Medical equipment full life cycle management system based on digital twinning technology

Abstract

The invention discloses a medical equipment full-life-cycle management system based on a digital twinning technology. The medical equipment full-life-cycle management system comprises four modules. The digital twinborn model construction module constructs and updates a simulation medical equipment digital model in real time; the intelligent data acquisition and monitoring module is responsible for data acquisition, transmission, monitoring and interface design; the intelligent decision and maintenance module realizes fault prediction, maintenance plan generation and record management; and the comprehensive analysis and optimization management module performs data analysis, optimization decision and life cycle planning. The system has the remarkable advantages that when equipment is used, the running state of the equipment is adjusted in time through real-time monitoring and intelligent analysis, and the fault rate and the maintenance and replacement frequency are reduced; in the aspect of cost control, a maintenance strategy and a purchase decision are optimized, and expenditure is reduced; at the medical service quality level, stable and efficient operation of equipment is guaranteed, patient safety is improved, and reasonable utilization of medical resources is achieved.

Description

Technical Field

[0001] The present invention belongs to the field of medical equipment management technology, specifically to a medical equipment full life cycle management system based on digital twin technology. Background Art

[0002] In the healthcare sector, efficient management of medical equipment plays a key role in improving the quality of medical services. Traditional medical equipment management methods, which primarily rely on manual record-keeping and regular inspections, suffer from numerous drawbacks. Firstly, a lack of real-time data support prevents timely monitoring of equipment operating status, leading to frequent equipment failures. For example, with some large medical imaging equipment, such as CT machines and MRI scanners, potential problems during operation go undetected. Once a failure occurs, it not only impacts patients' normal examinations and treatment but also results in high repair costs. Secondly, equipment utilization is inefficient, preventing it from fully utilizing its full performance. Without accurate visibility into equipment usage, hospitals lack a scientific basis for equipment procurement, deployment, and maintenance, resulting in wasted resources.

[0003] With the development of information technology, digital twin technology has gradually emerged. By combining physical entities with virtual models, digital twin technology leverages real-time data to enable real-time monitoring, analysis, and optimization of physical entities. This provides new insights and approaches to addressing the challenges of medical device management. Applying digital twin technology to medical device management enables real-time monitoring of device status, proactively predicting failures, and optimizing maintenance strategies, thereby improving equipment efficiency and reducing operating costs. Summary of the Invention

[0004] The purpose of this invention is to provide a medical equipment full life cycle management system based on digital twin technology to optimize the management of medical equipment in various stages such as procurement, use, maintenance and scrapping, improve equipment utilization efficiency, reduce operating costs, and improve the quality of medical services.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0006] The medical equipment full lifecycle management system based on digital twin technology includes:

[0007] A digital twin model building module, used to build digital models of medical devices and update and simulate them in real time;

[0008] Intelligent data acquisition and monitoring module, used for collecting, transmitting, monitoring data and designing interfaces for medical equipment;

[0009] Intelligent decision-making and maintenance module for medical equipment failure prediction, maintenance plan generation and record management;

[0010] Comprehensive analysis and optimization management module for data analysis, optimization decision-making and medical equipment life cycle planning.

[0011] According to the above technical solution, the digital twin model construction module includes:

[0012] The data acquisition unit collects the operating data of medical equipment through sensors and IoT devices and transmits it to the cloud data center via wireless networks;

[0013] A 3D model generation unit, combining the physical characteristics of the device with the operating data, to generate a 3D digital model including the exterior structure, internal components, and functional modules;

[0014] A real-time updating unit, which updates the 3D digital model through a real-time data stream to reflect the current status of the device;

[0015] The state and behavior simulation unit uses finite element analysis (FEA) and computational fluid dynamics (CFD) technology to simulate the state and behavior of equipment under different working conditions.

[0016] According to the above technical solution, the 3D model generation unit generates a 3D digital model through the following steps:

[0017] Based on the equipment's geometric parameters and structural design drawings, use computer graphics technology to construct a three-dimensional geometric model of the equipment's appearance and internal components;

[0018] Mapping the physical characteristic parameters in the operating data to corresponding components of the three-dimensional geometric model to form a digital twin model containing functional attributes;

[0019] The specific process of the state and behavior simulation unit includes:

[0020] Based on finite element analysis (FEA), mechanical modeling of equipment components is performed to simulate structural responses under mechanical stress, vibration and other working conditions;

[0021] Based on computational fluid dynamics (CFD), the flow characteristics of the fluid inside the equipment are modeled to simulate the temperature field and pressure field distribution;

[0022] Combined with real-time operation data, the simulation boundary conditions are updated and the state simulation results of the equipment under different working conditions are output.

[0023] According to the above technical solution, the intelligent data acquisition and monitoring module includes:

[0024] The data transmission unit filters and pre-processes the sensor data through the edge computing node and then transmits it to the cloud;

[0025] Real-time monitoring unit, using data visualization tools to display equipment operating status and set up alarm mechanisms;

[0026] The data interface unit is designed with a unified data interface standard to support real-time data upload and historical data query.

[0027] According to the above technical solution, in the intelligent data acquisition and monitoring module, data screening and preprocessing include:

[0028] Eliminate outliers and duplicate data, normalize and reduce noise, and downsample high-frequency data to a preset frequency;

[0029] In the intelligent data collection and monitoring module, data visualization tools include:

[0030] Dynamic dashboards displaying equipment key performance indicators (KPIs) in real time, including temperature, humidity, and operating status;

[0031] A 3D simulation interface for visualizing the real-time operating status of the device digital twin model;

[0032] The alarm prompt system triggers an audible and visual alarm or SMS notification when the equipment operating parameters exceed the set threshold.

[0033] According to the above technical solution, the intelligent decision-making and maintenance module includes:

[0034] Fault prediction unit, which uses machine learning models to predict equipment failures and generate maintenance recommendations based on historical and real-time data;

[0035] Maintenance plan generation unit, which generates maintenance plans and dispatches maintenance personnel based on fault prediction results;

[0036] Maintenance record management unit, establishes maintenance record database and updates maintenance history in real time.

[0037] According to the above technical solution, in the intelligent decision-making and maintenance module, the machine learning model uses the Random Forest (RandomForest) or Support Vector Machine (SVM) algorithm. The specific process includes:

[0038] Use historical fault data as training samples to extract feature vectors such as equipment operating time, fault records, and performance parameters;

[0039] Through supervised learning training model, the mapping relationship between fault type and feature vector is established;

[0040] Input real-time data feature vectors and output fault prediction results and maintenance recommendations.

[0041] According to the above technical solution, the comprehensive analysis and optimization management module includes:

[0042] Data analysis unit, which regularly analyzes equipment usage data, evaluates equipment performance and maintenance effects, and generates analysis reports;

[0043] Optimize decision-making units and optimize equipment procurement and maintenance strategies based on analysis results to reduce total cost of ownership (TCO);

[0044] Lifecycle management unit, planning equipment upgrade, update and retirement strategies.

[0045] According to the above technical solution, in the comprehensive analysis and optimization management module, the data analyzed by the data analysis unit includes:

[0046] Equipment operating efficiency data, including startup time, load factor, and downtime;

[0047] Maintenance cost data, including repair frequency, parts replacement records, and maintenance labor costs;

[0048] Performance reliability data, including failure rate, mean time between failures (MTBF), and mean time to repair (MTTR).

[0049] According to the above technical solution, in the comprehensive analysis and optimization management module, the optimization algorithm adopts the genetic algorithm (Genetic Algorithm). The specific process includes:

[0050] Define a maintenance strategy population, where each individual represents a combination of a maintenance cycle and a maintenance method;

[0051] The population is iteratively optimized through selection, crossover, and mutation operations, with the lowest total maintenance cost and the highest equipment availability as the objective function;

[0052] Output the optimal maintenance strategy as the basis for equipment management decision-making;

[0053] Full life cycle management includes:

[0054] Procurement stage: Use digital twin models to predict equipment performance and select the optimal equipment based on historical data and market trends;

[0055] Use phase: Provide equipment use guidance and status warnings through real-time monitoring to ensure that the equipment operates in optimal conditions;

[0056] Maintenance stage: Develop preventive maintenance plans based on fault prediction results to reduce downtime;

[0057] Scrap stage: Evaluate the technical status and use value of the equipment, and record historical data to provide reference for subsequent purchases.

[0058] Compared with the prior art, the present invention has the following beneficial effects:

[0059] The medical equipment life cycle management system based on digital twin technology of the present invention has significant beneficial effects. In terms of equipment utilization efficiency, through real-time monitoring and intelligent analysis, problems in equipment operation can be discovered and adjusted in a timely manner to ensure that the equipment is always in the best operating state, reduce failure rates, and reduce the frequency of repairs and replacements. In terms of cost control, optimized maintenance strategies and reasonable procurement decisions effectively reduce maintenance costs and achieve optimal allocation of resources. From the perspective of improving the quality of medical services, the stable operation and efficient use of equipment ensure the smooth development of medical services, improve patient safety, and ultimately achieve the rational use of medical resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 This is a data transmission flow chart of the system of the present invention. DETAILED DESCRIPTION

[0061] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0062] Example 1

[0063] like Figure 1 As shown in the figure, the medical equipment full life cycle management system based on digital twin technology includes:

[0064] A digital twin model building module, used to build digital models of medical devices and update and simulate them in real time;

[0065] Intelligent data acquisition and monitoring module, used for collecting, transmitting, monitoring data and designing interfaces for medical equipment;

[0066] Intelligent decision-making and maintenance module for medical equipment failure prediction, maintenance plan generation and record management;

[0067] Comprehensive analysis and optimization management module for data analysis, optimization decision-making and medical equipment life cycle planning.

[0068] In the present invention, the intelligent data acquisition and monitoring module obtains raw data through sensors, and transmits it to the digital twin module and decision module after preprocessing.

[0069] The digital twin model construction module builds / updates the model based on real-time data and outputs simulation results to support monitoring visualization and fault prediction.

[0070] The intelligent decision-making and maintenance module uses multi-source data (real-time + historical + simulation) to generate maintenance plans, record maintenance history and feed it back to the analysis module.

[0071] The comprehensive analysis and optimization management module integrates data from the entire life cycle, outputs optimization strategies (procurement, maintenance, and scrapping), and feeds back to the front-end module to form a closed loop.

[0072] Through the circular flow of data "collection-modeling-decision-making-optimization", the four major modules work together to achieve digital management of the entire process of medical equipment from procurement to scrapping, improving reliability and reducing operation and maintenance costs.

[0073] The medical equipment life cycle management system based on digital twin technology of the present invention has significant beneficial effects. In terms of equipment utilization efficiency, through real-time monitoring and intelligent analysis, problems in equipment operation can be discovered and adjusted in a timely manner to ensure that the equipment is always in the best operating state, reduce failure rates, and reduce the frequency of repairs and replacements. In terms of cost control, optimized maintenance strategies and reasonable procurement decisions effectively reduce maintenance costs and achieve optimal allocation of resources. From the perspective of improving the quality of medical services, the stable operation and efficient use of equipment ensure the smooth development of medical services, improve patient safety, and ultimately achieve the rational use of medical resources.

[0074] Example 2

[0075] This embodiment is a further refinement of the first embodiment.

[0076] In a specific embodiment, the digital twin model construction module is implemented as follows:

[0077] During the data acquisition phase, various sensors, such as temperature sensors, pressure sensors, and operating time counters, are installed at key locations on medical devices. These collected data is transmitted to a cloud data center via IoT devices using specific wireless communication protocols (such as Bluetooth, Wi-Fi, or ZigBee). During 3D model generation, a 3D geometric model of the device is constructed based on the device's design drawings and actual physical dimensions using professional 3D modeling software (such as 3ds Max and Maya). The physical characteristics (such as temperature and pressure distribution) collected by the sensors are then mapped to the corresponding model components via a programming interface. For real-time model updates, data push technology is used. Once the cloud data center receives new sensor data, it is immediately pushed to the digital twin model to update the model's state. For state and behavior simulation, finite element analysis software (such as ANSYS) is used to create a mechanical model of the device. After meshing, appropriate loads and boundary conditions are applied to simulate the device's mechanical response under different operating conditions. Computational fluid dynamics software (such as FLUENT) is used to model the fluid flow within the device, setting the fluid's physical properties and boundary conditions to simulate the temperature and pressure field distributions.

[0078] In a specific embodiment, the intelligent data acquisition and monitoring module is implemented as follows:

[0079] During the data transmission process, the edge computing node uses specific data processing algorithms (such as an outlier detection algorithm based on a sliding window, a mean filter noise reduction algorithm, etc.) to filter and preprocess the sensor data, and then transmits the processed data to the cloud through a high-speed network (such as 5G or a wired network). In terms of data visualization, professional data visualization tools (such as Echarts, Tableau, etc.) are used to develop dynamic dashboards to display the key performance indicators of the equipment in real time; three-dimensional simulation interfaces are developed based on virtual reality technology (VR) or augmented reality technology (AR) to intuitively present the operating status of the equipment; and an alarm prompt system is implemented using SMS gateways or instant messaging tools (such as DingTalk and WeChat Enterprise Accounts). The setting of unified data interface standards adopts common data formats (such as JSON or XML) and communication protocols (such as HTTP / HTTPS) to define the interface specifications and data interaction methods for data transmission.

[0080] In a specific embodiment, the intelligent decision-making and maintenance module is implemented as follows:

[0081] In fault prediction, a large amount of historical fault data is collected, and feature vectors such as equipment operating time, fault type, and pre-fault performance parameters are extracted. A machine learning framework (such as Scikit-learn) is used to train a random forest or support vector machine model. When there is new real-time data, the corresponding feature vector is extracted and input into the trained model to output the fault prediction results and maintenance recommendations. The maintenance plan is generated based on the prediction results, combined with the hospital's maintenance resources and equipment usage plan, and a detailed maintenance plan is formulated through project management software (such as Microsoft Project), and maintenance personnel are notified via text messages or internal management systems. Maintenance record management uses a relational database (such as MySQL or Oracle) to establish a maintenance record database. After each maintenance operation is completed, the maintenance personnel enter the maintenance content, replaced parts, maintenance time and other information into the database through a special maintenance record entry interface.

[0082] In a specific embodiment, the comprehensive analysis and optimization management module is implemented as follows: During data analysis, data analysis tools (such as Python's data analysis libraries Pandas and NumPy, etc.) are used to clean, convert, and analyze equipment usage data to generate equipment performance evaluation reports and maintenance effectiveness evaluation reports. During optimization decision-making, factors such as equipment procurement cost, maintenance cost, and equipment availability are incorporated into the objective function of the genetic algorithm, and the optimal procurement and maintenance strategy is found through multiple iterative calculations. In terms of lifecycle management, an equipment lifecycle assessment model is established, and equipment upgrade, update, and scrapping plans are formulated based on factors such as the equipment's service life, technological updates, and maintenance costs.

[0083] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0084] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A medical equipment full lifecycle management system based on digital twin technology, characterized by: include: A digital twin model building module, used to build digital models of medical devices and update and simulate them in real time; Intelligent data acquisition and monitoring module, used for collecting, transmitting, monitoring data and designing interfaces for medical equipment; Intelligent decision-making and maintenance module for medical equipment failure prediction, maintenance plan generation and record management; Comprehensive analysis and optimization management module for data analysis, optimization decision-making and medical equipment life cycle planning.

2. The medical equipment full life cycle management system based on digital twin technology according to claim 1 is characterized by: The digital twin model building blocks include: The data acquisition unit collects the operating data of medical equipment through sensors and IoT devices and transmits it to the cloud data center via wireless networks; A 3D model generation unit, combining the physical characteristics of the device with the operating data, to generate a 3D digital model including the exterior structure, internal components, and functional modules; A real-time updating unit, which updates the 3D digital model through a real-time data stream to reflect the current status of the device; The state and behavior simulation unit uses finite element analysis (FEA) and computational fluid dynamics (CFD) technology to simulate the state and behavior of equipment under different working conditions.

3. The medical equipment full life cycle management system based on digital twin technology according to claim 2 is characterized by: The 3D model generation unit generates a 3D digital model through the following steps: Based on the equipment's geometric parameters and structural design drawings, use computer graphics technology to construct a three-dimensional geometric model of the equipment's appearance and internal components; Mapping the physical characteristic parameters in the operating data to corresponding components of the three-dimensional geometric model to form a digital twin model containing functional attributes; The specific process of the state and behavior simulation unit includes: Based on finite element analysis (FEA), mechanical modeling of equipment components is performed to simulate structural responses under mechanical stress, vibration and other working conditions; Based on computational fluid dynamics (CFD), the flow characteristics of the fluid inside the equipment are modeled to simulate the temperature field and pressure field distribution; Combined with real-time operation data, the simulation boundary conditions are updated and the state simulation results of the equipment under different working conditions are output.

4. The medical equipment full life cycle management system based on digital twin technology according to claim 1 is characterized by: Intelligent data acquisition and monitoring modules include: The data transmission unit filters and pre-processes the sensor data through the edge computing node and then transmits it to the cloud; Real-time monitoring unit, using data visualization tools to display equipment operating status and set up alarm mechanisms; The data interface unit is designed with a unified data interface standard to support real-time data upload and historical data query.

5. The medical equipment full life cycle management system based on digital twin technology according to claim 4 is characterized by: In the intelligent data acquisition and monitoring module, data screening and preprocessing include: Eliminate outliers and duplicate data, normalize and reduce noise, and downsample high-frequency data to a preset frequency; In the intelligent data collection and monitoring module, data visualization tools include: Dynamic dashboards displaying equipment key performance indicators (KPIs) in real time, including temperature, humidity, and operating status; A 3D simulation interface for visualizing the real-time operating status of the device digital twin model; The alarm prompt system triggers an audible and visual alarm or SMS notification when the equipment operating parameters exceed the set threshold.

6. The medical equipment full life cycle management system based on digital twin technology according to claim 1 is characterized by: Intelligent decision-making and maintenance modules include: Fault prediction unit, which uses machine learning models to predict equipment failures and generate maintenance recommendations based on historical and real-time data; Maintenance plan generation unit, which generates maintenance plans and dispatches maintenance personnel based on fault prediction results; Maintenance record management unit, establishes maintenance record database and updates maintenance history in real time.

7. The medical equipment full life cycle management system based on digital twin technology according to claim 6 is characterized by: In the intelligent decision-making and maintenance module, the machine learning model uses the Random Forest or Support Vector Machine (SVM) algorithm. The specific process includes: Use historical fault data as training samples to extract feature vectors such as equipment operating time, fault records, and performance parameters; Through supervised learning training model, the mapping relationship between fault type and feature vector is established; Input real-time data feature vectors and output fault prediction results and maintenance recommendations.

8. The medical equipment full life cycle management system based on digital twin technology according to claim 1 is characterized by: The comprehensive analysis and optimization management module includes: Data analysis unit, which regularly analyzes equipment usage data, evaluates equipment performance and maintenance effects, and generates analysis reports; Optimize decision-making units and optimize equipment procurement and maintenance strategies based on analysis results to reduce total cost of ownership (TCO); Lifecycle management unit, planning equipment upgrade, update and retirement strategies.

9. The medical equipment full life cycle management system based on digital twin technology according to claim 8, characterized in that: In the comprehensive analysis and optimization management module, the data analyzed by the data analysis unit includes: Equipment operating efficiency data, including startup time, load factor, and downtime; Maintenance cost data, including repair frequency, parts replacement records, and maintenance labor costs; Performance reliability data, including failure rate, mean time between failures (MTBF), and mean time to repair (MTTR).

10. The medical equipment full life cycle management system based on digital twin technology according to claim 9 is characterized by: In the comprehensive analysis and optimization management module, the optimization algorithm adopts the genetic algorithm (Genetic Algorithm). The specific process includes: Define a maintenance strategy population, where each individual represents a combination of a maintenance cycle and a maintenance method; The population is iteratively optimized through selection, crossover, and mutation operations, with the lowest total maintenance cost and the highest equipment availability as the objective function; Output the optimal maintenance strategy as the basis for equipment management decision-making; Full life cycle management includes: Procurement stage: Use digital twin models to predict equipment performance and select the optimal equipment based on historical data and market trends; Use phase: Provide equipment use guidance and status warnings through real-time monitoring to ensure that the equipment operates in optimal conditions; Maintenance stage: Develop preventive maintenance plans based on fault prediction results to reduce downtime; Scrap stage: Evaluate the technical status and use value of the equipment, and record historical data to provide reference for subsequent purchases.

Images