Uninterruptible power supply control method and system for shelter medical equipment

Abstract

The invention provides an uninterruptible power supply control method and system for shelter medical equipment. The method comprises the following steps: monitoring working state data and power supply parameters of shelter medical equipment in real time, and generating an equipment state report; according to the equipment importance and power consumption characteristics in the equipment state report, constructing a dynamic priority distribution model, and generating an optimized power distribution scheme; synchronously activating an event-driven remote alarm system based on the optimized power distribution scheme, and generating a comprehensive alarm information sending record; and the standby battery use condition in the comprehensive alarm information sending record is utilized to reduce the power consumption of non-key equipment, and a maintenance plan and a charging request record are generated. According to the technical scheme provided by the invention, power distribution can be dynamically adjusted, so that the power supply control effect of the shelter medical equipment is improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of power supply control technology, and in particular to an uninterruptible power supply control method and system for modular medical equipment. Background Art

[0002] Fangcang medical equipment plays an important role in emergency medical treatment, field rescue, temporary hospitals, etc. These scenarios usually face problems such as unstable power supply, a wide variety of equipment and large differences in power consumption.

[0003] At present, the power management system of medical equipment in Fangcang Hospital mainly relies on a simple threshold alarm mechanism. These systems usually pre-set the power allocation ratio of each device and allocate power according to a fixed priority order when the power supply is insufficient. At the same time, some predefined thresholds are set to trigger alarms and notify relevant personnel to handle them.

[0004] However, the existing threshold alarm mechanism can only trigger the alarm when the preset conditions are met. It is unable to monitor in real time and quickly respond to abnormal power supply conditions, which may lead to delayed fault handling and increase patient risks. The existing system mainly relies on manual inspection and experience judgment for the management and maintenance of backup batteries, lacks scientific evaluation and prediction methods, and is difficult to detect battery aging and performance degradation problems in a timely manner, increasing maintenance costs and failure risks. Summary of the invention

[0005] The embodiments of the present application provide an uninterruptible power supply control method and system for modular medical equipment, which are used to solve the problem of poor power supply control effect in the prior art.

[0006] In a first aspect, an embodiment of the present application provides an uninterruptible power supply control method for a modular medical device, comprising:

[0007] Monitor the working status data and power supply parameters of the medical equipment in the shelter in real time and generate equipment status reports;

[0008] According to the importance and power consumption characteristics of the equipment in the equipment status report, a dynamic priority allocation model is constructed, the power allocation ratio of each medical equipment is adjusted in real time using a fuzzy logic controller, the energy consumption strategy of non-critical equipment is optimized through a linear programming algorithm, and an optimized power allocation plan is generated;

[0009] Based on the optimized power distribution scheme, the event-driven remote alarm system is synchronously activated, and the comprehensive alarm information is sent to the remote monitoring center and the preset emergency response team through a secure channel using an encrypted communication protocol, and a comprehensive alarm information sending record is generated;

[0010] The backup battery usage in the comprehensive alarm information sending record is used to regularly evaluate the health status and charging efficiency of the backup battery through a machine learning algorithm, a battery aging model is established to predict future battery performance trends, internal loads are coordinated through an intelligent scheduling algorithm, power consumption of non-critical equipment is reduced, and maintenance plans and charging request records are generated.

[0011] Optionally, the dynamic priority allocation model is constructed according to the importance and power consumption characteristics of the equipment in the equipment status report, the power allocation ratio of each medical device is adjusted in real time by using a fuzzy logic controller, the energy consumption strategy of non-critical equipment is optimized by a linear programming algorithm, and an optimized power allocation plan is generated, including:

[0012] By using real-time monitoring of the working status data and power supply parameters of all medical equipment in the shelter, the collected relevant data are pre-processed to obtain the equipment status report;

[0013] Based on the importance and power consumption characteristics of the equipment in the equipment status report, defining evaluation criteria, evaluating the importance of each medical equipment, and generating a dynamic priority allocation model taking into account the power consumption characteristics of the equipment;

[0014] The dynamic priority allocation model is used to integrate the model into a fuzzy logic controller, and the power allocation ratio is automatically adjusted according to the real-time power supply situation and the equipment priority to obtain the power allocation ratio adjustment result;

[0015] Based on the power distribution ratio adjustment result, a linear programming algorithm is used to optimize the energy consumption strategy of non-critical equipment to ensure that the power supply of critical equipment is not affected, while reducing the overall energy consumption and generating an energy consumption optimization strategy;

[0016] The power distribution ratio adjustment result and the energy consumption optimization strategy are combined to generate an optimized power distribution plan.

[0017] Optionally, based on the power distribution ratio adjustment result, a linear programming algorithm is used to optimize the energy consumption strategy of non-critical equipment to ensure that the power supply of critical equipment is not affected while reducing the overall energy consumption, and generating an energy consumption optimization strategy, including:

[0018] The total energy consumption after calculation optimization is E opt Previously, it was necessary to collect and preprocess the real-time power consumption and operating time data of non-critical devices, evaluate the power consumption fluctuations, and consider the nonlinear impact when the power consumption is close to the maximum value, laying the foundation for optimization calculations;

[0019] Energy consumption optimization formula for non-critical equipment:

[0020]

[0021] Among them, Eopt is the total energy consumption after optimization, N is the number of non-critical devices, P i is the current power consumption of the i-th non-critical device, t i is the operating time of the i-th non-critical device, λ is the penalty coefficient used to balance power consumption and power consumption fluctuation, P min,i is the minimum power consumption of the i-th non-critical device, β is an additional penalty coefficient used to consider the nonlinear effect when the power consumption is close to the maximum value, P max,i is the maximum power consumption of the ith non-critical device;

[0022] After calculating the total energy consumption E opt Finally, it is necessary to collect the current power consumption and operating time data of key equipment and calculate the power supply security degree S of key equipment. key And by introducing weight coefficients, we ensure the stable and reliable power supply of key equipment;

[0023] Formula for ensuring power supply to key equipment:

[0024]

[0025] Among them, S key is the power supply security of key equipment, M is the number of key equipment, P key,j is the current power consumption of the jth key device, t key,j is the operating time of the jth key device, P req,j is the required power consumption of the jth key device, α is the weight coefficient used to balance the power consumption requirement and actual power consumption of the key device; P k represents the current power consumption of the kth device; t k represents the running time of the kth device; N represents the total number of all devices;

[0026] After calculating the power supply security of key equipment S key After that, the comprehensive calculation E opt and S key , generate the final energy consumption optimization strategy, formulate a specific implementation plan, and generate a detailed energy consumption optimization strategy report.

[0027] Optionally, the step of defining an evaluation standard based on the importance and power consumption characteristics of the equipment in the equipment status report, evaluating the importance of each medical equipment, and generating a dynamic priority allocation model by considering the power consumption characteristics of the equipment includes:

[0028] Analyze the importance and power consumption characteristics of the equipment using the information in the equipment status report, define evaluation criteria, and obtain evaluation criteria;

[0029] According to the evaluation criteria, the importance of each medical device is evaluated, and an importance score is assigned to each device to obtain a device importance score;

[0030] Considering the power consumption characteristics of the devices and combining the importance scores of the devices, a preliminary priority allocation table is generated;

[0031] Based on the preliminary priority allocation table, a dynamic priority adjustment rule is designed to appropriately reduce the priority of key equipment when the power supply is sufficient to optimize the overall energy consumption, thereby obtaining a dynamic priority adjustment rule;

[0032] The preliminary priority allocation table and the dynamic priority adjustment rule are integrated into a dynamic priority allocation model. The dynamic priority allocation model has the ability to automatically adjust the priority when the power supply is tight, and considers the interdependence between devices to generate a dynamic priority allocation model.

[0033] Optionally, the dynamic priority allocation model is integrated into a fuzzy logic controller to automatically adjust the power allocation ratio according to the real-time power supply situation and the device priority to obtain the power allocation ratio adjustment result, including:

[0034] Using the dynamic priority allocation model, the model is integrated into a fuzzy logic controller to obtain an integrated fuzzy logic controller;

[0035] In the integrated fuzzy logic controller, input variables are set, output variables are defined, and input and output configurations of the fuzzy logic controller are generated;

[0036] Based on the input and output configuration of the fuzzy logic controller, a membership function and a fuzzy rule base are set to describe the relationship between the input variables and the output variables, and a fuzzy rule base is generated;

[0037] Through the fuzzy rule base, a fuzzy reasoning process is performed according to the real-time power supply situation and equipment priority, and the power distribution ratio is automatically adjusted to obtain the power distribution ratio adjustment result.

[0038] Optionally, the backup battery usage in the comprehensive alarm information sending record is used to regularly evaluate the health status and charging efficiency of the backup battery through a machine learning algorithm, establish a battery aging model to predict future battery performance trends, coordinate internal loads through an intelligent scheduling algorithm, reduce power consumption of non-critical equipment, and generate a maintenance plan and charging request record, including:

[0039] Utilizing the backup battery usage in the comprehensive alarm information sending record, collecting historical data of the backup battery, regularly evaluating the health status and charging efficiency of the backup battery through a machine learning algorithm, and generating a backup battery health status and charging efficiency evaluation report;

[0040] Based on the health status and charging efficiency evaluation report of the backup battery, a battery aging model is established, and the performance trend of the battery in the future is predicted using a time series analysis or regression analysis method to generate a battery performance trend prediction report;

[0041] Using the battery performance trend forecast report, combined with the current power supply situation and equipment priority, an intelligent scheduling algorithm is designed to reduce the power consumption of non-critical equipment by dynamically adjusting the internal load and generate an internal load adjustment plan;

[0042] Based on the internal load adjustment scheme, a maintenance plan for the backup battery is formulated, a charging request record is generated, and a final maintenance plan and charging request record are generated.

[0043] Optionally, the use of the backup battery in the comprehensive alarm information sending record is used to collect historical data of the backup battery, and the health status and charging efficiency of the backup battery are regularly evaluated by a machine learning algorithm to generate a health status and charging efficiency evaluation report of the backup battery, including:

[0044] Collect and pre-process the current capacity, discharge depth and internal resistance of the backup batteries, and assign appropriate weights to each backup battery to ensure data consistency and accuracy;

[0045] The backup battery health status is calculated using the following backup battery health status assessment formula:

[0046]

[0047] Where H(t) is the health status of the backup battery at time t, N is the number of backup batteries, and w i is the weight of the ith backup battery, C i (t) is the current capacity of the ith backup battery at time t, C min,i is the minimum capacity of the ith backup battery, C max,i is the maximum capacity of the ith backup battery, γ i is the additional weight of the ith backup battery, D i (t) is the discharge depth of the ith backup battery at time t, D max, is the maximum discharge depth of the ith backup battery, δ i is the resistance weight of the ith backup battery, R i (t) is the internal resistance of the ith backup battery at time t, Rmax, is the maximum internal resistance of the ith backup battery;

[0048] After calculating the health status H(t) of the backup battery, the charge capacity, temperature and voltage data of the backup battery are collected and preprocessed, and the charging efficiency E(t) of each backup battery is calculated by introducing a weight coefficient to ensure the comprehensiveness of the evaluation results;

[0049] Backup battery charging efficiency evaluation formula:

[0050]

[0051] Where E(t) is the charging efficiency of the backup battery at time t, η is the weight coefficient of the charging efficiency, and Q i (t) is the charge capacity of the ith backup battery at time t, O max,i is the maximum charge capacity of the ith backup battery, β is the weight coefficient of temperature influence, T i (t) is the temperature of the ith backup battery at time t, T min,i is the minimum temperature of the ith backup battery, T max,i is the maximum temperature of the ith backup battery, θ i is the voltage weight of the ith backup battery, V i (t) is the voltage of the ith backup battery at time t, V min,i is the lowest voltage of the ith backup battery, V max,i is the maximum voltage of the ith backup battery;

[0052] After calculating the charging efficiency E(t) of the backup battery, the results of H(t) and E(t) are combined to generate a health status and charging efficiency evaluation report of the backup battery.

[0053] Optionally, the battery performance trend forecast report is used in combination with the current power supply situation and device priority to design an intelligent scheduling algorithm, reduce the power consumption of non-critical devices by dynamically adjusting the internal load, and generate an internal load adjustment plan, including:

[0054] Using the battery performance trend forecast report, combined with current power supply conditions and equipment priorities, an intelligent scheduling algorithm is designed to generate an intelligent scheduling algorithm;

[0055] In the intelligent scheduling algorithm, input variables are set, output variables are defined, and an intelligent scheduling algorithm is generated;

[0056] Through the intelligent scheduling algorithm, the internal load is dynamically adjusted according to the input variables and the preset optimization goals, the power consumption of non-critical equipment is reduced, the power supply of critical equipment is ensured not to be affected, and the load adjustment strategy is generated;

[0057] The intelligent scheduling algorithm calculates the power distribution ratio and specific load adjustment measures of each device according to the input variables and the load adjustment strategy, and generates an internal load adjustment plan.

[0058] Optionally, based on the optimized power distribution scheme, an event-driven remote alarm system is synchronously activated, and the comprehensive alarm information is sent to the remote monitoring center and the preset emergency response team through a secure channel using an encrypted communication protocol, and a comprehensive alarm information sending record is generated, including:

[0059] Based on the optimized power distribution scheme, the power distribution situation and the equipment operation status are monitored in real time, and when an abnormal situation is detected, an event-driven remote alarm system is triggered to generate an alarm trigger signal;

[0060] Utilize the alarm trigger signal to collect relevant comprehensive alarm information, use the encrypted communication protocol to send the comprehensive alarm information to the remote monitoring center through a secure channel, and generate an alarm information sending record;

[0061] Based on the alarm information sending record, the comprehensive alarm information is sent to a preset emergency response team through the same secure channel to generate an alarm information sending record of the emergency response team;

[0062] Record the entire alarm information sending process and generate a comprehensive alarm information sending record.

[0063] In a second aspect, an embodiment of the present application provides an uninterruptible power supply control system for a modular medical device, comprising:

[0064] The monitoring module is used to monitor the working status data and power supply parameters of the medical equipment in the shelter in real time and generate equipment status reports;

[0065] A construction module is used to construct a dynamic priority allocation model according to the importance and power consumption characteristics of the equipment in the equipment status report, use a fuzzy logic controller to adjust the power allocation ratio of each medical device in real time, optimize the energy consumption strategy of non-critical equipment through a linear programming algorithm, and generate an optimized power allocation plan;

[0066] A sending module is used to synchronously activate the event-driven remote alarm system based on the optimized power distribution plan, send the comprehensive alarm information to the remote monitoring center and the preset emergency response team through a secure channel using an encrypted communication protocol, and generate a comprehensive alarm information sending record;

[0067] An evaluation module is used to utilize the backup battery usage in the comprehensive alarm information sending record, regularly evaluate the health status and charging efficiency of the backup battery through a machine learning algorithm, establish a battery aging model to predict future battery performance trends, coordinate internal loads through an intelligent scheduling algorithm, reduce power consumption of non-critical equipment, and generate maintenance plans and charging request records.

[0068] In an embodiment of the present application, the working status data and power supply parameters of the modular medical equipment are monitored in real time to generate an equipment status report; based on the equipment importance and power consumption characteristics in the equipment status report, a dynamic priority allocation model is constructed, and the power allocation ratio of each medical device is adjusted in real time using a fuzzy logic controller, and the energy consumption strategy of non-critical equipment is optimized through a linear programming algorithm to generate an optimized power allocation plan; based on the optimized power allocation plan, an event-driven remote alarm system is synchronously activated, and an encrypted communication protocol is used to send the comprehensive alarm information through a secure channel to a remote monitoring center and a preset emergency response team, and a comprehensive alarm information sending record is generated; using the backup battery usage in the comprehensive alarm information sending record, the health status and charging efficiency of the backup battery are regularly evaluated through a machine learning algorithm, a battery aging model is established to predict future battery performance trends, and an intelligent scheduling algorithm is used to coordinate internal loads to reduce the power consumption of non-critical equipment, and a maintenance plan and charging request record are generated.

[0069] The technical solution of this application has the following beneficial effects:

[0070] This application can detect power supply anomalies or equipment failures in a timely manner by real-time monitoring of the working status data and power supply parameters of the medical equipment in the square cabin, so as to take measures quickly to ensure the safety and reliability of power use. A dynamic priority allocation model is constructed, and the power allocation ratio of each medical device is adjusted in real time in combination with a fuzzy logic controller to ensure that critical medical equipment can obtain the necessary power support under any circumstances. At the same time, the energy consumption strategy of non-critical equipment is optimized through a linear programming algorithm to improve the overall utilization efficiency of power resources. Based on the optimized power distribution scheme, the event-driven remote alarm system is synchronously activated, which can quickly transmit alarm information to the remote monitoring center and the emergency response team, shorten the response time, and improve the efficiency of emergency handling. The health status and charging efficiency of the backup battery are regularly evaluated through a machine learning algorithm, and a battery aging model is established to predict future battery performance trends. This not only helps to detect potential power supply risks in advance, but also coordinates internal loads through intelligent scheduling algorithms to effectively extend the service life of the equipment.

[0071] Furthermore, the present application constructs a dynamic priority allocation model by preprocessing the collected data, generating a device status report, and defining evaluation criteria based on the importance and power consumption characteristics of the equipment. This process makes power distribution more rational and can better adapt to changes in demand in different scenarios. The dynamic priority allocation model is integrated into the fuzzy logic controller to achieve automatic adjustment of the power distribution ratio. This method not only reduces the need for human intervention, but also improves the accuracy and immediacy of the adjustment, further ensuring the rationality of power distribution. The linear programming algorithm is used to optimize the energy consumption strategy of non-critical equipment to ensure that the normal operation of critical medical equipment is not affected under limited power resources. This is crucial to maintaining the quality of medical services, especially in emergency situations or resource constraints. Through the above measures, not only the utilization efficiency of power resources is improved, but also unnecessary energy waste is effectively reduced, which is in line with the concept of green development and is conducive to reducing operating costs and environmental protection.

[0072] Furthermore, based on the optimized power distribution scheme, the present application monitors the power distribution situation and equipment operating status in real time to ensure the stable operation of the system. Utilize the alarm trigger signal to collect relevant comprehensive alarm information, including event type, occurrence time, affected equipment and detailed information, to ensure the integrity and accuracy of the information. Generate an alarm information sending record, record the sending time, recipient and sending status, to ensure the transparency and traceability of information sending. Record the entire alarm information sending process, and generate a comprehensive alarm information sending record, including event type, occurrence time, affected equipment, detailed information, sending time, recipient and sending status, to ensure the integrity and traceability of the information, and facilitate subsequent audits and responsibility tracing.

[0073] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0075] Figure 1 A flow chart of an uninterruptible power supply control method for a modular medical device provided in an embodiment of the present application;

[0076] Figure 2 A schematic diagram of the structure of an uninterruptible power supply control system for modular medical equipment provided in an embodiment of the present application. DETAILED DESCRIPTION

[0077] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0078] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0079] Figure 1 A flowchart of an uninterruptible power supply control method for a modular medical device is provided for an embodiment of the present application. Figure 1 As shown, the method includes:

[0080] 101. Monitor the working status data and power supply parameters of the medical equipment in the shelter in real time and generate equipment status reports;

[0081] This step refers to the continuous collection of equipment operation data (i.e., working status data) and various indicators of the power supply system (i.e., power supply parameters) through sensors and monitoring devices installed on the modular medical equipment.

[0082] Among them, the working status data includes the equipment's operating mode (such as power on, standby, fault, etc.), operating temperature, equipment load, etc., which are used to evaluate the current operating status of the equipment. Power supply parameters include current, voltage, frequency, power factor, etc., which are used to evaluate the quality and stability of power supply. The equipment status report is a detailed report generated after processing and analyzing the above collected data. It is used to reflect the real-time working status and energy efficiency performance of the shelter medical equipment, and provide a basis for subsequent power management and equipment maintenance.

[0083] Suppose that in a certain shelter hospital, a comprehensive monitoring system is installed to ensure the stable operation of medical equipment and the safety and reliability of power supply. The system collects the working status data and power supply parameters of the equipment in real time by installing sensors such as current transformers, voltage sensors, temperature sensors, etc. at key parts of each medical device and power supply system. Specifically, the sensor sends data to the central control system every few seconds, including the equipment's operating mode (such as power on, standby, fault), operating temperature, equipment load, and the current, voltage, frequency and power factor of the power supply. After receiving this data, the central control system performs real-time analysis and processing to generate detailed equipment status reports. These reports not only show the current working status data and power supply of each device, but also identify potential problems such as equipment overheating and current abnormality. Operators can view these reports through a visual interface and take timely measures based on the information in the report to ensure the normal operation of medical equipment and the stability of power supply. In addition, these status reports are saved regularly as an important reference for equipment maintenance and power management.

[0084] 102. According to the importance and power consumption characteristics of the equipment in the equipment status report, a dynamic priority allocation model is constructed, the power allocation ratio of each medical device is adjusted in real time using a fuzzy logic controller, the energy consumption strategy of non-critical equipment is optimized through a linear programming algorithm, and an optimized power allocation plan is generated;

[0085] This step refers to first extracting the importance and power consumption characteristic data of each medical device from the device status report. Then, based on these data, a dynamic priority allocation model is constructed, which can dynamically determine the priority of each device according to the importance of the device and the current power consumption. Next, the fuzzy logic controller is used to automatically adjust the power allocation ratio of each medical device according to the real-time monitored power supply and device priority to ensure that critical devices always have sufficient power supply. Finally, the energy consumption strategy of non-critical devices is optimized through a linear programming algorithm to reduce the power consumption of non-critical devices, thereby generating an optimized power allocation plan to ensure the efficient use of overall power resources.

[0086] Among them, the importance of equipment refers to the level of assessment based on the role and irreplaceability of the equipment in the medical treatment process, which is used to determine which equipment should be given priority in power supply when power resources are limited. Power consumption characteristics refer to the energy consumption characteristics of equipment under different working conditions, which is an important basis for evaluating equipment energy efficiency and formulating energy consumption optimization strategies. Among them, key equipment refers to equipment that is crucial to the patient's life safety and treatment effect, such as ventilators, ECG monitors, etc. Non-critical equipment refers to equipment that has little impact on the patient's life safety and treatment effect, such as office computers, printers, etc.

[0087] Optionally, in step 102, a dynamic priority allocation model is constructed according to the importance and power consumption characteristics of the equipment in the equipment status report, a fuzzy logic controller is used to adjust the power allocation ratio of each medical device in real time, and the energy consumption strategy of non-critical equipment is optimized by a linear programming algorithm to generate an optimized power allocation plan, including: using real-time monitoring of the working status data and power supply parameters of all medical equipment in the cabin, pre-processing the collected relevant data to obtain an equipment status report; defining evaluation criteria according to the importance and power consumption characteristics of the equipment in the equipment status report, evaluating the importance of each medical device, considering the power consumption characteristics of the equipment, and generating a dynamic priority allocation model; using the dynamic priority allocation model, integrating the model into the fuzzy logic controller, automatically adjusting the power allocation ratio according to the real-time power supply situation and equipment priority, and obtaining a power allocation ratio adjustment result; based on the power allocation ratio adjustment result, using a linear programming algorithm to optimize the energy consumption strategy of non-critical equipment, ensuring that the power supply of critical equipment is not affected, while reducing overall energy consumption, and generating an energy consumption optimization strategy; combining the power allocation ratio adjustment result and the energy consumption optimization strategy to generate an optimized power allocation plan.

[0088] Among them, based on the device importance and power consumption characteristics in the device status report, the evaluation criteria are defined, the importance of each medical device is evaluated, the power consumption characteristics of the device are considered, and a dynamic priority allocation model is generated, including: using the information in the device status report to analyze the device importance and power consumption characteristics, define the evaluation criteria, and obtain the evaluation criteria; based on the evaluation criteria, the importance of each medical device is evaluated, and an importance score is assigned to each device to obtain the device importance score; considering the power consumption characteristics of the device and combining the device importance score, a preliminary priority allocation table is generated; based on the preliminary priority allocation table, dynamic priority adjustment rules are designed to appropriately reduce the priority of key devices when the power supply is sufficient to optimize the overall energy consumption, and obtain dynamic priority adjustment rules; the preliminary priority allocation table and the dynamic priority adjustment rules are integrated into a dynamic priority allocation model, and the dynamic priority allocation model has the ability to automatically adjust the priority when the power supply is tight, and the interdependence between devices is considered to generate a dynamic priority allocation model.

[0089] Among the above options, the fuzzy logic controller is a control method that can handle uncertainty and fuzziness. It adjusts the output according to preset rules and membership functions of input variables, and is suitable for systems that need to respond flexibly to changing conditions.

[0090] Linear programming algorithm is a mathematical optimization technique that finds the optimal value of a set of variables by minimizing or maximizing the objective function while satisfying a given series of linear constraints. It is often used in fields such as resource allocation and production planning.

[0091] In the embodiment of the present application, first, by real-time monitoring of the working status data and power supply parameters of all medical devices in the shelter, the collected data is pre-processed to form an equipment status report. Then, based on the information in the equipment status report, the importance and power consumption characteristics of the equipment are analyzed, a set of evaluation criteria are defined, and the importance of each medical device is evaluated accordingly, and an importance score is assigned to each device, thereby generating a preliminary priority allocation table.

[0092] Then, based on the preliminary priority allocation table, dynamic priority adjustment rules are designed, which can appropriately reduce the priority of key devices when the power supply is sufficient to optimize the overall energy consumption. Next, these rules are integrated with the preliminary priority allocation table to construct a dynamic priority allocation model that can automatically adapt to changes in power supply.

[0093] Finally, the fuzzy logic controller is used to adjust the power distribution ratio of each medical device in real time, and the energy consumption strategy of non-critical equipment is further optimized through the linear programming algorithm to ensure that the power supply of critical equipment is not affected while reducing the overall energy consumption, and finally generate an optimized power distribution plan.

[0094] Assume that in a shelter hospital, there are the following medical equipment: ventilator, ECG monitor, ultrasound equipment and infusion pump. The specific implementation steps are as follows:

[0095] Sensors and monitoring equipment are used to collect real-time working status data and power supply parameters of all medical equipment in the cabin, including the operating status, temperature, current, voltage, power, etc. of the equipment; for example, the current of the ventilator is 2A, the voltage is 220V, and the power is 440W; the current of the ECG monitor is 0.5A, the voltage is 110V, and the power is 55W.

[0096] The collected data is transmitted to the central processing unit through the data acquisition module for data cleaning and formatting to generate a device status report; based on the information in the device status report, the importance and power consumption characteristics of the device are analyzed and evaluation criteria are defined; for example, the importance score ranges from 1 to 100, and the power consumption characteristic score ranges from 1 to 100; based on the defined evaluation criteria, the importance of each medical device is evaluated and an importance score is assigned to each device; for example, the importance score of the ventilator is 90, the importance score of the ECG monitor is 85, the importance score of the ultrasound device is 70, and the importance score of the infusion pump is 60; considering the power consumption characteristics of the equipment and combining the equipment importance score, a preliminary priority allocation table is generated.

[0097] For example, the preliminary priority allocation table is as follows:

[0098] Ventilator: Priority score 90, initial power allocation ratio 30%;

[0099] ECG monitor: priority score 85, initial power allocation ratio 25%;

[0100] Ultrasonic equipment: priority score 70, initial power allocation ratio 20%;

[0101] Infusion pump: priority score 60, initial power allocation ratio 15%;

[0102] Based on the preliminary priority allocation table, dynamic priority adjustment rules are designed; for example, when the power supply is sufficient, the priority of key equipment is appropriately lowered to optimize the overall energy consumption; if the power supply is sufficient, the priority score of the ventilator is reduced to 85, and the power allocation ratio is adjusted to 28%; if the power supply is tight, the priority of key equipment is increased; the priority score of the ventilator is increased to 95, and the power allocation ratio is adjusted to 35%; the priority score of the ECG monitor is increased to 90, and the power allocation ratio is adjusted to 30%.

[0103] The preliminary priority allocation table and dynamic priority adjustment rules are integrated into a dynamic priority allocation model; the dynamic priority allocation model has the ability to automatically adjust the priority when the power supply is tight, taking into account the interdependence between devices and ensuring the power supply of key equipment.

[0104] For example, the dynamic priority allocation model is as follows:

[0105] Ventilator: Priority score 90 (priority score drops to 85 when power supply is sufficient, otherwise the priority score increases to 95), power allocation ratio 30% (power allocation ratio is adjusted to 28% when power supply is sufficient, otherwise the power allocation ratio is adjusted to 35%);

[0106] ECG monitor: priority score 85 (priority score drops to 80 when power supply is sufficient, otherwise the priority score increases to 90), power allocation ratio 25% (power allocation ratio is adjusted to 22% when power supply is sufficient, otherwise the power allocation ratio is adjusted to 30%);

[0107] Ultrasonic equipment: priority score 70, power allocation ratio 20%;

[0108] Infusion pump: priority score 60, power allocation ratio 15%;

[0109] Through this series of steps, the power management system of the Fangcang Cabin Hospital can dynamically adjust power distribution according to the importance and power consumption characteristics of the equipment, ensure the power supply of key equipment, optimize the energy consumption of non-key equipment, and improve the overall power utilization efficiency.

[0110] Optionally, the dynamic priority allocation model is used to integrate the model into a fuzzy logic controller, and the power allocation ratio is automatically adjusted according to the real-time power supply situation and the equipment priority to obtain the power allocation ratio adjustment result, including: using the dynamic priority allocation model, integrating the model into the fuzzy logic controller to obtain an integrated fuzzy logic controller; in the integrated fuzzy logic controller, setting input variables, defining output variables, and generating the input and output configuration of the fuzzy logic controller; based on the input and output configuration of the fuzzy logic controller, setting membership functions and fuzzy rule bases to describe the relationship between input variables and output variables, and generating a fuzzy rule base; through the fuzzy rule base, performing a fuzzy reasoning process according to the real-time power supply situation and the equipment priority, automatically adjusting the power allocation ratio, and obtaining the power allocation ratio adjustment result.

[0111] Suppose in a square cabin hospital, there are the following medical equipment: ventilator, ECG monitor, ultrasound equipment and infusion pump.

[0112] The following steps will be used to integrate the dynamic priority allocation model into the fuzzy logic controller to automatically adjust the power allocation ratio as shown below:

[0113] Ventilator: current 2A, voltage 220V, power 440W, operating status normal;

[0114] ECG monitor: current 0.5A, voltage 110V, power 55W, operating status normal;

[0115] Ultrasonic equipment: current 1.5A, voltage 220V, power 330W, operating status normal;

[0116] Infusion pump: current 0.3A, voltage 110V, power 33W, operating status normal;

[0117] Further, clean and format the data to ensure data accuracy and consistency; generate equipment status reports, including equipment operating status, current, voltage, power and other information; ventilator: importance score 90, maximum power consumption 440W, minimum power consumption 110W; ECG monitor: importance score 85, maximum power consumption 55W, minimum power consumption 10W; ultrasound equipment: importance score 70, maximum power consumption 330W, minimum power consumption 80W; infusion pump: importance score 60, maximum power consumption 33W, minimum power consumption 5W; ventilator: priority score 90, initial power allocation ratio 30%; ECG monitor: priority score 85, initial power allocation ratio 25%; ultrasound equipment: priority score 70, initial power allocation ratio 20%; infusion pump: priority score 60, initial power allocation ratio 15%;

[0118] The preliminary priority allocation table and dynamic priority adjustment rules are integrated into the fuzzy logic controller to obtain the integrated fuzzy logic controller; the current power supply situation (such as total power supply, remaining power supply, etc.); generate input and output configurations; automatically adjust the power allocation ratio; optimize the energy consumption strategy of non-critical equipment; optimization goal: minimize the overall energy consumption while ensuring the power supply of critical equipment; the power supply of critical equipment must meet its minimum power consumption requirements; the total power supply cannot exceed the current power supply capacity.

[0119] Through this series of steps, the power management system of the Fangcang Cabin Hospital can dynamically adjust power distribution according to the importance and power consumption characteristics of the equipment, ensure the power supply of key equipment, optimize the energy consumption of non-key equipment, and improve the overall power utilization efficiency.

[0120] This application takes into account that in the power management system of the Fangcang Hospital, in order to ensure that the power supply of key equipment is not affected and reduce overall energy consumption, it is necessary to optimize the energy consumption of non-critical equipment. This goal can be effectively achieved through a linear programming algorithm. During the optimization process, not only the current power consumption and operating time of non-critical equipment should be considered, but also the nonlinear effects of power consumption fluctuations and power consumption close to the maximum value should be considered to ensure the accuracy and reliability of the optimization results.

[0121] Optionally, based on the power distribution ratio adjustment result, a linear programming algorithm is used to optimize the energy consumption strategy of non-critical equipment to ensure that the power supply of critical equipment is not affected while reducing the overall energy consumption, and generating an energy consumption optimization strategy, including:

[0122] The total energy consumption after calculation optimization is E opt Previously, it was necessary to collect and preprocess the real-time power consumption and operating time data of non-critical devices, evaluate the power consumption fluctuations, and consider the nonlinear impact when the power consumption is close to the maximum value, laying the foundation for optimization calculations;

[0123] Energy consumption optimization formula for non-critical equipment:

[0124]

[0125] Among them, E opt is the total energy consumption after optimization, N is the number of non-critical devices, P i is the current power consumption of the i-th non-critical device, t i is the operating time of the i-th non-critical device, λ is the penalty coefficient used to balance power consumption and power consumption fluctuation, P min,i is the minimum power consumption of the i-th non-critical device, β is an additional penalty coefficient used to consider the nonlinear effect when the power consumption is close to the maximum value, P max, i is the maximum power consumption of the i-th non-critical device;

[0126] After calculating the total energy consumption E opt Finally, it is necessary to collect the current power consumption and operating time data of key equipment and calculate the power supply security degree S of key equipment. key And by introducing weight coefficients, we ensure the stable and reliable power supply of key equipment;

[0127] Formula for ensuring power supply to key equipment:

[0128]

[0129] Among them, S key is the power supply security of key equipment, M is the number of key equipment, P key,j is the current power consumption of the jth key device, t key,j is the operating time of the jth key device, P req,j is the required power consumption of the jth key device, α is the weight coefficient used to balance the power consumption requirement and actual power consumption of the key device; P k represents the current power consumption of the kth device; t k represents the running time of the kth device; N represents the total number of all devices;

[0130] After calculating the power supply security of key equipment S key After that, the comprehensive calculation E opt and S key , generate the final energy consumption optimization strategy, formulate a specific implementation plan, and generate a detailed energy consumption optimization strategy report.

[0131] This formula is designed to ensure that key equipment is vital to the patient's life safety and treatment effect, so the stability and reliability of its power supply must be ensured; by optimizing the energy consumption of non-critical equipment, the overall power consumption can be reduced and energy utilization efficiency can be improved; power consumption fluctuations and nonlinear effects when approaching the maximum value will have a significant impact on the optimization results, so they need to be considered in the optimization formula.

[0132] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0133]

[0134] Energy consumption optimization formula E in non-critical equipment opt In, P i ·t i is the current power consumption of non-critical equipment multiplied by the running time, which represents the energy consumption of the equipment; λ·(P i -P min,i ) 2 represents the penalty term, which is used to balance power consumption and power consumption fluctuation to prevent excessive power consumption fluctuation; is an additional penalty term used to consider the nonlinear effect when the power consumption is close to the maximum value and to prevent the device from overloading.

[0135] The following is a brief introduction to how to obtain the parameters of the formula:

[0136] Among them, the current power consumption P i and running time t i Real-time data collection of non-critical equipment through sensors and monitoring equipment; min,i and P max,i The minimum power consumption and maximum power consumption of each non-critical device are obtained from the technical specification of the device; the penalty coefficients λ and β are determined appropriately through experiments and empirical data.

[0137] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0138]

[0139] The formula for ensuring the power supply of key equipment is S key middle, It is the ratio of the current power consumption and operation time of key equipment to the total power consumption, indicating the power supply security of key equipment; It is a penalty item used to balance the power consumption requirements and actual power consumption of key equipment to ensure stable and reliable power supply of key equipment.

[0140] The following is a brief introduction to how to obtain the parameters of the formula:

[0141] Where Pkey,i and running time t key,j Through sensors and monitoring equipment to collect key equipment in real time; req,j The required power consumption of each key device is obtained from the technical specification of the device; the weight coefficient α is determined through experiments and empirical data.

[0142] Suppose in a square cabin hospital, there are the following equipment:

[0143] Office computer: Current power consumption P1 = 100W, running time t1 = 8 hours, minimum power consumption P min,1 =50W, maximum power consumption P max,1 =150W; Printer: Current power consumption P2 = 50W, running time t2 = 4 hours, minimum power consumption P min,2 =20W, maximum power consumption P max,2 =100W; ECG monitor: current power consumption P key,2 =55W, running time t key,2 = 24 hours, power consumption required P req,2 =55W; λ=0.1, β=0.01; α=0.5; Office computer: P1=100W, t1=8 hours; Printer: P2=50W, t2=4 hours;

[0144]

[0145] Substituting the values:

[0146]

[0147] Calculate the parts:

[0148] 100·8=800

[0149] 0.1·(100-50) 2 =0.1·2500=250

[0150]

[0151] 50·4=200

[0152] 0.1·(50-20) 2 =0.1·900=90

[0153]

[0154] Comprehensive calculation:

[0155] E opt =800+250+0.00296+200+90+0.00125=1340.00421Wh

[0156] Calculate the power supply security S of key equipment key :

[0157] Ventilator: P key,1 =440W,t key,1 =24 hours; ECG monitor: P key,2 =55W,t key,2 =24 hours;

[0158]

[0159] Calculate S key :

[0160]

[0161] Substituting the values:

[0162]

[0163] Calculate the parts:

[0164]

[0165] (440-440) 2 =0

[0166] (55-55) 2 =0

[0167] Comprehensive calculation:

[0168] S key =0.82+0.1025-0.5·(0+0)=0.9225

[0169] Optimized total energy consumption E opt :

[0170] E opt ≈1340.00421Wh

[0171] E opt If it is lower than 1400Wh (determined by experience or set according to demand), it means the optimization effect is very good and the energy consumption of non-critical equipment is significantly reduced. opt ≈1340.00421Wh, indicating that through optimization, the total energy consumption of non-critical equipment has been effectively controlled, reducing unnecessary power consumption.

[0172] Power supply security of key equipment S key :

[0173] S key ≈0.9225

[0174] If S key Higher than 0.8 (determined based on experience or set based on demand), indicating that the power supply security of key equipment is high. The power supply security of key equipment is high. In the current scenario, S key ≈0.9225 indicates that the power supply of key equipment is effectively guaranteed, ensuring the treatment effect and life safety of patients.

[0175] Adjust the operating status of non-critical equipment: reduce the operating power of office computers, for example, from 100W to 80W; turn off non-essential functions of printers, such as turning off printers during non-peak hours; monitor the power consumption and operating time of critical equipment in real time to ensure that their power supply is stable and reliable; regularly check the operating status of critical equipment to identify and resolve potential problems in a timely manner; record the optimized total energy consumption and the power supply security of critical equipment; formulate a specific implementation plan, including adjusting the operating status of non-critical equipment and monitoring the operating status of critical equipment.

[0176] Through this series of steps, the power management system of the Fangcang Cabin Hospital can effectively optimize the energy consumption of non-critical equipment, ensure the power supply of critical equipment, and improve the overall power utilization efficiency.

[0177] 103. Based on the optimized power distribution scheme, the event-driven remote alarm system is synchronously activated, and the comprehensive alarm information is sent to the remote monitoring center and the preset emergency response team through a secure channel using an encrypted communication protocol, and a comprehensive alarm information sending record is generated;

[0178] The optimized power distribution scheme refers to the final power distribution strategy formed through the above series of processes (equipment status monitoring, importance and power consumption characteristics evaluation, dynamic priority allocation model construction and power distribution optimization), which aims to ensure the stable operation of critical medical equipment while reducing overall energy consumption.

[0179] The event-driven remote alarm system is an intelligent response mechanism that can automatically trigger the alarm process when a specific event (such as abnormal power distribution, equipment failure, etc.) occurs, and determine whether it is necessary to send an alarm to a designated person or system through pre-set logic.

[0180] The encrypted communication protocol is a set of technical specifications used to protect information security during data transmission. It ensures the confidentiality, integrity and availability of information during transmission through encryption algorithms to prevent information from being eavesdropped or tampered with.

[0181] Comprehensive alarm information sending records mean that after the alarm is triggered, the system records the alarm time, type, content, recipient and other information for subsequent auditing, analysis or responsibility tracing.

[0182] Optionally, in step 103, based on the optimized power distribution plan, an event-driven remote alarm system is synchronously activated, and the comprehensive alarm information is sent to the remote monitoring center and the preset emergency response team through a secure channel using an encrypted communication protocol, and a comprehensive alarm information sending record is generated, including: based on the optimized power distribution plan, the power distribution situation and equipment operation status are monitored in real time, and when an abnormal situation is detected, the event-driven remote alarm system is triggered to generate an alarm trigger signal; using the alarm trigger signal, relevant comprehensive alarm information is collected, and the comprehensive alarm information is sent to the remote monitoring center through a secure channel using an encrypted communication protocol to generate an alarm information sending record; based on the alarm information sending record, the comprehensive alarm information is sent to the preset emergency response team through the same secure channel to generate an alarm information sending record for the emergency response team; the entire alarm information sending process is recorded to generate a comprehensive alarm information sending record.

[0183] In the embodiment of the present application, based on the optimized power distribution scheme, the system will continuously monitor the power distribution and equipment operation status. When any abnormal situation is detected, such as unstable power supply or equipment failure, the system will automatically trigger the event-driven remote alarm system and generate an alarm trigger signal. This signal will start the alarm information collection process, and the system will collect all necessary information related to the abnormal event, including event type, time, location, list of affected equipment, etc., to form a comprehensive alarm information. Subsequently, using the encrypted communication protocol, the comprehensive alarm information is sent to the remote monitoring center through a secure channel, and an alarm information sending record is generated. Next, based on the existing alarm information sending record, the system will send the same comprehensive alarm information again through a secure channel to the preset emergency response team, and generate an alarm information sending record for the emergency response team. Throughout the process, the system will record in detail every step from alarm triggering to information sending completion, and finally generate a comprehensive alarm information sending record to ensure the transparency and traceability of the entire alarm process.

[0184] Assume that in a square cabin hospital, there are several types of medical equipment: ventilator, ECG monitor, ultrasound equipment and infusion pump. The following steps will be implemented based on the optimized power distribution scheme, synchronously activate the event-driven remote alarm system, and generate a comprehensive alarm information sending record.

[0185] First, the optimized power distribution plan is as follows:

[0186] Ventilator power allocation ratio 35%

[0187] ECG monitor power distribution ratio 30%

[0188] Ultrasonic equipment power allocation ratio 15%

[0189] Infusion pump power distribution ratio 10%

[0190] Secondly, use sensors and monitoring equipment to monitor the power distribution and operating status of each device in real time; for example, the real-time monitoring shows that the current of the ventilator is 2A, the voltage is 220V, the power is 440W, and the operating status is normal.

[0191] Furthermore, abnormal conditions include, but are not limited to, abnormal power distribution, equipment failure, and power supply interruption; when an abnormal condition is detected (e.g., assuming that the voltage of the ECG monitor is monitored in real time and suddenly drops to 90V, which is lower than the normal range (110V), the alarm system is triggered, so that when the system detects that the voltage of the ECG monitor is abnormal, an alarm trigger signal is generated.

[0192] For example, generating an alarm trigger signal is as follows:

[0193] Event Type: Power supply abnormality

[0194] Time of occurrence: November 22, 2024 14:05

[0195] Affected devices: ECG monitors

[0196] Details: The voltage of the ECG monitor dropped to 90V, which is lower than the normal range of 110V

[0197] Furthermore, the comprehensive alarm information includes the event type, occurrence time, affected equipment and detailed information, and uses the AES (Advanced Encryption Standard) encryption algorithm to protect the security of transmitted data; transmits data through a secure communication network (such as SSL / TLS protocol) to prevent data from being stolen or tampered with; sends the comprehensive alarm information to the remote monitoring center through an encrypted communication protocol; generates an alarm information sending record, recording the sending time, recipient and sending status.

[0198] The generated alarm information sending record is as follows:

[0199] Sending time: November 22, 2024 14:05

[0200] Receiver: Remote Monitoring Center

[0201] Sending status: Successfully sent

[0202] Furthermore, based on the alarm information sending record, the comprehensive alarm information is sent to a preset emergency response team through the same secure channel, and an alarm information sending record of the emergency response team is generated.

[0203] Among them, the emergency response team's alarm information sending record is as follows:

[0204] Sending time: November 22, 2024 14:06

[0205] Recipient: Emergency Response Team

[0206] Sending status: Successfully sent

[0207] Finally, the entire alarm information sending process is recorded to generate a comprehensive alarm information sending record.

[0208] The generated comprehensive alarm information sending record is as follows:

[0209] Event Type: Power supply abnormality

[0210] Time of occurrence: November 22, 2024 14:05

[0211] Affected devices: ECG monitors

[0212] Details: The voltage of the ECG monitor dropped to 90V, which is lower than the normal range of 110V

[0213] Remote Monitoring Center: Sending time: 14:05, November 22, 2024, receiving party remote monitoring center, sending status: successfully sent

[0214] Emergency Response Team: Sent on November 22, 2024 at 14:06, Recipient Emergency Response Team, Sent successfully

[0215] Through this series of steps, the power management system of the Fangcang Cabin Hospital can monitor the power distribution and equipment operating status in real time. When an abnormal situation is detected, the alarm system is triggered in time, and the comprehensive alarm information is sent to the remote monitoring center and the preset emergency response team through an encrypted communication protocol, ensuring timely response and handling of abnormal situations, and improving the reliability and safety of the system.

[0216] 104. Utilize the backup battery usage in the comprehensive alarm information sending record, regularly evaluate the health status and charging efficiency of the backup battery through a machine learning algorithm, establish a battery aging model to predict future battery performance trends, coordinate internal loads through an intelligent scheduling algorithm, reduce power consumption of non-critical equipment, and generate maintenance plans and charging request records.

[0217] The battery aging model is based on the historical usage data of the battery. It predicts the future performance trend of the battery through modeling, helps to identify possible problems with the battery in advance, and formulate corresponding maintenance plans.

[0218] Maintenance plan and charging request record refers to the maintenance plan generated based on the battery health assessment results, including tasks such as battery replacement and maintenance, and battery charging request record, which is used to track the battery charging status and frequency.

[0219] Intelligent scheduling algorithm refers to an optimization algorithm used to reasonably allocate resources to achieve the best effect when resources are limited. In this scenario, it is used to coordinate the power load inside the shelter hospital, reduce the power consumption of non-critical equipment, and improve overall energy efficiency.

[0220] In the embodiment of the present application, first, the usage of the backup battery is extracted from the comprehensive alarm information sending record, including data such as battery power, charge and discharge times, and usage time. The machine learning algorithm is used to regularly analyze the usage data of the backup battery to evaluate the battery health and charging efficiency.

[0221] Secondly, based on the historical usage data of the battery, the performance trend of the battery in the future is predicted through modeling, and the possible problems of the battery are identified. According to the prediction results of the battery aging model, a maintenance plan is generated, including tasks such as battery replacement and overhaul, to ensure the normal operation of the battery.

[0222] Furthermore, the power load within the square cabin hospital is coordinated through intelligent scheduling algorithms, reducing the power consumption of non-critical equipment and improving overall energy efficiency.

[0223] Finally, based on the battery's health and usage needs, a charging request record is generated to track the battery's charging status and frequency to ensure that the battery is always in optimal condition.

[0224] Optionally, the step 104 uses the backup battery usage in the comprehensive alarm information sending record, regularly evaluates the health status and charging efficiency of the backup battery through a machine learning algorithm, establishes a battery aging model to predict future battery performance trends, coordinates internal loads through an intelligent scheduling algorithm, reduces the power consumption of non-critical equipment, and generates a maintenance plan and a charging request record, including: using the backup battery usage in the comprehensive alarm information sending record to collect historical data of the backup battery, regularly evaluates the health status and charging efficiency of the backup battery through a machine learning algorithm, and generates a health status and charging efficiency evaluation report for the backup battery; based on the health status and charging efficiency evaluation report of the backup battery, establishes a battery aging model, uses time series analysis or regression analysis methods to predict future battery performance trends, and generates a battery performance trend prediction report; uses the battery performance trend prediction report, combined with the current power supply situation and equipment priority, designs an intelligent scheduling algorithm, reduces the power consumption of non-critical equipment by dynamically adjusting the internal load, and generates an internal load adjustment plan; based on the internal load adjustment plan, formulates a maintenance plan for the backup battery, generates a charging request record, and generates a final maintenance plan and charging request record.

[0225] Among them, the health status and charging efficiency evaluation report of the backup battery refers to a report generated by a machine learning algorithm, which contains information such as the current health status, charging efficiency, and service life of the backup battery, which is used to guide maintenance and optimization strategies.

[0226] The battery performance trend forecast report refers to a report generated based on the battery aging model, which predicts the future performance trend of the battery, including changes in indicators such as battery capacity and charging efficiency.

[0227] The internal load adjustment scheme refers to a power distribution strategy designed based on the battery performance trend forecast report and the current power supply situation, aiming to optimize the internal load and reduce the power consumption of non-critical equipment.

[0228] In the embodiment of the present application, it is assumed that a square cabin hospital is equipped with a variety of medical equipment, including ventilators, ECG monitors, ultrasound equipment, and infusion pumps. The power supply of these devices is jointly guaranteed by the main power supply and the backup battery. In order to ensure the reliability and efficiency of the power system, it is necessary to regularly evaluate the health of the backup battery and optimize the power distribution.

[0229] First, the usage of the backup battery is extracted from the comprehensive alarm information sending record, including data such as battery power, charge and discharge times, and usage time. For example, the record shows that a backup battery has been charged and discharged 10 times in the past month, with an average usage time of 2 hours and a current power level of 80%.

[0230] Secondly, the machine learning algorithm is used to regularly analyze the usage data of the backup battery to generate a health status and charging efficiency evaluation report for the backup battery. For example, the evaluation report shows that the charging efficiency of the backup battery has slightly decreased, and the battery capacity remains above 90%, and regular maintenance is recommended.

[0231] Furthermore, based on the health status and charging efficiency evaluation report of the backup battery, a battery aging model is established using time series analysis or regression analysis to predict the future performance trend of the battery and generate a battery performance trend forecast report. For example, the model predicts that the charging efficiency of the backup battery will further decrease in the next 6 months, and the battery capacity may drop to 85%, so it is recommended to replace or overhaul it in advance.

[0232] Furthermore, by using the battery performance trend forecast report, combined with the current power supply situation and equipment priority, an intelligent scheduling algorithm is designed to dynamically adjust the internal load, reduce the power consumption of non-critical equipment, and generate an internal load adjustment plan. For example, when the main power supply is normal, the power supply of key equipment (such as ventilators and ECG monitors) is prioritized, and the power consumption of non-critical equipment (such as ultrasound equipment and infusion pumps) is appropriately reduced to ensure the efficient use of power resources.

[0233] Finally, based on the internal load adjustment plan, a maintenance plan for the backup battery is formulated, a charging request record is generated, and finally a maintenance plan and charging request record are generated. For example, the generated maintenance plan includes a comprehensive overhaul of the backup battery before the end of next month and considering replacing a new battery within 6 months. The charging request record shows that the backup battery needs to be charged every Monday and Friday to ensure that it is always in the best condition.

[0234] Through the above steps, the power management system of the Fangcang Hospital can effectively evaluate the health of the backup battery, predict future performance trends, and generate maintenance plans and charging request records. At the same time, it optimizes power distribution through intelligent scheduling algorithms, reduces power consumption of non-critical equipment, ensures the stable operation of key medical equipment, and improves the reliability and energy efficiency of the overall power system.

[0235] Optionally, the use of the battery performance trend prediction report, combined with the current power supply situation and device priority, to design an intelligent scheduling algorithm, by dynamically adjusting the internal load, reduce the power consumption of non-critical equipment, and generate an internal load adjustment plan, including: using the battery performance trend prediction report, combined with the current power supply situation and device priority, to design an intelligent scheduling algorithm, and generate an intelligent scheduling algorithm; in the intelligent scheduling algorithm, setting input variables, defining output variables, and generating an intelligent scheduling algorithm; through the intelligent scheduling algorithm, dynamically adjusting the internal load according to the input variables and preset optimization goals, reducing the power consumption of non-critical equipment, ensuring that the power supply of critical equipment is not affected, and generating a load adjustment strategy; the intelligent scheduling algorithm calculates the power distribution ratio and specific load adjustment measures of each device according to the input variables and the load adjustment strategy, and generates an internal load adjustment plan.

[0236] Among them, the load adjustment strategy refers to the specific power distribution and load adjustment measures formulated based on the calculation results of the intelligent scheduling algorithm, which aims to reduce the power consumption of non-critical equipment and ensure that the power supply of critical equipment is not affected.

[0237] The internal load adjustment plan refers to a detailed plan generated according to the load adjustment strategy, including the power allocation ratio of each device, specific load adjustment measures, etc., which is used to guide actual operations.

[0238] In the embodiment of the present application, it is assumed that a square cabin hospital is equipped with a variety of medical equipment, including ventilators, ECG monitors, ultrasound equipment, and infusion pumps. The power supply of these devices is jointly guaranteed by the main power supply and the backup battery. In order to ensure the reliability and efficiency of the power system, it is necessary to design an intelligent scheduling algorithm based on the battery performance trend forecast report, combined with the current power supply situation and equipment priority, to optimize power distribution.

[0239] First, use the battery performance trend forecast report, combined with the current power supply and equipment priority, to design an intelligent scheduling algorithm. For example, according to the battery performance trend forecast report, the current backup battery charging efficiency has slightly decreased, and the battery capacity remains above 90%. Combined with the current power supply (assuming that the main power supply is normal), determine the equipment priority (ventilator > ECG monitor > ultrasound equipment > infusion pump).

[0240] Secondly, in the intelligent scheduling algorithm, set the input variables, including the current power supply situation, device priority, battery performance data, etc. Define the output variables, including the power allocation ratio of each device and the specific load adjustment measures. For example, the input variables include the current power supply situation (the main power supply is normal), the device priority (ventilator>ECG monitor>ultrasound equipment>infusion pump), and battery performance data (charging efficiency is slightly reduced, and the battery capacity is more than 90%). The output variables include the power allocation ratio of each device and the specific load adjustment measures.

[0241] Furthermore, through the intelligent scheduling algorithm, the internal load is dynamically adjusted according to the input variables and the preset optimization goals (such as reducing the power consumption of non-critical equipment and ensuring that the power supply of critical equipment is not affected), and the load adjustment strategy is generated. For example, when the power supply is tight, the power allocation ratio of non-critical equipment (such as ultrasound equipment and infusion pumps) is appropriately reduced to ensure that the power supply of critical equipment (such as ventilators and ECG monitors) is not affected.

[0242] Finally, the intelligent scheduling algorithm calculates the power distribution ratio and specific load adjustment measures for each device based on the input variables and load adjustment strategy, and generates an internal load adjustment plan.

[0243] For example, the internal load regulation scheme is generated as follows:

[0244] Ventilator: Power allocation ratio 35%, maintaining normal operation.

[0245] ECG monitor: Power allocation ratio is 30%, maintaining normal operation.

[0246] Ultrasonic equipment: The power allocation ratio is 15%, which can be appropriately reduced to 10% when the power supply is tight.

[0247] Infusion pump: The power allocation ratio is 10%, which can be appropriately reduced to 5% when the power supply is tight.

[0248] Through the above steps, the power management system of the Fangcang Hospital can design an intelligent scheduling algorithm and optimize power distribution based on the battery performance trend forecast report, combined with the current power supply situation and equipment priority. This not only ensures the stable operation of key medical equipment, but also reduces the power consumption of non-critical equipment, and improves the reliability and energy efficiency of the overall power system.

[0249] This application takes into account that in the power management system of the Fangcang Hospital, the health status and charging efficiency of the backup battery are crucial to the stable operation of the system. By regularly evaluating the health status and charging efficiency of the backup battery through machine learning algorithms, potential problems can be discovered in advance to ensure that the power supply of key equipment is not affected. To this end, two formulas are designed to evaluate the health status and charging efficiency of the backup battery.

[0250] Optionally, the use of the backup battery in the comprehensive alarm information sending record is used to collect historical data of the backup battery, and the health status and charging efficiency of the backup battery are regularly evaluated by a machine learning algorithm to generate a health status and charging efficiency evaluation report of the backup battery, including:

[0251] Before calculating the health status H(t) of the backup battery, it is necessary to collect and preprocess the historical data of the backup battery, such as the current capacity, discharge depth, and internal resistance, and assign an appropriate weight to each backup battery to ensure the consistency and accuracy of the data;

[0252] Backup battery health assessment formula:

[0253]

[0254] Where H(t) is the health status of the backup battery at time t, N is the number of backup batteries, and w i is the weight of the ith backup battery, C i (t) is the current capacity of the ith backup battery at time t, C min,i is the minimum capacity of the ith backup battery, C max,i is the maximum capacity of the ith backup battery, γ i is the additional weight of the ith backup battery, D i (t) is the discharge depth of the ith backup battery at time t, D max , is the maximum discharge depth of the ith backup battery, δ i is the resistance weight of the ith backup battery, R i (t) is the internal resistance of the ith backup battery at time t, R max , is the maximum internal resistance of the ith backup battery;

[0255] After calculating the health status H(t) of the backup battery, it is necessary to collect and preprocess the data of the charge capacity, temperature and voltage of the backup battery, and calculate the charging efficiency E(t) of each backup battery by introducing a weight coefficient to ensure the comprehensiveness of the evaluation results;

[0256] Backup battery charging efficiency evaluation formula:

[0257]

[0258] Where E(t) is the charging efficiency of the backup battery at time t, η is the weight coefficient of the charging efficiency, and Q i (t) is the charge capacity of the ith backup battery at time t, Q max,i is the maximum charge capacity of the ith backup battery, β is the weight coefficient of temperature influence, T i(t) is the temperature of the ith backup battery at time t, T min,i is the minimum temperature of the ith backup battery, T max,i is the maximum temperature of the ith backup battery, θ i is the voltage weight of the ith backup battery, V i (t) is the voltage of the ith backup battery at time t, V min,i is the lowest voltage of the ith backup battery, V max,i is the maximum voltage of the ith backup battery;

[0259] After calculating the charging efficiency E(t) of the backup battery, the results of H(t) and E(t) are combined to generate a health status and charging efficiency evaluation report for the backup battery, formulate a specific maintenance plan and charging request record, and ensure the effective use of the evaluation results and the stable operation of the system.

[0260] The solution is designed to enable backup batteries to provide power support when the main power fails, so their health status and charging efficiency directly affect the power supply of key equipment; by regularly evaluating the health status and charging efficiency of backup batteries, potential problems can be discovered in advance, maintenance plans can be made, and sudden failures can be avoided; evaluating charging efficiency helps optimize charging strategies, improve charging efficiency, and extend battery life.

[0261] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0262]

[0263] In the backup battery health assessment formula H(t), Current capacity is one of the key indicators for evaluating battery health. Through normalization, the current capacity is converted to a value between 0 and 1, and then squared to amplify the difference, ensuring that high-capacity batteries have a higher health score. The depth of discharge reflects the usage of the battery. Through normalization, the depth of discharge is converted to a value between 0 and 1, and then cubed to amplify the difference, ensuring that shallowly discharged batteries have a higher health score. Internal resistance is an important indicator for evaluating battery aging. Through normalization, the internal resistance is converted to a value between 0 and 1, and then squared to amplify the difference, ensuring that batteries with low internal resistance have a higher health score.

[0264] The following is a brief introduction to how to obtain the parameters of the formula:

[0265] Among them, C i (t) collect the current capacity of the backup battery at time t in real time through sensors and monitoring equipment; C min,i and C max,iObtain the minimum and maximum capacity of each backup battery from the equipment's technical specifications; D i (t) collect the discharge depth of the backup battery at time t in real time through sensors and monitoring equipment; D max,i Get the maximum depth of discharge of each backup battery from the equipment's technical specifications; R i (t) The internal resistance of the backup battery at time t is collected in real time through sensors and monitoring equipment; R max,i Get the maximum internal resistance of each backup battery from the device's technical specification; i , γ i and δ i Determine appropriate weights through experiments and empirical data;

[0266] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0267]

[0268] In the backup battery charging efficiency evaluation formula E(t), The charge capacity is one of the key indicators for evaluating battery charging efficiency. Through normalization, the charge capacity is converted to a value between 0 and 1, and then squared to amplify the difference, ensuring that batteries with high charge capacities have higher charging efficiency scores. Temperature has a significant impact on battery charging efficiency. Through normalization, the temperature is converted to a value between 0 and 1, and then cubed to amplify the difference, ensuring that the battery charging efficiency score at the appropriate temperature is higher. Voltage is an important indicator for evaluating battery charging efficiency. Through normalization, the voltage is converted to a value between 0 and 1, and then squared to amplify the difference, ensuring that high-voltage batteries have higher charging efficiency scores.

[0269] The following is a brief introduction to how to obtain the parameters of the formula:

[0270] Among them, Q i (t) collect the charge capacity of the backup battery at time t in real time through sensors and monitoring equipment; Q max,i Get the maximum charge capacity of each backup battery from the device's technical data sheet; T i (t) collecting the temperature of the backup battery at time t in real time through sensors and monitoring equipment; T min,i and T max,i Get the minimum and maximum temperatures of each backup battery from the device's technical specifications; V i (t) The voltage of the backup battery at time t is collected in real time through sensors and monitoring equipment; V min,i and V max,iObtain the minimum and maximum voltages of each backup battery from the device's technical data sheet; η, β, and θ i The appropriate weight coefficient is determined through experiments and empirical data.

[0271] Backup battery 1: Current capacity C1(t) = 80Ah, minimum capacity C min,1 =60Ah, maximum capacity C max,1 =100Ah, discharge depth D1(t) = 40%, maximum discharge depth D max,1 =80%, internal resistance R1(t)=0.05Ω, maximum internal resistance R max,1 =0.1Ω, charge capacity Q1(t) = 90Ah, maximum charge capacity Q max,1 =100Ah, temperature T1(t) = 25℃, minimum temperature T min,1 =15℃, maximum temperature T max,1 =35℃, voltage V1(t)=12.5V, minimum voltage V min,1 =12V, maximum voltage V max,1 =14V

[0272] Backup battery 2: Current capacity C2(t) = 70Ah, minimum capacity C min,2 =50Ah, maximum capacity C max,2 =100Ah, discharge depth D2(t)=50%, maximum discharge depth D max,2 =80%, internal resistance R2(t) = 0.06Ω, maximum internal resistance R max,2 =0.1Ω, charge capacity Q2(t)=85Ah, maximum charge capacity Q max,2 =100Ah, temperature T2(t) = 28℃, minimum temperature T min,2 =15℃, maximum temperature T max,2 =35℃, voltage V2(t)=12.3V, minimum voltage V min,2 =12V, maximum voltage V max,2 =14V

[0273] Weight coefficient: w1=0.5, w2=0.5, γ1=0.3, γ2=0.3, δ1=0.2, δ2=0.2, η=0.4, β=0.3, θ1=0.3, θ2=0.3

[0274] For backup battery 1:

[0275]

[0276] Calculated:

[0277] H1(t)=0.5·0.25+0.3·0.125+0.2·0.25=0.125+0.0375+0.05

[0278] =0.2125

[0279] For backup battery 2:

[0280]

[0281] Calculated:

[0282] H2(t)=0.5·0.16+0.3·0.2441+0.2·0.36=0.08+0.07323+0.072

[0283] =0.22523

[0284] Average health status:

[0285]

[0286] Calculate the charging efficiency E(t)

[0287] For backup battery 1:

[0288]

[0289] Calculated:

[0290] E1(t)=0.4·0.81+0.3·0.125+0.3·0.25=0.324+0.0375+0.075

[0291] =0.4365

[0292] For backup battery 2:

[0293]

[0294] Calculated:

[0295] E2(t)=0.4·0.7225+0.3·0.2197+0.3·0.225=0.289+0.06591+0.0675

[0296] =0.42241

[0297] Average charging efficiency:

[0298]

[0299] Health status: The average health status is 0.218865, indicating that the overall health status of the two backup batteries is good. Since this value is close to 0.25 (set based on experience), it is a relatively healthy level, indicating that the current capacity, discharge depth and internal resistance of the battery are all within a reasonable range.

[0300] Charging efficiency: The average charging efficiency is 0.429455, indicating that the charging efficiency of the two backup batteries is relatively high. Since this value is close to 0.5 (set based on experience), it is a high level, indicating that the battery performs well during the charging process.

[0301] Based on these results, specific maintenance plans can be developed, such as regularly replacing batteries with higher internal resistance or optimizing charging strategies to improve overall system stability. At the same time, it is also possible to consider adjusting the charging algorithm to adapt to the specific conditions of different batteries, thereby further improving charging efficiency.

[0302] Figure 2 A structural schematic diagram of an uninterruptible power supply control system for a modular medical device is provided in an embodiment of the present application, such as Figure 2 As shown, the device comprises:

[0303] Monitoring module 21, used to monitor the working status data and power supply parameters of the shelter medical equipment in real time and generate equipment status reports;

[0304] A construction module 22 is used to construct a dynamic priority allocation model according to the importance and power consumption characteristics of the equipment in the equipment status report, use a fuzzy logic controller to adjust the power allocation ratio of each medical device in real time, optimize the energy consumption strategy of non-critical equipment through a linear programming algorithm, and generate an optimized power allocation plan;

[0305] The sending module 23 is used to synchronously activate the event-driven remote alarm system based on the optimized power distribution plan, send the comprehensive alarm information to the remote monitoring center and the preset emergency response team through a secure channel using an encrypted communication protocol, and generate a comprehensive alarm information sending record;

[0306] The evaluation module 24 is used to utilize the backup battery usage in the comprehensive alarm information sending record, regularly evaluate the health status and charging efficiency of the backup battery through a machine learning algorithm, establish a battery aging model to predict future battery performance trends, coordinate internal loads through an intelligent scheduling algorithm, reduce the power consumption of non-critical equipment, and generate maintenance plans and charging request records.

[0307] Figure 2 The uninterruptible power supply control system of the modular medical equipment can be implemented Figure 1The implementation principle and technical effect of the uninterruptible power supply control method for a modular medical device described in the embodiment shown will not be described in detail. The specific way in which each module and unit performs operations in the uninterruptible power supply control system for a modular medical device in the above embodiment has been described in detail in the embodiment of the method, and will not be described in detail here.

[0308] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for controlling an uninterruptible power supply of a modular medical device, characterized in that: include: Monitor the working status data and power supply parameters of the medical equipment in the shelter in real time and generate equipment status reports; According to the importance and power consumption characteristics of the equipment in the equipment status report, a dynamic priority allocation model is constructed, the power allocation ratio of each medical equipment is adjusted in real time using a fuzzy logic controller, the energy consumption strategy of non-critical equipment is optimized through a linear programming algorithm, and an optimized power allocation plan is generated; Based on the optimized power distribution scheme, the event-driven remote alarm system is synchronously activated, and the comprehensive alarm information is sent to the remote monitoring center and the preset emergency response team through a secure channel using an encrypted communication protocol, and a comprehensive alarm information sending record is generated; The backup battery usage in the comprehensive alarm information sending record is used to regularly evaluate the health status and charging efficiency of the backup battery through a machine learning algorithm, a battery aging model is established to predict future battery performance trends, internal loads are coordinated through an intelligent scheduling algorithm, power consumption of non-critical equipment is reduced, and maintenance plans and charging request records are generated.

2. The method according to claim 1, characterized in that According to the device importance and power consumption characteristics in the device status report, a dynamic priority allocation model is constructed, a fuzzy logic controller is used to adjust the power allocation ratio of each medical device in real time, and the energy consumption strategy of non-critical devices is optimized by a linear programming algorithm to generate an optimized power allocation plan, including: By using real-time monitoring of the working status data and power supply parameters of all medical equipment in the shelter, the collected relevant data are pre-processed to obtain the equipment status report; Based on the importance and power consumption characteristics of the equipment in the equipment status report, defining evaluation criteria, evaluating the importance of each medical equipment, and generating a dynamic priority allocation model taking into account the power consumption characteristics of the equipment; The dynamic priority allocation model is used to integrate the model into a fuzzy logic controller, and the power allocation ratio is automatically adjusted according to the real-time power supply situation and the equipment priority to obtain the power allocation ratio adjustment result; Based on the power distribution ratio adjustment result, a linear programming algorithm is used to optimize the energy consumption strategy of non-critical equipment to ensure that the power supply of critical equipment is not affected, while reducing the overall energy consumption and generating an energy consumption optimization strategy; The power distribution ratio adjustment result and the energy consumption optimization strategy are combined to generate an optimized power distribution plan.

3. The method according to claim 2, characterized in that Based on the power distribution ratio adjustment result, the linear programming algorithm is used to optimize the energy consumption strategy of non-critical equipment to ensure that the power supply of critical equipment is not affected, while reducing the overall energy consumption, and generating an energy consumption optimization strategy, including: The total energy consumption after calculation optimization is E opt Previously, it was necessary to collect and preprocess the real-time power consumption and operating time data of non-critical devices, evaluate the power consumption fluctuations, and consider the nonlinear impact when the power consumption is close to the maximum value, laying the foundation for optimization calculations; Energy consumption optimization formula for non-critical equipment: Among them, e opt is the total energy consumption after optimization, N is the number of non-critical devices, P i is the current power consumption of the i-th non-critical device, t i is the operating time of the i-th non-critical device, λ is the penalty coefficient used to balance power consumption and power consumption fluctuation, P min,i is the minimum power consumption of the i-th non-critical device, β is an additional penalty coefficient used to consider the nonlinear effect when the power consumption is close to the maximum value, P max,i is the maximum power consumption of the ith non-critical device; After calculating the total energy consumption E opt Finally, it is necessary to collect the current power consumption and operating time data of key equipment and calculate the power supply security degree S of key equipment. key And by introducing weight coefficients, we ensure the stable and reliable power supply of key equipment; Formula for ensuring power supply to key equipment: Among them, S key is the power supply security of key equipment, M is the number of key equipment, P key,j is the current power consumption of the jth key device, t key,j is the operating time of the jth key device, P req,j is the required power consumption of the jth key device, α is the weight coefficient used to balance the power consumption requirement and actual power consumption of the key device; P k represents the current power consumption of the kth device; t k represents the running time of the kth device; N represents the total number of all devices; After calculating the power supply security of key equipment S key After that, the comprehensive calculation E opt and S key , generate energy consumption optimization strategies.

4. The method according to claim 2, characterized in that: Defining evaluation criteria according to the importance and power consumption characteristics of the equipment in the equipment status report, evaluating the importance of each medical device, considering the power consumption characteristics of the equipment, and generating a dynamic priority allocation model, including: Analyze the importance and power consumption characteristics of the equipment using the information in the equipment status report, define evaluation criteria, and obtain evaluation criteria; According to the evaluation criteria, the importance of each medical device is evaluated, and an importance score is assigned to each device to obtain a device importance score; Considering the power consumption characteristics of the devices and combining the importance scores of the devices, a preliminary priority allocation table is generated; Based on the preliminary priority allocation table, a dynamic priority adjustment rule is designed to appropriately reduce the priority of key equipment when the power supply is sufficient to optimize the overall energy consumption, thereby obtaining a dynamic priority adjustment rule; The preliminary priority allocation table and the dynamic priority adjustment rule are integrated into a dynamic priority allocation model. The dynamic priority allocation model has the ability to automatically adjust the priority when the power supply is tight, and considers the interdependence between devices to generate a dynamic priority allocation model.

5. The method according to claim 2, characterized in that: The dynamic priority allocation model is integrated into a fuzzy logic controller to automatically adjust the power allocation ratio according to the real-time power supply situation and the equipment priority, and obtain the power allocation ratio adjustment result, including: Using the dynamic priority allocation model, the model is integrated into a fuzzy logic controller to obtain an integrated fuzzy logic controller; In the integrated fuzzy logic controller, input variables are set, output variables are defined, and input and output configurations of the fuzzy logic controller are generated; Based on the input and output configuration of the fuzzy logic controller, a membership function and a fuzzy rule base are set to describe the relationship between the input variables and the output variables, and a fuzzy rule base is generated; Through the fuzzy rule base, a fuzzy reasoning process is performed according to the real-time power supply situation and equipment priority, and the power distribution ratio is automatically adjusted to obtain the power distribution ratio adjustment result.

6. The method according to claim 1, characterized in that The backup battery usage in the comprehensive alarm information sending record is used to regularly evaluate the health status and charging efficiency of the backup battery through a machine learning algorithm, establish a battery aging model to predict future battery performance trends, coordinate internal loads through an intelligent scheduling algorithm, reduce power consumption of non-critical equipment, and generate maintenance plans and charging request records, including: Utilizing the backup battery usage in the comprehensive alarm information sending record, collecting historical data of the backup battery, regularly evaluating the health status and charging efficiency of the backup battery through a machine learning algorithm, and generating a backup battery health status and charging efficiency evaluation report; Based on the health status and charging efficiency evaluation report of the backup battery, a battery aging model is established, and the performance trend of the battery in the future is predicted using a time series analysis or regression analysis method to generate a battery performance trend prediction report; Using the battery performance trend forecast report, combined with the current power supply situation and equipment priority, an intelligent scheduling algorithm is designed to reduce the power consumption of non-critical equipment by dynamically adjusting the internal load and generate an internal load adjustment plan; Based on the internal load adjustment scheme, a maintenance plan for the backup battery is formulated, a charging request record is generated, and a final maintenance plan and charging request record are generated.

7. The method according to claim 6, characterized in that The method utilizes the backup battery usage in the comprehensive alarm information sending record to collect historical data of the backup battery, regularly evaluates the health status and charging efficiency of the backup battery through a machine learning algorithm, and generates a backup battery health status and charging efficiency evaluation report, including: Collect and pre-process the current capacity, discharge depth and internal resistance of the backup batteries, and assign appropriate weights to each backup battery to ensure data consistency and accuracy; The backup battery health status is calculated using the following backup battery health status assessment formula: Where H(t) is the health status of the backup battery at time t, N is the number of backup batteries, and w i is the weight of the ith backup battery, C i (t) is the current capacity of the ith backup battery at time t, C min,i is the minimum capacity of the ith backup battery, C max,i is the maximum capacity of the ith backup battery, γ i is the additional weight of the ith backup battery, D i (t) is the discharge depth of the ith backup battery at time t, D max, is the maximum discharge depth of the ith backup battery, δ i is the resistance weight of the ith backup battery, R i (t) is the internal resistance of the ith backup battery at time t, R max, is the maximum internal resistance of the ith backup battery; After calculating the health status H(t) of the backup battery, the charge capacity, temperature and voltage data of the backup battery are collected and preprocessed, and the charging efficiency E(t) of each backup battery is calculated by introducing a weight coefficient to ensure the comprehensiveness of the evaluation results; Backup battery charging efficiency evaluation formula: Where E(t) is the charging efficiency of the backup battery at time t, η is the weight coefficient of the charging efficiency, and Q i (t) is the charge capacity of the ith backup battery at time t, Q max,i is the maximum charge capacity of the ith backup battery, β is the weight coefficient of temperature influence, T i (t) is the temperature of the ith backup battery at time t, T min,i is the minimum temperature of the ith backup battery, T max,i is the maximum temperature of the ith backup battery, θ i is the voltage weight of the ith backup battery, V i (t) is the voltage of the ith backup battery at time t, V min,i is the lowest voltage of the ith backup battery, V max,i is the maximum voltage of the ith backup battery; After calculating the charging efficiency E(t) of the backup battery, the results of H(t) and E(t) are combined to generate a health status and charging efficiency evaluation report of the backup battery.

8. The method according to claim 6, characterized in that The battery performance trend forecast report is used to combine the current power supply situation and equipment priority to design an intelligent scheduling algorithm, dynamically adjust the internal load, reduce the power consumption of non-critical equipment, and generate an internal load adjustment plan, including: Using the battery performance trend forecast report, combined with current power supply conditions and equipment priorities, an intelligent scheduling algorithm is designed to generate an intelligent scheduling algorithm; In the intelligent scheduling algorithm, input variables are set, output variables are defined, and an intelligent scheduling algorithm is generated; Through the intelligent scheduling algorithm, the internal load is dynamically adjusted according to the input variables and the preset optimization goals, the power consumption of non-critical equipment is reduced, the power supply of critical equipment is ensured not to be affected, and the load adjustment strategy is generated; The intelligent scheduling algorithm calculates the power distribution ratio and specific load adjustment measures of each device according to the input variables and the load adjustment strategy, and generates an internal load adjustment plan.

9. The method according to claim 1, characterized in that: Based on the optimized power distribution scheme, the event-driven remote alarm system is synchronously activated, and the comprehensive alarm information is sent to the remote monitoring center and the preset emergency response team through a secure channel using an encrypted communication protocol, and a comprehensive alarm information sending record is generated, including: Based on the optimized power distribution scheme, the power distribution situation and the equipment operation status are monitored in real time, and when an abnormal situation is detected, an event-driven remote alarm system is triggered to generate an alarm trigger signal; Utilize the alarm trigger signal to collect relevant comprehensive alarm information, use the encrypted communication protocol to send the comprehensive alarm information to the remote monitoring center through a secure channel, and generate an alarm information sending record; Based on the alarm information sending record, the comprehensive alarm information is sent to a preset emergency response team through the same secure channel to generate an alarm information sending record of the emergency response team; Record the entire alarm information sending process and generate a comprehensive alarm information sending record.

10. An uninterruptible power supply control system for modular medical equipment, characterized in that: include: The monitoring module is used to monitor the working status data and power supply parameters of the medical equipment in the shelter in real time and generate equipment status reports; A construction module is used to construct a dynamic priority allocation model according to the importance and power consumption characteristics of the equipment in the equipment status report, use a fuzzy logic controller to adjust the power allocation ratio of each medical device in real time, optimize the energy consumption strategy of non-critical equipment through a linear programming algorithm, and generate an optimized power allocation plan; A sending module is used to synchronously activate the event-driven remote alarm system based on the optimized power distribution plan, send the comprehensive alarm information to the remote monitoring center and the preset emergency response team through a secure channel using an encrypted communication protocol, and generate a comprehensive alarm information sending record; An evaluation module is used to utilize the backup battery usage in the comprehensive alarm information sending record, regularly evaluate the health status and charging efficiency of the backup battery through a machine learning algorithm, establish a battery aging model to predict future battery performance trends, coordinate internal loads through an intelligent scheduling algorithm, reduce power consumption of non-critical equipment, and generate maintenance plans and charging request records.

Images