A medical instrument electromagnetic compatibility surge test real-time monitoring and judgment method and system

Abstract

The application discloses a kind of medical instrument electromagnetic compatibility surge test real-time monitoring and determination method and system, and the mapping of equipment characteristics-surge interference-reference parameter is established by machine learning model pretraining, the matching degree of test parameter and reference parameter is calculated in real time by combining jaccard similarity, the problems that traditional surge test relies on artificial analysis, cannot be determined in real time, and is difficult to adapt to different equipment models and different surge interference are solved.Multiple task loss function fuses physical, performance, software parameter optimization model, and improves the adaptability to different models of medical instrument;Abnormal value processing and missing value filling in data acquisition stage guarantee input data quality;Three-level compatibility grade division and visual image, light prompt, realize the intuitive display of determination result.The application realizes the real-time determination of medical instrument electromagnetic compatibility surge test result, and the result is accurate and reliable, meets the efficiency, precision requirement of medical instrument electromagnetic compatibility test.

Description

Technical Field

[0001] This invention relates to the field of medical device technology, and more specifically, to a real-time monitoring and judgment system for electromagnetic compatibility surge testing of medical devices. Background Technology

[0002] With the rapid development of medical technology, the stable operation of medical devices in electromagnetic environments has become crucial. Electromagnetic compatibility (EMC) surge testing is an important means of evaluating the performance stability of medical devices under electromagnetic interference such as lightning and switching transients. However, traditional surge testing systems typically only provide test data and cannot determine the test results in real time, which affects testing efficiency and accuracy to some extent. Therefore, developing a monitoring system capable of determining the EMC surge test results of medical devices in real time is of great significance.

[0003] Chinese invention patent CN112986739B discloses a fully automatic pneumatically controlled electromagnetic compatibility (EMC) auxiliary testing system and method. Its control device achieves various simulated switches by controlling the timing and frequency of air pressure pulses. However, this technical solution does not perform real-time detection and analysis of the equipment's parameters over a continuous period, lacking continuity in EMC testing, and it does not classify the EMC levels of the tested equipment. Summary of the Invention

[0004] The present invention aims to overcome the shortcomings of the prior art and provide a method and system for real-time monitoring and judgment of electromagnetic compatibility surge tests for medical devices. This method and system can adapt to different equipment models and different surge interferences, and provide real-time judgment results, thereby improving the accuracy and efficiency of electromagnetic compatibility surge tests for medical devices.

[0005] The technical solution adopted by this invention is to provide a method for real-time monitoring and judgment of electromagnetic compatibility surge tests of medical devices, characterized by the following steps: S1. Modeling and pre-training: The machine learning model is constructed by calling the set of equipment feature parameters, surge interference and reference electrical parameters of the equipment under the corresponding operating conditions from the normal operation database of the equipment. The machine learning model is trained using a multi-task loss function to establish a mapping between the set of equipment feature parameters, surge interference and reference electrical parameters. S2. Real-time data acquisition: During the monitoring period, the voltage and current of the device under test under surge interference are collected synchronously to obtain the set of test electrical parameters. S3. Reference parameter generation: Input the device model and surge interference of the device under test into the machine learning model, and output a set of reference electrical parameters through the mapping. S4. Similarity Calculation: The similarity between the test electrical parameter set and the reference electrical parameter set is calculated using Jaccard similarity. S5. Based on the comparison between the similarity and the preset threshold, determine the electromagnetic compatibility level of the device under test.

[0006] The above solution establishes a mapping between equipment features, surge interference, and reference parameters through a machine learning model, enabling electromagnetic compatibility surge testing to adapt to multiple equipment models and different surge conditions. Combined with Jaccard similarity calculation, it can determine the compatibility level in real time. The combination of the two solves the problem that traditional testing cannot determine the compatibility level in real time, significantly improving testing efficiency and result reliability.

[0007] Further, in step S1, the device feature parameter set includes a physical parameter set, a performance parameter set, and a software parameter set; the multi-task loss function includes a physical parameter loss function, a performance parameter loss function, and a software parameter loss function, and its calculation expression is: ; in, This represents the loss value obtained by calculating the loss function. Represents the physical parameter loss function The weighting coefficients, where This represents the total number of samples in the training set. This represents the total number of categories of physical parameters. Indicates the first The sample belongs to the first The true label of the category for each parameter, with a value of , Represents the logarithmic function. This indicates that the machine learning model predicts the first... The sample belongs to the first The probability of each state category; Represents the performance parameter loss function The weighting coefficients, where Indicates the first The true value of each performance parameter Indicates the first Predicted values ​​for each performance parameter; Represents the software parameter loss function The weighting coefficients, where Indicates the first The true values ​​of the software parameters for each sample. Indicates the first The predicted values ​​of software parameters for each sample, where, .

[0008] Furthermore, in step S1, the physical parameters include size, weight, material, and appearance; the performance parameters include accuracy, repeatability, resolution, range, and response time; and the software parameters include system requirements, algorithm performance, and network security.

[0009] Furthermore, the machine learning model undergoes testing and training until the accuracy reaches a first accuracy threshold, at which point the training stops. The training direction is controlled by weight coefficients (α, β, γ), such as prioritizing the optimization of performance parameters that significantly impact compatibility, accelerating model convergence to the first accuracy threshold, avoiding the long training time of complex models, and facilitating real-time decision-making.

[0010] In existing technologies, machine learning models for electromagnetic compatibility (EMC) testing often employ a single loss function (such as using only MSE to predict parameter values) or fail to consider the classification characteristics of physical parameters (such as whether the equipment is in normal condition), resulting in inaccurate reference parameter predictions and poor real-time performance. The loss function of this invention achieves "classification-regression" collaborative optimization through multi-task fusion, significantly improving the reliability of reference parameters and providing core support for real-time judgment.

[0011] Further, in step S4, the expression for calculating the similarity is: In this algorithm, XS represents the similarity, A represents the set of experimental electrical parameters, B represents the set of reference electrical parameters, |A∩B∣| represents the number of elements in the intersection of the two sets, and |A∪B∣| represents the number of elements in the union of the two sets. The Jaccard similarity algorithm is naturally suitable for calculating the similarity between sets, directly reflecting the degree of overlap between two parameter sets. In this scenario, it corresponds to the matching degree between the experimental electrical parameter set and the reference electrical parameter set, perfectly aligning with the core logic of electromagnetic compatibility evaluation. Furthermore, this algorithm only needs to count the number of elements in the intersection and union of the sets, with a time complexity of O(n) (where n is the number of elements in the set), far lower than the O(n) time complexity of neural networks. 2 Complexity of 1000 or higher meets the low latency requirement for real-time decision-making.

[0012] Furthermore, in step S5, the comparison image is plotted with monitoring time on the horizontal axis and current and voltage parameter values ​​on the vertical axes, using different colors to draw the test electrical parameter curve and the reference electrical parameter curve, respectively. This dual-track comparison image, plotted with time on the horizontal axis and electrical parameters on the vertical axis, visually presents the dynamic differences between the test parameters and the reference parameters, facilitating technicians to quickly locate abnormal fluctuations.

[0013] Another objective of this invention is to provide a real-time monitoring and judgment system that applies the above-mentioned method, including a surge generation module, a data acquisition module, a real-time judgment module, and a result display module; The surge generation module is used to generate surge interference and generate surge signals, which are then transmitted to the real-time determination module. The data acquisition module is used to acquire the voltage and current of the device under test under the surge interference in real time, generate a set of test electrical parameters after preprocessing, and draw an electrical parameter image. The set of test electrical parameters is transmitted to the real-time judgment module, and the electrical parameter image is transmitted to the result display module. The real-time judgment module is equipped with a machine learning model, which generates a reference electrical parameter set based on the equipment feature parameter set of the device under test and surge interference, calculates the similarity between the test electrical parameter set and the reference electrical parameter set, generates an electromagnetic compatibility evaluation based on the similarity, and transmits it to the result display module. The results display module is used to display the electromagnetic compatibility evaluation and electrical parameter images.

[0014] Furthermore, the data acquisition module includes an acquisition unit and a processing unit; the acquisition unit acquires the current and voltage parameters of the device under test under the action of the surge signal based on the sensor device, and transmits the parameters to the processing unit; the processing unit performs abnormal data removal processing and missing value filling processing on the current and the voltage respectively, and generates a set of test electrical parameters.

[0015] Furthermore, the real-time determination module is configured with an electromagnetic compatibility (EMC) analysis strategy, which includes: obtaining a similarity score; comparing the similarity score with a first similarity threshold and a second similarity threshold to obtain an EMC evaluation; when the similarity score is less than the first similarity threshold, the EMC evaluation is a first compatibility level; when the similarity score is greater than or equal to the first similarity threshold and less than the second similarity threshold, the EMC evaluation is a second compatibility level; and when the similarity score is greater than or equal to the second similarity threshold, the EMC evaluation is a third compatibility level.

[0016] Furthermore, the result display module is configured with an electromagnetic compatibility (EMC) display strategy. This strategy includes: when the EMC evaluation is at a first compatibility level, the display unit emits a red light at a first brightness threshold; when the EMC evaluation is at a second compatibility level, the display unit emits a yellow light at a second brightness threshold; and when the EMC evaluation is at a third compatibility level, the display unit emits a green light at a third brightness threshold. This three-color light display provides intuitive feedback on the judgment result, allowing for rapid identification of equipment compliance without complex readings, thus improving on-site testing efficiency.

[0017] Another objective of this invention is to provide a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the above-described method for real-time monitoring and determination of electromagnetic compatibility surge tests for medical devices.

[0018] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention provides a real-time monitoring and judgment method and system for electromagnetic compatibility surge testing of medical devices. It establishes a mapping between device features, surge interference, and reference parameters through pre-training a machine learning model, and calculates the matching degree between test parameters and reference parameters in real time using Jaccard similarity. This solves the problems of traditional surge testing relying on manual analysis, inability to make real-time judgments, and difficulty in adapting to different device models and surge interferences. A multi-task loss function integrates physical, performance, and software parameter optimization models to improve adaptability to different medical device models; outlier handling and missing value imputation during data acquisition ensure input data quality; and a three-level compatibility classification with visual images and light prompts provides an intuitive display of judgment results. Full-process automation significantly improves testing efficiency, and pre-set judgment criteria and algorithm models ensure accurate and reliable results, meeting the high efficiency and accuracy requirements of electromagnetic compatibility testing for medical devices. Attached Figure Description

[0019] Figure 1 This invention provides a basic flowchart of a real-time monitoring and judgment system for electromagnetic compatibility surge testing of medical devices. Detailed Implementation

[0020] The present invention will now be further illustrated with specific examples. The following embodiments are merely illustrative and do not constitute a limitation thereof. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.

[0021] Example 1 This embodiment provides a real-time monitoring and judgment system for electromagnetic compatibility surge testing of medical devices, including a surge generation module, a data acquisition module, a real-time judgment module, and a result display module; The surge generation module is used to generate electromagnetic interference, including lightning electromagnetic interference and switching transient electromagnetic interference, to generate surge signals. The surge signals are transmitted to the real-time judgment module, and electromagnetic compatibility surge tests are performed on the device under test based on the surge signals. The data acquisition module is used to collect the voltage and current of the device under test under the surge interference in real time, generate a set of test electrical parameters after preprocessing, and draw an electrical parameter image. The set of test electrical parameters is transmitted to the real-time judgment module, and the electrical parameter image is transmitted to the result display module. The real-time judgment module is equipped with a machine learning model, which generates a reference electrical parameter set based on the equipment feature parameter set of the device under test and surge interference, calculates the similarity between the test electrical parameter set and the reference electrical parameter set, generates an electromagnetic compatibility evaluation based on the similarity, and transmits it to the result display module. The results display module is used to display the electromagnetic compatibility evaluation and electrical parameter images.

[0022] This solution simulates interference signals targeting medical devices through a surge generation module, and monitors and analyzes the current and voltage parameters of the medical devices in real time during the monitoring period. This achieves continuous monitoring, improves the accuracy of the test, and enables real-time determination of the electromagnetic compatibility surge test results of medical devices, thus improving testing efficiency. By pre-building a machine learning model, it obtains the reference electrical parameters corresponding to the type of device under test and the type of surge interference, and calculates the similarity between the real-time monitored device parameters and the reference electrical parameters to determine the electromagnetic compatibility performance of the device. Through preset judgment criteria and advanced algorithms, the accuracy and reliability of the judgment results are ensured. The result display module presents the judgment results in an intuitive form, facilitating user analysis and judgment, and improving the clarity and intuitiveness of data display.

[0023] The surge generation module is configured with a surge signal control strategy, which includes: Receive a first trigger condition, identify the first trigger condition, obtain a first identification result, and generate corresponding data information based on the first identification result; Receive the second trigger condition, identify the second trigger condition, obtain the second identification result, and stop generating data information based on the second identification result; The first trigger condition and the second trigger condition include a button click signal and a touch screen signal, respectively.

[0024] In practice, the surge generation module is equipped with a surge generator to simulate electromagnetic interference phenomena such as lightning strikes and switching transients, generating surge signals to perform electromagnetic compatibility surge tests on the device under test. First, a suitable surge generator is selected according to actual needs and connected to the medical device under test via a connecting cable. Then, the surge generator is turned on to perform electromagnetic compatibility surge tests on the medical device under test.

[0025] The data acquisition module includes an acquisition unit and a processing unit; The acquisition unit collects parameters of the device under test under surge signal based on sensor devices, and transmits the parameters of the device under test under surge signal to the processing unit. The parameters include current and voltage. The processing unit performs abnormal data removal and missing value filling for current and voltage respectively, generating a set of test electrical parameters.

[0026] In practice, the data acquisition module is used to collect the electrical parameters of the device under test in real time under the action of surge signals. The electrical parameters include voltage and current.

[0027] The real-time decision-making module includes a machine learning model unit, a computation unit, and an analysis unit; The machine learning model unit constructs a machine learning model for feeding back reference electrical parameters. The machine learning model uses the set of equipment feature parameters from the equipment normal operation database, surge interference, and the set of reference electrical parameters of the equipment under corresponding operating conditions as a sample set for testing and training until the accuracy reaches the first accuracy threshold. The machine learning model uses the equipment model and surge interference of the device under test as inputs and the reference electrical parameters as outputs, and transmits the reference electrical parameters to the computing unit. The calculation unit receives reference electrical parameters and test electrical parameters within the monitoring period, generates a set of reference electrical parameters and a set of test electrical parameters, calculates the similarity between the set of reference electrical parameters and the set of test electrical parameters, and transmits the similarity between the set of reference electrical parameters and the set of test electrical parameters to the analysis unit. The analysis unit compares the similarity with a first similarity threshold and a second similarity threshold to obtain an electromagnetic compatibility evaluation, and then transmits the electromagnetic compatibility evaluation to the result display module.

[0028] The real-time judgment module is configured with a model building strategy. The model building strategy includes: calling the device normal operation database, obtaining historical parameters and the surge signal features corresponding to the historical parameters, and using the historical parameters and the surge signal features corresponding to the historical parameters as a sample set. The sample set is divided into a training set and a test set according to a certain ratio. A machine learning model is constructed. The machine learning model takes the experimental electrical parameters and the training set as input and the reference electrical parameters as output. The machine learning model is trained using the training set and the loss function to obtain the reference electrical parameters. The test electrical parameters include physical parameters, performance parameters, and software parameters; Training a machine learning model includes: The loss function includes the physical parameter loss function, the performance parameter loss function, and the software parameter loss function. The calculation expression of the loss function is as follows: ; in, This represents the loss value obtained by calculating the loss function. Represents the physical parameter loss function The weighting coefficients, where This represents the total number of samples in the training set. This represents the total number of categories of physical parameters. Indicates the first The sample belongs to the first The true label of the category for each parameter, with a value of , Represents the logarithmic function. This indicates that the machine learning model predicts the first... The sample belongs to the first The probability of each state category; Represents the performance parameter loss function The weighting coefficients, where Indicates the first The true value of each performance parameter Indicates the first Predicted values ​​for each performance parameter; Represents the software parameter loss function The weighting coefficients, where Indicates the first The true values ​​of the software parameters for each sample. Indicates the first The predicted values ​​of software parameters for each sample, where, .

[0029] The physical parameters include size, weight, material, and appearance; the material refers to the material that comes into contact with the human body or constitutes a key component (such as medical stainless steel, titanium alloy, silicone, special plastics, biodegradable materials, etc.), and biocompatibility must be considered; the appearance categories include three conditions: sterile, pyrogen-free, and free of visible foreign matter.

[0030] The performance parameters include accuracy, repeatability, resolution, range, and response time.

[0031] The software parameters include system requirements, algorithm performance, and network security; where system requirements refer to the hardware configuration and operating system required for operation; algorithm performance, for diagnostic AI, requires sensitivity, specificity, accuracy, and AUC; and network security refers to data encryption information, user access control information, and information to prevent unauthorized access.

[0032] By continuously optimizing and improving the machine learning model using the training set and loss function, the machine learning model can adapt to different situations of different medical devices, providing strong support for obtaining more accurate reference electrical parameters for the machine learning model.

[0033] The computing unit is configured with a similarity calculation strategy, which includes: Obtain reference electrical parameters and experimental electrical parameters for the first monitoring time period to generate a reference electrical parameter set and an experimental electrical parameter set; calculate the similarity between the reference electrical parameter set and the experimental electrical parameter set based on the Jaccard coefficient algorithm, wherein the similarity calculation expression is XS=1. ∣A∩B∣ / ∣A∪B∣, where XS represents the similarity, A represents the set of experimental electrical parameters, B represents the set of reference electrical parameters, ∣A∩B∣ is the number of elements in the intersection of the two sets, and ∣A∪B∣ is the number of elements in the union of the two sets.

[0034] Jaccard similarity calculation is based directly on the overlap ratio of set elements, eliminating the need for parameter vectorization and reducing real-time computation latency.

[0035] The analysis unit is configured with an electromagnetic compatibility (EMC) analysis strategy, which includes: The similarity score is obtained and compared with a first similarity threshold and a second similarity threshold to obtain an electromagnetic compatibility (EMC) evaluation. When the similarity score is less than the first similarity threshold, the EMC evaluation is at the first compatibility level. When the similarity score is greater than or equal to the first similarity threshold and less than the second similarity threshold, the EMC evaluation is at the second compatibility level. When the similarity score is greater than or equal to the second similarity threshold, the EMC evaluation is at the third compatibility level.

[0036] In practical implementation, the real-time judgment module is the core of this invention. Based on preset judgment criteria, it processes and analyzes the parameters collected by the data acquisition module in real time to determine whether the device under test meets electromagnetic compatibility requirements. The real-time judgment module employs a machine learning model. By training on a large amount of data, the machine learning model improves the accuracy and efficiency of the judgment. The first compatibility level represents incompatibility, the second compatibility level represents partial compatibility, and the third compatibility level represents compatibility.

[0037] The results display module includes an image drawing unit and a display unit; The image drawing unit is used to draw current comparison images and voltage comparison images. The current comparison images and voltage comparison images include the graphs corresponding to the test electrical parameters and the graphs corresponding to the reference electrical parameters, respectively. The graphs corresponding to the test electrical parameters and the graphs corresponding to the reference electrical parameters are represented by different colors, and the current comparison images and voltage comparison images are transmitted to the display unit. The display unit is used to display electromagnetic compatibility evaluation, current comparison images, and voltage comparison images.

[0038] In practice, the results display module will present the real-time judgment results to the user in an intuitive form, making it easy for the user to understand the electromagnetic compatibility performance of the medical device under test.

[0039] The advantages of the monitoring system for real-time determination of electromagnetic compatibility surge test results of medical devices of the present invention include: it can determine the electromagnetic compatibility surge test results of medical devices in real time, which greatly improves the testing efficiency; through preset determination criteria and advanced algorithms, it ensures the accuracy and reliability of the determination results; and the result display module displays the determination results in an intuitive form, which is convenient for users to analyze and judge the results.

[0040] The monitoring system for real-time determination of electromagnetic compatibility surge test results for medical devices of the present invention, by introducing a real-time determination module, realizes real-time determination of the electromagnetic compatibility surge test results of medical devices, thereby improving testing efficiency. Simultaneously, through preset determination criteria and advanced algorithms, the accuracy and reliability of the determination results are improved. Furthermore, the introduction of a result display module makes the determination results more intuitive, facilitating user analysis and judgment. Therefore, the present invention has broad application prospects and significant practical value in the field of electromagnetic compatibility technology for medical devices.

[0041] The real-time judgment module is used to process and analyze the voltage and current parameters collected by the data acquisition module in real time according to the preset judgment criteria, and to determine whether the medical device under test meets the electromagnetic compatibility requirements. The results display module is used to visualize the real-time judgment results in the form of charts, curves, etc.

[0042] The above are merely preferred embodiments of the present invention and are not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0043] It should be recognized that embodiments of the present invention can be implemented or carried out by a combination of computer hardware and software, or by computer instructions stored in a non-transitory computer-readable storage medium. The method can be implemented using standard programming techniques—including a non-transitory computer-readable storage medium configured with a computer program, wherein such a storage medium causes the computer to operate in a specific and predefined manner—according to the methods and drawings described in the specific embodiments. Each program can be implemented in a high-level procedural or object-oriented programming language to communicate with the computer system. However, if desired, the program can be implemented in assembly or machine language. In any case, the language can be a compiled or interpreted language. Furthermore, for this purpose, the program can run on a programmed application-specific integrated circuit (ASIC).

[0044] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for real-time monitoring and judgment of electromagnetic compatibility surge testing of medical devices, characterized in that, Includes the following steps: S1. Modeling and pre-training: The machine learning model is constructed by calling the set of equipment feature parameters, surge interference and reference electrical parameters of the equipment under the corresponding operating conditions from the normal operation database of the equipment. The machine learning model is trained using a multi-task loss function to establish a mapping between the set of equipment feature parameters, surge interference and reference electrical parameters. S2. Real-time data acquisition: During the monitoring period, the voltage and current of the device under test under surge interference are collected synchronously to obtain the set of test electrical parameters. S3. Reference parameter generation: Input the device model and surge interference of the device under test into the machine learning model, and output a set of reference electrical parameters through the mapping. S4. Similarity Calculation: The similarity between the test electrical parameter set and the reference electrical parameter set is calculated using Jaccard similarity. S5. Judgment result: Based on the comparison between the similarity and the preset threshold, the electromagnetic compatibility level of the device under test is determined, and a comparison image is generated.

2. The method according to claim 1, characterized in that, In step S1, the device feature parameter set includes a physical parameter set, a performance parameter set, and a software parameter set; the multi-task loss function includes a physical parameter loss function, a performance parameter loss function, and a software parameter loss function, and its calculation expression is: ； in, This represents the loss value obtained by calculating the loss function. Represents the physical parameter loss function The weighting coefficients, where This represents the total number of samples in the training set. This represents the total number of categories of physical parameters. Indicates the first The sample belongs to the first The true label of the category for each parameter, with a value of , Represents the logarithmic function. This indicates that the machine learning model predicts the first... The sample belongs to the first The probability of each state category; Represents the performance parameter loss function The weighting coefficients, where Indicates the first The true value of each performance parameter Indicates the first Predicted values ​​for each performance parameter; Represents the software parameter loss function The weighting coefficients, where Indicates the first The true values ​​of the software parameters for each sample. Indicates the first The predicted values ​​of software parameters for each sample, where, .

3. The method according to claim 1, characterized in that, In step S1, the set of physical parameters includes size, weight, material, and appearance; the set of performance parameters includes accuracy, repeatability, resolution, range, and response time.

4. The method according to claim 1, characterized in that, In step S4, the expression for calculating the similarity is: Where XS represents similarity, A represents the set of experimental electrical parameters, B represents the set of reference electrical parameters, |A∩B∣ is the number of elements in the intersection of the two sets, and |A∪B∣ is the number of elements in the union of the two sets.

5. The method according to claim 1, characterized in that, In step S5, the comparison images are plotted with monitoring time on the horizontal axis and current and voltage parameter values ​​on the vertical axis, and the test electrical parameter graph and the reference electrical parameter graph are plotted in different colors respectively.

6. A real-time monitoring and judgment system applying the method according to any one of claims 1 to 5, characterized in that, It includes a surge generation module, a data acquisition module, a real-time judgment module, and a result display module; The surge generation module is used to generate surge interference and generate surge signals, which are then transmitted to the real-time determination module. The data acquisition module is used to acquire the voltage and current of the device under test under the surge interference in real time, generate a set of test electrical parameters after preprocessing, and draw an electrical parameter image. The set of test electrical parameters is transmitted to the real-time judgment module, and the electrical parameter image is transmitted to the result display module. The real-time judgment module is equipped with a machine learning model, which generates a reference electrical parameter set based on the equipment feature parameter set of the device under test and surge interference, calculates the similarity between the test electrical parameter set and the reference electrical parameter set, generates an electromagnetic compatibility evaluation based on the similarity, and transmits it to the result display module. The results display module is used to display the electromagnetic compatibility evaluation and electrical parameter images.

7. The system according to claim 6, characterized in that, The data acquisition module includes an acquisition unit and a processing unit; the acquisition unit acquires the current and voltage parameters of the device under test under the action of the surge signal based on the sensor device, and transmits the parameters to the processing unit; the processing unit performs abnormal data removal processing and missing value filling processing on the current and the voltage respectively, and generates a set of test electrical parameters.

8. The system according to claim 6, characterized in that, The real-time determination module is configured with an electromagnetic compatibility (EMC) analysis strategy, which includes: obtaining a similarity score; comparing the similarity score with a first similarity threshold and a second similarity threshold to obtain an EMC evaluation; when the similarity score is less than the first similarity threshold, the EMC evaluation is a first compatibility level; when the similarity score is greater than or equal to the first similarity threshold and less than the second similarity threshold, the EMC evaluation is a second compatibility level; and when the similarity score is greater than or equal to the second similarity threshold, the EMC evaluation is a third compatibility level.

9. The system according to claim 6, characterized in that, The result display module is configured with an electromagnetic compatibility (EMC) display strategy, which includes: when the EMC evaluation is at the first compatibility level, the display unit emits a red light at the first brightness threshold; when the EMC evaluation is at the second compatibility level, the display unit emits a yellow light at the second brightness threshold; and when the EMC evaluation is at the third compatibility level, the display unit emits a green light at the third brightness threshold.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the real-time monitoring and judgment method for electromagnetic compatibility surge testing of medical devices as described in any one of claims 1 to 5.

Images