Electrocardiograph electromagnetic compatibility test data diagnosis method based on intelligent sensor

Abstract

The invention provides an electrocardiograph electromagnetic compatibility test data diagnosis method based on an intelligent sensor, and relates to the technical field of electrocardiograph electromagnetic compatibility test. The method includes generating structured test data. And calculating a theoretical interference reference threshold. And generating an initial interference judgment atlas arranged according to the interference time sequence. And constructing a dynamic compensation coefficient matrix, and injecting the dynamic compensation coefficient matrix into the initial interference determination map to obtain a dynamic interference determination map. And calculating the characteristic similarity between the real-time test data in each interference time sequence window and the dynamic interference judgment map, and diagnosing the electromagnetic compatibility state of the electrocardiograph. According to the invention, through multi-dimensional data acquisition and interference identification, through a dynamic reference threshold and a compensation mechanism, environment and equipment state changes are adapted, the diagnosis stability of a complex scene is improved, through real-time data comparison and traceability, the equipment state is rapidly judged, the interference source is positioned, the debugging time is shortened, and finally the measurement accuracy of the electrocardiograph is guaranteed.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electrocardiograph electromagnetic compatibility testing, and particularly relates to an electrocardiograph electromagnetic compatibility test data diagnosis method based on intelligent sensors. BACKGROUND

[0002] In the modern medical system, as the core medical instrument for diagnosing cardiovascular diseases, the accuracy of the measurement data of the electrocardiograph directly relates to the scientificity of clinical diagnosis and the effectiveness of treatment plan. With the continuous progress of medical technology, the functions of the electrocardiograph are increasingly rich, and the integration and intelligence levels continue to improve. At the same time, its application scenarios have expanded from traditional hospital wards and treatment rooms to mobile medical care, remote monitoring, community medical care and other diversified environments, making the electromagnetic environment faced by the device increasingly complex.

[0003] Currently, there are a large number of electromagnetic radiation sources in the medical scene, including high-frequency surgical devices, monitors, medical imaging devices, communication devices, etc. These devices will produce various types of electromagnetic interference such as conducted interference, radiated interference, electrostatic discharge, surge impact, etc. during operation. These electromagnetic interferences will act on the electrocardiograph through power lines, signal lines or space propagation, etc., causing the output electrocardiograph signal of the device to have problems such as baseline drift, waveform distortion, noise superposition, etc. In severe cases, it can mask the true physiological signal characteristics, affecting the accurate judgment of the medical staff on the patient's condition, and even may cause misdiagnosis, missed diagnosis and other medical risks.

[0004] Electromagnetic compatibility performance has become a key indicator to measure the quality and safety of the electrocardiograph, and the electromagnetic compatibility requirements of the electrocardiograph in relevant industry standards and regulations are also increasingly strict. However, the existing electrocardiograph electromagnetic compatibility test technology is difficult to fully capture the multi-type interference characteristics in a complex electromagnetic environment; the dynamic factors such as environmental temperature and humidity, power stability, and state changes of the device itself are not considered in the test process, resulting in insufficient repeatability and reliability of the test results; it is difficult to distinguish interference signals from environmental background noise, and misjudgment is easy to occur; test data are mostly stored and processed in raw form, lacking systematic feature extraction and structured management, which is not conducive to interference tracing and in-depth analysis of test results, resulting in that the existing electromagnetic compatibility test technology cannot meet the high-precision and high-reliability requirements of the electrocardiograph test in complex medical environments, and cannot provide sufficient technical support for the electromagnetic compatibility performance optimization and quality control of the device. SUMMARY

[0005] The present application provides an electrocardiograph electromagnetic compatibility test data diagnosis method based on intelligent sensors to solve the defects in the prior art.

[0006] The present application provides an electrocardiograph electromagnetic compatibility test data diagnosis method based on intelligent sensors, comprising:

[0007] Collect the equipment parameters, test environment parameters and multi-dimensional electromagnetic interference data collected by intelligent sensors of the electrocardiograph electromagnetic compatibility test scene, identify the interference type sequence in the test data through interference source feature decoding, 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 the interference intensity distribution, equipment anti-interference response curve and interference timing characteristics in the historical data, and calculate the theoretical interference reference threshold according to the interference intensity distribution and the equipment anti-interference response curve.

[0009] Set a dynamic tolerance range, and generate an initial interference judgment atlas arranged according to the interference timing in combination with the theoretical interference reference threshold.

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

[0011] Collect real-time electromagnetic compatibility test data sequences, compare the actual interference mean value of each test stage, calculate the feature similarity between the real-time test data in each interference timing window and the dynamic interference judgment atlas, and diagnose the electromagnetic compatibility state of the electrocardiograph.

[0012] According to the electrocardiograph electromagnetic compatibility test data diagnosis method based on intelligent sensors provided by the application, the equipment parameters include the electrocardiograph signal sampling rate, input impedance threshold, filter circuit cutoff frequency, amplifier gain parameter and lead interface anti-interference level. The test environment parameters include the environmental electromagnetic field intensity, temperature and humidity gradient, grounding resistance value and power supply harmonic content. The multi-dimensional electromagnetic interference data includes conducted interference voltage data, radiated interference field strength data, electrostatic discharge pulse data and surge impact response data. The feature identifier includes the interference frequency bandwidth, interference amplitude peak value, interference duration, pulse rising edge slope and spectrum distortion coefficient.

[0013] According to the electrocardiograph electromagnetic compatibility test data diagnosis method based on intelligent sensors provided by the application, the process of identifying the interference type sequence in the test data through interference source feature decoding includes:

[0014] The collected electromagnetic interference original data is converted from time domain to frequency domain to extract key spectral features.

[0015] Based on the type and amplitude variation of the key spectral features, the continuous interference section is segmented to generate an initial interference sequence.

[0016] The core feature set of each interference type in the initial interference sequence is extracted, and the core feature set includes the interference frequency range and the interference trigger condition.

[0017] According to the core feature set, environmental background noise interference in the initial interference sequence is filtered out, and an interference type sequence in the test data is obtained.

[0018] According to the electrocardiograph electromagnetic compatibility test data diagnosis method based on the intelligent sensor provided by the application, the feature identification of each interference type is extracted combined with the device parameters, and the process of generating the structured test data includes:

[0019] According to the interference frequency range and the interference trigger condition, the effective filtering threshold is obtained by associating the electrocardiograph filtering circuit parameters.

[0020] Combined with the interference frequency range and the effective filtering threshold, the interference attenuation amount is calculated.

[0021] The maximum allowed interference amplitude of the current interference type is derived in association with the input impedance threshold.

[0022] The interference sensitivity coefficient is calibrated combined with the lead interface anti-interference level.

[0023] The interference type unique identifier, the core feature set and the interference attenuation amount are packaged as a structured data object, and the structured test data is obtained.

[0024] According to the electrocardiograph electromagnetic compatibility test data diagnosis method based on the intelligent sensor provided by the application, the process of extracting the interference intensity distribution, the device anti-interference response curve and the interference timing feature in the historical electromagnetic compatibility test data includes:

[0025] The historical test records of the same type of electrocardiograph are screened.

[0026] The interference attenuation amount in the historical structured data object is analyzed, and the interference intensity probability distribution is counted.

[0027] The mapping model of interference intensity and device output distortion is constructed by analyzing the historical sensor acquisition data.

[0028] The time stamp and interference type conversion relationship of the historical interference sequence are extracted.

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

[0030] According to the interference intensity distribution, the device anti-interference model is generated, and the basic interference reference value is generated.

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

[0032] The electromagnetic compatibility safety margin coefficient is introduced, and the theoretical interference reference threshold is generated.

[0033] The electrocardiograph electromagnetic compatibility test data diagnosis method based on the intelligent sensor provided by the application, the process of generating the initial interference judgment atlas arranged according to the interference time sequence in combination with the theoretical interference reference threshold value comprises:

[0034] A time sequence-interference intensity two-dimensional coordinate system is created.

[0035] The theoretical reference threshold value is connected according to the interference time sequence to form a reference curve.

[0036] The difference tolerance bandwidth is set according to the interference type characteristics.

[0037] The tolerance range boundary is visually marked to form the initial interference judgment atlas.

[0038] The process of constructing the dynamic compensation coefficient matrix in the electrocardiograph electromagnetic compatibility test data diagnosis method based on the intelligent sensor provided by the application comprises:

[0039] The noise compensation coefficient is generated according to the noise spectrum of the sensor.

[0040] The temperature compensation coefficient is calculated according to the device temperature drift data.

[0041] The voltage stability coefficient is calibrated by analyzing the power fluctuation parameters.

[0042] The noise compensation coefficient, the temperature compensation coefficient and the voltage stability coefficient are integrated to obtain the dynamic compensation coefficient matrix.

[0043] The process of injecting the dynamic compensation coefficient matrix into the initial interference judgment atlas to obtain the dynamic interference judgment atlas in the electrocardiograph electromagnetic compatibility test data diagnosis method based on the intelligent sensor provided by the application comprises:

[0044] The theoretical interference reference threshold value of the initial atlas is adjusted according to the dynamic compensation coefficient matrix.

[0045] The tolerance bandwidth is dynamically scaled according to the interference sensitivity coefficient.

[0046] A compensation factor value marking layer is superimposed on the initial interference judgment atlas.

[0047] A real-time data interface is established, and the dynamic compensation coefficient matrix is updated according to a preset period.

[0048] The process of diagnosing the electrocardiograph electromagnetic compatibility state in the electrocardiograph electromagnetic compatibility test data diagnosis method based on the intelligent sensor provided by the application comprises:

[0049] The actual interference mean value of each test stage 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 atlas.

[0050] When the actual interference mean value exceeds the dynamic tolerance range or the feature similarity is lower than the preset threshold, it is determined that the electrocardiograph electromagnetic compatibility state is abnormal, and the abnormal type and the tracing result are output.

[0051] The electrocardiograph electromagnetic compatibility test data diagnosis method based on intelligent sensors provided by the application can effectively filter out environmental background noise, accurately distinguish the differential characteristics of different types of interference, encapsulate the test data as structured objects, provide standardized data support for interference tracing and historical data comparison, and greatly improve the accuracy of interference identification and the systematicness of data processing.

[0052] By introducing a dynamic reference threshold and a compensation mechanism, the environmental adaptability and diagnostic accuracy of the method are enhanced. By analyzing historical test data to construct a theoretical interference reference threshold, and combining with dynamic factors such as device temperature drift, power fluctuation and sensor noise to construct a compensation coefficient matrix, the interference judgment standard is adjusted in real time, effectively avoiding the limitations of fixed threshold in complex environment, and ensuring stable and reliable diagnostic results in different test scenarios.

[0053] By real-time acquisition of test data and calculation of actual interference mean value and feature similarity, the electromagnetic compatibility state of the device can be quickly determined, and once an abnormality is found, the abnormal type and the tracing result can be immediately output, providing clear problem positioning direction for the staff, greatly shortening the time of device debugging and interference suppression, and improving the test and maintenance efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the application or prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0055] Figure 1 is a flowchart of the electrocardiograph electromagnetic compatibility test data diagnosis method based on intelligent sensors provided by the embodiments of the application;

[0056] Figure 2 is a flowchart of the interference type sequence recognition in the test data by interference source feature decoding in the embodiments of the application;

[0057] Figure 3 is a flowchart of the generation of structured test data in the embodiments of the application;

[0058] Figure 4is a flowchart of constructing a dynamic compensation coefficient matrix in the embodiment of the application;

[0059] Figure 5 is a flowchart of obtaining a dynamic interference judgment graph in the embodiment of the application. DETAILED DESCRIPTION

[0060] In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below with reference to the drawings in the present application. Obviously, the described embodiments are some embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the protection scope of the present application.

[0061] The present application is described below with reference to the drawings. Figures 1-5 The present application provides an electrocardiograph electromagnetic compatibility test data diagnosis method based on an intelligent sensor.

[0062] The electrocardiograph electromagnetic compatibility test data diagnosis method based on an intelligent sensor provided by the embodiment of the present application comprises the following steps.

[0063] Device parameters, test environment parameters and multi-dimensional electromagnetic interference data collected by an intelligent sensor in an electrocardiograph electromagnetic compatibility test scene are collected, the interference type sequence in the test data is identified through interference source feature decoding, and the feature identifier of each interference type is extracted in combination with the device parameters to generate structured test data.

[0064] The device parameters include an electrocardiograph signal sampling rate, an input impedance threshold value, a filter circuit cutoff frequency, an amplifier gain parameter and a lead interface anti-interference level. The test environment parameters include an environmental electromagnetic field intensity, a temperature and humidity gradient, a grounding resistance value and a power supply harmonic content. The multi-dimensional electromagnetic interference data include conducted interference voltage data, radiated interference field intensity data, electrostatic discharge pulse data and surge impact response data. The feature identifier includes an interference frequency bandwidth, an interference amplitude peak value, an interference duration, a pulse rising edge slope and a spectral distortion coefficient.

[0065] The process of identifying the interference type sequence in the test data through interference source feature decoding comprises the following steps.

[0066] The collected electromagnetic interference original data is subjected to time domain-frequency domain conversion, a fast Fourier transform algorithm is used to convert the continuous voltage or field intensity signal in the time domain into spectral distribution data in the frequency domain, the spectral resolution is ensured to meet the interference feature extraction requirement, and key spectral features including a center frequency corresponding to a spectral peak value, an amplitude distribution law of the spectrum, an amplitude proportion of a feature frequency point and other core parameters are extracted.

[0067] The continuous interference segment is segmented based on the type and amplitude value change of the key spectral features, an amplitude value threshold (set as 3 times the amplitude value of the device inherent noise) and a frequency change rate threshold (set as 10 MHz / μs) are set, when the amplitude value in the original data exceeds the amplitude value threshold and the frequency change rate exceeds the frequency change rate threshold, it is determined that the starting point of the interference signal, when the amplitude value is lower than the amplitude value threshold and the duration exceeds 50 μs, it is determined that the end point of the interference signal, thereby the continuous interference segment is segmented, and the initial interference sequence is generated, each initial interference segment includes a starting time stamp, an ending time stamp, time domain waveform data and frequency domain spectral data.

[0068] The core feature set of each interference type in the initial interference sequence is extracted, the core feature set includes an interference frequency range and an interference trigger condition, the interference frequency range is determined through spectral analysis, and the frequency interval corresponding to the interference signal amplitude greater than the peak amplitude by 3 dB is taken as the interference frequency range. The interference trigger condition is determined according to the cause of the interference, for example, the trigger condition of conducted interference is usually related to the power load change, the trigger condition of electrostatic discharge interference is related to the discharge voltage and the number of discharges, and the trigger condition of radiation interference is related to the working state of the surrounding electromagnetic radiation source.

[0069] According to the core feature set, the environmental background noise interference in the initial interference sequence is filtered out, and an adaptive noise suppression algorithm is used to match the core feature set of each initial interference segment with a preset environmental background noise feature library, and if the matching similarity is higher than 80%, it is determined that it is an environmental background noise interference, and is filtered out, to obtain the interference type sequence in the test data, each element in the sequence includes an interference type label, interference time information and core feature set data.

[0070] The feature identification of each interference type is extracted in combination with the device parameters, and the process of generating structured test data includes:

[0071] According to the interference frequency range and the interference trigger condition, the electrocardiograph filter circuit parameters are associated, the filter circuit parameters include the cutoff frequency, the filter order and the filter type (low pass, high pass or band pass), the attenuation characteristics of the filter circuit under different interference frequencies are simulated through a circuit simulation software (such as Multisim), and the effective filter threshold is obtained, the effective filter threshold refers to the input signal amplitude corresponding to the actual attenuation amount of the filter circuit reaching 30 dB for the interference frequency signal.

[0072] The interference attenuation amount is calculated in combination with the interference frequency range and the effective filter threshold, and the formula is:

[0073]

[0074] In the formula, is the attenuation amount of the i-th interference, is the interference frequency, is the cutoff frequency of the filter circuit, For the amplifier gain compensation value, the formula combines the amplifier gain compensation by the logarithmic operation of the frequency ratio to quantify the degree of attenuation of the interference signal after filtering and amplification by the device, for example, when the interference frequency is 10 kHz, the filter circuit cutoff frequency is 5 kHz, and the amplifier gain compensation value is 2 dB, the interference attenuation is 20lg(10k / 5k)+2=20×0.3010+2=8.02dB.

[0075] In association with the input impedance threshold, the maximum allowed interference amplitude of the current interference type is derived, and the formula is expressed as:

[0076]

[0077] In the formula, is the maximum allowed interference amplitude, is the input impedance of the electrocardiograph, is the maximum leakage current allowed by the device, is the safety factor.

[0078] In combination with the lead interface anti-interference level, the interference sensitivity coefficient is calibrated.

[0079] The interference type unique identifier, core feature set, and interference attenuation are packaged as structured data objects, and structured test data is obtained.

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

[0081] The historical electromagnetic compatibility test data includes test data of the same type of electrocardiograph under different test environments, different interference types, and different interference intensities, covering structured test data, device output distortion data, test environment parameter records, device working state parameters, etc. The data time span is not less than 1 year, the test sample number is not less than 1000 groups, ensuring the diversity and representativeness of the data, and the data sources include laboratory test data, field use test data, and industry similar device test data.

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

[0083] Screening historical test records of the same type of electrocardiograph, screening data by device model code, and eliminating records with inconsistent models, missing test conditions, or abnormal data. The abnormal data judgment standard is that the interference amplitude exceeds 3 times the standard deviation of the normal range.

[0084] The interference attenuation amount in the historical structured data object is analyzed, statistical analysis methods (such as histogram statistics and probability density function fitting) are used to statistically analyze the interference intensity probability distribution, the interference intensity obeys a lognormal distribution or a Weibull distribution, the fitting degree of the distribution type is verified through K-S test (Kolmogorov-Smirnov test), and the fitting degree threshold is set to 0.95, so as to ensure that the distribution model can accurately reflect the distribution rule of the historical interference intensity.

[0085] The historical sensor collected data and corresponding device output data are analyzed, the device output data includes ECG machine output signal distortion, baseline drift, signal-to-noise ratio and other indicators, a mapping model of interference intensity and device output distortion is constructed, a least square method is used to fit a linear or nonlinear mapping relationship, the mapping model can quantify the change rule of device output performance under different interference intensities, for example, when the interference intensity exceeds a certain threshold, the device output distortion will rise sharply. Finally, the timestamp and interference type conversion relationship of the historical interference sequence are extracted, the occurrence time and duration of each interference event are recorded, the conversion probability between different interference types is statistically analyzed, such as the probability of radiation interference after conduction interference, the probability of surge interference after electrostatic discharge interference, and a interference timing conversion matrix is formed.

[0086] The process of calculating the theoretical interference reference threshold according to the interference intensity distribution and the device anti-interference response curve includes:

[0087] According to the interference intensity distribution and the device anti-interference model, the device anti-interference model is represented by a segmented function, when the interference intensity is lower than the first threshold, the device output distortion is less than 1%, and it is determined that the device is in a normal working interval. When the interference intensity is between the first threshold and the second threshold, the device output distortion is between 1%-5%, and it is determined that the device is in a lightly disturbed interval. When the interference intensity is higher than the second threshold, the device output distortion is greater than 5%, and it is determined that the device is in a severely disturbed interval, and the first threshold is taken as the basic interference reference value .

[0088] The formula is:

[0089]

[0090] In the formula, is the reference value after superimposing the inherent noise, is the basic interference reference value, The formula reflects the superposition effect of the basic interference and the device's own noise, because in the actual test scene, the device is not only affected by external interference, but also has its own inherent noise, both of which affect the working state of the device. For example, if the basic interference reference value is 0.5V and the device inherent noise amplitude is 0.05V, the reference value after superimposing the inherent noise is 0.55V.

[0091] The electromagnetic compatibility safety margin coefficient is introduced to generate the theoretical interference reference threshold, which is expressed by the formula:

[0092]

[0093] In the formula, is the theoretical interference reference threshold, is the electromagnetic compatibility safety margin coefficient (value range 1.3-1.8), for medical devices and other scenes with high safety requirements, the value is 1.6-1.8. For ordinary scenes, the value is 1.3-1.5. The setting of the safety margin coefficient ensures that the device can maintain normal working state even if it is affected by unexpected interference during actual use, avoiding device failure or measurement error caused by interference. For example, if the reference value after superimposing the inherent noise is 0.55V and the safety margin coefficient is 1.5, the theoretical interference reference threshold is 0.55x1.5=0.825V.

[0094] Set the dynamic tolerance range and generate the initial interference judgment graph arranged according to the interference time sequence in combination with the theoretical interference reference threshold, the process includes:

[0095] Create a time-interference intensity two-dimensional coordinate system, the horizontal coordinate is time, the time range is set according to the test period, and the vertical coordinate is the interference intensity, the vertical coordinate range is 0.5-2 times the theoretical interference reference threshold, which ensures that the change range of the interference intensity can be completely displayed.

[0096] Connect the theoretical reference threshold according to the interference time sequence to form a reference curve, determine the theoretical interference reference threshold in different time periods according to the historical interference time sequence conversion matrix, connect the theoretical reference threshold of each time period in time sequence to form a continuous reference curve, the slope of the reference curve reflects the change trend of the interference intensity with time, the positive slope indicates that the interference intensity gradually increases, and the negative slope indicates that the interference intensity gradually decreases.

[0097] Set a differentiated tolerance bandwidth according to the interference type characteristics, which is expressed by the formula:

[0098]

[0099] In the formula, is the tolerance bandwidth, The interference type complexity coefficient (1 for conducted interference, 1.5 for radiated interference, and 2.0 for electrostatic discharge) is set based on the complexity of the interference characteristics of different interference types. The spectral characteristics of electrostatic discharge interference are the most complex, the duration is the shortest, and the impact on the device is the most uncertain, so the highest complexity coefficient is assigned. The propagation path of conducted interference is relatively fixed, and the spectral characteristics are simple, so the lowest complexity coefficient is assigned. For example, the theoretical interference reference threshold is 0.825V, and for electrostatic discharge interference, the tolerance bandwidth is 0.825x(0.1+0.05x2.0)=0.825x0.2=0.165V.

[0100] The tolerance range boundary is visualized. In the time-interference intensity two-dimensional coordinate system, the upper tolerance boundary is offset by the tolerance bandwidth from the reference curve, and the lower tolerance boundary is offset by the tolerance bandwidth from the reference curve. The reference curve is marked with a red solid line, the upper tolerance boundary is marked with a blue dashed line, and the lower tolerance boundary is marked with a green dashed line to form an initial interference judgment graph. The graph is labeled with interference type identification, time scale and interference intensity scale for intuitive viewing and subsequent comparative analysis.

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

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

[0103] According to the sensor noise spectrum, the noise energy entropy value is calculated, and the noise compensation coefficient is generated, which is expressed by the formula:

[0104]

[0105] In the formula, The noise compensation coefficient (value range 0.8-1.0), The noise energy entropy value, The maximum allowed noise energy entropy value.

[0106] According to the device temperature drift data, the temperature compensation coefficient is calculated, which is expressed by the formula:

[0107]

[0108] In the formula, The temperature compensation coefficient, The device temperature coefficient, The actual test temperature, The standard test temperature.

[0109] Analyze the power fluctuation parameters and calibrate the voltage stability coefficient, which is expressed by the formula:

[0110]

[0111] In the formula, is a voltage stability coefficient, is a standard power supply voltage, is an actual power supply voltage.

[0112] The integrated noise compensation coefficient, temperature compensation coefficient and voltage stability coefficient are obtained to obtain a dynamic compensation coefficient matrix, and the matrix form is .

[0113] The process of injecting the dynamic compensation coefficient matrix into the initial interference judgment graph to obtain a dynamic interference judgment graph includes:

[0114] According to the dynamic compensation coefficient matrix, the theoretical interference reference threshold of the initial graph is adjusted in time sequence, and the formula is expressed as:

[0115]

[0116] In the formula, is an adjusted theoretical interference reference threshold, for example, the initial theoretical interference reference threshold is 0.825V, the noise compensation coefficient is 0.9, the temperature compensation coefficient is 1.0025, the voltage stability coefficient 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] According to the interference sensitivity coefficient, the dynamic scaling tolerance bandwidth, the adjusted tolerance bandwidth , wherein is an interference sensitivity coefficient, the greater the interference sensitivity coefficient, the greater the tolerance bandwidth, the higher the tolerance of the fluctuation of the interference intensity, for example, the initial tolerance bandwidth is 0.165V, the interference sensitivity coefficient is 1.2, then the adjusted tolerance bandwidth is 0.165*1.2=0.198V.

[0118] The compensation factor value marking layer is superimposed on the initial interference judgment graph, and the noise compensation coefficient, temperature compensation coefficient, voltage stability coefficient and adjusted theoretical interference reference threshold of the current time sequence point are displayed in real time in the marking layer. Yellow text is used for annotation, and the annotation position is located on the right side of the time sequence-interference intensity two-dimensional coordinate system, which does not affect the main display content of the graph.

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

[0120] Collect real-time electromagnetic compatibility test data sequences, compare the actual interference mean value of each test stage, and calculate the feature similarity of real-time test data and dynamic interference judgment atlas within each interference timing window, to diagnose the electromagnetic compatibility state of the electrocardiograph, the process includes:

[0121] The actual interference mean value of each test stage is calculated, and the formula is:

[0122]

[0123] In the formula, is the actual interference mean value, N is the number of sampling points in the test stage, is the interference amplitude of the jth sampling point.

[0124] The cosine similarity algorithm is used to calculate the feature similarity of real-time test data and dynamic interference judgment atlas, and the formula is:

[0125]

[0126] In the formula, S is the feature similarity (value range 0-1), M is the number of sampling points in the timing window, is the amplitude of the kth point of the real-time test data, is the amplitude of the kth point of the dynamic atlas.

[0127] When the actual interference mean value exceeds the dynamic tolerance range or the feature similarity is lower than the preset threshold, the electromagnetic compatibility state of the electrocardiograph is determined to be abnormal, and the abnormal type and the traceability result are output. The abnormal type includes interference intensity exceeding the standard and feature similarity mismatching, and the interference intensity exceeding the standard is further divided into upper limit exceeding and lower limit exceeding. The traceability result is based on the test environment parameters, device state parameters and interference type characteristics at the time of the abnormality, to analyze the cause of the abnormality, such as environmental electromagnetic field intensity being too high to cause radiation interference intensity exceeding the standard, power harmonic content exceeding the standard to cause conductive interference feature similarity mismatching, etc. The output result is in the form of a text report and a visual atlas mark, and the text report includes the time of the abnormality, the type of the abnormality, the value of the abnormality, the cause of the abnormality and the processing suggestion. The visual atlas uses red flashing marks to mark the abnormal area, which facilitates users to quickly locate and troubleshoot problems.

[0128] In summary, the embodiment provides an electrocardiograph electromagnetic compatibility test data diagnosis method based on intelligent sensors. By collecting multi-dimensional electromagnetic interference data through intelligent sensors, combining time domain-frequency domain conversion and core feature extraction technology, the method can effectively filter out environmental background noise, accurately distinguish the differentiated characteristics of different types of interference, and encapsulate the test data as structured objects, providing standardized data support for interference tracing and historical data comparison, greatly improving the accuracy of interference identification and the systematicness of data processing.

[0129] By introducing a dynamic reference threshold and a compensation mechanism, the environmental adaptability and diagnostic accuracy of the method are enhanced. By analyzing historical test data to construct a theoretical interference reference threshold, and combining dynamic factors such as device temperature drift, power fluctuation, and sensor noise to construct a compensation coefficient matrix, the interference judgment standard is adjusted in real time, effectively avoiding the limitations of fixed thresholds in complex environments, ensuring stable and reliable diagnostic results in different test scenarios.

[0130] By collecting test data in real time and calculating the actual interference mean value and feature similarity, the electromagnetic compatibility state of the device can be quickly determined. Once an anomaly is found, the type of anomaly and the tracing result can be output immediately, providing clear problem positioning directions for staff, greatly shortening the time for device debugging and interference suppression, and improving test and maintenance efficiency.

[0131] The application of the method helps to improve the safety and reliability of electrocardiograph in clinical use. By accurately identifying and warning electromagnetic interference risks, the influence of interference on device measurement data is reduced, the risk of misdiagnosis and missed diagnosis caused by data distortion is reduced, and strong protection is provided for accurate diagnosis of cardiovascular diseases. At the same time, it provides a new idea and technical support for the development of medical device electromagnetic compatibility test technology, and has wide application prospect and promotion value.

[0132] From the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be implemented by means of software and the necessary general hardware platform, or by hardware. Based on this understanding, the above technical solutions can be embodied in the form of a software product, which can be stored in a computer readable storage medium such as ROM / RAM, magnetic disk, optical disk, etc., and includes a plurality of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0133] It should be pointed out finally that the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit the same; and although the present application has been described in detail with reference to the foregoing embodiments, it should be appreciated by those skilled in the art that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features thereof can be replaced equivalently; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A smart sensor-based electrocardiograph electromagnetic compatibility test data diagnosis method, characterized in that, The application relates to a method for diagnosing the electromagnetic compatibility of an electrocardiograph. The method comprises the following steps: collecting equipment parameters, test environment parameters and multi-dimensional electromagnetic interference data collected by intelligent sensors in an electrocardiograph electromagnetic compatibility test scene, identifying interference type sequences in test data through interference source feature decoding, extracting feature identifiers of each interference type in combination with the equipment parameters, generating structured test data, collecting historical electromagnetic compatibility test data, extracting interference intensity distribution, equipment anti-interference response curves and interference timing characteristics in the historical data, calculating a theoretical interference reference threshold according to the interference intensity distribution and the equipment anti-interference response curves, setting a dynamic tolerance range, generating an initial interference judgment graph arranged according to interference timing in combination with the theoretical interference reference threshold, collecting equipment temperature drift data, power fluctuation parameters and sensor noise spectrum during the test, constructing a dynamic compensation coefficient matrix, injecting the dynamic compensation coefficient matrix into the initial interference judgment graph to obtain a dynamic interference judgment graph, collecting real-time electromagnetic compatibility test data sequences, comparing actual interference averages of each test stage, calculating feature similarity of real-time test data in each interference timing window and the dynamic interference judgment graph, and diagnosing the electromagnetic compatibility state of the electrocardiograph. The equipment parameters include electrocardiograph signal sampling rate, input impedance threshold value, filter circuit cutoff frequency, amplifier gain parameter and lead interface anti-interference level; the test environment parameters include environmental electromagnetic field intensity, temperature and humidity gradient, grounding resistance value and power supply harmonic content; the multi-dimensional electromagnetic interference data include conducted interference voltage data, radiation interference field intensity data, electrostatic discharge pulse data and surge impact response data; and the feature identifiers include interference frequency bandwidth, interference amplitude peak value, interference duration, pulse rising edge slope and spectral distortion coefficient. The process of identifying interference type sequences in test data through interference source feature decoding comprises the following steps: performing time domain-frequency domain conversion on collected electromagnetic interference original data to extract key spectral features; segmenting continuous interference sections based on the type and amplitude variation of the key spectral features to generate an initial interference sequence; extracting a core feature set of each interference type in the initial interference sequence, wherein the core feature set comprises an interference frequency range and an interference trigger condition; and filtering environmental background noise interference in the initial interference sequence according to the core feature set to obtain interference type sequences in the test data. The process of extracting feature identifiers of each interference type in combination with the equipment parameters to generate structured test data comprises the following steps: associating electrocardiograph filter circuit parameters according to the interference frequency range and the interference trigger condition to obtain an effective filter threshold value; calculating an interference attenuation amount in combination with the interference frequency range and the effective filter threshold value; associating an input impedance threshold value to deduce a maximum allowed interference amplitude value of the current interference type; associating a lead interface anti-interference level to calibrate an interference sensitivity coefficient; and packaging an interference type unique identifier, the core feature set and the interference attenuation amount into a structured data object to obtain structured test data. The process of extracting interference intensity distribution, equipment anti-interference response curves and interference timing characteristics in historical electromagnetic compatibility test data comprises the following steps: screening historical test records of the same type of electrocardiograph; 2. The smart sensor based ECG machine electromagnetic compatibility test data diagnostic method of claim 1, wherein, ​ 3. The smart sensor based ECG machine electromagnetic compatibility test data diagnostic method of claim 1, wherein, ​ ​ ​ ​ ​ 4. The smart sensor based ECG machine electromagnetic compatibility test data diagnostic method of claim 1, wherein, ​ ​ ​ ​ ​ ​ 5. The smart sensor based electrocardiograph electromagnetic compatibility test data diagnostic method of claim 1, wherein, ​ ​ Analyzing the interference attenuation amount in historical structured data objects, and counting the interference intensity probability distribution; Analyzing historical sensor data, and constructing a mapping model of interference intensity and device output distortion; Extracting the timestamp and interference type conversion relationship of historical interference sequences.

6. The smart sensor based electrocardiograph electromagnetic compatibility test data diagnostic method of claim 1, wherein, The process of calculating the theoretical interference reference threshold according to the interference intensity distribution and the device anti-interference response curve includes: Mapping the device anti-interference model according to the interference intensity distribution, and generating a basic interference reference value; Superimposing the device inherent noise reference value; Introducing an electromagnetic compatibility safety margin coefficient to generate a theoretical interference reference threshold.

7. The smart sensor based electrocardiograph electromagnetic compatibility test data diagnostic method of claim 1, wherein, The process of generating an initial interference judgment graph arranged according to the interference time sequence in combination with the theoretical interference reference threshold includes: Creating a time sequence-interference intensity two-dimensional coordinate system; Connecting the theoretical reference threshold according to the interference time sequence to form a reference curve; Setting a differential tolerance bandwidth according to the interference type characteristics; Visualizing the tolerance range boundary to form an initial interference judgment graph.

8. The smart sensor based electrocardiograph electromagnetic compatibility test data diagnostic method of claim 1, wherein, The process of constructing a dynamic compensation coefficient matrix includes: Calculating the noise energy entropy value according to the sensor noise spectrum to generate a noise compensation coefficient; Calculating the temperature compensation coefficient according to the device temperature drift data; Analyzing the power fluctuation parameters to calibrate the voltage stability coefficient; Integrating the noise compensation coefficient, temperature compensation coefficient, and voltage stability coefficient to obtain a dynamic compensation coefficient matrix.

9. The smart sensor based electrocardiograph electromagnetic compatibility test data diagnostic method of claim 1, wherein, The process of injecting the dynamic compensation coefficient matrix into the initial interference judgment graph to obtain a dynamic interference judgment graph includes: Adjusting the theoretical interference reference threshold of the initial graph according to the dynamic compensation coefficient matrix; Dynamically scaling the tolerance bandwidth according to the interference sensitivity coefficient; Superimposing the compensation factor value label layer on the initial interference judgment graph; Establishing a real-time data interface to update the dynamic compensation coefficient matrix according to the preset period.

10. The smart sensor based electrocardiograph electromagnetic compatibility test data diagnostic method of claim 1, wherein, The process of diagnosing the electromagnetic compatibility state of an electrocardiograph includes: Calculating the actual interference mean value of each test stage, and calculating the feature similarity between the real-time test data and the dynamic interference judgment graph using the cosine similarity algorithm; When the actual interference mean value exceeds the dynamic tolerance range or the feature similarity is lower than the preset threshold, it is determined that the electromagnetic compatibility state of the electrocardiograph is abnormal, and the abnormal type and traceability result are output.

Images