Fault diagnosis system for arterial blood pressure monitor

Abstract

The invention relates to the technical field of medical instruments, in particular to an arterial blood pressure monitor fault diagnosis system which comprises a dynamic monitoring module, a data acquisition module, a data analysis module, an evaluation module and an optimization module. The dynamic monitoring module is used for monitoring the running state of the arterial blood pressure monitor in real time; the data acquisition module is used for acquiring various parameter information of the arterial blood pressure monitor and uploading data to a cloud end or a remote server through a wireless communication technology; the data analysis module is used for calculating a monitor state deviation degree Yv, a complex scene influence coefficient Fz and a fault early warning index Sj according to various acquired parameter information of the arterial blood pressure monitor; the evaluation module is used for evaluating the running state of the monitor according to the fault early warning index Sj and performing early warning grading according to an evaluation result; the method is used for automatically adjusting and optimizing system parameters according to the evaluation result. The system has the advantages of high-precision data processing, multi-mode intelligent diagnosis and strong data security protection.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical devices, and particularly relates to an arterial blood pressure monitor fault diagnosis system. BACKGROUND

[0002] With the development of medical informatization and intelligent technology, various types of monitoring devices for vital sign collection have gradually been popularized in clinical and family medical scenarios. Among them, the arterial blood pressure monitor has become one of the key devices in modern medical diagnosis and treatment due to its real-time reflection capability on the health status of the circulatory system. In order to ensure the continuity and reliability of the device operation, the matching fault diagnosis system is widely used for monitoring the operating state and fault identification of the monitor, so as to assist medical staff to timely find system abnormalities and prevent risks caused by measurement errors or device damage.

[0003] The existing arterial blood pressure monitor fault diagnosis system still faces problems in actual application. On the one hand, at the data processing level, the diagnosis system needs to perform preprocessing operations such as denoising, filtering, feature extraction, etc. on the arterial blood pressure signal, but the existing technology has limited suppression effect on high-frequency noise and artifact interference in the signal, and the processing precision is difficult to meet the requirements of high-reliability fault identification. On the other hand, in terms of fault identification algorithm, the traditional diagnosis method is mostly based on fixed models or rule bases for reasoning, which is difficult to adapt to diversified fault types and dynamically changing patient states, and there is a risk of fault missed detection and false detection under complex or extreme working conditions. In addition, with the improvement of device networking degree, the monitoring data is exposed to the external network environment during transmission and storage, and if there is no effective security protection mechanism, it is easy to be subjected to illegal access or malicious tampering, thereby affecting the timeliness and reliability of the fault identification function.

[0004] To sum up, how to solve the problems of low data processing precision, poor fault diagnosis accuracy, traditional algorithm difficult to cope with complex fault scenarios, and security risks in data transmission and storage affecting real-time monitoring in the existing arterial blood pressure monitor fault diagnosis system is the current difficult problem. SUMMARY

[0005] The present application provides an arterial blood pressure monitor fault diagnosis system, which has the advantages of high-precision data processing, multi-mode intelligent diagnosis, and strong data security protection. The present application provides the following technical solutions:

[0006] In a first aspect, the present application provides an arterial blood pressure monitor fault diagnosis system, which comprises a dynamic monitoring module, a data acquisition module, a data analysis module, an evaluation module, and an optimization module.

[0007] The dynamic monitoring module is used for real-time monitoring of the operating state of the arterial blood pressure monitor.

[0008] The data acquisition module is configured to acquire various types of parameter information of the arterial blood pressure monitor monitored during the operation of the dynamic monitoring module, and upload the data to the cloud or a remote server through wireless communication technology.

[0009] The data analysis module is configured to calculate the monitor state deviation degree Yv, the complex scene influence coefficient Fz, and the fault early warning index Sj according to the acquired various types of parameter information of the arterial blood pressure monitor.

[0010] The evaluation module is configured to evaluate the running state of the monitor according to the fault early warning index Sj, and perform early warning grading according to the evaluation result.

[0011] The system parameters are automatically adjusted and optimized according to the evaluation result.

[0012] In a specific implementation scheme, the data acquisition module comprises a data secure transmission unit configured to protect the acquired data through an encryption algorithm, and the encryption algorithm formula in the data secure transmission unit is as follows:

[0013]

[0014] In the formula, E represents the encrypted data, E0 represents the original data, K represents the encryption key, and C0 represents the initialization vector.

[0015] In a specific implementation scheme, the data acquisition module comprises a physiological signal acquisition unit configured to acquire physiological signal data, and divide the physiological signal data into systolic pressure signals, diastolic pressure signals, pulse wave feature signals, and heart rate signals according to the signal types.

[0016] In a specific implementation scheme, the data acquisition module comprises a monitor state parameter acquisition unit configured to acquire monitor state parameters, and divide the monitor state parameters into power supply state parameters, sensor working state parameters, air path sealing property parameters, and communication state parameters according to the parameter properties.

[0017] In a specific implementation scheme, the data acquisition module comprises a complex scene interference data acquisition unit configured to acquire complex scene interference data, and divide the complex scene interference data into motion-related interference data, environmental temperature and humidity interference data, electromagnetic interference data, and device aging interference data according to the interference sources.

[0018] In a specific implementation scheme, the data analysis module comprises a complex scene weakening unit configured to calculate the complex scene influence coefficient Fz according to the complex scene interference data, and the calculation formula is as follows:

[0019]

[0020] In the formula, Fz represents the complex scene influence coefficient, R i represents the real-time measurement value of the i-th complex scene interference parameter, represents the reference value of the i-th complex scene interference parameter, represents the historical standard deviation of the i-th complex scene interference parameter, γ i represents the weighted interference deviation degree of the i-th complex scene interference parameter, and n represents the total number of interference parameters.

[0021] In a specific implementable embodiment, the data analysis module comprises a monitor state interference exclusion unit configured to calculate a monitor state deviation degree Yv according to monitor state parameters, and the calculation formula is as follows:

[0022]

[0023] In the formula, Yv represents the monitor state deviation degree, W k represents the k-th measured parameter of the monitor state, represents the k-th reference parameter of the monitor state, a k represents the corresponding weight coefficient of the k-th state parameter of the monitor, and m represents the number of different states of the monitor.

[0024] In a specific implementable embodiment, the data analysis module comprises a fault data judgment unit configured to calculate a fault warning index Sj according to the monitor state deviation degree Yv, the complex scene influence coefficient Fz, and the physiological signal data, and the calculation formula is as follows:

[0025]

[0026] In the formula, Sj represents the fault warning index, Yv represents the monitor state deviation degree, Fz represents the complex scene influence coefficient, H represents the real-time physiological signal vector, H0 represents the physiological health baseline vector, ε represents the physiological signal normalization coefficient, α, β, μ, and α respectively represent the corresponding weight coefficients of the physiological signal data, the monitor state parameters, and the complex scene interference data, and λ represents the system automatic calibration offset.

[0027] In a specific implementable embodiment, in the evaluation module, when the fault warning index Sj is <0.3, no intervention measure is needed to maintain regular monitoring, it is judged that the physiological signal, the monitor state, and the environmental interference are all within the safe range, and it is indicated that the current running state is normal.

[0028] When the fault early warning index Sj is in the range of 0.3-0.7, it indicates that there is a potential risk at present, and a third-level early warning needs to be triggered, the parameter calibration program is automatically started, and the user is prompted to check the equipment connection state, it is judged that the monitoring data deviates from the reference value but does not reach the fault threshold, and the risk needs to be eliminated through calibration or user intervention, and the risk is reduced through automatic calibration and user prompt;

[0029] When the fault early warning index Sj>0.7, it indicates that a serious fault occurs at present, and a first-level early warning needs to be triggered, the blood pressure measurement is immediately stopped, the device function is locked, and the medical staff is prompted to repair through sound and light alarm and remote notification, it is judged that multiple parameters are abnormal and exceed the safety boundary, and emergency shutdown is needed to avoid misdiagnosis or device damage, the measurement is forcibly stopped and the device operation is limited, and local alarm and remote push are performed.

[0030] In a specific implementable scheme, in the optimization module, the threshold range is dynamically adjusted, and the threshold range can be dynamically adjusted according to the device model, the use scene or the user physical sign.

[0031] In summary, the beneficial effects of the present application at least include:

[0032] (1) By introducing a multi-dimensional data acquisition mechanism, the system can comprehensively cover physiological signals, monitor state parameters and complex scene interference data, and further realize high-precision data modeling and fault recognition basis. Specifically, the system sets a physiological signal acquisition unit, a monitor state parameter acquisition unit and a complex scene interference data acquisition unit to acquire blood pressure related physiological information, monitor running state and external interference factors. Various types of collected data are subdivided into multiple dimensions in structure, such as dividing physiological signals into systolic pressure, diastolic pressure, heart rate, etc.; dividing device state into sensor, power supply, airway, etc.; and introducing motion, electromagnetic, temperature and humidity, etc. Environmental parameters, a comprehensive and clear data acquisition system is constructed. This mechanism effectively improves the comprehensive perception ability of the diagnosis system to the device running state, and lays a data foundation for high reliability diagnosis in complex scenes.

[0033] (2) By constructing a multi-index fused fault early warning index Sj, the system realizes dynamic quantitative evaluation of equipment failure, and significantly improves the accuracy and robustness of fault identification. The system uses mathematical modeling method, combines the state deviation of the monitor, the influence coefficient of complex scene and real-time physiological signal, and constructs the early warning index calculation model with sensitivity and discrimination by comprehensively considering the weighted influence of various factors. In this model, the system not only considers the stability of the internal running state of the equipment, but also fully identifies the potential interference of the complex environment on the measurement data, and enhances the adaptability of the model by introducing individual difference compensation term (such as calibration offset λ). Therefore, even under complex conditions such as motion interference, extreme temperature and humidity, power fluctuation, etc., the system can still maintain high accuracy in identifying real faults, reducing the risk of false positives and false negatives.

[0034] (3) By setting up a closed-loop control mechanism composed of evaluation module and optimization module, the system realizes dynamic grading response of fault level and intelligent adaptive adjustment of parameters, thereby greatly improving the safety and stability of system operation. The evaluation module sets multiple thresholds according to the early warning index Sj, realizes the fine judgment of three levels of normal, potential risk and serious failure, and responds to potential risks in time through automatically triggered calibration program or shutdown measures. At the same time, the optimization module dynamically adjusts system parameters, thresholds or prompt mechanism according to the evaluation results, taking into account different equipment types, application scenarios and user characteristics, to realize customized configuration and continuous enhancement of fault prevention and control capability. This closed-loop design not only improves the risk prevention and control capability during equipment use, but also effectively reduces manual intervention, improves the real-time response of fault and the self-repairing ability of the system as a whole.

[0035] By establishing dynamic monitoring module, data acquisition module, data analysis module, evaluation module and optimization module, the modules cooperate with each other to realize the whole process closed-loop management from real-time data acquisition, safe transmission, accurate analysis to intelligent evaluation and dynamic optimization, finally effectively improving the timeliness and accuracy of system fault diagnosis, so as to ensure the stable operation of intelligent arterial blood pressure monitor in complex environment. Specifically, the fault data judgment unit calculates the fault early warning index Sj according to the monitor state deviation Yv, the complex scene influence coefficient Fz and the physiological signal data, which is used as the quantitative standard to judge whether the monitor is in normal operation state after excluding the influence of environmental interference and abnormal state of the equipment itself. The above measures can actively intervene before potential failure occurs, effectively avoid failure escalation and ensure the effectiveness of monitoring data.

[0036] The above description is only a summary of the technical scheme of the present application. In order to more clearly understand the technical means of the present application, and to implement the content of the description, the following will describe the preferred embodiments of the present application in detail with the help of the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0037] Figure 1 is a flowchart of the arterial blood pressure monitor fault diagnosis method in the embodiment of the present application. DETAILED DESCRIPTION

[0038] The specific embodiments of the present application will be further described in detail below in conjunction with the drawings and examples. The following examples are used to illustrate the present application, but not to limit the scope of the present application.

[0039] Referring to Figure 1 is a structural block diagram of the arterial blood pressure monitor fault diagnosis system provided by an embodiment of the present application, and the system includes a dynamic monitoring module, a data acquisition module, a data analysis module, an evaluation module and an optimization module.

[0040] The dynamic monitoring module is used to monitor the running state of the arterial blood pressure monitor in real time.

[0041] The data acquisition module is used to obtain various parameter information of the arterial blood pressure monitor monitored in the working process of the dynamic monitoring module, and upload the data to the cloud or the remote server through wireless communication technology. The data acquisition module includes a data security transmission unit, which is used to protect the collected data through an encryption algorithm to prevent data leakage.

[0042] Specifically, the encryption algorithm formula in the data security transmission unit is:

[0043]

[0044] In the formula, E represents the encrypted data, E0 represents the original data, represents the encryption key, and C0 represents the initialization vector. By introducing the encryption algorithm formula in the data security transmission unit, the collected data always maintains an encrypted state during the transmission process, which can effectively resist hacker attacks and data theft, ensure the security and privacy of user health data, and ultimately greatly reduce the data transmission risk in the remote medical monitoring scene. Optionally, the encryption key can be any existing encryption key, and the present application does not limit this.

[0045] The data acquisition module further comprises a physiological signal acquisition unit, a monitor state parameter acquisition unit, and a complex scene interference data acquisition unit. The physiological signal acquisition unit is configured to acquire physiological signal data and divide the physiological signal data into systolic pressure signals, diastolic pressure signals, pulse wave characteristic signals, and heart rate signals according to signal types. The monitor state parameter acquisition unit is configured to acquire monitor state parameters and divide the monitor state parameters into power supply state parameters, sensor working state parameters, air path sealing property parameters, and communication state parameters according to parameter properties. The complex scene interference data acquisition unit is configured to acquire complex scene interference data and divide the complex scene interference data into motion-related interference data, environmental temperature and humidity interference data, electromagnetic interference data, and device aging interference data according to interference sources.

[0046] The data analysis module is configured to calculate a monitor state deviation degree Yv, a complex scene influence coefficient Fz, and a fault early warning index Sj according to the acquired various parameter information of the arterial blood pressure monitor. The data analysis module comprises a complex scene weakening unit, a monitor state interference exclusion unit, and a fault data judgment unit.

[0047] Specifically, the complex scene weakening unit is configured to calculate the complex scene influence coefficient Fz according to complex scene interference data (such as motion noise amplitude, environmental temperature change, humidity change, electromagnetic interference strength, signal attenuation degree, device aging degree, and power supply fluctuation amplitude), and the calculation formula is as follows:

[0048]

[0049] In the formula, Fz represents the complex scene influence coefficient, R i represents a real-time measurement value of the ith complex scene interference parameter (such as motion noise amplitude, environmental temperature change, humidity change, electromagnetic interference strength, signal attenuation degree, device aging degree, and power supply fluctuation amplitude), represents a reference value of the ith complex scene interference parameter (such as motion noise amplitude, environmental temperature change, humidity change, electromagnetic interference strength, signal attenuation degree, device aging degree, and power supply fluctuation amplitude), represents a historical standard deviation of the ith complex scene interference parameter, and γ i represents a weighted interference deviation degree of the ith complex scene interference parameter, reflecting the importance of different interference types, and n represents the total number of interference parameters. By calculating the complex scene influence coefficient Fz and substituting it into the calculation formula of the fault early warning index Sj, the motion, environmental temperature and humidity change, electromagnetic interference, and other complex environmental factors are excluded from the interference with the monitoring data, and the dynamic influence of the environmental variables is fully considered in the fault diagnosis process, so as to achieve the effect of quantifying and stripping the environmental interference from the monitoring data, and finally improve the anti-interference ability of the fault diagnosis result.

[0050] The monitor state interference elimination unit is configured to calculate a monitor state deviation degree Yv according to the monitor state parameters (the power supply state parameter, the sensor working state parameter, the air path sealing property parameter and the communication state parameter), and the calculation formula is:

[0051]

[0052] In the formula, Yv represents the monitor state deviation degree, W k represents the kth type of measured parameter of the monitor (such as the power supply state measured parameter, the sensor working state measured parameter, the air path sealing property measured parameter and the communication state measured parameter value), represents the kth type of reference parameter of the monitor (such as the power supply state reference parameter, the sensor working state reference parameter, the air path sealing property reference parameter and the communication state reference parameter value), a k represents the corresponding weight coefficient of the kth type of state parameter of the monitor, and m represents the number of different states of the monitor. By calculating the monitor state deviation degree Yv and substituting it into the calculation formula of the fault early warning index Sj, the influence of the monitor itself hardware aging, power supply fluctuation, air path sealing property decline and other internal state changes on the monitoring result is eliminated, the fault diagnosis can accurately identify the device itself abnormality, the purpose of distinguishing the device fault from the normal physiological signal fluctuation is achieved, and the pertinence of the fault early warning is finally improved.

[0053] The fault data judgment unit is configured to calculate a fault early warning index Sj according to the monitor state deviation degree Yv, the complex scene influence coefficient Fz and the physiological signal data, and the calculation formula is:

[0054]

[0055] In the formula, Sj represents a fault warning index, Yv represents a monitor state deviation degree, Fz represents a complex scene influence coefficient for quantifying the influence degree of environmental interference (such as movement, temperature and humidity change, electromagnetic interference and the like) on the system performance, H represents a real-time physiological signal vector (such as physiological signal data divided into systolic pressure signal, diastolic pressure signal, pulse wave feature signal and heart rate signal), H0 represents a physiological health baseline vector dynamically generated based on user historical data, ε represents a physiological signal normalization coefficient for preventing the denominator from being 0, and α, β, μ and α respectively represent corresponding weight coefficient of physiological signal data, monitor state parameter and complex scene interference data, which are adjusted according to system design and actual test results to reflect the sensitivity of different types of data in the system to fault warning, and λ represents a system automatic calibration offset for compensating individual differences (for example, diabetic patients, λ = 0.05). The fault data judgment unit calculates the fault warning index Sj according to the monitor state deviation degree Yv, the complex scene influence coefficient Fz and the physiological signal data, so as to make it as a quantitative standard for judging whether the monitor is in a normal running state under the influence of excluding environmental interference and device state abnormality.

[0056] In another feasible embodiment, in order to further improve the modeling ability of the fault warning index, make it enhance the expandability of the model structure and the semantic correlation between parameters without changing the original parameter use mode and calculation result, the application provides an equivalent alternative fault warning index calculation method. This method introduces a structure reconstruction and function recombination mechanism, which optimizes the logical expression of the original weighted sum structure while keeping the final value consistent.

[0057] Specifically, the fault data judgment unit is configured to calculate the fault warning index Sj according to the monitor state deviation degree Yv, the complex scene influence coefficient Fz and the physiological signal data, and the calculation formula is as follows:

[0058]

[0059] In the design process of the above formula, the original model independently weights each parameter and linearly superimposes them, ignoring the cross-influence relationship between the parameters. In the new model, the physiological signal deviation degree, the monitor state deviation degree and the environmental interference intensity are combined in a product structure, which can more truly reflect the nonlinear characteristics of the "device state deterioration + environmental interference resonance amplification" in the actual system. For example, when the monitor itself is abnormal (Yv is large) and there is a strong interference environment (Fz is large), the fault risk is much higher than the simple additive result of the two alone, and the multiplicative structure can better reflect the risk resonance effect.

[0060] Therefore, the physiological signal deviation term increases the sensitivity of the calculated value by exponential means. Even slight physiological fluctuations can produce a nonlinear amplification effect in the exponential term, helping to identify potential anomalies in advance. Simultaneously, the environmental interference term is added with a new structure, which can significantly suppress the final exponent when Fz is large, simulating the weakening effect of environmental interference on signal quality. This structure retains the logic of introducing risk influencing factors while enhancing control through a fractional form. Furthermore, the logarithmic function compresses the input exponential value to a more stable output range, preventing the warning exponent from amplifying indefinitely in high-risk situations, thus avoiding misjudgment or system overreaction. At the same time, the logarithmic function also reserves space for subsequent model expansion (such as exponential trend fitting and cumulative exponential modeling), enhancing the future upgrade capability of the system model.

[0061] By reconstructing and optimizing the above-mentioned fault warning index formula, the following technical advantages are achieved without changing the original data input type and dimensions or the result judgment criteria: enhancing the expressive power and recognition accuracy of fault risks under complex scene interference, especially suitable for early warning in scenarios with multiple factors causing disturbance; improving the model's response sensitivity to nonlinearity and extreme values, which is more in line with the physical characteristics of fluctuation and coupling in actual equipment operation; and strengthening the model's scalability and interpretability, providing a good basic structure for subsequent intelligent algorithms.

[0062] The evaluation module is used to assess the operating status of the monitor based on the fault warning index Sj, and to classify the warning based on the evaluation results.

[0063] Specifically, when the fault warning index Sj is <0.3, no intervention measures are required. The system maintains routine monitoring and determines that physiological signals, monitor status, and environmental interference are all within safe ranges. The system can operate normally, indicating that the current operating status is normal.

[0064] When the fault warning index Sj is in the range of 0.3-0.7, it indicates that there is a potential risk and a level 3 warning needs to be triggered. The system will automatically start the parameter calibration program and prompt the user to check the equipment connection status. It will determine that the monitoring data deviates from the reference value but has not reached the fault threshold. The risk needs to be eliminated through calibration or user intervention. The risk can be reduced through automatic calibration (such as sensor zero point correction and gas pressure adjustment) and user prompts (such as screen warnings and voice broadcasts).

[0065] When the fault warning index Sj>0.7, it indicates that a serious fault has occurred and a level one warning needs to be triggered. The system will immediately stop blood pressure measurement, lock the device function, and prompt medical staff to carry out maintenance through audible and visual alarms and remote notifications. If multiple parameters are found to be abnormal and exceed the safety boundary, an emergency shutdown is required to avoid misdiagnosis or equipment damage. Measurement will be forcibly stopped and device operation will be restricted. At the same time, local alarms (LED / buzzer) and remote push (to medical institutions or cloud platforms) will ensure timely handling.

[0066] The optimization module automatically adjusts and optimizes system parameters based on evaluation results to improve the accuracy and reliability of the monitor. By setting threshold ranges, which can be dynamically adjusted according to device model, usage scenario (e.g., hospital / home), or user characteristics (e.g., hypertensive patients), the system's early warning accuracy is enhanced. This enables tiered management and precise response to fault risks, significantly improving the system's safety and reliability.

[0067] In summary, by establishing dynamic monitoring, data acquisition, data analysis, evaluation, and optimization modules, and ensuring their collaborative operation, a closed-loop management system is achieved, encompassing real-time data acquisition, secure transmission, accurate analysis, intelligent evaluation, and dynamic optimization. This effectively improves the timeliness and accuracy of system fault diagnosis, thereby guaranteeing the stable operation of the intelligent arterial blood pressure monitor in complex environments. Specifically, the fault data judgment unit calculates a fault warning index Sj based on the monitor's state deviation Yv, the influence coefficient of complex scenarios Fz, and physiological signal data. After excluding the influence of environmental interference and abnormal equipment conditions, this index serves as a quantitative standard for judging whether the monitor's operating status is normal. These measures enable the system to proactively intervene before potential faults occur, effectively preventing fault escalation and ensuring the validity of monitoring data.

[0068] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0069] The above embodiments merely illustrate several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A fault diagnosis system for an arterial blood pressure monitor, characterized in that, The system includes a dynamic monitoring module, a data acquisition module, a data analysis module, an evaluation module, and an optimization module; The dynamic monitoring module is used to monitor the operating status of the arterial blood pressure monitor in real time. The data acquisition module is used to acquire various parameter information of the arterial blood pressure monitor monitored during the operation of the dynamic monitoring module, and upload the data to the cloud or remote server through wireless communication technology. The data analysis module is used to calculate the monitor state deviation Yv, the complex scenario influence coefficient Fz, and the fault warning index Sj based on the collected arterial blood pressure monitor parameter information. The evaluation module is used to evaluate the operating status of the monitor based on the fault warning index Sj, and to classify the warning based on the evaluation results; The system parameters are automatically adjusted and optimized based on the evaluation results.

2. The arterial blood pressure monitor fault diagnosis system according to claim 1, characterized in that, The data acquisition module includes a data security transmission unit, which is used to protect the acquired data through an encryption algorithm. The encryption algorithm formula in the data security transmission unit is: In the formula, E represents the encrypted data, and E0 represents the original data. C0 represents the encryption key and C0 represents the initialization vector.

3. The arterial blood pressure monitor fault diagnosis system according to claim 1, characterized in that, The data acquisition module includes a physiological signal acquisition unit, which is used to acquire physiological signal data and classify the physiological signal data into systolic blood pressure signal, diastolic blood pressure signal, pulse wave characteristic signal and heart rate signal according to the signal type.

4. The arterial blood pressure monitor fault diagnosis system according to claim 3, characterized in that, The data acquisition module includes a monitor status parameter acquisition unit, which is used to acquire monitor status parameters and classify them into power status parameters, sensor operating status parameters, gas path sealing parameters, and communication status parameters according to their properties.

5. The arterial blood pressure monitor fault diagnosis system according to claim 4, characterized in that, The data acquisition module includes a complex scene interference data acquisition unit, which is used to collect complex scene interference data and classify the complex scene interference data into motion-related interference data, environmental temperature and humidity interference data, electromagnetic interference data and equipment aging interference data according to the source of interference.

6. The arterial blood pressure monitor fault diagnosis system according to claim 5, characterized in that, The data analysis module includes a complex scene weakening unit, which is used to calculate the complex scene influence coefficient Fz based on the complex scene interference data. The calculation formula is as follows: In the formula, Fz represents the influence coefficient of complex scenarios, and R i This represents the real-time measured value of the interference parameter for the i-th type of complex scene. This represents the baseline value of the interference parameters for the i-th type of complex scene. γ represents the historical standard deviation of the disturbance parameters for the i-th type of complex scene. i denoted as the interference deviation degree after weighting the interference parameters of the i-th complex scene, and n represents the total number of interference parameters.

7. The arterial blood pressure monitor fault diagnosis system according to claim 6, characterized in that, The data analysis module includes a monitor state interference elimination unit, which calculates the monitor state deviation Yv based on the monitor state parameters. The calculation formula is as follows: In the formula, Yv represents the monitor's state deviation, and W... k This represents the measured parameter of the k-th state of the monitor. Let a represent the baseline parameter for the k-th type of state of the monitor. k represents the weight coefficient corresponding to the k-th state parameter of the monitor, and m represents the number of different states of the monitor.

8. The arterial blood pressure monitor fault diagnosis system according to claim 7, characterized in that, The data analysis module includes a fault data judgment unit, which calculates the fault warning index Sj based on the monitor state deviation Yv, the complex scene influence coefficient Fz, and physiological signal data. The calculation formula is as follows: In the formula, Sj represents the fault warning index, Yv represents the monitor state deviation, Fz represents the complex scene influence coefficient, H represents the real-time physiological signal vector, H0 represents the physiological health baseline vector, ε represents the physiological signal normalization coefficient, α, β, μ, and α represent the corresponding weight coefficients of physiological signal data, monitor state parameters, and complex scene interference data, respectively, and λ represents the system automatic calibration offset.

9. The arterial blood pressure monitor fault diagnosis system according to claim 1, characterized in that, In the evaluation module, when the fault warning index Sj is <0.3, no intervention measures are needed to maintain routine monitoring. It is determined that the physiological signals, monitor status, and environmental interference are all within a safe range, indicating that the current operating status is normal. When the fault warning index Sj is in the range of 0.3-0.7, it indicates that there is a potential risk that needs to be triggered to trigger a level 3 warning. The parameter calibration program will be automatically started and the user will be prompted to check the device connection status. It is determined that the monitoring data deviates from the benchmark value but has not reached the fault threshold. The risk needs to be eliminated through calibration or user intervention. The risk is reduced through automatic calibration and user prompts. When the fault warning index Sj>0.7, it indicates that a serious fault has occurred and a level one warning needs to be triggered. Blood pressure measurement will be stopped immediately, the device function will be locked, and medical staff will be notified to carry out maintenance through audible and visual alarms and remote notifications. If multiple parameters are found to be abnormal and exceed the safety boundary, an emergency shutdown is required to avoid misdiagnosis or equipment damage. Measurement will be forcibly stopped and device operation will be restricted. At the same time, local alarms and remote push notifications will be issued.

10. The arterial blood pressure monitor fault diagnosis system according to claim 1, characterized in that, In the optimization module, the threshold range is dynamically adjusted, and the threshold range can be dynamically adjusted according to the device model, usage scenario or user characteristics.

Images