Electrocardiograph electromagnetic compatibility test data diagnosis method based on intelligent sensor

Abstract

The application provides a kind of electrocardiograph electromagnetic compatibility test data diagnosis method based on intelligent sensor, it is related to electrocardiograph electromagnetic compatibility test technical field.Method includes generating structured test data.Calculation theoretical interference reference threshold value.Generate initial interference judgment atlas arranged according to interference time sequence.Construct dynamic compensation coefficient matrix, and dynamic compensation coefficient matrix is injected into initial interference judgment atlas, and dynamic interference judgment atlas is obtained.Calculation real-time test data in each interference time sequence window and the feature similarity of dynamic interference judgment atlas, the electromagnetic compatibility state of electrocardiograph is diagnosed.The application is through multidimensional data acquisition and interference identification, through dynamic reference threshold value and compensation mechanism, adapts to environmental and equipment state change, improves the stability of complex scene diagnosis, through real-time data comparison and traceability, quickly determines equipment state, locates interference root, shortens debugging time, and finally guarantees electrocardiograph measurement accuracy.

Description

Technical Field

[0001] This invention relates to the field of electromagnetic compatibility testing technology for electrocardiographs, and in particular to a diagnostic method for electromagnetic compatibility testing data of electrocardiographs based on intelligent sensors. Background Technology

[0002] In the modern medical system, the electrocardiograph (ECG) machine is a core medical device for diagnosing cardiovascular diseases. The accuracy of its measurement data directly affects the scientific nature of clinical diagnosis and the effectiveness of treatment plans. With the continuous advancement of medical technology, the functions of ECG machines are becoming increasingly diverse, and their integration and intelligence are constantly improving. At the same time, their application scenarios are expanding from traditional hospital wards and treatment rooms to diversified environments such as mobile healthcare, remote monitoring, and community healthcare, making the electromagnetic environment faced by the equipment increasingly complex.

[0003] Currently, there are numerous sources of electromagnetic radiation in medical settings, including high-frequency surgical equipment, monitors, medical imaging equipment, and communication devices. These devices generate various types of electromagnetic interference during operation, such as conducted interference, radiated interference, electrostatic discharge, and surge impact. This electromagnetic interference can affect electrocardiographs (ECGs) through power lines, signal lines, or spatial propagation, causing problems such as baseline drift, waveform distortion, and noise superposition in the output ECG signals. In severe cases, it can mask the true physiological signal characteristics, affecting the accurate judgment of medical personnel and potentially leading to misdiagnosis or missed diagnosis.

[0004] Electromagnetic compatibility (EMC) performance has become a key indicator for evaluating the quality and safety of electrocardiographs (ECGs), and relevant industry standards and regulations are increasingly stringent regarding EMC requirements for ECGs. However, existing EMC testing technologies for ECGs struggle to comprehensively capture the characteristics of various types of interference in complex electromagnetic environments. The lack of consideration for dynamic factors such as ambient temperature and humidity, power supply stability, and changes in the equipment's own state during testing leads to insufficient repeatability and reliability of test results. Distinguishing between interference signals and ambient background noise is difficult, easily resulting in misjudgments. Test data is mostly stored and processed in its raw form, lacking systematic feature extraction and structured management, which hinders interference tracing and in-depth analysis of test results. Consequently, existing EMC testing technologies are insufficient to meet the high-precision and high-reliability requirements of ECG testing in complex medical environments, and cannot provide adequate technical support for optimizing the EMC performance and quality control of the equipment. Summary of the Invention

[0005] This invention provides a diagnostic method for electromagnetic compatibility test data of an electrocardiograph based on a smart sensor, in order to overcome the deficiencies in the existing technology.

[0006] This invention provides a diagnostic method for electromagnetic compatibility test data of an electrocardiograph based on a smart sensor, comprising:

[0007] We collect equipment parameters, test environment parameters, and multi-dimensional electromagnetic interference data collected by intelligent sensors in the electromagnetic compatibility test scenario of an electrocardiograph. By decoding the characteristics of interference sources, we identify the interference type sequence in the test data and extract the feature identifier of each interference type in combination with the equipment parameters to generate structured test data.

[0008] Collect historical electromagnetic compatibility test data, extract interference intensity distribution, equipment anti-interference response curve and interference timing characteristics from the historical data, and calculate the theoretical interference reference threshold based on the interference intensity distribution and equipment anti-interference response curve.

[0009] Set a dynamic tolerance range and generate an initial interference judgment spectrum arranged according to the interference time sequence by combining the theoretical interference benchmark threshold.

[0010] Collect equipment temperature drift data, power fluctuation parameters, and sensor noise spectrum during the test process, construct a dynamic compensation coefficient matrix, and inject the dynamic compensation coefficient matrix into the initial interference judgment spectrum to obtain the dynamic interference judgment spectrum.

[0011] Collect real-time electromagnetic compatibility test data sequences, compare the actual average interference value at each test stage, and calculate the feature similarity between the real-time test data and the dynamic interference judgment spectrum within each interference time window to diagnose the electromagnetic compatibility status of the electrocardiograph.

[0012] According to the electromagnetic compatibility (EMC) test data diagnostic method for electrocardiographs based on intelligent sensors provided by this invention, the equipment parameters include the electrocardiograph signal sampling rate, input impedance threshold, filter circuit cutoff frequency, amplifier gain parameters, and lead interface anti-interference level. Test environment parameters include ambient electromagnetic field strength, temperature and humidity gradient, grounding resistance value, and power supply harmonic content. Multi-dimensional electromagnetic interference data includes conducted interference voltage data, radiated interference field strength data, electrostatic discharge pulse data, and surge response data. Characteristic identifiers include interference frequency bandwidth, peak interference amplitude, interference duration, pulse rise slope, and spectral distortion coefficient.

[0013] The method for diagnosing electromagnetic compatibility test data of an electrocardiograph based on a smart sensor provided by the present invention includes the following process for identifying interference type sequences in the test data through interference source feature decoding:

[0014] The collected raw electromagnetic interference data were converted from the time domain to the frequency domain to extract key spectral features.

[0015] Continuous interference segments are segmented based on the type and amplitude changes of key spectral features to generate an initial interference sequence.

[0016] Extract the core feature set for each type of interference in the initial interference sequence. The core feature set includes the interference frequency range and the interference triggering conditions.

[0017] By filtering out environmental background noise interference from the initial interference sequence based on the core feature set, the interference type sequence in the test data is obtained.

[0018] The method for diagnosing electromagnetic compatibility test data of an electrocardiograph based on a smart sensor, provided by the present invention, includes the following process for generating structured test data by extracting feature identifiers for each type of interference in conjunction with equipment parameters:

[0019] Based on the interference frequency range and interference triggering conditions, the effective filtering threshold is obtained by associating the parameters of the electrocardiograph's filtering circuit.

[0020] The interference attenuation is calculated by combining the interference frequency range with the effective filtering threshold.

[0021] By associating the input impedance threshold, the maximum allowable interference amplitude for the current interference type is derived.

[0022] Based on the interference immunity level of the lead interface, the interference sensitivity coefficient is calibrated.

[0023] The unique identifier of the interference type, the core feature set, and the interference attenuation amount are encapsulated into a structured data object to obtain structured test data.

[0024] According to the electrocardiograph electromagnetic compatibility test data diagnostic method based on intelligent sensors provided by the present invention, the process of extracting interference intensity distribution, equipment anti-interference response curve and interference timing characteristics from historical electromagnetic compatibility test data includes:

[0025] Filter historical test records of the same model of electrocardiograph.

[0026] Analyze the interference attenuation in historical structured data objects and statistically analyze the probability distribution of interference intensity.

[0027] By analyzing historical sensor data, a mapping model between interference intensity and device output distortion is constructed.

[0028] Extract the timestamps and interference type conversion relationships of historical interference sequences.

[0029] According to the electrocardiograph electromagnetic compatibility test data diagnosis method based on intelligent sensors provided by the present invention, the process of calculating the theoretical interference reference threshold based on the interference intensity distribution and the equipment anti-interference response curve includes:

[0030] Based on the interference intensity distribution, the equipment anti-interference model is mapped to generate basic interference reference values.

[0031] The inherent noise reference value of the superimposed equipment.

[0032] An electromagnetic compatibility safety margin coefficient is introduced to generate a theoretical interference reference threshold.

[0033] The method for diagnosing electromagnetic compatibility test data of an electrocardiograph based on a smart sensor, according to the present invention, includes the following process for generating an initial interference determination spectrum arranged according to the interference time sequence by combining a theoretical interference reference threshold:

[0034] Create a two-dimensional coordinate system for timing and interference intensity.

[0035] A reference curve is formed by connecting the theoretical baseline threshold according to the interference timing.

[0036] Differentiated tolerance bandwidths are set based on the characteristics of the interference type.

[0037] Visualize and annotate the tolerance range boundaries to form an initial interference judgment map.

[0038] According to the electrocardiograph electromagnetic compatibility test data diagnosis method based on intelligent sensors provided by the present invention, the process of constructing a dynamic compensation coefficient matrix includes:

[0039] The noise energy entropy value is calculated based on the sensor noise spectrum, and a noise compensation coefficient is generated.

[0040] Calculate the temperature compensation coefficient based on the equipment temperature drift data.

[0041] Analyze power supply fluctuation parameters and calibrate the voltage stability coefficient.

[0042] By integrating noise compensation coefficient, temperature compensation coefficient, and voltage stability coefficient, a dynamic compensation coefficient matrix is ​​obtained.

[0043] According to the electrocardiograph electromagnetic compatibility test data diagnosis method based on intelligent sensors provided by the present invention, the process of injecting the dynamic compensation coefficient matrix into the initial interference determination spectrum to obtain the dynamic interference determination spectrum includes:

[0044] Based on the dynamic compensation coefficient matrix, the theoretical interference reference threshold of the initial spectrum is adjusted sequentially.

[0045] The allowable bandwidth is dynamically adjusted based on the interference sensitivity coefficient.

[0046] A compensation factor numerical labeling layer is superimposed on the initial interference determination spectrum.

[0047] Establish a real-time data interface and update the dynamic compensation coefficient matrix according to a preset cycle.

[0048] According to the electrocardiograph electromagnetic compatibility test data diagnosis method based on intelligent sensors provided by the present invention, the process of diagnosing the electromagnetic compatibility status of the electrocardiograph includes:

[0049] The mean actual interference value for each test phase is calculated, and the cosine similarity algorithm is used to calculate the feature similarity between the real-time test data and the dynamic interference judgment spectrum.

[0050] When the actual mean interference exceeds the dynamic tolerance range or the feature similarity is lower than the preset threshold, the electrocardiograph is determined to be in an abnormal electromagnetic compatibility state, and the abnormality type and source tracing results are output.

[0051] This invention provides a diagnostic method for electromagnetic compatibility test data of an electrocardiograph based on intelligent sensors. By collecting multi-dimensional electromagnetic interference data through intelligent sensors and combining time-domain to frequency-domain conversion and core feature extraction technology, it can effectively filter out environmental background noise, accurately distinguish the differentiated characteristics of different types of interference, and encapsulate the test data into structured objects, providing standardized data support for interference source tracing and historical data comparison, thus greatly improving the accuracy of interference identification and the systematic nature of data processing.

[0052] By introducing a dynamic benchmark threshold and compensation mechanism, the method's environmental adaptability and diagnostic accuracy are enhanced. A theoretical interference benchmark threshold is constructed by analyzing historical test data, and a compensation coefficient matrix is ​​built by combining dynamic factors such as equipment temperature drift, power fluctuations, and sensor noise. The interference judgment criteria are adjusted in real time, effectively avoiding the limitations of fixed thresholds in complex environments and ensuring stable and reliable diagnostic results in different test scenarios.

[0053] By collecting test data in real time and calculating the actual interference mean and feature similarity, the electromagnetic compatibility status of the equipment can be quickly determined. Once an anomaly is detected, the anomaly type and source tracing results can be output immediately, providing staff with a clear direction for problem localization, greatly shortening the time for equipment debugging and interference suppression, and improving testing and maintenance efficiency. Attached Figure Description

[0054] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0055] Figure 1 This is a flowchart illustrating the electromagnetic compatibility test data diagnosis method for electrocardiographs based on intelligent sensors provided in an embodiment of the present invention;

[0056] Figure 2 This is a flowchart illustrating the process of identifying interference type sequences in test data through interference source feature decoding in an embodiment of the present invention.

[0057] Figure 3 This is a schematic diagram of the process for generating structured test data in an embodiment of the present invention;

[0058] Figure 4This is a schematic diagram of the process for constructing the dynamic compensation coefficient matrix in an embodiment of the present invention;

[0059] Figure 5 This is a schematic diagram of the process for obtaining dynamic interference determination spectrum in an embodiment of the present invention. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0061] The following is combined Figures 1-5 This invention describes a diagnostic method for electromagnetic compatibility test data of an electrocardiograph based on a smart sensor.

[0062] The electromagnetic compatibility test data diagnostic method for electrocardiographs based on intelligent sensors provided in this invention includes:

[0063] We collect equipment parameters, test environment parameters, and multi-dimensional electromagnetic interference data collected by intelligent sensors in the electromagnetic compatibility test scenario of an electrocardiograph. By decoding the characteristics of interference sources, we identify the interference type sequence in the test data and extract the feature identifier of each interference type in combination with the equipment parameters to generate structured test data.

[0064] Equipment parameters include the ECG machine signal sampling rate, input impedance threshold, filter circuit cutoff frequency, amplifier gain parameters, and lead interface anti-interference level. Test environment parameters include ambient electromagnetic field strength, temperature and humidity gradient, grounding resistance, and power supply harmonic content. Multi-dimensional electromagnetic interference data includes conducted interference voltage data, radiated interference field strength data, electrostatic discharge pulse data, and surge response data. Characteristic identifiers include interference frequency bandwidth, peak interference amplitude, interference duration, pulse rise slope, and spectral distortion coefficient.

[0065] The process of identifying interference type sequences in test data through interference source feature decoding includes:

[0066] The collected raw electromagnetic interference data is converted from the time domain to the frequency domain. The Fast Fourier Transform algorithm is used to convert the continuous voltage or field strength signal in the time domain into the spectral distribution data in the frequency domain, ensuring that the spectral resolution meets the requirements for interference feature extraction. Key spectral features are extracted, including the center frequency corresponding to the spectral peak, the amplitude distribution law of the spectrum, the amplitude ratio of the characteristic frequency points, and other core parameters.

[0067] Continuous interference segments are segmented based on the type and amplitude variation of key spectral features. An amplitude threshold (3 times the inherent noise amplitude of the device) and a frequency change rate threshold (10MHz / μs) are set. When the amplitude in the original data exceeds the amplitude threshold and the frequency change rate exceeds the frequency change rate threshold, it is determined as the start point of the interference signal. When the amplitude is lower than the amplitude threshold and the duration exceeds 50μs, it is determined as the end point of the interference signal. Based on this, continuous interference segments are segmented to generate an initial interference sequence. Each initial interference segment includes a start timestamp, an end timestamp, time-domain waveform data, and frequency-domain spectrum data.

[0068] The core feature set for each type of interference in the initial interference sequence is extracted. This core feature set includes the interference frequency range and the interference triggering conditions. The interference frequency range is determined through spectral analysis, taking the frequency interval corresponding to an interference signal amplitude greater than the peak amplitude by 3 dB as the interference frequency range. The interference triggering conditions are determined based on the causes of the interference. For example, the triggering conditions for conducted interference are usually related to changes in power load; the triggering conditions for electrostatic discharge interference are related to discharge voltage and the number of discharges; and the triggering conditions for radiated interference are related to the operating state of surrounding electromagnetic radiation sources.

[0069] Based on the core feature set, environmental background noise interference in the initial interference sequence is filtered out. An adaptive noise suppression algorithm is used to match the core feature set of each initial interference segment with the preset environmental background noise feature library. If the matching similarity is higher than 80%, it is determined to be environmental background noise interference and filtered out to obtain the interference type sequence in the test data. Each element in the sequence contains interference type label, interference time information and core feature set data.

[0070] The process of extracting feature identifiers for each type of interference by combining equipment parameters and generating structured test data includes:

[0071] Based on the interference frequency range and interference triggering conditions, the parameters of the ECG machine's filter circuit are correlated. The filter circuit parameters include the cutoff frequency, filter order, and filter type (low-pass, high-pass, or band-pass). The attenuation characteristics of the filter circuit under different interference frequencies are simulated using circuit simulation software (such as Multisim) to obtain the effective filter threshold. The effective filter threshold refers to the input signal amplitude corresponding to the actual attenuation of the interference frequency signal by the filter circuit reaching 30dB.

[0072] The interference attenuation is calculated by combining the interference frequency range and the effective filtering threshold, and the formula is expressed as follows:

[0073]

[0074] In the formula, Let be the attenuation amount of the i-th type of interference. For interference frequency, This is the cutoff frequency of the filter circuit. This is the amplifier gain compensation value. This formula combines the logarithmic operation of the frequency ratio with amplifier gain compensation to quantify the attenuation of the interference signal after it has been filtered and amplified by the equipment. For example, when the interference frequency is 10kHz, the cutoff frequency of the filter circuit is 5kHz, and the amplifier gain compensation value is 2dB, the interference attenuation is 20lg(10k / 5k)+2=20×0.3010+2=8.02dB.

[0075] By associating the input impedance threshold with the maximum allowable interference amplitude for the current interference type, the formula is derived as follows:

[0076]

[0077] In the formula, For the maximum permissible interference amplitude, This refers to the input impedance of the electrocardiograph. The maximum allowable leakage current of the equipment. This is for the safety factor.

[0078] Based on the interference immunity level of the lead interface, the interference sensitivity coefficient is calibrated.

[0079] The unique identifier of the interference type, the core feature set, and the interference attenuation amount are encapsulated into a structured data object to obtain structured test data.

[0080] Collect historical electromagnetic compatibility test data, extract interference intensity distribution, equipment anti-interference response curve and interference timing characteristics from the historical data, and calculate the theoretical interference reference threshold based on the interference intensity distribution and equipment anti-interference response curve.

[0081] Historical electromagnetic compatibility test data includes test data of the same model of electrocardiograph under different test environments, different types of interference, and different interference intensities. It covers structured test data, equipment output distortion data, test environment parameter records, equipment operating status parameters, etc. The data spans no less than one year and the number of test samples is no less than 1,000 sets to ensure the diversity and representativeness of the data. The data sources include laboratory test data, field use test data, and test data of similar equipment in the industry.

[0082] The process of extracting interference intensity distribution, equipment anti-interference response curves, and interference timing characteristics from historical electromagnetic compatibility test data includes:

[0083] Historical test records of the same model of electrocardiograph were screened by equipment model code. Records with incorrect model, missing test conditions, or abnormal data were removed. The standard for judging abnormal data was that the interference amplitude exceeded three times the standard deviation of the normal range.

[0084] The interference attenuation in historical structured data objects is analyzed, and statistical analysis methods (such as histogram statistics and probability density function fitting) are used to statistically analyze the probability distribution of interference intensity. The interference intensity follows a log-normal distribution or a Weibull distribution. The goodness of fit of the distribution type is verified by the Kolmogorov-Smirnov test. The goodness of fit threshold is set to 0.95 to ensure that the distribution model can accurately reflect the distribution law of historical interference intensity.

[0085] Historical sensor data and corresponding device output data were analyzed, including indicators such as output signal distortion, baseline drift, and signal-to-noise ratio of the electrocardiograph. A mapping model between interference intensity and device output distortion was constructed, and the least squares method was used to fit linear or nonlinear mapping relationships. The mapping model can quantify the changes in device output performance under different interference intensities; for example, when the interference intensity exceeds a certain threshold, the device output distortion will increase sharply. Finally, the timestamps and interference type conversion relationships of historical interference sequences were extracted, recording the occurrence time and duration of each interference event. Through correlation analysis, the conversion probabilities between different interference types were statistically analyzed, such as the probability of radiated interference following conducted interference, and the probability of surge interference following electrostatic discharge interference, forming an interference time series conversion matrix.

[0086] The process of calculating the theoretical interference reference threshold based on the interference intensity distribution and the equipment's anti-interference response curve includes:

[0087] Based on the interference intensity distribution mapping, the equipment anti-interference model is represented by a piecewise function. When the interference intensity is below the first threshold, the equipment output distortion is less than 1%, which is determined to be the normal operating range of the equipment. When the interference intensity is between the first and second thresholds, the equipment output distortion is between 1% and 5%, which is determined to be the slightly disturbed range of the equipment. When the interference intensity is above the second threshold, the equipment output distortion is greater than 5%, which is determined to be the severely disturbed range of the equipment. The first threshold is taken as the basic interference reference value. .

[0088] The superimposed reference value of the inherent noise of the equipment is expressed by the following formula:

[0089]

[0090] In the formula, This is the reference value after adding inherent noise. Based on the reference value for interference, The formula represents the inherent noise amplitude of the device. It reflects the superposition effect of the basic interference and the device's own noise. In actual test scenarios, the device is not only subject to external interference, but also has its own inherent noise. Both affect the device's working state. For example, if the basic interference reference value is 0.5V and the device's inherent noise amplitude is 0.05V, then the reference value after adding the inherent noise is 0.55V.

[0091] An electromagnetic compatibility safety margin factor is introduced to generate a theoretical interference reference threshold, expressed by the formula:

[0092]

[0093] In the formula, The theoretical interference baseline threshold, This is the electromagnetic compatibility safety margin factor (range 1.3-1.8). For scenarios with high safety requirements, such as medical equipment, a value of 1.6-1.8 is used. For ordinary scenarios, a value of 1.3-1.5 is used. The safety margin factor ensures that the equipment can maintain normal operation even when subjected to unexpected interference during actual use, avoiding equipment failure or measurement errors caused by interference. For example, if the reference value after adding inherent noise is 0.55V, and the safety margin factor is 1.5, then the theoretical interference reference threshold is 0.55 × 1.5 = 0.825V.

[0094] The process includes setting a dynamic tolerance range and generating an initial interference judgment spectrum arranged according to the interference time sequence, based on a theoretical interference benchmark threshold.

[0095] Create a two-dimensional coordinate system of time-interference intensity, with the horizontal axis representing time and the time range set according to the test cycle, and the vertical axis representing interference intensity, with the vertical axis range being 0.5 to 2 times the theoretical interference baseline threshold, to ensure that the variation range of interference intensity can be fully displayed.

[0096] A reference curve is formed by connecting theoretical reference thresholds according to the interference time sequence. Based on the historical interference time sequence transformation matrix, the theoretical interference reference thresholds for different time periods are determined. The theoretical reference thresholds for each time period are connected in chronological order to form a continuous reference curve. The slope of the reference curve reflects the trend of interference intensity changing over time. A positive slope indicates that the interference intensity is gradually increasing, and a negative slope indicates that the interference intensity is gradually decreasing.

[0097] Differentiated tolerance bandwidths are set based on the characteristics of the interference type, expressed by the formula:

[0098]

[0099] In the formula, For the allowable bandwidth, This is the interference type complexity coefficient (1 for conducted interference, 1.5 for radiated interference, and 2.0 for electrostatic discharge). This coefficient is set based on the complexity of the interference characteristics of different interference types. Electrostatic discharge interference has the most complex spectral characteristics, the shortest duration, and the most uncertain impact on equipment, therefore it is assigned the highest complexity coefficient. Conducted interference has a relatively fixed propagation path and simpler spectral characteristics, so it is assigned the lowest complexity coefficient. For example, if the theoretical interference baseline threshold is 0.825V, the allowable bandwidth for electrostatic discharge interference is 0.825 × (0.1 + 0.05 × 2.0) = 0.825 × 0.2 = 0.165V.

[0100] The tolerance range boundaries are visualized and marked. In the two-dimensional coordinate system of time-interference intensity, the upper tolerance boundary is obtained by shifting the tolerance bandwidth upward with the reference curve as the center, and the lower tolerance boundary is obtained by shifting the tolerance bandwidth downward. The reference curve is marked with a solid red line, the upper tolerance boundary is marked with a dashed blue line, and the lower tolerance boundary is marked with a dashed green line, forming an initial interference judgment spectrum. The spectrum is marked with interference type identifier, time scale, and interference intensity scale for easy intuitive viewing and subsequent comparative analysis.

[0101] Collect equipment temperature drift data, power fluctuation parameters, and sensor noise spectrum during the test process, construct a dynamic compensation coefficient matrix, and inject the dynamic compensation coefficient matrix into the initial interference judgment spectrum to obtain the dynamic interference judgment spectrum.

[0102] The process of constructing the dynamic compensation coefficient matrix includes:

[0103] The noise energy entropy value is calculated based on the sensor noise spectrum, and a noise compensation coefficient is generated. The formula is as follows:

[0104]

[0105] In the formula, This is the noise compensation factor (value range 0.8-1.0). The noise energy entropy value. This represents the maximum permissible noise energy entropy value.

[0106] Based on the equipment temperature drift data, the temperature compensation coefficient is calculated using the following formula:

[0107]

[0108] In the formula, This is the temperature compensation coefficient. For equipment temperature coefficient, This is the actual test temperature. This is the standard test temperature.

[0109] Analyze power supply fluctuation parameters and calibrate the voltage stability coefficient. The formula is as follows:

[0110]

[0111] In the formula, The voltage stability coefficient. Standard supply voltage, This is the actual power supply voltage.

[0112] Integrating noise compensation coefficients, temperature compensation coefficients, and voltage stability coefficients, a dynamic compensation coefficient matrix is ​​obtained, in the form of: .

[0113] The process of injecting the dynamic compensation coefficient matrix into the initial interference determination map to obtain the dynamic interference determination map includes:

[0114] Based on the dynamic compensation coefficient matrix, the theoretical interference reference threshold of the initial spectrum is adjusted time-series, as expressed by the formula:

[0115]

[0116] In the formula, The adjusted theoretical interference reference threshold, for example, the initial theoretical interference reference threshold. The voltage is 0.825V, and the noise compensation factor is [missing information]. The temperature compensation coefficient is 0.9. The voltage stability coefficient is 1.0025. If the value is 1.0476, then the adjusted theoretical interference reference threshold is 0.825×0.9×1.0025×1.0476≈0.825×0.9447≈0.780V.

[0117] Based on the interference sensitivity coefficient, the allowable bandwidth is dynamically adjusted. ,in This refers to the interference sensitivity coefficient. A larger interference sensitivity coefficient indicates a larger allowable bandwidth and a higher tolerance to fluctuations in interference intensity, such as the initial allowable bandwidth. The interference sensitivity coefficient is 0.165V. If the value is 1.2, then the adjusted tolerance bandwidth is 0.165 × 1.2 = 0.198V.

[0118] A compensation factor numerical marker layer is superimposed on the initial interference determination spectrum. The marker layer displays the noise compensation coefficient, temperature compensation coefficient, voltage stability coefficient, and adjusted theoretical interference reference threshold at the current time point in real time. The markers are marked in yellow and are located on the right side of the time-interference intensity two-dimensional coordinate system, without affecting the main display content of the spectrum.

[0119] Establish a real-time data interface with the smart sensor and update the dynamic compensation coefficient matrix according to a preset cycle (1-5 seconds).

[0120] Collect real-time electromagnetic compatibility (EMC) test data sequences, compare the actual average interference values ​​at each test stage, and calculate the feature similarity between the real-time test data and the dynamic interference judgment spectrum within each interference time window to diagnose the EMC status of the electrocardiograph. The process includes:

[0121] The actual mean interference for each test phase is calculated using the following formula:

[0122]

[0123] In the formula, The actual mean of the interference is N, where N is the number of sampling points during the testing phase. Let be the interference amplitude at the j-th sampling point.

[0124] The cosine similarity algorithm is used to calculate the feature similarity between real-time test data and dynamic interference judgment map. The formula is as follows:

[0125]

[0126] In the formula, S represents the feature similarity (ranging from 0 to 1), and M represents the number of sampling points within the time window. The magnitude of the k-th point in the real-time test data. This represents the amplitude at point k in the dynamic graph.

[0127] When the actual mean interference exceeds the dynamic tolerance range or the feature similarity is lower than the preset threshold, the electrocardiograph is determined to have an electromagnetic compatibility (EMC) abnormality, and the abnormality type and source tracing results are output. Abnormality types include interference intensity exceeding the limit and feature similarity mismatch. Interference intensity exceeding the limit is further subdivided into upper limit exceeding the limit and lower limit exceeding the limit. The source tracing results are based on the test environment parameters, equipment status parameters, and interference type characteristics at the time of the abnormality, analyzing the causes of the abnormality, such as excessively high environmental electromagnetic field strength leading to excessive radiated interference intensity, or excessive power supply harmonic content leading to conduction interference feature similarity mismatch. The output results are presented in the form of a text report and a visual graph with annotations. The text report includes the time of the abnormality, the abnormality type, the abnormal value, the source tracing cause, and handling suggestions. The visual graph uses red flashing markers to indicate abnormal areas, facilitating quick location and troubleshooting for users.

[0128] In summary, this embodiment provides a diagnostic method for electromagnetic compatibility test data of electrocardiographs based on intelligent sensors. By collecting multi-dimensional electromagnetic interference data through intelligent sensors and combining time-domain to frequency-domain conversion and core feature extraction technology, it can effectively filter out environmental background noise, accurately distinguish the differentiated characteristics of different types of interference, and encapsulate the test data into structured objects, providing standardized data support for interference source tracing and historical data comparison, thus significantly improving the accuracy of interference identification and the systematic nature of data processing.

[0129] By introducing a dynamic benchmark threshold and compensation mechanism, the method's environmental adaptability and diagnostic accuracy are enhanced. A theoretical interference benchmark threshold is constructed by analyzing historical test data, and a compensation coefficient matrix is ​​built by combining dynamic factors such as equipment temperature drift, power fluctuations, and sensor noise. The interference judgment criteria are adjusted in real time, effectively avoiding the limitations of fixed thresholds in complex environments and ensuring stable and reliable diagnostic results in different test scenarios.

[0130] By collecting test data in real time and calculating the actual interference mean and feature similarity, the electromagnetic compatibility status of the equipment can be quickly determined. Once an anomaly is detected, the anomaly type and source tracing results can be output immediately, providing staff with a clear direction for problem localization, greatly shortening the time for equipment debugging and interference suppression, and improving testing and maintenance efficiency.

[0131] The application of this method helps improve the safety and reliability of electrocardiographs in clinical use. By accurately identifying and warning of electromagnetic interference risks, it reduces the impact of interference on the measurement data of the equipment, reduces the risk of misdiagnosis and missed diagnosis caused by data distortion, and provides strong support for the accurate diagnosis of cardiovascular diseases. At the same time, it provides new ideas and technical support for the development of electromagnetic compatibility testing technology for medical equipment, and has broad application prospects and promotion value.

[0132] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0133] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A diagnostic method for electromagnetic compatibility test data of an electrocardiograph based on intelligent sensors, characterized in that, include: Collect equipment parameters, test environment parameters, and multi-dimensional electromagnetic interference data collected by intelligent sensors in the electromagnetic compatibility test scenario of electrocardiograph. Identify the interference type sequence in the test data by decoding the interference source characteristics, and extract the feature identifier of each interference type in combination with the equipment parameters to generate structured test data. Collect historical electromagnetic compatibility test data, extract interference intensity distribution, equipment anti-interference response curve and interference timing characteristics from the historical data, and calculate the theoretical interference reference threshold based on the interference intensity distribution and equipment anti-interference response curve; Set a dynamic tolerance range and generate an initial interference judgment spectrum arranged in the interference time sequence by combining the theoretical interference benchmark threshold; Collect equipment temperature drift data, power fluctuation parameters and sensor noise spectrum during the test process, construct a dynamic compensation coefficient matrix, and inject the dynamic compensation coefficient matrix into the initial interference judgment spectrum to obtain the dynamic interference judgment spectrum. Collect real-time electromagnetic compatibility test data sequences, compare the actual average interference value at each test stage, and calculate the feature similarity between the real-time test data within each interference time window and the dynamic interference judgment spectrum to diagnose the electromagnetic compatibility status of the electrocardiograph.

2. The method for diagnosing electromagnetic compatibility test data of an electrocardiograph based on a smart sensor according to claim 1, characterized in that, The equipment parameters include the ECG machine signal sampling rate, input impedance threshold, filter circuit cutoff frequency, amplifier gain parameters, and lead interface anti-interference level; the test environment parameters include ambient electromagnetic field strength, temperature and humidity gradient, grounding resistance value, and power supply harmonic content; the multi-dimensional electromagnetic interference data include conducted interference voltage data, radiated interference field strength data, electrostatic discharge pulse data, and surge impact response data; the feature identifiers include interference frequency bandwidth, interference amplitude peak value, interference duration, pulse rise slope, and spectral distortion coefficient.

3. The method for diagnosing electromagnetic compatibility test data of an electrocardiograph based on a smart sensor according to claim 1, characterized in that, The process of identifying interference type sequences in test data through interference source feature decoding includes: The collected raw electromagnetic interference data were transformed from the time domain to the frequency domain to extract key spectral features; Continuous interference segments are segmented based on the type and amplitude changes of key spectral features to generate an initial interference sequence; Extract the core feature set for each type of interference in the initial interference sequence. The core feature set includes the interference frequency range and the interference triggering conditions. By filtering out environmental background noise interference from the initial interference sequence based on the core feature set, the interference type sequence in the test data is obtained.

4. The method for diagnosing electromagnetic compatibility test data of an electrocardiograph based on a smart sensor according to claim 1, characterized in that, The process of extracting feature identifiers for each type of interference by combining equipment parameters and generating structured test data includes: Based on the interference frequency range and interference triggering conditions, the effective filtering threshold is obtained by associating the electrocardiograph's filter circuit parameters. Calculate the interference attenuation by combining the interference frequency range and the effective filtering threshold; By associating the input impedance threshold, the maximum permissible interference amplitude for the current interference type is derived. Based on the interference immunity level of the lead interface, calibrate the interference sensitivity coefficient; The unique identifier of the interference type, the core feature set, and the interference attenuation amount are encapsulated into a structured data object to obtain structured test data.

5. The method for diagnosing electromagnetic compatibility test data of an electrocardiograph based on a smart sensor according to claim 1, characterized in that, The process of extracting interference intensity distribution, equipment anti-interference response curves, and interference timing characteristics from historical electromagnetic compatibility test data includes: Filter historical test records of the same model of electrocardiograph; Analyze the interference attenuation in historical structured data objects and statistically analyze the probability distribution of interference intensity; Analyze historical sensor data to construct a mapping model between interference intensity and device output distortion; Extract the timestamps and interference type conversion relationships of historical interference sequences.

6. The method for diagnosing electromagnetic compatibility test data of an electrocardiograph based on a smart sensor according to claim 1, characterized in that, The process of calculating the theoretical interference reference threshold based on the interference intensity distribution and the equipment's anti-interference response curve includes: Based on the interference intensity distribution, map the equipment's anti-interference model to generate basic interference reference values; Superimposed equipment inherent noise reference value; An electromagnetic compatibility safety margin coefficient is introduced to generate a theoretical interference reference threshold.

7. The method for diagnosing electromagnetic compatibility test data of an electrocardiograph based on a smart sensor according to claim 1, characterized in that, The process of generating an initial interference determination map arranged in the interference time sequence based on a theoretical interference benchmark threshold includes: Create a two-dimensional coordinate system for timing and interference intensity; A reference curve is formed based on the theoretical baseline threshold of the interference timing connection; Differentiated tolerance bandwidths are set based on the characteristics of the interference type; Visualize and annotate the tolerance range boundaries to form an initial interference judgment map.

8. The method for diagnosing electromagnetic compatibility test data of an electrocardiograph based on a smart sensor according to claim 1, characterized in that, The process of constructing the dynamic compensation coefficient matrix includes: Calculate the noise energy entropy value based on the sensor noise spectrum, and generate the noise compensation coefficient; Calculate the temperature compensation coefficient based on the equipment temperature drift data; Analyze power supply fluctuation parameters and calibrate the voltage stability coefficient; By integrating noise compensation coefficient, temperature compensation coefficient, and voltage stability coefficient, a dynamic compensation coefficient matrix is ​​obtained.

9. The method for diagnosing electromagnetic compatibility test data of an electrocardiograph based on a smart sensor according to claim 1, characterized in that, The process of injecting the dynamic compensation coefficient matrix into the initial interference determination map to obtain the dynamic interference determination map includes: Based on the dynamic compensation coefficient matrix, the theoretical interference reference threshold of the initial spectrum is adjusted sequentially over time. The allowable bandwidth is dynamically adjusted based on the interference sensitivity coefficient. A compensation factor numerical labeling layer is superimposed on the initial interference determination map; Establish a real-time data interface and update the dynamic compensation coefficient matrix according to a preset cycle.

10. The method for diagnosing electromagnetic compatibility test data of an electrocardiograph based on a smart sensor according to claim 1, characterized in that, The process of diagnosing the electromagnetic compatibility status of an electrocardiograph includes: The mean value of actual interference in each test phase is calculated, and the cosine similarity algorithm is used to calculate the feature similarity between the real-time test data and the dynamic interference judgment map. When the actual mean interference exceeds the dynamic tolerance range or the feature similarity is lower than the preset threshold, the electrocardiograph is determined to be in an abnormal electromagnetic compatibility state, and the abnormality type and source tracing results are output.

Images