A sensor detection method and system

Abstract

The present invention relates to the technical field of sensor detection, and particularly to a sensor detection method and system. The method includes the following steps: collecting geometric, mechanical, and electrical parameters of the sensor installation environment in real time to construct a sensor digital twin model; automatically identifying and initializing sensor parameters through a local area network by an edge computing device to obtain initial sensor configuration data; generating sensor simulation data based on the sensor digital twin model and the initial sensor configuration data; and performing performance detection and evaluation based on the sensor simulation data to obtain sensor detection data. The present invention can not only perform real-time detection and evaluation in a dynamically changing environment, but also accurately predict the performance of the sensor under various working conditions by combining the virtual model with the actual performance of the sensor, ensuring the efficient and stable operation of the system.

Description

Technical Field

[0001] The present invention relates to the technical field of sensor detection, and particularly to a sensor detection method and system. Background Art

[0002] With the wide application of Internet of Things (IoT) technology and intelligent devices, sensors, as key hardware components, are widely used in various fields such as industry, agriculture, medical care, and transportation, undertaking important functions such as environmental monitoring, data collection, and status perception. The performance of sensors directly affects the reliability of devices and the overall efficiency of systems. Therefore, the detection and evaluation of sensors are particularly important. Traditional sensor detection methods mostly rely on manual operation or evaluation in a single environment based on a fixed test model. This method not only has certain limitations but also leads to measurement errors and cannot truly reflect the actual performance of sensors in complex working environments. Summary of the Invention

[0003] In order to solve the above technical problems, the present invention proposes a sensor detection method and system to solve at least one of the above technical problems.

[0004] The present application provides a sensor detection method, including the following steps:

[0005] Step S1: Collect the geometric, mechanical, and electrical parameters of the sensor installation environment in real time, and construct a sensor digital twin model;

[0006] Step S2: Automatically identify and initialize the sensor parameters through a local area network by an edge computing device to obtain the initial configuration data of the sensor;

[0007] Step S3: Generate sensor simulation data according to the sensor digital twin model and the initial configuration data of the sensor;

[0008] Step S4: Perform performance detection and evaluation according to the sensor simulation data to obtain the sensor detection data.

[0009] In the present invention, by collecting the geometric, mechanical, and electrical parameters of the sensor installation environment in real time and constructing a digital twin model of the sensor, the performance of the sensor in the actual working environment can be accurately simulated. The digital twin model can provide precise environmental interaction relationships, making the simulation data more reliable, thereby providing accurate basic data for performance detection. Automated configuration reduces errors caused by human intervention, improves the adaptability and flexibility of the sensor during deployment, and helps improve the overall deployment efficiency and accuracy of the system. The sensor simulation data generated based on the digital twin model can reflect the working state of the sensor in real time. With the efficient data processing capabilities of edge computing and local area networks, the system can monitor the sensor performance in real time and quickly respond to potential problems, helping to detect performance problems or faults of the sensor in a timely manner, reducing the response time of equipment failures, and improving the reliability and security of the system. Through the simulation data generated by the digital twin model, performance evaluation and testing can be carried out without actual sensor hardware. It can effectively reduce the number and cost of physical experiments, especially in the large-scale deployment stage of sensors, and can significantly reduce resource consumption during the testing and verification process.

[0010] Preferably, step S1 is specifically as follows:

[0011] Step S11: Deploy an environmental sensor array and collect real-time environmental parameter data through an edge device;

[0012] Step S12: Generate a virtual sensor environment based on the real-time environmental parameter data to obtain virtual sensor environment data;

[0013] Step S13: Use laser scanning to obtain the geometric shape of the installation location to obtain sensor geometric shape data, and perform geometric reconstruction based on the sensor geometric shape data to obtain sensor installation geometric parameter data;

[0014] Step S14: Use a pressure sensor and an accelerometer to calibrate the mechanical parameters of the installation environment to obtain sensor mechanical characteristic data;

[0015] Step S15: Use an oscilloscope to measure the connector impedance, voltage waveform, and grounding status to obtain electrical characteristic data;

[0016] Step S16: Establish a digital twin model with the sensor installation geometric parameter data, sensor mechanical characteristic data, electrical characteristic data, and virtual sensor environment data to obtain a sensor digital twin model.

[0017] The present invention provides accurate real-time environmental data, which helps to make immediate adjustments during sensor configuration, debugging, and operation to cope with environmental changes. Generating virtual sensor environmental data based on real-time environmental parameter data helps to simulate and predict the performance of sensors in specific environments, especially when physical testing is inconvenient or impossible. The acquisition and modeling of geometric data can help better analyze the impact of the environment on sensor signals, thereby improving the reliability of the system. The present invention can provide accurate mechanical property data, enabling the working performance of the sensor to be accurately evaluated under specific mechanical conditions. By accurately measuring the electrical characteristics of the sensor (such as impedance, voltage, and grounding status), the stability of signal transmission and the electrical reliability of the sensor can be ensured. The digital twin model can accurately simulate the working state of the sensor and its interaction with the environment in the virtual space, providing profound insights into the behavior of the sensor.

[0018] Preferably, step S12 is specifically as follows:

[0019] Extract features from the real-time environmental parameter data to obtain environmental parameter feature data;

[0020] Perform environmental geometric modeling based on the environmental parameter feature data to obtain environmental geometric data;

[0021] Map the real-time environmental parameter data and the environmental geometric data to obtain environmental physical property distribution map data;

[0022] Generate virtual environment textures for the environmental physical property distribution map data to obtain environmental texture map data;

[0023] Generate a virtual sensor position interface based on the environmental texture map data to obtain virtual sensor environmental data.

[0024] Feature extraction in the present invention makes the real-time monitoring of the environment more efficient, reduces the complexity of raw data processing, and can significantly improve the computing efficiency, especially when dealing with large-scale data sets. It provides a more accurate basis for real-time response to environmental changes and evaluation of sensor adaptability. By performing geometric modeling on the environment, the three-dimensional structure of the environment can be accurately reproduced in the virtual space. It can help understand the impact of the environment on sensor operation, especially in complex or inaccessible environments. The acquisition of environmental geometric data provides accurate geometric characteristics, such as surface morphology and spatial layout. Mapping provides a realistic basis for sensor performance simulation and optimization, enabling the sensor to be accurately evaluated and optimized under more complex physical environments. Virtual texture generation helps to test and optimize the sensor under various conditions in the virtual environment, avoiding the need for a large number of on-site tests in the actual environment. Through these virtual tests, potential problems can be discovered and corresponding design adjustments can be made to avoid problems in advance and improve the adaptability and accuracy of the sensor.

[0025] Preferably, the feature extraction specifically includes:

[0026] Performing window data slicing on the real-time environmental parameter data to obtain environmental parameter slice data;

[0027] Calculating an environmental disturbance index based on the environmental parameter slice data to obtain environmental disturbance index data;

[0028] Calculating a covariance matrix of multiple environmental variables based on the environmental parameter slice data to obtain multi-environmental variable correlation data;

[0029] Performing environmental space abnormal fluctuation processing on the environmental disturbance index data and the multi-environmental variable correlation data to obtain environmental parameter feature data.

[0030] In the present invention, by performing window data slicing on the environmental parameter data, this method can extract representative and distinguishable time periods or data segments from the originally collected real-time environmental data. The calculation of the index can help detect the degree of interference of the sensor under different environmental conditions, and timely discover abnormal situations caused by environmental changes, thereby providing a more accurate basis for the evaluation of the stability and reliability of the sensor. The calculation of the covariance matrix helps to reveal the interaction between environmental factors, so as to more comprehensively evaluate the performance of the sensor under different combinations of environmental variables. Comprehensive analysis of the environmental disturbance index and multi-environmental variable correlation data is performed to detect potential abnormal fluctuation regions.

[0031] Preferably, the window data slicing specifically includes:

[0032] Performing window slicing on the real-time environmental parameter data through a preset first window slicing parameter data and a preset second window slicing parameter data to respectively obtain first preliminary window slicing data and second preliminary window slicing data;

[0033] Performing clustering calculation on the first preliminary window slicing data and the second preliminary window slicing data to respectively obtain first window slicing clustering data and second window slicing clustering data;

[0034] Calculating a cluster change rate based on the first window slicing clustering data and the second window slicing clustering data to respectively obtain first clustering cluster change rate data and second clustering cluster change rate data;

[0035] Performing window dynamic re-partitioning on the first window slicing parameter data according to the first clustering cluster change rate data to obtain first window re-slicing parameter data, and performing second window re-slicing parameter data on the second window slicing parameter data according to the second clustering cluster change rate data;

[0036] Perform window slicing on the real-time environmental parameter data according to the preset first window reslicing parameter data and the preset second window reslicing parameter data, respectively obtaining first preliminary window reslicing data and second preliminary window reslicing data;

[0037] Extract window data features from the first preliminary window reslicing data and the second preliminary window reslicing data, respectively obtaining first window feature data and second window feature data;

[0038] Use the first window feature data and the second window feature data, the first preliminary window reslicing data and the second preliminary window reslicing data to construct a cross-window feature matrix, obtaining environmental parameter slice data.

[0039] In the present invention, slicing and re-partitioning the real-time environmental data through preset window slicing parameters can subdivide large-scale environmental data into smaller time windows. This can better capture the local features of environmental changes, reduce the influence of noise, and improve the accuracy of analysis. Clustering and cluster change rate analysis are very important for the sensor system. It can real-time detect major changes occurring in the environment, such as drastic fluctuations in temperature, humidity, or pressure, helping the system quickly adjust and optimize the operating state. Dynamic re-partitioning can effectively cope with uncertain changes in the environment, especially under unstable or rapidly changing environmental conditions, it can timely adjust the slicing strategy to avoid the decline of data processing accuracy caused by overly static window slicing strategies. For example, in the dynamic monitoring of climate change, rapidly changing weather conditions can obtain more accurate monitoring results by real-time adjusting the slicing strategy. Feature extraction helps to conduct deeper analysis on complex environmental data and helps to establish a more intelligent prediction model. For example, in intelligent manufacturing and precision equipment monitoring, valuable features can be extracted from sensor data to achieve predictive maintenance and intelligent decision-making. Cross-window feature matrix construction can integrate feature data from different time windows, providing rich context information for further data analysis and decision-making. By integrating cross-window data, the changing trend of the environment can be more comprehensively understood, further improving the accuracy and stability of the model.

[0040] Preferably, the environmental geometric modeling specifically is:

[0041] Obtain installation environment geometric data;

[0042] Perform spatial mapping according to the real-time environmental parameter data and the installation environment geometric data, obtaining installation environment mapping data;

[0043] Perform installation environment geometric estimation according to the real-time environmental parameter data, obtaining installation environment geometric estimation data;

[0044] Fuse the environmental parameters based on the geometric estimation data of the installation environment and the installation environment mapping data to obtain the environmental geometric data.

[0045] In the present invention, through spatial mapping and geometric estimation, the error caused by environmental uncertainty is reduced, ensuring the accuracy of the model. During the spatial mapping process, by combining the geometric form of the installation environment with the real-time environmental data, a more realistic environmental space mapping can be created. Through the geometric estimation of the installation environment, the change of the geometric form of the environment where the sensor is located can be predicted. Especially when the environment is affected by external disturbances such as temperature and humidity, the geometric form of the environment will change. By effectively synthesizing data from different sources (such as geometric data, real-time environmental data), a multi-dimensional and comprehensive environmental geometric data can be obtained, providing a more accurate environmental background for the sensor, helping the sensor adjust its own parameter settings, and enhancing its working stability and fault tolerance in complex environments.

[0046] Preferably, step S2 is specifically as follows:

[0047] Step S21: Perform hardware connection verification based on the edge computing device to obtain hardware connection verification data;

[0048] Step S22: Configure the communication channel for the hardware connection verification data to obtain communication channel configuration data;

[0049] Step S23: Read the sensor characteristics according to the communication channel configuration data to obtain sensor characteristic data;

[0050] Step S24: Calibrate the parameters according to the sensor characteristic data to obtain calibrated parameter data;

[0051] Step S25: Adjust the gain for the calibrated parameter data to obtain optimized gain value data;

[0052] Step S26: Initialize the parameters according to the optimized gain value data to obtain sensor initial configuration data.

[0053] In the present invention, the hardware connection check ensures that the hardware connection between the sensor and the edge computing device is reliable and stable. By checking the hardware connection status, data loss or communication failure caused by poor connection is avoided. By configuring the communication channel according to the hardware connection check result, it is ensured that the sensor data can be accurately transmitted through a suitable network channel. The communication channel configuration not only improves the stability of data transmission but also provides a stable communication foundation for sensor data acquisition. The sensor characteristic reading step can extract key information (such as sensitivity, range, error characteristics, etc.) from the sensor, ensuring that the characteristics of the sensor are fully understood, so that the actual performance of the sensor can be taken into account during parameter initialization and optimization. By calibrating the sensor, it is ensured that its output data is closer to the true value, improving the accuracy and consistency of the data. Gain adjustment can optimize the response sensitivity and output range of the sensor. By adjusting the gain, the response of the sensor under different working conditions can be made more in line with the actual requirements. Especially in an environment where the signal strength is inconsistent or the noise is large, gain adjustment can significantly improve the signal quality and reduce errors. Through parameter initialization after optimizing the gain value, it is ensured that the sensor has the correct working state and performance settings when starting up.

[0054] Preferably, step S3 is specifically as follows:

[0055] Step S31: Perform sensor parameter fitting based on the sensor digital twin model and the initial configuration data of the sensor to obtain a sensor fitting model;

[0056] Step S32: Perform noise simulation on the sensor fitting model to obtain noise interference data;

[0057] Step S33: Perform usage scenario simulation based on the sensor fitting model and the noise interference data to obtain sensor simulation data.

[0058] In the present invention, by combining the sensor digital twin model with the initial configuration data of the sensor, sensor parameter fitting is performed, and various performance parameters of the sensor can be accurately estimated and adjusted. The noise simulation step generates noise interference data by performing interference simulation on the fitting model, which can comprehensively evaluate the performance of the sensor in a complex environment. Noise factors in the real environment (such as electromagnetic interference, vibration, temperature fluctuations, etc.) will affect the output of the sensor. By simulating noise interference, the anti-interference ability of the sensor can be tested and optimized. By combining the sensor fitting model and the noise interference data to perform usage scenario simulation, the working state and performance of the sensor in actual applications can be more realistically restored. Scenario simulation can consider the superposition of various factors, such as environmental temperature changes, pressure fluctuations, mechanical vibrations, etc., to comprehensively test the adaptability and reliability of the sensor.

[0059] Preferably, step S4 is specifically as follows:

[0060] Step S41: Obtain the target data for sensor use;

[0061] Step S42: Perform qualified parameter mapping based on the target data for sensor use to obtain sensor qualified parameter data;

[0062] Step S43: Conduct in-depth performance evaluation based on the sensor qualified parameter data and sensor simulation data to obtain sensor detection data.

[0063] In the present invention, obtaining the target data for sensor use is the first step in sensor performance evaluation, ensuring that the evaluation work is based on the specific goals required by the sensor during actual use. Transforming the use goals of the sensor into quantifiable performance criteria (such as accuracy, response time, operating temperature, etc.) to ensure that the sensor meets the use requirements in terms of various performance indicators. Through the combination of qualified parameter data and simulation data, comprehensive performance detection is carried out to ensure that the sensor can meet the design standards during actual operation, providing an accurate and in-depth performance evaluation of the sensor, discovering possible defects and optimizing them.

[0064] Preferably, the present application also provides a sensor detection system for performing the above-mentioned sensor detection method. The sensor detection system includes:

[0065] A sensor digital twin model construction module for collecting the geometric, mechanical, and electrical parameters of the sensor installation environment in real time and constructing a sensor digital twin model;

[0066] A sensor initial configuration module for automatically identifying and initializing sensor parameters through a local area network by an edge computing device to obtain sensor initial configuration data;

[0067] A sensor simulation module for generating sensor simulation data based on the sensor digital twin model and the sensor initial configuration data;

[0068] A performance detection and evaluation module for performing performance detection and evaluation based on the sensor simulation data to obtain sensor detection data.

[0069] The beneficial effects of the present invention are as follows: By collecting the geometric, mechanical, and electrical parameters of the sensor installation environment in real time and establishing a digital twin model, the present invention provides an accurate and dynamic digital representation for the detection of sensors. The digital twin model can simulate the physical environment and sensor behavior in the real world, helping to track the working state of the sensor and environmental changes in real time. The introduction of edge computing devices can push the computing and data processing from the cloud to the vicinity of the sensor, reducing the data transmission delay and improving the real-time performance and data processing efficiency. The automatic identification and initialization of the sensor are completed through the local area network, ensuring the rapid configuration and seamless integration of the device. By combining the digital twin model with the initial configuration data of the sensor, simulated data is generated, and the simulated data can more accurately predict the behavior and performance of the sensor in different working environments. It is not limited to testing the basic performance of the sensor (such as sensitivity, response time, etc.), but also takes into account the effects of external disturbances, environmental factors, and system interactions, enabling comprehensive and multi-dimensional performance testing. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Other features, objects, and advantages of the present application will become more apparent by reading the detailed description of the non-limiting embodiments with reference to the following drawings:

[0071] Figure 1 The flowchart showing the steps of a sensor detection method according to an embodiment is shown;

[0072] Figure 2 The flowchart showing the steps of a method for constructing a sensor digital twin model according to an embodiment is shown;

[0073] Figure 3 The flowchart showing the steps of a sensor initial configuration method according to an embodiment is shown;

[0074] Figure 4 The flowchart showing the steps of a sensor simulation method according to an embodiment is shown;

[0075] Figure 5 The flowchart showing the steps of a performance detection and evaluation method according to an embodiment is shown. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0076] The technical method of the present invention will be clearly and completely described below with reference to the drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0077] In addition, the attached drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0078] It should be understood that although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0079] Please refer to Figures 1 to 5 , this application provides a sensor detection method, including the following steps:

[0080] Step S1: Collect the geometric, mechanical, and electrical parameters of the sensor installation environment in real time and construct a digital twin model of the sensor;

[0081] Specifically, a set of environmental perception devices (such as temperature sensors, humidity sensors, light sensors, etc.) are installed to collect the geometric, mechanical, and electrical parameters of the environment where the sensor is located. The geometric parameters include the physical dimensions of the installation location, the spatial position relationship, etc.; the mechanical parameters include stress, vibration, etc. in the environment; and the electrical parameters include voltage, current, power, etc. A digital twin model is established based on the geometric shape, working conditions, and mechanical properties of the sensor in the actual environment. This model is based on the data of the actual sensor and environmental parameters and is modeled using digital 3D modeling tools and simulation software (such as CAD software, ANSYS, MATLAB, etc.), and includes simulation data of the physical structure of the sensor, external environmental changes, mechanical responses, and electrical performance.

[0082] Step S2: Automatically identify and initialize the sensor parameters through the edge computing device via the local area network to obtain the initial configuration data of the sensor;

[0083] Specifically, an edge computing device communicates with sensors via a local area network (such as Wi-Fi or Ethernet) to automatically identify the model, specifications, production information, etc. of the sensors. The edge device can identify the sensors through the IDs or QR codes carried by the sensors and read the basic configuration data of the sensors (such as sensitivity, range, operating voltage, etc.). The edge computing device performs initialization settings on the identified sensors, including setting the initial working state of the sensors, the sampling frequency of the sensors, the data transmission method (such as serial communication, wireless transmission, etc.), and the working mode (such as continuous working mode, periodic detection mode, etc.). The edge computing device stores the configuration data after initializing the sensors and uploads this data to the cloud platform or local server via the local area network.

[0084] Step S3: Generate sensor simulation data according to the sensor digital twin model and the initial configuration data of the sensors;

[0085] Specifically, using the digital twin model and the initial configuration data of the sensors, simulate the working states of the sensors in different environments (such as temperature, humidity, current fluctuations, etc.) through simulation software. The simulation data includes the output signals, errors, response times, etc. of the sensors. The simulation process needs to take into account various environmental changes and the physical characteristics of the sensors. Based on the initial configuration data and the environmental model, calculate the response characteristics and performance of the sensors. For example, based on the geometric and mechanical characteristics of the sensors, simulate the output errors under different vibration, temperature, and humidity conditions; based on the electrical parameters, simulate the fluctuations in the voltage and current responses of the sensors. In the simulation, combined with the digital twin model, use known mathematical models and sensor characteristics to generate a complete set of simulation data, including the expected outputs of the sensors in various environments. The accuracy of the simulation data directly affects the effectiveness of the performance evaluation. Therefore, multiple simulations need to be carried out and the consistency with the actual data needs to be verified.

[0086] Step S4: Perform performance detection and evaluation based on the sensor simulation data to obtain sensor detection data.

[0087] Specifically, according to the application requirements and expected performance standards of the sensor, specific evaluation indicators are set, such as sensitivity, response time, stability, linearity, etc. For each performance parameter, a performance threshold is determined. By comparing the simulated data with the performance indicators (performance thresholds) set by the standard, the performance of the sensor is evaluated. The detection process compares the simulated data with the actual measurement results of the sensor to check the difference between the two. The difference is used to identify faults or deviations of the sensor. Through the deviation analysis of the simulated data and the actual detection data, it can be further determined whether the sensor has faults or performance degradation. For example, if there is an obvious difference between the simulated data and the actual output, it may be due to problems such as sensor drift, aging, or improper installation. According to the results of performance evaluation and fault diagnosis, the detection data of the sensor are generated and provided to the user for subsequent maintenance, calibration, or optimization measures.

[0088] Preferably, step S1 is specifically as follows:

[0089] Step S11: Deploy an environmental sensor array, and collect real-time environmental parameter data through an edge device;

[0090] Specifically, multiple environmental sensors are arranged in the sensor installation environment to monitor environmental parameters in real time, such as temperature, humidity, air pressure, light intensity, etc., such as DHT22 temperature and humidity sensors, BME680 air pressure and air quality sensors, etc. In the temperature sensor installation environment of a factory, a temperature sensor (such as DS18B20), a humidity sensor (such as DHT22), and a barometric pressure sensor (such as BME280) are arranged. All sensors are connected to an edge computing device (such as Raspberry Pi or an industrial edge computing gateway). The edge device collects sensor data in real time through interfaces (such as I2C, SPI, or GPIO) and stores it. The data includes real-time information such as environmental temperature, humidity, and air pressure. The edge device reads the temperature, humidity, and air pressure data once per second and uploads the data to the cloud platform through a wireless network (such as Wi-Fi or Ethernet) for further processing.

[0091] Step S12: Generate a virtual sensor environment based on the real-time environmental parameter data to obtain virtual sensor environment data;

[0092] Specifically, based on the real-time collected environmental parameter data, a virtual sensor working environment is generated using a computational model or simulation software to simulate the response and performance of the sensor in a real environment. The temperature range of the actual working environment of the temperature sensor is 20°C to 40°C, the humidity range is 30% to 80%, and the pressure range is 950 hPa to 1050 hPa. On this basis, a virtual simulation tool (such as ANSYS, MATLAB, or Simulink) is used to generate simulated environmental data to deduce the reaction of the sensor under different temperatures, humidities, and air pressures. The virtual output data of the sensor under different environmental conditions (such as the output voltage of the temperature sensor) is calculated through the model. Through simulation, it is obtained that when the temperature is 30°C, the humidity is 50%, and the air pressure is 1010 hPa, the output voltage of the temperature sensor is 2.5V.

[0093] Step S13: Use laser scanning to obtain the geometric shape of the installation position, obtain sensor geometric shape data, and perform geometric reconstruction based on the sensor geometric shape data to obtain sensor installation geometric parameter data;

[0094] Specifically, use a laser scanning device (such as a laser scanner from Leica or FARO) to scan the installation position of the sensor. The laser scanner can accurately obtain the three-dimensional geometric data of the installation position, including the dimensions and positions of the wall, bracket, etc. Use a Leica ScanStation P40 for laser scanning to scan the geometric shape of the sensor installation position and accurately obtain the three-dimensional coordinate data of each installation point. Input the laser scanning data into three-dimensional modeling software (such as AutoCAD, SolidWorks, or MeshLab) for geometric reconstruction to generate a three-dimensional model of the sensor installation environment. This model will display geometric parameters such as the distance and relative position between the sensor and other devices. Through geometric reconstruction software, the point cloud data obtained by laser scanning is converted into a three-dimensional CAD model to obtain the accurate geometric shape data of the sensor installation position (such as the distance between the sensor and the wall, the angle of the bracket, the spatial coordinates of the installation point, etc.).

[0095] Step S14: Use a pressure sensor and an accelerometer to calibrate the mechanical parameters of the installation environment to obtain sensor mechanical characteristic data;

[0096] Specifically, install a pressure sensor (such as the differential pressure sensor of Honeywell) and an accelerometer (such as ADXL345) in the sensor installation environment to monitor mechanical changes in the environment, such as pressure fluctuations, vibrations, and accelerations. Arrange the accelerometer and the pressure sensor in the sensor installation environment to monitor the vibration and pressure changes in the environment in real time. For example, use the accelerometer to measure the vibration frequency of the installation environment and use the pressure sensor to monitor the air pressure fluctuations. Calibrate the mechanical characteristics of the sensor under different environmental conditions through the environmental data collected by the sensor. For example, calculate the response characteristics of the sensor in such an environment based on the vibration frequency measured by the accelerometer and the pressure fluctuations measured by the pressure sensor. The vibration frequency in the environment is 50 Hz and the pressure fluctuation is ±5 Pa. Calibrate the sensitivity of the sensor to these mechanical changes through the response data of the sensor to obtain the mechanical characteristic data of the sensor.

[0097] Step S15: Measure the connector impedance, voltage waveform, and grounding status using an oscilloscope to obtain electrical characteristic data;

[0098] Specifically, measure the electrical characteristics of the sensor connector using an oscilloscope (such as Tektronix or Keysight). First, measure the impedance of the sensor power supply pins to ensure stable electrical connection. Observe the sensor voltage waveform to ensure that the voltage output is stable and meets the design requirements. Finally, test the grounding status to ensure good grounding. Measure the voltage signal of the sensor using an oscilloscope. Assume that the measured voltage waveform is a sine wave of 1 kHz with an amplitude of 5 V. Then, test the grounding status and confirm that the grounding voltage is 0 V and the grounding is good. Calibrate the electrical characteristics of the sensor based on the measured data, including the resistance of the connector, the stability of the output signal, and the grounding status. The measured electrical characteristic data includes an impedance of 50 Ω, a voltage waveform of a sine wave (1 kHz, 5 V), and good grounding.

[0099] Step S16: Establish a digital twin model using the sensor installation geometric parameter data, sensor mechanical characteristic data, electrical characteristic data, and virtual sensor environment data to obtain a sensor digital twin model.

[0100] Specifically, using software such as MATLAB / Simulink or ANSYS, input the geometric data, mechanical data, electrical data, and environmental data of the sensor into the simulation platform to generate a digital twin model. The model can simulate the response and performance of the sensor under different environmental conditions. Use the above-integrated data to establish a digital twin model and simulate the performance of the sensor under different environmental conditions. Through this model, the status of the sensor in the actual working environment can be monitored in real time, and predictive maintenance can be carried out. Establish a virtual model in MATLAB / Simulink that includes the geometric parameters of the sensor, environmental data, electrical characteristics, etc., simulate the output of the sensor under changes in temperature and humidity, and monitor the performance of the sensor in real time.

[0101] Preferably, step S12 is specifically as follows:

[0102] Extract features from the real-time environmental parameter data to obtain environmental parameter feature data;

[0103] Specifically, the real-time environmental parameter data includes multiple sensed data, such as temperature, humidity, air pressure, light, etc. The data is sourced from a sensor array or other environmental monitoring devices. The goal of environmental parameter feature extraction is to extract meaningful features from these raw data, such as change trends, fluctuation amplitudes, periodicity, etc. The extraction methods include statistical analysis (such as mean, variance, kurtosis, skewness, etc.), frequency domain analysis (such as Fourier transform), and time series analysis, etc. For the data collected by each sensor, first perform data preprocessing (denoising, normalization, etc.). Then, use a filtering algorithm or a sliding window technique to slice the data and extract features. Environmental features include: temperature change rate, humidity fluctuation range, air pressure periodicity, etc.

[0104] Perform environmental geometric modeling based on the environmental parameter feature data to obtain environmental geometric data;

[0105] Specifically, environmental geometric modeling is to model the spatial layout of the environment, and it is necessary to collect the geometric data of the environment, such as spatial dimensions, positions of obstacles, shapes of walls, etc. If the geometric data of the environment has been collected by devices such as laser scanning or 3D cameras, these data can be directly used for modeling. Otherwise, simulation or mathematical modeling methods can be used to generate the geometric model of the environment. Environmental geometric modeling usually includes the following methods: Obtain the point cloud data of the environmental space through a laser rangefinder, and then convert the point cloud data into a three-dimensional model. Or, perform environmental modeling through a camera and a depth sensor (such as Kinect) to obtain the geometric information of the space. Or, if there are existing architectural design drawings or CAD models, these data can be directly used for modeling.

[0106] Perform physical property mapping on the real-time environmental parameter data and the environmental geometric data to obtain environmental physical property distribution map data;

[0107] Specifically, map the real-time environmental parameter data (such as temperature, humidity, etc.) to the environmental geometric data (such as the walls, floors, ceilings of a room, etc.). Calibrate the corresponding physical properties (such as temperature, humidity, etc.) at each spatial position to generate a distribution map of environmental physical properties. The mapping process uses interpolation algorithms (such as nearest-neighbor interpolation, bilinear interpolation, cubic interpolation, etc.) to distribute the environmental data to each point in space. Divide the space into grids according to the spatial layout of the environmental geometric data, and assign a physical property (such as temperature or humidity) to each grid point. Use a 3D visualization tool (such as OpenGL or Unity3D) to generate a distribution map of environmental physical properties, which represents the physical states such as temperature and humidity at different spatial positions.

[0108] Generate virtual environment texture from the distribution map data of environmental physical properties to obtain environmental texture map data;

[0109] Specifically, the purpose of texture generation is to visually represent physical properties (such as temperature, humidity, etc.) so that they can be reflected in the virtual environment in the form of images or textures. This includes mapping the physical property data to the corresponding texture layers. For example, use color gradients on the temperature distribution map to represent different temperature ranges, or use different textures on the humidity distribution map to show the changes in humidity. Use texture mapping techniques in computer graphics to combine the generated distribution map of physical properties with the 3D environmental model. For example, use color bands or texture maps to express temperature changes (such as using red for high temperature and blue for low temperature), and use tools such as Photoshop, Blender or Unity to generate and apply these textures. For the temperature distribution map, generate a temperature map, where areas with higher temperatures (such as near windows) are represented by red, and areas with lower temperatures (such as near walls) are represented by blue. By applying these textures to the surface of the virtual environment model, visually display the temperature distribution of the entire room.

[0110] Generate virtual sensor position interfaces based on the environmental texture map data to obtain virtual sensor environmental data.

[0111] Specifically, based on the environmental texture map data, determine the position of the sensor in the virtual environment and associate the sensor with specific positions in the environment (such as walls, windows, etc.). Each virtual sensor will collect physical property data (such as temperature, humidity, etc.) from this position and generate corresponding environmental data. The process of generating the position interface is usually implemented through virtual simulation tools, where the "position" of the sensor can be specified according to the physical space layout. Specify a position for each sensor in the virtual environment and generate the actual working environment data of the sensor according to the texture map data of this position. Each sensor position can be mapped to a specific physical property (such as the temperature or humidity at a specific position) and simulate its behavior in the virtual environment. The virtual sensor is located at the center of the room, and the sensor environmental data is generated according to the temperature map data (such as 21 °C) at this position. The virtual sensor obtains the environmental parameters it needs according to the position data in the room.

[0112] Preferably, the feature extraction specifically is as follows:

[0113] Perform window data slicing on the real-time environmental parameter data to obtain environmental parameter slice data;

[0114] Specifically, in order to analyze the dynamic changes of environmental parameters, divide the original time series data into several windows, and each window contains data with a fixed duration or a fixed number. For example, select a time window (such as 5 seconds or 10 seconds), and then extract the data slice within this time period for analysis.

[0115] Calculate the environmental perturbation index based on the environmental parameter slice data to obtain environmental perturbation index data;

[0116] Specifically, the perturbation index is an indicator used to quantify the amplitude and frequency of environmental parameter changes. Use the volatility, standard deviation or change rate of the data to calculate the perturbation index. For example, when the temperature, humidity or air pressure changes greatly, the environmental perturbation index will be higher. For each data slice, calculate the standard deviation or change rate (such as the change amount per second) of each environmental parameter (such as temperature, humidity, air pressure) as a component of the perturbation index. By calculating the perturbation index of each window, the environmental perturbation index data of each time window can be obtained.

[0117] Calculate the covariance matrix of multiple environmental variables based on the environmental parameter slice data to obtain multi-environmental variable correlation data;

[0118] Specifically, the covariance matrix is an important tool for measuring the correlation between multiple environmental variables. By calculating the covariance matrix of environmental parameters, the mutual relationships between different environmental parameters (such as temperature, humidity, air pressure, etc.) can be understood. For the sliced data of each environmental parameter (such as temperature, humidity, and air pressure), calculate the covariance matrix between these variables. The diagonal elements of the covariance matrix represent the variances of each environmental parameter, and the off-diagonal elements indicate the correlations between different environmental parameters. Through this matrix, it can be known which environmental parameters have strong correlations and which have weak correlations.

[0119] Perform environmental space abnormal fluctuation processing on the environmental perturbation index data and the multi-environmental variable correlation data to obtain environmental parameter characteristic data.

[0120] Specifically, the goal of abnormal fluctuation processing is to remove noise from the environmental data and eliminate abnormal fluctuations to ensure that the obtained characteristic data can accurately reflect the actual state of the environment. Abnormal fluctuations include short-term fluctuations caused by sudden climate changes, equipment failures, etc. These fluctuations are accidental and unrepresentative. Perform abnormal detection on the environmental perturbation index and the correlation data of multi-environmental variables to identify abnormal fluctuations in the environment. Use statistical methods (such as Z-score detection) or machine learning methods (such as outlier detection algorithms) to discover abnormal fluctuations. Perform Z-score standardization on the environmental perturbation index data and the data in the covariance matrix, and calculate the Z-score of each data point. If the Z-score of a certain data point is greater than a certain threshold (such as 3), it is regarded as an abnormal fluctuation. The perturbation index of a certain time window is 3.5 and the Z-score is 3, indicating that this is an abnormal fluctuation and needs further processing. After detecting abnormal fluctuations, the data can be smoothed or denoised to remove interference factors and obtain more accurate environmental parameter characteristics. For the identified abnormal fluctuations, use the moving average method for smoothing. For example, average the perturbation index data of the last 5 windows to eliminate short-term abnormal fluctuations.

[0121] Preferably, the window data slicing is specifically as follows:

[0122] Perform window slicing on the real-time environmental parameter data through the preset first window slicing parameter data and the preset second window slicing parameter data to obtain the first preliminary window slicing data and the second preliminary window slicing data respectively;

[0123] Specifically, set the window size. For example, the "first window slicing parameter" is defined as 5 seconds, and the "second window slicing parameter" is defined as 10 seconds. The environmental parameter data is collected once per second. According to the preset first window slicing parameter (5 seconds) and second window slicing parameter (10 seconds), the first preliminary window slicing data and the second preliminary window slicing data are sliced from the real-time environmental parameter data.

[0124] Perform clustering calculations on the first preliminary window slicing data and the second preliminary window slicing data, respectively obtaining the first window slicing clustering data and the second window slicing clustering data;

[0125] Specifically, perform clustering calculations on the first preliminary window slicing data and the second preliminary window slicing data. Clustering algorithms such as K-means can divide the data into multiple clusters according to similarity. Each cluster represents a dataset with a similar environmental parameter change pattern. Use the K-means clustering algorithm to process the first window slicing data (5-second window), and divide it into two clusters: First cluster: [25°C, 50%, 1013hPa], [25.1°C, 50.1%, 1013.1hPa], [25.2°C, 50.2%, 1013.2hPa], second cluster: [25.3°C, 50.3%, 1013.3hPa], [25.4°C, 50.4%, 1013.4hPa]. Perform similar processing on the second window slicing data (10-second window) to obtain: First cluster: [25°C, 50%, 1013hPa],..., [25.4°C, 50.4%, 1013.4hPa], second cluster: [25.5°C, 50.5%, 1013.5hPa],..., [25.9°C, 50.9%, 1013.9hPa].

[0126] Calculate the cluster change rates based on the first window slicing clustering data and the second window slicing clustering data, respectively obtaining the first clustering cluster change rate data and the second clustering cluster change rate data;

[0127] Specifically, the change rate of each cluster is calculated. The change rate can be obtained by calculating the time series change of the cluster center. The change rate of the cluster describes how the cluster changes in the time dimension and reflects the degree of dynamic change of the environment. For the first cluster of the first window slice data, calculate the change rates of temperature and humidity: Temperature change rate = (25.2°C - 25°C) / (2s - 0s) = 0.1°C / s, Humidity change rate = (50.2% - 50%) / (2s - 0s) = 0.1% / s. For the first cluster of the second window slice data, calculate the change rates of temperature and humidity within the cluster: Temperature change rate = (25.4°C - 25°C) / (4s - 0s) = 0.1°C / s, Humidity change rate = (50.4% - 50%) / (4s - 0s) = 0.1% / s. Obtain the change rate data of the first clustering cluster: [0.1°C / s, 0.1% / s], and the change rate data of the second clustering cluster: [0.1°C / s, 0.1% / s].

[0128] Perform window dynamic re-partitioning on the first window slice parameter data according to the change rate data of the first clustering cluster to obtain the first window re-slice parameter data, and perform the second window re-slice parameter data on the second window slice parameter data according to the change rate data of the second clustering cluster;

[0129] Specifically, perform dynamic re-partitioning of the window according to the cluster change rate data. If the change rate of the cluster is large, it indicates that the environmental change is relatively drastic, and the window needs to be re-partitioned to better capture the volatility of the environment. Dynamically adjust the length of the slice according to the change rate of the cluster, or perform partitioning in time according to the change rate. For example, if the cluster change rate of the first window is greater than 0.1°C / s, the time interval of the slice can be shortened from 5 seconds to 3 seconds.

[0130] Perform window slicing on the real-time environmental parameter data through the preset first window re-slice parameter data and the preset second window re-slice parameter data to obtain the first preliminary window re-slice data and the second preliminary window re-slice data respectively;

[0131] Specifically, based on the adjusted re-slice parameter data (such as the adjusted window time), re-slice the real-time environmental parameter data.

[0132] Extract window data features from the first preliminary window re-slice data and the second preliminary window re-slice data to obtain the first window feature data and the second window feature data respectively;

[0133] Specifically, extract features from each window slice data (whether it is the original data or the re-slice data). The features include mean, standard deviation, maximum value, minimum value, amplitude, volatility, etc.

[0134] Specifically, and more importantly, matrix decomposition is performed on the first preliminary window resliced data and the second preliminary window resliced data to obtain first matrix decomposition data and second matrix decomposition data respectively; principal feature extraction is performed on the first matrix decomposition data and the second matrix decomposition data to obtain first principal feature data and second principal feature data respectively; clustering calculation is performed according to the first principal feature data and the second principal feature data to obtain first principal feature clustering data and second principal feature clustering data respectively; cross-window aggregation is performed on the first principal feature data and the second principal feature data according to the first principal feature clustering data and the second principal feature clustering data to obtain cross-window aggregation data; feature extraction is performed according to the cross-window aggregation data to obtain first window feature data; time series difference cumulative calculation is performed on the first preliminary window resliced data and the second preliminary window resliced data to obtain first window change rate feature data and second window change rate feature data respectively; spatial dimension mapping is performed according to the first window change rate feature data and the second window change rate feature data to obtain first window virtual space grid data and second window virtual space grid data respectively; spatial characteristic stratification is performed according to the first window virtual space grid data and the second window virtual space grid data to obtain first spatial characteristic stratification data and second spatial characteristic stratification data respectively; multi-scale recursive aggregation analysis is performed according to the first spatial characteristic stratification data and the second spatial characteristic stratification data to obtain multi-scale recursive aggregation data; graph feature extraction is performed according to the multi-scale recursive aggregation data to obtain second window feature data; wherein the cross-window aggregation specifically is: similarity calculation is performed according to the first principal feature clustering data and the second principal feature clustering data to obtain principal feature similarity data; aggregation is performed on the first principal feature data and the second principal feature data according to the principal feature similarity data to obtain cross-window aggregation data.

[0135] Construct the first preliminary window resliced data and the second preliminary window resliced data into matrices respectively, where the rows represent time points and the columns represent different environmental variables (such as temperature, humidity, air pressure). Decompose the matrix and decompose it into two low-dimensional matrices. Select the first two main modes from the decomposition and extract their corresponding principal components. For example, the first principal component reflects the main changes in temperature fluctuations; the second principal component reflects the co-variation of humidity and air pressure. Extract the main features according to the matrix decomposition results through singular value decomposition (SVD) or principal component analysis (PCA) to obtain the first main feature data and the second main feature data respectively. Cluster the first main feature data and the second main feature data respectively to identify the distribution of feature patterns. For example, the first main feature data [0.9, 0.8, 0.7] is clustered into two categories after clustering, and the result is [1, 1, 2], indicating that the first and second time points belong to the same category, and the third time point belongs to another category. The clustering process of the second window is similar, and the second main feature clustering data is output. Compare the first main feature clustering data and the second main feature clustering data across windows to identify the change pattern and obtain the clustering label sequence comparison sequence. Generate aggregation metrics based on the clustering label sequence comparison sequence, such as consistency, drift degree, etc. For example, the first window clustering is [1, 1, 2], and the second window clustering is [1, 2, 2]. Cross-window consistency metric: The first two time points are consistent (1 and 1), and the last time point changes (2 and 2). Aggregate the first main feature clustering data and the second main feature clustering data through weight calculation (that is, generate weights based on the aggregation metrics and cross-window consistency metrics. If the consistency is high (such as >0.8), then rely more on the main feature data of the first window. If the drift degree is high, then consider increasing the feature weight of the second window to highlight the time change) to obtain cross-window aggregated data. Integrate the cross-window aggregated data with the main feature data to generate a feature vector.

[0136] For the time series in the first preliminary window resliced data and the second preliminary window resliced data, calculate the difference and cumulative change rate. The difference represents the change value between adjacent data points in the time series. The cumulative change rate represents the cumulative change from the initial moment to the current moment. Map the change rate feature data to the spatial dimension to generate a virtual space grid. The spatial grid points are composed of positions and characteristic values of environmental variables. Use the interpolation algorithm to assign the change rate values of non-grid points to the grid. Stratify the virtual space grid data by space and time to extract the stratified characteristics. Group the grid points by position and calculate the mean and gradient of each group of grid points. Aggregate the change rates of the grid points by time to generate the characteristic data of each layer. The first spatial characteristic stratified data: mean characteristic: μ = [1.5, 2.5], gradient characteristic: = [1, 0.5]; The second spatial characteristic stratified data: mean characteristic: μ = [0.75, 1.5], gradient characteristic: =[0.5,0.25].

[0137] Aggregate and analyze the spatially characteristic hierarchical data by a multi-scale recursive method to extract global features. The recursive analysis is used to capture short-term, medium-term, and long-term trends: , For the recursive characteristic value corresponding to the moment, is the first time-scale weight data, is the recursive characteristic value of the previous moment. At the initial moment (t = 1), is set to the initial value of the first spatially characteristic hierarchical data, such as the mean or gradient of the first time point. is the second time-scale weight data, is the characteristic value of the current time point, coming from the spatially characteristic hierarchical data. Short-term trend: is small, such as 0.2, making the recursive characteristic more dependent on the current characteristic value. is large, such as 0.8, highlighting the contribution of the characteristic of the current time point. Medium-term trend: is medium, such as 0.5, balancing the historical trend and the current characteristic. is medium, such as 0.5. Long-term trend: is large, such as 0.8, emphasizing the historical trend. is small, such as 0.2, weakening the influence of the fluctuation of the current data.

[0138] Use the spatial grid points as the nodes of the graph, and the distance or gradient between the nodes as the edge weights. Extract the global features (such as centrality, connectivity) of the graph to obtain the graph features. Fuse the recursive aggregation data and the graph features to generate the second window feature vector.

[0139] Utilize the first window feature data, the second window feature data, the first preliminary window resliced data, and the second preliminary window resliced data to construct a cross-window feature matrix to obtain the environmental parameter sliced data.

[0140] Specifically, combine the feature data of the first window and the second window to form a cross-window feature matrix. This matrix can contain the feature data of each window and be arranged in chronological order. Window 1 feature data: [25.1°C, 50.1%, 1013.1hPa], Window 2 feature data: [25.55°C, 50.55%, 1013.55hPa]. Cross-window feature matrix: [[25.1, 50.1, 1013.1], [25.55, 50.55, 1013.55]].

[0141] Preferably, the environmental geometric modeling is specifically:

[0142] Obtain the geometric data of the installation environment;

[0143] Specifically, the geometric data of the installation environment is obtained through a sensor array (such as a laser scanner, RGB-D camera, depth camera, etc.) or a 3D scanning device. The device can collect information such as the spatial layout of the scene, the object surface, and the spatial coordinates. The collected geometric data includes information such as the three-dimensional point cloud data of the scene, object boundaries, and surface curvature. These data can be used to model the three-dimensional shape of the environment.

[0144] Perform spatial mapping based on the real-time environmental parameter data and the geometric data of the installation environment to obtain the installation environment mapping data;

[0145] Specifically, the geometric data of the environment is spatially mapped with the real-time environmental parameters (such as temperature, humidity, air pressure, etc.), and is completed through technologies such as spatial interpolation, registration, and coordinate transformation. The goal is to bind each collected environmental parameter to the corresponding geometric position, thereby generating a three-dimensional space model with environmental parameters. According to the variation law of the environmental parameters, interpolation is performed between the known geometric data position points to infer the environmental parameter values at other spatial positions. Align the real-time collected environmental data with the geometric model to ensure that the spatial coordinates match the environmental parameter data. Given some environmental parameter data (such as temperature, humidity, etc.) and having a corresponding three-dimensional point cloud model, the environmental parameters are combined with the point cloud data through an interpolation method (such as Kriging interpolation, inverse distance weighting method, etc.). For example, the temperature data corresponds to 25°C at the coordinates (x1, y1, z1), and the humidity data corresponds to 50% at the coordinates (x2, y2, z2). Through spatial mapping, a three-dimensional data set containing environmental parameters can be obtained

[0146] Perform geometric estimation of the installation environment based on the real-time environmental parameter data to obtain the geometric estimation data of the installation environment;

[0147] Specifically, based on the existing geometric data and environmental parameter data, prediction algorithms or modeling methods (such as machine learning, data fitting, etc.) are used to estimate the environment geometry. Through the correlation between historical data and real-time environmental parameters, predict the change trend of the environment geometry in the future. Time series prediction methods (such as ARIMA, LSTM network, etc.) or machine learning methods based on environmental characteristics (such as regression analysis, support vector machine, etc.) can be used to predict the geometric changes of the environment. For example, predict the position change of a certain device or object in a certain spatial area. Through historical data analysis, it is concluded that temperature changes will cause deformation of certain objects. For example, due to temperature changes, the length or position of certain devices may change slightly. Through a prediction model (such as regression analysis), the change situation of the device position (x, y, z) within the next 10 minutes can be predicted

[0148] Fuse the environmental parameters based on the geometric estimation data of the installation environment and the installation environment mapping data to obtain the environmental geometry data.

[0149] Specifically, fuse the geometric estimation data of the installation environment and the environment mapping data, combine the advantages of both, and obtain a more accurate and complete environmental geometry data. Environmental parameter fusion often relies on data fusion algorithms (such as Kalman filtering, particle filtering, etc.), which can perform weighted fusion on data from different sources (such as geometric data, environmental parameter data) to obtain an optimal environmental geometry model. Use methods such as weighted average method and Kalman filter to handle uncertainties and obtain a more accurate environmental geometry model. For example, Kalman filtering can dynamically fuse the geometric data collected in real time with the environmental parameters to predict and correct the changes in the environmental geometry data. There is the following data: the environmental parameter data obtained through spatial mapping, such as the correspondence between temperature, humidity and spatial position. The position change of the environmental geometry at a future moment obtained through the prediction model. Fuse the two through the Kalman filtering algorithm to obtain a more accurate environmental geometry data. For example, at a certain position in the installation environment, the changes in temperature and humidity cause changes in the device position. Kalman filtering can combine these changes and finally give more accurate position information and environmental parameters of the device:

[0150] Preferably, step S2 is specifically as follows:

[0151] Step S21: Perform hardware connection verification based on the edge computing device to obtain hardware connection verification data;

[0152] Specifically, make a physical connection between the edge computing device and the sensor, and verify the normal connection of the power supply and signal transmission channels (such as I2C, SPI, UART, etc.) of the sensor. Check the connection stability, whether there are problems such as unstable power supply and poor contact. It is possible to confirm whether the connection is successful by reading the ID of the sensor or the return of the self-check signal. Use a simple "heartbeat" signal or self-check signal to confirm the hardware connection. Verify the connection stability by detecting the response time and data integrity of the sensor. The connected sensor is a temperature sensor. The edge computing device will send a connection request (such as an initialization signal or a query command) to the sensor and wait for the sensor to return its unique ID and response code. If the returned data is complete and there is no error code, the connection verification is successful; if the verification fails, a hardware failure prompt is returned.

[0153] Step S22: Configure the communication channel for the hardware connection verification data to obtain communication channel configuration data;

[0154] Specifically, configure the communication protocol between devices according to the hardware connection verification result. Different sensors support different communication methods, such as I2C, SPI, UART, etc. Ensure that data can be correctly exchanged between the edge computing device and the sensor. During the configuration process, it is necessary to set the transmission rate, data format, communication parameters, etc. to ensure that data can be correctly transmitted. According to the communication interface standard of the sensor, set the communication port parameters of the edge device (such as baud rate, clock frequency, etc.). When using the I2C protocol for communication, the edge computing device configures the frequency of the I2C bus to 100 kHz and the device address to 0x48.

[0155] Step S23: Read the sensor characteristics according to the communication channel configuration data to obtain sensor characteristic data;

[0156] Specifically, use the configured communication channel to interact with the sensor to read the basic characteristics of the sensor, such as sensor model, firmware version, sampling rate, sensor range, etc. Obtain the basic information of the sensor by issuing specific commands (such as "Read device ID" or "Read sensor characteristics" command). Read the characteristic data of the temperature sensor, and the returned characteristic data includes model, sampling rate, range, etc.: Sensor model: DHT22, firmware version: V1.2, sampling rate: 1 Hz, range: -40°C to 80°C, accuracy: ±0.5°C.

[0157] Step S24: Calibrate the parameters according to the sensor characteristic data to obtain calibrated parameter data;

[0158] Specifically, calibrate the sensor according to the read sensor characteristic data. The calibration process usually involves measuring the error between the output of the sensor and the standard reference value and making corrections. The calibration parameters include offset correction, sensitivity correction, zero calibration, etc. Use a known reference standard to correct the output value of the sensor to make it more consistent with the actual value. For example, if the sensor is a temperature sensor, the deviation of the temperature sensor can be calibrated by comparing it with a standard thermometer. Calculate the offset and sensitivity through linear regression or other methods.

[0159] Step S25: Adjust the gain of the calibrated parameter data to obtain optimized gain value data;

[0160] Specifically, adjust the gain of the sensor according to the calibration result. Gain adjustment is to amplify or reduce the output signal of the sensor to make its output value more accurate and closer to the actual measured value. The purpose of gain adjustment is to minimize errors and improve the accuracy and stability of the sensor. Use a gain coefficient to correct the output of the sensor. For example, if it is found that the actual output of the sensor is lower than the standard value after calibration, the gain can be increased, and vice versa.

[0161] Step S26: Initialize the parameters according to the optimized gain value data to obtain the initial configuration data of the sensor.

[0162] Specifically, use the optimized gain value and calibration data to initialize the sensor. The initialization process usually involves applying the setting parameters of the sensor (such as gain, offset, sampling frequency, etc.) to the firmware or hardware configuration of the sensor. According to the previous calibration and gain adjustment results, set the working parameters of the sensor and save them. These settings will serve as the initial configuration data of the sensor.

[0163] Preferably, step S3 is specifically as follows:

[0164] Step S31: Fit the sensor parameters according to the sensor digital twin model and the initial configuration data of the sensor to obtain the sensor fitting model;

[0165] Specifically, the digital twin model of the sensor includes the physical characteristics of the sensor (such as temperature, humidity, pressure, etc.) and the response characteristics under different environmental conditions. The initial configuration data includes the parameter settings of the sensor, such as gain, sampling rate, working range, etc. By fitting the mathematical formula or physical model in the sensor digital twin model with the initial configuration data, a sensor fitting model is established. The sensor fitting model is a mathematical model that describes the relationship between the output and input of the sensor. Optimize the parameters of the sensor model through methods such as least squares method, nonlinear regression, and support vector machine to make the output of the model as close as possible to the output of the real sensor. According to different environmental conditions, input the working environment data of the sensor (such as temperature, humidity, etc.), calculate the predicted output, and adjust the parameters of the sensor model to minimize the error of the fitting result.

[0166] Step S32: Perform noise simulation on the sensor fitting model to obtain noise interference data;

[0167] Specifically, the sensor may be affected by various noise interferences during actual use, and these noises come from electronic noise, environmental fluctuations, power supply noise, etc. To more accurately simulate the working state of the sensor, add a noise term to the fitting model. The noise simulation can be achieved through different noise models (such as Gaussian noise, white noise, etc.). The noise is usually random and has certain statistical characteristics (mean, standard deviation, etc.). Based on the output of the sensor fitting model, add a noise term to generate simulated noisy data. This can be achieved by generating random numbers that follow a specific distribution (such as Gaussian distribution) and adding them to the fitting result.

[0168] Step S33: Simulate the usage scenario according to the sensor fitting model and the noise interference data to obtain the sensor simulation data.

[0169] Specifically, the usage scenarios of sensors usually involve multiple factors, such as environmental conditions like temperature, humidity, pressure, etc., which can affect the performance of sensors. During the simulation process, according to the actual usage scenarios (such as temperature changes, device vibrations, environmental humidity, etc.), simulated data is generated. The key to the simulation scenario is to combine the sensor fitting model and noise data with the specific usage scenario data to simulate the performance of the sensor under various working environments. According to different usage scenarios (such as environmental temperature changes, sensor stress, etc.), by inputting different environmental parameters, the response of the sensor under these conditions is calculated. Use simulation tools (such as MATLAB / Simulink, Python, etc.) to simulate environmental changes, input various environmental data (such as changing temperature or humidity), and output sensor simulation data.

[0170] Preferably, step S4 is specifically as follows:

[0171] Step S41: Obtain the target data for sensor usage;

[0172] Specifically, the target data for sensor usage refers to the performance goals or standards that the sensor should meet in actual applications, such as measurement accuracy, response time, range, error tolerance, etc. The data comes from multiple sources, such as product design requirements, industry standards, actual test results, etc. The use of target data helps to define the "desired behavior" or "qualified criteria" of the sensor. The process of obtaining the target data for usage needs to extract relevant standards from the system design stage or engineering specifications. The maximum error range of the sensor (such as ±0.5°C), the response time requirement (such as less than 1 second), the operating temperature range (such as -40°C to 85°C), etc.

[0173] Step S42: Perform qualified parameter mapping according to the target data for sensor usage to obtain sensor qualified parameter data;

[0174] Specifically, qualified parameter mapping is to compare the target data for usage with the actual performance of the sensor to determine which sensor parameters meet the requirements within the target range. The mapping process can be achieved by comparing the simulated output data of the sensor with the target data for usage. Identify whether the sensor meets the design requirements and whether it meets the needs in terms of accuracy, response speed, stability, etc. The core of the mapping is to correspond the actually measured data (such as simulated data) with the target data to determine whether it meets the qualified criteria. The target accuracy of the temperature sensor is ±0.5°C, and the qualified parameter mapping requires comparing the simulated data with the target range. For example, if the simulated data indicates that the temperature change is within the range of ±0.4°C, then it meets the target accuracy.

[0175] Step S43: Perform in-depth performance evaluation based on the sensor qualified parameter data and the sensor simulated data to obtain sensor detection data.

[0176] Specifically, the depth performance evaluation is a comprehensive analysis and assessment of the performance of the sensor under actual or simulated conditions, taking into account various characteristics of the sensor, such as accuracy, response time, stability, anti-interference ability, etc. The evaluation results will determine whether the sensor meets the expected working standards. The depth performance evaluation uses statistical methods, regression analysis, error analysis and other means to quantify the performance, and uses simulated data to verify the reliability of the sensor under various environmental conditions. The simulated data is compared with the qualified parameter data to analyze the performance of the sensor. The evaluation is carried out by calculating error values, response times, stability indicators, etc. For example, to evaluate the accuracy of the sensor, the error range is calculated, and to evaluate the response time, the response time under different environmental conditions is simulated. For example, error analysis is performed using the sensor simulated data and the target data to evaluate whether the sensor meets the accuracy and response speed requirements. If the error of the simulated data exceeds the target error range, the sensor needs to be adjusted or optimized.

[0177] Preferably, the present application also provides a sensor detection system for performing the sensor detection method as described above. The sensor detection system includes:

[0178] A sensor digital twin model construction module, configured to collect in real time the geometric, mechanical and electrical parameters of the sensor installation environment and construct a sensor digital twin model;

[0179] A sensor initial configuration module, configured to automatically identify and initialize the sensor parameters through a local area network by an edge computing device to obtain sensor initial configuration data;

[0180] A sensor simulation module, configured to generate sensor simulation data according to the sensor digital twin model and the sensor initial configuration data;

[0181] A performance detection and evaluation module, configured to perform performance detection and evaluation according to the sensor simulation data to obtain sensor detection data.

[0182] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended application documents rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the application documents are intended to be included in the present invention.

[0183] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather will be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A sensor detection method, characterized in that: The following steps are involved: Step S1: Collect the geometric, mechanical and electrical parameters of the sensor installation environment in real time and build a digital twin model of the sensor; Step S2: Automatically identify and initialize sensor parameters through the local area network according to the edge computing device to obtain initial configuration data of the sensor; Step S3: Generate sensor simulation data according to the sensor digital twin model and the sensor initial configuration data; Step S4: Perform performance testing and evaluation based on the sensor simulation data to obtain sensor testing data; Step S1 is specifically as follows: Step S11: deploy an environmental sensor array to collect real-time environmental parameter data through edge devices; Step S12: Generate a virtual sensor environment according to the real-time environmental parameter data to obtain virtual sensor environment data; Step S13: using laser scanning to obtain the geometric shape of the installation position, obtaining sensor geometric shape data, and performing geometric reconstruction based on the sensor geometric shape data to obtain sensor installation geometric parameter data; Step S14: calibrating the mechanical parameters of the installation environment using the pressure sensor and the accelerometer to obtain the mechanical characteristic data of the sensor; Step S15: using an oscilloscope to measure the connector impedance, voltage waveform and grounding state to obtain electrical characteristic data; Step S16: Establishing a digital twin model of the sensor installation geometric parameter data, sensor mechanical characteristic data, electrical characteristic data, and virtual sensor environment data to obtain a sensor digital twin model; Step S12 is specifically as follows: Perform feature extraction based on real-time environmental parameter data to obtain environmental parameter feature data; Perform environmental geometry modeling according to environmental parameter characteristic data to obtain environmental geometry data; Perform physical attribute mapping on real-time environmental parameter data and environmental geometry data to obtain environmental physical attribute distribution map data; Generate virtual environment texture based on environment physical property distribution map data to obtain environment texture map data; Generate a virtual sensor position interface according to the environment texture map data to obtain virtual sensor environment data; The feature extraction is as follows: Slice the window data according to the real-time environmental parameter data to obtain environmental parameter slice data; Calculate the environmental disturbance index according to the environmental parameter slice data to obtain environmental disturbance index data; Calculate the covariance matrix of multiple environmental variables based on the environmental parameter slice data to obtain the correlation data of multiple environmental variables; The environmental disturbance index data and multi-environmental variable correlation data are processed for abnormal environmental spatial fluctuations to obtain environmental parameter characteristic data; The window data slices are as follows: Perform window slicing according to the real-time environment parameter data using preset first window slicing parameter data and preset second window slicing parameter data to obtain first preliminary window slicing data and second preliminary window slicing data respectively; Performing cluster calculation on the first preliminary window slice data and the second preliminary window slice data to obtain first window slice cluster data and second window slice cluster data respectively; Calculating the cluster change rate according to the first window slice clustering data and the second window slice clustering data to obtain first cluster cluster change rate data and second cluster cluster change rate data respectively; Dynamically re-dividing the first window slice parameter data according to the first cluster change rate data to obtain first window re-slicing parameter data, and dynamically re-dividing the first window slice parameter data according to the second cluster change rate data to obtain second window re-slicing parameter data; Perform window slicing according to the real-time environment parameter data using preset first window reslicing parameter data and preset second window reslicing parameter data, to obtain first preliminary window reslicing data and second preliminary window reslicing data respectively; Performing window data feature extraction on the first preliminary window reslicing data and the second preliminary window reslicing data to obtain first window feature data and second window feature data respectively; The first window feature data and the second window feature data are used to construct a cross-window feature matrix for the first preliminary window re-slicing data and the second preliminary window re-slicing data to obtain environmental parameter slice data.

2. The method according to claim 1, characterized in that The specific environment geometry modeling is as follows: Get the installation environment geometry data; Perform spatial mapping according to real-time environmental parameter data and installation environment geometric data to obtain installation environment mapping data; Perform geometric estimation of the installation environment according to the real-time environmental parameter data to obtain geometric estimation data of the installation environment; Environmental parameters are fused according to the installation environment geometry estimation data and the installation environment mapping data to obtain environmental geometry data.

3. The method according to claim 1, characterized in that Step S2 is specifically as follows: Step S21: Perform hardware connection verification according to the edge computing device to obtain hardware connection verification data; Step S22: performing communication channel configuration on the hardware connection verification data to obtain communication channel configuration data; Step S23: reading sensor characteristics according to the communication channel configuration data to obtain sensor characteristic data; Step S24: calibrating parameters according to the sensor characteristic data to obtain calibration parameter data; Step S25: performing gain adjustment on the parameter calibration data to obtain optimized gain value data; Step S26: Initialize parameters according to the optimized gain value data to obtain sensor initial configuration data.

4. The method according to claim 1, characterized in that: Step S3 is specifically as follows: Step S31: performing sensor parameter fitting according to the sensor digital twin model and the sensor initial configuration data to obtain a sensor fitting model; Step S32: performing noise simulation on the sensor fitting model to obtain noise interference data; Step S33: simulating the usage scenario according to the sensor fitting model and the noise interference data to obtain sensor simulation data.

5. The method according to claim 1, characterized in that Step S4 is specifically as follows: Step S41: obtaining sensor usage target data; Step S42: performing qualified parameter mapping according to the sensor usage target data to obtain sensor qualified parameter data; Step S43: Perform in-depth performance evaluation based on the sensor qualified parameter data and the sensor simulation data to obtain sensor detection data.

6. A sensor detection system, characterized in that: For executing the sensor detection method according to claim 1, the sensor detection system comprises: The sensor digital twin model construction module is used to collect the geometric, mechanical and electrical parameters of the sensor installation environment in real time and build the sensor digital twin model; The sensor initial configuration module is used to automatically identify and initialize sensor parameters through the local area network according to the edge computing device to obtain the sensor initial configuration data; A sensor simulation module is used to generate sensor simulation data based on the sensor digital twin model and the sensor initial configuration data; The performance detection and evaluation module is used to perform performance detection and evaluation based on the sensor simulation data to obtain sensor detection data.

Images