Composite medical instrument collaborative state monitoring and intelligent regulation and control system based on Internet of Things

Abstract

The invention discloses a composite medical instrument collaborative state monitoring and intelligent regulation and control system based on the Internet of Things, and mainly relates to the technical field of medical instrument Internet of Things. Comprising a state monitoring module, a data processing module, a collaborative decision-making module, an intelligent regulation and control module and an Internet of Things communication module, the state monitoring module is configured to collect real-time state data of at least one medical instrument; the data processing module is configured to process and analyze the state data; the collaborative decision-making module is configured to generate a collaborative regulation and control instruction based on the processed data, and the collaborative regulation and control instruction is used for coordinating operation of a plurality of medical instruments; the intelligent regulation and control module is configured to regulate and control the medical instrument according to the regulation and control instruction; the Internet of Things communication module is configured to perform data communication between the modules and with an external device. The medical equipment management system has the advantages that multi-equipment cooperative monitoring, intelligent regulation and control and data intercommunication are achieved, and the medical equipment management efficiency and safety are improved.

Description

Technical Field

[0001] This invention relates to the field of Internet of Things (IoT) technology for medical devices, specifically an IoT-based collaborative status monitoring and intelligent control system for composite medical devices. Background Technology

[0002] With the widespread application of IoT technology in the medical field, remote status monitoring technology for individual medical devices has gradually matured. Currently, there are sensor network-based device monitoring solutions on the market that can collect operating parameters (such as temperature and voltage) of individual devices and wirelessly transmit the data to a central server for basic analysis. Some advanced systems integrate simple threshold alarm functions, triggering warnings when monitored data exceeds preset ranges.

[0003] However, the following problems still exist: 1. Lack of multi-device collaborative control capability: The existing system can only monitor and manage independent devices, and cannot perform status collaborative analysis and joint control of composite device groups that work together to complete medical tasks; 2. Insufficient depth of data analysis: The system is mostly limited to basic data collection and simple threshold judgment, lacking trend prediction, correlation analysis and intelligent decision support for equipment operating status; 3. System response lag: There is a significant delay in the entire process from status monitoring to execution control, which makes it difficult to meet the needs of clinical scenarios with high real-time requirements.

[0004] Therefore, there is an urgent need for an IoT-based collaborative status monitoring and intelligent control system for medical devices to solve the above problems. Summary of the Invention

[0005] The purpose of this invention is to provide a collaborative status monitoring and intelligent control system for composite medical devices based on the Internet of Things. It realizes collaborative monitoring, intelligent control and data interoperability of multiple devices, thereby improving the efficiency and safety of medical device management.

[0006] To achieve the above objectives, the present invention employs the following technical solution: This invention provides an Internet of Things-based collaborative status monitoring and intelligent control system for composite medical devices, comprising: The system includes a status monitoring module, a data processing module, a collaborative decision-making module, an intelligent control module, and an IoT communication module. The status monitoring module is configured to collect real-time status data of at least one medical device, including temperature, pressure, motion parameters, and power consumption. The data processing module is configured to process and analyze the state data, and the processing and analysis specifically includes: filtering, feature extraction, and anomaly detection of the state data; The collaborative decision-making module is configured to generate collaborative control instructions based on the processed data, and the collaborative control instructions are used to coordinate the operation of several medical devices. The intelligent control module is configured to control the medical device according to the control command; The IoT communication module is configured to perform data communication between the modules and with external devices.

[0007] Preferably, the status monitoring module includes several sensor units, including a temperature sensor, a pressure sensor, a motion sensor, and a power monitoring sensor; The temperature sensor is configured to measure the surface temperature or internal temperature of the medical device. The pressure sensor is configured to monitor the pneumatic or hydraulic parameters of the medical device; The motion sensor is configured to detect the displacement, acceleration, or angular velocity of the medical device. It employs a triaxial accelerometer and a gyroscope, with a sampling frequency of 100Hz. The power monitoring sensor is configured to measure the voltage, current, and power of the medical device; The status monitoring module also includes a data preprocessing unit, which performs noise reduction and standardization on the collected raw data. The noise reduction uses a moving average filtering algorithm, and the standardization converts the data into a format with zero mean and unit variance. The status monitoring module is connected to the data processing module via wired or wireless means.

[0008] Preferably, the data processing module includes a data storage unit, a feature extraction unit, and an anomaly detection unit; The data storage unit is configured to store historical state data and real-time data, and uses non-volatile memory. The data storage format is JSON or binary format. The feature extraction unit is configured to extract key features from the state data, including time-domain features and frequency-domain features. The time-domain features include mean, variance, and peak value, while the frequency-domain features are calculated using fast Fourier transform. The extracted features are used for subsequent analysis and decision-making. The anomaly detection unit is configured to identify anomalies in the state data, using a statistical Z-score algorithm, as follows: ; in, This represents the standardized outlier score. Represents the original data points. This represents the mean of the dataset. Represents the standard deviation of the dataset; when When this happens, it is judged as abnormal; The data processing module also integrates a machine learning model for state prediction. This model employs a linear regression algorithm and is expressed as follows: ; in, Indicates the predicted state value. to Indicates the input feature variables. Represents the intercept term. to Represents the regression coefficient; The model is trained using historical data, and the parameters are optimized using gradient descent during the training process.

[0009] Preferably, the anomaly detection unit in the data processing module further integrates a deep learning model for complex anomaly pattern recognition. The model employs a convolutional neural network, and its forward propagation formula is: ; in, Indicates the first The activation value of the layer, Indicates the first The weight matrix of the layer, Indicates the first Layer bias vector, The activation function is represented by the ReLU function, defined as follows: The convolutional neural network includes an input layer, convolutional layers, pooling layers, and a fully connected layer. The input layer receives a state data vector, the convolutional layers use 3x3 convolutional kernels to extract local features, the pooling layers use max pooling to reduce parameters, and the fully connected layer outputs the anomaly probability. The training process uses the backpropagation algorithm, and the loss function is the cross-entropy loss, expressed as: ; in, Indicates the loss value. Indicates the number of samples. Indicates the true label, Indicates the predicted probability; The model is trained using GPU acceleration, and the training dataset contains no fewer than 100,000 samples.

[0010] Preferably, the collaborative decision-making module includes a rule engine unit, an optimization algorithm unit, and a decision output unit; The rule engine unit is configured to store preset control rules, which are based on the medical device's operation manual and clinical guidelines, including reducing power if the temperature exceeds a threshold and activating a safety mode if the pressure is abnormal. The optimization algorithm unit is configured to generate the optimal control command, and adopts a multi-objective optimization algorithm with the objective function being: ; in, Describe the overall objective function. Represents the energy consumption function. Represents the performance function. and Represents the weight coefficient and , This represents a decision variable vector, which includes the operating parameters of the medical device. The decision output unit is configured to output a coordinated control command, which includes adjusting temperature, pressure or motion parameters, and is sent to the intelligent control module via the Internet of Things communication module. The collaborative decision-making module also supports real-time learning, dynamically adjusting rules and weights based on feedback data.

[0011] Preferably, the optimization algorithm unit in the collaborative decision-making module further employs a genetic algorithm for multi-objective optimization, the steps of which include: Initialize the population and set the population size to 100, with each individual representing a set of decision variables; Calculate the fitness function, which is based on the objective function. And add constraints; The selection operation uses a roulette wheel selection method, where the selection probability is directly proportional to the fitness. The crossover operation uses a single-point crossover with a crossover probability of 0.8. The mutation operation uses Gaussian mutation with a mutation probability of 0.1; The population is updated iteratively, with a maximum of 1000 iterations. The formula for the genetic algorithm is expressed as follows: ; in, Indicates the generation number of the population. Indicates a selection operation. Indicates an interleaving operation. Indicates the mutation operation; The optimization algorithm unit also integrates a real-time adaptive mechanism to dynamically adjust the weight coefficients according to the system load. and .

[0012] Preferably, the intelligent control module includes an actuator unit, a feedback control unit, and a safety protection unit; The actuator unit is configured to adjust the operating parameters of the medical device according to the control command, including adjusting the temperature of the heating element, controlling the pressure of the pump, or adjusting the speed of the motor. The actuator unit uses a stepper motor or a servo motor; the feedback control unit is configured to monitor the control effect and uses a PID controller, whose control formula is: ; in, Indicates control output. This indicates the error signal, which is the difference between the set value and the actual value. Represents the proportionality coefficient. Represents the integral coefficient. Represents the differential coefficient; The safety protection unit is configured to stop the medical device in an emergency under abnormal circumstances, including over-temperature protection, over-voltage protection and power failure protection; The intelligent control module receives instructions through the Internet of Things (IoT) communication module and uploads control logs in real time.

[0013] Preferably, the IoT communication module includes a data transmission unit, a protocol conversion unit, and a network security unit; The data transmission unit is configured to use the MQTT or CoAP protocol for data exchange and supports bidirectional communication. The protocol conversion unit is configured to convert the data formats of different medical devices into a unified format, using JSON or XML schema. The network security unit is configured to encrypt data transmission, employing the AES-256 encryption algorithm and implementing an authentication mechanism.

[0014] Preferably, the system further includes a user interaction module and a log recording module; The user interaction module is configured to display status data and control results through a graphical user interface, supports touch screen operation, and the interface elements include real-time curves, alarm indicators, and parameter setting panels. The log recording module is configured to store the system operation history, including status data, control instructions and abnormal events, using a time-series database, and the data retention time is not less than 1 year; The user interaction module also supports remote access, which can be achieved through a web interface or mobile application, and uses RESTful API for data interaction. The log recording module integrates data analysis tools for generating reports and trend analysis, with report formats including PDF and CSV.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. Through the multi-sensor fusion acquisition of the status monitoring module and the intelligent analysis of the collaborative decision-making module, the system breaks through the limitations of traditional single device independent operation. It can acquire the operating status data of multiple medical devices in real time and generate collaborative control instructions based on preset rules and optimization algorithms, enabling the device group to work collaboratively as a whole. 2. The system adopts a multi-level data processing architecture, integrating traditional statistical algorithms and deep learning models. It obtains time-domain and frequency-domain features through feature extraction units, and combined with the complex pattern recognition capabilities of convolutional neural networks, it can mine deep patterns from massive monitoring data. 3. Through distributed architecture design and the application of edge computing technology, the system rationally distributes data processing tasks across three levels: terminals, edge nodes, and cloud platforms. The average response time is significantly reduced, greatly improving the system's real-time performance and meeting the immediate response needs of critical medical scenarios such as emergency care and surgery. 4. The intelligent control module adopts a combination of PID controller and advanced actuator, which realizes precise control of the working parameters of medical devices. At the same time, through real-time correction of the feedback control unit, the system can effectively suppress external interference and maintain the long-term stability of equipment operation. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the system structure of the present invention; Figure 2 This is a flowchart of the multi-objective optimization method of the optimization algorithm unit of the present invention. Detailed Implementation

[0017] The present invention will be further illustrated below with reference to specific embodiments. It should be understood that these embodiments are for illustrative purposes only and are not intended to limit the scope of the invention. Furthermore, it should be understood that after reading the teachings of this invention, those skilled in the art can make various alterations or modifications to the invention, and these equivalent forms also fall within the scope defined in this application.

[0018] In this invention, terms such as "upper," "lower," "left," "right," "front," "back," "vertical," "horizontal," "side," and "bottom" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are only used to facilitate the description of the structural relationships of the various components or elements of this invention and do not specifically refer to any component or element in this invention. They should not be construed as limiting the invention.

[0019] Example: This embodiment provides an IoT-based collaborative status monitoring and intelligent control system for composite medical devices, which has been specifically applied in the intensive care unit (ICU). For example... Figure 1As shown, the system adopts a distributed architecture design, including a status monitoring module, a data processing module, a collaborative decision-making module, an intelligent control module, an IoT communication module, a user interaction module, and a log recording module. These modules are interconnected through the IoT communication module to form a complete monitoring and control closed loop.

[0020] 1. Specific implementation of the status monitoring module: In an ICU setting, the status monitoring module is responsible for real-time status monitoring of critical medical equipment such as ventilators, ECG monitors, infusion pumps, and defibrillators. This module comprises multiple sensor units, with the following specific configuration: The temperature sensor uses a PT100 platinum resistance temperature sensor with a measurement range of 0-100℃ and an accuracy of ±0.1℃. In ventilator applications, the temperature sensor is installed in the gas output line to monitor the temperature of the output gas in real time. The sampling frequency is 10Hz. When an abnormal temperature is detected, the system can issue an early warning within 100ms. The pressure sensor is an MPX5100DP piezoresistive pressure sensor with a range of 0-100kPa and an accuracy of ±0.5%FS. In the ventilator system, the pressure sensor is installed in the airway circuit to monitor changes in airway pressure. The sensor output signal is converted by ADC and then transmitted to the data preprocessing unit through the SPI interface. The motion sensor uses the MPU-6050 six-axis motion processing sensor, which includes a three-axis accelerometer and a three-axis gyroscope. This sensor is installed on a mobile medical device to monitor the device's displacement, vibration and attitude. The accelerometer range is ±16g, the angular velocity range is ±2000° / s, and the sampling frequency is set to 100Hz, which can accurately capture the device's micro-vibrations and displacement changes. The power monitoring sensor uses an ACS712 Hall effect current sensor and an ADS1115 analog-to-digital converter. The voltage measurement range is 0-240VAC, the current measurement range is 0-20A, and the power measurement accuracy is ±1%. This sensor monitors the power consumption of the equipment in real time and communicates with the main controller through an I2C interface. The data preprocessing unit uses an STM32H7 series microcontroller to process the acquired raw data in real time. The noise reduction process uses a moving average filtering algorithm with a window size of 10 sampling points. The standardization process uses the z-score standardization method to convert the data into a distribution with a mean of 0 and a standard deviation of 1. The processed data is transmitted to the data processing module via a CAN bus.

[0021] 2. Specific implementation of the data processing module: The data processing module uses a Raspberry Pi 4B as the main controller, equipped with 8GB of RAM and a 128GB solid-state drive. The data storage unit uses a MySQL database, and the storage structure includes a device information table, a real-time data table, a historical data table, and an exception record table. The data storage format is JSON, which facilitates data transmission and parsing. The feature extraction unit implements time-domain and frequency-domain feature extraction algorithms. Time-domain features include: Mean: , variance: , Peak value: , Frequency domain features are calculated using Fast Fourier Transform (FFT) with the Cooley-Tukey algorithm, 1024 sampling points, and a frequency resolution of 0.977Hz. The feature extraction process is implemented on a dedicated DSP chip with a processing latency of less than 5ms. The anomaly detection unit implements a multi-layer detection mechanism. The first layer uses the Z-score algorithm, with a threshold set at [value missing]. The second layer uses a linear regression prediction model, and the least squares method is used to estimate the regression coefficients: ; in For the characteristic matrix, The target variable is used; the third layer uses a convolutional neural network, and the network structure includes: Input layer: Receives state data from 1000 sampling points. Convolutional layer: 32 3×3 convolutional kernels, stride 1, ReLU activation function. Pooling layer: 2×2 max pooling, Fully connected layer: 128 neurons Output layer: 2 neurons (normal / abnormal); The training process used the Adam optimizer with a learning rate of 0.001, a batch size of 64, and 100 training epochs. The model was deployed on an NVIDIA Jetson Nano, and the inference time was less than 20ms.

[0022] 3. Specific implementation of the collaborative decision-making module: The collaborative decision-making module uses an x86 architecture industrial computer, equipped with an Intel i7 processor and 16GB of memory. The rule engine unit is implemented based on the Drools rule engine and contains more than 200 business rules, such as: Rule 1: When the airway pressure of the ventilator exceeds 40 cmH2O for 10 seconds, an overpressure warning is triggered and the tidal volume is automatically adjusted. Rule 2: When the ECG monitor shows a heart rate exceeding 150 beats / min, automatically adjust the infusion pump's drug delivery rate; The optimization algorithm unit implements multi-objective optimization algorithms, such as... Figure 2 As shown, the optimization process includes the following steps: (1) Problem Modeling: The equipment control problem is transformed into a multi-objective optimization problem, with the objective function being: , in Represents the energy consumption function. This represents a performance function, with weighting coefficients dynamically adjusted based on clinical needs. (2) Genetic Algorithm Optimization: An improved NSGA-II algorithm is adopted, with the following specific parameters: Population size: 100 Crossover probability: 0.8 Mutation probability: 0.1 Maximum number of iterations: 1000; (3) Decision output: Select the most suitable control scheme for the current scenario based on the Pareto optimal solution set; The real-time learning mechanism is based on the Q-learning algorithm, with a learning rate of... Discount factor Decision-making strategies are updated by continuously receiving feedback data.

[0023] 4. Specific implementation of the intelligent control module: The intelligent control module adopts a modular design, including an actuator unit, a feedback control unit, and a safety protection unit; The actuator unit includes: Temperature control: Employs SSR solid-state relays with a control accuracy of ±0.1℃. Pressure control: A proportional valve is used, with a control accuracy of ±0.5%. Speed ​​control: Servo motors are used, with a control accuracy of ±0.01%; The feedback control unit implements a digital PID controller, employing an incremental PID algorithm. , The parameters were tuned using the Ziegler-Nichols method, with the proportional coefficient... Integral time Differential time ; The security protection unit implements a three-level protection mechanism: Level 1 protection: Software limit; automatically adjusts when parameters exceed the safe range. Level 2 protection: Hardware protection circuit with a response time of less than 10ms. Level 3 protection: Mechanical protection devices ensure absolute equipment safety.

[0024] 5. Specific implementation of the Internet of Things (IoT) communication module: The IoT communication module is designed to support multiple protocols. The data transmission unit supports the MQTT protocol with a QoS level of 1 to ensure that messages are transmitted at least once. The protocol conversion unit implements HL7 / FHIR medical data standard conversion, supports JSON and XML formats, and the network security unit uses TLS 1.3 encrypted transmission with AES-256-GCM encryption algorithm, while also implementing OAuth 2.0-based authentication. The edge computing nodes use NVIDIA Jetson Xavier, with a computing power of 32 TFLOPS, which can complete 80% of the data processing tasks locally and keep the average system response time within 50ms.

[0025] 6. System workflow: In practical applications, the system workflow is as follows: (1) The status monitoring module collects status data of each medical device at a frequency of 100Hz; (2) The data processing module completes data preprocessing and feature extraction at the edge nodes; (3) The collaborative decision-making module generates control instructions based on a multi-objective optimization algorithm; (4) The intelligent control module performs control operations and ensures control accuracy through feedback control; (5) The IoT communication module uploads key data to the cloud platform for remote monitoring and analysis.

[0026] The above is a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the embodiments described. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of this application.

Claims

1. A collaborative status monitoring and intelligent control system for composite medical devices based on the Internet of Things, characterized in that, include: The system includes a status monitoring module, a data processing module, a collaborative decision-making module, an intelligent control module, and an IoT communication module. The status monitoring module is configured to collect real-time status data of at least one medical device, including temperature, pressure, motion parameters, and power consumption. The data processing module is configured to process and analyze the state data, and the processing and analysis specifically includes: filtering, feature extraction, and anomaly detection of the state data; The collaborative decision-making module is configured to generate collaborative control instructions based on the processed data, and the collaborative control instructions are used to coordinate the operation of several medical devices. The intelligent control module is configured to control the medical device according to the control command; The IoT communication module is configured to perform data communication between the modules and with external devices.

2. The IoT-based collaborative status monitoring and intelligent control system for composite medical devices according to claim 1, characterized in that, The status monitoring module includes several sensor units, including a temperature sensor, a pressure sensor, a motion sensor, and a power monitoring sensor. The temperature sensor is configured to measure the surface temperature or internal temperature of the medical device. The pressure sensor is configured to monitor the pneumatic or hydraulic parameters of the medical device; The motion sensor is configured to detect the displacement, acceleration, or angular velocity of the medical device. It employs a triaxial accelerometer and a gyroscope, with a sampling frequency of 100Hz. The power monitoring sensor is configured to measure the voltage, current, and power of the medical device; The status monitoring module also includes a data preprocessing unit, which performs noise reduction and standardization on the collected raw data. The noise reduction uses a moving average filtering algorithm, and the standardization converts the data into a format with zero mean and unit variance. The status monitoring module is connected to the data processing module via wired or wireless means.

3. The IoT-based collaborative status monitoring and intelligent control system for composite medical devices according to claim 1, characterized in that, The data processing module includes a data storage unit, a feature extraction unit, and an anomaly detection unit; The data storage unit is configured to store historical state data and real-time data, and uses non-volatile memory. The data storage format is JSON or binary format. The feature extraction unit is configured to extract key features from the state data, including time-domain features and frequency-domain features. The time-domain features include mean, variance, and peak value, while the frequency-domain features are calculated using fast Fourier transform. The extracted features are used for subsequent analysis and decision-making. The anomaly detection unit is configured to identify anomalies in the state data, using a statistical Z-score algorithm, as follows: ； in, This represents the standardized outlier score. Represents the original data points. This represents the mean of the dataset. Represents the standard deviation of the dataset; when When this happens, it is judged as abnormal; The data processing module also integrates a machine learning model for state prediction. This model employs a linear regression algorithm and is expressed as follows: ； in, Indicates the predicted state value. to Indicates the input feature variables. Represents the intercept term. to Represents the regression coefficient; The model is trained using historical data, and the parameters are optimized using gradient descent during the training process.

4. The IoT-based collaborative status monitoring and intelligent control system for composite medical devices according to claim 3, characterized in that, The anomaly detection unit in the data processing module also integrates a deep learning model for complex anomaly pattern recognition. This model employs a convolutional neural network, and its forward propagation formula is: ； in, Indicates the first The activation value of the layer, Indicates the first The weight matrix of the layer, Indicates the first Layer bias vector, The activation function is represented by the ReLU function, defined as follows: The convolutional neural network includes an input layer, convolutional layers, pooling layers, and a fully connected layer. The input layer receives a state data vector, the convolutional layers use 3x3 convolutional kernels to extract local features, the pooling layers use max pooling to reduce parameters, and the fully connected layer outputs the anomaly probability. The training process uses the backpropagation algorithm, and the loss function is the cross-entropy loss, expressed as: ； in, Indicates the loss value. Indicates the number of samples. Indicates the true label, Indicates the predicted probability; The model is trained using GPU acceleration, and the training dataset contains no fewer than 100,000 samples.

5. The IoT-based collaborative status monitoring and intelligent control system for composite medical devices according to claim 1, characterized in that, The collaborative decision-making module includes a rule engine unit, an optimization algorithm unit, and a decision output unit; The rule engine unit is configured to store preset control rules, which are based on the medical device's operation manual and clinical guidelines, including reducing power if the temperature exceeds a threshold and activating a safety mode if the pressure is abnormal. The optimization algorithm unit is configured to generate the optimal control command, and adopts a multi-objective optimization algorithm with the objective function being: ； in, Describe the overall objective function. Represents the energy consumption function. Represents the performance function. and Represents the weight coefficient and , This represents a decision variable vector, which includes the operating parameters of the medical device. The decision output unit is configured to output a coordinated control command, which includes adjusting temperature, pressure or motion parameters, and is sent to the intelligent control module via the Internet of Things communication module. The collaborative decision-making module also supports real-time learning, dynamically adjusting rules and weights based on feedback data.

6. The IoT-based collaborative status monitoring and intelligent control system for composite medical devices according to claim 5, characterized in that, The optimization algorithm unit in the collaborative decision-making module also employs a genetic algorithm for multi-objective optimization, the steps of which include: Initialize the population and set the population size to 100, with each individual representing a set of decision variables; Calculate the fitness function, which is based on the objective function. And add constraints; The selection operation uses a roulette wheel selection method, where the selection probability is directly proportional to the fitness. The crossover operation uses a single-point crossover with a crossover probability of 0.

8. The mutation operation uses Gaussian mutation with a mutation probability of 0.1; The population is updated iteratively, with a maximum of 1000 iterations. The formula for the genetic algorithm is expressed as follows: ； in, Indicates the generation number of the population. Indicates a selection operation. Indicates an interleaving operation. Indicates the mutation operation; The optimization algorithm unit also integrates a real-time adaptive mechanism to dynamically adjust the weight coefficients according to the system load. and .

7. The IoT-based collaborative status monitoring and intelligent control system for composite medical devices according to claim 1, characterized in that, The intelligent control module includes an actuator unit, a feedback control unit, and a safety protection unit; The actuator unit is configured to adjust the operating parameters of the medical device according to the control command, including adjusting the temperature of the heating element, controlling the pressure of the pump, or adjusting the speed of the motor. The actuator unit uses a stepper motor or a servo motor; the feedback control unit is configured to monitor the control effect and uses a PID controller, whose control formula is: ； in, Indicates control output. This indicates the error signal, which is the difference between the set value and the actual value. Represents the proportionality coefficient. Represents the integral coefficient. Represents the differential coefficient; The safety protection unit is configured to stop the medical device in an emergency under abnormal circumstances, including over-temperature protection, over-voltage protection and power failure protection; The intelligent control module receives instructions through the Internet of Things (IoT) communication module and uploads control logs in real time.

8. The IoT-based collaborative status monitoring and intelligent control system for composite medical devices according to claim 1, characterized in that, The IoT communication module includes a data transmission unit, a protocol conversion unit, and a network security unit; The data transmission unit is configured to use the MQTT or CoAP protocol for data exchange and supports bidirectional communication. The protocol conversion unit is configured to convert the data formats of different medical devices into a unified format, using JSON or XML schema. The network security unit is configured to encrypt data transmission, employing the AES-256 encryption algorithm and implementing an authentication mechanism.

9. The IoT-based collaborative status monitoring and intelligent control system for composite medical devices according to claim 1, characterized in that, The system also includes a user interaction module and a log recording module; The user interaction module is configured to display status data and control results through a graphical user interface, supports touch screen operation, and the interface elements include real-time curves, alarm indicators, and parameter setting panels. The log recording module is configured to store the system operation history, including status data, control instructions and abnormal events, using a time-series database, and the data retention time is not less than 1 year; The user interaction module also supports remote access, which can be achieved through a web interface or mobile application, and uses RESTful API for data interaction. The log recording module integrates data analysis tools for generating reports and trend analysis, with report formats including PDF and CSV.

Images