Intelligent infusion amount weighing system
By using data fusion technology from multimodal sensors and intelligent unit processors, the problems of inaccurate monitoring and poor adaptability of existing intelligent infusion devices have been solved, achieving precision and safety in the infusion process, providing a comfortable treatment experience and efficient remote monitoring.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Utility models(China)
- Current Assignee / Owner
- THE THIRD MEDICAL CENT OF THE CHINESE PEOPLES LIBERATION ARMY GENERAL HOSPITAL
- Filing Date
- 2025-04-08
- Publication Date
- 2026-05-08
AI Technical Summary
Existing intelligent infusion devices lack multimodal data fusion and real-time accurate weighing capabilities, making it difficult to provide comprehensive infusion monitoring. This leads to inaccuracies and safety hazards during the infusion process, especially when the patient is active, the complexity and weight of the devices create a burden.
It employs multimodal sensors (ultrasonic flow sensor and strain gauge sensor) combined with an intelligent unit processor, and uses graph convolutional networks and wavelet convolutional neural networks for data fusion to monitor infusion rate and flow rate in real time. It also combines with a weighing device for accurate weighing and supports wireless communication to achieve remote data transmission and real-time monitoring.
It improves the accuracy and safety of the infusion process, reduces the risk of leakage and incorrect infusion volume, enhances the adaptability and stability of the system, provides a comfortable treatment experience, and improves medical efficiency through remote monitoring.
Smart Images
Figure CN224207177U_ABST
Abstract
Description
Technical Field
[0001] This invention relates to medical equipment technology, particularly to infusion volume weighing and flow rate monitoring systems, specifically an intelligent infusion volume weighing system. Background Technology
[0002] With the rapid development of smart healthcare and health monitoring technologies, traditional medical infusion methods have gradually revealed problems such as low efficiency, inaccurate monitoring, and poor patient comfort. This is especially true for patients who are hospitalized for long periods or require frequent infusions, where traditional infusion monitoring methods often suffer from inaccurate infusion rates and insufficient patient awareness. Furthermore, most traditional infusion monitoring systems rely on single sensors and lack real-time weighing and multimodal data fusion, making it difficult to provide comprehensive infusion monitoring.
[0003] To address these issues, intelligent infusion devices are increasingly being used, especially intelligent infusion systems employing multiple sensor modules. These systems can monitor flow rate, fluid volume, and other relevant parameters in real time, effectively improving the accuracy and safety of treatment. However, existing intelligent infusion devices still suffer from poor adaptability. Especially when patients are active, the complexity and weight of the devices can cause discomfort and additional burden. More importantly, current devices lack multimodal data fusion and real-time accurate weighing capabilities, making it difficult to provide comprehensive monitoring and thus failing to reduce potential risks during the infusion process.
[0004] This invention proposes an intelligent infusion volume weighing system that uses multimodal sensors (including ultrasonic flow sensors and strain gauge sensors) combined with an intelligent unit processor to perform real-time weighing and precise monitoring of the infusion process. By fusing data from different sensors, the system can monitor the infusion rate and volume in real time and accurately weigh each infusion, ensuring the accuracy and safety of the infusion process and reducing the risks of leakage and incorrect infusion volume. Through this multimodal data fusion technology, the system can better adapt to the patient's activities, reduce interference and burden on the patient, and provide a more comfortable treatment experience. Utility Model Content
[0005] To address the shortcomings of existing technologies, the present invention aims to provide an intelligent infusion weighing system. This system aims to improve the accuracy and safety of the infusion process and reduce risks through multi-sensor data fusion, real-time weighing, and flow rate monitoring, thereby solving problems such as inaccurate monitoring, inaccurate infusion volume, and numerous safety hazards in traditional infusion devices.
[0006] The technical solution adopted by this utility model to solve its technical problem is as follows:
[0007] A smart infusion volume weighing system includes a smart unit, which includes a sensor data fusion module that uses graph convolutional network algorithm (GCN) and wavelet convolutional neural network (WaveletCNN); a bus, an ultrasonic flow sensor that transmits flow velocity data to the smart unit processor via the bus; and a weighing device (4) that includes a strain gauge sensor, a cavity, an inflow catheter, and an outflow catheter.
[0008] The intelligent unit employs a microprocessor and includes memory, a computing unit, and input / output ports. The ultrasonic flow sensor uses the time difference between the ultrasonic signal and the received signal to calculate the fluid flow velocity and transmits the velocity data to the intelligent unit processor. The strain gauge sensor includes a strain gauge mounted on a platform surface; when subjected to weight, the strain gauge undergoes minute deformation, causing a change in its resistance.
[0009] The resistance change signal of the strain gauge is transmitted to the signal conditioning circuit, which uses an analog-to-digital converter (ADC) to convert the conditioned analog signal into a digital signal and transmits it to the intelligent unit via a bus.
[0010] The smart unit supports wireless communication protocols, including Wi-Fi 802.11ac, Bluetooth 4.0 and above, and ZigBee 3.0.
[0011] The beneficial effects of this utility model are:
[0012] The intelligent infusion volume weighing system significantly improves the accuracy and safety of infusion processes by monitoring the flow rate and volume in real time and combining this with a weighing device for precise measurement. Through sensor data fusion technology, the system can acquire and process data such as flow rate and infusion volume in real time, effectively reducing the risks of leakage and incorrect infusion volume, ensuring patients receive the correct treatment.
[0013] Furthermore, the intelligent unit design enables the entire system to be compatible with various sensor modules. The use of Graph Convolutional Networks (GCN) and Wavelet Convolutional Neural Networks (WCNN) for data analysis and processing improves the accuracy and real-time performance of data processing. This not only enhances the system's adaptability but also improves its stability and reliability in various medical environments.
[0014] With the support of a wireless communication module, the intelligent infusion weighing system of this invention enables remote data transmission and real-time monitoring. Medical staff can obtain information on the patient's infusion progress at any time through remote devices, and adjust infusion parameters or intervene in a timely manner. This function significantly improves medical efficiency, reduces the workload of medical staff, and provides patients with a safer and more convenient treatment experience.
[0015] This system also has good patient adaptability. During the patient's activities, the system can continuously and accurately monitor without affecting the patient's normal activities, thereby effectively improving the patient's quality of life and treatment comfort.
[0016] Furthermore, the intelligent unit, through its built-in embedded microprocessor, can not only process sensor data in real time but also intelligently calculate the infusion completion time. Using real-time data from the ultrasonic flow sensor, the intelligent unit processor automatically calculates the remaining infusion time and provides advance reminders to medical staff or patients via a voice broadcast, thus avoiding the risk of not stopping the infusion promptly after completion, as is common in traditional infusion devices, and ensuring patient safety.
[0017] Furthermore, the intelligent infusion weighing system uses a built-in voice broadcaster to provide real-time reminders to patients and medical staff about the infusion status. Especially during prolonged infusions, the voice prompts effectively remind medical staff to check the infusion status promptly, avoiding risks arising from delayed problem detection. In addition, the voice prompts can automatically issue a reminder when the infusion is complete, ensuring effective control of the infusion process.
[0018] Furthermore, the battery is a rechargeable lithium battery, connected to the intelligent unit processor via a bus, providing continuous power support during extended use. This battery design not only ensures stable operation of the device over long periods but also supports fast charging, reducing waiting time for patients and medical staff.
[0019] Furthermore, the clamping device can be equipped with a flow regulator that automatically adjusts the flow rate based on real-time sensor data and works in conjunction with other devices via an intelligent unit processor to ensure the accuracy of the infusion process. Under different environmental conditions (such as changes in health status or temperature effects), the regulator can make corresponding adjustments to maintain the efficient operation of the device.
[0020] Furthermore, the cavity is designed to be replaceable, facilitating cleaning and maintenance and ensuring hygiene standards are maintained for each use; the infusion catheter is made of antibacterial material, which can effectively prevent bacterial growth, ensuring hygiene and safety during the infusion process and reducing the risk of infection. Attached Figure Description
[0021] To more clearly illustrate the technical solutions in the embodiments or examples of the present invention, the accompanying drawings used in the following description of the embodiments or examples will be briefly introduced. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the technical solutions shown in these drawings without creative effort.
[0022] Fig. 1This is a schematic diagram of the overall structure of the intelligent infusion volume weighing system.
[0023] Fig. 2 This is a schematic diagram of the weighing device structure for an intelligent infusion volume weighing system.
[0024] Legend:
[0025] 1-Intelligent unit; 2-Bus; 3-Ultrasonic flow sensor; 4-Weighing device; 41-Strain gauge sensor; 42-Cavity; 43-Inflow conduit; 44-Outflow conduit. Detailed Implementation
[0026] The present invention will be further described below with reference to the accompanying drawings and embodiments.
[0027] It should be noted that the following detailed descriptions are exemplary and intended to provide further explanation of this application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.
[0028] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments according to this application. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.
[0029] like Figs. 1-2 As shown, this embodiment provides an intelligent infusion volume weighing system. The intelligent unit 1, as the core component of the system, is connected to various sensors and control components in the system via bus 2. Bus 2 not only transmits power but also handles data exchange between components, ensuring that the intelligent unit 1 can receive data from the ultrasonic flow sensor 3 and process it in real time. Simultaneously, the intelligent unit 1 sends control signals to these components via bus 2 to adjust the operating status of each component.
[0030] The ultrasonic flow sensor 3 is used to monitor the infusion flow rate. It calculates the fluid flow rate based on the time difference between the ultrasonic signal and the received signal, and transmits the flow rate data to the intelligent unit 1. The intelligent unit 1 calculates the infusion completion time based on the received flow rate data and monitors the infusion process in real time.
[0031] The weighing device 4 uses a strain gauge sensor 41 to weigh the liquid in real time. The strain gauge is mounted on the platform surface. When the strain gauge is subjected to weight, it undergoes a slight deformation, causing a change in resistance. The resistance change signal of the strain gauge is transmitted to the signal conditioning circuit, which converts the analog signal into a digital signal through an analog-to-digital converter (ADC) and transmits it to the intelligent unit 1 via bus 2.
[0032] Intelligent Unit 1 employs a microprocessor and includes memory, a computing unit, and input / output ports for data processing and control. The system utilizes a sensor data fusion module, employing Graph Convolutional Network (GCN) and Wavelet Convolutional Neural Network (Wavelet CNN) algorithms to process and fuse data from the ultrasonic flow sensor 3 and strain gauge sensor 41, extracting features to ensure accurate monitoring and control of the infusion process. The data fusion module uses Graph Convolutional Network (GCN) and Wavelet Convolutional Neural Network (Wavelet CNN) algorithms. Specific implementation steps are as follows:
[0033] Graph Convolutional Networks (GCNs) process data through graph convolutional layers. First, weight parameters are initialized and a forward propagation is performed. Sensor data is passed by multiplying the feature matrix and adjacency matrix. Graph convolution operations are then performed, and non-linear features are introduced through activation functions, outputting an updated node feature matrix. After graph convolution processing, the result is passed to subsequent layers for further analysis.
[0034] Wavelet Convolutional Neural Networks (CNNs) combine wavelet transform and convolution operations. First, wavelet transform is applied to the sensor data to extract signals from different frequency bands. Then, convolution operations are performed to extract local features of the signals. Activation functions and pooling operations are used to further extract effective features. Finally, data features from multiple sensors are fused into a unified feature vector.
[0035] By combining these two algorithms, the data fusion module can comprehensively capture the spatial, temporal, and frequency characteristics of sensor signals and transmit the processed data to the subsequent decision-making and control modules to make accurate judgments and responses.
[0036] The output of the sensor data fusion module is a processed and fused high-dimensional feature matrix, representing the comprehensive information from data from various sensors. This output is further input to the intelligent control module to ensure that the system can monitor and make corresponding control and adjustments based on sensor data in real time.
[0037] Through this system, intelligent unit 1 can calculate various data during the infusion process in real time, including flow rate and infusion volume, ensuring the accuracy of the infusion process. Real-time processing and fusion of sensor data improves the reliability and safety of the system.
[0038] The wireless communication module supports Wi-Fi, Bluetooth 4.0 and above, and ZigBee 3.0 standard, enabling wireless data transmission to remote devices. This allows medical staff to remotely monitor and adjust infusion parameters, improving medical efficiency and reducing workload.
[0039] Instructions for use:
[0040] The infusion solution flows into the cavity through the infusion catheter. During this process, a weighing device activates to measure the weight of the infusion solution in the cavity in real time. Through monitoring by strain gauge sensors, the system can accurately record the inflow rate of the fluid during the infusion process.
[0041] Once the injection solution has been weighed, the outlet of the inlet tube automatically opens, allowing the liquid to continue flowing. At this point, the liquid flows through the inlet tube and is monitored for flow rate by an ultrasonic flow sensor.
[0042] The ultrasonic flow sensor measures the liquid flow rate in real time by measuring the time difference between the ultrasonic signal and the received signal, and transmits the flow rate data to the intelligent unit. The intelligent unit processes the data in real time to ensure accurate monitoring of the flow rate and volume during the infusion process, and makes adjustments as needed.
[0043] The entire infusion process is monitored by an intelligent unit. Through a sensor data fusion module, the system can analyze data such as flow rate, volume, and fluid weight in real time to ensure the accuracy of the infusion process. If the system detects an anomaly, such as abnormal flow rate or inconsistent fluid flow rate, it can transmit the information to a remote device via a wireless communication module for remote monitoring and intervention by medical personnel.
[0044] Through the above steps, this system can accurately monitor the entire infusion process, ensuring the efficiency and safety of liquid injection, flow rate control, and real-time weighing.
Claims
1. An intelligent infusion volume weighing system, comprising: The intelligent unit (1) includes a sensor data fusion module, which uses graph convolutional network algorithm and wavelet convolutional neural network; a bus (2), an ultrasonic flow sensor (3), which transmits flow velocity data to the intelligent unit processor (1) via the bus (2); and a weighing device (4), which includes a strain gauge sensor (41), a cavity (42), an inflow conduit (43), and an outflow conduit (44).
2. The intelligent infusion volume weighing system according to claim 1, characterized in that, The intelligent unit (1) employs a microprocessor and includes memory, a computing unit, and input / output ports.
3. The intelligent infusion volume weighing system according to claim 1, characterized in that, The ultrasonic flow sensor (3) uses the time difference between the ultrasonic signal and the received signal to calculate the fluid velocity and transmits the velocity data to the intelligent unit processor (1).
4. The intelligent infusion volume weighing system according to claim 1, characterized in that, The strain sensor (41) includes a strain gauge mounted on the platform surface.
5. The intelligent infusion volume weighing system according to claim 4, characterized in that, The resistance change signal of the strain gauge is transmitted to the signal conditioning circuit, which uses an analog-to-digital converter to convert the conditioned analog signal into a digital signal and transmits it to the intelligent unit (1) via the bus (2).
6. The intelligent infusion volume weighing system according to claim 1, characterized in that, The intelligent unit (1) supports wireless communication protocols, including Wi-Fi 802.11ac, Bluetooth 4.0 and above, and ZigBee 3.0 standard.