Internet of Things equipment monitoring method, system and terminal based on 3D twinborn model

Abstract

The invention discloses an Internet of Things equipment monitoring method and system based on a 3D twinborn model, and a terminal, and the method comprises the steps: obtaining historical operation data, collected by a plurality of sensors, of a plurality of Internet of Things equipment, carrying out the preprocessing of the historical operation data, and obtaining target historical operation data; constructing an initial 3D twinborn model according to the target historical operation data, and analyzing and optimizing model parameters of the initial 3D twinborn model through historical data to obtain a 3D twinborn model meeting performance requirements; and acquiring real-time operation data of target Internet of Things equipment, inputting the real-time operation data into the 3D twinborn model, and outputting a performance analysis and prediction result of the target Internet of Things equipment. The state and performance of the Internet of Things equipment can be monitored and diagnosed in real time based on the 3D twinborn model, and predictive maintenance and optimization suggestions of the equipment are provided.

Description

Technical Field

[0001] The present invention relates to the field of Internet of Things technology, and in particular to an Internet of Things device monitoring method, system, terminal and computer-readable storage medium based on a 3D twin model. Background Art

[0002] In the IoT environment, monitoring and optimizing the operating status and performance of a large number of devices is a challenge; traditional operation and maintenance methods are mainly: (1) Regular inspection: The method and process are as follows: the operation and maintenance personnel conduct on-site inspections of the equipment according to a predetermined schedule, check the working status of the equipment, read instrument data, record logs, etc. For example, in a factory, the operation and maintenance personnel may need to inspect the machines on the production line every day or every week, including listening to sounds, observing operating conditions, checking oil levels, etc. The problem is that manual participation requires a large number of operation and maintenance personnel to conduct regular inspections; the inspection process is time-consuming, and inspections may also be required during non-working hours; it relies on the experience and intuition of personnel, has limited monitoring capabilities, and cannot provide continuous monitoring data.

[0003] (2) Repair after a fault occurs. The method and process are as follows: after a device fails, the operation and maintenance personnel or maintenance engineers repair the device or replace parts. For example, if the air conditioning system of a building suddenly stops working, the maintenance personnel will go to the site to inspect and fix the problem after receiving the report. The problem is that manual fault diagnosis and repair require professional technicians; the equipment may be shut down for a long time from the occurrence of the fault to the completion of the repair; it is impossible to predict potential faults in advance, and the monitoring capability is limited, so it can only passively respond to the faults that have occurred.

[0004] (3) Manual data recording and analysis: The method process is as follows: the operation and maintenance personnel manually record the operating data of the equipment and then analyze it to identify potential problems. For example, in a data center, the operation and maintenance personnel may need to record the temperature and power consumption of each server and then analyze the performance trend by comparing historical data. The problems are that data collection and recording require manual operation; the data analysis process is cumbersome and time-consuming; and because the amount of data may be very large and the monitoring capacity is limited, manual analysis is prone to missing key information.

[0005] Therefore, the prior art still needs to be improved and developed. Summary of the invention

[0006] The main purpose of the present invention is to provide an IoT device monitoring method, system, terminal and computer-readable storage medium based on a 3D twin model, aiming to solve the problem that the operation and maintenance methods of IoT devices in the prior art often require manual participation and a large amount of time cost, and have limited monitoring and fault diagnosis capabilities for the equipment.

[0007] To achieve the above object, the present invention provides an Internet of Things device monitoring method based on a 3D twin model, and the Internet of Things device monitoring method based on a 3D twin model comprises the following steps: Acquire historical operation data of multiple IoT devices collected by multiple sensors, pre-process the historical operation data, and obtain target historical operation data; Constructing an initial 3D twin model according to the target historical operation data, and optimizing model parameters of the initial 3D twin model through historical data analysis to obtain a 3D twin model that meets performance requirements; Acquire the real-time operation data of the target IoT device, input the real-time operation data into the 3D twin model, and output the performance analysis and prediction results of the target IoT device.

[0008] Optionally, in the IoT device monitoring method based on a 3D twin model, the historical operation data includes: historical temperature data, historical pressure value data, historical vibration frequency and amplitude data, and historical current intensity data; The acquiring of historical operation data of multiple IoT devices collected by multiple sensors and preprocessing of the historical operation data to obtain target historical operation data specifically includes: Acquire historical temperature data inside or on the surface of the IoT device collected by a temperature sensor, where the historical temperature data is used to monitor whether the IoT device is within a normal operating temperature range; Acquire historical pressure value data inside the IoT device collected by the pressure sensor, wherein the historical pressure value data is used to detect whether the IoT device is operating under specified pressure conditions; Acquire historical vibration frequency and amplitude data of the IoT device collected by the vibration sensor, wherein the historical vibration frequency and amplitude data are used to analyze the operating status of the IoT device and detect potential mechanical failures; Obtaining historical current intensity data of the operation of the IoT device collected by the current sensor, wherein the historical current intensity data is used to monitor the load condition and energy consumption of the electrical system; The historical temperature data, the historical pressure value data, the historical vibration frequency and amplitude data, and the historical current intensity data are preprocessed to obtain target historical temperature data, target historical pressure value data, target historical vibration frequency and amplitude data, and target historical current intensity data.

[0009] Optionally, in the IoT device monitoring method based on 3D twin model, the preprocessing includes: data cleaning, data normalization, feature extraction, data fusion and data caching; The preprocessing of the historical temperature data, the historical pressure value data, the historical vibration frequency and amplitude data, and the historical current intensity data to obtain target historical temperature data, target historical pressure value data, target historical vibration frequency and amplitude data, and target historical current intensity data specifically includes: removing noise, abnormal values ​​and incomplete records from the historical temperature data, the historical pressure value data, the historical vibration frequency and amplitude data and the historical current intensity data; Scaling the historical temperature data, the historical pressure value data, the historical vibration frequency and amplitude data, and the historical current intensity data to a fixed range; Extracting the most valuable information for predicting equipment performance from the historical temperature data, the historical pressure value data, the historical vibration frequency and amplitude data, and the historical current intensity data; The historical temperature data, the historical pressure value data, the historical vibration frequency and amplitude data, and the historical current intensity data are fused to obtain a device data set; The device data set is stored in a database or a data lake.

[0010] Optionally, the IoT device monitoring method based on a 3D twin model, wherein the initial 3D twin model is constructed according to the target historical operation data, and the model parameters of the initial 3D twin model are optimized through historical data analysis to obtain a 3D twin model that meets performance requirements, specifically includes: Dividing the device data set into a training set, a validation set, and a test set according to a preset ratio; designing an initial 3D twin model of the device based on the device dataset using 3D modeling software; Using the training set to train the initial 3D twin model until a total loss function of the initial 3D twin model reaches a preset convergence condition; The validation set is used to adjust the model parameters of the initial 3D twin model after training, and the initial 3D twin model after adjusting the model parameters is tested using the test set through simulation software to verify whether the initial 3D twin model can accurately reflect the performance and status of the actual device. If the test results meet the preset requirements, a 3D twin model that meets the performance requirements is obtained.

[0011] Optionally, the IoT device monitoring method based on the 3D twin model, wherein the 3D twin model includes: a geometric model, a physical model, a behavioral model, a data model, an analysis model and a visualization interface; The geometric model is used to allow users to intuitively see the structure of the equipment and provide a reference during design or maintenance; The physical model is used to simulate the physical behavior of the device in the actual environment to help understand the performance of the device under different conditions; The behavior model is used to ensure that the model operates according to the operation logic of the actual device and is used to simulate and predict the behavior of the device; The data model is used to provide necessary data support for the model; The analytical model is used to provide predictive maintenance suggestions for equipment performance by analyzing data in the data model; The visual interface is used for operation and maintenance personnel to monitor equipment status and perform fault diagnosis and decision support.

[0012] Optionally, the IoT device monitoring method based on the 3D twin model, wherein the step of acquiring the real-time operation data of the target IoT device, inputting the real-time operation data into the 3D twin model, and outputting the performance analysis and prediction results of the target IoT device, specifically includes: Initialize the 3D twin model, obtain real-time operation data of the target IoT device, and input the real-time operation data into the initialized 3D twin model; Perform trend analysis and fault prediction on the real-time operation data through the machine learning and data analysis algorithms of the 3D twin model, and output performance analysis and prediction results of the target IoT device; Generate recommendations for optimizing equipment operating parameters or maintenance plans based on the performance analysis and prediction results, verify the accuracy of the prediction results through actual operation data, and continuously adjust the 3D twin model; The performance analysis and prediction results include the overall operating status of the equipment, key performance indicators of the equipment, abnormal data and fault diagnosis results.

[0013] Optionally, the IoT device monitoring method based on a 3D twin model, wherein the real-time operation data of the target IoT device is obtained, the real-time operation data is input into the 3D twin model, and the performance analysis and prediction results of the target IoT device are output, and then the method further includes: The 3D twin model of the target IoT device and the performance analysis and prediction results are displayed through the visual interface of the 3D twin model, and optimization suggestions are provided to support the decision-making of operation and maintenance personnel.

[0014] In addition, to achieve the above purpose, the present invention also provides an Internet of Things device monitoring system based on a 3D twin model, wherein the Internet of Things device monitoring system based on a 3D twin model includes: A data acquisition module is used to obtain historical operation data of multiple IoT devices collected by multiple sensors, and pre-process the historical operation data to obtain target historical operation data; A model optimization module, used to construct an initial 3D twin model according to the target historical operation data, and optimize the model parameters of the initial 3D twin model through historical data analysis to obtain a 3D twin model that meets performance requirements; The result analysis module is used to obtain the real-time operation data of the target IoT device, input the real-time operation data into the 3D twin model, and output the performance analysis and prediction results of the target IoT device.

[0015] In addition, to achieve the above-mentioned purpose, the present invention also provides a terminal, wherein the terminal includes: a memory, a processor, and an Internet of Things device monitoring program based on a 3D twin model stored in the memory and runnable on the processor, and when the Internet of Things device monitoring program based on a 3D twin model is executed by the processor, the steps of the Internet of Things device monitoring method based on a 3D twin model as described above are implemented.

[0016] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores an Internet of Things device monitoring program based on a 3D twin model, and when the Internet of Things device monitoring program based on a 3D twin model is executed by a processor, the steps of the Internet of Things device monitoring method based on a 3D twin model as described above are implemented.

[0017] In the present invention, the historical operation data of multiple IoT devices collected by multiple sensors are obtained, and the historical operation data are preprocessed to obtain the target historical operation data; an initial 3D twin model is constructed according to the target historical operation data, and the model parameters of the initial 3D twin model are optimized through historical data analysis to obtain a 3D twin model that meets the performance requirements; the real-time operation data of the target IoT device is obtained, and the real-time operation data is input into the 3D twin model, and the performance analysis and prediction results of the target IoT device are output. Based on the 3D twin model, the present invention can monitor and diagnose the status and performance of IoT devices in real time, and provide predictive maintenance and optimization suggestions for the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a flow chart of a preferred embodiment of the Internet of Things device monitoring method based on 3D twin model of the present invention; Figure 2 It is a structural diagram of a preferred embodiment of the Internet of Things device monitoring system based on a 3D twin model of the present invention; Figure 3 It is a structural diagram of a preferred embodiment of the terminal of the present invention. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the present invention clearer and more specific, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0020] The Internet of Things device monitoring method based on 3D twin model described in the preferred embodiment of the present invention is as follows: Figure 1 As shown, the IoT device monitoring method based on the 3D twin model includes the following steps: Step S10: Acquire historical operation data of multiple IoT devices collected by multiple sensors, and pre-process the historical operation data to obtain target historical operation data.

[0021] Specifically, the historical operation data includes: historical temperature data, historical pressure value data, historical vibration frequency and amplitude data, and historical current intensity data; obtaining historical temperature data inside or on the surface of the Internet of Things device collected by the temperature sensor, and the historical temperature data is used to monitor whether the Internet of Things device is within the normal operating temperature range; obtaining historical pressure value data inside the Internet of Things device collected by the pressure sensor, and the historical pressure value data is used to detect whether the Internet of Things device is operating under specified pressure conditions; obtaining historical vibration frequency and amplitude data of the Internet of Things device collected by the vibration sensor (accelerometer), and the historical vibration frequency and amplitude data are used to analyze the operating status of the Internet of Things device and detect potential mechanical failures; obtaining historical current intensity data of the operation of the Internet of Things device collected by the current sensor, and the historical current intensity data is used to monitor the load condition and energy consumption of the electrical system; then preprocessing the historical temperature data, the historical pressure value data, the historical vibration frequency and amplitude data, and the historical current intensity data to obtain target historical temperature data, target historical pressure value data, target historical vibration frequency and amplitude data, and target historical current intensity data.

[0022] The preprocessing includes: data cleaning, data normalization, feature extraction, data fusion and data caching; the specific preprocessing process is as follows: (1) Data cleaning: removing noise, outliers and incomplete records from the historical temperature data, the historical pressure value data, the historical vibration frequency and amplitude data and the historical current intensity data; for example, using statistical methods, filtering algorithms or machine learning models to identify and eliminate erroneous data, thereby ensuring that subsequent analysis is based on high-quality data and improving the accuracy and reliability of the model.

[0023] (2) Data normalization or standardization: Scale the historical temperature data, the historical pressure value data, the historical vibration frequency and amplitude data, and the historical current intensity data to a fixed range; usually between 0 and 1, or make them have zero mean and unit variance. This helps to compare parameters of different dimensions; normalization allows data collected by different sensors to be analyzed at the same scale, which is conducive to algorithm processing and model training.

[0024] (3) Feature extraction: extract the most valuable information for predicting equipment performance from the historical temperature data, the historical pressure value data, the historical vibration frequency and amplitude data, and the historical current intensity data; for example, extract features using methods such as time series analysis, Fourier transform, and wavelet transform; through feature extraction, data dimensions can be reduced, computing efficiency can be improved, and the interpretability of the model can be enhanced.

[0025] (4) Data fusion: The historical temperature data, the historical pressure value data, the historical vibration frequency and amplitude data, and the historical current intensity data from different sensors or at different time points are fused (merged) to obtain a device data set, that is, to create a more comprehensive data set that reflects the comprehensive status of the device; data fusion can provide richer information and help to more accurately predict and diagnose equipment problems.

[0026] (5) Data caching and storage: Store the device data set in a database or data lake to facilitate subsequent analysis and model training; use efficient data storage solutions, such as column storage databases or distributed file systems, to quickly read and write large amounts of data and support real-time analysis and historical data queries.

[0027] Step S20: construct an initial 3D twin model according to the target historical operation data, and optimize the model parameters of the initial 3D twin model through historical data analysis to obtain a 3D twin model that meets performance requirements.

[0028] Specifically, the device data set is divided into a training set, a validation set and a test set according to a preset ratio; an initial 3D twin model of the device is designed according to the device data set using 3D modeling software; the initial 3D twin model is trained using the training set until the total loss function of the initial 3D twin model reaches a preset convergence condition; the model parameters of the trained initial 3D twin model are adjusted using the validation set, and the initial 3D twin model after the adjusted model parameters is tested using the test set through simulation software to verify whether the initial 3D twin model can accurately reflect the performance and status of the actual device. If the test results meet the preset requirements, a 3D twin model that meets the performance requirements is obtained.

[0029] The initial 3D twin model of the device is constructed as follows: (1) Data collection: First, collect the geometric data, physical properties, functional characteristics, etc. of the equipment.

[0030] (2) Model design: Use 3D modeling software (such as AutoCAD, SolidWorks, Blender, etc.) to design an initial 3D twin model of the device based on the collected data.

[0031] (3) Attribute association: Associating the data collected by the sensor with the corresponding parts in the initial 3D twin model to ensure that the model can reflect the operating status of the actual equipment.

[0032] (4) Model integration: Connect the initial 3D twin model with the data interface of the physical device to achieve real-time data synchronization.

[0033] (5) Simulation and verification: The initial 3D twin model is tested through simulation software to verify whether it can accurately reflect the performance and status of the actual equipment.

[0034] Among them, the 3D twin model includes: a geometric model, a physical model, a behavioral model, a data model, an analytical model and a visualization interface; the geometric model is used for users to intuitively see the structure of the equipment and provide a reference during design or maintenance; the physical model is used to simulate the physical behavior of the equipment in the actual environment to help understand the performance of the equipment under different conditions; the behavioral model is used to ensure that the model operates according to the operating logic of the actual equipment, and is used to simulate and predict the behavior of the equipment; the data model is used to provide necessary data support for the model, and is the basis for the interaction between the model and the real world; the analytical model is used to provide in-depth insights into equipment performance and predictive maintenance recommendations by analyzing the data in the data model; the visualization interface is used for operation and maintenance personnel to easily monitor the equipment status, and perform fault diagnosis and decision support.

[0035] The functions and compositions of each model in the 3D twin model are as follows: (1) Geometric model: Function: Provides the precise 3D geometry of the device.

[0036] Composition: It is composed of basic geometric elements such as points, lines, and surfaces, reflecting the physical size and structure of the equipment.

[0037] (2) Physical model: Function: Simulate the physical behavior of the device, such as heat conduction, mechanical response, etc.

[0038] Composition: including material properties, mechanical characteristics, thermodynamic parameters, etc.

[0039] (3) Behavioral model: Function: Simulate the working logic and operation behavior of the device.

[0040] Composition: A set of rules and algorithms that describe the responses and actions of a device under different conditions.

[0041] (4) Data model: Function: Store and process equipment-related data, such as sensor readings, historical operating data, etc.

[0042] Composition: Database and data structure used to store real-time data and historical data.

[0043] (5) Analysis model: Function: Use machine learning and data analysis algorithms to predict and analyze equipment performance.

[0044] Composition: Includes modules such as data preprocessing, feature extraction, model training and prediction.

[0045] (6) Visual interface: Function: Provides an interface for users to interact with the 3D twin model and displays the model's operating status and analysis results.

[0046] Composition: Graphical user interface (GUI), including 3D view, control panel, alarm system, etc.

[0047] Step S30: Acquire the real-time operation data of the target IoT device, input the real-time operation data into the 3D twin model, and output the performance analysis and prediction results of the target IoT device.

[0048] Specifically, the 3D twin model is initialized to ensure that the 3D twin model correctly reflects the initial state of the device, the real-time operation data of the target IoT device is obtained, the real-time operation data is input into the initialized 3D twin model, and the state of the model is updated; the performance indicators of each component in the 3D twin model, such as efficiency, energy consumption, wear, etc., are calculated; the real-time operation data is trend analyzed and fault predicted through the machine learning and data analysis algorithms of the 3D twin model, the changing trends of performance indicators are analyzed, possible performance degradation or fault signs are identified, and the machine learning model is used to predict the potential failure points and time of the equipment, predictive maintenance is performed, and the performance analysis and prediction results of the target IoT device are output.

[0049] The performance analysis and prediction results include the overall operating status of the equipment, key performance indicators of the equipment, abnormal data and fault diagnosis results.

[0050] There is a close relationship between the machine learning and data analysis algorithms and the 3D twin model in the present invention. The following are the interactions and connections between them: (1) Data collection and preprocessing: Machine learning and data analysis algorithms rely on high-quality data collected from various device sensors. These data, including temperature, pressure, vibration, etc., are the basis for building 3D twin models. The data acquisition module is responsible for collecting this data and providing a format suitable for analysis for machine learning algorithms through preprocessing (such as cleaning, normalization, feature extraction, etc.).

[0051] (2) Model construction: The construction of 3D twin models requires a combination of physical modeling technology and machine learning algorithms. Physical modeling is used to simulate the actual working principle of the device, while machine learning algorithms are used to learn the operating mode and abnormal behavior of the device. Machine learning algorithms can assist the physical modeling process and optimize model parameters through historical data analysis to make the 3D twin model more accurate.

[0052] (3) Performance analysis and prediction: Machine learning algorithms conduct in-depth analysis of the real-time data and 3D twin models of the equipment to predict the future status and potential failures of the equipment. The analysis results can be used to update the 3D twin model to reflect the latest status of the equipment.

[0053] (4) Visualization and decision support: The 3D twin model is displayed through a visual interface, allowing operation and maintenance personnel to intuitively understand the operating status of the equipment and thus intuitively understand relevant information about the equipment, such as abnormal information, fault information, etc. The analysis results of the machine learning algorithm, such as fault prediction and maintenance suggestions, will also be displayed in the visual interface to support the decision-making of operation and maintenance personnel.

[0054] The specific relationship is as follows: Machine learning and data analysis algorithms are the core of the intelligent 3D twin model. They enable the model to not only reflect the static structure of the equipment, but also simulate the dynamic behavior of the equipment and predict the future state. The 3D twin model provides a platform for machine learning algorithms, so that its analysis results can be presented in an intuitive way in three-dimensional space, enhancing the operation and maintenance personnel's understanding of the equipment status. The two promote each other. The machine learning algorithm improves the prediction ability of the 3D twin model, while the 3D twin model provides a practical application scenario for the machine learning algorithm. In summary, machine learning and data analysis algorithms complement the 3D twin model and together constitute a powerful operation and optimization system, thereby improving the monitoring and maintenance efficiency of IoT devices.

[0055] Simulation tests are performed on the 3D twin model to simulate the response of the equipment under different operating conditions and predict performance changes. Based on the performance analysis and prediction results, recommendations for optimizing equipment operating parameters or maintenance plans are generated. The accuracy of the prediction results is verified through actual operating data, and the 3D twin model is continuously adjusted to improve prediction accuracy.

[0056] Furthermore, the 3D twin model of the target IoT device and the performance analysis and prediction results are displayed through the visualization interface of the 3D twin model, and optimization suggestions are provided to support the decision-making of operation and maintenance personnel.

[0057] The performance analysis and prediction results include: (1) Equipment status overview: Real-time display of the overall operating status of the equipment, including normal, warning, fault, etc.

[0058] (2) Performance indicator analysis: key performance indicators (KPIs) of equipment, such as efficiency, energy consumption, output, reliability, etc.

[0059] (3) Abnormal data detection: Identify data points that deviate from the normal range, for example, temperature anomaly: the temperature of a certain part of the equipment exceeds the preset safety threshold; vibration anomaly: the vibration amplitude of the equipment exceeds the normal operating level, which may indicate bearing wear or other mechanical problems.

[0060] (4) Fault diagnosis: Analyze possible causes based on abnormal data. For example, if both vibration and temperature are abnormal at the same time, it may indicate that the equipment has insufficient lubrication problems; if the current suddenly increases while the output decreases, it may indicate that the motor efficiency is reduced.

[0061] For example, actual temperature anomaly handling: Analysis results: The 3D twin model shows that the temperature of a certain equipment component continues to rise; processing suggestions: Check whether the cooling system is working properly, clean or replace the radiator, and adjust the workload to reduce the component temperature.

[0062] Beneficial effects of the present invention: (1) The present invention can quickly and in real time monitor and diagnose the status and performance of IoT devices.

[0063] (2) The present invention is based on a 3D twin model to accurately provide predictive maintenance and optimization suggestions for equipment.

[0064] (3) The present invention provides a more intuitive equipment monitoring and management interface through a visual interface, thereby improving the operation and maintenance efficiency of the equipment.

[0065] Furthermore, if Figure 2 As shown, based on the above-mentioned Internet of Things device monitoring method based on the 3D twin model, the present invention also provides an Internet of Things device monitoring system based on the 3D twin model, wherein the Internet of Things device monitoring system based on the 3D twin model includes: The data collection module 51 is used to obtain the historical operation data of multiple IoT devices collected by multiple sensors, and pre-process the historical operation data to obtain target historical operation data; A model optimization module 52, configured to construct an initial 3D twin model according to the target historical operation data, and optimize the model parameters of the initial 3D twin model through historical data analysis to obtain a 3D twin model that meets the performance requirements; The result analysis module 53 is used to obtain the real-time operation data of the target IoT device, input the real-time operation data into the 3D twin model, and output the performance analysis and prediction results of the target IoT device.

[0066] The IoT device monitoring system based on the 3D twin model also includes: A visualization display module is used to display the 3D twin model of the target IoT device and the performance analysis and prediction results through the visualization interface of the 3D twin model, and to provide optimization suggestions and support for the decision-making of operation and maintenance personnel.

[0067] The present invention provides an Internet of Things device monitoring method and system based on a 3D twin model. By establishing a 3D twin model of the device, real-time monitoring, fault diagnosis and predictive maintenance of the Internet of Things device are realized. It combines physical modeling, data analysis and visualization technology, can comprehensively analyze the status and performance of the device, and provide optimization suggestions and decision support.

[0068] Furthermore, if Figure 3 As shown, based on the above-mentioned Internet of Things device monitoring method and system based on 3D twin model, the present invention also provides a terminal accordingly, and the terminal includes a processor 10, a memory 20 and a display 30. Figure 3 Only some components of the terminal are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0069] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard disk or memory of the terminal. In other embodiments, the memory 20 may also be an external storage device of the terminal, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the terminal. Furthermore, the memory 20 may also include both an internal storage unit of the terminal and an external storage device. The memory 20 is used to store application software and various types of data installed on the terminal, such as the program code of the installation terminal. The memory 20 may also be used to temporarily store data that has been output or is to be output. In one embodiment, an Internet of Things device monitoring program 40 based on a 3D twin model is stored on the memory 20, and the Internet of Things device monitoring program 40 based on a 3D twin model can be executed by the processor 10, thereby realizing the Internet of Things device monitoring method based on a 3D twin model in the present application.

[0070] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run the program code or process data stored in the memory 20, such as executing the IoT device monitoring method based on the 3D twin model.

[0071] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 30 is used to display information on the terminal and to display a visual user interface. The components 10-30 of the terminal communicate with each other via a system bus.

[0072] In one embodiment, when the processor 10 executes the IoT device monitoring program 40 based on the 3D twin model in the memory 20, the following steps are implemented: Acquire historical operation data of multiple IoT devices collected by multiple sensors, pre-process the historical operation data, and obtain target historical operation data; Constructing an initial 3D twin model according to the target historical operation data, and optimizing model parameters of the initial 3D twin model through historical data analysis to obtain a 3D twin model that meets performance requirements; Acquire the real-time operation data of the target IoT device, input the real-time operation data into the 3D twin model, and output the performance analysis and prediction results of the target IoT device.

[0073] The historical operation data includes: historical temperature data, historical pressure value data, historical vibration frequency and amplitude data, and historical current intensity data; The acquiring of historical operation data of multiple IoT devices collected by multiple sensors and preprocessing of the historical operation data to obtain target historical operation data specifically includes: Acquire historical temperature data inside or on the surface of the IoT device collected by a temperature sensor, where the historical temperature data is used to monitor whether the IoT device is within a normal operating temperature range; Acquire historical pressure value data inside the IoT device collected by the pressure sensor, wherein the historical pressure value data is used to detect whether the IoT device is operating under specified pressure conditions; Acquire historical vibration frequency and amplitude data of the IoT device collected by the vibration sensor, wherein the historical vibration frequency and amplitude data are used to analyze the operating status of the IoT device and detect potential mechanical failures; Obtaining historical current intensity data of the operation of the IoT device collected by the current sensor, wherein the historical current intensity data is used to monitor the load condition and energy consumption of the electrical system; The historical temperature data, the historical pressure value data, the historical vibration frequency and amplitude data, and the historical current intensity data are preprocessed to obtain target historical temperature data, target historical pressure value data, target historical vibration frequency and amplitude data, and target historical current intensity data.

[0074] Wherein, the preprocessing includes: data cleaning, data normalization, feature extraction, data fusion and data caching; The preprocessing of the historical temperature data, the historical pressure value data, the historical vibration frequency and amplitude data, and the historical current intensity data to obtain target historical temperature data, target historical pressure value data, target historical vibration frequency and amplitude data, and target historical current intensity data specifically includes: removing noise, abnormal values ​​and incomplete records from the historical temperature data, the historical pressure value data, the historical vibration frequency and amplitude data and the historical current intensity data; Scaling the historical temperature data, the historical pressure value data, the historical vibration frequency and amplitude data, and the historical current intensity data to a fixed range; Extracting the most valuable information for predicting equipment performance from the historical temperature data, the historical pressure value data, the historical vibration frequency and amplitude data, and the historical current intensity data; The historical temperature data, the historical pressure value data, the historical vibration frequency and amplitude data, and the historical current intensity data are fused to obtain a device data set; The device data set is stored in a database or a data lake.

[0075] The step of constructing an initial 3D twin model according to the target historical operation data and optimizing the model parameters of the initial 3D twin model through historical data analysis to obtain a 3D twin model that meets the performance requirements specifically includes: Dividing the device data set into a training set, a validation set, and a test set according to a preset ratio; designing an initial 3D twin model of the device based on the device dataset using 3D modeling software; Using the training set to train the initial 3D twin model until a total loss function of the initial 3D twin model reaches a preset convergence condition; The validation set is used to adjust the model parameters of the initial 3D twin model after training, and the initial 3D twin model after adjusting the model parameters is tested using the test set through simulation software to verify whether the initial 3D twin model can accurately reflect the performance and status of the actual device. If the test results meet the preset requirements, a 3D twin model that meets the performance requirements is obtained.

[0076] The 3D twin model includes: a geometric model, a physical model, a behavioral model, a data model, an analysis model and a visualization interface; The geometric model is used to allow users to intuitively see the structure of the equipment and provide a reference during design or maintenance; The physical model is used to simulate the physical behavior of the device in the actual environment to help understand the performance of the device under different conditions; The behavior model is used to ensure that the model operates according to the operation logic of the actual device and is used to simulate and predict the behavior of the device; The data model is used to provide necessary data support for the model; The analytical model is used to provide predictive maintenance suggestions for equipment performance by analyzing data in the data model; The visual interface is used for operation and maintenance personnel to monitor equipment status and perform fault diagnosis and decision support.

[0077] The step of acquiring the real-time operation data of the target IoT device, inputting the real-time operation data into the 3D twin model, and outputting the performance analysis and prediction results of the target IoT device specifically includes: Initialize the 3D twin model, obtain real-time operation data of the target IoT device, and input the real-time operation data into the initialized 3D twin model; Perform trend analysis and fault prediction on the real-time operation data through the machine learning and data analysis algorithms of the 3D twin model, and output performance analysis and prediction results of the target IoT device; Generate recommendations for optimizing equipment operating parameters or maintenance plans based on the performance analysis and prediction results, verify the accuracy of the prediction results through actual operation data, and continuously adjust the 3D twin model; The performance analysis and prediction results include the overall operating status of the equipment, key performance indicators of the equipment, abnormal data and fault diagnosis results.

[0078] The method further comprises: obtaining real-time operation data of the target IoT device, inputting the real-time operation data into the 3D twin model, and outputting performance analysis and prediction results of the target IoT device, and then further comprising: The 3D twin model of the target IoT device and the performance analysis and prediction results are displayed through the visual interface of the 3D twin model, and optimization suggestions are provided to support the decision-making of operation and maintenance personnel.

[0079] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores an Internet of Things device monitoring program based on a 3D twin model, and when the Internet of Things device monitoring program based on a 3D twin model is executed by a processor, the steps of the Internet of Things device monitoring method based on a 3D twin model as described above are implemented.

[0080] In summary, the present invention provides an IoT device monitoring method, system, terminal and computer-readable storage medium based on a 3D twin model, the method comprising: obtaining historical operation data of multiple IoT devices collected by multiple sensors, preprocessing the historical operation data to obtain target historical operation data; constructing an initial 3D twin model based on the target historical operation data, and optimizing the model parameters of the initial 3D twin model through historical data analysis to obtain a 3D twin model that meets performance requirements; obtaining real-time operation data of the target IoT device, inputting the real-time operation data into the 3D twin model, and outputting the performance analysis and prediction results of the target IoT device. Based on the 3D twin model, the present invention can monitor and diagnose the status and performance of IoT devices in real time, and provide predictive maintenance and optimization suggestions for the equipment.

[0081] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or terminal including the element.

[0082] Of course, those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the program can be stored in a computer-readable storage medium that can be read by a computer, and the program can include the processes of the above-mentioned method embodiments when executed. The computer-readable storage medium can be a memory, a disk, an optical disk, etc.

[0083] It should be understood that the application of the present invention is not limited to the above examples. For ordinary technicians in this field, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to the present invention.

Claims

1. A method for monitoring IoT devices based on a 3D twin model, characterized in that: The IoT device monitoring method based on the 3D twin model includes: Acquire historical operation data of multiple IoT devices collected by multiple sensors, and pre-process the historical operation data to obtain target historical operation data; Constructing an initial 3D twin model according to the target historical operation data, and optimizing model parameters of the initial 3D twin model through historical data analysis to obtain a 3D twin model that meets performance requirements; Acquire the real-time operation data of the target IoT device, input the real-time operation data into the 3D twin model, and output the performance analysis and prediction results of the target IoT device.

2. The method for monitoring IoT devices based on 3D twin models according to claim 1, characterized in that: The historical operation data includes: historical temperature data, historical pressure value data, historical vibration frequency and amplitude data, and historical current intensity data; The acquiring of historical operation data of multiple IoT devices collected by multiple sensors and preprocessing of the historical operation data to obtain target historical operation data specifically includes: Acquire historical temperature data inside or on the surface of the IoT device collected by a temperature sensor, where the historical temperature data is used to monitor whether the IoT device is within a normal operating temperature range; Acquire historical pressure value data inside the IoT device collected by the pressure sensor, wherein the historical pressure value data is used to detect whether the IoT device is operating under specified pressure conditions; Acquire historical vibration frequency and amplitude data of the IoT device collected by the vibration sensor, wherein the historical vibration frequency and amplitude data are used to analyze the operating status of the IoT device and detect potential mechanical failures; Obtaining historical current intensity data of the operation of the IoT device collected by the current sensor, wherein the historical current intensity data is used to monitor the load condition and energy consumption of the electrical system; The historical temperature data, the historical pressure value data, the historical vibration frequency and amplitude data, and the historical current intensity data are preprocessed to obtain target historical temperature data, target historical pressure value data, target historical vibration frequency and amplitude data, and target historical current intensity data.

3. The method for monitoring IoT devices based on 3D twin models according to claim 2, characterized in that: The preprocessing includes: data cleaning, data normalization, feature extraction, data fusion and data caching; The preprocessing of the historical temperature data, the historical pressure value data, the historical vibration frequency and amplitude data, and the historical current intensity data to obtain target historical temperature data, target historical pressure value data, target historical vibration frequency and amplitude data, and target historical current intensity data specifically includes: removing noise, abnormal values ​​and incomplete records from the historical temperature data, the historical pressure value data, the historical vibration frequency and amplitude data and the historical current intensity data; Scaling the historical temperature data, the historical pressure value data, the historical vibration frequency and amplitude data, and the historical current intensity data to a fixed range; Extracting the most valuable information for predicting equipment performance from the historical temperature data, the historical pressure value data, the historical vibration frequency and amplitude data, and the historical current intensity data; The historical temperature data, the historical pressure value data, the historical vibration frequency and amplitude data, and the historical current intensity data are fused to obtain a device data set; The device data set is stored in a database or a data lake.

4. The method for monitoring IoT devices based on 3D twin models according to claim 3 is characterized in that: The step of constructing an initial 3D twin model according to the target historical operation data, and optimizing the model parameters of the initial 3D twin model through historical data analysis to obtain a 3D twin model that meets the performance requirements, specifically includes: Dividing the device data set into a training set, a validation set, and a test set according to a preset ratio; designing an initial 3D twin model of the device based on the device dataset using 3D modeling software; Using the training set to train the initial 3D twin model until a total loss function of the initial 3D twin model reaches a preset convergence condition; The validation set is used to adjust the model parameters of the initial 3D twin model after training, and the initial 3D twin model after adjusting the model parameters is tested using the test set through simulation software to verify whether the initial 3D twin model can accurately reflect the performance and status of the actual device. If the test results meet the preset requirements, a 3D twin model that meets the performance requirements is obtained.

5. The method for monitoring IoT devices based on 3D twin models according to claim 4 is characterized in that: The 3D twin model includes: a geometric model, a physical model, a behavioral model, a data model, an analysis model and a visualization interface; The geometric model is used to allow users to intuitively see the structure of the equipment and provide a reference during design or maintenance; The physical model is used to simulate the physical behavior of the device in the actual environment to help understand the performance of the device under different conditions; The behavior model is used to ensure that the model operates according to the operation logic of the actual device and is used to simulate and predict the behavior of the device; The data model is used to provide necessary data support for the model; The analytical model is used to provide predictive maintenance suggestions for equipment performance by analyzing data in the data model; The visual interface is used for operation and maintenance personnel to monitor equipment status and perform fault diagnosis and decision support.

6. The method for monitoring IoT devices based on 3D twin models according to claim 1 or 4, characterized in that: The acquiring of real-time operation data of the target IoT device, inputting the real-time operation data into the 3D twin model, and outputting the performance analysis and prediction results of the target IoT device specifically includes: Initialize the 3D twin model, obtain real-time operation data of the target IoT device, and input the real-time operation data into the initialized 3D twin model; Perform trend analysis and fault prediction on the real-time operation data through the machine learning and data analysis algorithms of the 3D twin model, and output performance analysis and prediction results of the target IoT device; Generate recommendations for optimizing equipment operating parameters or maintenance plans based on the performance analysis and prediction results, verify the accuracy of the prediction results through actual operation data, and continuously adjust the 3D twin model; The performance analysis and prediction results include the overall operating status of the equipment, key performance indicators of the equipment, abnormal data and fault diagnosis results.

7. The method for monitoring IoT devices based on 3D twin models according to claim 6, characterized in that: The real-time operation data of the target IoT device is obtained, the real-time operation data is input into the 3D twin model, and the performance analysis and prediction results of the target IoT device are output, and then the following is further included: The 3D twin model of the target IoT device and the performance analysis and prediction results are displayed through the visual interface of the 3D twin model, and optimization suggestions are provided to support the decision-making of operation and maintenance personnel.

8. An IoT device monitoring system based on a 3D twin model, characterized in that: The IoT device monitoring system based on the 3D twin model includes: A data acquisition module is used to obtain historical operation data of multiple IoT devices collected by multiple sensors, and pre-process the historical operation data to obtain target historical operation data; A model optimization module, used to construct an initial 3D twin model according to the target historical operation data, and optimize the model parameters of the initial 3D twin model through historical data analysis to obtain a 3D twin model that meets performance requirements; The result analysis module is used to obtain the real-time operation data of the target IoT device, input the real-time operation data into the 3D twin model, and output the performance analysis and prediction results of the target IoT device.

9. A terminal, characterized in that: The terminal includes: a memory, a processor, and an Internet of Things device monitoring program based on a 3D twin model stored in the memory and executable on the processor. When the Internet of Things device monitoring program based on a 3D twin model is executed by the processor, the steps of the Internet of Things device monitoring method based on a 3D twin model as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an Internet of Things device monitoring program based on a 3D twin model. When the Internet of Things device monitoring program based on a 3D twin model is executed by a processor, the steps of the Internet of Things device monitoring method based on a 3D twin model as described in any one of claims 1 to 7 are implemented.

Images