A strain measurement error compensation method for a thermal power plant generator stator bottom load test based on an internal standard method

Abstract

The present application relates to the technical field of power plant generator state detection and testing, in particular to a strain measurement error compensation method for a power plant generator stator bottom load test based on an internal standard method, comprising: arranging a pair of measurement units at the to-be-measured measuring points on the side of the stator bottom foot; collecting to-be-measured strain signals and internal standard strain signals of all the pair of measurement units; preprocessing; calculating the amplitude ratio of the to-be-measured strain signal and the internal standard strain signal in each pair of measurement units as a calibration feature; taking the calibration feature as the independent variable and the standard strain value as the dependent variable to establish a calibration model; and evaluating the calibration model using test set data. The present application combines the internal standard method principle with the strain measurement field to construct a to-be-measured-internal standard pair of measurement system, calculate the strain amplitude ratio of the two to eliminate systematic errors, and eliminate systematic errors caused by the differences in the pasting process and environmental interference by establishing a linear regression internal standard calibration model, thereby improving the measurement accuracy.

Description

Technical Field

[0001] This invention relates to the field of condition detection and testing technology for thermal power plant generators, specifically a method for compensating for strain measurement errors in thermal power plant generator stator bottom load tests based on the internal standard method. Background Technology

[0002] The stator base is the core load-bearing component of the generator, and its mechanical strength and assembly quality directly affect the long-term safe and stable operation of the generator. The stator base load test is a critical test item in the generator manufacturing and maintenance process. By applying graded loads to the bottom of the stator base, the strain distribution of the stator base under different loads is measured, the stress state and structural strength of each base are evaluated, and potential defects such as unevenness and uneven stress at the base are detected in a timely manner, preventing core damage accidents during generator operation.

[0003] Strain gauges are the most widely used sensors in stator bottom load tests, reflecting the strain value of the measured structure through changes in resistance. However, in actual testing, the accuracy of strain measurement is affected by various factors, mainly exhibiting the following core defects: Uneven bonding force of strain gauges can lead to inconsistent adhesive layer thickness, affecting the efficiency of strain transfer from the iron core to the strain gauge; incorrect bonding position can cause the measuring point to deviate from the theoretical stress concentration area, introducing significant measurement errors; factors such as adhesive curing time and ambient humidity can also lead to dispersion in bonding quality.

[0004] Stator load tests typically last for several hours, and changes in ambient temperature can cause temperature drift in the strain gauges. Mechanical vibrations and electromagnetic interference from the test platform can also be superimposed on the strain signal, causing signal distortion.

[0005] Existing technologies mostly employ single-point static calibration before testing, which cannot eliminate errors caused by dynamic changes during testing; empirical correction methods rely on the operator's experience and lack quantitative calibration basis, resulting in poor repeatability of measurement results.

[0006] The errors caused by the above factors are mostly systematic errors. Traditional filtering and noise reduction methods can only remove some random noise and cannot fundamentally eliminate systematic deviations. The average relative error of the final measurement results can reach 10% to 15%, which is difficult to accurately reflect the true stress state of the generator base.

[0007] In summary, although strain gauges widely used in stator bottom load tests can reflect structural strain through changes in resistance, their measurement accuracy is affected by the bonding process. In the test environment, temperature changes lasting for several hours cause temperature drift, and mechanical vibration and electromagnetic interference cause signal distortion. The limitations of existing technology are that single-point static calibration cannot cope with dynamic errors, and empirical correction lacks quantitative basis, resulting in insufficient repeatability. Summary of the Invention

[0008] To address the problems of low measurement accuracy and large result dispersion caused by uneven strain gauge adhesion force, positional errors, differences in adhesive layer thickness, and ambient temperature drift in existing stator bottom load tests, this invention provides a strain measurement error compensation method for thermal power plant generator stator bottom load tests based on the internal standard method.

[0009] This invention is achieved through the following technical solution: A method for compensating for strain measurement errors in the stator bottom load test of a thermal power plant generator based on the internal standard method includes: Step 1: Arrange the strain gauges to be measured at the test points on the side of the stator base, and arrange the same batch and model of internal standard strain gauges at adjacent positions of each test point to form a one-to-one paired measurement unit. Step 2: During the staged loading process of the stator bottom load test, the strain signals to be measured and the internal standard strain signals of all paired measurement units are collected simultaneously; Step 3: Preprocess the acquired strain signal to be measured and the internal standard strain signal to obtain the corresponding preprocessed data; Step 4: Based on the preprocessed data, calculate the amplitude ratio of the strain signal to be measured to the internal standard strain signal in each paired measurement unit, and use the amplitude ratio as a calibration feature; Step 5: Using calibration characteristics as independent variables and standard strain values ​​as dependent variables, establish a calibration model using linear regression. Step 6: Divide the data samples into a test set and a training set, and use the test set data to evaluate the calibration model; Step 7: Embed the trained calibration model into the data acquisition system to automatically calibrate the strain signals acquired in real time and output the true strain value.

[0010] Preferably, in step 1, the center distance between the internal standard strain gauge and the corresponding strain gauge to be measured does not exceed a preset distance, and the internal standard strain gauge and the strain gauge to be measured are in the same stress field and environmental field.

[0011] Preferably, in step 2, the signal sampling frequency is 50Hz~2000Hz, and the stable acquisition time for each load level is not less than 30s.

[0012] Preferably, in step 3, the preprocessing involves sequentially performing polynomial fitting baseline correction, wavelet transform denoising, and Min-Max normalization on the acquired strain signal to be measured and the internal standard strain signal.

[0013] Preferably, the polynomial fitting baseline correction uses a polynomial of degree 3 to 6; the wavelet transform noise reduction uses the Daubechies-4 wavelet basis function, the decomposition layer is 3, the high-frequency coefficients are processed with soft thresholding, and the threshold is 0.02 times the maximum value of the signal; finally, the signal is scaled to the [0,1] interval by Min-Max normalization.

[0014] Preferably, in step 5, the least squares linear regression method is used to establish the calibration model.

[0015] Preferably, in step 6, the calibration model is evaluated using the coefficient of determination R², mean square error MSE, and mean relative error MRE. When the coefficient of determination R² is not less than 0.95 and the mean square error MSE is not greater than 0.01, it is judged as a qualified model.

[0016] A strain measurement error compensation system for the stator bottom load test of a thermal power plant generator based on the internal standard method, used in the method, comprising: The data acquisition module is used to simultaneously acquire the strain signals to be measured and the internal standard strain signals of all paired measurement units during the graded loading process of the stator bottom load test. The data preprocessing module is used to preprocess the acquired strain signals to be measured and internal standard strain signals to obtain the corresponding preprocessed data. The model building module is used to calculate the amplitude ratio of the strain signal to be measured and the internal standard strain signal in each paired measurement unit based on preprocessed data, and use the amplitude ratio as a calibration feature; and to establish a calibration model using the calibration feature as the independent variable and the standard strain value as the dependent variable, and employing a linear regression method. The model evaluation module is used to evaluate the calibration model using test set data.

[0017] An electronic device includes a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of the method.

[0018] A storage medium having a computer program stored thereon, the computer program being executed by a processor to perform the steps of the method.

[0019] Compared with the prior art, the present invention has the following beneficial effects: This invention discloses a strain measurement error compensation method for the stator bottom load test of a thermal power plant generator based on the internal standard method. It combines the principle of the internal standard method with the field of strain measurement. By arranging internal standard strain gauges of the same batch and model at adjacent positions of each test point, a test-internal standard paired measurement system is constructed. The ratio of their strain amplitudes is calculated to eliminate systematic errors. An internal standard calibration model is established based on linear regression. This model eliminates systematic errors caused by differences in bonding processes and environmental interference, thereby improving measurement accuracy.

[0020] Among them, the internal standard method reduces the impact of experimental condition fluctuations on measurement results by introducing a stable internal standard signal. In elemental quantitative analysis, this method has achieved significant results in calibration, interference elimination and measurement accuracy by adding a known, stable and unchanging standard.

[0021] Furthermore, this invention employs polynomial fitting baseline correction, Daubechies-4 wavelet transform denoising, and Min-Max normalization for signal preprocessing. First, a polynomial fitting baseline correction algorithm is introduced to remove nonlinear, slowly varying baselines caused by instrument temperature drift, electrode contact impedance changes, or environmental background interference. Then, multi-scale decomposition and reconstruction using the Daubechies-4 (Db4) wavelet basis accurately restores the true contour and peak height of the signal without losing the effective low-frequency signal, thus improving detection accuracy. Finally, Min-Max normalization linearly maps multidimensional feature data to a unified interval (e.g., [0, 1]), eliminating numerical deviations caused by differences in sensor dimensions and sample concentration ranges. This combined approach to standardize the collected data not only reduces the difficulty of extracting weak effective signals but also improves the accuracy of data processing. Attached Figure Description

[0022] Figure 1 This is a flowchart of a method for compensating for strain measurement errors in the stator bottom load test of a thermal power plant generator based on the internal standard method, according to the present invention. Figure 2 This is a flowchart of the calibration model established in this invention. Detailed Implementation

[0023] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known drone identification technologies, drone identification algorithms, and electronic devices are omitted so as not to obscure the description of the invention with unnecessary detail.

[0024] The terminology used in the following embodiments is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification and appended claims of this invention, the singular expressions “a,” “the,” “the,” and “the” are intended to also include expressions such as “one or more,” unless the context clearly indicates otherwise.

[0025] The following specific embodiments illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification.

[0026] Exemplary embodiments of the present invention will now be described with reference to the accompanying drawings. However, the present invention may be embodied in many different forms and is not limited to the embodiments described herein. These embodiments are provided to fully and completely disclose the invention and to fully convey its scope to those skilled in the art. The terminology used in the exemplary embodiments illustrated in the drawings is not intended to limit the invention. In the drawings, the same units / elements are referred to by the same reference numerals.

[0027] Unless otherwise stated, the terms used herein (including technical terms) have their common meaning as understood by one of ordinary skill in the art. Furthermore, it is understood that terms defined in commonly used dictionaries should be understood to have a meaning consistent with the context of their relevant field, and not to be interpreted as having an idealized or overly formal meaning.

[0028] The present invention will be further described in detail below with reference to specific embodiments. These descriptions are for explanation purposes only and are not intended to limit the scope of the invention.

[0029] This invention discloses a method for compensating for strain measurement errors in the stator bottom load test of a thermal power plant generator based on the internal standard method, referring to... Figure 1 ,include: Step 1: Arrange the strain gauges to be measured at the test points on the side of the stator base. Place internal standard strain gauges of the same batch and model at adjacent positions of each test point, forming a one-to-one paired measurement unit. The center distance between the internal standard strain gauge and the corresponding strain gauge to be measured should not exceed a preset distance (e.g., 5mm). This distance ensures that the internal standard strain gauge and the strain gauge to be measured are in the same stress field and environmental field, and that they are pasted in the same direction, using the same pasting process and adhesive to ensure that they are subjected to the same mechanical loads and environmental factors. Furthermore, the number of internal standard strain gauges is equal to the number of strain gauges to be measured, and they correspond one-to-one.

[0030] Step 2: During the staged loading process of the stator bottom load test, the strain signals to be measured and the internal standard strain signals of all paired measurement units are simultaneously acquired. During sampling, the signal sampling frequency is 50Hz~2000Hz, and the stable acquisition time under each load level is not less than 30s. The ambient temperature is recorded at each moment during the acquisition process, and the temperature sampling interval is 1min.

[0031] Step 3: Perform polynomial fitting baseline correction, wavelet transform noise reduction, and Min-Max normalization on the acquired strain signal to be measured and the internal standard strain signal in sequence to obtain the corresponding preprocessed data, as follows: The polynomial fitting baseline correction uses a 3rd to 6th order polynomial. Specifically, the baseline of the strain signal is fitted with a 3rd to 6th order polynomial, and the fitted baseline is subtracted from the original signal to eliminate temperature drift and slowly changing baseline offset.

[0032] Wavelet transform denoising uses the Daubechies-4 wavelet basis function, with a decomposition layer of 3. Soft thresholding is applied to the high-frequency coefficients, with a threshold value of 0.02 times the maximum signal value. The reconstructed signal is then used to remove high-frequency noise.

[0033] The signal is scaled to the [0,1] interval using Min-Max normalization, and the calculation formula is as follows:

[0034] In the formula, The original signal value, The minimum value of the signal. This represents the maximum value of the signal.

[0035] Step 4: Based on the preprocessed data, calculate the amplitude ratio of the strain signal to be measured to the internal standard strain signal in each paired measurement unit, and use the amplitude ratio as a calibration feature. The calculation formula is as follows:

[0036] In the formula, For the first i Calibration characteristics of each paired measurement unit, The signal amplitude of the strain gauge under test after preprocessing. The signal amplitude after preprocessing corresponding to the internal standard strain gauge Step 5: Using calibration characteristics as independent variables and standard strain values ​​as dependent variables, establish a calibration model using the least squares linear regression method.

[0037] The formula for the linear regression calibration model is:

[0038] in, The true strain value after calibration. For calibration features, For the model slope, The model intercept is used; the collected dataset is randomly divided into training and test sets in a 7:3 ratio, and the training set data is used to fit the model parameters. and .

[0039] Step 6: Evaluate the calibration model using the test set data. The coefficient of determination (R²), mean squared error (MSE), and mean relative error (MRE) are used to evaluate the calibration model, as shown in the following formulas:

[0040]

[0041]

[0042] in, For the sample size, The standard strain value, These are the model's predicted values. This represents the average value of the standard strain.

[0043] A model is considered qualified when the coefficient of determination R² is not less than 0.95 and the mean square error MSE is not greater than 0.01.

[0044] Step 7: Embed the trained calibration model into the data acquisition system to automatically calibrate the strain signals acquired in real time and output the true strain value.

[0045] When conducting a measurement test on the bottom load of a generator in a thermal power plant, the internal standard method for on-site testing is explained in detail, with the specific steps as follows: Step 1, Sensor Pairing and Arrangement Method: Before the generator stator under-load test begins, determine the location and number of test points based on the structural characteristics and stress analysis results of the stator core. Attach the strain gauge to be measured at the center of each test point, with the strain gauge's attachment direction aligned with the theoretical principal stress direction.

[0046] An internal standard strain gauge is attached to an adjacent position at each test point. The center-to-center distance between the internal standard strain gauge and the strain gauge under test is controlled within a reasonable range, ensuring that both are in the same stress field and environmental field and do not interfere with each other. Furthermore, the internal standard strain gauge and the strain gauge under test must be from the same production batch and of the same model to ensure that their sensitivity coefficients, temperature coefficients, and other parameters are completely consistent.

[0047] The internal standard strain gauge and the strain gauge under test were bonded using the exact same process: the same adhesive was used, and the same sanding, cleaning, gluing, pressurizing, and curing steps were followed, with consistent curing time and temperature. After bonding, a multimeter was used to check the resistance and insulation resistance of the strain gauges to ensure that all strain gauges were functioning correctly.

[0048] Step 2, Multi-condition signal acquisition method: According to the stator base load test procedure, the load is applied in stages, which can be divided into six levels: no load, 25% rated load, 50% rated load, 75% rated load, 100% rated load, and 125% rated load. Under each load level, the load is kept stable for no less than 30 minutes. Signal acquisition begins after the stator base deformation stabilizes.

[0049] A multi-channel strain gauge was used to simultaneously acquire the output signals of all strain gauges under test and the internal standard strain gauge. The sampling frequency was adjusted according to the stator structure dimensions and the load change rate. The continuous acquisition time for each load level was no less than 30 seconds. During the acquisition process, personnel movement and equipment vibration should be avoided to minimize external interference.

[0050] Simultaneously, temperature sensors are placed near the stator base to synchronously collect ambient temperature signals. The temperature sampling interval is set to 1 minute to analyze the impact of temperature drift on the measurement results. All collected data is automatically stored in the data acquisition system for subsequent processing and analysis.

[0051] Step 3, Signal preprocessing method: Perform multi-step preprocessing on the acquired raw strain signal to improve signal quality. The specific steps are as follows: Outlier Removal: The 3σ criterion is used to remove outliers from the original signal. Outliers exceeding the mean are excluded. Data points that are 3 times the standard deviation are replaced with the average of adjacent data points.

[0052] Polynomial Fitting Baseline Correction: Based on the degree of baseline drift, a 3rd to 6th order polynomial is selected to fit the signal, obtaining the baseline trend. The fitted baseline is subtracted from the original signal to eliminate baseline shift caused by temperature changes and sensor zero-point drift.

[0053] Wavelet transform denoising: The preprocessed signal is decomposed into three layers using the Daubechies-4 wavelet basis function, resulting in one low-frequency approximation component and three high-frequency detail components. Soft thresholding is applied to the high-frequency detail components, setting coefficients below the threshold to zero and retaining coefficients above the threshold. Wavelet reconstruction is then performed on each processed component to obtain the denoised strain signal.

[0054] Min-Max Normalization: The noise-reduced signal is normalized using Min-Max normalization to scale the amplitude of all signals to a uniform range, eliminating the effects of differences in the sensitivity of different strain gauges and fluctuations in signal amplitude.

[0055] Step 4, Internal Standard Calibration Feature Calculation Method: For each measured-internal standard paired measurement unit, extract the stable amplitude of the preprocessed measured strain signal and internal standard strain signal under each load level.

[0056] The method for calculating the stable amplitude is as follows: take the signal data in the middle 20 seconds of the acquisition period under each load level, and calculate its average value as the signal amplitude under that load.

[0057] Calculate the strain amplitude ratio of each paired measurement unit under different loads, and use it as the calibration feature after eliminating systematic errors. Form a feature matrix from the calibration features of all paired measurement units under different loads, which is used as the input data for subsequently establishing the calibration model.

[0058] Step 5, with reference to Figure 2 , establish an internal reference calibration model: Standard strain values are obtained in the following two ways: First, the deformation of the stator foot is measured by a high-precision displacement sensor, and the theoretical strain value is calculated by combining with the material mechanics formula; Second, through finite element simulation analysis, a three-dimensional finite element model of the stator foot is established, the same load as that in the test is applied, and the simulated strain values of each measuring point are obtained through calculation.

[0059] Taking the calibration features as independent variables and the corresponding standard strain values as dependent variables, the least square linear regression method is used to establish the calibration model.

[0060] All sample data are randomly divided into a training set and a test set at a ratio of 7:3, ensuring that both the training set and the test set contain data of all load levels and all measuring points. The training set data is used to fit model parameters, and the calibration model corresponding to each paired measurement unit is obtained.

[0061] Step 6, model performance evaluation method: the established calibration model is comprehensively evaluated for performance using the test set data, and three indicators, namely the coefficient of determination R², mean square error MSE and mean relative error MRE, are used to comprehensively evaluate the accuracy and stability of the model.

[0062] When the model meets the preset performance standard, it is determined as a qualified model. For models that fail to meet the standard, the sensor bonding quality and data acquisition process are checked, and the model is retrained after excluding abnormal data.

[0063] At the same time, the model errors under different load levels are analyzed to evaluate the adaptability of the model in the full load range. If the error of the model in the high-load or low-load interval is large, the number of samples in this interval can be appropriately increased, and the model is retrained to improve the accuracy.

[0064] Step 7, on-line measurement calibration method: embed the trained and verified qualified calibration model into the test data acquisition system to realize real-time automatic calibration of strain signals.

[0065] During the real-time measurement of the stator foot load test, the data acquisition system synchronously collects the original signals of the strain gauge to be measured and the internal reference strain gauge, and automatically completes signal preprocessing and internal reference calibration feature calculation. The calculated calibration features are input into the corresponding calibration model, and the calibrated real strain value is output in real time.

[0066] This invention discloses a method for compensating for strain measurement errors in the stator bottom load test of a thermal power plant generator based on the internal standard method. First, it pairs adjacent internal standard strain gauges of the same batch and model with the strain gauge under test. Then, it utilizes synchronous acquisition and signal preprocessing under graded loading to extract the amplitude ratio between the test signal and the internal standard signal as a calibration feature. A calibration model is established using linear regression and optimized through test set evaluation. Finally, it is embedded into the data acquisition system to achieve real-time automatic calibration. This invention requires no hardware modification to the existing test system; it only requires adding a small number of internal standard strain gauges and upgrading the software algorithm to reduce measurement errors and improve the measurement accuracy and reliability of the generator stator bottom load test. It is applicable to strain measurement in the stator bottom load test of steam turbine generators.

[0067] This invention also discloses a strain measurement error compensation system for the stator bottom load test of a thermal power plant generator based on the internal standard method, used to implement the method, comprising: The data acquisition module is used to simultaneously acquire the strain signals to be measured and the internal standard strain signals of all paired measurement units during the graded loading process of the stator bottom load test. The data preprocessing module is used to preprocess the acquired strain signals to be measured and internal standard strain signals to obtain the corresponding preprocessed data. The model building module is used to calculate the amplitude ratio of the strain signal to be measured and the internal standard strain signal in each paired measurement unit based on preprocessed data, and to use the amplitude ratio as a calibration feature; and to establish a calibration model using the calibration feature as the independent variable and the standard strain value as the dependent variable, and using the linear regression method. The model evaluation module is used to evaluate the calibration model using test set data.

[0068] This invention also discloses a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the method. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, and is suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions from a computer storage medium to implement the corresponding method flow or corresponding function. This invention also discloses a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method. The computer-readable storage medium is a memory device in a computer device used to store programs and data. It is understood that the computer-readable storage medium here can include both built-in storage media in the computer device and extended storage media supported by the computer device. The computer-readable storage medium provides storage space containing the terminal's operating system. Furthermore, this storage space also contains one or more instructions suitable for loading and execution by a processor; these instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device. The processor can load and execute one or more instructions stored in the computer-readable storage medium.

[0069] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0070] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations 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, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0071] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1The function specified in one or more boxes.

[0072] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0073] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the functions specified in one or more boxes. Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

[0074] It should be understood that, when used in this specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0075] It should also be understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0076] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of the invention include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0077] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for compensating for strain measurement errors in the stator bottom load test of a thermal power plant generator based on the internal standard method, characterized in that, include: Step 1: Arrange the strain gauges to be measured at the test points on the side of the stator base, and arrange the same batch and model of internal standard strain gauges at adjacent positions of each test point to form a one-to-one paired measurement unit. Step 2: During the staged loading process of the stator bottom load test, the strain signals to be measured and the internal standard strain signals of all paired measurement units are collected simultaneously; Step 3: Preprocess the acquired strain signal to be measured and the internal standard strain signal to obtain the corresponding preprocessed data; Step 4: Based on the preprocessed data, calculate the amplitude ratio of the strain signal to be measured to the internal standard strain signal in each paired measurement unit, and use the amplitude ratio as a calibration feature; Step 5: Using calibration characteristics as independent variables and standard strain values ​​as dependent variables, establish and train a calibration model using linear regression. Step 6: Divide the data samples into a test set and a training set, and use the test set data to evaluate the calibration model; Step 7: Embed the trained calibration model into the data acquisition system to automatically calibrate the strain signals acquired in real time and output the true strain value.

2. The method for compensating for strain measurement errors in the stator bottom load test of a thermal power plant generator based on the internal standard method according to claim 1, characterized in that, In step 1, the center distance between the internal standard strain gauge and the corresponding strain gauge to be measured does not exceed the preset distance, and the internal standard strain gauge and the strain gauge to be measured are in the same stress field and environmental field.

3. The method for compensating for strain measurement errors in the stator bottom load test of a thermal power plant generator based on the internal standard method, as described in claim 1, is characterized in that... In step 2, the signal sampling frequency is 50Hz~2000Hz, and the stable acquisition time for each load level is not less than 30s.

4. The method for compensating for strain measurement errors in the stator bottom load test of a thermal power plant generator based on the internal standard method according to claim 1, characterized in that, In step 3, the preprocessing involves performing polynomial fitting baseline correction, wavelet transform denoising, and Min-Max normalization on the acquired strain signal to be measured and the internal standard strain signal in sequence.

5. The method for compensating for strain measurement errors in the stator bottom load test of a thermal power plant generator based on the internal standard method according to claim 4, characterized in that, Polynomial fitting baseline correction uses polynomials of degree 3 to 6; wavelet transform denoising uses Daubechies-4 wavelet basis functions, with a decomposition layer of 3 layers, and high-frequency coefficients are processed with soft thresholding, with a threshold of 0.02 times the maximum signal value; finally, Min-Max normalization is used to scale the signal to the [0,1] interval.

6. The method for compensating for strain measurement errors in the stator bottom load test of a thermal power plant generator based on the internal standard method according to claim 1, characterized in that, In step 5, the least squares linear regression method is used to establish a calibration model.

7. The method for compensating for strain measurement errors in the stator bottom load test of a thermal power plant generator based on the internal standard method according to claim 1, characterized in that, In step 6, the calibration model is evaluated using the coefficient of determination R², mean square error (MSE), and mean relative error (MRE). A model is considered qualified when the coefficient of determination R² is not less than 0.95 and the mean square error (MSE) is not greater than 0.

01.

8. A strain measurement error compensation system for the stator bottom load test of a thermal power plant generator based on the internal standard method, used to implement the method described in any one of claims 1 to 7, characterized in that, include: The data acquisition module is used to simultaneously acquire the strain signals to be measured and the internal standard strain signals of all paired measurement units during the graded loading process of the stator bottom load test. The data preprocessing module is used to preprocess the acquired strain signals to be measured and internal standard strain signals to obtain the corresponding preprocessed data. The model building module is used to calculate the amplitude ratio of the strain signal to be measured and the internal standard strain signal in each paired measurement unit based on preprocessed data, and to use the amplitude ratio as a calibration feature. Using calibration characteristics as independent variables and standard strain values ​​as dependent variables, a calibration model was established using linear regression. The model evaluation module is used to evaluate the calibration model using test set data.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images