Medical equipment intelligent early warning system based on Internet of Things

Abstract

The invention relates to the technical field of equipment operation monitoring, in particular to a medical equipment intelligent early warning system based on the Internet of Things, which comprises an abnormal accumulation risk assessment module, a core component degradation analysis module, a workload analysis module, an equipment health state monitoring module and a dynamic alarm grading module. According to the invention, the equipment operation parameters including X-ray tube current fluctuation, cooling system temperature change and the like are collected by using the Internet of Things technology, the accumulated influence of abnormal parameters is calculated through accumulated data, the long-term degradation curve of the equipment is effectively fitted, the potential long-term degradation trend of the equipment can be predicted, the possibility of preventive maintenance is enhanced, and the maintenance efficiency is improved. By dynamically monitoring the working load and calculating the influence of the working load on the equipment state, the service life of the equipment is prolonged, the maintenance cost is reduced, the accuracy of fault detection is improved, the resource configuration is optimized, and greater economic and safety values are created for medical institutions.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment operation monitoring, and particularly to an intelligent early warning system for medical equipment based on the Internet of Things. Background Technique

[0002] The technical field of equipment operation monitoring involves data collection, analysis, and anomaly detection of the operating states of various equipment to ensure the stable operation of the equipment, improve maintenance efficiency, and reduce the risk of failures. This technical field generally includes links such as sensor data collection, status parameter monitoring, operating mode analysis, fault prediction, and diagnosis, and is widely applied in industries such as industrial manufacturing, transportation, energy management, and medical devices. The core technologies cover methods such as signal processing, machine learning, deep learning, modal analysis, and trend prediction. By establishing an equipment health model, intelligent operation and maintenance of the equipment and fault early warning are realized, the service life of the equipment is increased, and resource allocation is optimized.

[0003] Among them, the intelligent early warning system for medical equipment aims to monitor and intelligently analyze the operating state of medical equipment in real time to identify potential fault risks and provide early warnings to ensure the stable operation of medical equipment. This system can be applied to imaging equipment, monitoring equipment, laboratory testing equipment, etc. By monitoring the operating state of medical equipment in real time, detecting potential anomalies, and issuing early warnings, it ensures the normal operation of the equipment and reduces medical risks caused by equipment failures. The system predicts possible failures of the equipment through data analysis, status evaluation, and intelligent analysis, and provides maintenance suggestions to improve the use efficiency and safety of medical equipment.

[0004] Traditional early warning systems rely on signal processing and threshold judgment, and it is difficult to achieve the target effect when dealing with complex equipment and changing operating conditions. For example, when traditional methods deal with non-linear and non-statically changing equipment operating parameters, it is difficult to accurately predict the degradation trend of the equipment, and potential equipment failures cannot be detected in time, resulting in sudden shutdowns and increased maintenance costs. When traditional systems monitor the health status of equipment, they ignore the actual impact of workload changes on equipment performance, resulting in misjudgment of the equipment status, affecting medical safety and the effective utilization of equipment, and restricting their application effects in high-demand medical environments. Summary of the Invention

[0005] The purpose of the present invention is to solve the disadvantages existing in the prior art, and to propose an intelligent early warning system for medical equipment based on the Internet of Things.

[0006] To achieve the above purpose, the present invention adopts the following technical solution: An intelligent early warning system for medical equipment based on the Internet of Things, the system includes: The abnormal accumulation risk assessment module obtains the operating data of medical devices through the Internet of Things, calculates the cumulative impact value of abnormal parameters per unit time, combines the device operating duration and workload level, calculates the slope of the device degradation trend, and obtains the long-term degradation rate prediction value; Based on the long-term degradation rate prediction value, the core component deterioration analysis module extracts the operating state parameters of the core components of the medical device, screens the parameter groups associated with the operating state fluctuations, invokes the change trends of the parameters in multiple operating stages, calculates the cumulative impact of the parameters during the device operating cycle, and obtains the core component deterioration degree value; The workload analysis module invokes the core component deterioration degree value, monitors the workload level of the medical monitoring device, calculates the current workload level, obtains the parameter deterioration degree values under multiple load levels, calculates the impact of the current load state on the device operation, and obtains the load impact information; The device health status monitoring module invokes the load impact information, calculates the health index of the device under the current load level, calculates the deviation degree of the health index according to the normal health standard curve, and obtains the device health deviation degree.

[0007] The improvements of the present invention are that the long-term degradation rate prediction value is specifically the slope of the abnormal accumulation curve, the calculation result of the degradation impact weight, the fitting parameter of the long-term degradation trend, the calculated value of the dynamic inflection point detection, and the slope of the device degradation trend. The core component deterioration degree value includes the change amount of the temperature rise rate, the cumulative value of the power consumption change amplitude, the evaluation value of the vibration frequency fluctuation range, and the cumulative change rate of the parameter contribution value. The load impact information is specifically the fluctuation value of the electrocardiogram signal processing power consumption, the change amount of the blood oxygen sensor data update frequency, the power fluctuation value of the temperature regulation system, the calculated value of the parameter deterioration degree values under multiple load levels, and the current load state impact coefficient. The device health deviation degree includes the deviation amount of the motor speed, the abnormal amplitude of the signal fluctuation, the deviation interval value of the temperature change, the calculation result of the health index, and the evaluation value of the health index deviation degree.

[0008] The improvements of the present invention are that the abnormal accumulation risk assessment module includes: The abnormal parameter analysis module obtains the operating data of the medical device through the Internet of Things. The operating data includes the X-ray tube current fluctuation, the cooling system temperature change, and the frame vibration frequency. It calculates the change rate of each abnormal parameter per unit time, determines whether the parameter change exceeds the set threshold, screens the parameters that meet the abnormal standard, and establishes the change trend curve of each abnormal parameter to obtain the abnormal parameter trend data; The abnormal cumulative impact calculation module invokes the abnormal parameter trend data, sets the degradation impact weight for each abnormal type, calculates the cumulative impact value of each abnormal parameter per unit time, and uses the formula: ; Calculate the cumulative impact value of each abnormal parameter to obtain the abnormal cumulative impact value; Among them, represents the abnormal cumulative impact value per unit time, represents the degradation impact weight of the i-th abnormal parameter, represents the parameter value of the i-th abnormal parameter at time t, represents time the parameter value of the i-th abnormal parameter at time represents the time interval, and n represents the total number of abnormal parameters; The device degradation trend prediction module calls the abnormal cumulative impact value, combines the device operation duration and workload level, calculates the contribution degree of the abnormal impact in the long-term degradation trend, fits the long-term degradation curve of the device, calculates the curve change rate, combines the dynamic inflection point detection to calculate the device degradation trend slope, and obtains the long-term degradation rate prediction value.

[0009] The improvement of the present invention is that the core component deterioration analysis module includes: The operating state parameter extraction module extracts the operating state parameters of the core components of the medical device based on the long-term degradation rate prediction value, including the temperature rise rate, power consumption change range, and vibration frequency fluctuation range, calls the state record data during the device operation cycle, calculates the change rate of each parameter in multiple time periods, and obtains the operating state parameter data; The parameter correlation screening module calls the operating state parameter data, calculates the fluctuation range of each parameter, analyzes the change trend of each parameter, calculates the correlation between each parameter and the device operating state, screens the parameter group associated with the operating state fluctuation, and obtains the state fluctuation associated parameters; The core component deterioration calculation module calls the state fluctuation associated parameters, calculates the cumulative impact of the parameters during the device operation cycle according to the change trend of the parameters in various operating stages of the device, and uses the formula: ; Calculates and obtains the core component deterioration degree value; Among them, represents the core component deterioration degree value, represents the fluctuation amplitude of the j-th state fluctuation associated parameter, represents the action duration of the j-th state fluctuation associated parameter, represents the device load level corresponding to the j-th state fluctuation associated parameter, represents the device reference load level, represents the operating weight of the j-th state fluctuation associated parameter, represents the reliability factor of the j-th state fluctuation associated parameter, and N represents the total number of state fluctuation associated parameters.

[0010] The improvement of the present invention is that the workload analysis module includes: The workload monitoring sub-module calls the deterioration degree value of the core component to monitor the workload level of the medical monitoring device, including the power consumption of electrocardiogram signal processing, the data update frequency of the blood oxygen sensor, and the power change of the temperature regulation system, and obtains the workload status parameters; The load level calculation sub-module calls the workload status parameters and uses the formula: ; Calculate and obtain the current workload level value; Among them, represents the current workload level value, represents the total number of device components, represents the power consumption of the a-th type of device component, represents the operating frequency of the a-th type of device component, represents the operating cycle of the a-th type of device component, represents the load variance of the a-th type of device component; The load impact assessment sub-module calls the current workload level value and calculates the impact of the current load status on the device operation based on the parameter deterioration degree values under various load levels, and obtains the load impact information.

[0011] The improvement of the present invention is that the device health status monitoring module includes: The operating status parameter extraction sub-module calls the load impact information and extracts the current working status parameters of the device through the Internet of Things, including the motor speed, signal fluctuation, and temperature change, and obtains the device working status parameter set; The health index calculation sub-module calls the device working status parameter set and calculates the health index of the status parameters under the current load level, using the formula: ; Calculate and obtain the device health index; Among them, represents the device health index, represents the total number of monitoring parameters, represents the importance coefficient of the k-th parameter, represents the current status value of the k-th parameter, represents the reference health status value of the k-th parameter, represents the tolerance threshold of the k-th parameter; The health deviation assessment sub-module calls the device health index and calculates the health index deviation degree based on the normal health standard curve corresponding to the device usage years, and obtains the device health deviation degree.

[0012] The improvement of the present invention is that the system further includes: The dynamic alarm grading module calls the device health deviation degree, combines the operating parameters of the key components of the device, and calculates the alarm level in the current health state according to the ratio of each parameter deviating from the stable range, so as to obtain the dynamic alarm level of the device. The dynamic alarm level of the device specifically refers to the abnormal deviation value of power consumption, the over-limit ratio of current fluctuation, the abnormal detection value of vibration amplitude, the matching result of the health score standard, and the classification determination value of the alarm level.

[0013] The improvement of the present invention is that the dynamic alarm grading module includes: The key component parameter monitoring sub-module calls the device health deviation degree, combines the operating parameters of the key components of the device, extracts the operating state parameters of the key components, calculates the ratio of each parameter deviating from the stable range, and obtains the deviation ratio of the device health state. The health state alarm calculation sub-module calls the deviation ratio of the device health state and the device health deviation degree, and uses the formula: ; Calculate through operation to obtain the device health alarm level value. Among them, represents the device health alarm level value, represents the total number of health monitoring parameters, represents the alarm influence coefficient of the d-th parameter, represents the current deviation value of the d-th parameter, represents the reference stable range value of this parameter, represents the stability threshold of the d-th parameter, represents the health deviation degree weight coefficient, represents the device health deviation degree; The device alarm level acquisition sub-module calls the device health alarm level value, and compares and obtains the dynamic alarm level of the device according to the mapping rule between the device health state and the alarm level.

[0014] Compared with the prior art, the advantages and positive effects of the present invention are as follows: In the present invention, by using the Internet of Things technology to collect device operation parameters, including X-ray tube current fluctuation, cooling system temperature change, etc., and calculating the cumulative impact of abnormal parameters through accumulated data, the long-term degradation curve of the device can be effectively fitted, and the potential long-term deterioration trend of the device can be predicted, enhancing the possibility of preventive maintenance. By dynamically monitoring the workload and calculating its impact on the device state, the medical device can maintain the best operating state under different working conditions, extend the device life, reduce the maintenance cost, improve the accuracy of fault detection, optimize the resource allocation, and create greater economic and safety value for medical institutions. Brief Description of the Drawings

[0015] Figure 1It is the system flow chart of the present invention; Figure 2 It is the flow chart of the abnormal accumulation risk assessment module of the present invention; Figure 3 It is the flow chart of the deterioration analysis module of the core components of the present invention; Figure 4 It is the flow chart of the workload analysis module of the present invention; Figure 5 It is the flow chart of the device health status monitoring module of the present invention; Figure 6 It is the flow chart of the dynamic alarm grading module of the present invention. Detailed implementation manners

[0016] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention.

[0017] In the description of the present invention, it should be understood that the orientation or positional relationships indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. are based on the orientation or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as limiting the present invention. In addition, in the description of the present invention, the meaning of "a plurality of" is two or more unless otherwise specifically defined.

[0018] Please refer to Figure 1 , the present invention provides a technical solution: an intelligent early warning system for medical devices based on the Internet of Things, and the system includes: The abnormal accumulation risk assessment module obtains the operation data of medical devices through the Internet of Things. The operation data includes the fluctuation of the X-ray tube current, the temperature change of the cooling system, and the vibration frequency of the gantry. It calculates the cumulative impact value of abnormal parameters per unit time, establishes an abnormal accumulation curve based on the trend of each abnormal parameter, sets a degradation impact weight for the abnormal type, combines the device operation duration and the workload level, calculates the contribution degree of the abnormal impact in the long-term degradation trend, fits the long-term degradation curve of the device, calls the curve change rate, and combines the dynamic inflection point detection to calculate the slope of the device degradation trend, and obtains the long-term degradation rate prediction value; Based on the long-term degradation rate prediction value, the core component degradation analysis module extracts the operating state parameters of the core components of the medical device, including the temperature rise rate, the power consumption change range, and the vibration frequency fluctuation range, screens the parameter groups associated with the operating state fluctuations, calls the change trends of the parameters in various operating stages, calculates the cumulative impact of the parameters during the device operation cycle, and obtains the core component degradation degree value; The workload analysis module calls the core component degradation degree value to monitor the workload level of the medical monitoring device. The workload level includes the power consumption for electrocardiogram signal processing, the data update frequency of the blood oxygen sensor, and the power change of the temperature regulation system, calculates the current workload level, obtains the parameter degradation degree values under various load levels, calculates the impact of the current load state on the device operation, and obtains the load impact information; The device health status monitoring module calls the load impact information, extracts the current operating state parameters of the device through the Internet of Things, including the motor speed, signal fluctuation, and temperature change, calculates the health index of the device under the current load level, calculates the deviation degree of the health index based on the normal health standard curve, and obtains the device health deviation degree; The dynamic alarm classification module calls the device health deviation degree, combines the operating parameters of the key components of the device, and calculates the alarm level in the current health state according to the ratio of each parameter deviating from the stable interval, and obtains the device dynamic alarm level.

[0019] The long-term degradation rate prediction value specifically includes the slope of the abnormal accumulation curve, the calculation result of the degradation impact weight, the fitting parameter of the long-term degradation trend, the calculated value of the dynamic inflection point detection, and the slope of the device degradation trend. The core component degradation degree value includes the change amount of the temperature rise rate, the cumulative value of the power consumption change range, the evaluation value of the vibration frequency fluctuation range, and the cumulative change rate of the parameter contribution value. The load impact information specifically includes the fluctuation value of the power consumption for electrocardiogram signal processing, the change amount of the data update frequency of the blood oxygen sensor, the power fluctuation value of the temperature regulation system, the calculated value of the parameter degradation degree values under various load levels, and the current load state impact coefficient. The device health deviation degree includes the deviation amount of the motor speed, the abnormal amplitude of the signal fluctuation, the deviation interval value of the temperature change, the calculation result of the health index, and the evaluation value of the deviation degree of the health index. The device dynamic alarm level specifically refers to the abnormal deviation value of the power consumption, the over-limit ratio of the current fluctuation, the abnormal detection value of the vibration amplitude, the matching result of the health score standard, and the classification determination value of the alarm level.

[0020] Please refer to Figure 2 , the abnormal accumulation risk assessment module includes: The abnormal parameter analysis module obtains the operation data of medical devices through the Internet of Things. The operation data includes the X-ray tube current fluctuation, the temperature change of the cooling system, and the rack vibration frequency. It calculates the change rate of each abnormal parameter per unit time, determines whether the parameter change exceeds the set threshold, filters the parameters that meet the abnormal criteria, establishes the change trend curve of each abnormal parameter, and obtains the abnormal parameter trend data; The abnormal parameter analysis module obtains the operation data of medical devices from the Internet of Things system, including the X-ray tube current fluctuation, the temperature change of the cooling system, and the rack vibration frequency. Among them, the X-ray tube current fluctuation data is sourced from the real-time monitoring of the high-voltage power supply system. The temperature change of the cooling system is continuously measured by temperature sensors deployed at different nodes of the cooling pipeline. The rack vibration frequency is obtained by an acceleration sensor or a laser vibrometer at multiple support points, and the main frequency component is extracted through Fourier transform. When calculating the change rate of each abnormal parameter per unit time, a time window is first set , for the X-ray tube current, the time interval is set to 1 second, and the change value of the current within the time window is calculated. For example, the current value at time t is 150 mA, and the time When the current is 140 mA at a certain moment, the current change rate per unit time is (150 - 140) / 1 = 10 mA / s. For the temperature of the cooling system, taking a 5-second time window, the temperature at time t is set to 20.5 °C, and the temperature at time t - 1 is 19.8 °C. Then the temperature change rate is (20.5 - 19.8) / 5 = 0.14 °C / s. For the rack vibration frequency, the main vibration frequency at time t is set to 60 Hz, and the vibration frequency at time t - 1 is 58 Hz. Then the vibration frequency change rate is calculated as (60 - 58) / 1 = 2 Hz / s. When judging whether the parameter change exceeds the set threshold, the abnormal threshold of the X-ray tube current is set according to the medical device manufacturing standard. The current stability requirement of this device is that the current fluctuation does not exceed 15% of the full-scale current. The full-scale current of this device is 200 mA. Therefore, the abnormal threshold is calculated as 200×15% = 30 mA / s. The temperature change threshold of the cooling system is set based on the calculation of the heat exchange efficiency of the coolant. The cooling capacity range of the cooling system of this device is ±2.5 °C per minute, that is, 0.5 °C / s. The abnormal threshold of the rack vibration frequency is set according to the vibration tolerance standard. The maximum allowable rack vibration frequency deviation in the device operating environment is 5 Hz / s. Therefore, the abnormal threshold is set to 3 Hz / s. Since there may be short-term large fluctuations in occasional vibration adjustments during normal operation, 60% of this value is taken as the abnormal determination threshold, that is, 3 Hz / s. Comparing the obtained change rates, it is found that the current change rate of 10 mA / s does not exceed the threshold, the temperature change rate of 0.14 °C / s does not exceed the threshold, and the vibration frequency change rate of 2 Hz / s does not exceed the threshold. Therefore, no abnormal parameters are screened out. If a certain parameter exceeds the threshold, it is marked as abnormal and subsequent trend analysis is carried out. When establishing the abnormal parameter change trend curve, time series data points are selected, such as data points in the past 10 minutes, and the least squares method is used for curve fitting to obtain the slope and curvature of the trend curve, and finally the abnormal parameter trend data is obtained.

[0021] The abnormal cumulative impact calculation module calls the abnormal parameter trend data, sets the degradation impact weight for each abnormal type, calculates the cumulative impact value of each abnormal parameter per unit time, and uses the formula: ; Calculate the cumulative impact value of each abnormal parameter to obtain the abnormal cumulative impact value; Among them, represents the abnormal cumulative impact value per unit time, represents the degradation impact weight of the i-th abnormal parameter, represents the parameter value of the i-th abnormal parameter at time t, represents time the parameter value of the i-th abnormal parameter at time represents the time interval, and n represents the total number of abnormal parameters; The abnormal cumulative impact calculation module sets the degradation impact weight for each type of abnormal parameter based on the abnormal parameter trend data. The weight setting is based on the analysis of the long-term operation impact of the device. By statistically analyzing the operation data of the past 100,000 hours, the impact ratio of each abnormal parameter in the device failure is evaluated. For example, in the historical maintenance data of the device, the proportion of critical component damage caused by the fluctuation of the X-ray tube current is 30%, the proportion of device degradation damage caused by the temperature change of the cooling system is 50%, and the proportion of structural fatigue impact caused by the abnormal vibration frequency of the rack is 20%. Accordingly, the degradation impact weight of the current fluctuation is set to 0.3, the temperature change of the cooling system is set to 0.5, and the vibration frequency of the rack is set to 0.2. The setting of the weight value makes the contribution of different abnormalities to the overall degradation impact conform to the actual situation of the device operation environment. When calculating the cumulative impact value of each abnormal parameter per unit time, the formula is brought in: ; Set the unit time interval to 1 second. The change rates of the X-ray tube current, the temperature of the cooling system, and the vibration frequency of the rack at time t are 10 mA / s, 0.14 °C / s, and 2 Hz / s respectively. Then calculate the cumulative impact value: ; The obtained abnormal cumulative impact value is 3.47. After obtaining the abnormal cumulative impact value, it is compared with the device health status evaluation standard. For example, it is set that the impact value in the range of 0 - 2 indicates normal, the range of 2 - 5 indicates mild abnormality, and greater than 5 indicates severe abnormality. The current impact value of 3.47 is in the mild abnormality range.

[0022] The device degradation trend prediction module calls the abnormal cumulative impact value, combines the device operation duration and the workload level, calculates the contribution degree of the abnormal impact in the long-term degradation trend, fits the long-term degradation curve of the device, calculates the curve change rate, combines the dynamic inflection point detection to calculate the slope of the device degradation trend, and obtains the long-term degradation rate prediction value; The device degradation trend prediction module calls the abnormal cumulative impact value and combines the device operation duration and the workload level to calculate the contribution degree of the abnormal impact in the long-term degradation trend. The device operation duration is extracted from the device usage log. It is set that the current device has been running for 5000 hours. The workload level is calculated by the average value of the daily task processing volume. For example, the maximum daily task processing volume designed for the device is 1000 times, and the current actual daily processing task is 700 times. Then the load level is 700 / 1000 = 0.7. When fitting the long-term degradation curve of the device, the abnormal cumulative impact value data points of the past 6 months are used, and the exponential smoothing method is used to calculate the long-term degradation trend. The cumulative impact values of the past 6 months are set as: , calculate the slope of the long-term degradation trend: Slope = ; Combined with dynamic inflection point detection, for example, when the slope change exceeds 0.5 in three consecutive months, it is identified as a degradation acceleration trend. Calculate the long-term degradation rate prediction value of the device, and based on the setting of the device's maximum allowable degradation impact threshold. For example, when the abnormal cumulative impact value reaches 10 as specified in the device user manual, the key component needs to be replaced. Therefore, the replacement standard threshold is set to 10, and predict whether this threshold will be reached in the next three months. Set the current slope of 0.32 to remain unchanged, then the impact value is expected to reach: 4.0 + (0.32 × 3) = 4.96 after three months; The results show that the device degradation is still within the acceptable range in the short term and does not reach the replacement standard.

[0023] Please refer to Figure 3 , the core component degradation analysis module includes: The operating state parameter extraction module extracts the operating state parameters of the core components of the medical device based on the long-term degradation rate prediction value, including the temperature rise rate, power consumption change range, and vibration frequency fluctuation range. Call the state record data during the device operation cycle, calculate the change rate of each parameter in multiple time periods, and obtain the operating state parameter data; The operating state parameter extraction module extracts the operating state parameters of the core components of the medical device based on the long-term degradation rate prediction value. Select the temperature rise rate, power consumption change range, and vibration frequency fluctuation range as the main monitoring objects. In the calculation of the temperature rise rate, record the temperature changes of each component through the internal temperature sensor of the device. Set the temperature of the core component at time t to 75 °C, the temperature at time t - 1 to 70 °C, and the time interval is set to 1 month. Then the temperature rise rate is calculated as (75 - 70) / 1 = 5 °C / month. For the power consumption change range, measure the working current of the device using a current sensor and calculate the power consumption in combination with the working voltage. Set the current at time t to 2.5 A and the voltage to 220 V, and the current at time t - 1 to 2.3 A. Then the power consumption change range is calculated as (2.5 × 220 - 2.3 × 220) / 1 = 44 W / month. The vibration frequency fluctuation range obtains data through the acceleration sensor installed on the rack and calculates the main vibration frequency using Fourier transform. Set the main vibration frequency at time t to 62 Hz and at time t - 1 to 59 Hz. Then the fluctuation range is calculated as 62 - 59 = 3 Hz. When calling the state record data during the device operation cycle, select the operation logs of the past 30 months, calculate the parameter change rate at 1-month intervals, and store it in the database to obtain the complete operating state parameter data.

[0024] The parameter correlation screening module calls the operating state parameter data, calculates the fluctuation range of each parameter, analyzes the change trend of each parameter, calculates the correlation between each parameter and the device operating state, screens the parameter groups associated with the state fluctuation, and obtains the state fluctuation associated parameters; The parameter correlation screening module calls the operating status parameter data and calculates the fluctuation range of each parameter. The fluctuation range of the temperature rise rate is determined by calculating the maximum and minimum change rates in the past 30 months. The maximum value is set at 8 °C / month and the minimum value at 3 °C / month, so the fluctuation range is 8 - 3 = 5 °C / month. The fluctuation range of the power consumption change amplitude is calculated in the same way. The maximum value is set at 50 W / month and the minimum value at 10 W / month, so the fluctuation range is 40 W / month. The calculation method for the vibration frequency fluctuation range is the same. The maximum value is set at 6 Hz and the minimum value at 2 Hz, so the fluctuation range is 4 Hz. When analyzing the change trend of each parameter, the data for the past 30 months is extracted and the trend slope is calculated using linear regression. For example, the trend slope of the temperature rise rate is calculated as 0.4 °C / month 2 The slope of the power consumption change amplitude is calculated as 3 W / month 2 The slope of the vibration frequency fluctuation range is calculated as 0.2 Hz / month 2 When calculating the correlation between each parameter and the device operating status, the operating load level of the device is selected as the reference variable, and the Pearson correlation coefficient is used to calculate the correlation. The correlation coefficient between the temperature rise rate and the load level is set at 0.85, the correlation coefficient for the power consumption change amplitude is 0.9, and the correlation coefficient for the vibration frequency fluctuation range is 0.6. The correlation threshold is set at 0.75. The basis for setting this threshold is as follows: By analyzing the operating data of the device in the past 30 months, the distribution of the correlation coefficients is statistically analyzed, and the top 25% of the data is used as the high-correlation standard. Parameters with a correlation below 0.75 have a weak correlation and are therefore not selected as state fluctuation correlation parameters. Finally, the temperature rise rate and the power consumption change amplitude are selected as state fluctuation correlation parameters to obtain the state fluctuation correlation parameters

[0025] The core component deterioration calculation module calls the state fluctuation correlation parameters and calculates the cumulative impact of the parameters during the device operation cycle based on the change trends of the parameters in various operating stages of the device. The formula used is: ; Calculate and obtain the core component deterioration degree value; where represents the core component deterioration degree value, represents the fluctuation amplitude of the j-th state fluctuation correlation parameter, represents the duration of action of the j-th state fluctuation correlation parameter, represents the device load level corresponding to the j-th state fluctuation correlation parameter, represents the device reference load level, represents the operating weight of the j-th state fluctuation correlation parameter, represents the reliability factor of the j-th state fluctuation correlation parameter, and N represents the total number of state fluctuation correlation parameters

[0026] The core component deterioration calculation module calls the state fluctuation correlation parameters, and calculates the cumulative impact of the parameters during the device operation cycle according to the change trend of the parameters in various operation stages of the device. The device operation cycle is set to 60 months, and the formula is called: ; Set the fluctuation range of the temperature rise rate / month, the action duration months, the operation weight , the current load level of the device , the reference load level , the reliability factor , where: the reference load level The setting basis is: the historical average load level of the device under normal operation. The load data for the past 60 months is statistically analyzed, and the median with relatively small load changes is taken as the reference load level to prevent abnormal data from affecting the calculation results; the operation weight The setting basis is: by classifying the influence degree of each core component of the device, the temperature change has a greater impact, and the weight is set to 0.4, and the power consumption has a relatively greater impact, and the weight is set to 0.5; the reliability factor The setting basis is: based on the reliability test data provided by the device manufacturer, combined with the actual operation of the device, calculated using the failure rate of the device in the past 60 months. The average failure rate of the device under high load operation is 5%, so the reliability factor is set to 0.95.

[0027] Substitute into the calculation: ;

[0028] Parameter setting of the power consumption change range W / month, months, , , , , where: the reference load level The setting basis is the same as that of the temperature rise rate part to ensure data consistency; the operation weight The setting basis is: according to the device operation energy consumption model, the change of power consumption has a more direct impact, so a higher weight of 0.5 is set; the reliability factor The setting basis is: statistically analyze the device operation data for 60 months, calculate the probability of failure occurrence at different load levels, and the change of the device's power consumption has a greater impact on the failure rate, so the reliability factor is set to 0.92.

[0029] Substitute into the calculation: ;

[0030] The calculation result of the deterioration degree value of the core component is: ;

[0031] This result indicates that the operating state of the core component is greatly affected by the temperature rise rate and the power consumption change range. Moreover, when the device operates under high load, the deterioration degree value of the core component will further increase.

[0032] Please refer to Figure 4 , the workload analysis module includes: The workload monitoring sub-module calls the deterioration degree value of the core component to monitor the workload level of the medical monitoring device, including the power consumption of electrocardiogram signal processing, the data update frequency of the blood oxygen sensor, and the power change of the temperature regulation system, and obtains the workload status parameters; The workload monitoring sub-module calls the deterioration rate of the core component to monitor the workload level of the medical monitoring device. In the monitoring of the power consumption of electrocardiogram signal processing, by measuring the current input of the electrocardiogram processing unit in real time and combining with the system voltage to calculate the power consumption. Suppose the working current of the electrocardiogram signal processing unit is 1.5 A at a certain moment and the power supply voltage is 5 V, then the power consumption is calculated as P = 1.5 × 5 = 7.5 W. When monitoring the data update frequency of the blood oxygen sensor, count the number of data samplings per second. Suppose the blood oxygen sensor samples 100 times per second and the time interval is set to 60 seconds, then the data update frequency is 100 × 60 = 6000 times / minute. When monitoring the power change of the temperature regulation system, measure the power output of the system during heating or cooling in real time. Suppose the system power is 200 W during the heating stage and 150 W during the cooling stage, then the power change is calculated as 200 - 150 = 50 W. When obtaining the workload status parameters, store the above measurement data in the load monitoring database and continuously update it to ensure the continuity and integrity of the data. The monitoring threshold for the power change of the temperature regulation system is set to 60 W, and this value refers to the power change range of the device under steady-state working conditions. The specific calculation method is to obtain the power change curve for 10 consecutive hours under full-load operating conditions, calculate the mean value and add the standard deviation. If the actual power fluctuation exceeds this range, it indicates abnormal load regulation. In the example calculation, the power mean value during full-load operation is 180 W and the standard deviation is 15 W, then the threshold is calculated as 180 + 15 = 195 W. If the monitored power change exceeds this value, record the abnormal data.

[0033] The load level calculation sub-module calls the workload status parameters and uses the formula: ; Calculate and obtain the current workload level value; Among them, represents the current workload level value, represents the total number of device components, represents the power consumption of the a-th type of device component, represents the operating frequency of the a-th device component, represents the operating cycle of the a-th device component, represents the load variance of the a-th device component; The load level calculation sub-module calls the workload status parameters and uses the formula: ; Calculate the current workload level value. It is assumed that the medical monitoring device includes three components: an electrocardiogram signal processing unit, a blood oxygen sensor, and a temperature regulation system. Then the total number of components , set the power consumption of the electrocardiogram signal processing , operating frequency , operating cycle seconds, load variance , substitute into the calculation: ; The power consumption of the blood oxygen sensor is set to , operating frequency , operating cycle = 3600 seconds, load variance , substitute into the calculation: ; The power consumption of the temperature regulation system is set to , operating frequency , operating cycle = 3600 seconds, load variance , substitute into the calculation: ; Calculate the current workload level value: ; The calculation of the current workload level value is completed. Among them, the load variance is set based on the long-term operation data of the device. The calculation formula is , where represents the power consumption of the device at different time points, represents the average power consumption of the device. It is assumed that the average power consumption of the electrocardiogram signal processing unit at the past 100 sampling points is 7.2W, and the power consumption at a certain sampling point is 7.8W. Then the variance calculation part is , and the current load variance is calculated accordingly.

[0034] The load impact assessment sub-module calls the current workload level value, calculates the impact of the current load status on the device operation based on the parameter degradation degree values under multiple load levels, and obtains the load impact information; The load impact assessment sub-module calls the current workload level value and calculates the impact of the current load status on the device operation based on the parameter degradation rates under various load levels. During the long-term operation of the device, load level partitions are set, such as the low load range , the medium load range , and the high load range . The currently calculated workload level value is 0.3, which belongs to the medium load range. When evaluating the impact of the load on the device operation, the device operation historical data is extracted, and the degradation rates of the core components under the same load level are analyzed. For example, when set in the medium load range, the core component temperature rise rate is 0.4℃ / s, the power consumption change range is 3W / s, and the vibration frequency fluctuation range is 2Hz. The above data is compared with the device safe operation threshold. The safe threshold of the temperature rise rate is set to 0.6℃ / s, which is calculated based on the device heat dissipation capacity. The calculation formula is , where is the device heat loss power, is the device heat dissipation coefficient. Set the device heat dissipation coefficient to 20W / ℃ and the heat loss power to 12W. Then the maximum temperature change rate is calculated as . This value is used as the safe operation threshold. If it exceeds this value, it may cause the device to overheat, and finally the load impact information is obtained.

[0035] Please refer to Figure 5 , the device health status monitoring module includes: The operation status parameter extraction sub-module calls the load impact information and extracts the current working status parameters of the device through the Internet of Things, including motor speed, signal fluctuation, and temperature change, to obtain the device working status parameter set; The operation status parameter extraction sub-module calls the load impact information and extracts the current working status parameters of the device through the Internet of Things. During the extraction of the motor speed, the real-time data of the built-in speed sensor of the device is read, and the change amount per unit time is calculated. Set the motor speed of a certain medical monitoring device to 3000 revolutions per minute at time t and 2950 revolutions per minute at time t - 1. Then the calculated speed change rate is: revolutions per minute; During the extraction of the signal fluctuation, the internal signal processing module of the device is used to perform mean filtering on the sensor signal, and the signal fluctuation range is calculated. Set that within a 10-second time window, the collected signal fluctuation amplitude ranges from 2.1V to 2.5V. Then the calculated fluctuation range is: 2.5 - 2.1 = 0.4V; The threshold setting for signal fluctuation is based on the device signal stability standard. Generally, the signal fluctuation of medical devices shall not exceed 5% of the rated signal amplitude. If the rated signal amplitude is set to 10V, then the fluctuation threshold is calculated as 10×0.05 = 0.5V. The currently calculated fluctuation range of 0.4V is lower than the threshold, indicating that the signal is within the normal range. During the extraction of temperature changes, the data of the internal temperature sensor of the device is called, and the temperature change rate is calculated. If the device temperature at time t is 37.8°C and the temperature at time t - 1 is 37.5°C, then the temperature change rate is calculated as follows: ; The reference value setting for temperature change is based on the temperature range during normal operation of the device. The core components of medical devices generally need to be maintained between 35°C and 40°C. Exceeding this range may cause the device to malfunction. The reference value is taken as 37.5°C. The currently measured value of 37.8°C is still within the reasonable range. Finally, the calculated motor speed, signal fluctuation, and temperature change data are stored in the device status database to obtain the device working status parameter set.

[0036] The health index calculation sub-module calls the device working status parameter set to calculate the health index of the status parameters under the current load level, using the formula: ; Calculate the device health index through operations; Among them, represents the device health index, represents the total number of monitoring parameters, represents the importance coefficient of the k-th parameter, represents the current status value of the k-th parameter, represents the reference healthy status value of the k-th parameter, represents the tolerance threshold of the k-th parameter; The health index calculation sub-module calls the device working status parameter set to calculate the health index of the status parameters under the current load level, using the formula: ; Set the total number of monitoring parameters , set the importance coefficient of the motor speed , the current speed r / min, the reference healthy status value r / min, the tolerance threshold = 200 r / min, substitute into the calculation: ; The setting basis of the importance coefficient of the motor speed lies in its influence on the overall performance of the equipment. According to the operating characteristics of the equipment, the influence of the motor speed on the system stability accounts for 40%. Therefore, the set weight is 0.4. The tolerance threshold of 200 revolutions per minute is based on the rated speed fluctuation range of the motor. Generally, the rated speed of medical equipment allows a ±5% fluctuation. If the rated speed is set at 4000 revolutions per minute, then the tolerance threshold is calculated as 4000×0.05 = 200. Set the importance coefficient of signal fluctuation , the current signal fluctuation amplitude , the reference value , the tolerance threshold , substitute into the calculation: ; The importance coefficient of signal fluctuation is set at 0.3. Based on the influence degree of the equipment signal processing module on the overall system, the tolerance threshold is set at 0.2V. According to the error standard of medical equipment signal processing, the signal fluctuation tolerance generally takes 2% of the rated signal amplitude. If the rated signal amplitude is set at 10V, then the tolerance threshold is calculated as 10×0.02 = 0.2V. Set the importance coefficient of temperature change , the current temperature , the reference value , the tolerance threshold , substitute into the calculation: ; The importance coefficient of temperature change is set at 0.3. Based on the influence degree of the temperature control system of medical equipment on the equipment stability, the tolerance threshold is set at 1℃. According to the temperature fluctuation range during the normal operation of medical equipment, the temperature change within the range of ±1℃ will not affect the equipment stability. Therefore, the tolerance threshold is set at 1℃. Calculate the health index: ; Finally, obtain the equipment health index.

[0037] The health deviation assessment sub-module calls the equipment health index. Based on the normal health standard curve corresponding to the equipment service life, calculate the deviation degree of the health index to obtain the equipment health deviation; The health deviation assessment sub-module calls the equipment health index. Based on the normal health standard curve corresponding to the equipment service life, calculate the deviation degree of the health index. When evaluating the health deviation, set the equipment service life at 5 years and call the equipment health standard curve. This curve defines the normal health index range under different service lives. For example, the health index interval corresponding to a 5-year service life is set as , compare the current health index with this interval and calculate the health index deviation: Deviation = 0.7 - 0.6468 = 0.0532; The basis for setting the health index reference value is the long-term health standard curve of the device. This standard curve is obtained by fitting the relationship between the initial health state of the device at the time of factory shipment and the service life. The health index corresponding to a 5-year service life is usually in the range of 0.7 - 0.9. This range is obtained by fitting the performance decay data of the device at different operating stages. If the deviation exceeds 0.1, it is determined that the health state of the device has decreased significantly. The currently calculated deviation is less than 0.1, and finally the device health deviation is obtained.

[0038] Please refer to Figure 6 , the dynamic alarm classification module includes: The key component parameter monitoring sub-module calls the device health deviation, combines the operating parameters of the device's key components, extracts the operating state parameters of the key components, calculates the ratio of each parameter deviating from the stable range, and obtains the device health state deviation ratio; The operating state parameter extraction sub-module calls the load impact information, extracts the current working state parameters of the device through the Internet of Things. During the extraction of the motor speed, the real-time data of the built-in speed sensor of the device is read, and the change amount per unit time is calculated. It is set that the motor speed of a certain medical monitoring device is 3000 revolutions per minute at time t and 2950 revolutions per minute at time t - 1. Then the calculated speed change rate is: revolutions per minute; During the extraction of signal fluctuations, the internal signal processing module of the device is used to perform mean filtering on the sensor signal, and the signal fluctuation range is calculated. It is set that within a 10-second time window, the collected signal fluctuation amplitude ranges from 2.1V to 2.5V. Then the calculated fluctuation range is: 2.5 - 2.1 = 0.4V; The threshold for signal fluctuations is set based on the stability standard of medical device signal transmission. The signal fluctuation should not exceed 5% of the rated signal amplitude. It is set that the rated signal amplitude is 10V. Then the threshold calculation is 10×0.05 = 0.5V. The currently calculated fluctuation range is 0.4V, which is lower than the set threshold, indicating that the signal change is still in the normal operating state. During the extraction of temperature changes, the data of the internal temperature sensor of the device is called, and the temperature change rate is calculated. It is set that the device temperature is 37.8℃ at time t and 37.5℃ at time t - 1. Then the calculated temperature change rate is: ; The reference value for temperature changes is set based on the long-term stable operating temperature of the device. The normal operating temperature of the core components of medical devices is generally controlled between 35℃ - 40℃. The reference value selects the optimal operating point of 37.5℃. When the temperature exceeds or is lower than this value, it will cause an increase in the load of the device's thermal management system. The currently measured temperature is 37.8℃, which is still within the allowable range. Finally, the calculated motor speed, signal fluctuation, and temperature change data are stored in the device status database to obtain the device working state parameter set.

[0039] The health status warning calculation sub-module calls the device health status deviation ratio and the device health deviation degree, and uses the formula: ; Perform operations to obtain the device health warning level value; Among them, represents the device health warning level value, represents the total number of health monitoring parameters, represents the warning influence coefficient of the d-th parameter, represents the current deviation value of the d-th parameter, represents the reference stable interval value of this parameter, represents the stability threshold of the d-th parameter, represents the health deviation degree weight coefficient, represents the device health deviation degree; The health index calculation sub-module calls the device working state parameter set and calculates the health index of the state parameters under the current load level, using the formula: ; Set the total number of monitoring parameters , set the importance coefficient of the motor speed , the current speed revolutions per minute, the reference health state value revolutions per minute, the tolerance threshold = 200 revolutions per minute, substitute into the calculation: ; The importance coefficient of the motor speed is set based on the operating stability of the device's core power unit. The key components of medical devices need to ensure a constant speed. The influence of the motor speed on the overall performance of the device accounts for about 40%. Therefore, the weight is set to 0.4. The tolerance threshold is set based on the maximum allowable fluctuation range of the motor. Usually, medical devices allow a fluctuation of ±5% of the rated speed. Set the rated speed to 4000 revolutions per minute, then calculate the tolerance threshold as 4000×0.05 = 200 revolutions per minute. Set the importance coefficient of the signal fluctuation , the current signal fluctuation amplitude , the reference value , the tolerance threshold , substitute into the calculation: ; The importance coefficient of the signal fluctuation is set based on the weight of the signal stability in the medical device monitoring. Signal anomalies will affect the data accuracy, and the proportion is set to 30%. The tolerance threshold is based on the medical signal processing error standard. Usually, it is set not to exceed 2% of the rated signal amplitude. Set the rated signal amplitude to 10V, then calculate the tolerance threshold as 10×0.02 = 0.2V. Set the importance coefficient of the temperature change , the current temperature , the reference value , the tolerance threshold , substitute into the calculation: ; The importance coefficient of temperature change is set to 0.3. According to the influence degree of the temperature control system of the medical device on the device stability, the tolerance threshold is set to 1°C. According to the temperature fluctuation range during the normal operation of the medical device, the temperature change within the range of ±1°C will not affect the device stability. Therefore, the tolerance threshold is set to 1°C, and calculate the health index: ; Finally, obtain the device health index.

[0040] The device alarm level acquisition sub-module calls the device health alarm level value, and compares and obtains the device dynamic alarm level according to the mapping rule between the device health status and the alarm level; The health deviation evaluation sub-module calls the device health index, and calculates the degree of deviation of the health index according to the normal health standard curve corresponding to the device usage years. When evaluating the health deviation degree, the device usage years is set to 5 years, and the device health standard curve is called. This curve defines the normal health index range under different usage years. For example, the health index interval corresponding to 5 years of usage years is set to , compare the current health index with this interval, and calculate the degree of deviation of the health index: deviation degree = 0.7 - 0.6468 = 0.0532; The health index reference value is set according to the health assessment standard provided by the device manufacturer. This standard is obtained by fitting the health status at the time of device factory and the long-term operation data. The set range of the health index corresponding to 5 years of usage years is 0.7 - 0.9. This interval is calculated from the historical performance data of the medical device under different operating environments. If the deviation degree exceeds 0.1, it is determined that the device health status has decreased significantly. The currently calculated deviation degree is less than 0.1, and finally obtain the device health deviation degree.

[0041] The above is only the preferred embodiment of the present invention, and it does not limit the present invention in other forms. Any person skilled in the art may use the disclosed technical content to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical content of the technical solution of the present invention, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention still belong to the protection scope of the technical solution of the present invention.

Claims

1. An intelligent early warning system for medical equipment based on the Internet of Things, characterized in that: The system comprises: The abnormal accumulation risk assessment module obtains the operation data of medical equipment through the Internet of Things, calculates the cumulative impact value of abnormal parameters per unit time, and calculates the slope of the equipment degradation trend based on the equipment operation time and workload level to obtain the long-term degradation rate prediction value; The core component degradation analysis module extracts the operating status parameters of the core components of the medical equipment based on the long-term degradation rate prediction value, screens the parameter group associated with the operating status fluctuation, calls the changing trend of the parameters in various operating stages, calculates the cumulative impact of the parameters in the equipment operation cycle, and obtains the degradation degree value of the core components; The workload analysis module calls the degradation degree value of the core component, monitors the workload level of the medical monitoring equipment, calculates the current workload level, obtains the parameter degradation degree values ​​under multiple load levels, calculates the impact of the current load state on the operation of the equipment, and obtains load impact information; The equipment health status monitoring module calls the load impact information, calculates the health index of the equipment under the current load level, calculates the degree of deviation of the health index based on the normal health standard curve, and obtains the equipment health deviation degree.

2. According to claim 1, the intelligent early warning system for medical equipment based on the Internet of Things is characterized in that: The long-term degradation rate prediction value is specifically the slope of the abnormal accumulation curve, the calculation result of the degradation impact weight, the long-term degradation trend fitting parameter, the dynamic inflection point detection calculation value and the equipment degradation trend slope. The core component degradation degree value includes the temperature rise rate change, the power consumption change amplitude cumulative value, the vibration frequency fluctuation range evaluation value and the parameter contribution value cumulative change rate. The load impact information is specifically the ECG signal processing power consumption fluctuation value, the blood oxygen sensor data update frequency change, the temperature control system power fluctuation value, the parameter degradation degree value calculation value under multiple load levels and the current load state influence coefficient. The equipment health deviation includes the motor speed deviation, the signal fluctuation abnormal amplitude, the temperature change deviation interval value, the health index calculation result and the health index deviation degree evaluation value.

3. According to claim 1, the intelligent early warning system for medical equipment based on the Internet of Things is characterized in that: The abnormal accumulation risk assessment module includes: The abnormal parameter analysis module obtains the operation data of medical equipment through the Internet of Things. The operation data includes X-ray tube current fluctuation, cooling system temperature change and rack vibration frequency. It calculates the change rate of each abnormal parameter per unit time, determines whether the parameter change exceeds the set threshold, screens the parameters that meet the abnormal standards, establishes the change trend curve of each abnormal parameter, and obtains the abnormal parameter trend data; The abnormal cumulative impact calculation module calls the abnormal parameter trend data, sets the degradation impact weight for each abnormal type, and calculates the cumulative impact value of each abnormal parameter in unit time using the formula: ； Calculate the cumulative impact value of each abnormal parameter to obtain the abnormal cumulative impact value; in, Represents the cumulative impact value of abnormalities per unit time, represents the degradation impact weight of the i-th abnormal parameter, represents the parameter value of the i-th abnormal parameter at time t, Representative time The parameter value of the i-th abnormal parameter at time, represents the time interval, and n represents the total number of abnormal parameters; The equipment degradation trend prediction module calls the abnormal cumulative impact value, combines the equipment operation time and workload level, calculates the contribution of the abnormal impact in the long-term degradation trend, fits the equipment long-term degradation curve, calculates the curve change rate, calculates the equipment degradation trend slope in combination with dynamic inflection point detection, and obtains the long-term degradation rate prediction value.

4. The medical equipment intelligent early warning system based on the Internet of Things according to claim 1 is characterized in that: The core component degradation analysis module includes: The operating state parameter extraction module extracts the operating state parameters of the core components of the medical device based on the long-term degradation rate prediction value, including the temperature rise rate, power consumption change amplitude and vibration frequency fluctuation range, calls the state record data within the equipment operation cycle, calculates the change rate of each parameter in multiple time periods, and obtains the operating state parameter data; The parameter correlation screening module calls the operating status parameter data, calculates the fluctuation range of each parameter, analyzes the change trend of each parameter, calculates the correlation between each parameter and the equipment operating status, screens the parameter group associated with the operating status fluctuation, and obtains the status fluctuation associated parameters; The core component degradation calculation module calls the state fluctuation associated parameters, and calculates the cumulative impact of the parameters during the equipment operation cycle according to the changing trends of the parameters in various operation stages of the equipment, using the formula: ; Calculate and obtain the degradation degree value of core components; in, Represents the degradation degree of the core component. represents the fluctuation amplitude of the jth state fluctuation associated parameter, represents the duration of action of the j-th state fluctuation associated parameter, represents the equipment load level corresponding to the jth state fluctuation associated parameter, Represents the baseline load level of the equipment, represents the running weight of the jth state fluctuation associated parameter, represents the reliability factor of the jth state fluctuation associated parameter, and N represents the total number of state fluctuation associated parameters.

5. The medical equipment intelligent early warning system based on the Internet of Things according to claim 1 is characterized in that: The workload analysis module includes: The workload monitoring submodule calls the degradation degree value of the core component to monitor the workload level of the medical monitoring equipment, including the power consumption of electrocardiogram signal processing, the frequency of updating blood oxygen sensor data and the power change of the temperature regulation system, and obtains the workload status parameters; The load level calculation submodule calls the workload state parameter using the formula: ； Calculate and obtain the current workload level value; in, Represents the current workload level value, Represents the total number of device components, represents the power consumption of the a-th device component, represents the operating frequency of the a-th device component, Represents the operation cycle of the a-th equipment component, represents the load variance of the a-th equipment component; The load impact assessment submodule calls the current workload level value, calculates the impact of the current load state on the equipment operation according to the parameter degradation degree values ​​under various load levels, and obtains load impact information.

6. The medical equipment intelligent early warning system based on the Internet of Things according to claim 1 is characterized in that: The equipment health status monitoring module includes: The operating state parameter extraction submodule calls the load impact information, extracts the current working state parameters of the device through the Internet of Things, including motor speed, signal fluctuation and temperature change, and obtains the device working state parameter set; The health index calculation submodule calls the equipment working status parameter set to calculate the health index of the status parameters under the current load level using the formula: ; Calculate and obtain the device health index; in, Represents the device health index, Represents the total number of monitored parameters, represents the importance coefficient of the kth parameter, represents the current state value of the kth parameter, represents the reference health status value of the kth parameter, Represents the tolerance threshold of the kth parameter; The health deviation assessment submodule calls the equipment health index, calculates the health index deviation degree according to the normal health standard curve corresponding to the equipment service life, and obtains the equipment health deviation degree.

7. The medical equipment intelligent early warning system based on the Internet of Things according to claim 1 is characterized in that: The system further comprises: The dynamic alarm classification module calls the equipment health deviation, combines the operating parameters of the key components of the equipment, calculates the alarm level under the current health state according to the ratio of each parameter deviation from the stable interval, and obtains the dynamic alarm level of the equipment; The dynamic alarm level of the equipment specifically refers to the abnormal power consumption deviation value, the current fluctuation over-limit ratio, the abnormal vibration amplitude detection value, the health score standard matching result and the alarm level classification judgment value.

8. The intelligent early warning system for medical equipment based on the Internet of Things according to claim 7 is characterized in that: The dynamic alarm classification module includes: The key component parameter monitoring submodule calls the equipment health deviation, combines the equipment key component operation parameters, extracts the key component operation status parameters, calculates the ratio of each parameter deviation from the stable interval, and obtains the equipment health status deviation ratio; The health status alarm calculation submodule calls the equipment health status deviation ratio and equipment health deviation degree, using the formula: ; Calculate and obtain the health warning level value of the device; in, Represents the health warning level of the device. Represents the total number of health monitoring parameters, Represents the alarm impact coefficient of the dth parameter, represents the current deviation value of the dth parameter, Represents the reference stable interval value of the parameter, represents the stability threshold of the dth parameter, represents the health deviation weight coefficient, Represents the health deviation of the equipment; The device alarm level acquisition submodule calls the device health alarm level value, and obtains the device dynamic alarm level by comparison according to the device health status and alarm level mapping rule.

Images