Fault Self-Diagnosis Method and System for Temperature Transmitters under Real-Time Monitoring

Abstract

This invention discloses a fault self-diagnosis method and system for temperature transmitters under real-time monitoring, belonging to the field of fault self-diagnosis technology. The method includes: collecting spatial location information and operating status parameters of high-frequency electrical equipment; combining this with the spatial location information of the target temperature transmitter to perform electromagnetic interference analysis and generate an electromagnetic interference distribution map; establishing an electromagnetic-temperature influence correlation; deploying electromagnetic interference sensing modules to obtain electromagnetic interference change curves; and monitoring temperature signal fluctuation curves in real time; performing correlation comparison analysis to generate correlation matching results; and when abnormal matching results are found, reconstructing the temperature transmitter signal to generate transmitter compensation parameters for signal correction and providing fault risk warnings. This invention solves the technical problem in the prior art where faults in temperature transmitters are difficult to detect and accurately locate in a timely manner when affected by electromagnetic interference, achieving the technical effect of improving the accuracy and real-time performance of temperature transmitter fault diagnosis.

Description

Technical Field

[0001] This invention relates to the field of fault self-diagnosis technology, specifically to a fault self-diagnosis method and system for temperature transmitters under real-time monitoring. Background Technology

[0002] In industrial settings, temperature transmitters typically operate in conjunction with high-frequency electrical equipment such as frequency converters, motors, and high-power transformers. These devices generate varying degrees of electromagnetic interference (EMI) during operation. Because the effects of EMI are often insidious and gradual, conventional temperature signal monitoring methods struggle to effectively identify signal fluctuations caused by it. Furthermore, the complex temporal and spatial coupling characteristics of EMI's impact on temperature signals make fault location and fault type identification difficult, consequently affecting the stable operation of temperature transmitters and the accuracy of fault warnings. Summary of the Invention

[0003] This application provides a fault self-diagnosis method and system for temperature transmitters under real-time monitoring, which is used to address the technical problem that faults in temperature transmitters are difficult to detect and accurately locate in a timely manner when affected by electromagnetic interference in the prior art.

[0004] In view of the above problems, this application provides a fault self-diagnosis method and system for temperature transmitters under real-time monitoring.

[0005] The first aspect of this application provides a fault self-diagnosis method for a temperature transmitter under real-time monitoring, the method comprising:

[0006] Based on the real-time industrial environment, spatial location information and operating status parameters of high-frequency electrical equipment within the area are collected. Combined with the spatial location information of the target temperature transmitter, electromagnetic interference (EMI) analysis is performed to generate an EMI distribution map. Based on the EMI distribution map, an EMI-temperature influence correlation is established, and EMI sensing modules are deployed. EMI monitoring is performed based on the EMI sensing modules to obtain EMI change curves. Simultaneously, the temperature signal fluctuation curve of the target temperature transmitter is monitored in real time. The EMI change curve and the temperature signal fluctuation curve are compared and analyzed to generate a correlation matching result. If an abnormal match is found in the correlation matching result, the temperature transmitter signal is reconstructed based on the EMI-temperature influence correlation, transmitter compensation parameters are generated to correct the transmitter signal, and a fault risk warning is issued based on the interference intensity.

[0007] A second aspect of this application provides a fault self-diagnosis system for a temperature transmitter under real-time monitoring, the system comprising:

[0008] The system comprises the following modules: a parameter acquisition module, a sensor module, and a risk warning module. The parameter acquisition module collects spatial location information and operating status parameters of high-frequency electrical equipment within a real-time industrial environment. Combined with the spatial location information of the target temperature transmitter, it performs electromagnetic interference (EMI) analysis and generates an EMI distribution map. The sensor module deployment module establishes an EMI-temperature correlation based on the EMI distribution map and deploys EMI sensor modules. The interference monitoring module monitors EMI based on the sensor modules, acquires EMI variation curves, and simultaneously monitors the temperature signal fluctuation curve of the target temperature transmitter in real time. The comparison and analysis module performs a correlation comparison analysis between the EMI variation curve and the temperature signal fluctuation curve, generating a correlation matching result. The risk warning module reconstructs the temperature transmitter signal based on the EMI-temperature correlation when an abnormal match is found in the correlation matching result, generates transmitter compensation parameters for signal correction, and provides a fault risk warning based on the interference intensity.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] This application, based on a real-time industrial environment, collects spatial location information and operating status parameters of high-frequency electrical equipment within the area. Combined with the spatial location information of the target temperature transmitter, it performs electromagnetic interference (EMI) analysis to generate an EMI distribution map. Based on the EMI distribution map, it establishes an electromagnetic-temperature influence correlation and deploys an EMI sensing module. Based on the EMI sensing module, it monitors EMI and obtains EMI change curves. Simultaneously, it monitors the temperature signal fluctuation curve of the target temperature transmitter in real time. It performs correlation comparison analysis between the EMI change curve and the temperature signal fluctuation curve to generate a correlation matching result. When an abnormal match is found in the correlation matching result, it reconstructs the temperature transmitter signal based on the EMI-temperature influence correlation, generates transmitter compensation parameters to correct the transmitter signal, and provides a fault risk warning based on the interference intensity. This invention addresses the technical problem in the prior art where faults in temperature transmitters are difficult to detect and accurately locate in a timely manner when affected by electromagnetic interference. By constructing an electromagnetic interference distribution map, establishing an electromagnetic-temperature influence correlation, and introducing a correlation comparison and signal reconstruction mechanism, it achieves timely identification and compensation correction of temperature anomalies caused by electromagnetic interference, thereby improving the accuracy and real-time performance of temperature transmitter fault diagnosis. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 A schematic flowchart of a fault self-diagnosis method for a temperature transmitter under real-time monitoring provided in an embodiment of this application;

[0013] Figure 2 This is a schematic diagram of the fault self-diagnosis system for a temperature transmitter under real-time monitoring provided in an embodiment of this application.

[0014] Explanation of reference numerals in the attached diagram: Parameter acquisition module 11, Sensor module deployment module 12, Interference monitoring module 13, Comparison and analysis module 14, Risk warning module 15. Detailed Implementation

[0015] This application provides a fault self-diagnosis method and system for temperature transmitters under real-time monitoring. It addresses the technical problem in the prior art that faults in temperature transmitters are difficult to detect and accurately locate in a timely manner when affected by electromagnetic interference. By constructing an electromagnetic interference distribution map, establishing an electromagnetic-temperature influence correlation, and introducing a correlation comparison and signal reconstruction mechanism, it achieves the technical effect of timely identification and compensation correction of temperature anomalies caused by electromagnetic interference, thereby improving the accuracy and real-time performance of temperature transmitter fault diagnosis.

[0016] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0017] It should be noted that any variation of the terms "comprising" and "having" is intended to cover non-exclusive inclusion, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or modules that are not explicitly listed or that are inherent to such processes, methods, products, or devices.

[0018] Example 1, as Figure 1 As shown, this application provides a fault self-diagnosis method for a temperature transmitter under real-time monitoring, the method comprising:

[0019] Step S100: Based on the real-time industrial environment, collect the spatial location information and operating status parameters of high-frequency electrical equipment in the area, combine them with the spatial location information of the target temperature transmitter, perform electromagnetic interference analysis, and generate an electromagnetic interference distribution map.

[0020] In this embodiment, in a real-time industrial environment, spatial coordinate information and operating status parameters (including operating frequency, current, voltage, etc.) of various high-frequency electrical devices (such as frequency converters, motors, etc.) within the area are acquired through industrial IoT nodes, and the spatial location information of the target temperature transmitter is collected simultaneously. Subsequently, based on the collected spatial coordinate and location information, an electromagnetic field propagation model is constructed. Finally, according to the electromagnetic field propagation model and combined with the operating status parameters of each high-frequency electrical device, the electromagnetic radiation intensity from each device to the temperature transmitter is calculated, and an electromagnetic interference distribution map including spatial location relationships and electromagnetic coupling strength is established.

[0021] Furthermore, the method provided in the application embodiment, based on the real-time industrial environment, collects the spatial location information and operating status parameters of high-frequency electrical equipment in the area, and combines this with the spatial location information of the target temperature transmitter to perform electromagnetic interference analysis, further includes:

[0022] Through industrial IoT nodes, the operating status parameters and spatial coordinate information of high-frequency electrical equipment in the target industrial environment, as well as the spatial location information of the target temperature transmitter, are collected in real time. Based on the spatial coordinate information of the high-frequency electrical equipment and the spatial location information of the target temperature transmitter, an electromagnetic field propagation model is built. According to the electromagnetic field propagation model, combined with the operating status parameters of each high-frequency electrical equipment, the electromagnetic radiation intensity from each device to the temperature transmitter is calculated, and an electromagnetic interference distribution map including spatial position relationship and electromagnetic coupling strength is established.

[0023] In this embodiment, within the target industrial environment, industrial IoT nodes are first deployed at the ports of each high-frequency electrical device to collect real-time operating status parameters and spatial coordinate information of each device. The operating status parameters include operational characteristic indicators such as the device's switching frequency (e.g., 15kHz), output current amplitude (e.g., 12A), and voltage amplitude (e.g., 380V). The spatial coordinate information uses a unified plant coordinate system for three-dimensional positioning (e.g., X=25.3m, Y=42.8m, Z=4.2m). Simultaneously, the spatial location information of the target temperature transmitter is acquired synchronously through the same industrial IoT system, for example, its installation point X=20.0m, Y=40.0m, Z=4.0m.

[0024] Subsequently, an electromagnetic field propagation model is constructed based on the spatial coordinates of the high-frequency electrical equipment and the spatial location of the target temperature transmitter. Specifically, the straight-line distance between each device and the temperature transmitter is first calculated, and then the presence of spatial obstructions such as concrete walls, steel plates, or equipment frames along the propagation path is identified. If the path is unobstructed, a direct propagation path is constructed based on the straight-line distance; if obstacles exist, penetration or reflection paths are considered, and a corresponding attenuation factor is assigned to each type of obstacle material. After determining the path, the electromagnetic radiation intensity at the temperature transmitter location is calculated based on the electrical parameters of each device. The calculation method is as follows: first, the electromagnetic field strength value at a standard distance (e.g., 1 meter) of the device is determined, which is calculated using a known model based on the device's switching frequency, current, and voltage parameters. Next, distance attenuation is calculated using the spatial propagation formula based on the straight-line distance between the two devices; finally, the corresponding material attenuation value is superimposed based on the material and thickness of the obstacles in the path to obtain the final field strength value of the device at the temperature transmitter. For example, a frequency converter operates at a frequency of 15kHz, the device is 10 meters away from the temperature transmitter, and the path passes through a concrete wall. The model calculates the electromagnetic field strength at 1 meter to be 90 dBμV / m. A distance of 10 meters introduces approximately 30 dB of spatial attenuation, and the concrete wall introduces an additional 10 dB of attenuation. Therefore, the electromagnetic radiation intensity at the temperature transmitter location is 90 dBμV / m - 30 dB - 10 dB = 50 dBμV / m. By repeating the above steps for all high-frequency electrical equipment, the electromagnetic radiation intensity at the temperature transmitter location is calculated for each device.

[0025] Finally, the spatial location of each device and its corresponding electromagnetic radiation intensity are mapped to a unified coordinate system, and the calculation results are summarized in the spatial grid to generate an electromagnetic interference distribution map.

[0026] Step S200: Based on the electromagnetic interference distribution map, establish the electromagnetic-temperature influence correlation and deploy the electromagnetic interference sensing module.

[0027] In this embodiment, when establishing the electromagnetic-temperature influence correlation based on the electromagnetic interference distribution map, a long-term monitoring method is first used to continuously collect and statistically analyze the electromagnetic radiation intensity of each high-frequency electrical device, extracting the trend of interference intensity changing over time to form a gradual change law of electromagnetic interference. Subsequently, combined with the electromagnetic interference distribution map, a gradual interference analysis is carried out to identify the correlation characteristics between the change of interference intensity and the temperature signal response, constructing a four-dimensional electromagnetic environment evolution law that includes the electromagnetic-temperature influence correlation, i.e., forming a dynamic evolutionary characteristic.

[0028] Based on this, technical experts selected representative locations as sensor deployment points according to the strong coupling area and change-sensitive area reflected in the electromagnetic interference distribution map and the electromagnetic-temperature influence correlation, and deployed electromagnetic interference sensing modules with multi-band sensing capabilities.

[0029] Furthermore, in the method provided in the application embodiments, establishing the electromagnetic-temperature influence correlation based on the electromagnetic interference distribution spectrum further includes:

[0030] Long-term monitoring is adopted to accumulate and statistically analyze the changing trends of electromagnetic radiation intensity of each interference source, and predict the gradual change law of electromagnetic interference intensity. Based on the gradual change law, combined with the electromagnetic interference distribution map, a gradual interference analysis is performed to establish an electromagnetic-temperature influence correlation. The electromagnetic-temperature influence correlation includes the four-dimensional electromagnetic environment evolution law in the time dimension.

[0031] In this embodiment of the application, a long-term monitoring method is first adopted to continuously collect data from multiple high-frequency electrical devices through industrial Internet of Things nodes, record their operating status parameters such as switching frequency, output current, and voltage amplitude at different operating stages, and simultaneously collect the electromagnetic radiation intensity at the corresponding locations to construct a time series of electromagnetic radiation intensity from multiple interference sources.

[0032] Subsequently, based on the electromagnetic radiation intensity time series, a sliding time window statistical method was used to extract the trend of electromagnetic radiation variation of each device over time, and to analyze the interference intensity variation pattern under different operating states (such as startup, steady state, and load switching). For example, within 40 minutes of continuous operation of a certain high-frequency device, the radiation intensity showed a slow upward trend, which was recorded as a gradual interference mode.

[0033] Next, the above radiation variation trend is combined with the spatial positional relationship between each device and the target temperature transmitter in the electromagnetic interference distribution map to carry out gradual interference analysis and calculate the change of the intensity of the composite electromagnetic interference that may be received at the temperature transmitter location over time.

[0034] Based on this, the time series of temperature signal fluctuations of the target temperature transmitter within the same time period is extracted, and the response relationship between electromagnetic radiation changes and temperature signal fluctuations is compared using a time alignment analysis method. By analyzing the correspondence between the two in terms of fluctuation direction, amplitude changes, and response hysteresis, the influence process of interference changes on the temperature signal is identified.

[0035] Based on the above process, an electromagnetic-temperature influence correlation was finally established, clarifying how changes in radiation intensity affect the temperature transmitter under specific equipment operating conditions, causing fluctuations in the temperature output signal. This correlation comprehensively considers the spatial distribution, temporal evolution, and temperature response characteristics of electromagnetic interference, forming a four-dimensional electromagnetic environment evolution law that includes spatial location, temporal variation, electromagnetic intensity, and signal response.

[0036] After establishing the electromagnetic-temperature influence correlation, the deployment of electromagnetic interference sensing modules is carried out based on the significant interference areas and interference paths identified in the correlation. Priority is given to the areas surrounding temperature transmitters and regions sensitive to interference fluctuations as deployment points, and sensors capable of acquiring multi-frequency electromagnetic signals are deployed to achieve real-time interference monitoring of key interference sources and the transmitter environment.

[0037] Step S300: Perform electromagnetic interference monitoring based on the electromagnetic interference sensing module, obtain the electromagnetic interference change curve, and simultaneously monitor the temperature signal fluctuation curve of the target temperature transmitter in real time.

[0038] In this embodiment, firstly, the electromagnetic environment of the area where the temperature transmitter is located is continuously monitored based on the deployed electromagnetic interference sensing module. This electromagnetic interference sensing module has multi-frequency signal sensing capabilities, capable of simultaneously sensing electromagnetic interference signals within the ranges of power frequency (e.g., 50Hz), intermediate frequency (e.g., several kHz), and radio frequency (e.g., MHz). During operation, the electromagnetic interference sensing module senses changes in the intensity of the spatial electric or magnetic field through its built-in antenna array and records the collected electromagnetic signals in chronological order. After filtering and time series processing, the electromagnetic interference variation curve data over time is obtained.

[0039] Simultaneously, the output of the target temperature transmitter is synchronously acquired. The acquisition method involves acquiring temperature measurements at preset time intervals (e.g., once per second or higher) through the transmitter's signal output interface, continuously recording the change process of the transmitter's output temperature, and obtaining the temperature signal fluctuation curve.

[0040] Furthermore, in the method provided in the application embodiment, before performing correlation comparison analysis on the electromagnetic interference change curve and the temperature signal fluctuation curve to generate correlation matching results, a fluctuation anomaly analysis is first performed on the temperature signal fluctuation curve, which further includes:

[0041] The temperature signal fluctuation curve is subjected to moving average filtering to eliminate random measurement noise, and then signal abrupt change points and abnormal fluctuation intervals are detected and extracted; based on the signal abrupt change points and abnormal fluctuation intervals, temperature signal fluctuation characteristics are extracted.

[0042] In this embodiment, the temperature signal fluctuation curve is first subjected to moving average filtering. By setting a fixed-length sliding window (such as 5 or 10 consecutive sampling points), the temperature values ​​within the window are averaged and replaced with the original value of the current sampling point, thereby suppressing random measurement noise caused by sampling errors, short-period fluctuations or environmental disturbances.

[0043] After filtering, the smoothed temperature signal fluctuation curve undergoes abrupt change detection and abnormal fluctuation interval identification. Specifically, the temperature difference sequence between adjacent sampling points is calculated. If the difference exceeds a preset abrupt change threshold (e.g., ±1.5℃), it is marked as a signal abrupt change point. If the differences of multiple consecutive sampling points fluctuate significantly in the same direction (e.g., continuously increasing or decreasing), the time period is marked as an abnormal fluctuation interval. For example, if the temperature suddenly jumps from 65℃ to 71℃ over a certain period and maintains a high fluctuation state, this data segment is identified as an abnormal fluctuation interval.

[0044] Based on the above detection results, temperature signal fluctuation characteristics were extracted. These characteristics include the number of abrupt change points, the duration of abnormal intervals, the maximum temperature change amplitude, and the direction of the fluctuation trend. Specifically, the number of abrupt change points reflects the frequency of sudden anomalies; the duration of abnormal intervals reflects the duration of temperature fluctuations; the maximum temperature change amplitude reflects the intensity of the temperature response fluctuations; and the direction of the fluctuation trend is categorized as upward, downward, or bidirectional.

[0045] Step S400: Perform correlation comparison analysis on the electromagnetic interference change curve and the temperature signal fluctuation curve to generate correlation matching results.

[0046] In this embodiment, when performing correlation analysis between the electromagnetic interference change curve and the temperature signal fluctuation curve, the electromagnetic interference change curve is first analyzed to extract its corresponding electromagnetic fluctuation characteristics, which are then compared with the extracted temperature signal fluctuation characteristics to calculate the time-domain correlation coefficient between the two, thereby quantifying the degree of correlation between the electromagnetic interference intensity change and the temperature signal fluctuation. Subsequently, based on this time-domain correlation coefficient, the correlation level between the two is evaluated. If the level reaches or exceeds a preset correlation threshold, it is determined to be a temperature anomaly caused by electromagnetic interference, and a corresponding correlation matching result is generated accordingly.

[0047] Furthermore, in the method provided in the application embodiments, the process of performing correlation comparison analysis between the electromagnetic interference change curve and the temperature signal fluctuation curve to generate correlation matching results further includes:

[0048] Based on the electromagnetic interference change curve, electromagnetic fluctuation characteristics are extracted; based on the electromagnetic fluctuation characteristics, the temperature signal fluctuation characteristics are compared, and the time-domain correlation coefficient between the electromagnetic interference intensity change and the temperature signal fluctuation is calculated; based on the time-domain correlation coefficient, the correlation level between the electromagnetic interference change and the temperature fluctuation is determined; if the correlation level meets the preset correlation threshold, it is determined to be a temperature anomaly caused by electromagnetic interference, and the correlation matching result is generated according to the strength of the correlation.

[0049] In this embodiment, the electromagnetic interference variation curve is first feature extracted, and the electromagnetic field strength time series is processed by the window sliding extreme value detection method. Within the set time window, the maximum value, minimum value and variation trend of each data segment are identified, and electromagnetic wave characteristics are extracted, including information such as maximum interference intensity, interference change rate, duration of fluctuation interval and peak occurrence time.

[0050] Subsequently, the temperature signal fluctuation features extracted from the temperature signal fluctuation curve in the previous stage are invoked, including the location of temperature abrupt change points, the length of abnormal fluctuation intervals, and the maximum temperature fluctuation amplitude. To ensure the correspondence between the two curves in the time domain, the electromagnetic interference change curve and the temperature signal fluctuation curve are aligned and normalized along a unified time axis. This is achieved by subtracting their respective means and dividing by the standard deviation to standardize them, making the time series of different dimensions comparable and avoiding bias in the results caused by differences in data amplitude.

[0051] After time alignment and normalization, the Pearson correlation coefficient analysis method was used to compare the standardized electromagnetic wave characteristics with the temperature wave characteristics. The time-domain correlation coefficient r was calculated by statistically analyzing the relationship between the change in interference intensity and the change in temperature value at each moment. The r value represents the degree of linear correlation between the two time series in terms of the direction and trend of fluctuation, ranging from -1 to +1. r close to +1 indicates a positive correlation, meaning the temperature signal rises synchronously when the electromagnetic interference increases; r close to -1 indicates a negative correlation; and r close to 0 indicates no significant correlation. For example, within a certain analysis interval, if the electromagnetic field strength increases from 50 dBμV / m to 68 dBμV / m, and the temperature signal simultaneously rises from 65℃ to 70℃, the correlation coefficient calculated for the two sets of data after standardization is r = +0.82, indicating a significant positive synchronous relationship between the two signals.

[0052] Next, based on the calculated time-domain correlation coefficient *r*, and in conjunction with pre-defined correlation level standards, the correlation between electromagnetic interference changes and temperature fluctuations is assessed. Correlation levels are typically categorized as strong correlation (|r|≥0.8), moderate correlation (0.5≤|r|<0.8), weak correlation (0.3≤|r|<0.5), and no significant correlation (|r|<0.3). When the time-domain correlation coefficient reaches or exceeds a preset correlation threshold, such as moderate correlation or higher, the abnormal temperature fluctuations within that time period are determined to be caused by electromagnetic interference, and this determination serves as the basis for subsequent interference identification and signal correction.

[0053] Finally, the association matching results are generated, and the output includes whether a match is made, the matching time period, the main interference source device number, the calculated time domain correlation coefficient r value, and its corresponding correlation level.

[0054] Step S500: When the correlation matching result shows an abnormal match, the temperature transmission signal is reconstructed according to the electromagnetic-temperature influence correlation, the transmitter compensation parameters are generated to correct the transmission signal, and a fault risk warning is given according to the interference intensity.

[0055] In this embodiment, when an abnormal match occurs in the correlation matching result, it means that there is a strong correlation between the electromagnetic interference change curve and the temperature signal fluctuation curve with a time-domain correlation coefficient higher than a preset correlation threshold, indicating that the current abnormal temperature fluctuation is very likely caused by electromagnetic interference. At this time, temperature transmitter signal reconstruction is performed based on the established electromagnetic-temperature influence correlation. Specifically, firstly, the current electromagnetic interference intensity is determined based on the abnormal matching result, and then a traversal matching is performed in the electromagnetic-temperature influence correlation based on this intensity to obtain the corresponding electromagnetic interference mode. Subsequently, a signal compensation coefficient matrix for signal correction is calculated based on this interference mode. Then, an established historical normal operating condition temperature signal reference model is called, and the difference between the reference model and the interfered signal is compared. The compensation coefficients are used to reconstruct the temperature transmitter signal, ultimately generating transmitter compensation parameters for real-time correction.

[0056] After generating the transmitter compensation parameters, these parameters are applied to the real-time output data of the current temperature transmitter to perform a signal correction operation. Specifically, based on the amplitude correction factor and phase compensation amount in the signal compensation coefficient matrix, the output of the current temperature transmitter is adjusted point by point to restore the interfered temperature signal to a reference value close to normal operating conditions, ensuring that interference suppression and correction are completed before data transmission.

[0057] At the same time, the current electromagnetic interference intensity is compared with the preset interference level standard. If the intensity exceeds the risk threshold, a fault warning is triggered, a risk warning message is generated and sent to the maintenance personnel's terminal.

[0058] Furthermore, in the method provided in the application embodiment, when an abnormal match occurs in the correlation matching result, the temperature transmitter signal is reconstructed based on the electromagnetic-temperature influence correlation to generate transmitter compensation parameters, and the method further includes:

[0059] Based on the correlation matching results, the electromagnetic interference intensity is obtained; based on the electromagnetic interference intensity, the electromagnetic-temperature influence correlation is traversed to obtain the electromagnetic interference mode under the corresponding operating condition; based on the electromagnetic interference mode, the signal compensation coefficient matrix is ​​calculated; based on historical normal operating condition data, a temperature signal reference model is established, and the temperature transmitter signal is reconstructed by comparing it with the signal compensation coefficient matrix to generate the transmitter compensation parameters.

[0060] In this embodiment, the electromagnetic interference intensity within the corresponding time period is first obtained based on the time period information and device identifier in the association matching results. This electromagnetic interference intensity is the electric field strength value collected and recorded by the electromagnetic interference sensing module during real-time monitoring, typically expressed in dBμV / m, and is used to reflect the current interference level experienced by the target area.

[0061] After obtaining the electromagnetic interference (EMI) intensity, the interference pattern identification stage begins. At this stage, the current EMI intensity is used as an index to traverse the electromagnetic-temperature influence correlation. The stored historical data is used to retrieve the interference behavior record closest to the current EMI intensity, and the corresponding EMI pattern under the specified operating condition is obtained. This EMI pattern includes the characteristics of the impact of electromagnetic disturbances generated under specific frequency, current, and voltage conditions on the temperature signal, such as temperature shift trends, response delay ranges, and fluctuation amplitude ranges.

[0062] After acquiring the electromagnetic interference (EMI) pattern, a signal compensation coefficient matrix for signal correction is calculated based on the interference characteristics recorded in the EMI pattern (such as frequency, duration, and interference source type). By employing spectral analysis methods, such as Short-Time Fourier Transform (STFT) or Fast Fourier Transform (FFT), the interfered temperature signal is frequency-domain mapped, and combined with the typical responses of the interference pattern in each frequency band, a compensation coefficient matrix covering multiple frequency bands is generated. For example, in a typical application, if the detected interference amplitude is 3.5 dB in the 10–50 Hz range, the corresponding compensation coefficient is 0.92; in the 50–100 Hz range, the interference amplitude is 6.2 dB, and the compensation coefficient is 0.85; in the 100–500 Hz range, the interference amplitude reaches 8.8 dB, and the corresponding compensation coefficient is further reduced to 0.73. This segment-by-segment configuration of frequency bands and compensation coefficients suppresses the influence of interference components on the signal in each frequency band, thus forming a differentiated frequency domain correction basis for the original signal.

[0063] Finally, a temperature signal reference model is established based on historical normal operating condition data, and the temperature transmitter signal is reconstructed by comparing it with the signal compensation coefficient matrix. Specifically, firstly, temperature signal samples under normal operating conditions that match the current operating conditions are extracted from the historical database, and a corresponding temperature signal reference model is constructed. Then, the aforementioned signal compensation coefficient matrix is ​​used to perform frequency domain decomposition and reconstruction operations on the disturbed temperature signal to reconstruct a preliminarily recovered temperature signal. After obtaining the reconstructed signal, it is adaptively matched and calibrated with the temperature signal reference model, and its deviations in multiple dimensions such as amplitude and phase are compared. Based on the deviation values, the final transmitter compensation parameter set is calculated, which specifically includes an amplitude correction factor and a phase compensation amount.

[0064] Furthermore, in the method provided in the application embodiments, the method further includes: establishing a temperature signal reference model based on historical normal operating condition data, reconstructing the temperature transmitter signal by comparing it with the signal compensation coefficient matrix, and generating the transmitter compensation parameters;

[0065] Extract normal temperature signal samples that meet the threshold of similarity to the current operating condition from the historical database; construct a temperature signal reference model based on the normal temperature signal samples; perform frequency domain decomposition and reconstruction on the disturbed temperature signal according to the signal compensation coefficient matrix to generate a reconstructed temperature signal; perform adaptive matching calibration between the reconstructed temperature signal and the temperature signal reference model to generate a transmitter compensation parameter set containing amplitude correction factor and phase compensation amount.

[0066] In this embodiment, firstly, a feature vector similarity retrieval method is used to extract normal temperature signal samples from the historical database that meet a threshold similarity to the current operating condition. This method uses the temperature, electromagnetic interference level, etc., of the current operating condition to construct a feature vector, calculates the cosine similarity with the feature vectors of historical operating conditions, and determines that the data is suitable for modeling when the similarity is greater than a set threshold (e.g., 0.9). Through this process, normal temperature signal samples are obtained.

[0067] Next, a multi-scale wavelet decomposition modeling method is adopted to construct a temperature signal reference model based on normal temperature signal samples. Specifically, multi-level wavelet decomposition (such as db4 wavelet four-level decomposition) is performed on each normal temperature signal sample to extract its low-frequency baseline trend and high-frequency disturbance components at different frequency scales. The wavelet coefficients of all samples are then aggregated into a statistical mean model at the corresponding scale to form a temperature signal reference model with operating condition representativeness and spectral resolution.

[0068] Next, a frequency domain modulation compensation method is employed. Based on the signal compensation coefficient matrix, the interfered temperature signal is decomposed and reconstructed in the frequency domain to generate a reconstructed temperature signal. This method uses a Fast Fourier Transform (FFT) to convert the interference signal to the frequency domain, and then corrects the amplitude of each frequency component according to the proportion specified in the signal compensation coefficient matrix. For example, if the interference is mainly concentrated in the 90~130Hz frequency band, the amplitude of the corresponding frequency band is multiplied by a compensation coefficient (e.g., between 0.85 and 0.92) to weaken the interference components. Subsequently, an inverse transform (IFFT) is performed to obtain the preliminarily corrected reconstructed temperature signal.

[0069] Then, a dynamic time warping and residual regression fusion method is employed to adaptively match and calibrate the reconstructed temperature signal with the temperature signal reference model. The matching process first performs Z-score normalization on both sets of signals, then applies the DTW algorithm to achieve nonlinear alignment on the time axis. Calibration factors are generated by calculating the amplitude difference and phase shift between the reconstructed signal and the reference model. The extracted calibration factors include an amplitude correction factor (e.g., +1.5%) and a phase compensation amount, both used to quantitatively describe the degree of residual correction after interference compensation. Finally, the amplitude correction factor and phase compensation amount are summarized to generate the transmitter compensation parameter set.

[0070] Furthermore, in the method provided in the application embodiments, when the association matching result does not have an abnormal match, it further includes:

[0071] If no abnormal match is found in the correlation matching result, the process is switched to the slow-change fault analysis channel. Through the slow-change fault analysis channel, combined with the temperature signal fluctuation characteristics, a multi-factor fault investigation analysis is performed to generate a slow-change fault analysis result.

[0072] In this embodiment of the application, when there is no abnormal match in the correlation matching result, that is, the time domain correlation coefficient between electromagnetic interference fluctuation and temperature signal fluctuation is lower than the preset threshold, it indicates that the temperature abnormality is not caused by electromagnetic interference, and the process is switched to the slow-change fault analysis channel.

[0073] After switching to the slow-change fault analysis channel, a knowledge base of non-electromagnetic interference fault characteristics is established, and a three-dimensional diagnostic model of time-space-information is constructed to identify the evolution trend of temperature anomalies. Temperature signal fluctuation characteristics are extracted from three dimensions: time accumulation, spatial stability and signal integrity. The extracted characteristics are then input into the slow-change fault analysis channel for slow-change fault analysis, and finally, slow-change fault diagnosis results are generated.

[0074] Furthermore, in the method provided in the application embodiment, the multi-factor fault analysis is performed through the slow-varying fault analysis channel, combined with the temperature signal fluctuation characteristics, to generate slow-varying fault analysis results, and further includes:

[0075] A feature knowledge base for non-electromagnetic interference faults is established and embedded in the slow-varying fault analysis channel; a three-dimensional diagnostic model of time-space-signal is constructed, and temperature drift characteristics are analyzed from three dimensions: time accumulation, spatial stability, and signal integrity. The model is then input into the slow-varying fault analysis channel for slow-varying fault analysis to generate slow-varying fault diagnosis results.

[0076] In this embodiment, a feature knowledge base for non-electromagnetic interference faults is first established using a feature clustering analysis method. Specifically, slow-changing fault conditions that occurred during historical operation are extracted from a historical database, and the corresponding temperature drift data is extracted from these conditions. Data with similar features are then clustered into one class using a clustering algorithm (such as K-means). Each class represents a non-electromagnetic interference slow-changing fault mode, such as thermal insulation aging or structural loosening leading to unstable heat conduction. These feature modes are encoded into feature vectors and stored as a feature knowledge base, which is then embedded into the slow-changing fault analysis channel.

[0077] Subsequently, a three-dimensional diagnostic model based on multi-factor feature extraction was constructed to analyze the variation patterns of the temperature signal from three dimensions. In the time dimension, the cumulative trend of temperature drift was calculated using the moving average; in the spatial dimension, temperature changes from multiple sensing points were compared to calculate the stability of the temperature difference; and in the signal dimension, wavelet transform was used to decompose the temperature signal in the frequency domain to analyze the integrity of its frequency components. These three features represent the temporal cumulativeity, spatial stability, and signal integrity of the temperature, respectively. The results of these three analyses together constitute a three-dimensional feature vector of temperature drift, a comprehensive descriptive vector containing the amount of time drift, the degree of spatial fluctuation, and the frequency domain energy distribution.

[0078] Finally, the three-dimensional feature vector of temperature drift is used as input and fed into the slow-varying fault analysis channel for analysis. This channel integrates a pre-trained shallow neural network model. During the training phase, the network takes a large number of labeled slow-varying fault samples as input and outputs fault type labels. During the inference phase, the three-dimensional feature vector is processed by the neural network to identify the fault type, and then matched against the aforementioned feature knowledge base for non-electromagnetic interference faults. The final output is a slow-varying fault diagnosis result, such as determining that the fault is caused by uneven heat diffusion due to structural loosening or data drift due to sensor aging.

[0079] In summary, the embodiments of this application have at least the following technical effects:

[0080] This application, based on a real-time industrial environment, collects spatial location information and operating status parameters of high-frequency electrical equipment within the area. Combined with the spatial location information of the target temperature transmitter, it performs electromagnetic interference (EMI) analysis to generate an EMI distribution map. Based on the EMI distribution map, it establishes an electromagnetic-temperature influence correlation and deploys an EMI sensing module. Based on the EMI sensing module, it monitors EMI and obtains EMI change curves. Simultaneously, it monitors the temperature signal fluctuation curve of the target temperature transmitter in real time. It performs correlation comparison analysis between the EMI change curve and the temperature signal fluctuation curve to generate a correlation matching result. When an abnormal match is found in the correlation matching result, it reconstructs the temperature transmitter signal based on the EMI-temperature influence correlation, generates transmitter compensation parameters to correct the transmitter signal, and provides a fault risk warning based on the interference intensity. This invention addresses the technical problem in the prior art where faults in temperature transmitters are difficult to detect and accurately locate in a timely manner when affected by electromagnetic interference. By constructing an electromagnetic interference distribution map, establishing an electromagnetic-temperature influence correlation, and introducing a correlation comparison and signal reconstruction mechanism, it achieves timely identification and compensation correction of temperature anomalies caused by electromagnetic interference, thereby improving the accuracy and real-time performance of temperature transmitter fault diagnosis.

[0081] Example 2, based on the same inventive concept as the fault self-diagnosis method for temperature transmitters under real-time monitoring in the foregoing examples, such as... Figure 2 As shown, this application provides a fault self-diagnosis system for temperature transmitters under real-time monitoring. The system and method embodiments in this application are based on the same inventive concept. The system includes:

[0082] The parameter acquisition module 11 is used to collect the spatial location information and operating status parameters of high-frequency electrical equipment in the area based on the real-time industrial environment, and perform electromagnetic interference analysis by combining the spatial location information of the target temperature transmitter to generate an electromagnetic interference distribution map. The sensor module deployment module 12 is used to establish an electromagnetic-temperature influence correlation based on the electromagnetic interference distribution map and deploy electromagnetic interference sensor modules. The interference monitoring module 13 is used to perform electromagnetic interference monitoring based on the electromagnetic interference sensor modules, obtain the electromagnetic interference change curve, and simultaneously monitor the temperature signal fluctuation curve of the target temperature transmitter in real time. The comparison and analysis module 14 is used to perform correlation comparison and analysis between the electromagnetic interference change curve and the temperature signal fluctuation curve to generate a correlation matching result. The risk warning module 15 is used to reconstruct the temperature transmitter signal based on the electromagnetic-temperature influence correlation when the correlation matching result shows an abnormal match, generate transmitter compensation parameters to correct the transmitter signal, and provide a fault risk warning based on the interference intensity.

[0083] Furthermore, the system is also used to implement the following functions:

[0084] Through industrial IoT nodes, the operating status parameters and spatial coordinate information of high-frequency electrical equipment in the target industrial environment, as well as the spatial location information of the target temperature transmitter, are collected in real time. Based on the spatial coordinate information of the high-frequency electrical equipment and the spatial location information of the target temperature transmitter, an electromagnetic field propagation model is built. According to the electromagnetic field propagation model, combined with the operating status parameters of each high-frequency electrical equipment, the electromagnetic radiation intensity from each device to the temperature transmitter is calculated, and an electromagnetic interference distribution map including spatial position relationship and electromagnetic coupling strength is established.

[0085] Furthermore, the system is also used to implement the following functions:

[0086] Long-term monitoring is adopted to accumulate and statistically analyze the changing trends of electromagnetic radiation intensity of each interference source, and predict the gradual change law of electromagnetic interference intensity. Based on the gradual change law, combined with the electromagnetic interference distribution map, a gradual interference analysis is performed to establish an electromagnetic-temperature influence correlation. The electromagnetic-temperature influence correlation includes the four-dimensional electromagnetic environment evolution law in the time dimension.

[0087] Furthermore, the system is also used to implement the following functions:

[0088] The temperature signal fluctuation curve is subjected to moving average filtering to eliminate random measurement noise, and then signal abrupt change points and abnormal fluctuation intervals are detected and extracted; based on the signal abrupt change points and abnormal fluctuation intervals, temperature signal fluctuation characteristics are extracted.

[0089] Furthermore, the system is also used to implement the following functions:

[0090] Based on the electromagnetic interference change curve, electromagnetic fluctuation characteristics are extracted; based on the electromagnetic fluctuation characteristics, the temperature signal fluctuation characteristics are compared, and the time-domain correlation coefficient between the electromagnetic interference intensity change and the temperature signal fluctuation is calculated; based on the time-domain correlation coefficient, the correlation level between the electromagnetic interference change and the temperature fluctuation is determined; if the correlation level meets the preset correlation threshold, it is determined to be a temperature anomaly caused by electromagnetic interference, and the correlation matching result is generated according to the strength of the correlation.

[0091] Furthermore, the system is also used to implement the following functions:

[0092] Based on the correlation matching results, the electromagnetic interference intensity is obtained; based on the electromagnetic interference intensity, the electromagnetic-temperature influence correlation is traversed to obtain the electromagnetic interference mode under the corresponding operating condition; based on the electromagnetic interference mode, the signal compensation coefficient matrix is ​​calculated; based on historical normal operating condition data, a temperature signal reference model is established, and the temperature transmitter signal is reconstructed by comparing it with the signal compensation coefficient matrix to generate the transmitter compensation parameters.

[0093] Furthermore, the system is also used to implement the following functions:

[0094] Extract normal temperature signal samples that meet the threshold of similarity to the current operating condition from the historical database; construct a temperature signal reference model based on the normal temperature signal samples; perform frequency domain decomposition and reconstruction on the disturbed temperature signal according to the signal compensation coefficient matrix to generate a reconstructed temperature signal; perform adaptive matching calibration between the reconstructed temperature signal and the temperature signal reference model to generate a transmitter compensation parameter set containing amplitude correction factor and phase compensation amount.

[0095] Furthermore, the system is also used to implement the following functions:

[0096] If no abnormal match is found in the correlation matching result, the process is switched to the slow-change fault analysis channel. Through the slow-change fault analysis channel, combined with the temperature signal fluctuation characteristics, a multi-factor fault investigation analysis is performed to generate a slow-change fault analysis result.

[0097] Furthermore, the system is also used to implement the following functions:

[0098] A feature knowledge base for non-electromagnetic interference faults is established and embedded in the slow-varying fault analysis channel; a three-dimensional diagnostic model of time-space-signal is constructed, and temperature drift characteristics are analyzed from three dimensions: time accumulation, spatial stability, and signal integrity. The model is then input into the slow-varying fault analysis channel for slow-varying fault analysis to generate slow-varying fault diagnosis results.

[0099] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0100] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0101] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. A fault self-diagnosis method for temperature transmitters under real-time monitoring, characterized in that, The method includes: Based on the real-time industrial environment, the spatial location information and operating status parameters of high-frequency electrical equipment in the area are collected. Combined with the spatial location information of the target temperature transmitter, electromagnetic interference analysis is performed to generate an electromagnetic interference distribution map. Based on the electromagnetic interference distribution map, an electromagnetic-temperature influence correlation was established, and electromagnetic interference sensing modules were deployed. Electromagnetic interference is monitored based on the electromagnetic interference sensing module to obtain the electromagnetic interference change curve. At the same time, the temperature signal fluctuation curve of the target temperature transmitter is monitored in real time. The electromagnetic interference variation curve and the temperature signal fluctuation curve are compared and analyzed to generate correlation matching results. When an abnormal match occurs in the correlation matching result, the temperature transmission signal is reconstructed according to the electromagnetic-temperature influence correlation, the transmitter compensation parameters are generated to correct the transmission signal, and a fault risk warning is given according to the interference intensity.

2. The fault self-diagnosis method for a temperature transmitter under real-time monitoring as described in claim 1, characterized in that, Based on the real-time industrial environment, spatial location information and operating status parameters of high-frequency electrical equipment within the area are collected. Combined with the spatial location information of the target temperature transmitter, electromagnetic interference analysis is performed, including: Through industrial IoT nodes, the operating status parameters and spatial coordinate information of high-frequency electrical equipment in the target industrial environment, as well as the spatial location information of the target temperature transmitter, are collected in real time. An electromagnetic field propagation model is built based on the spatial coordinate information of high-frequency electrical equipment and the spatial location information of the target temperature transmitter. Based on the electromagnetic field propagation model and combined with the operating parameters of each high-frequency electrical device, the electromagnetic radiation intensity from each device to the temperature transmitter is calculated, and an electromagnetic interference distribution map including spatial positional relationships and electromagnetic coupling strength is established.

3. The fault self-diagnosis method for a temperature transmitter under real-time monitoring as described in claim 2, characterized in that, Based on the electromagnetic interference distribution map, an electromagnetic-temperature influence correlation is established, including: By employing long-term monitoring, the changing trends of electromagnetic radiation intensity from each interference source are statistically analyzed to predict the gradual change pattern of electromagnetic interference intensity. Based on the aforementioned gradual change pattern, and combined with the electromagnetic interference distribution map, a gradual interference analysis is performed to establish an electromagnetic-temperature influence correlation. This electromagnetic-temperature influence correlation includes a four-dimensional electromagnetic environment evolution pattern in the time dimension.

4. The fault self-diagnosis method for a temperature transmitter under real-time monitoring as described in claim 1, characterized in that, Before performing correlation and comparison analysis between the electromagnetic interference variation curve and the temperature signal fluctuation curve to generate correlation matching results, a fluctuation anomaly analysis is first performed on the temperature signal fluctuation curve, including: After performing a moving average filter on the temperature signal fluctuation curve to eliminate random measurement noise, the signal abrupt change points and abnormal fluctuation intervals are detected and extracted. Based on the signal abrupt change points and abnormal fluctuation ranges, temperature signal fluctuation characteristics are extracted.

5. The fault self-diagnosis method for a temperature transmitter under real-time monitoring as described in claim 4, characterized in that, The electromagnetic interference variation curve and the temperature signal fluctuation curve are compared and analyzed to generate correlation matching results, including: Based on the electromagnetic interference variation curve, electromagnetic wave characteristics are extracted; Based on the electromagnetic wave characteristics, and by comparing them with the temperature signal fluctuation characteristics, the time-domain correlation coefficient between the electromagnetic interference intensity change and the temperature signal fluctuation is calculated. Based on the aforementioned time-domain correlation coefficient, determine the correlation level between electromagnetic interference changes and temperature fluctuations; If the correlation level meets the preset correlation threshold, it is determined to be a temperature anomaly caused by electromagnetic interference, and the correlation matching result is generated according to the strength of the correlation.

6. The fault self-diagnosis method for a temperature transmitter under real-time monitoring as described in claim 1, characterized in that, When an abnormal match occurs in the correlation matching result, the temperature transmitter signal is reconstructed based on the electromagnetic-temperature influence correlation to generate transmitter compensation parameters, including: Based on the correlation matching results, the electromagnetic interference intensity is obtained; Based on the electromagnetic interference intensity, the electromagnetic-temperature influence correlation is traversed to obtain the electromagnetic interference mode under the corresponding operating condition. Calculate the signal compensation coefficient matrix based on the electromagnetic interference mode; A temperature signal reference model is established based on historical normal operating condition data. The temperature transmission signal is reconstructed by comparing the signal compensation coefficient matrix, and the transmitter compensation parameters are generated.

7. The fault self-diagnosis method for a temperature transmitter under real-time monitoring as described in claim 6, characterized in that, A temperature signal reference model is established based on historical normal operating condition data. The temperature transmitter signal is reconstructed by comparing the signal compensation coefficient matrix, and the transmitter compensation parameters are generated, including: Extract normal temperature signal samples from historical databases that meet the threshold of similarity to the current operating conditions; Based on the normal temperature signal samples, a temperature signal reference model is constructed. Based on the signal compensation coefficient matrix, the disturbed temperature signal is decomposed and reconstructed in the frequency domain to generate a reconstructed temperature signal. The reconstructed temperature signal is adaptively matched and calibrated with the temperature signal reference model to generate a transmitter compensation parameter set that includes amplitude correction factors and phase compensation amounts.

8. The fault self-diagnosis method for a temperature transmitter under real-time monitoring as described in claim 4, characterized in that, When the association matching result does not contain any abnormal matches, it also includes: If no abnormal match is found in the correlation matching results, the process switches to the slow-change fault analysis channel. By using the slow-change fault analysis channel and combining the temperature signal fluctuation characteristics, multi-factor fault analysis is performed to generate slow-change fault analysis results.

9. The fault self-diagnosis method for a temperature transmitter under real-time monitoring as described in claim 8, characterized in that, By using the slow-varying fault analysis channel and combining the temperature signal fluctuation characteristics, multi-factor fault analysis is performed to generate slow-varying fault analysis results, including: Establish a feature knowledge base for non-electromagnetic interference faults, and embed it into the slow-change fault analysis channel; A three-dimensional diagnostic model of time, space, and signal is constructed. Temperature drift characteristics are analyzed from three dimensions: time cumulativeity, spatial stability, and signal integrity. The results are then input into the slow-change fault analysis channel to perform slow-change fault analysis and generate slow-change fault diagnosis results.

10. A fault self-diagnosis system for temperature transmitters under real-time monitoring, characterized in that, The system is used to execute the fault self-diagnosis method for a temperature transmitter under real-time monitoring as described in any one of claims 1-9, the system comprising: The parameter acquisition module is used to collect the spatial location information and operating status parameters of high-frequency electrical equipment in the area based on the real-time industrial environment, and combine it with the spatial location information of the target temperature transmitter to perform electromagnetic interference analysis and generate an electromagnetic interference distribution map. The sensor module deployment module is used to establish an electromagnetic-temperature influence correlation based on the electromagnetic interference distribution map and to deploy electromagnetic interference sensor modules. The interference monitoring module is used to monitor electromagnetic interference based on the electromagnetic interference sensing module, obtain the electromagnetic interference change curve, and at the same time, monitor the temperature signal fluctuation curve of the target temperature transmitter in real time. The comparison and analysis module is used to perform correlation and comparison analysis between the electromagnetic interference change curve and the temperature signal fluctuation curve, and generate correlation matching results; The risk warning module is used to reconstruct the temperature transmission signal based on the electromagnetic-temperature influence correlation when the correlation matching result shows an abnormal match, generate transmitter compensation parameters to correct the transmission signal, and provide a fault risk warning based on the interference intensity.

Images