A method for intelligent monitoring of an annealing process of a wound transformer core

Abstract

The application discloses a kind of winding transformer core annealing process intelligent monitoring methods, specifically related to intelligent monitoring technical field;It is through the temperature data and magnetic field intensity data generated in the annealing process of winding transformer core, time domain synchronous processing and abnormal data annotation are carried out;According to the synchronous data, the micro-deformation region of the core and the corresponding temperature anomaly region are identified, and the temperature anomaly fluctuation characteristics are extracted;The dynamic coupling relationship between the temperature anomaly fluctuation characteristics and the stress change of the core is analyzed, and the characteristic data of the interaction of the core magnetic field and stress is output;Synchronous analysis of the interference intensity of temperature anomaly fluctuation on the uniformity of annealing heat distribution, output temperature disturbance intensity data;Coupling abnormal evolution model is constructed, and core annealing abnormal evaluation data is generated, the quality fluctuation risk in the annealing process is quantified, and intelligent early warning information is generated.The accuracy and reliability of the core annealing process monitoring are effectively improved, and the annealing quality of the transformer core is guaranteed.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent monitoring, more specifically, the present application relates to a winding type transformer core annealing process intelligent monitoring method. BACKGROUND

[0002] The winding type transformer core is usually made of continuous silicon steel sheets or continuous silicon steel strips by special winding equipment, and is widely used in power transformers as a key magnetic component.

[0003] The existing winding type transformer core annealing process quality evaluation method only focuses on a single index of local temperature or static magnetic performance, and cannot effectively monitor and accurately identify the multi-field coupling effect between the magnetic field, temperature field and stress field during the annealing process and its influence on the performance of the core, resulting in difficulty in timely discovery and early warning of the coupling type quality defects in the annealing process, increasing the risk of overall quality fluctuation and uncertainty of the winding type transformer core after annealing. SUMMARY

[0004] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present application provide a winding type transformer core annealing process intelligent monitoring method to solve the problems raised in the background art.

[0005] To achieve the above-mentioned purpose, the present application provides the following technical scheme:

[0006] A winding type transformer core annealing process intelligent monitoring method, comprising the following steps:

[0007] S1: Collecting temperature data and magnetic field intensity data generated by the winding type transformer core during the annealing process, performing time domain synchronization processing and abnormal data labeling, and generating time sequence synchronization data of temperature and magnetic field;

[0008] S2: According to the time sequence synchronization data of temperature and magnetic field, identifying the core micro-deformation area and the corresponding temperature abnormal area, and generating the temperature abnormal fluctuation characteristics of the core micro-deformation area;

[0009] S3: According to the temperature abnormal fluctuation characteristics of the core micro-deformation area, analyzing the dynamic coupling effect of stress change on magnetic field distribution, and outputting the characteristic data of core magnetic field and stress interaction;

[0010] S4: According to the temperature abnormal fluctuation characteristics of the core micro-deformation area, analyzing the interference intensity of the core temperature abnormal change on the uniformity of the core annealing heat distribution, and outputting the temperature disturbance intensity data;

[0011] S5: Based on the characteristic data of core magnetic field and stress interaction and the core temperature disturbance intensity data, establishing a coupling abnormal evolution model of magnetic field-thermal field-stress field, and generating core annealing abnormal evaluation data;

[0012] S6: evaluating the quality fluctuation risk of the core annealing process according to the core annealing abnormality evaluation data, and generating intelligent early warning information of core annealing abnormality.

[0013] In a preferred embodiment, S1, specifically:

[0014] Collecting real-time temperature data of the wound transformer core during the annealing process;

[0015] Collecting real-time magnetic field intensity data of the wound transformer core during the annealing process;

[0016] Aligning the real-time temperature data and the real-time magnetic field intensity data in time series data, aligning the time according to the unified time axis, and synchronously integrating into a unified time series data sequence;

[0017] Abnormal data labeling is performed on the data points in the unified time series data sequence that exceed the preset normal range, forming time series synchronous data of temperature and magnetic field.

[0018] In a preferred embodiment, S2, specifically:

[0019] Based on the time series synchronous data, the magnetic field intensity difference and the corresponding temperature difference of adjacent sampling points are calculated to generate a magnetic field gradient sequence and a temperature gradient sequence;

[0020] According to the preset magnetic field gradient threshold, the initial candidate area of core micro-deformation is determined in the magnetic field gradient sequence;

[0021] According to the preset temperature gradient threshold, the temperature abnormal candidate area is determined in the temperature gradient sequence, and the spatial position matching is performed with the initial candidate area of core micro-deformation to determine the core micro-deformation area and the temperature abnormal area that completely coincide in spatial position;

[0022] The time domain mean, time domain variance and frequency domain amplitude of the temperature data in the temperature abnormal area are calculated to generate the temperature abnormal fluctuation characteristics of the core micro-deformation area.

[0023] In a preferred embodiment, S3, specifically:

[0024] Based on the temperature abnormal fluctuation characteristics of the core micro-deformation area, the thermal expansion coefficient and Young's modulus of the core material are combined to generate a core stress change sequence;

[0025] Time axis registration is performed between the core stress change sequence and the time series synchronous data to construct a stress and magnetic field joint matrix;

[0026] Correlation analysis is performed on the stress and magnetic field joint matrix to obtain a magnetic stress coupling coefficient sequence;

[0027] Screening the coupling enhancement interval in the magnetic stress coupling coefficient sequence, and marking the corresponding core space position as the magnetic stress interaction enhancement area;

[0028] Extracting the coupling coefficient mean, coupling coefficient variance and frequency domain amplitude in the magnetic stress interaction enhancement area, and outputting the characteristic data of the interaction between the core magnetic field and stress.

[0029] In a preferred embodiment, S4, specifically:

[0030] Based on the temperature abnormal fluctuation characteristics of the core micro-deformation area, the spatial coordinate position corresponding to the core micro-deformation area is determined, and the real-time temperature data sequence of the spatial coordinate position in the time sequence synchronization data is extracted;

[0031] Taking the spatial coordinate position corresponding to the core micro-deformation area as the center, a spatial neighborhood with a preset spatial radius as the range is constructed;

[0032] Extracting the time domain temperature difference of the real-time temperature data sequence in the spatial neighborhood;

[0033] According to the time domain temperature difference, the interference intensity of the temperature abnormal change of the core micro-deformation area on the overall annealing heat distribution uniformity of the core is determined, and the temperature disturbance intensity data of the core micro-deformation area is output.

[0034] In a preferred embodiment, S5, specifically:

[0035] Synchronizing and aligning the characteristic data of the interaction between the core magnetic field and stress and the temperature disturbance intensity data of the core micro-deformation area according to the time axis to generate a coupling input matrix;

[0036] Normalizing the coupling input matrix and unifying the data dimension;

[0037] Based on the coupling input matrix, a magnetic field-thermal field-stress field coupling abnormal evolution model is established;

[0038] Based on the coupling abnormal evolution model, a magnetic field-thermal field-stress field coupling index sequence is calculated, and based on a preset coupling threshold, a coupling abnormal interval is screened, and core annealing abnormality evaluation data is output.

[0039] In a preferred embodiment, S6, specifically:

[0040] Dividing the core annealing abnormality evaluation data into multiple time windows, and extracting the mean and variance of the core annealing abnormality evaluation data in each time window;

[0041] Calculating the deviation of the mean and variance of the core annealing abnormality evaluation data in each time window relative to the preset normal threshold to obtain a core annealing quality fluctuation risk index;

[0042] According to the core annealing quality fluctuation risk index, the risk levels of each time window in the core annealing process are determined;

[0043] For the time window whose risk level exceeds the preset risk level threshold, mark it as an annealing quality abnormal period, and generate core annealing abnormal intelligent early warning information containing risk level, start and end time and corresponding core space position.

[0044] The technical effect and advantage of the winding type transformer core annealing process intelligent monitoring method are as follows:

[0045] Through real-time synchronous collection and abnormal annotation of the temperature field and magnetic field intensity field in the winding type transformer core annealing process, comprehensive online monitoring of the core annealing state is realized;Based on the time sequence synchronous data, the core micro-deformation area and the corresponding temperature abnormal area are accurately positioned, so that the temperature abnormal fluctuation characteristics and the micro-deformation behavior are directly related, and the recognition ability of the hidden defects is improved;By analyzing the dynamic coupling effect of temperature abnormal fluctuation and stress change on the magnetic field distribution, the characteristic data reflecting the stress-magnetic field interaction is obtained, and the quantitative description of the multi-field coupling effect is realized;Through quantitative evaluation of the interference intensity of core temperature abnormal change on the uniformity of core annealing heat distribution, accurate interference index for annealing temperature field distribution uniformity is provided;A three-dimensional coupling evolution model including magnetic field, thermal field and stress field is established, the prediction and evaluation of the coupling abnormal evolution process are realized, and core annealing abnormal evaluation data is generated;Through the evaluation of the quality fluctuation risk of the core annealing process, the annealing quality fluctuation risk can be warned in real time, the stability and reliability of the annealing process are significantly improved, and the final magnetic performance consistency and product qualification rate of the transformer core are guaranteed. BRIEF DESCRIPTION OF DRAWINGS

[0046] Figure 1 A winding type transformer core annealing process intelligent monitoring method is provided. DETAILED DESCRIPTION

[0047] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0048] EMBODIMENT

[0049] Figure 1 A winding type transformer core annealing process intelligent monitoring method is provided.

[0050] S1: Collect temperature data and magnetic field intensity data generated during the annealing process of the wound transformer core, perform time domain synchronous processing and abnormal data labeling, and generate time sequence synchronous data of temperature and magnetic field;

[0051] S2: According to the time sequence synchronous data of temperature and magnetic field, identify the core micro-deformation area and the corresponding temperature abnormal area, and generate the temperature abnormal fluctuation characteristics of the core micro-deformation area;

[0052] S3: According to the temperature abnormal fluctuation characteristics of the core micro-deformation area, analyze the dynamic coupling effect of stress change on magnetic field distribution, and output the characteristic data of core magnetic field and stress interaction;

[0053] S4: According to the temperature abnormal fluctuation characteristics of the core micro-deformation area, analyze the interference intensity of core temperature abnormal change on core annealing heat distribution uniformity, and output the temperature disturbance intensity data;

[0054] S5: Based on the characteristic data of core magnetic field and stress interaction and the core temperature disturbance intensity data, a coupling abnormal evolution model of magnetic field-thermal field-stress field is established, and core annealing abnormal evaluation data is generated;

[0055] S6: According to the core annealing abnormal evaluation data, the quality fluctuation risk of the core annealing process is evaluated, and the intelligent early warning information of the core annealing abnormality is generated.

[0056] S1: Collect temperature data and magnetic field intensity data generated during the annealing process of the wound transformer core, perform time domain synchronous processing and abnormal data labeling, and generate time sequence synchronous data of temperature and magnetic field, including:

[0057] Collect real-time temperature data of the wound transformer core during the annealing process;

[0058] The wound transformer core refers to the core structure in the form of a circular ring or a rectangular section processed by continuous silicon steel sheets or continuous silicon steel strips through special winding equipment, mainly used for the magnetic circuit of a transformer. Due to the mechanical stress in the winding forming process, the wound transformer core needs to be stress-relieved by high-temperature heat treatment during annealing, so as to improve the magnetic properties of the material. The annealing process refers to the heat treatment process of orderly heating, holding and cooling the wound transformer core in a high-temperature furnace, and the temperature control precision and stability directly determine the final magnetic properties of the core. Therefore, in order to monitor the dynamic changes of the temperature in the annealing process, temperature sensors are used to continuously collect real-time temperature data of each local space position of the core in the annealing furnace. A plurality of K-type or N-type thermocouple temperature sensors are arranged at different spatial positions around the wound transformer core, and the real-time temperature at different spatial positions is continuously collected and recorded at a frequency of 1 to 10 data points per second, forming a real-time temperature data set containing time stamps and spatial position markers. For example, the real-time temperature data collected at a certain time point may be: the real-time temperature at position coordinates (x1, y1, z1) is 550 degrees Celsius, the real-time temperature at position coordinates (x2, y2, z2) is 548 degrees Celsius, and the real-time temperature at position coordinates (x3, y3, z3) is 549 degrees Celsius.

[0059] Collecting real-time magnetic field strength data of the wound transformer core during the annealing process;

[0060] In order to monitor the magnetic field changes during the core annealing process, a plurality of magnetic field strength sensors are arranged around the wound transformer core, taking the magnetic flux gate type magnetic field strength sensor or the Hall element type magnetic field strength sensor as an example, to measure and collect the magnetic field strength change data during the core annealing process in real time. The magnetic field strength sensor is installed at a plurality of specific spatial positions inside the annealing furnace, continuously collects and records the magnetic field strength at different positions, and forms a real-time magnetic field strength data set with time stamps and spatial coordinate position markers. For example, the magnetic field strength data obtained at a certain time point is: the real-time magnetic field strength at position coordinates (x1, y1, z1) is 200 Gauss, the real-time magnetic field strength at position coordinates (x2, y2, z2) is 198 Gauss, and the real-time magnetic field strength at position coordinates (x3, y3, z3) is 199 Gauss.

[0061] Aligning the real-time temperature data and the real-time magnetic field strength data in time series data, aligning the time according to a unified time axis, and synchronously integrating into a unified time series data sequence;

[0062] Since the temperature data and the magnetic field data are from different sensors and can have different sampling start times and frequencies, it is necessary to align them on a unified time axis. For example, missing data points can be interpolated using an interpolation method or a linear interpolation method to make the temperature data and the magnetic field strength data correspond to each other at each time node. For example, the temperature data has one data point at 1 second, 2 seconds, and 3 seconds, and the magnetic field strength data can be collected at 1.5 seconds, 2.5 seconds, and 3.5 seconds. Therefore, a linear interpolation method is used to adjust the magnetic field data to the same 1 second, 2 seconds, and 3 seconds corresponding to the temperature data, so as to obtain a unified time series data sequence. Through the above method, a time series data sequence is obtained, for example, at 2 seconds, the data combination obtained is: at position coordinates (x1, y1, z1), the temperature is 550 degrees Celsius, and the magnetic field strength is 200 Gauss; at position coordinates (x2, y2, z2), the temperature is 548 degrees Celsius, and the magnetic field strength is 198 Gauss; and so on. Through the above synchronization and integration process, the time series data sequence accurately reflects the real-time temperature and real-time magnetic field change law during the annealing process of the wound transformer core.

[0063] Abnormal data labeling is performed on data points in the unified time series data sequence that exceed the preset normal range to form temperature and magnetic field time series synchronization data.

[0064] Through the preset temperature data threshold range and the magnetic field strength data threshold range, data that exceeds the reasonable physical range or the process setting range in the unified time series data sequence is automatically identified and marked as abnormal data. For example, it is preset that the normal temperature range during the annealing process is 520 to 560 degrees Celsius, and the normal magnetic field strength range is 190 to 210 Gauss. If the temperature data at a certain time and a certain spatial position is 570 degrees Celsius, it exceeds the preset normal temperature range, and the corresponding data point in the data sequence is labeled as abnormal data. If the magnetic field strength data at a certain time and a certain spatial position is 215 Gauss, it also exceeds the preset normal magnetic field strength range, and the corresponding data point in the data sequence is labeled as abnormal data. For example, the temperature and magnetic field time series synchronization data sequence after abnormal data labeling processing can be: at time point t=2 seconds, at position (x1, y1, z1), the temperature is 550 degrees Celsius, and the magnetic field strength is 200 Gauss, both of which are normal data; at time point t=3 seconds, at position (x2, y2, z2), the temperature is 570 degrees Celsius (abnormal data marked), and the magnetic field strength is 202 Gauss.

[0065] S2: According to the temperature and magnetic field time series synchronization data, the core micro-deformation region and the corresponding temperature abnormal region are identified, and the temperature abnormal fluctuation characteristics of the core micro-deformation region are generated, including:

[0066] Based on the time series synchronization data, the magnetic field strength difference and the corresponding temperature difference of adjacent sampling points are calculated to generate a magnetic field gradient sequence and a temperature gradient sequence.

[0067] The time sequence synchronization data refers to time sequence synchronization data of temperature and magnetic field generated through synchronization processing, and embodies real-time temperature data and real-time magnetic field intensity data of each time point and each spatial position of the wound transformer core in the annealing process. In order to embody the gradient characteristics of dynamic changes of temperature and magnetic field in the annealing process, it is necessary to calculate the magnetic field intensity change amount and the temperature change amount between adjacent sampling time points respectively. For example, taking the position coordinates (x1, y1, z1) as an example, the magnetic field intensity at two adjacent sampling points of the first second and the second second is 200 Gauss and 202 Gauss, and the difference value of the magnetic field intensity is 2 Gauss through calculation; at the same time, the real-time temperature at two adjacent sampling points of the first second and the second second is 550 degrees Celsius and 552 degrees Celsius respectively, and the corresponding temperature difference value is 2 degrees Celsius. Through continuous execution of the above calculation process, a magnetic field gradient sequence and a temperature gradient sequence composed of the magnetic field intensity difference value and the temperature difference value are obtained, embodying the dynamic change law of the magnetic field and the temperature in the time dimension.

[0068] According to the preset magnetic field gradient threshold value, an initial candidate area of core micro-deformation is determined in the magnetic field gradient sequence;

[0069] The magnetic field gradient threshold value is a threshold value preset according to the magnetic field intensity change law and the magnetostriction effect law of the wound transformer core in the annealing process. The magnetostriction effect shows that when the core has a slight mechanical deformation, the magnetic field intensity will change. Therefore, by setting a suitable magnetic field gradient threshold value, for example, setting the magnetic field gradient threshold value to 1.5 Gauss / s, the interval in the magnetic field gradient sequence where the magnetic field gradient is greater than 1.5 Gauss / s is considered to have a magnetic field change, which means that the core has a micro-deformation possibility. For example, at the position coordinates (x2, y2, z2), the magnetic field gradient from the second second to the third second reaches 2 Gauss / s, which exceeds the preset magnetic field gradient threshold value, and then the spatial position corresponding to the position coordinates (x2, y2, z2) of the core is marked as the initial candidate area of core micro-deformation, providing the initial spatial positioning of the core micro-deformation.

[0070] According to the preset temperature gradient threshold value, a temperature abnormality candidate area is determined in the temperature gradient sequence, and a spatial position matching is performed with the initial candidate area of core micro-deformation to determine a core micro-deformation area and a temperature abnormality area that completely coincide in spatial position;

[0071] The temperature gradient threshold is also preset based on empirical rules of the annealing process and characteristics of the core material, for example, the temperature gradient threshold is set to 1.2 degrees Celsius per second. When the temperature gradient in the temperature gradient sequence exceeds 1.2 degrees Celsius per second, it indicates that there is abnormal temperature fluctuation at the corresponding spatial position. For example, at the position coordinate (x2, y2, z2), the temperature gradient reaches 1.5 degrees Celsius per second from the 2nd second to the 3rd second, exceeding the set temperature gradient threshold, so the position is marked as a temperature abnormality candidate area. The core micro-deformation initial candidate area determined by the magnetic field gradient sequence and the temperature abnormality candidate area determined by the temperature gradient sequence are matched one by one in the spatial position. If it is found that a certain position coordinate (such as (x2, y2, z2)) exceeds the corresponding threshold in the magnetic field gradient and the temperature gradient, and the spatial positions are completely consistent, then it is confirmed that the spatial position corresponding to the position coordinate (x2, y2, z2) is the core micro-deformation area and the temperature abnormality area. Through the judgment standard of complete coincidence of spatial positions, the core area actually occurring micro-deformation and accompanied by temperature abnormality is accurately identified.

[0072] The time domain mean, time domain variance, and frequency domain amplitude of the temperature data in the temperature abnormality area are calculated to generate the temperature abnormality fluctuation characteristics of the core micro-deformation area;

[0073] In the determined core micro-deformation area and temperature abnormality area, the statistical characteristics and frequency domain characteristics of the real-time temperature data in the area are extracted to quantify the abnormal fluctuation characteristics. Among them, the time domain mean refers to the average value of all real-time temperature data in the time window; the time domain variance refers to the fluctuation degree of the real-time temperature data relative to the average value; the frequency domain amplitude is the amplitude size at the characteristic frequency calculated by converting the real-time temperature data sequence to the frequency space using Fourier transform. For example, for the determined core micro-deformation area coordinate (x2, y2, z2), in the time window from the 2nd second to the 6th second, the collected real-time temperature data are 552, 554, 553, 556, and 555 degrees Celsius, respectively. The time domain mean of the temperature data in the time window is 554 degrees Celsius, the time domain variance is 2.0 degrees Celsius, and the frequency domain analysis shows that the temperature fluctuation characteristic frequency is 0.2 Hz, and the amplitude is 1.5 degrees Celsius. Through the above statistical analysis and frequency domain analysis, the amplitude, stability, and change mode of the local temperature abnormal fluctuation of the core micro-deformation area in the annealing process are reflected.

[0074] S3: According to the temperature abnormality fluctuation characteristics of the core micro-deformation area, analyze the dynamic coupling effect of stress change on the magnetic field distribution, and output the characteristic data of the interaction between the core magnetic field and the stress, including:

[0075] Based on the temperature abnormality fluctuation characteristics of the core micro-deformation area, the thermal expansion coefficient and Young's modulus of the core material are combined to generate a core stress change sequence;

[0076] To determine the impact of temperature abnormal fluctuations on the actual mechanical properties of the core, the physical properties of the core material need to be considered comprehensively, specifically the material thermal expansion coefficient and Young's modulus. The thermal expansion coefficient represents the degree of change in the length of the wound transformer core material when the unit temperature changes; the Young's modulus represents the rigidity of the core material in resisting deformation within the elastic deformation range. By combining the temperature abnormal fluctuation characteristics of the core micro-deformation region with the thermal expansion coefficient and Young's modulus of the core material, the dynamic stress change of the core under abnormal temperature fluctuations can be calculated, generating a core stress change sequence. For example, if the core material is silicon steel sheet, the thermal expansion coefficient is 11.5x10^-6 per degree Celsius, and the Young's modulus is 195GPa. At the coordinate position (e.g., position coordinates (x2, y2, z2)) of the micro-deformation region, when the temperature abnormal fluctuation characteristic shows that the real-time temperature fluctuates rapidly from 550 degrees Celsius to 560 degrees Celsius, the thermal stress change amplitude at the corresponding position is calculated using the thermal expansion coefficient and Young's modulus through the temperature difference of 10 degrees Celsius. Through the formula Δσ = E·α·ΔT, where Δσ represents the stress change, E is the Young's modulus, α is the thermal expansion coefficient, and ΔT is the temperature change, substituting the above parameters, the stress change Δσ = 195GPa x 11.5x10^-6 per degree Celsius x 10 degrees Celsius = 22.425MPa. According to the same calculation method, the temperature abnormal fluctuation data at multiple time points are processed in succession, and the stress change values are obtained in sequence to form a continuous core stress change sequence. The core stress change sequence reflects the dynamic evolution trend and amplitude of the stress caused by temperature abnormal changes in the local region of the core during the annealing process.

[0077] The core stress change sequence is time axis aligned with the time sequence data to construct a stress and magnetic field joint matrix.

[0078] To accurately study the dynamic correlation between core stress changes and magnetic field strength, the core stress change sequence and the magnetic field strength data sequence need to be matched in the time dimension, referred to as time axis alignment. For example, if the sampling interval of the core stress change sequence is 1 second and the sampling interval of the magnetic field strength data is also 1 second, the core stress change sequence and the magnetic field strength data sequence are aligned at each time point in seconds. For example, at position coordinates (x2, y2, z2), the core stress change values at the 1st to 5th seconds are 22.425MPa, 23.500MPa, 21.300MPa, 24.000MPa, and 23.100MPa, respectively; at the corresponding time points of the 1st to 5th seconds, the magnetic field strength data are 200 Gauss, 201 Gauss, 202 Gauss, 200 Gauss, and 199 Gauss, respectively. By aligning the stress and magnetic field data with the time point as the coordinate, a stress and magnetic field joint matrix is constructed. The stress and magnetic field joint matrix reflects the numerical information of the stress and magnetic field strength of the core local region at each time point.

[0079] Correlation analysis is performed on the stress and magnetic field combined matrix to obtain a magnetic stress coupling coefficient sequence;

[0080] The correlation analysis uses numerical statistical analysis methods, such as calculating the covariance between the magnetic field intensity data and the stress data in each time window, and calculating the correlation coefficient value, to generate the magnetic stress coupling coefficient. The magnetic stress coupling coefficient is usually between 0 and 1, and the closer to 1 indicates that the dynamic correlation between the magnetic field intensity and the stress is stronger. For example, using the Pearson correlation coefficient calculation method, the magnetic stress coupling coefficient between the magnetic field intensity and the stress data in the 1st to 5th second time window is calculated to be 0.85, indicating that there is a positive correlation between the magnetic field and the stress. The above calculation method is continuously performed in multiple consecutive time windows to obtain a magnetic stress coupling coefficient sequence; each value in the magnetic stress coupling coefficient sequence reflects the dynamic correlation between the magnetic field intensity and the stress in the corresponding time window.

[0081] The coupling enhancement interval in the magnetic stress coupling coefficient sequence is screened, and the corresponding core space position is marked as a magnetic stress interaction enhancement region;

[0082] The coupling enhancement interval refers to the continuous time period in the magnetic stress coupling coefficient sequence where the magnetic stress coupling coefficient exceeds a pre-set magnetic stress coupling coefficient threshold. For example, if the magnetic stress coupling coefficient threshold is set to 0.75, and the magnetic stress coupling coefficient sequence in the 1st to 3rd second is 0.80, 0.82, and 0.85, respectively, all of which exceed the magnetic stress coupling coefficient threshold, then the continuous time period is marked as a coupling enhancement interval, and the corresponding space position, such as position coordinates (x2, y2, z2), is marked as a magnetic stress interaction enhancement region, determining the core space region where the interaction between the magnetic field and the stress is significantly enhanced.

[0083] The coupling coefficient mean, coupling coefficient variance, and frequency domain amplitude are extracted in the magnetic stress interaction enhancement region, and the characteristic data of the core magnetic field and stress interaction are output;

[0084] The characteristic data is obtained through statistical and frequency domain feature analysis. For example, in the magnetic stress interaction enhancement region at position coordinates (x2, y2, z2) from the 1st to 3rd second, the coupling coefficients are 0.80, 0.82, and 0.85, respectively, then the coupling coefficient mean is calculated to be 0.823, and the variance is 0.00042, and through Fourier spectrum analysis, the frequency domain amplitude at the magnetic stress coupling coefficient frequency of 0.5 Hz is calculated to be 0.015, which together constitute the characteristic data of the core magnetic field and stress interaction.

[0085] S4: According to the temperature abnormal fluctuation characteristics of the core micro-deformation region, analyze the interference intensity of the core temperature abnormal change on the uniformity of the core annealing heat distribution, and output the temperature disturbance intensity data, including:

[0086] determine the spatial coordinate position corresponding to the core micro-deformation region based on the temperature abnormal fluctuation characteristics of the core micro-deformation region, and extract the real-time temperature data sequence of the spatial coordinate position in the time sequence synchronization data;

[0087] The temperature abnormal fluctuation characteristics include the time domain mean, variance, and frequency domain amplitude of the temperature data in a specific time interval, reflecting the amplitude, frequency, and stability information of the local temperature change. Through the analysis of the temperature abnormal fluctuation characteristics, the position coordinates of the micro-deformation region can be confirmed. For example, during the annealing process of the wound transformer core, the position coordinates of the micro-deformation region are determined as (x2, y2, z2). In order to analyze the real-time temperature change of the micro-deformation region, based on the time sequence synchronization data of temperature and magnetic field, the complete real-time temperature data sequence corresponding to the position coordinates is extracted. The real-time temperature data sequence records the real-time temperature change of the position coordinates at each time during the entire annealing process of the core, reflecting the whole process of temperature change in the micro-deformation region. For example, the real-time temperature data of the position coordinates (x2, y2, z2) from the 1st second to the 10th second are 550 degrees Celsius, 551 degrees Celsius, 552 degrees Celsius, 560 degrees Celsius, 563 degrees Celsius, 559 degrees Celsius, 558 degrees Celsius, 556 degrees Celsius, 555 degrees Celsius, and 553 degrees Celsius, reflecting the dynamic process of rapid temperature rise and subsequent gradual decline in the micro-deformation region during the annealing process.

[0088] A spatial neighborhood with a preset spatial radius is constructed around the spatial coordinate position corresponding to the core micro-deformation region.

[0089] In order to quantitatively analyze the influence of temperature abnormal change in the core micro-deformation region on the uniformity of the overall annealing heat distribution of the core, a proper spatial range is set around the core micro-deformation region to obtain sufficient spatial comparison temperature data; the set spatial range is the spatial neighborhood. The spatial neighborhood is a three-dimensional or two-dimensional region with the spatial position coordinates of the micro-deformation region (such as (x2, y2, z2)) as the center and extending in all directions of the core with a preset spatial radius, forming a solid or two-dimensional region with the center position as the origin. The size of the preset spatial radius is determined according to the size of the core and the actual process conditions, for example, 10 to 50 mm. For example, the preset spatial radius is determined as 20 mm, and the spatial neighborhood is determined with the position coordinates (x2, y2, z2) as the center and 20 mm as the radius; the spatial neighborhood may contain several different spatial coordinate positions, such as (x2+5, y2, z2), (x2-10, y2, z2), (x2, y2+15, z2), etc., forming a spatial position set. Through the setting of the spatial neighborhood, the real-time temperature data of the micro-deformation region and the neighborhood region can be compared and analyzed to evaluate the interference degree of the temperature abnormal change in the micro-deformation region on the overall temperature uniformity of the core.

[0090] extracting time domain temperature difference of real-time temperature data sequence in spatial neighborhood;

[0091] In the range of spatial neighborhood, the real-time temperature data sequence of all spatial position points are compared with each other, and the temperature difference in the time domain is calculated. The temperature difference reflects the non-uniform distribution of the temperature field in the vicinity of the micro-deformation region. For example, the real-time temperature data at the position coordinates (x2+5, y2, z2) in the spatial neighborhood is 552 degrees Celsius, 553 degrees Celsius, 554 degrees Celsius, 555 degrees Celsius, and 556 degrees Celsius, and the real-time temperature data at (x2-10, y2, z2) is 551 degrees Celsius, 552 degrees Celsius, 553 degrees Celsius, 554 degrees Celsius, and 555 degrees Celsius. The real-time temperature data of the micro-deformation region (x2, y2, z2) is 560 degrees Celsius, 563 degrees Celsius, 559 degrees Celsius, 558 degrees Celsius, and 556 degrees Celsius from the 3rd second to the 7th second. By comparing the real-time temperature data of different spatial positions with each other, it can be found that there is a significant difference between the temperature of the micro-deformation region and the temperature of the surrounding spatial positions, for example, the temperature of the micro-deformation region is 563 degrees Celsius at the 4th second, and the temperature of the surrounding spatial positions is lower than 556 degrees Celsius, with a temperature difference of 7 degrees Celsius, which reflects the time domain temperature difference characteristics in the spatial neighborhood. By calculating the time domain temperature difference characteristics, the interference degree of the temperature anomaly of the micro-deformation region on the uniformity of the overall annealing heat distribution of the core is reflected.

[0092] According to the time domain temperature difference, the interference intensity of the temperature abnormal change of the core micro-deformation region on the overall annealing heat distribution uniformity of the core is determined, and the temperature disturbance intensity data of the core micro-deformation region is output;

[0093] The interference intensity is the difference between the real-time temperature data of the micro-deformation region and the real-time temperature data of other positions in the spatial neighborhood in the time dimension, which is processed by the mean method or the mean square error method to quantify the disturbance degree of the micro-deformation region on the temperature of the spatial neighborhood. For example, in the temperature fluctuation period from the 3rd second to the 7th second, the average value of the temperature difference between the micro-deformation region and the neighborhood position is calculated every second, and the temperature difference is 6 degrees Celsius, 7 degrees Celsius, 5 degrees Celsius, 4 degrees Celsius, and 3 degrees Celsius. By taking the average value of the temperature difference, the average disturbance intensity is 5 degrees Celsius, which reflects the average disturbance degree of the micro-deformation region on the temperature of the neighborhood. At the same time, the standard deviation of the temperature difference is calculated to reflect the stability of the disturbance, for example, the standard deviation of the disturbance intensity is 1.414 degrees Celsius. In addition, the frequency domain analysis method is used to calculate the frequency spectrum amplitude of the temperature difference, which is used to evaluate the periodic characteristics and dynamic change trend of the disturbance. For example, the main frequency of the disturbance is determined to be 0.25 Hz by frequency domain analysis, and the frequency domain amplitude is 1.2 degrees Celsius, which together constitutes the temperature disturbance intensity data of the core micro-deformation region, reflecting the interference degree and change characteristics of the temperature anomaly of the micro-deformation region on the overall annealing heat distribution uniformity of the core.

[0094] S5: Based on the characteristic data of the interaction between the magnetic field of the core and the stress and the temperature disturbance intensity data of the core, a coupled abnormal evolution model of the magnetic field-thermal field-stress field is established, and core annealing abnormality evaluation data is generated, including:

[0095] Synchronize and align the characteristic data of the interaction between the magnetic field of the core and the stress and the temperature disturbance intensity data of the core micro-deformation region according to the time axis to generate a coupled input matrix;

[0096] The characteristic data of the interaction between the magnetic field of the core and the stress includes the mean, variance and frequency domain amplitude of the coupling coefficient in the magnetic stress interaction enhancement region. The characteristic data represents the change trend and amplitude of the dynamic interaction between the magnetic field and the mechanical stress in the core micro-deformation region. The temperature disturbance intensity data of the core micro-deformation region is represented by the average, standard deviation and frequency domain amplitude of the disturbance intensity, which reflects the interference degree and change law of the local temperature anomaly in the micro-deformation region on the overall core temperature distribution uniformity during the annealing process. Since the characteristic data of the interaction between the magnetic field of the core and the stress and the temperature disturbance intensity data come from different analysis paths, they need to be synchronized and aligned according to a unified time axis to show the synchronous change relationship between the core magnetic field, mechanical stress and temperature disturbance. For example, the time sampling points of the characteristic data of the interaction between the magnetic field of the core and the stress and the temperature disturbance intensity data of the core micro-deformation region are uniformly adjusted to be sampled once every 1 second; if the sampling points of the characteristic data of the interaction between the magnetic field and the stress are originally located at integer seconds such as 1st, 2nd and 3rd seconds, and the sampling points of the temperature disturbance intensity data are located at 1.5th and 2.5th seconds, the sampling points of the temperature disturbance intensity data can be adjusted to integer seconds by linear interpolation method. For example, at the 2nd second, if the mean of the magnetic stress coupling coefficient in the magnetic stress interaction characteristic data is 0.82, the variance is 0.0004, and the frequency domain amplitude is 0.015, and the disturbance intensity average of the temperature disturbance intensity data after interpolation adjustment is 5 degrees Celsius, the standard deviation is 1.4 degrees Celsius, and the frequency domain amplitude is 1.2 degrees Celsius, then at the 2nd second of the time axis, the magnetic field-stress-temperature synchronous characteristic data set is formed. According to the above method, the data of each sampling time point is uniformly aligned to form a multi-dimensional data sequence containing magnetic field, stress and temperature parameters at each time point based on the time axis, which is defined as a coupled input matrix. The coupled input matrix reflects the synchronous dynamic relationship of the magnetic field, stress and temperature at each moment during the core annealing process.

[0097] Normalize the coupled input matrix and unify the data dimensions;

[0098] The data in the coupling input matrix includes parameters of three different physical fields of magnetic field, mechanical stress and temperature. The numerical dimension and numerical range of the parameters are different. For example, the unit of magnetic field strength is Gauss, and the value is usually in the range of several tens to several hundreds. The unit of mechanical stress is megapascal (MPa), and the numerical range is usually in the range of several to several tens of megapascal. The unit of temperature disturbance strength is Celsius, and the value is in the range of several degrees Celsius. In order to avoid the influence of the difference in the numerical order of magnitude between different physical parameters, all the data in the coupling input matrix are normalized to unify the numerical range of each data dimension to the same standard range, for example, between 0 and 1. The minimum-maximum normalization method is adopted, that is, the minimum value and the maximum value of each parameter sequence are calculated respectively, and the formula is: normalized data value=(original data value-minimum value) / (maximum value-minimum value). All data are converted to the interval of 0 to 1. Through the above method, each physical field parameter is uniformly normalized, and finally the different physical quantity data in the coupling input matrix are in the same dimensionless numerical range, eliminating the influence of the difference in dimension and amplitude between different data.

[0099] Based on the coupling input matrix, a coupling abnormal evolution model of magnetic field-thermal field-stress field is established.

[0100] The coupling abnormal evolution model includes a coupling equation set and a time sequence parameter matrix. The coupling equation set refers to a mathematical equation established according to physical laws and statistical analysis methods, which reflects the quantitative relationship between the dynamic interaction of magnetic field, stress and temperature. For example, a mathematical equation is established by using linear or nonlinear multiple regression analysis, the magnetic field strength change, stress change and temperature disturbance data are respectively taken as the independent variables of the equation, and the coupling abnormal state is defined as the dependent variable, for example: coupling abnormal state index=coefficient A x normalized magnetic field data+coefficient B x normalized stress data+coefficient C x normalized temperature data, wherein the coefficients A, B and C are determined according to historical data regression analysis. The time sequence parameter matrix is a data matrix composed of synchronous normalized data at each time point. Each row represents a time point, and each column represents the values of magnetic field, stress and temperature respectively. The coupling equation set and the time sequence parameter matrix together constitute the coupling abnormal evolution model of magnetic field-thermal field-stress field, so that the complex coupling relationship between magnetic field, thermal field and stress field is quantified and calculated.

[0101] Based on the coupling abnormal evolution model, a coupling index sequence of magnetic field-thermal field-stress field is calculated, and a coupling abnormal interval is screened based on a preset coupling threshold value, and iron core annealing abnormality evaluation data is output.

[0102] According to the coupling abnormal evolution model, each time point data in the time sequence parameter matrix is substituted into the coupling equation set for calculation one by one to generate the magnetic field-thermal field-stress field coupling index at each moment. The coupling indexes at continuous moments form a coupling index sequence. For example, the coupling index ranges from 0 to 1, and the closer to 1 indicates that the coupling between the three physical fields is abnormally strong. Then, the coupling indexes at continuous moments are screened by a preset coupling threshold (such as 0.8) to determine the continuous time period exceeding the preset coupling threshold as the coupling abnormal interval. For example, the coupling indexes from the 5th second to the 8th second are 0.81, 0.85, 0.83, and 0.80 in turn, and it is determined that this period is the coupling abnormal interval. The core annealing abnormality evaluation data is the magnetic field-thermal field-stress field coupling index in the coupling abnormal interval.

[0103] S6: According to the core annealing abnormality evaluation data, the quality fluctuation risk of the core annealing process is evaluated, and intelligent early warning information of the core annealing abnormality is generated, including:

[0104] The core annealing abnormality evaluation data is divided into multiple time windows, and the average value and the variance of the core annealing abnormality evaluation data in each time window are extracted;

[0105] The length of the time window is preset according to the actual core annealing process requirement, which can be 5 seconds, 10 seconds or longer. For example, it is determined that 10 seconds is the standard time window length, and the annealing process time, for example, from the 0th second to the 100th second, is divided into independent time windows of 10 seconds each, generating the 0th second to the 10th second, the 10th second to the 20th second, the 20th second to the 30th second, and so on, forming continuous multiple time windows of the same length. The average value and the variance of all coupling indexes in each time window are calculated. The average value is used to quantify the overall level of the coupling index in each time window, and the variance is used to evaluate the fluctuation amplitude of the data in each window. For example, in the time window from the 10th second to the 20th second, if the core annealing abnormality evaluation data in the time window is 0.81, 0.83, 0.85, 0.84, 0.82, 0.86, 0.87, 0.85, 0.84, 0.83, the average value is 0.84, and the variance is 0.0004. Similarly, the above calculation is performed for each time window to obtain the average value and the variance of the core annealing abnormality evaluation data of multiple time windows.

[0106] The deviation of the average value and the variance of the core annealing abnormality evaluation data in each time window relative to the preset normal threshold is calculated to obtain the core annealing quality fluctuation risk index;

[0107] The preset normal threshold is a standard determined according to historical data of the coupling index sequence of the magnetic field-thermal field-stress field of the core under the normal running state of the annealing process, and reflects the coupling characteristics between the magnetic field, the thermal field and the stress field under the normal annealing process condition. For example, through a large amount of historical process data analysis, it is determined that the average value threshold of the magnetic field-thermal field-stress field coupling index under the normal state in the core annealing process is 0.75, and the variance threshold is 0.0002. The core annealing quality fluctuation risk index is obtained by comparing the average value and the variance calculated in each time window with the normal threshold, and quantitatively describing the severity of the deviation of the abnormal evaluation data in each time window from the normal state. For example, for the time window from the 10th second to the 20th second, the calculated average value is 0.84 and the variance is 0.0004, and the deviation degree is calculated respectively, wherein the average value deviation degree is (0.84-0.75) / 0.75x100%=12%, and the variance deviation degree is (0.0004-0.0002) / 0.0002x100%=100%. Through a weighted method, for example, the average value deviation degree weight is 60%, and the variance deviation degree weight is 40%, then the final core annealing quality fluctuation risk index of the time window is determined as: 12% x 60% + 100% x 40% = 47.2%. The same method is used to obtain the core annealing quality fluctuation risk index of all time windows, which reflects the quantitative evaluation information of the quality fluctuation risk of the core annealing process in each time window.

[0108] According to the core annealing quality fluctuation risk index, the risk level of each time window in the core annealing process is determined;

[0109] The risk level is divided into three levels of low risk, medium risk and high risk, and each level corresponds to the interval range of the core annealing quality fluctuation risk index. For example, it is set that the core annealing quality fluctuation risk index between 0% and 20% is the low risk level, indicating that the core annealing process is in a basically normal range; the index between 20% and 40% is the medium risk level, indicating that the core annealing process has a certain degree of abnormal risk and needs attention; and the index above 40% is the high risk level, indicating that the core annealing process state deviates from the normal range seriously and has a significant quality abnormal risk. According to the calculated core annealing quality fluctuation risk index of each time window, for example, the index of the 10th second to the 20th second window is 47.2%, and the risk level of this time window is determined as the high risk level according to the risk level division rule. If the index of the 20th second to the 30th second window is 15%, the risk level is determined as the low risk level. Through the above method, the risk level of the core annealing process in each time window is determined.

[0110] For the time window whose risk level exceeds the preset risk level threshold, it is marked as an annealing quality abnormal period, and the core annealing abnormal intelligent early warning information containing the risk level, the start and end time and the corresponding core spatial position is generated.

[0111] The preset risk level threshold is used to determine the abnormal state requiring intervention or treatment. For example, the risk level above the medium risk level (including the medium risk level and the high risk level) is set as the preset risk level threshold. The time window with all risk levels exceeding the risk level threshold is marked as the annealing quality abnormal period. For example, the case that the risk level is high risk level in the 10th to 20th second time window is marked, and the time window is determined as the annealing quality abnormal period. At the same time, the core annealing abnormal intelligent early warning information of the abnormal period is generated, including the abnormal risk level (high risk level), the abnormal start and end time (10th to 20th second), and the core space position coordinates (such as (x2, y2, z2)) corresponding to the abnormality. The above intelligent early warning information is output to the monitoring terminal or the equipment management platform in the form of visual graphics or list, and timely prompts the operator to manually intervene or detect the core annealing abnormal area, so as to ensure the stability and reliability of the core annealing process quality.

[0112] The above formulas are all dimensionless numerical calculations, and the formulas are obtained by software simulation of a large amount of data to obtain a formula of the nearest real situation. The preset parameters and threshold values in the formula are set by the person skilled in the art according to the actual situation.

[0113] The above embodiments can be realized wholly or partially by software, hardware, firmware or any other combination. When realized by software, the above embodiments can be realized wholly or partially in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable devices. The computer instructions can be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.) mode. The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center and the like containing one or more available medium collections. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid state disk.

[0114] Those of skill in the art would understand that the modules and algorithms described in connection with the examples described herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. The

[0115] Those of skill in the art would understand that, for the purposes of description and brevity, the above description has described the system, device and module in detail, and the corresponding process in the foregoing method embodiments can be referred to for the specific working process of the system, device and module, which will not be described here.

[0116] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the device embodiments described above are merely illustrative, for example, the division of the modules is merely a logical function division, and actual implementation can have another division manner, for example, a plurality of modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed modules can be indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0117] The modules described as separate components can or can not be physically separated, and the components displayed as modules can or can not be physical modules, which can be located in one place or distributed on a plurality of network modules. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0118] In addition, the functional modules in each embodiment of the present application can be integrated in one processing module, or each module can exist physically, or two or more modules can be integrated in one module.

[0119] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0120] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0121] Finally: the above is only a preferred embodiment of the present application and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A method for intelligent monitoring of the annealing process of a wound transformer core, characterized in that, Includes the following steps: S1: Collect temperature and magnetic field strength data generated by the core of the wound transformer during the annealing process, perform time-domain synchronization processing and anomaly data labeling, and generate time-series synchronized data of temperature and magnetic field. S2: Based on the time-series synchronized data of temperature and magnetic field, identify the micro-deformation region of the iron core and the corresponding temperature anomaly region, and generate the temperature anomaly fluctuation characteristics of the micro-deformation region of the iron core, specifically: The magnetic field strength difference and corresponding temperature difference between adjacent sampling points are calculated based on time-series synchronous data to generate magnetic field gradient sequences and temperature gradient sequences. The initial candidate region for micro-deformation of the iron core is determined in the magnetic field gradient sequence based on a preset magnetic field gradient threshold. Based on the preset temperature gradient threshold, candidate areas for temperature anomalies are determined in the temperature gradient sequence, and their spatial positions are matched with the initial candidate areas for micro-deformation of the iron core to determine the micro-deformation areas and temperature anomaly areas of the iron core that completely overlap in spatial position. Calculate the time-domain mean, time-domain variance, and frequency-domain amplitude of temperature data within the temperature anomaly region to generate the temperature anomaly fluctuation characteristics of the core micro-deformation region. S3: Based on the abnormal temperature fluctuation characteristics of the micro-deformation region of the iron core, analyze the dynamic coupling effect of stress changes on the magnetic field distribution, and output the characteristic data of the interaction between the iron core magnetic field and stress, specifically: Based on the abnormal temperature fluctuation characteristics of the micro-deformation region of the iron core, and combined with the thermal expansion coefficient and Young's modulus of the iron core material, a sequence of iron core stress variation is generated. The core stress variation sequence is registered with the time-series synchronous data to construct a joint matrix of stress and magnetic field. Correlation analysis was performed on the joint matrix of stress and magnetic field to obtain the magnetic stress coupling coefficient sequence. Screen the coupling enhancement intervals in the magnetic stress coupling coefficient sequence and mark the corresponding iron core spatial locations as magnetic stress interaction enhancement regions; In the magnetic stress interaction enhancement region, the mean value of the coupling coefficient, the variance of the coupling coefficient and the frequency domain amplitude are extracted to output the characteristic data of the interaction between the core magnetic field and stress. S4: Based on the abnormal temperature fluctuation characteristics of the micro-deformation region of the iron core, analyze the interference intensity of abnormal temperature changes on the uniformity of heat distribution during iron core annealing, and output the temperature disturbance intensity data, specifically: Based on the temperature anomaly fluctuation characteristics of the micro-deformation region of the iron core, the spatial coordinate position corresponding to the micro-deformation region of the iron core is determined, and the real-time temperature data sequence of the spatial coordinate position in the time-series synchronization data is extracted. A spatial neighborhood with a preset spatial radius is constructed, centered on the spatial coordinate position corresponding to the micro-deformation region of the iron core. Extract the temporal temperature difference of real-time temperature data sequences in the spatial neighborhood; Based on the time-domain temperature difference, determine the interference intensity of the abnormal temperature change in the micro-deformation region of the iron core on the overall annealing heat distribution uniformity of the iron core, and output the temperature disturbance intensity data of the micro-deformation region of the iron core. S5: Based on the characteristic data of the interaction between the core magnetic field and stress, and the core temperature disturbance intensity data, a coupled anomaly evolution model of the magnetic field-thermal field-stress field is established to generate core annealing anomaly assessment data, specifically: The characteristic data of the interaction between the magnetic field and stress in the iron core are synchronized and aligned with the temperature disturbance intensity data of the micro-deformation region of the iron core according to the time axis to generate a coupled input matrix; Normalize the coupled input matrix and unify the data dimensions; A coupled anomaly evolution model of magnetic field-thermal field-stress field is established based on the coupled input matrix; The magnetic field-thermal field-stress field coupling index sequence is calculated based on the coupling anomaly evolution model, and the coupling anomaly interval is screened based on the preset coupling threshold to output the iron core annealing anomaly assessment data. S6: Based on the core annealing anomaly assessment data, evaluate the quality fluctuation risk of the core annealing process and generate intelligent early warning information for core annealing anomalies, specifically: The core annealing anomaly assessment data was divided into multiple time windows, and the mean and variance of the core annealing anomaly assessment data were extracted within each time window. The deviation of the average and variance of the iron core annealing anomaly assessment data within each time window from the preset normal threshold is calculated to obtain the iron core annealing quality fluctuation risk index. The risk level of each time window in the iron core annealing process is determined based on the risk index of iron core annealing quality fluctuation. For time windows where the risk level exceeds the preset risk level threshold, mark them as periods of abnormal annealing quality, and generate intelligent early warning information for abnormal core annealing that includes the risk level, start and end time, and corresponding core spatial location.

2. The intelligent monitoring method for the annealing process of a wound transformer core according to claim 1, characterized in that, S1, specifically: Real-time temperature data of the core of a wound transformer during the annealing process was collected. Real-time magnetic field strength data of the core of a wound transformer during the annealing process were collected. Real-time temperature data and real-time magnetic field strength data are aligned according to a unified time axis and integrated synchronously into a unified time-series data sequence. Abnormal data points that exceed the preset normal range in a unified time-series data sequence are marked as abnormal data to form time-series synchronized data of temperature and magnetic field.

Images