensation parameter group based on the measurement data fluctuation characteristics, generate a steady-state compensation parameter group and lock it to the nonlinear compensation curve.

[0155] During the pre-transition phase (for example, from 26°C to 28°C) in the steady-state range after a temperature jump (e.g., 28°C-30°C), a pre-adjusted compensation parameter set is loaded. During this transition phase, measurement data fluctuation characteristics are collected in real time, such as fluctuations in equipment vibration amplitude, current intensity, and other measurements. For example, if significant fluctuations in vibration amplitude measurements are observed, analysis of these fluctuations reveals that the current pre-adjusted compensation parameter set is not effectively suppressing these fluctuations. Based on the analysis results, the pre-adjusted compensation parameter set is fine-tuned, for example, by adjusting the offset correction factor from 0.5 to 0.6. After fine-tuning, a steady-state compensation parameter set is generated and locked to the nonlinear compensation curve. This allows the nonlinear compensation curve to better calibrate the measurement data under the new temperature jump, further improving the accuracy and stability of the intelligent monitor's measurement data, effectively suppressing the impact of temperature drift noise on measurement results, and ensuring the reliability of equipment condition monitoring in industrial production workshops.

[0156] The embodiment of the present application realizes accurate suppression of temperature drift noise and long-term stability improvement through a multi-dimensional dynamic compensation mechanism. First, based on the real-time collected environmental temperature data and the pre-set temperature-drift characteristic model, the temperature drift characteristics of the sensor under the current working condition are dynamically analyzed, a nonlinear compensation curve suitable for the corresponding temperature distribution is generated, and the linearization limitation of the traditional fixed compensation model is broken through. Secondly, an adaptive compensation parameter optimization algorithm is used, the compensation parameters are continuously iteratively optimized, the nonlinear compensation curve can dynamically track the environmental temperature fluctuation, and the adaptive evolution of the compensation strategy is realized. In addition, the sensor aging factor is innovatively integrated into the parameter optimization process, the characteristic deviation caused by device aging is compensated synchronously in the iterative correction, and a cooperative suppression system of temperature drift and device aging is constructed. Through real-time correction processing, the optimized compensation parameter set is dynamically fused with the original measurement data, the nonlinear interference of the temperature drift noise on the measurement result is effectively eliminated, and the long-term compensation failure problem caused by ignoring device aging in the traditional method is overcome. In this way, a cooperative compensation mechanism that dynamically adapts to environmental temperature changes and device aging process can be constructed, the measurement accuracy stability in a complex temperature field environment is significantly improved, the compensation lag caused by parameter solidification in the conventional temperature drift correction technology is avoided, and adaptive compensation calibration in the whole life cycle is realized.

[0157] The embodiment of the present application provides a computer readable storage medium, which stores a program, and the program is executed by a processor to realize the intelligent monitor temperature drift correction method based on the temperature compensation algorithm.

[0158] The embodiment of the present application provides a processor, which is used for running a program, wherein the program is executed to perform the intelligent monitor temperature drift correction method based on the temperature compensation algorithm.

[0159] As shown in the embodiment of the present application, Figure 2 The intelligent monitor temperature drift correction system 100 includes at least one processor 101, at least one memory 102 connected with the processor 101, and a bus 103; wherein the processor 101 and the memory 102 complete mutual communication through the bus 103; the processor 101 is used for calling program instructions in the memory 102 to execute the intelligent monitor temperature drift correction method based on the temperature compensation algorithm.

[0160] The application is described with reference to the flowchart and / or block diagrams of the methods, the intelligent monitor temperature drift correction system (system), and the computer program product according to embodiments of the application. It will be understood that each block of the flowchart and / or block diagrams, and combinations of blocks in the flowchart and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks.

[0161] In one typical arrangement, the intelligent monitor temperature drift correction system includes one or more processors (CPUs), memory, and buses. The intelligent monitor temperature drift correction system can also include input / output interfaces, network interfaces, and the like.

[0162] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) about which the processor can read instructions stored in memory to execute application programs, device drivers, and the like. The memory can also include non-volatile memory, such as read only memory (ROM) about which the processor can read instructions stored in memory to execute application programs, device drivers, and the like. The memory includes at least one memory chip.

[0163] Computer readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for storage of information. The information can be computer readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital versatile discs (DVDs) or other optical storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage computer readable storage media, or any other non-transitory medium that can be used to store information that can be accessed by the intelligent monitor temperature drift correction system. According to the definition herein, computer readable media does not include transitory media, such as modulated data signals and carrier waves.

[0164] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or computer-readable storage medium that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, commodity, or computer-readable storage medium. In the absence of further limitations, an element defined by the phrase "comprises a..." does not preclude the presence of additional identical elements in the process, method, commodity, or computer-readable storage medium that includes the element.

[0165] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code.

[0166] The above are merely embodiments of the present invention and are not intended to limit the present invention. It will be apparent to those skilled in the art that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention are intended to be included within the scope of the claims of the present invention.

[0167] In the technical solutions involved in the above-mentioned embodiments of the present invention, whether it is performing comparison calculations of multi-dimensional features or constructing composite parameters, if there are problems caused by significant differences in the number of dimensions, dimensional units and semantic meanings of different features, technical personnel in this field, based on their professional knowledge and past practical experience, are fully able to understand that these differences need to be properly handled so that the calculation results are accurate and comparable, and avoid situations such as logical confusion and unclear mathematical meaning.

[0168] In detail, when faced with features with different numbers of dimensions, in order to accurately calculate the similarity, matching degree or feature distance between different features, technical personnel in this field can use a variety of strategies, such as feature selection, feature extraction, kernel function and other strategies for adaptive processing.

[0169] When processing the comparison of multi-dimensional features, in order to achieve comparable alignment of feature spaces, those skilled in the art may adopt a variety of existing general technical means, including but not limited to the following existing technologies: standardization preprocessing, mapping conversion, space projection, etc.

[0170] In the process of constructing composite parameters (such as loss function values), different parameter items often have different dimensions. Those skilled in the art can adopt existing normalization processing or adaptive weight allocation mechanism based on distribution characteristics.

[0171] The general technical approaches described above for solving the feature matching and loss balancing problems are common knowledge in the field. These techniques have been fully validated and widely used in numerous practical applications, and those skilled in the art can skillfully and flexibly apply these methods to address similar dimensional discrepancies.

[0172] The formulas and calculation processes involved in the embodiments of the present invention, whether used for multi-dimensional feature comparison or composite loss function construction, strictly follow the principle of dimensional correspondence. The variables in each formula have clear and definite physical meanings, and their operation logic is also fully consistent with basic mathematical and physical logic. The operation results must be the reasonable results expected by the present invention. Those skilled in the art have the ability to comprehensively apply the above-mentioned general technical means according to specific data conditions and business needs, and effectively solve the various problems caused by the number of dimensions, dimensional differences, etc. in the multi-dimensional feature comparison calculation and composite loss function construction in the embodiments, and ensure the accuracy, reliability and feasibility of the technical solution of the present invention.

Claims

1. A temperature drift correction method for an intelligent monitor based on a temperature compensation algorithm, characterized in that: include: Collecting ambient temperature data of the environment in which the intelligent monitor is located in real time, and obtaining a sensor aging factor preset in the intelligent monitor; Based on the ambient temperature data and a preset temperature-drift characteristic model, the temperature drift characteristic of the intelligent monitor is extracted: the ambient temperature data is divided into a plurality of temperature data segments according to a preset time window, and a temperature fluctuation trend analysis is performed on each temperature data segment to obtain a temperature change rate and a temperature fluctuation amplitude of each temperature data segment; The temperature-drift characteristic model is invoked to perform nonlinear correlation mapping processing on the temperature change rate and the temperature fluctuation amplitude to generate a temperature drift characteristic of the intelligent monitor. The temperature drift characteristic includes a first mapping relationship between the temperature change rate and the drift amount, and a second mapping relationship between the temperature fluctuation amplitude and the drift amount. A nonlinear compensation curve matching the temperature drift characteristic is dynamically generated: the temperature change rate is mapped into a corresponding first drift component according to the first mapping relationship, and the temperature fluctuation amplitude is mapped into a corresponding second drift component according to the second mapping relationship. The first drift component and the second drift component are dimensionless relative change rates obtained after normalization. The first drift component and the second drift component are input into a preset compensation curve generation function, and initial compensation parameters are obtained through nonlinear weighted fusion calculation. The initial compensation parameters are dynamically adjusted according to model parameters in the temperature-drift characteristic model to generate adjusted compensation parameters. A piecewise continuous nonlinear compensation curve is constructed based on the adjusted compensation parameters, and the nonlinear compensation curve is used to provide differentiated compensation amounts within different temperature fluctuation ranges. Adopting an adaptive compensation parameter optimization algorithm, the compensation parameters of the nonlinear compensation curve are iteratively optimized, and the sensor aging factor is integrated in the iterative optimization process to dynamically correct the compensation parameters to obtain an optimized compensation parameter set: the preset sensor aging factor value interval is divided according to the value of the sensor aging factor, and a corresponding compensation parameter correction weight is configured for each sensor aging factor value interval; the offset compensation parameter and the temperature drift slope compensation parameter in the current iteration cycle are extracted from the compensation parameter set, and the offset compensation parameter and the temperature drift slope compensation parameter are decomposed into independent parameter components according to the parameter type; wherein the independent parameter component is a dimensionless standardized parameter component obtained after completing the dedimensionalization process; according to the sensor aging factor value interval in which the sensor aging factor is located, the corresponding compensation parameter correction weight is matched, and the compensation parameter correction weight is distributed to each independent parameter component; based on the parameter of each independent parameter component According to the direction of change of the number, a directional weighted operation is performed on the allocated compensation parameter correction weight to generate an aging correction component corresponding to each independent parameter component; the aging correction component is superimposed on the corresponding independent parameter component to generate a corrected offset compensation parameter component and a corrected temperature drift slope compensation parameter component; the corrected offset compensation parameter component and the corrected temperature drift slope compensation parameter component are recombined according to parameter type to generate a dynamically corrected compensation parameter set; the dynamically corrected compensation parameter set is input into the nonlinear compensation curve for parameter verification to obtain a verified temperature drift correction error; according to the error distribution characteristics of the verified temperature drift correction error, the compensation parameter correction weight corresponding to the sensor aging factor value interval is reversely adjusted to generate an updated compensation parameter correction weight table; based on the updated compensation parameter correction weight table, dynamic correction weight allocation is performed on the independent parameter components of the next iteration cycle to generate an optimized compensation parameter set; The original measurement data of the intelligent monitor is corrected in real time according to the optimized compensation parameter set, and a target measurement result with temperature drift noise suppressed is output.

2. The method according to claim 1, wherein The updating process of the preset compensation curve generating function includes: monitoring an average correction error of the nonlinear compensation curve within a preset time period, and determining whether the average correction error exceeds a dynamic adjustment threshold; If it exceeds, adjusting the coefficients of the nonlinear relationship expression in the compensation curve generating function according to the distribution characteristics of the average correction error; The adjusted compensation curve generating function is reapplied to subsequent temperature drift characteristic processing to achieve adaptive updating of the nonlinear compensation curve.

3. The method according to claim 1, wherein The obtaining of the sensor aging factor preset in the intelligent monitoring instrument includes: Obtaining a historical operating time and sensor aging weight distribution table of the intelligent monitoring instrument; wherein the sensor aging weight distribution table includes aging impact weights corresponding to different operating time intervals; According to the historical working hours, a corresponding aging impact weight is matched from the sensor aging weight allocation table, and a reference aging factor is weighted based on the aging impact weight to generate a dynamically updated sensor aging factor.

4. The method according to claim 3, wherein The process of generating the sensor aging weight distribution table includes: Acquire historical data of multiple reference intelligent monitors during an aging test phase, wherein the historical data includes sensor performance degradation indicators at different operating times; According to the correlation between the sensor performance degradation index and the temperature drift correction error, the impact level corresponding to different working time intervals is divided; A corresponding aging impact weight is allocated to each working time interval based on the impact level, and the sensor aging weight allocation table is generated.

5. The method according to claim 1, wherein The adaptive compensation parameter optimization algorithm is used to iteratively optimize the compensation parameters of the nonlinear compensation curve, including: Obtaining a temperature drift correction error in a current iteration cycle, and comparing the temperature drift correction error with a preset error threshold; If the temperature drift correction error is greater than the preset error threshold, adjusting the parameter values ​​in the compensation parameter set according to the error gradient direction to generate an updated compensation parameter set; The updated compensation parameter set is re-inputted into the nonlinear compensation curve for parameter verification until the temperature drift correction error is less than or equal to the preset error threshold.

6. The method according to claim 1, wherein The method of performing real-time correction processing on the original measurement data of the intelligent monitor according to the optimized compensation parameter set and outputting a target measurement result after suppressing temperature drift noise includes: Dividing the original measurement data into a plurality of time-synchronized measurement data segments according to the acquisition timestamp, wherein the time range of each measurement data segment corresponds one-to-one with the time range of the ambient temperature data segment; matching a corresponding compensation parameter group from the optimized compensation parameter set according to the time range of the ambient temperature data segment, and assigning the compensation parameter group to the time-synchronized measurement data segment; performing a linear compensation operation on each measurement value in the time-synchronized measurement data segment based on the offset correction coefficient and the temperature drift slope in the compensation parameter group to generate a compensated measurement data sequence; Performing sliding window mean filtering on the compensated measurement data sequence, calculating the average value of the measurement data in each window according to a preset window length and overlapping step length, and generating a filtered measurement data sequence; The filtered measurement data sequences are merged in the order of timestamps, and the measurement data corresponding to duplicate timestamps are removed to generate the target measurement result after suppressing the temperature drift noise.

7. An intelligent monitoring instrument temperature drift correction system, characterized in that: It includes a processor and a memory and a bus connected to the processor; wherein the processor and the memory communicate with each other through the bus; the processor is used to call program instructions in the memory to execute the temperature drift correction method of the intelligent monitor based on the temperature compensation algorithm according to any one of claims 1 to 6.

Images