Micro-nano impact press-in tester operation monitoring system based on digital twinning

Abstract

The invention provides a micro-nano impact press-in tester operation monitoring system based on digital twinning, and is suitable for the field of precise instrument maintenance. The system realizes multi-physical field coupling modeling in a micro-nano press-in test through a digital twinning technology, and can monitor the state of an instrument in real time with high precision, predict faults and perform dynamic optimization. The system is integrated with a high-precision sensor, data such as micro force, extremely high temperature and nanoscale displacement are collected in real time, a digital twin model is constructed, and the operation state of an instrument is mapped. Historical and real-time data are analyzed by means of a machine learning algorithm, potential faults can be accurately predicted, maintenance suggestions can be provided, and the precision retentivity and the test stability of the instrument under the material service working condition are ensured. The interaction center provides a visual interface, supports real-time monitoring, dynamic adjustment and early warning functions, and remarkably improves the intelligent maintenance level of the instrument. The invention is suitable for the fields of material science, micro-nano mechanical test and the like, and provides an innovative precise instrument intelligent management scheme.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent manufacturing and high-precision instrument maintenance technology, and specifically relates to the innovative application of digital twin technology in micro-nano impact indentation testers. The present invention proposes an intelligent operation monitoring system, which uses digital twin technology to achieve high-precision real-time monitoring, accurate fault prediction, and intuitive visual management of the state of micro-nano impact indentation testers, thereby ensuring the accuracy retention, operation stability, and test reliability of the tester at the micro-nano scale. This system is suitable for fields such as materials science, precision manufacturing, and microstructure characterization, and provides a new solution for the intelligent maintenance of high-precision instruments. Background Art

[0002] The micro-nano impact indentation tester is an important instrument for studying the mechanical properties of materials at the micro-nano scale. It is mainly used in the fields of micro-nano mechanical testing, microstructure analysis and precision manufacturing. With the rapid development of nanotechnology and micro-electromechanical systems (MEMS) technology, people have put forward higher requirements for the accuracy, stability and reliability of the tester. However, the current instrument operating environment is complex. For example, under high temperature and vacuum environment, the sensor output signal is susceptible to noise interference, resulting in mechanical data deviation. In addition, vibration and mechanical wear during the test process will cause the accumulation of displacement measurement errors, resulting in a serious reduction in the reproducibility of experimental data. These problems make it difficult for existing equipment to meet the requirements in high-precision scenarios. Therefore, realizing accurate monitoring and intelligent maintenance of the tester has become an important topic in instrument reliability research.

[0003] At present, instrument maintenance mainly relies on manual inspection and regular maintenance, which is inefficient and slow to respond, and is difficult to adapt to the needs of high-precision test instruments for real-time monitoring and precise maintenance. To solve this problem, digital twin technology has gradually entered people's field of vision. By establishing a real-time mapping between physical instruments and virtual models, digital twin technology can dynamically track the operating status of instruments, predict faults, and optimize operating strategies, providing a new technical path for instrument management.

[0004] The advantage of digital twin technology lies in its dynamic management capability throughout the entire life cycle of the instrument. Based on real-time data and historical data, digital twin technology can build a high-precision dynamic model to provide real-time feedback and predict the operating status of the instrument. When this technology is applied to micro-nano testers, it can overcome the shortcomings of traditional methods in response speed and monitoring accuracy, achieve high-precision monitoring, fault warning and dynamic optimization of instrument status, and greatly improve the intelligence level and operational stability of the instrument. Summary of the invention

[0005] The present invention aims to provide an innovative solution to the deficiencies in the prior art, in particular to solve the difficulties in high-precision monitoring and fault prediction of micro-nano impact indentation testers.

[0006] The present invention proposes an intelligent monitoring system based on digital twin technology for the operation status management of micro-nano impact indentation tester. The system effectively solves the problems of monitoring response delay, low maintenance efficiency, and delayed fault handling in the prior art by real-time monitoring of the instrument status, intelligent prediction of potential faults, and optimization of operation efficiency. Through the application of this system, the high-precision operation capability of the instrument can be significantly improved, the service life can be extended, and the operation safety and stability can be improved.

[0007] The technical innovations of the present invention are mainly reflected in the following aspects:

[0008] (1) Multi-sensor data fusion and dynamic monitoring: The system integrates a variety of high-precision sensors (such as force sensors, temperature sensors, displacement sensors, etc.) to collect instrument operation data in real time. The fusion processing of multi-sensor data is achieved through advanced algorithms such as Kalman filtering suitable for micro-nano impact and compression testing processes, which greatly improves the ability to capture tiny dynamic changes and ensures the accuracy of monitoring results.

[0009] (2) High-precision multi-physics modeling: Multi-physics coupling simulation technology is used to combine multiple physical field parameters such as mechanics, thermals, and vacuum to build a detailed digital twin model. This model can dynamically map the real state of the instrument during the micro-nano impact test and keep the virtual model synchronized with the actual instrument operation state through a real-time update mechanism.

[0010] (3) Intelligent fault prediction: Introduce a fault prediction model for micro-nano impact penetration tester based on machine learning (such as random forest, long short-term memory network LSTM, etc.), use real-time and historical data for dynamic analysis, effectively identify potential risks of the instrument, issue warnings, and provide maintenance recommendations.

[0011] (4) Real-time data synchronization and feedback: The system uses efficient streaming data processing technology to support microsecond-level data acquisition and real-time transmission, achieving low-latency synchronization between physical instruments and digital twin models. This function significantly improves the real-time performance of instrument monitoring and the accuracy of prediction.

[0012] This invention breaks through the limitations of traditional digital twin technology applied to large instruments and applies it to the field of micro-nano testers for the first time. The system adopts a technical path combining multi-dimensional sensor arrays with intelligent algorithms, which significantly improves the state monitoring and intelligent maintenance level of micro-nanoscale instruments.

[0013] To achieve the above objectives, the present invention constructs an intelligent monitoring system for micro-nano impact indentation tester based on digital twins. The system architecture consists of the following core modules:

[0014] Physical layer module of micro-nano impact penetration tester: This module includes the physical instrument of the micro-nano impact penetration tester and the sensor array of its key parts. The sensors realize real-time perception of the operating data of each part through the data network. By deploying the sensor system, the physical layer module can accurately collect key parameters such as force, displacement, temperature, etc. during the working process of the tester. The integrated data network integrates the data of each part through the Internet of Things technology, laying the foundation for subsequent data analysis and real-time status feedback;

[0015] Data acquisition and processing module of micro-nano impact indentation tester: This module integrates multiple functions such as data acquisition, analysis, filtering, denoising and integration, and is used to process the data collected by the sensors of the physical layer module. After preliminary filtering and denoising, the multi-source data collected in real time is integrated in a standard data format and uploaded to the cloud database. This module can interconnect sensor data with the digital twin model, so that the digital twin model can obtain the latest instrument status information for subsequent real-time monitoring and intelligent analysis;

[0016] Digital twin model of micro-nano impact indentation tester: The digital twin model achieves dynamic mapping of the tester structure and status through synchronization of virtual simulation and instrument operation process. This model not only achieves accurate reproduction of the physical structure of the tester, but also optimizes and analyzes the instrument's operating procedures and operating safety, performs fault prediction, and sends early warning information in real time. The core goal of the digital twin model is to achieve a seamless combination of the tester's virtual space and real-world operations, ensuring efficient monitoring of the instrument's operating status and timely response to abnormal conditions;

[0017] Digital twin monitoring system interactive center: The interactive center uses the data monitoring screen as the main operation interface. Through the source data in the test process and the data support provided by the digital twin model, users can realize visual monitoring and interactive operation of the instrument. This module integrates the three-dimensional real-time visualization function of the instrument, as well as the full-process data monitoring, real-time interaction and fault response functions, allowing users to observe the operating status of the instrument from multiple angles. The interactive center provides an integrated operation experience for instrument managers, which helps to quickly identify the instrument status and make corresponding maintenance adjustments.

[0018] The physical layer module of the micro-nano impact penetration tester includes the following components:

[0019] The micro-nano impact indentation tester is used to perform fine mechanical property tests of materials at the micro-nano scale. High-precision sensors are installed at key parts of the instrument, including but not limited to micro dynamic force sensors, acceleration sensors, temperature sensors, and laser Doppler displacement sensors, which can continuously monitor various operating status parameters of the instrument entity to ensure the accuracy and stability of the test process. Each sensor can independently provide different types of micro-nano scale data (such as micro displacement, ultra-low force, temperature change, etc.). These data can not only be synchronized to the digital twin model in real time, but also be comprehensively analyzed through data fusion technology to build a virtual model that fully reflects the operating status of the instrument. By fusing data from different sensors, the dynamic behavior of micro-nano instruments at extremely small scales can be effectively captured, breaking through the limitations of a single sensor model.

[0020] The data acquisition and processing module of the micro-nano impact indentation tester includes the following submodules:

[0021] Data acquisition module, which is used to collect multiple physical parameter data provided by the above-mentioned high-precision sensors in real time. The data includes dynamic mechanical data of the load applied by the micro-nano impact indentation tester, indenter acceleration data, temperature data of the instrument and the test material, applied displacement data and its corresponding timestamp information. This module ensures that all key operating parameters can be obtained in real time, providing a basis for subsequent data processing and analysis;

[0022] Data processing module, which is used to systematically analyze and process the collected high-precision sensor data, including but not limited to filtering the raw data to effectively remove noise and irrelevant data. Through further processing of mechanical data, this module can determine whether the force and acceleration of the micro-nano impact indentation tester during loading meet the set working standards; at the same time, the analysis of temperature data and displacement data can determine whether the instrument successfully simulates and reproduces the expected working environment during operation, thereby ensuring the accuracy and consistency of the test conditions;

[0023] Data integration module: This module is responsible for the unified integration of various processed data, and packages various data into a data set that meets the standards. After the data set is integrated, the module transfers the data to the cloud database for subsequent use in the digital twin model;

[0024] The data upload module is used to upload the integrated standardized data set to the cloud database, serving as the core bridge for the interconnection between physical sensor data and the digital twin model. Through this module, the digital twin model can obtain the latest status information of the instrument, thereby realizing real-time monitoring of the instrument and data-driven intelligent analysis and prediction.

[0025] The digital twin model of the micro-nano impact indentation tester includes the following components:

[0026] Digital twin geometric model building module, based on the geometric shape and material properties of the instrument, builds a digital twin model that is highly consistent with the physical instrument, ensuring that the structure and working characteristics of the instrument are fully mapped. By collecting the geometric dimensions, structural characteristics, material properties and operating function parameters of the tester, combined with variable operating parameters, a three-dimensional digital model is built that can fully reflect the static and dynamic characteristics of the physical entity of the micro-nano impact penetration tester. This three-dimensional model not only accurately restores the geometric structure of the instrument, but also ensures that the dynamic behavior of key components can be truly mapped to the virtual model, presenting motion characteristics consistent with the physical instrument;

[0027] Data transmission and real-time synchronization module, which uses high-precision sensors to collect instrument operating parameters such as force, displacement, temperature, etc. in real time, and transmits the data to the database to provide real-time data support for the digital model. Data synchronization uses an optimized database structure and reduces transmission delays through interpolation algorithms to ensure that the instrument status in the virtual environment can be updated in real time. The data synchronization mechanism also combines an adaptive error correction algorithm to reduce synchronization errors and optimize data smoothness, achieving high-precision consistency between physical instruments and virtual models;

[0028] 3D visualization module: This module builds an interactive 3D visualization interface to intuitively present the operating status and fault conditions of the instrument, and supports users to monitor the instrument status in real time. Through this visualization interface, users can view key indicators such as the temperature distribution and stress conditions of the instrument in real time, and can perform interactive operations, thereby improving the convenience and intuitiveness of user instrument management;

[0029] The fault prediction and early warning module builds a fault prediction model based on machine learning algorithms to determine the operating status of the micro-nano impact indentation tester and predict its performance trend. This module analyzes the changing trends of real-time data and historical data to effectively identify fault risks and issue early warning signals;

[0030] The aforementioned machine learning algorithms mainly include: using decision trees, random forests and long short-term memory networks (LSTM) as the main models, and building an efficient fault prediction model by analyzing the historical and real-time data of the instrument. The model provides early warning before instrument failure occurs and generates maintenance recommendations, thereby supporting efficient management of the instrument and extending its service life.

[0031] The digital twin monitoring system interaction center module includes the following components:

[0032] Instrument operation intelligent monitoring module, this module focuses on real-time status monitoring and intelligent analysis of the instrument. Through the data monitoring large screen, the system presents the operating status of the tester, real-time data of key components and environmental variables (such as temperature, pressure, etc.) in multiple dimensions. Based on the support of the digital twin model, this module integrates various sensor data to ensure the synchronous update of the instrument's physical status and virtual model. At the same time, the intelligent monitoring center can automatically identify abnormal situations and issue alarms through preset thresholds to help managers detect and handle emergencies in instrument operation in a timely manner, thereby improving the safety and stability of instrument operation;

[0033] Instrument intelligent diagnosis module: This module realizes intelligent diagnosis of potential instrument failures and performance degradation through in-depth analysis of instrument operation data. Relying on the digital twin model, the intelligent diagnosis center predicts the possibility of instrument failure and generates maintenance recommendations by analyzing historical data and real-time data. The system can identify the aging, fatigue and other conditions of different components, and provide preventive maintenance guidance to users based on the diagnosis results, helping users take measures before failures occur, reducing unplanned downtime of instruments and improving the availability and service life of instruments;

[0034] Instrument information management module, this module provides information support for instrument management personnel to manage the entire life cycle of the instrument. This module records and updates the basic information, operating specifications, technical parameters, maintenance records, etc. of the instrument to form a complete instrument archive. Users can use this module to view the historical data and operating status reports of the instrument in real time. The system also supports a variety of information display methods (such as charts, curves, etc.) for managers to analyze the instrument status. This information management function not only helps with the daily management of the instrument, but also provides detailed data references for decisions such as instrument maintenance and performance optimization;

[0035] Instrument parts management module, this module establishes a refined management system for various parts of the instrument. This module records the use status, life cycle, maintenance records and other information of key parts of the instrument, and realizes dynamic monitoring and early warning management of parts. Users can view the operating status, consumption progress and replacement suggestions of parts, so as to reasonably arrange the replacement and inventory of parts. This module not only improves the efficiency of parts management, but also reduces the risk of instrument downtime due to component failure, ensuring that the instrument is always in good working condition;

[0036] Knowledge base management module: This module brings together professional knowledge on instrument operation, maintenance, fault diagnosis and solutions, and provides a wealth of knowledge resources for instrument managers. The system continuously updates the instrument's operating manual, common faults and their solutions, best maintenance practices, and other content. Users can use this module to access relevant information and solve difficult problems in instrument operation and maintenance. The knowledge base management center also supports knowledge sharing and accumulation, provides support for the long-term management and optimization of instruments, and enables managers to quickly find the corresponding solutions in the event of complex operations or sudden failures.

[0037] Safety information management module: This module is responsible for safety monitoring and information management during instrument operation to ensure the safety of the tester operation process. The safety information management center integrates risk factor warning, fault alarm, emergency handling guidance and other functions during instrument operation. The system can identify and record various safety hazards that may occur during instrument operation, generate safety reports and issue warnings for events that do not comply with safety operation specifications. This module helps instrument operators understand and respond to safety risks in a timely manner, improve safety awareness and response speed in instrument management, and ensure the safe and reliable operation of the tester.

[0038] The aforementioned security information management module includes the following submodules:

[0039] Risk warning and alarm log module, this submodule is used to record potential risk factors during instrument operation and automatically issue an alarm when an abnormal situation is detected. The system sets risk thresholds through multi-dimensional data analysis. Once the instrument operating parameters exceed the preset range, the early warning mechanism is triggered immediately. The alarm information will be displayed in real time on the data monitoring interface. At the same time, the system will prompt the management personnel with sound or icons, and prioritize according to the severity of the incident, so as to help managers respond quickly and deal with the safety hazards of the instrument in a timely manner. In addition, the module will automatically generate and record alarm logs, including the time, type, parameter limit violation and processing status of the alarm, to facilitate subsequent analysis and improvement of risk management strategies;

[0040] Emergency handling guidance module, the emergency handling guidance module provides detailed safety operation guidelines for quick handling in emergency situations. The system will provide a step-by-step emergency handling plan based on the type and urgency of the fault, helping operators to quickly take necessary measures to ensure the safety of the instrument and operators. In addition, the module can provide automatically generated emergency operation reports, recording the handling steps and results, to provide support for subsequent analysis;

[0041] Fault record and maintenance log module, this module is responsible for recording and managing all fault events and maintenance history. After each alarm is triggered, emergency treatment or maintenance is completed, the system will automatically generate a detailed record, including fault description, alarm level, treatment measures, timestamp and maintenance personnel information. Managers can query the instrument's fault history and maintenance log at any time to analyze the instrument's operating reliability, identify repetitive problems and optimize maintenance strategies, further improving the long-term operating stability of the instrument;

[0042] Safety report and analysis module, this module automatically generates safety reports for instrument operation, recording abnormal conditions, safety hazards, alarm times, emergency operations and other information during operation. The report content can not only help managers analyze the main sources of safety risks, but also provide support for optimizing instrument management strategies. In addition, the safety report and analysis module provides long-term data statistics for managers to identify the safety weaknesses of instruments from trends, so as to make timely improvements or upgrades and achieve continuous improvement management of safety risks.

[0043] The technical solution provided by the embodiments of the present application brings at least the following beneficial effects:

[0044] The implementation scheme of this application provides a complete set of intelligent monitoring systems based on digital twins, which realizes all-round real-time monitoring, intelligent diagnosis and fault prediction of micro-nano impact press-in testers, greatly improving the operating accuracy and stability of the instrument. Through the integrated sensor array and Internet of Things technology, the system can obtain key data such as force, displacement, temperature, etc. at a microscopic scale, form a dynamic mapping, so that the status of the instrument can be reflected in real time, solving the delay problem in traditional manual inspections. At the same time, the system's built-in machine learning algorithms (including decision trees, random forests, and long and short-term memory networks, etc.) can conduct in-depth analysis of the data, identify potential faults, issue early warnings, effectively reduce the occurrence rate of faults and extend the life of the instrument, and avoid losses caused by unexpected downtime. The intelligent diagnosis module provides precise guidance for the maintenance of the instrument, generates maintenance suggestions based on the detected abnormal data, and realizes targeted instrument maintenance, thereby reducing unnecessary regular maintenance and reducing maintenance costs. The three-dimensional visualization function of the interactive interface further enhances the intuitiveness and convenience of the operation. Users can clearly understand the real-time status of the instrument through a three-dimensional perspective, including temperature distribution and force conditions, which is convenient for multi-perspective operation. At the same time, the system's built-in security management module provides multiple safeguards for instrument operation, identifies risks in real time and triggers multi-level alarms, provides emergency guidance for emergencies, and ensures the safety and compliance of the instrument. In addition, the parts management module provides maintenance reminders by dynamically monitoring the life and wear progress of key components to avoid instrument downtime caused by component aging and ensure long-term stable operation of the instrument. The knowledge base management module provides managers with detailed knowledge resources by collecting operating manuals, troubleshooting solutions, and maintenance best practices, which not only helps solve daily operational problems, but also accumulates valuable maintenance experience to ensure continuous optimization of instrument management. In summary, the digital twin system of this application integrates multiple functions such as monitoring, diagnosis, data visualization, risk management, and knowledge support, provides an integrated instrument operation and maintenance solution, and comprehensively improves the reliability and management level of the micro-nano impact penetration tester. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0046] Figure 1 It is an operation flow chart of an intelligent monitoring system for a micro-nano impact indentation tester based on digital twins according to an embodiment of the present application;

[0047] Figure 2 It is an implementation roadmap of the intelligent monitoring system of the micro-nano impact indentation tester based on digital twins according to the embodiment of the present application, showing the technical route for the specific implementation of the system;

[0048] Figure 3It is a general structural block diagram of an intelligent monitoring system for a micro-nano impact indentation tester based on digital twins according to an embodiment of the present application, showing the main modules, the functions of each module and their associations;

[0049] Figure 4 is a detailed structural block diagram of a physical layer module according to an embodiment of the present application;

[0050] Figure 5 is a block diagram of a data acquisition and processing module according to an embodiment of the present application;

[0051] Figure 6 It is a block diagram of the composition of the digital twin model shown in the embodiment of the present application;

[0052] Figure 7 is a functional block diagram of an interaction center according to an embodiment of the present application;

[0053] Figure 8 It is a sub-function composition block diagram of the security information management module shown in an embodiment of the present application. DETAILED DESCRIPTION

[0054] The following is a detailed description of a specific embodiment of the present application in conjunction with the accompanying drawings. This embodiment describes the specific architecture and functional modules of the micro-nano impact indentation tester operation monitoring system based on digital twin technology, and shows the main components of the system and its operation process through the accompanying drawings. The description of the embodiment with reference to the accompanying drawings is for illustrative purposes only, intended to help explain the content of this application, and should not be regarded as a restrictive statement of this application.

[0055] Figure 1 The operation flow chart of the monitoring system of the micro-nano impact indentation tester operation monitoring system based on digital twin technology is shown. Figure 2 The specific steps and technical routes for system implementation are demonstrated. Figure 3 It is the overall structural block diagram of the intelligent monitoring system of the micro-nano impact penetration tester based on digital twin, showing the main modules, the functions of each module and their interrelationships.

[0056] The system consists of the following four main modules:

[0057] Physical layer module: responsible for the operation of the core physical components of the tester and data collection;

[0058] Data acquisition and processing module: real-time acquisition, analysis and transmission of instrument operation data;

[0059] Digital twin model module: build a virtual model of the instrument and realize dynamic update;

[0060] Interactive Center Module: Provides a user-friendly data visualization and instrument management interface.

[0061] The physical layer module: The physical layer module is the core foundation of the system, responsible for supporting the actual operation and data acquisition functions of the instrument. Its main components include the micro-nano impact indentation tester entity and the high-precision sensor array arranged in key positions. The specific contents are as follows:

[0062] Tester body: The instrument body is used to perform precise mechanical property tests at the micro-nano scale. The body structure is highly stable and can maintain accurate operation under micromechanical conditions.

[0063] Sensor array: including force sensors, temperature sensors, displacement sensors and laser Doppler displacement sensors, etc. These sensors are arranged in key parts of the instrument to collect parameters such as force, temperature, displacement, etc. in real time, forming a multi-dimensional real-time data stream.

[0064] like Figure 4 As shown in the figure, the specific layout of each sensor in the physical layer module is optimized according to the working requirements of the instrument to ensure the accuracy and comprehensiveness of the collected data. The force sensor is installed at the loading position and is mainly used to monitor the dynamic changes of the applied load; the temperature sensor is distributed near the instrument body and the test sample to monitor the thermal state of the working environment; the laser Doppler displacement sensor is used to accurately measure small displacements to capture the dynamic behavior during the test process.

[0065] Through the collaborative work of multiple sensors, the physical layer module can provide real-time key parameters of the instrument operating at the micro-nano scale, providing high-quality input for subsequent data processing and model building.

[0066] like Figure 5 As shown, the data acquisition and processing module: The data acquisition and processing module is an important intermediate link to achieve real-time monitoring of instrument status. Its main functions include multi-dimensional data acquisition, signal processing, data fusion and integrated upload. This module ensures that the real-time status of instrument operation can be reflected through high-quality data, providing support for the accurate modeling and dynamic update of the digital twin model. The specific contents are as follows:

[0067] Data acquisition module: The data acquisition module acquires the key operating parameters of the instrument in real time, including force, temperature, displacement, acceleration, etc., through a variety of sensor arrays deployed in the physical layer module.

[0068] The physical layer sensor types and functions involved in the acquisition module are:

[0069] Force sensor: collects the changes in dynamic force during loading and is used to evaluate the stress response of the test;

[0070] Laser Doppler displacement sensor: accurately measure the tiny displacement of the loading part;

[0071] Acceleration sensor: records the dynamic changes of the loading head acceleration and is used to evaluate the motion characteristics;

[0072] Temperature sensor: monitors the thermal state of the instrument and test material to ensure consistent test conditions.

[0073] Data timing management: To ensure the synchronization of multi-source sensor data, the system marks the collected data with timestamps to avoid measurement errors caused by timing offsets.

[0074] Data processing module: The collected raw data usually contains a certain amount of noise or redundant information. The data processing module uses advanced algorithms to accurately process the raw data to ensure the cleanliness and effectiveness of the data. The processing flow includes the following steps:

[0075] Filtering and denoising: Apply Kalman filtering and adaptive filtering algorithms in the micro-nano impact test process to remove noise from the signal;

[0076] Fourier transform technology is used to enhance the tiny signal to further improve the signal clarity.

[0077] Parameter calculation and verification: Calculate key parameters in micro-nano impact loading, such as dynamic mechanical response, displacement change rate, etc.; verify whether the instrument working status meets the standard expectations to ensure the stability and controllability of the test process.

[0078] Abnormal data processing: Use machine learning models (such as random forests) to identify and remove abnormal data points to prevent errors from propagating to subsequent modeling stages.

[0079] Data integration and upload module: The processed data is multi-dimensionally integrated and standardized through the data integration module. This module implements the following functions:

[0080] Data fusion: The Kalman filter algorithm of the micro-nano impact test process is used to comprehensively analyze the multi-dimensional data collected by different sensors to generate a high-precision data set that reflects the instrument status; the principal component analysis (PCA) method is used to extract key features and simplify the data structure.

[0081] Standardized storage: Data sets are integrated in a unified format to ensure that data can be quickly read and applied by the model when uploaded to the cloud database.

[0082] Upload to the cloud: The integrated data is transmitted to the cloud database via a high-speed network, providing real-time update support for the digital twin model.

[0083] The data flow is summarized as follows: the raw data collected from the sensor is processed by denoising and filtering, and finally uploaded to the cloud in a standardized format, providing core data support for the subsequent dynamic modeling and optimization analysis of the digital twin model. Through the efficient operation of data processing and integration, the real-time status of the instrument operation can be accurately reflected in the virtual model.

[0084] like Figure 6 As shown, the digital twin model module: The digital twin model module is the core part of realizing the synchronous operation of virtual devices and physical devices. By mapping physical sensor data to the virtual model in real time, the system can accurately reproduce the dynamic behavior of the device and provide intelligent analysis support. This module includes four key components: digital twin geometric model construction module, data transmission and real-time synchronization module, three-dimensional visualization module and fault prediction and warning module. The specific contents are as follows:

[0085] Digital twin geometric model building module: The geometric model building module is responsible for generating a virtual model that is consistent with the physical device, ensuring that the geometric structure and dynamic characteristics of the device are realistically presented in the virtual space. The specific steps are as follows:

[0086] Model generation: Use professional modeling tools (such as CATIA or SolidWorks) to build a 3D geometric model of the equipment and optimize the design based on the size and material properties of the actual equipment;

[0087] Dynamic characteristics simulation: Combine multi-physics field data such as micromechanics, thermal and vacuum, and use multi-physics field simulation software (such as COMSOL Multiphysics or ANSYS) to simulate the dynamic behavior of the device in a micro-nano environment;

[0088] Accurate mapping: Using a hierarchical modeling approach, the device is divided into multiple layers, such as mechanical layer, thermal layer, and electrical layer. By coupling the simulation results of these layers, accurate mapping of the overall behavior of the device is achieved.

[0089] Data transmission and real-time synchronization module: The data transmission and real-time synchronization module ensures that the virtual model can reflect the actual operating status of the equipment in real time. The specific contents are as follows:

[0090] Real-time data transmission: The multi-dimensional data collected by the sensor is transmitted to the cloud database through a high-speed transmission protocol (such as CAN bus, Ethernet or Wi-Fi6) and loaded into the digital twin model in real time;

[0091] Synchronization and update: The system uses optimized interpolation algorithms (such as Lagrange interpolation) to achieve data smoothing, ensuring that the virtual model can be updated in real time and reducing delays and errors during data transmission;

[0092] Further explanation, this application example uses the Lagrange interpolation method, and the specific formula is:

[0093]

[0094] Parameter explanation:

[0095] P(x): interpolation polynomial, that is, the estimated result for a given x value.

[0096] n: The number of known points minus one (i.e. n+1 known points).

[0097] x i : The x-coordinate of the known interpolation point, the i-th point.

[0098] y i : The y value (i.e. function value) corresponding to the known interpolation point at the i-th point. : This part is the Lagrangian basis function L i (x), which constructs the weight of the i-th data point.

[0099] Basis Functions Function: Basis function It is the core of constructing Lagrange interpolation polynomial. Each basis function L i (x) is zero at all interpolation points except the i-th point and is one at the i-th point. This ensures that y at each known point i The values ​​are uniquely assigned to the interpolating polynomial so that all data points are accurately fit by the polynomial.

[0100] Lagrange interpolation method is used specifically:

[0101] For a set of irregular displacement data y i , the corresponding acquisition time is x i (Take three data points as an example) and use Lagrange interpolation to perform data smoothing:

[0102] Construct Lagrangian basis function L 0 (x),L 1 (x),L 2 (x),L 3 (x): for L 0 (x), its formula is:

[0103]

[0104] For L 1 (x), the formula is:

[0105]

[0106] And so on until L3 (x).

[0107] Calculate the interpolation polynomial P(x):

[0108] P(x)=y 0 L 0 (x)+y 1 L 1 (x)+y 2 L 2 (x)+y 3 L 3 (x)

[0109] Select interpolation points: Select different values ​​of time x (for example, 0.5, 1.5, 2.5, etc.) to calculate the corresponding displacement value P(x) and obtain a smooth curve. In this way, Lagrange interpolation can smooth the data and make the data change smoothly between given points. Advantages of Lagrange interpolation method: No need to solve linear equations: This method does not need to solve the system of equations to obtain the interpolation polynomial, which is more direct than other interpolation methods; High accuracy: When the number of known points is small, this method can effectively construct a high-precision interpolation polynomial and accurately fit the known data points; Wide applicability: It is applicable to interpolation points of any distribution and can be used to interpolate various types of non-uniformly distributed data.

[0110] Data consistency guarantee: An adaptive error correction algorithm is introduced to dynamically adjust the state difference between the physical device and the virtual model to ensure high-precision synchronization between the virtual and the real.

[0111] 3D visualization module: The 3D visualization module provides users with an intuitive interface for displaying the equipment's operating status. The specific contents are as follows:

[0112] Interactive visualization: Using the Unity 3D platform to develop a three-dimensional display function, users can view the operating status of the equipment in real time through the interface, including temperature distribution, stress conditions and dynamics of key components;

[0113] Multi-view switching: Supports multi-view modes, and users can freely switch from the overall view or the partial magnified view, which is convenient for detailed analysis of the device status;

[0114] Virtual experiment support: Users can simulate the operating status of equipment under different working conditions in a virtual environment, observe potential problems and optimize equipment operation.

[0115] Fault prediction and early warning module: The fault prediction and early warning module uses machine learning algorithms to analyze the historical and real-time data of the equipment, predict potential faults and issue early warnings. The specific contents are as follows:

[0116] Fault prediction model: Combine decision tree, support vector machine, random forest and long short-term memory network (LSTM) algorithms to build a high-precision fault prediction model, analyze data change trends and identify key risks;

[0117] Early warning mechanism: The system sets anomaly detection thresholds based on historical data trends. Once real-time data exceeds the preset range, a multi-level early warning mechanism is triggered;

[0118] Generation of maintenance suggestions: Based on the prediction results, the system automatically generates maintenance suggestions, including replacement of faulty parts, adjustment of operating parameters, etc., to help users take preventive maintenance measures in advance.

[0119] Use deep learning frameworks such as TensorFlow or PyTorch to predict equipment status and diagnose faults based on LSTM and deep neural network (DNN) models. These frameworks can help the system automatically adjust and optimize fault warning strategies to ensure the accuracy of real-time monitoring and prediction. Taking force data as an example, the application of machine learning algorithms in instrument fault warning is as follows:

[0120] Decision tree: In the decision tree model, the main role of force data is to provide feature information so that the algorithm can identify whether there is a fault. Common features may include the mean, peak, volatility, standard deviation, etc. of the force. The decision tree uses these features to split the data set for fault classification. The decision tree uses the historical operation data and real-time feature data of the equipment to build a hierarchical decision rule. For example, it can identify abnormal patterns by monitoring changes in key parameters such as temperature, vibration, and pressure. The segmentation rules of the decision tree (based on information gain or Gini coefficient) help to find the feature combinations with the greatest risk of failure. Through layer-by-layer segmentation, the decision tree can quickly classify whether the current equipment status is normal or has a potential risk of failure, making it suitable for fault classification tasks.

[0121] Information Gain:

[0122]

[0123] in:

[0124] H(T) is the entropy of data set T, representing the uncertainty of the data.

[0125] T v It is a subset of the data set T that satisfies the feature A value v.

[0126] Information gain measures the reduction in entropy after splitting a dataset T by selecting feature A.

[0127] In this formula, force data usually influences the splitting decision through extracted features (such as mean, standard deviation, etc.), and the selection of splitting features is based on the reduction of entropy by different features.

[0128] Support Vector Machine (SVM): The function of a support vector machine is to classify data into two categories: "fault" and "normal" by finding an optimal hyperplane. In force data applications, features such as peak value, volatility, and rate of change are usually used to construct decision boundaries. SVM can be used to classify fault types or predict fault risks, separating fault states from normal states through a separating hyperplane in a high-dimensional feature space. Support vector machines are particularly suitable for processing complex and diverse sensor data and helping to identify the boundary conditions of potential equipment failures. By training the SVM model, it can find the optimal boundaries between various faults and normal operation. For example, when temperature, vibration, and load are outside the normal range, SVM can determine whether the equipment is close to failure based on its classification boundary and trigger an alarm in advance.

[0129] Maximum margin optimization objective function:

[0130]

[0131] in:

[0132] w is the normal vector of the hyperplane, which determines the direction and boundary of the separation.

[0133] b is the bias, which determines the shift of the hyperplane.

[0134] x i is the feature vector of the i-th sample, which usually contains multiple features from the force data.

[0135] y i is the label of the sample, indicating "normal" or "faulty".

[0136] The goal of this formulation is to find the hyperplane that maximizes the data classification margin, thereby determining the fault classification through the characteristics of the force data.

[0137] Random forest: Random forest improves the accuracy of prediction by integrating multiple decision trees for voting. In force data analysis, each decision tree is trained based on a different subset of features in the force data. Random forest improves the accuracy and robustness of fault detection by building an integrated model of multiple decision trees. Each tree is trained by random selection of features and data, which can avoid the overfitting problem that may occur in a single model. In fault warning, random forest can combine multiple features (such as temperature, vibration frequency, fluid pressure, etc.), integrate the weights of different features, and improve the accuracy of fault prediction. The results of each tree will be voted on comprehensively to give a final judgment on whether the equipment has a fault, and can identify potential feature interaction effects.

[0138] Prediction of Random Forest:

[0139]

[0140] in:

[0141] is the prediction result of the i-th tree.

[0142] is the final prediction result, which depends on the output of the majority of trees.

[0143] In this formula, force data is predicted by multiple decision trees. Each tree is trained using a different subset of features (such as force fluctuations, peaks, etc.) and sample subsets, and the prediction results are finally synthesized through a voting mechanism.

[0144] Long Short-Term Memory Network (LSTM): LSTM has unique advantages in time series analysis and is suitable for predicting equipment states that change over time. By processing historical sensor data (such as temperature, pressure, and vibration change trends over the past period of time), LSTM can capture the time dependencies of equipment in different states. Therefore, in fault prediction based on force data, LSTM can use the historical information of force data to predict future fault risks. The time series features of force data, such as the change in force value within a time window, are fed into LSTM as input for modeling. In fault warning, LSTM can identify warning signals before an abnormality occurs by learning the time features of the normal and abnormal states of the equipment. For example, LSTM can capture the trend of gradual deterioration of equipment status, predict the probability of potential faults in advance, and prompt users to take preventive maintenance measures.

[0145] The LSTM model contains multiple gating mechanisms (forget gate, input gate, output gate) to handle long-term dependencies in time series data:

[0146] Forget Gate:

[0147] f t =σ(W f ·[h t-1 ,x t ]+b f )

[0148] Input Gate:

[0149] i t =σ(W i ·[h t-1 ,x t ]+b i )

[0150] Candidate memory cells:

[0151]

[0152] Update memory unit:

[0153]

[0154] Output Gate:

[0155] o t =σ(W o ·[h t-1 ,x t ]+b o )

[0156] h t =o t tanh(C t )

[0157] in:

[0158] x t is the input at the current moment (from the force data).

[0159] h t It is the hidden state at the current moment, representing the current fault prediction information.

[0160] In these formulas, the temporal features of force data (such as the force value at the current moment and the historical force values) are the inputs of the LSTM network, affecting its learned long-term dependencies and the final fault prediction.

[0161] In general, these machine learning algorithms process data features, identify patterns, and predict trends in different ways, thereby improving the accuracy and timeliness of equipment fault warnings. Decision trees and random forests are suitable for fault classification and detection, support vector machines are suitable for detecting boundary conditions, and LSTM is good at analyzing time-dependent change trends. Through the combination of these algorithms, the instrument's fault prediction system can monitor the equipment status more comprehensively and issue warnings in a timely manner, effectively reducing equipment downtime and maintenance costs.

[0162] In summary, the digital twin model proposed in this application can effectively realize the connection between the virtual space of the micro-nano impact press-in tester and its physical space and operation space, and construct an integrated "three-layer interactive system": physical space-virtual space-interactive space. Through this system, the data and knowledge in the physical space can be gathered to the data base of the virtual space, and the characteristics and operating status of the equipment can be mapped to the virtual model in real time, realizing the control of the model and the flexible application of intelligent algorithms. The control platform in the operating space uses the data base of the virtual space as the database support and the virtual model as the operation basis. The introduced intelligent algorithm provides an automatic alarm interface, which facilitates the operator to quickly obtain early warning information. With the help of the operating platform, users can adjust and edit the parameters and status of the virtual space, and then remotely control the physical equipment, thereby realizing the intelligent operation and management functions of the micro-nano impact press-in tester based on digital twins. In addition, this system combines machine learning algorithms with expert knowledge to further optimize the dynamic adjustment ability of the digital twin model. Through the analysis of real-time status data and historical trends, the system can identify the key parameters of the equipment's operating status and dynamically correct the input parameters of the model to achieve precise control. The expert knowledge module embeds domain experience and operational specifications to provide additional adjustment basis for the model, making up for the shortcomings of relying solely on algorithmic reasoning, thereby further improving the stability and intelligence of the model.

[0163] like Figure 7 As shown, the interactive center of the digital twin monitoring system: the interactive center module serves as the user interface of the digital twin monitoring system, integrating real-time status monitoring, fault prediction and diagnosis, data management and security management functions. Through the visual operation interface, users can grasp the operating status of the equipment in real time, analyze key data and make timely operational adjustments. The core goal of the interactive center is to provide intuitive and convenient equipment management tools to create an integrated operation and maintenance experience for users. It specifically includes the following sub-modules:

[0164] Instrument operation intelligent monitoring module: The operation intelligent monitoring module is the core component of the interaction center, responsible for presenting the real-time status of the equipment in the user interface. It mainly includes:

[0165] Data monitoring screen: Based on streaming data processing technology (such as Apache Kafka), multi-dimensional data of the equipment (including force, temperature, displacement, etc.) can be obtained in real time. The large screen displays the operating status, environmental parameters and component performance of the equipment, so that users can view the core indicators of the equipment at a glance;

[0166] Anomaly detection and warning: The system sets the safety threshold of key indicators through the built-in rule engine (such as Drools). Once the data beyond the range is detected, the system will automatically trigger the warning and notify the user by icon, sound or email;

[0167] Dynamic adjustment support: Users can adjust equipment operating parameters (such as load and test conditions) in real time in the interface, and the interactive center will immediately provide feedback on the adjusted equipment status.

[0168] Instrument Intelligent Diagnosis Module: The Intelligent Diagnosis Module uses the aforementioned machine learning algorithms to conduct in-depth analysis of the historical and real-time data of the equipment, predict potential failures and generate maintenance recommendations. It mainly includes:

[0169] Data feature analysis: The system extracts key data features through models such as random forest and LSTM, and analyzes equipment operation trends. For example, an abnormal pattern of displacement change may indicate fatigue risk of mechanical parts of the equipment;

[0170] Fault classification and prediction: The system classifies equipment faults based on the trained machine learning model and combines time series analysis to predict the likelihood and time frame of potential problems.

[0171] Maintenance suggestion generation: The system generates targeted maintenance suggestions based on the diagnosis results, including parts replacement cycles, operating condition adjustments, or key monitoring plans for specific components.

[0172] Data and knowledge management module: The data and knowledge management module supports the full life cycle management of equipment and provides users with detailed data support by recording and analyzing the equipment operation history. It mainly includes:

[0173] Operation data archiving: The system records key data of the equipment (such as temperature curve, load change trend, etc.) and displays it in the form of charts so that users can quickly understand the long-term performance of the equipment;

[0174] Knowledge base management: collects information such as equipment operation manuals, common fault diagnosis and solutions. The knowledge base supports dynamic updates, and users can query solutions to specific problems and accumulate experience through knowledge sharing functions;

[0175] Safety management module: The safety management module ensures the safe operation of the equipment through multi-level risk monitoring and emergency response plans. Figure 8 As shown, it mainly includes:

[0176] Risk warning and graded response: The system sets risk levels based on the degree of abnormality of equipment operation data. Low-level risks will be displayed as prompts, and high-level risks will trigger mandatory shutdown recommendations;

[0177] Emergency handling guide: The module provides step-by-step emergency handling solutions, including detailed operation steps and alternative solutions, to help users quickly respond to emergencies;

[0178] Log recording and analysis: The system automatically records all risk events, including trigger time, event type, handling measures and subsequent results. Users can use these records to optimize device management strategies.

[0179] This application proposes an operation monitoring system for a micro-nano impact indentation tester based on digital twins, and its digital twin operation monitoring interactive center has multiple functions, including data loading, cache optimization, database management, etc., to meet the real-time monitoring needs of the tester. The interactive center has role authority management, which controls the access scope to functions and data by setting different levels of user permissions; in terms of data security verification, the system performs integrity checks, source authentication, communication encryption, and transmission records in data transmission to ensure data security and privacy; computing resource allocation optimization reasonably allocates processing tasks by calling edge computing, cloud computing, and distributed computing resources, thereby meeting the efficient operation requirements of the digital twin environment, while optimizing bandwidth usage and improving the resource utilization of sensors and local devices. In this way, not only the real-time linkage and efficient interaction between virtual models and physical devices are realized, but also the precise expression of physical operations in virtual space is supported, thereby building a complete digital twin monitoring and control system, and realizing real-time mapping, feedback, and adaptive optimization between the physical world and the virtual world.

[0180] The system and its technology can be implemented on a computer that supports user interaction. The computer system includes an information display device (such as an LCD screen) as well as a keyboard and a touch device (such as a touchpad or a mouse) for user input. The feedback of the system can be visual, auditory or tactile feedback, and the input method supports multiple forms such as voice, gesture and touch to meet the flexibility of user operation needs.

[0181] The system can be implemented in a front-end, middle-tier, and back-end architecture: the back-end server is responsible for data storage and processing, the middle-tier is responsible for data interaction and algorithm application, and the front-end serves as a user interface and operating platform. The various components are interconnected through a variety of digital communication methods (such as local area networks, the Internet, or distributed networks) to form a complete distributed computing architecture.

[0182] A computer system consists of two parts: a client and a server, which are usually distributed in different locations and interact through a communication network. The relationship between the client and the server can be established by running the client and server programs on different devices. The server can be a cloud server to provide scalability and convenient management functions, or a distributed server or a server combined with blockchain technology to ensure decentralized management and security of data.

[0183] The operating process of the system can be flexibly adjusted as needed. The steps can be executed in parallel, sequentially, or arranged in different orders to achieve the expected effect of this technical solution without limiting the specific implementation method.

[0184] The above embodiments are not intended to limit the scope of protection of this application. Technicians may adjust, combine or replace them according to design requirements and specific application conditions. All modifications, equivalent replacements or improvements within the spirit and basic principles of this application should be included in the scope of protection.

Claims

1. A micro-nano impact indentation tester operation monitoring system based on digital twin, characterized by: include: (1) Physical layer module: It includes a micro-nano impact indentation tester and a high-precision sensor array arranged at its key positions, which is used to collect multi-dimensional data such as force, temperature, displacement, etc. in real time during the test under complex and multi-physical field coupling conditions at the micro-nano scale to meet the needs of high-precision monitoring; The sensor system includes: High-precision force sensor: monitors the tiny force changes loaded by the tester to ensure accurate collection of stress data for mechanical analysis during micro-nano impact pressing; Laser Doppler displacement sensor: It realizes dynamic monitoring of micro-nanoscale displacement and captures the subtle structural behavior changes of the tester during the impact pressing process; High-precision temperature sensor: monitors the temperature status of the test environment, core components of the tester and test materials, ensures the stability of micro-nano test conditions, and builds accurate material service conditions; By optimizing the sensor layout and the joint collection of multi-dimensional data, the physical level module ensures the integrity of the operating data of the micro-nano impact penetration tester under high-precision conditions, providing basic support for the subsequent establishment of the digital twin model and accurate monitoring of the test process; (2) Data acquisition and processing module: Integrates data acquisition, signal processing and data fusion functions to collect complex data from impact and indentation tests at micro-nano scales, including: Multi-source data acquisition: uniformly collect the loading force, dynamic displacement and temperature parameters obtained by the above-mentioned high-precision sensors, use synchronized timestamps to ensure the synchronization of data streams, and meet the high-precision requirements at the micro-nano scale; signal processing: adopt the Kalman filter algorithm suitable for the micro-nano scale press-in test process and the micro-nano scale test adaptive error correction method to eliminate noise and environmental interference in the collected data, improve signal quality, and optimize the timing consistency of the data; Data fusion and standardization: Fuse multi-sensor data, extract key features using analytical data dimensionality reduction methods suitable for micro-nano test data, and form a data set in a unified format to facilitate real-time application of digital twin models; Data interpolation and smoothing: For irregular intervals and noise in the collected data, the Lagrange interpolation method suitable for micro-nano test data is used to perform data smoothing to optimize the stability and real-time performance of data transmission; Cloud synchronization: The processed data is uploaded to the cloud database through a high-speed transmission protocol to achieve real-time storage and fast access, providing complete data support for the monitoring and analysis of the micro-nano impact press-in test process; (3) Digital twin model module: Through multi-physics field coupling simulation technology, a digital twin virtual model of the micro-nano impact indentation tester is constructed, which has the following features: Geometric model construction: Use 3D modeling software to accurately reproduce the structure and parameters of the tester, combine actual material properties and physical field behavior, and optimize the model to meet the special needs of micro-nano impact indentation testing; Dynamic characteristics simulation: Combining multi-physics field data such as micromechanics, thermals and vacuum, the dynamic behavior of the tester in a micro-nano environment is simulated using simulation software to support detailed analysis of the impact pressing process; Intelligent fault prediction: Introducing machine learning models such as random forest and long short-term memory network (LSTM) to analyze the high-precision data of the real-time test process and the changing trend of historical data, and realize dynamic analysis and potential fault prediction of the micro-nano tester during the press-in test process; Dynamic mapping and updating: Using efficient interpolation algorithms for micro-nano test data, real-time data of physical-level modules are seamlessly mapped into the digital twin model, ensuring synchronization between the virtual model and the physical test process. Multi-dimensional visualization: Using a three-dimensional visualization interface, the operating status of the tester during micro-nano impact pressing is intuitively presented, supporting all-round monitoring of dynamic force, temperature distribution, and displacement changes, satisfying the refined observation of the micro-nano impact pressing process. (4) Interaction center module: Provide users with a real-time operation interface that integrates multiple functions: Condition monitoring under micro-nano test conditions: Through the three-dimensional visualization interface, users can view the key parameters of the micro-nano impact test process in real time, including micro-loading force, nano-level displacement dynamics and temperature changes; Intelligent diagnosis and maintenance suggestions: Based on the fault prediction model applicable to micro-nano test data, combined with real-time data and historical data, the system can identify potential faults and generate customized maintenance plans, provide suggestions for replacing parts and guidance on optimizing operating conditions to ensure the high accuracy of the instrument, the stability of micro-nano test data and the reliability of the test; High-precision dynamic adjustment function: Based on real-time feedback, users can adjust the operating conditions of the tester at the micro-nano scale, including micro-load parameters and precise temperature control range, to ensure precise control of micro-nano test conditions; Fault warning and diagnosis: Combined with the data change trend during the micro-nano test, it supports real-time anomaly detection, automatically generates fault diagnosis reports and maintenance suggestions, and ensures the smooth progress of the micro-nano impact press-in test process; Knowledge base management: Integrates professional knowledge bases, provides operation manuals, common fault solutions and maintenance best practices, and supports users to query and learn relevant knowledge; Risk warning and graded response: A multi-level warning mechanism is set up based on real-time data to issue alerts for high-risk situations and generate emergency response plans; Parts monitoring and management: Dynamically monitor the life and usage status of key tester components, and provide replacement suggestions to reduce the risk of downtime due to component aging.

2. The operation monitoring system of a micro-nano impact indentation tester based on digital twin according to claim 1, characterized in that: The physical level module forms a sensor array through the combination of high-precision force sensors, laser Doppler displacement sensors and temperature sensors, which can realize real-time and high-precision monitoring of the micro-nano impact indentation tester during the test process and meet the testing requirements under complex multi-physical field coupling conditions; this module supports the precise perception of tiny loading forces, nano-scale displacement dynamics and temperature changes, and provides a reliable data basis for monitoring the indentation test process at the micro-nano scale.

3. The operation monitoring system of a micro-nano impact indentation tester based on digital twin according to claim 1, characterized in that: The data acquisition and processing module adopts the Kalman filtering algorithm and adaptive error correction method suitable for the micro-nano scale indentation test process to improve the quality and synchronization performance of multi-source data, eliminate noise and optimize signal processing; through the fusion of multi-sensor data, the principal component analysis (PCA) and other data dimension reduction methods suitable for micro-nano test data are used to extract key features and form a data set in a unified format; the processed data is uploaded to the cloud database through a high-speed transmission protocol to achieve real-time storage and fast access, providing complete data support for the monitoring and analysis of the micro-nano impact indentation test process.

4. The operation monitoring system of a micro-nano impact indentation tester based on digital twin according to claim 1, characterized in that: The digital twin model module uses multi-physics field simulation technology to construct a digital twin virtual model of the micro-nano impact penetration tester, simulates the dynamic behavior of the tester during the testing process at the micro-nano scale, and realizes accurate simulation and real-time update of the testing process; the module uses an efficient interpolation algorithm to seamlessly map the real-time data of the physical level module to the digital twin model, ensuring the synchronization of the virtual model and the physical testing process; at the same time, it uses a three-dimensional visualization interface to intuitively present the operating status of the tester, support all-round monitoring of dynamic force, temperature distribution and displacement changes, and meet the needs of refined observation of the micro-nano impact penetration process.

5. The operation monitoring system of a micro-nano impact indentation tester based on digital twin according to claim 1, characterized in that: The interactive center module provides three-dimensional visualization function and supports multi-perspective switching. Users can explore the operating status of the micro-nano impact press-in tester under different test conditions through the simulation experiment function; the module integrates intelligent diagnosis function, extracts key features, identifies potential faults and generates customized maintenance plans by analyzing the operating data during the test process; combined with risk warning, emergency handling and log recording functions, it supports comprehensive safety monitoring and dynamic response of the micro-nano impact press-in test process; using edge computing and cloud computing resources Dynamic scheduling technology improves the system's data processing efficiency during the micro-nano impact press-in test process, supports real-time requirements, and meets the high-precision and high-real-time requirements of press-in test process monitoring at the micro-nano scale.

Images