Hospital Internet of Things equipment intelligent monitoring and fault early warning system based on edge computing

Abstract

The invention discloses a hospital Internet of Things equipment intelligent monitoring and fault early warning system based on edge computing, relates to the technical field of equipment monitoring and early warning, and aims to solve the technical problem that fault discovery lags in a high-real-time scene of an existing intelligent monitoring and fault early warning system. The system is used for collecting various data of hospital Internet of Things equipment and sending the data to a preset storage position, and comprises a local database, a data processing module and an abnormal data judgment unit; the Internet of Things base station is used for being connected with Internet of Things equipment, collecting equipment data and achieving intelligent monitoring and fault early warning through an algorithm model, and the algorithm model is constructed based on a core algorithm and rules; and the hospital Internet of Things edge computing platform is used for carrying out edge computing management on the data sent by the Internet of Things base station, feeding back an analysis result and storing the data. The method has the advantage of improving the fault discovery speed of the Internet of Things equipment.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of equipment monitoring and early warning, in particular to a hospital Internet of Things equipment intelligent monitoring and fault early warning system based on edge computing. BACKGROUND

[0002] In the field of hospital Internet of Things, the stable operation of various medical equipment (such as intensive care monitors, intelligent infusion pumps, disinfection equipment, etc.) is directly related to the quality of medical services and patient safety. At present, the existing hospital Internet of Things equipment monitoring system mainly relies on a cloud centralized data processing mode, and the equipment operation data need to be uploaded to the cloud for analysis and fault judgment, which leads to high data transmission delay and lag of the edge end in responding to equipment abnormalities. In high real-time scenarios such as surgery and intensive care, this lag may lead to equipment failure that cannot be discovered and handled in time, which may cause medical risks and become a key technical problem restricting the efficient and safe operation of hospital Internet of Things equipment. In view of this, the application provides a hospital Internet of Things equipment intelligent monitoring and fault early warning system based on edge computing. SUMMARY

[0003] The application aims to provide a hospital Internet of Things equipment intelligent monitoring and fault early warning system based on edge computing to solve the problem of lag in fault discovery of intelligent monitoring and fault early warning systems in high real-time scenarios.

[0004] To solve the above technical problems, the application provides the following technical scheme: a hospital Internet of Things equipment intelligent monitoring and fault early warning system based on edge computing, comprising: a data access and processing module for collecting various data of hospital Internet of Things equipment and sending them to a preset storage location, including a local database, a data processing module and an abnormal data judgment unit; an Internet of Things base station for connecting Internet of Things equipment, collecting equipment data and realizing intelligent monitoring and fault early warning through an algorithm model, wherein the algorithm model is constructed based on core algorithms and rules; a hospital Internet of Things edge computing platform for edge computing management of data sent by the Internet of Things base station, feedback analysis results and storage of data; a central cloud for receiving edge computing data and performing cloud computing analysis, model updating and generating analysis reports; a fault judgment and processing module for real-time detection and processing of equipment faults, generation of fault alarm and processing records, including a fault processing database and a background, wherein the background includes a system data center; a predictive maintenance module for fault prediction using historical data, development of preventive maintenance plans and judgment of equipment health status; The system further comprises core algorithms and rules and a module coordination mechanism, the core algorithms and rules provide algorithm support for data processing and analysis of each module, and the module coordination mechanism is used for realizing the coordinated work between the modules.

[0005] Preferably, the data access and processing module further comprises a data acquisition module and a data sending module. The data acquisition module establishes a connection through an interface matched with the hospital Internet of Things equipment, acquires real-time data, statistical data, alarm data and abnormal data at a set acquisition interval, and The data sending module encapsulates the collected data, adds a unique device identifier and an accurate acquisition timestamp, and then synchronously sends the data to a local database and an Internet of Things base station through an internal data transmission bus. The data acquisition module preliminarily marks the continuously collected abnormal data, and the marking logic calculates the abnormal deviation degree of the data through an abnormal deviation degree formula When the abnormal deviation degree is greater than a set fault judgment threshold, the abnormal data is marked as abnormal candidate data. When the abnormal deviation degree is greater than a set fault judgment threshold, the abnormal data is marked as abnormal candidate data.

[0006] Preferably, the Internet of Things base station is connected with the Internet of Things equipment and comprises a device driver, a data processing module, a remote control module, a data communication module, a rule engine, a local storage module, an edge computing algorithm, an edge computing rule, an abnormal analysis module and a prediction analysis module. The Internet of Things base station sorts the generated fault warning information records according to emergency degrees and then sends the information records to an Internet of Things edge computing platform. The data processing module performs secondary verification on the abnormal candidate data, and calculates the data fluctuation degree through a sliding window variance formula.

[0007] Preferably, the core algorithms and rules comprise an edge computing algorithm model, rule content and a data processing model, wherein the edge computing algorithm model and the data processing model are deployed on the Internet of Things base station, and training and optimization of the algorithm model are completed in cooperation with the hospital Internet of Things edge computing platform and the central cloud. In the edge computing algorithm model, an LSTM model is deployed on the Internet of Things base station, contains an input layer, multiple hidden layers and an output layer, and is trained by using an optimizer; and a decision tree algorithm is deployed on the Internet of Things base station and is used for fault classification, with common fault types of the equipment as a classification target and multiple equipment operation features related to the faults as classification bases. In the rule content, a fault judgment threshold is set as a fixed proportion of a normal operation parameter range according to the equipment type, and equipment state evaluation is divided into three levels of health, mild abnormality and serious abnormality. In the data processing model, the processing logic is deployed in the Internet of Things base station, and the mean value filling method is used to replace the mean value of the surrounding effective data for a small amount of continuous missing values, and the missing values reaching a set number of continuous collection periods or a set proportion of single batch data missing are marked as data interruption; Abnormal values are detected and removed by statistical principles, data is stored in a time series database, and is indexed by device identification and timestamp; The potential correlation between faults and device parameters is mined by a correlation rule algorithm, and the complex rule iteration of the algorithm is completed by the central cloud; The parameter change trend is displayed by a line chart, and the fault rates of different devices are compared by a column chart, and the visual data is updated at a set period; The abnormal data judgment unit of the data processing module of the data access and processing module uses the above data processing model to mark the faults in the fault history data that meet the serious abnormal characteristics, and the abnormal data judgment unit includes a device data judgment unit, which stores the historical normal operation parameter range of each device as a judgment reference.

[0008] Preferably, the hospital Internet of Things edge computing platform is connected with the Internet of Things base station through a stable network connection mode, including a big data cloud computing cluster, an Internet of Things data storage module, an Internet of Things data uploading module, and an edge computing management end; Through an Internet of Things data download interface, the Internet of Things data from the central cloud is received and stored in a local storage device according to the device type, and remote access to the data by different departments is realized through permission management, ensuring the safety and pertinence of data access; The edge computing management end realizes Internet of Things device access management and configuration management through a Web console, allocates edge computing tasks through a task scheduling algorithm, and optimizes network paths through a dynamic routing algorithm, and automatically switches to a backup path when a certain path has too high delay; The central cloud is deployed in a hospital data center, including a central Internet of Things display and monitoring module, a central Internet of Things management module, and a central cloud database; Through a cloud data interaction interface, the edge computing algorithm model, rules, and Internet of Things data from the Internet of Things edge computing platform are received, the Internet of Things data is cloud computed and analyzed, the algorithm model and rules are updated and optimized, and an analysis report is generated and stored in the central cloud database.

[0009] Preferably, the fault judgment and processing module further includes a fault processing alarm unit and a fault record statistics unit; The fault processing alarm unit sends device fault alarm information and device fault notification information to the background through a sound-light alarm and a short message gateway; The fault processing alarm unit comprises a device fault alarm unit, a device fault notification unit and an alarm judgment unit; The alarm judgment unit compares the current data of the device with the preset threshold in real time, and sends an alarm information when the threshold is exceeded for continuous multiple collection periods. The alarm information comprises accurate alarm time, clear alarm cause and specific alarm data; The fault record statistics unit is responsible for recording the complete information of a single fault and generating a fault detail file of a single device; The alarm judgment unit determines whether to trigger an alarm through a fault confidence formula.

[0010] Preferably, the background further comprises a wireless gateway, an edge computing module and a remote terminal; The edge computing module filters and normalizes the device data; The remote terminal further comprises a data classification unit, a data filtering unit and a data extraction unit; When the Internet of Things device fails, the edge computing module processes the Internet of Things data to obtain device state abnormal data and health data. The edge computing module transmits the device state abnormal data and the health data to the data processing module.

[0011] Preferably, the predictive maintenance module comprises a prediction judgment unit, a prediction data storage unit, a prediction database, a cloud prediction module and a wireless cloud prediction module; The prediction judgment unit predicts the probability of failure and possible failure causes in the subsequent use cycle of the device based on the accumulated operation data in the operation cycle and the historical fault records stored by the system.

[0012] Preferably, the module coordination mechanism comprises a three-level architecture coordination mechanism and a fault judgment and processing module and a predictive maintenance module coordination mechanism; The three-level architecture coordination mechanism is that the Internet of Things base station uploads real-time data to the edge computing platform at a preset period. The data format adopts a unified format, and the key fields include device identification, collection time, parameter name and numerical value; The edge computing platform uploads the summary data to the central cloud at a preset period; The central cloud sends the updated model and rules to the edge computing platform at a preset period. Before sending, the data is checked to ensure the file integrity; The fault judgment and processing module and the predictive maintenance module coordination mechanism is that the network time protocol is used to synchronize the time of all devices in the system; The predictive maintenance module obtains the recent fault data from the fault judgment and processing module at a preset period, and performs fault prediction in combination with the locally stored device operation data. When obtaining the fault data, the predictive maintenance module filters the effective data according to the time stamp and checks the data integrity; When the center cloud needs to issue a control instruction to the Internet of Things base station, the instruction is forwarded through the edge computing platform, the edge computing platform records the instruction transmission state, and the execution result is fed back to the center cloud.

[0013] Preferably, the Internet of Things service terminal is further included; The data of the Internet of Things service terminal is derived from real-time alarm information of the fault judgment and processing module, preventive maintenance plans of the predictive maintenance module, and analysis reports generated by the center cloud, and the data update frequency is consistent with the data interaction period in the module cooperative mechanism; The Internet of Things service terminal includes a device state presentation end, a fault warning end, an alarm management end and a cloud data download end. The device state presentation end visually displays the device state through the device health index.

[0014] Compared with the prior art, the beneficial effects of the present application are: 1. The present application realizes local real-time processing and abnormality judgment of device data by deploying edge computing algorithm models in the Internet of Things base station, without relying on cloud centralized computing, greatly reducing data transmission delay, responding to device abnormalities in milliseconds, effectively solving the problem of fault discovery lag in high real-time scenarios, and ensuring the continuous and stable operation of medical devices.

[0015] 2. The present application also relies on the LSTM model in the core algorithm and rule to perform time series prediction on device state parameters, the decision tree algorithm to perform accurate classification of faults, and the data processing model to perform targeted processing on missing values and abnormal values, which can significantly improve the accuracy of edge fault judgment, avoid misjudgment caused by local rapid processing, and reduce the interference of invalid alarms on medical work.

[0016] 3. The present application also realizes dynamic data interaction and model collaborative optimization of the Internet of Things base station, the edge computing platform and the center cloud through the module cooperative mechanism, generates a preventive maintenance plan based on historical data through the predictive maintenance module, changes the traditional passive fault processing mode to an active prevention mode, reduces the probability of device sudden failure, further reduces the risk of medical service interruption caused by device downtime, and improves the overall reliability of the hospital Internet of Things system. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 The figure is a schematic diagram of the system framework of the present application. DETAILED DESCRIPTION

[0018] In order to facilitate those skilled in the art to understand the technical scheme of the present application, the technical scheme of the present application will be further described in conjunction with the drawings of the specification.

[0019] Example 1, as Figure 1As shown, this invention provides a hospital IoT device intelligent monitoring and fault early warning system based on edge computing, comprising: The data access and processing module is used to collect various types of data from the hospital's IoT devices and send them to a preset storage location, including a local database, a data processing module, and an abnormal data judgment unit; IoT base stations are used to connect IoT devices, collect device data, and realize intelligent monitoring and fault early warning through algorithm models. The algorithm models are built based on core algorithms and rules. The hospital's IoT edge computing platform is used to manage, analyze, and store data sent by IoT base stations using edge computing. The central cloud is used to receive data from edge computing and perform cloud computing analysis, model updates, and generate analysis reports. The fault diagnosis and handling module is used to detect and handle equipment faults in real time, generate fault alarms and handling records, including a fault handling database and a backend, the backend of which includes a system data center; The predictive maintenance module is used to predict faults using historical data, develop preventive maintenance plans, and determine the health status of equipment. The system also includes core algorithms and rules, as well as a module collaboration mechanism. The core algorithms and rules provide algorithmic support for data processing and analysis in each module, while the module collaboration mechanism is used to enable collaborative work between modules.

[0020] In embodiments of the present invention, the data access and processing module further includes a data acquisition module and a data transmission module; The data acquisition module establishes a connection with the hospital's IoT devices through an interface that matches the data acquisition data, and acquires real-time data, statistical data, alarm data and abnormal data at set acquisition intervals. The data transmission module encapsulates the collected data, adds a unique device identifier and a precise collection timestamp, and then synchronously sends it to the local database and IoT base station via the internal data transmission bus. The data sent to the local database is compressed and stored at fixed intervals to save space, while the data sent to the IoT base station maintains its original precision to ensure the accuracy of the analysis. The data acquisition module initially marks the continuously acquired abnormal data. The marking logic calculates the abnormal deviation of the data using the abnormal deviation formula. ,when When the value exceeds the set fault judgment threshold, it is marked as abnormal candidate data: ; in, Indicates the first The abnormal deviation of each collected data is a dimensionless parameter used to determine whether the data is an abnormal candidate data. Indicates the first The collected device data reflects the specific parameter values ​​of the device at a certain moment; This represents the historical average value of similar parameters for the equipment, serving as a benchmark value reflecting the long-term average level of the equipment's parameters. This represents the historical standard deviation of similar parameters for the device, used to measure the dispersion of historical data. This formula is used to measure the first The degree of deviation of each collected data point from the historical average level of similar parameters of the device. This is determined by calculating the... Data collected Compared with historical average The absolute difference, divided by the historical standard deviation. The dimensionless deviation is obtained. ,when When the data exceeds the set fault judgment threshold, it indicates that the data deviates significantly from the normal range. It is marked as abnormal candidate data, providing a preliminary screening basis for subsequent abnormal data verification. Historical average and standard deviation Update via sliding window: ; The historical average is dynamically updated using a sliding window approach. (The last part, "current moment," appears to be an error and doesn't translate directly.) Data collection and the historical average at the previous moment Based on this, by updating the coefficients Perform a weighted calculation to obtain the historical average at the current time. This update method allows the historical average to be continuously adjusted as new data is added, making it more consistent with the real-time changes in equipment parameters; ; in, express The historical average of the device parameters at any given time is an average that has been dynamically updated. This represents a dimensionless update coefficient, with a value between 0 and 1, used to adjust the weight of newly collected data and historical data in the update calculation; express The device data collected in real time, and With the same dimensions, it is the latest data that participates in the updating of historical mean and variance; express Historical average at time, and Same dimension, used for calculation Historical benchmark of historical average at any given time; express Historical variance at time, and The square of a unitary quantity reflects the fluctuation of current equipment parameters; express Data collection in real time and The square of the difference between the historical mean and the current time is used to calculate the contribution of the current data to the historical variance. express Historical variance at time, and Squares of the same dimension are used for calculation. Historical benchmark of historical variance at any given moment; Similar to the historical mean update logic, the historical variance is dynamically updated based on the data collected at the current moment. Compared with the current historical average The squared difference, combined with the historical variance at the previous time step. By updating the coefficients The historical variance at the current time is obtained by weighted calculation. Ensure that historical variance reflects the latest fluctuations in equipment parameters; Precise screening of abnormal data: The abnormal deviation formula can objectively identify abnormal candidate data that deviates from the normal range by quantitatively comparing the collected data with the historical mean and standard deviation, avoiding the subjectivity and error of manual judgment and improving the accuracy of the initial screening of abnormal data. Dynamically adapting to equipment changes: The sliding window update mechanism of historical mean and variance enables the benchmark value to be dynamically adjusted as the equipment operates over a long period of time, adapting to the slow drift of equipment parameters caused by factors such as aging and environmental changes, and ensuring the timeliness and applicability of the anomaly judgment benchmark. Improve system response speed: Through differentiated processing of data transmission modules, local database storage compresses data to save space, and IoT base stations receive raw data to ensure analysis accuracy. This balances data storage efficiency and subsequent analysis accuracy, providing a data foundation for rapid system response and anomaly handling. Providing reliable input for subsequent modules: The initially labeled abnormal candidate data provides high-quality input for subsequent processing steps such as secondary verification of IoT base stations, reduces the interference of invalid data on subsequent analysis, and improves the operating efficiency of the entire system and the reliability of analysis results.

[0021] In the embodiments of the present application, the Internet of Things base station is connected with various types of Internet of Things devices, including device drivers, data processing, remote control, data communication, rule engine, local storage, edge computing algorithms, edge computing rules, anomaly analysis module and prediction analysis module; The device driver contains special drivers for different brands and models of devices, which can quickly adapt to newly connected devices through dynamic loading, ensuring the compatibility of data acquisition; The data processing module performs format conversion and unit standardization processing on the received raw data; The rule engine stores device-specific fault judgment logic, which can be flexibly configured and modified through a visual operation interface to adapt to the characteristics of different devices; The local storage uses stable storage media to store recent raw data and analysis results by device classification. When the storage space is insufficient, the earliest historical data will be automatically overwritten in chronological order; The Internet of Things base station sends the generated fault warning information records to the Internet of Things edge computing platform in order of emergency; Data communication is realized through Wi-Fi to interface with the hospital Internet of Things edge computing platform, using wireless standards suitable for medical scenarios, suitable for high-precision equipment in the operating room for high-speed, short-distance data transmission scenarios; The data processing module performs secondary verification on the abnormal candidate data, and calculates the data fluctuation degree through the sliding window variance formula: ; Wherein, represents the variance of the data in the th sliding window, which is used to measure the dispersion degree and fluctuation of the data in the window; represents the dimensionless sliding window size, i.e. the number of data contained in the window, which determines the range of data involved in the calculation; represents the time index of the data, which is used to identify the data collected at different times in the window; represents the index of the sliding window, which represents the th window that is currently calculated; represents the mean value of the data in the th sliding window, which has the same dimension as , and is used as a reference value to measure the fluctuation of the data in the window; This formula is used to calculate the fluctuation degree of the data in a specific window, which is a secondary verification of the abnormal candidate data. With a window size , the th to the The difference between each data and the window mean is calculated and squared, and then the average of these squared values is calculated to obtain the window variance , , The greater the value of the window variance, the more intense the fluctuations of the data in the window, and in combination with the abnormal deviation degree , the abnormal data can be more accurately identified; When and satisfy the conditions at the same time (converted to the same order of magnitude by threshold conversion), the abnormal data is identified; The window mean is calculated by the following formula: ; This mean serves as the benchmark for data fluctuation calculation, and the dynamic mean forms a complementary verification of short-term and long-term benchmarks; This formula is used to calculate the average level of data in the sliding window, which serves as the benchmark for measuring the fluctuations of data in the window. The sum of the first to the last data in the window is calculated, and then divided by the window size to obtain the window mean , which reflects the concentration trend of data in the short term, and cooperates with the dynamic mean reflecting the long-term average level to evaluate the data from different time dimensions; The sliding window variance formula calculates the fluctuations of data within a certain range to further verify the preliminary marked abnormal candidate data, reducing the misjudgment caused by accidental factors. When and satisfy the conditions at the same time, the abnormal data is identified, greatly improving the accuracy of abnormal identification and avoiding unnecessary warnings; The window mean reflects the short-term average level of data, and the dynamic mean reflecting the long-term average level forms a complement. This combination enables the system to focus on both the instantaneous fluctuations of data and its long-term trend, evaluating the data state from multiple angles and improving the comprehensiveness of the judgment of the equipment running state; The size of the sliding window can be flexibly adjusted according to the characteristics of the equipment For equipment with rapid data fluctuations, a smaller window can be selected to quickly capture changes; for relatively stable equipment, a larger window can be selected to smooth short-term noise. This flexibility enables the system to better adapt to the running characteristics of different equipment, improving the adaptability of the system; The abnormal data confirmed by the secondary verification provides high-quality input data for subsequent modules such as edge computing and fault judgment of the Internet of Things base station, reduces the interference of invalid data on subsequent analysis, improves the operation efficiency and reliability of decision-making of the whole system, and helps to discover equipment failure in time and take measures.

[0022] In the embodiment of the application, the core algorithm and rules include an edge computing algorithm model, rule content and a data processing model, wherein the edge computing algorithm model and the data processing model are deployed in the Internet of Things base station, and the training and optimization of the algorithm model are completed in cooperation with the hospital Internet of Things edge computing platform and the central cloud; In the edge computing algorithm model, the LSTM model is deployed in the Internet of Things base station, and includes an input layer, multiple hidden layers and an output layer, and is trained by using an optimizer; the decision tree algorithm is deployed in the Internet of Things base station and is used for fault classification, taking common fault types of equipment as the classification target and selecting multiple equipment operation features related to faults as the classification basis; In the rule content, the fault judgment threshold is set as a fixed proportion of the normal operation parameter range according to the equipment type, and the equipment state evaluation is divided into three levels of health, mild abnormality and serious abnormality; In the data processing model, the processing logic is deployed in the Internet of Things base station, and the mean filling method is used to replace a small amount of continuous missing values with the mean of the surrounding valid data, and the missing values that reach a set number of continuous collection periods or have a missing proportion reaching a set proportion in a single batch of data are marked as data interruption; The abnormal values are detected and removed by statistical principles, the data is stored by using a time series database, and the index is established according to the equipment identifier and the time stamp to improve the query efficiency; The potential association between the faults and the equipment parameters is mined by using the association rule algorithm, and the complex rule iteration of the algorithm is completed by the central cloud; The parameter change trend is displayed by using a line chart, and the column chart is used to compare the fault rates of different equipment, and the visualized data is updated according to a set period; The abnormal data judgment unit of the data processing module of the data access and processing module uses the above data processing model to mark the faults in the fault history data that meet the serious abnormality characteristics, and the abnormal data judgment unit includes an equipment data judgment unit, which stores the historical normal operation parameter range of each equipment as a judgment reference; The prediction formula of the LSTM model for the equipment state parameter is: ; Wherein, represents the predicted value of the equipment state parameter at the moment, and has the same dimension as the equipment parameter, which is used to predict the future operation state of the equipment; The Sigmoid activation function is a dimensionless function, and its formula is: Its function is to map input values ​​to... An interval is used to determine the proportion of control information transmitted in a gating mechanism. This represents the weight matrix of the output layer. It is dimensionless and is used to weight the processed cell state values, thus affecting the output of the prediction results. The hyperbolic tangent function is dimensionless and its formula is: Input values ​​can be mapped to Intervals are used to process cell states and candidate cell states. express The cell state at any given time is dimensionless and is the core of the LSTM model, used to store long-term historical information. This represents the bias term of the output layer, and Same dimension, used to adjust the baseline value of the output layer; This formula is used to predict the device's performance. The state parameters at any given time. First, Cellular state at any given moment After the hyperbolic tangent function Processing, mapping values ​​to The interval, and then the output layer weight matrix. Multiply, plus the output layer bias Finally, it is activated by the Sigmoid function. Map the results to The interval is obtained Predicted value at time By comparing the predicted value with the actual value, the deviation can be used as the basis for triggering an early warning. Cell state The update relies on the combined action of the input gate, forget gate, and output gate: ; The input gate is used to determine which new information is stored in the cell state. Hidden state of time and Input data at any time After concatenation, it is combined with the input gate weight matrix. Multiply, plus input gate bias Then it goes through the Sigmoid activation function Processing yields the input gate output. Its value is Between these values, the closer the value is to 1, the more important that part of the information is. ; The forget gate is used to determine which information to discard from the cell state. Similarly, the and are concatenated, multiplied by the forget gate weight matrix , added with the forget gate bias , and processed by the Sigmoid activation function to get the forget gate output , whose value is between , and the closer to 1 means the more history information is kept; ; The formula generates the candidate cell state at the current time, which is obtained by concatenating and , multiplying by the candidate state weight matrix , adding the candidate state bias , and processing by the function to get the candidate cell state , whose value is between ; ; The update of the cell state combines the history information and the new information. The forget gate output is multiplied by the cell state at the last time to keep the history information needed; the input gate output is multiplied by the candidate cell state to get the new information needed to be added; and the two are added to get the cell state at the current time ; wherein represents the output of the input gate at the time, dimensionless, whose value is between , and controls the proportion of new information entering the cell state; represents the weight matrix of the input gate, dimensionless, used for weighted processing of the input information, and affects the output result of the input gate; represents the hidden state at the time, dimensionless, which contains important information of the past time and is used for the calculation at the current time; represents the input data at the time after normalization processing, dimensionless, and has the same meaning as , which is the input information of the model at the current time; represents the bias term of the input gate, dimensionless, used for adjusting the calculation reference of the input gate; represents the output of the forget gate at the current time step, dimensionless, with a value between and controls the proportion of historical information forgotten from the cell state; represents the weight matrix of the forget gate, dimensionless, used to weight the input information and affect the output of the forget gate; represents the bias term of the forget gate, dimensionless, used to adjust the calculation reference of the forget gate; represents the candidate cell state at the current time step, dimensionless, containing new information at the current time step, for cell state update; represents the weight matrix of the candidate cell state, dimensionless, used to weight the input information and affect the generation of the candidate cell state; represents the bias term of the candidate cell state, dimensionless, used to adjust the calculation reference of the candidate cell state; represents the cell state at the current time step, dimensionless, storing long-term information at the previous time step, providing a basis for the update of the current time cell state; The LSTM model can effectively capture the time series characteristics of device state parameters through a unique gating mechanism and cell state, and accurately predict the device state at This enables the system to predict potential device abnormalities in advance, providing a reliable basis for fault warning and helping to take preventive measures in a timely manner; Traditional recurrent neural networks are prone to gradient vanishing or explosion when processing long sequence data, while the LSTM model can selectively remember and forget information through cell state and gating mechanism, effectively solving the long-term dependency problem and being suitable for processing large amounts of time series data generated by long-term operation of hospital Internet of Things devices, ensuring the accuracy of long-term trend analysis of devices; The LSTM model is deployed on the Internet of Things base station and can directly process data and make predictions at the edge, reducing the amount of data transmitted to the cloud, reducing network bandwidth pressure, and accelerating the response speed of prediction, enabling edge computing to play a more efficient role in device monitoring; The training and optimization of the model rely on the cooperation of the edge computing platform and the central cloud, and can continuously adjust the model parameters according to new device operation data, making the model adapt to the characteristics of different devices and changes in different operating stages, improving the adaptability and generalization ability of the model in complex medical Internet of Things environments; By combining decision tree algorithms to classify faults, the prediction results of LSTM models can provide more dimensional feature information for fault classification, which helps to more accurately determine the fault type, provide more targeted guidance for subsequent fault handling and maintenance, and improve the fault handling efficiency of the system.

[0023] In an embodiment of the present invention, the hospital IoT edge computing platform and the IoT base station establish a connection through a stable network connection method, including a big data cloud computing cluster, an IoT data storage module, an IoT data upload module, and an edge computing management terminal; The system receives IoT data from the central cloud via an IoT data download interface and stores it on local storage devices according to device type. At the same time, it enables remote access to the data by different departments through access control, ensuring the security and relevance of data access. The edge computing management terminal realizes IoT device access management and configuration management through a web console, allocates edge computing tasks through task scheduling algorithms, optimizes network paths with dynamic routing algorithms, and automatically switches to backup paths when a certain path has too high latency. Task scheduling algorithms allocate resources by calculating device priority coefficients: ; in, Indicates the first The priority coefficient of each device is dimensionless and is used to measure the priority of the device in task scheduling. The higher the value, the higher the priority. The weighting coefficients representing the importance score of equipment are dimensionless and related to... Together, they determine the weight of the two evaluation indicators in the priority calculation, and ; Indicates the first The importance score of each device is dimensionless and ranges from 1 to 10. The higher the score, the more important the device is in the hospital's Internet of Things system. The weighting coefficient represents the current load rate of the equipment; it is dimensionless and related to... To facilitate a comprehensive evaluation of equipment priorities; Indicates the first The current load rate of the device is dimensionless and ranges from 0 to 1. It reflects the current resource usage of the device. The closer the value is to 1, the heavier the load. This formula is used to calculate the first... The priority coefficients of each device are used to determine the order in which edge computing tasks are allocated. This is achieved by scoring the importance of each device. and current load rate of equipment respectively multiplied by the corresponding weight coefficient and , and then added to obtain the priority coefficient Since , the weights of the two indicators in the comprehensive evaluation are reasonable, The higher the value, the higher the priority the device obtains in task scheduling, and it can obtain computing resources in priority; The device load rate U_m is calculated by the following formula: ; wherein represents the number of tasks currently being processed by the device, dimensionless, which is one of the important indicators for evaluating the load of the device; represents the maximum number of tasks that the device can carry, dimensionless, reflecting the upper limit of the task processing capacity of the device; represents the weight of the number of tasks in the load rate calculation, dimensionless, with a value range of , used to adjust the proportion of the number of tasks and CPU occupancy in the load evaluation; represents the current CPU occupancy rate of the device, dimensionless, usually expressed in percentage, reflecting the occupancy of the computing resources of the device; This formula is used to comprehensively evaluate the load of the device. First, the ratio of the current number of tasks to the maximum number of tasks that can be carried, and the ratio of the current CPU occupancy rate to 100%, are calculated, and then multiplied by the task number weight and , and finally the results are added to obtain the device load rate The formula takes into account both the number of tasks and the CPU occupancy rate, comprehensively reflecting the resource occupancy state of the device, and providing an accurate basis for the calculation of the priority coefficient; Through the device priority coefficient formula, the edge computing resources can be reasonably allocated according to the importance and current load of the device. Important and low-load devices are given priority to obtain resources, ensuring that the computing needs of critical devices (such as high-precision devices in the operating room) are met in priority, improving the rationality and effectiveness of resource utilization; The device load rate formula considers both the number of tasks and the CPU occupancy rate, avoiding the one-sidedness of single-index evaluation. It can reflect both the amount of tasks currently being processed by the device and the occupancy of computing resources, making the load evaluation more accurate and providing a reliable basis for priority calculation, which helps to avoid performance degradation due to high load of the device; Reasonable task scheduling enables edge computing tasks to run on the most suitable device, reduces task queuing waiting time and device idle time, improves the operation efficiency of the whole hospital Internet of Things edge computing platform, ensures that data processing and analysis can be completed quickly, and provides timely support for device monitoring and fault warning; Weight coefficient 、 and According to the actual situation, the task scheduling strategy can adapt to different application scenarios and device characteristics. For example, in the emergency medical scene, the weight of device importance can be increased to ensure that the key device runs first; when the device load is generally high, the weight of the load rate can be adjusted to balance the device burden, enhancing the adaptability and flexibility of the system; The calculation of the device load rate is linked and adapted to the calculation demand of the LSTM model. When the LSTM model has high calculation demand, the system can allocate more suitable device resources to it through the task scheduling algorithm to ensure the efficient operation of the model, realize the collaborative work between modules, and improve the stability and reliability of the whole system.

[0024] In the embodiment of the application, the center cloud is deployed in the hospital data center, including a central Internet of Things display monitoring module, a central Internet of Things management module and a center cloud database; Through the cloud data interaction interface, the edge computing algorithm model, rules and Internet of Things data from the Internet of Things edge computing platform are received, the Internet of Things data is cloud calculated and analyzed, the algorithm model and rules are updated and optimized, and the analysis report is stored in the center cloud database after being generated; The optimization of the edge computing model by the center cloud is realized through loss function iteration: ; Among them, Loss function, dimensionless, comprehensively reflects the model prediction error and parameter complexity, is the objective function of model optimization, and the smaller the value is, the better the model performance is; N represents the sample number, dimensionless, that is, the total number of data samples participating in model training; N represents the sample index, which is used to identify different training samples; Y represents the actual value of the nth sample, which is the same dimension as the device parameter, and is the target reference value predicted by the model; Y represents the model prediction value of the nth sample, which is the same as The meaning is consistent, that is, the prediction result output by the model; ​​denotes the regularization coefficient, dimensionless, used to adjust the weight of the regularization term in the loss function, the larger the value, the stronger the punishment of the model parameters; denotes the regularization term, dimensionless, measures the complexity of the model parameters; denotes the set of model parameters, dimensionless, contains all the parameters in the model that need to be learned and optimized; The formula is used to measure the deviation of the edge computing model prediction value from the actual value, which is the core index of model optimization. First, calculate the square of the difference between the actual value and the prediction value of each sample, and take the average to get the mean square error term, which reflects the prediction accuracy of the model; plus the regularization term multiplied by the regularization coefficient and the regularization term , used to control the complexity of the model parameters. By minimizing the loss function using the gradient descent method, the model parameters are constantly adjusted to achieve model optimization; The regularization term uses L2 regularization: ; where, denotes the parameter index, used to identify different parameters in the model; denotes the th parameter of the model, dimensionless, is the specific parameter that needs to be adjusted in the model optimization process; This formula is used to calculate the regularization term, which is obtained by summing the squares of all parameters in the model. Its role is to punish large model parameters and avoid overfitting the training data, so that the model can ensure prediction accuracy while having simpler parameters and improving adaptability to new data and different devices; The loss function considers both prediction error and parameter complexity, and minimizes the loss function by gradient descent method, which can improve prediction accuracy while avoiding excessive parameter complexity, achieving precise optimization of the edge computing model and improving the model's ability to analyze and predict hospital Internet of Things device data; The L2 regularization term effectively suppresses model overfitting by punishing large model parameters. In the hospital Internet of Things scenario, there are many types of devices and data differences, and regularization can prevent the model from relying too much on training data from specific devices, ensuring that the model works stably in different devices and data scenarios and improving the model's generalization ability; The optimized model has higher prediction accuracy and stronger adaptability, can more accurately analyze equipment operation data and judge equipment state, provides reliable basis for analysis reports generated by the center cloud, and improves the intelligent monitoring and fault warning capability of the whole system on the hospital Internet of Things equipment; The center cloud continuously optimizes the model based on the received edge computing platform data, so that the model can evolve with the accumulation of equipment operation data, adapt to performance changes and new fault modes in long-term equipment operation, ensure that the model performance always remains at a high level, and prolong the effective life cycle of the model; The model optimization mechanism ensures that the edge computing model and the center cloud model are updated in coordination, ensures that the processing logic and analysis standards of equipment data at the edge and in the cloud are consistent, avoids data interpretation deviation caused by model differences, and improves the consistency and reliability of the whole system data processing.

[0025] In the embodiment of the application, the fault judgment and processing module further comprises a fault processing alarm unit and a fault record statistics unit; The fault processing alarm unit sends device fault alarm information and device fault notification information to the background through a sound-light alarm and an SMS gateway; The fault processing alarm unit comprises a device fault alarm unit, a device fault notification unit and an alarm judgment unit; The alarm judgment unit compares the current data of the device with the preset threshold in real time, and sends an alarm information when a plurality of continuous collection periods exceed the threshold, the alarm information comprising accurate alarm time, clear alarm reason and specific alarm data; The fault record statistics unit is responsible for recording complete information of a single fault, and generating a fault detail file of a single device; The alarm judgment unit determines whether to trigger an alarm through a fault confidence formula: ; Wherein, The fault confidence is a dimensionless number, which comprehensively reflects the possibility of device failure, and is the core index for determining whether to trigger an alarm; The number of continuous abnormal periods is a dimensionless number, which refers to the number of periods in which the device data exceeds the preset threshold continuously within the judgment window; The total number of judgment window periods is a dimensionless number, which refers to the total number of periods included in the window for judging whether the device is faulty; The maximum abnormal deviation in the window is a dimensionless number, which is consistent with It refers to the maximum value of all abnormal deviation degrees in the judgment window, and reflects the severity of the abnormality; The formula is used for quantitative evaluation of the reliability of equipment failure, which is the key basis for triggering alarm. First, the ratio of the number of continuous abnormal periods to the total number of judgment windows is calculated, reflecting the frequency of abnormal data occurrence; then multiplied by the maximum abnormal deviation in the window, comprehensively considering the degree of abnormality. The product of the two is the failure confidence , The higher the value, the greater the possibility of equipment failure. When it exceeds the alarm threshold, the alarm is triggered; The alarm threshold is dynamically adjusted according to the type of equipment: ; Among them, represents the alarm threshold of the th equipment, dimensionless, which is the critical value for triggering alarm when the failure confidence exceeds it; represents the adjustment coefficient, dimensionless, greater than 1, used to adjust the alarm threshold based on the historical average failure confidence, making the threshold more consistent with the actual situation of the equipment; represents the historical average failure confidence of the th equipment, dimensionless, which is the average value of the failure confidence of the equipment in the past, reflecting the historical failure characteristics of the equipment; represents the equipment index, used to identify different equipment; This formula is used to dynamically determine the alarm threshold of different equipment. Based on the historical average failure confidence of the equipment, multiplied by the adjustment coefficient (greater than 1), the alarm threshold of the equipment is obtained. This setting can adapt the threshold to the historical failure characteristics of the equipment, avoid the inadaptation of alarm sensitivity to different equipment due to uniform threshold, and improve the accuracy and relevance of the alarm; The failure confidence formula considers the frequency and severity of abnormal data, avoiding false alarm triggered by single accidental abnormality and improving the accuracy of the alarm. Only when abnormal conditions persist and are relatively severe, the alarm will be triggered, reducing the interference of invalid alarm to the staff; The alarm threshold formula dynamically adjusts the threshold according to the historical average failure confidence of the equipment, so that different types and different use conditions of the equipment can have their own alarm standards. For example, for equipment with high failure rate, the threshold will be increased accordingly to avoid frequent alarms; for critical equipment, the alarm sensitivity can be improved by adjusting value to ensure timely detection of failure; Accurate alarm can make the designated personnel quickly obtain effective fault information, including alarm time, reason and data, so as to help the staff quickly locate the problem and take processing measures, shorten the fault processing time, and guarantee the normal operation of the hospital Internet of Things equipment; The reasonable alarm judgment mechanism and dynamic threshold adjustment make the fault judgment and processing module more reliably detect equipment failure, reduce the false alarm and false alarm situation. At the same time, the fault record statistics unit generates a fault detail file, which provides data support for equipment maintenance and analysis, and helps to continuously optimize system performance; The maximum abnormal deviation used in the fault confidence calculation Corresponding to the abnormal deviation , the coherent processing of data from collection, abnormal marking to fault judgment is realized, which embodies the synergy between the modules of the system and guarantees the integrity and effectiveness of the technical scheme.

[0026] In the embodiment of the present application, the background also includes a wireless gateway, an edge computing module and a remote terminal; The edge computing module filters and normalizes the device data; The remote terminal further includes a data classification unit, a data filtering unit and a data extraction unit; When the Internet of Things equipment fails, the edge computing module obtains device state abnormal data and health data after processing the Internet of Things data, and the edge computing module transmits the device state abnormal data and health data to the data processing module; The formula for normalizing the data by the edge computing module is: ; Wherein, The normalized data is dimensionless, and the value is between , which eliminates the dimensional and order differences of the original data and is used for subsequent fault judgment calculation; The historical minimum value represents the minimum value of the device parameter in history, which is one of the normalization bases; The historical maximum value represents the maximum value of the device parameter in history, which is another normalization base; The formula is used to convert the original device data into dimensionless data. By calculating the difference between the original data and the historical minimum value , and then dividing by the difference between the historical maximum value and the historical minimum value , the normalized data is obtained, and the value range is The processing can eliminate the influence of different equipment parameters caused by dimensional and magnitude differences, make the data comparable, and facilitate subsequent fault judgment unit for unified calculation and analysis. historical maximum value , Optimization through regular update mechanism: ; The formula is used to dynamically update the historical minimum value. Take the historical minimum value of the last time and the minimum value of the sampling data in the current update period , and the smaller one of the two is the historical minimum value of the current time , which ensures that the historical minimum value can reflect the latest minimum level of the equipment parameter and adapt to the parameter drift in long-term operation of the equipment; ; wherein, is the update period, dimensionless, indicating the time interval of historical extreme value update, which determines the range of sampling data included in each update; is the sampling data index, used to identify different sampling data in the update period; is the sampling data in the update period, which has the same dimension as , and is the basis for updating the historical extreme value; is the historical maximum value at time , which has the same dimension as , and reflects the maximum level of the current equipment parameter after dynamic update; is the historical maximum value at time , which has the same dimension as , and provides a historical reference for updating the historical maximum value at the current time; The formula is similar to the historical minimum value update logic, which is used to dynamically update the historical maximum value. Take the historical maximum value of the last time and the maximum value of the sampling data in the current update period , and the larger one of the two is the historical maximum value of the current time , which ensures that the historical maximum value can reflect the latest maximum level of the equipment parameter, and makes the normalization reference more suitable for the actual operation of the equipment; The data normalization formula converts the original equipment data of different dimensions and different magnitudes to the interval, eliminates the differences between the data, makes the parameters (such as temperature and pressure) that cannot be directly compared comparable, provides convenience for unified analysis and calculation of the fault judgment unit, and improves the accuracy of the analysis results; The periodic updating mechanism of the historical extreme value avoids normalization distortion caused by fixed reference value, and dynamically adjusts with slow drift of parameters in long-term operation of the equipment. And The edge computing module locally normalizes the data, reducing the amount of raw data transmitted to the cloud and reducing network transmission pressure. At the same time, the normalized data is more suitable for fast computing and analysis at the edge, improving the efficiency of edge computing and enabling quick completion of fault judgment and other processing at the edge. The normalized data provides standardized input for the fault judgment unit, ensuring consistency in fault confidence calculations. The historical extreme value updating and dynamic mean updating complement each other, dynamically tracking changes in device parameters from both extreme value and mean value dimensions, fully reflecting the device operating state and enhancing the accuracy of the system's device state assessment. The stable normalization reference and dynamic updating mechanism ensure that the data processing process is not affected by short-term fluctuations and long-term drifts in device parameters, ensuring the stability of data processing. This provides high-quality data support for subsequent fault alarm and predictive maintenance modules, helping to improve the stability and reliability of the entire system.

[0027] In an embodiment of the present application, the predictive maintenance module includes a prediction judgment unit, a prediction data storage unit, a prediction database, a cloud prediction module, and a wireless cloud prediction module. The prediction judgment unit predicts the probability of future faults and possible fault causes based on accumulated operating data and historical fault records stored by the system during the device's operating period. The operating period and subsequent use period are pre-set based on device type and hospital operation and maintenance requirements. The prediction maintenance module sets a prediction model, and the training data of the prediction model comes from long-term accumulated historical fault data and device operating data. The model parameters are adjusted through cross-validation method, and accuracy, recall rate and F1 value are used as evaluation indexes. When the indexes reach the preset standard, the model training is completed and put into use. The model is retrained regularly to adapt to changes in device performance. The prediction judgment unit outputs the future fault probability through a fault probability prediction formula: ; Where, P represents the fault probability in the future preset period, dimensionless, and the value range is 0-1, which represents the possibility of future device failure. ​This represents the Sigmoid function, which maps the input composite variables to the 0-1 interval to obtain the failure probability; and These represent dimensionless coefficients, used to adjust the historical average fault confidence level. and historical average volatility Weights in failure probability prediction; It represents the historical average failure confidence level, is dimensionless, and reflects the average level of the equipment's historical failure confidence level; This represents the historical average volatility, which is dimensionless. The normalized average value reflects the average degree of fluctuation in the equipment's historical data; This represents the bias term, used to adjust the baseline value of the comprehensive variables so that the failure probability prediction is more in line with the actual situation of the equipment. This formula is used to predict the probability of equipment failure within a preset future period. First, the historical average failure confidence level is calculated. and historical average volatility Multiply by the coefficient respectively and In addition to the bias term This yields a composite variable; then, this composite variable is input into the Sigmoid function. Mapping the results to the range of 0-1 yields the failure probability. , The closer the value is to 1, the greater the likelihood of future equipment failure, providing a basis for developing preventative maintenance plans; Historical average failure confidence The calculation method is as follows: ; in, This represents the number of historical fault samples, which is dimensionless and is used to calculate the historical average fault confidence level. This represents the historical fault index, used to identify different historical fault records; Indicates the first The confidence level of each historical failure is dimensionless and is the basic data for calculating the confidence level of the historical average failure.

[0028] In embodiments of the present invention, the module collaboration mechanism includes a three-level architecture collaboration mechanism and a fault judgment and processing module and a predictive maintenance module collaboration mechanism; The three-level architecture coordination mechanism is that the Internet of Things base station uploads real-time data to the edge computing platform at a preset period, the data format adopts a unified format, and the key fields include device identification, collection time, parameter name and value; The edge computing platform uploads the summary data to the central cloud at a preset period; The central cloud sends the updated model and rule to the edge computing platform at a preset period, and the file integrity is ensured through data verification before sending, and an abnormal processing mechanism is provided; The fault judgment and processing module and the prediction maintenance module cooperate to synchronize the time of all devices in the system by using the network time protocol, so as to ensure the consistency of data time and automatically calibrate regularly; The prediction maintenance module obtains the recent fault data from the fault judgment and processing module at a preset period, and combines the locally stored device operation data to perform fault prediction, and when obtaining the fault data, the prediction maintenance module selects valid data according to the time stamp and verifies the data integrity; The abnormal processing mechanism in the three-level architecture coordination is that when data transmission fails, the sender retransmits the data after waiting for a set time, the retransmission times do not exceed the set times, and if the retransmission still fails, the transmission log is recorded and manual intervention is triggered for reminding; When the instruction is lost, the receiver does not receive the instruction within a set time, sends an instruction loss notification to the sender, and the sender reissues the instruction; When the central cloud needs to send a control instruction to the Internet of Things base station, the instruction is forwarded through the edge computing platform, the edge computing platform records the instruction transmission state, and the execution result is fed back to the central cloud.

[0029] In the embodiment of the application, the Internet of Things service terminal is further included; The data of the Internet of Things service terminal is derived from the real-time alarm information of the fault judgment and processing module, the preventive maintenance plan of the prediction maintenance module, and the analysis report generated by the central cloud, and the data update frequency is consistent with the data interaction period in the module coordination mechanism; The Internet of Things service terminal includes a device state presentation end, a fault warning end, an alarm management end and a cloud data download end; The device state presentation end directly displays the device state through the device health index: ; Among them, is the health index, is the sum of the fault probabilities of the future multiple periods, is the sum of the recent fault confidence, is the normalization coefficient, The closer to 1, the healthier the device state is.

[0030] The embodiments of the present application disclose the preferred embodiments, but are not limited to the same. Those skilled in the art can easily understand the spirit of the present application according to the above embodiments, and make different inferences and changes, as long as they do not deviate from the spirit of the present application, and are within the protection scope of the present application.

Claims

1. A hospital IoT device intelligent monitoring and fault early warning system based on edge computing, characterized in that, include: The data access and processing module is used to collect various types of data from the hospital's IoT devices and send them to a preset storage location, including a local database, a data processing module, and an abnormal data judgment unit; An IoT base station is used to connect IoT devices, collect device data, and realize intelligent monitoring and fault early warning through an algorithm model, which is built based on core algorithms and rules. The hospital's IoT edge computing platform is used to manage, analyze, and store data sent by IoT base stations using edge computing. The central cloud is used to receive data from edge computing and perform cloud computing analysis, model updates, and generate analysis reports. The fault diagnosis and handling module is used to detect and handle equipment faults in real time, generate fault alarms and handling records, including a fault handling database and a backend, the backend including a system data center; The predictive maintenance module is used to predict faults using historical data, develop preventive maintenance plans, and determine the health status of equipment. The system also includes core algorithms and rules, as well as a module collaboration mechanism. The core algorithms and rules provide algorithmic support for data processing and analysis of each module, while the module collaboration mechanism is used to enable collaborative work between modules.

2. The intelligent monitoring and fault early warning system for hospital IoT devices based on edge computing according to claim 1, characterized in that, The data access and processing module also includes a data acquisition module and a data transmission module; The data acquisition module establishes a connection with the hospital's IoT devices through an interface that matches the data acquisition data, and acquires real-time data, statistical data, alarm data and abnormal data at set acquisition intervals. The data transmission module encapsulates the collected data, adds a unique device identifier and a precise collection timestamp, and then synchronously sends it to the local database and IoT base station via the internal data transmission bus. The data acquisition module initially marks the continuously acquired abnormal data, and the marking logic calculates the abnormal deviation of the data using an anomaly deviation formula. ,when When the value exceeds the set fault judgment threshold, it is marked as abnormal candidate data.

3. The intelligent monitoring and fault early warning system for hospital IoT devices based on edge computing according to claim 2, characterized in that, The IoT base station is connected to IoT devices and includes device drivers, data processing, remote control, data communication, rule engine, local storage, edge computing algorithm, edge computing rules, anomaly analysis module, and predictive analysis module. The IoT base station will record the generated fault warning information, sort it by urgency, and send it to the IoT edge computing platform. The data processing module performs secondary verification on the abnormal candidate data and calculates the degree of data fluctuation using the sliding window variance formula.

4. The intelligent monitoring and fault early warning system for hospital IoT devices based on edge computing according to claim 3, characterized in that, The core algorithms and rules include edge computing algorithm models, rule content, and data processing models. The edge computing algorithm models and data processing models are deployed on IoT base stations, and the training and optimization of the algorithm models are completed collaboratively by the hospital's IoT edge computing platform and the central cloud. In the edge computing algorithm model, the LSTM model is deployed on the Internet of Things base station and includes an input layer, multiple hidden layers, and an output layer. It is trained using an optimizer. The decision tree algorithm is deployed in IoT base stations for fault classification. It takes common fault types of equipment as the classification target and selects multiple fault-related equipment operating features as the classification basis. In the rules, the fault judgment threshold is set as a fixed proportion of the normal operating parameter range according to the equipment type, and the equipment status assessment is divided into three levels: healthy, slightly abnormal, and seriously abnormal. In the data processing model, the processing logic is deployed on the Internet of Things base station. The mean-filling method is used to replace a small number of consecutive missing values ​​with the mean of the surrounding valid data. Missing values ​​that have reached a set number of consecutive collection cycles or a set proportion of missing data in a single batch are marked as data interruptions. Outliers are detected and removed using statistical principles, and data is stored in a time-series database with indexes created based on device identifiers and timestamps. The algorithm uses association rule analysis to uncover potential correlations between faults and equipment parameters. The complex rule iterations of this algorithm are completed by the central cloud. Line charts are used to display parameter change trends, and bar charts are used to compare the failure rates of different devices. The visualized data is updated according to a set period. The abnormal data judgment unit of the data processing module of the data access and processing module adopts the above-mentioned data processing model to mark faults that meet the serious abnormality characteristics in the fault history data. The abnormal data judgment unit includes a device data judgment unit, which stores the historical normal operating parameter range of each device as the judgment benchmark.

5. The intelligent monitoring and fault early warning system for hospital IoT devices based on edge computing according to claim 4, characterized in that, The hospital's IoT edge computing platform establishes a connection with IoT base stations through a stable network connection method, including a big data cloud computing cluster, an IoT data storage module, an IoT data upload module, and an edge computing management terminal; The system receives IoT data from the central cloud via an IoT data download interface and stores it on local storage devices according to device type. At the same time, it enables remote access to the data by different departments through access control, ensuring the security and relevance of data access. The edge computing management terminal realizes IoT device access management and configuration management through a web console, allocates edge computing tasks through task scheduling algorithms, optimizes network paths with dynamic routing algorithms, and automatically switches to backup paths when a certain path has too high latency. The central cloud is deployed in the hospital's data center and includes a central IoT display and monitoring module, a central IoT management module, and a central cloud database. The system receives edge computing algorithm models, rules, and IoT data from the IoT edge computing platform through a cloud data interaction interface. It performs cloud computing and analysis on the IoT data, updates and optimizes the algorithm models and rules, generates analysis reports, and stores them in the central cloud database.

6. The intelligent monitoring and fault early warning system for hospital IoT devices based on edge computing according to claim 5, characterized in that, The fault diagnosis and processing module also includes a fault processing alarm unit and a fault record statistics unit; The fault handling alarm unit sends equipment fault alarm information and equipment fault notification information to the backend through the audible and visual alarm and SMS gateway; The fault handling alarm unit includes an equipment fault alarm unit, an equipment fault notification unit, and an alarm judgment unit; The alarm judgment unit compares the current data of the device with the preset threshold in real time. When the threshold is exceeded for multiple consecutive collection cycles, an alarm message is issued. The alarm message includes the precise alarm time, the clear alarm reason and the specific alarm data. The fault recording and statistics unit is responsible for recording complete information about a single fault and generating a fault detail file for each device. The alarm judgment unit determines whether an alarm is triggered by using a fault confidence formula.

7. The intelligent monitoring and fault early warning system for hospital IoT devices based on edge computing according to claim 6, characterized in that, The backend also includes a wireless gateway, an edge computing module, and a remote terminal; The edge computing module filters and normalizes device data; The remote terminal also includes a data classification unit, a data filtering unit, and a data extraction unit; When an IoT device malfunctions, the edge computing module processes the IoT data to obtain abnormal device status data and health data, and then transmits the abnormal device status data and health data to the data processing module.

8. The intelligent monitoring and fault early warning system for hospital IoT devices based on edge computing according to claim 7, characterized in that, The prediction maintenance module includes a prediction judgment unit, a prediction data storage unit, a prediction database, a cloud prediction module, and a wireless cloud prediction module; The prediction and judgment unit predicts the probability of failure and possible causes of failure in the subsequent use cycle of the equipment based on the operating data accumulated during the equipment's operating cycle and the historical fault records stored in the system.

9. A hospital IoT device intelligent monitoring and fault early warning system based on edge computing according to claim 8, characterized in that, The module collaboration mechanism includes a three-level architecture collaboration mechanism and a collaboration mechanism between the fault judgment and handling module and the predictive maintenance module. The three-level architecture collaboration mechanism is that the IoT base station uploads real-time data to the edge computing platform at a preset period. The data format adopts a unified format and includes key fields such as device identifier, collection time, parameter name and value. The edge computing platform uploads aggregated data to the central cloud at preset intervals; The central cloud distributes updated models and rules to the edge computing platform at a preset cycle, and ensures file integrity through data verification before distribution. The collaborative mechanism between the fault diagnosis and handling module and the predictive maintenance module is to use the Network Time Protocol to synchronize the time of all devices in the system. The predictive maintenance module obtains recent fault data from the fault diagnosis and handling module at a preset cycle, and combines it with locally stored equipment operation data to predict faults. When obtaining fault data, the predictive maintenance module filters valid data based on timestamps and verifies data integrity. When the central cloud needs to issue control commands to the IoT base station, the commands are forwarded through the edge computing platform. The edge computing platform records the command transmission status and feeds back the execution results to the central cloud.

10. A hospital IoT device intelligent monitoring and fault early warning system based on edge computing according to claim 9, characterized in that, It also includes IoT service terminals; The data of the IoT service terminal comes from real-time alarm information from the fault diagnosis and handling module, preventive maintenance plans from the predictive maintenance module, and analysis reports generated by the central cloud. The data update frequency is consistent with the data interaction cycle in the module collaboration mechanism. The IoT service terminal includes a device status display terminal, a fault early warning terminal, an alarm management terminal, and a cloud data download terminal; The device status display interface visually shows the device status through the device health index.

Images