Complex environment thermal temperature dynamic monitoring and metering system fusing digital twinborn technology
By deploying distributed sensors and digital twin modeling technology in complex environments, the problems of insufficient spatiotemporal resolution, low fusion of multi-source data, and dynamic error accumulation in traditional temperature monitoring systems are solved, achieving high-precision, real-time temperature monitoring and measurement, and supporting decision support in complex environments.
Patent Information
- Application Number
- CN202511311006.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-09-15
- Publication Date
- 2026-01-09
AI Technical Summary
Traditional temperature monitoring technologies suffer from insufficient spatiotemporal resolution, low fusion of multi-source data, accumulation of dynamic errors, and lack of visualization and prediction capabilities in complex environments. Existing fused digital twin systems suffer from low modeling accuracy, inaccurate mapping of thermal characteristics, and large virtual-real synchronization delays.
A physical sensing layer is constructed using a distributed fiber optic grating sensor array, an infrared thermal imaging module, and miniature wireless temperature nodes. Combined with geometric modeling and thermal property mapping of the digital twin modeling layer, high-precision temperature measurement of the dynamic measurement layer is achieved through spatiotemporal feature extraction and multi-source data fusion. Application interaction is achieved through adaptive calibration and a visualization platform.
It achieves high-precision temperature measurement, with spatial resolution improved to 0.1m, time response rate reaching 10kHz, virtual mirror and physical environment synchronization delay less than 10ms, and measurement accuracy reaching ±0.05℃, supporting real-time monitoring and decision support in complex environments.
Smart Images
Figure CN121298048A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of thermal monitoring and measurement technology, specifically to a dynamic monitoring and measurement system for thermal temperature in complex environments that integrates digital twin technology. Background Technology
[0002] In complex environments, dynamic temperature monitoring and accurate measurement are crucial for industrial production safety, energy optimization, and equipment maintenance. Traditional temperature monitoring technologies suffer from the following significant drawbacks:
[0003] Insufficient spatiotemporal resolution: Sensor networks using single points or sparsely distributed points are difficult to capture the three-dimensional distribution and dynamic changes of temperature fields in complex environments. Spatial resolution is usually limited to 1-5m, and time response delay is >100ms, which cannot meet the requirements of high dynamic scenarios.
[0004] Low fusion of multi-source data: Measurement data from different types of sensors (such as thermocouples, infrared thermometers, and fiber optic sensors) are heterogeneous. Traditional fusion methods only perform simple weighted averaging without considering the spatiotemporal correlation of the temperature field, resulting in large errors in the fusion results (usually > ±0.5℃).
[0005] Dynamic error accumulation: Electromagnetic interference, vibration, and temperature and humidity changes in complex environments can cause sensor drift. Traditional static calibration methods (such as periodic offline calibration) cannot compensate for dynamic errors in real time, and the measurement accuracy decreases by more than 30% after long-term operation.
[0006] Lack of visualization and prediction capabilities: Traditional systems mostly display monitoring results in the form of numerical tables, which cannot intuitively present the temperature field distribution; and they can only monitor passively, and cannot predict temperature change trends based on historical data and current conditions, making it difficult to support proactive decision-making.
[0007] However, existing temperature monitoring systems that integrate digital twins still suffer from problems such as low modeling accuracy (geometric error >1%), inaccurate mapping of thermal characteristics, and large virtual-real synchronization delay (>50ms). To address these issues, a dynamic monitoring and measurement system for thermal temperature in complex environments that integrates digital twin technology is proposed. Summary of the Invention
[0008] In view of this, the present invention provides a dynamic monitoring and measurement system for thermal temperature in complex environments that integrates digital twin technology, in order to solve or alleviate the technical problems existing in the prior art, and at least provide a beneficial option.
[0009] The technical solution of this invention is implemented as follows: a dynamic monitoring and measurement system for thermal temperature in complex environments that integrates digital twin technology, comprising a physical sensing layer, a digital twin modeling layer, a data fusion layer, a dynamic measurement layer, and an application interaction layer;
[0010] The physical sensing layer includes a distributed fiber optic sensor array, an infrared thermal imaging module, and a miniature wireless temperature node, used to collect multi-dimensional temperature data in complex environments.
[0011] The digital twin modeling layer includes a geometric modeling engine, a thermal property mapping module, and a real-time rendering engine, which are used to construct a virtual thermal image that is synchronized with the physical environment in real time.
[0012] The data fusion layer includes a spatiotemporal feature extraction module, an anomaly detection unit, and a multi-source data fusion network, which are used to process multimodal sensor data and extract key thermal features.
[0013] The dynamic metrology layer includes a dynamic compensation algorithm module, an adaptive calibration unit, and a metrology traceability engine, which are used to achieve high-precision temperature metrology and error correction.
[0014] The application interaction layer includes a 3D visualization platform, a data interface module, and a decision support system, which are used for user interaction and application of monitoring results.
[0015] Further preferably, the distributed fiber optic grating sensor array adopts a π-type layout, with one sensing point every 0.5m along the X, Y, and Z axes in three-dimensional space, a wavelength drift of 1525-1565nm, a temperature measurement range of -50℃ to 1200℃, and a resolution of 0.01℃; the infrared thermal imaging module has an infrared detector with a resolution of 1280×1024, a frame rate of 50Hz, a temperature measurement range of -20℃ to 1500℃, and a spatial resolution of 1mrad; the miniature wireless temperature node uses the LoRaWAN protocol for communication, has an adjustable sampling frequency of 1-10kHz, a built-in MEMS temperature sensor, and a measurement accuracy of ±0.1℃.
[0016] More preferably, the virtual thermal image constructed by the digital twin modeling layer satisfies the following characteristics:
[0017] The 3D dimensional error between the geometric model and the physical environment is <0.1%;
[0018] The thermal parameter mapping includes the spatiotemporal distribution of thermal conductivity λ(x,y,z,t), specific heat capacity c(x,y,z,t), and density ρ(x,y,z,t);
[0019] In terms of real-time performance, the synchronization latency between the virtual image and the physical environment is <10ms;
[0020] Dynamic evolution is achieved using a coupled equation of heat flow field and temperature field, wherein the coupled equation is:
[0021]
[0022] Where T(x,y,z,t) is the temperature at position (x,y,z) at time t, α=λ / (ρc) is the thermal diffusivity, and Q(x,y,z,t) is the heat source intensity. For the Laplace operator.
[0023] More preferably, the multi-source data fusion network is an improved spatiotemporal attention fusion network, comprising: a temporal attention module: extracting the temporal dependence features of the temperature sequence through a gated recurrent unit (GRU); and a spatial attention module: capturing spatial correlation features using a graph convolutional network (GCN).
[0024] More preferably, the dynamic compensation algorithm module adopts a dynamic error compensation model based on Kalman filtering, and the compensation formula is: in, The compensated temperature estimate is T_m(k), the sensor measurement is T_d(k), the digital twin model prediction is T_d(k), K(k) is the Kalman gain, and H(k) is the observation matrix.
[0025] More preferably, the adaptive calibration unit employs an online dual-frequency calibration method, which involves introducing a standard blackbody radiation source (emissivity ε = 0.995) and performing calibration in real time during system operation.
[0026] High-frequency calibration: Perform a rapid calibration every 10 minutes to correct the drift error ΔT_drift;
[0027] Low-frequency calibration: A comprehensive calibration is performed every 24 hours to correct the system error ΔT_system;
[0028] The total calibration error ΔT_calib = ΔT_drift + ΔT_system, and the system metrological accuracy after calibration reaches ±0.05℃.
[0029] More preferably, the metrological traceability engine establishes a complete traceability chain from sensor measurements to the national temperature benchmark, satisfying the formula:
[0030] T_measured=T_true+ΣΔT_i+ε;
[0031] Where T_true is the true temperature, ΣΔT_i is the sum of all errors (including sensor error, environmental interference error, and transmission error), and ε is the random error that satisfies ε~N(0,σ) 2 ), σ<0.02℃.
[0032] A method for monitoring temperature in complex environments includes the following steps:
[0033] Physical layer deployment: Install fiber optic grating sensor arrays, infrared thermal imaging modules, and wireless temperature nodes in a π-shaped layout in complex environments to build a multi-dimensional sensing network;
[0034] Twin model construction: A three-dimensional point cloud of the environment is acquired by laser scanning, a geometric model is constructed, and a digital twin model of the coupled heat flow field and temperature field is established by combining the thermal parameters of the materials with the initial temperature distribution.
[0035] Real-time data acquisition: Simultaneously acquire wavelength signals from fiber optic sensors, infrared thermal image data, and temperature values from wireless nodes, and preprocess them through edge computing nodes;
[0036] Data fusion processing: A spatiotemporal attention fusion network is used to fuse multi-source data, extract spatiotemporal features, and perform anomaly detection;
[0037] Dynamic metrology and calibration: Real-time metrology and calibration are achieved by using Kalman filtering for dynamic error compensation and combining it with online dual-frequency calibration.
[0038] Visualization and Application: Display the dynamic distribution of the temperature field on a 3D visualization platform and provide temperature control suggestions through a decision support system.
[0039] The embodiments of the present invention have the following advantages due to the adoption of the above technical solutions:
[0040] I. This invention achieves a measurement accuracy of ±0.05℃ through digital twin modeling of heat flow-temperature coupling and Kalman dynamic compensation, solving the problem of error accumulation in complex environments and improving accuracy by more than 90% compared to traditional systems. The π-type sensing layout and STA-Fusion fusion network achieve a spatial resolution of 0.1m and a time response rate of 10kHz, which can capture small temperature gradients and rapid changes, providing fine data for thermal analysis.
[0041] Second, this invention constructs a virtual thermal image with a synchronization delay of <10ms with the physical environment. Combined with three-dimensional visualization technology, it intuitively presents the temperature field distribution, solving the problem of "lots of data but little insight" in traditional systems. Adaptive dual-frequency calibration and a complete traceability chain ensure the reliability and legality of measurement results, meeting the stringent requirements of industrial metrology and scientific research.
[0042] The above overview is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of the invention will become readily apparent from the accompanying drawings and the following detailed description. Attached Figure Description
[0043] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0044] Figure 1 This is a system flowchart of the present invention;
[0045] Figure 2 This is a flowchart of the dynamic metering layer of the present invention. Detailed Implementation
[0046] In the following description, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments can be modified in various ways without departing from the spirit or scope of the invention. Therefore, the drawings and description are considered to be exemplary in nature and not restrictive.
[0047] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.
[0048] like Figure 1-2 As shown, this embodiment of the invention provides a dynamic monitoring and measurement system for thermal temperature in complex environments that integrates digital twin technology, including a physical sensing layer, a digital twin modeling layer, a data fusion layer, a dynamic measurement layer, and an application interaction layer;
[0049] The physical sensing layer includes a distributed fiber Bragg grating sensor array, an infrared thermal imaging module, and miniature wireless temperature nodes, used to collect multi-dimensional temperature data in complex environments.
[0050] The digital twin modeling layer includes a geometric modeling engine, a thermal property mapping module, and a real-time rendering engine, which are used to build a virtual thermal image that is synchronized with the physical environment in real time.
[0051] The data fusion layer includes a spatiotemporal feature extraction module, an anomaly detection unit, and a multi-source data fusion network, which are used to process multimodal sensor data and extract key thermal features.
[0052] The dynamic metrology layer includes a dynamic compensation algorithm module, an adaptive calibration unit, and a metrology traceability engine, which are used to achieve high-precision temperature metrology and error correction.
[0053] The application interaction layer includes a 3D visualization platform, a data interface module, and a decision support system, which are used for user interaction and application of monitoring results.
[0054] In one embodiment, the distributed fiber Bragg grating sensor array adopts a π-type layout, with a sensing point every 0.5m along the X, Y, and Z axes in three-dimensional space. The wavelength drift is 1525-1565nm, the temperature measurement range is -50℃ to 1200℃, and the resolution is 0.01℃. The infrared thermal imaging module has an infrared detector with a resolution of 1280×1024, a frame rate of 50Hz, a temperature measurement range of -20℃ to 1500℃, and a spatial resolution of 1mrad. The miniature wireless temperature node uses the LoRaWAN protocol for communication, has an adjustable sampling frequency of 1-10kHz, a built-in MEMS temperature sensor, and a measurement accuracy of ±0.1℃.
[0055] In one embodiment, the virtual thermal image constructed by the digital twin modeling layer satisfies the following characteristics:
[0056] The 3D dimensional error between the geometric model and the physical environment is <0.1%;
[0057] The thermal parameter mapping includes the spatiotemporal distribution of thermal conductivity λ(x,y,z,t), specific heat capacity c(x,y,z,t), and density ρ(x,y,z,t);
[0058] In terms of real-time performance, the synchronization latency between the virtual image and the physical environment is <10ms;
[0059] Dynamic evolution is achieved using a coupled equation of heat flow field and temperature field. The coupled equation is as follows:
[0060]
[0061] Where T(x,y,z,t) is the temperature at position (x,y,z) at time t, α=λ / (ρc) is the thermal diffusivity, and Q(x,y,z,t) is the heat source intensity. For the Laplace operator.
[0062] In one embodiment, the multi-source data fusion network is an improved spatiotemporal attention fusion network, comprising: a temporal attention module that extracts the temporal dependence features of the temperature sequence through a gated recurrent unit (GRU), and a spatial attention module that captures spatial correlation features using a graph convolutional network (GCN).
[0063] In one embodiment, the dynamic compensation algorithm module adopts a dynamic error compensation model based on Kalman filtering, and the compensation formula is as follows: in, The compensated temperature estimate is T_m(k), the sensor measurement is T_d(k), the digital twin model prediction is T_d(k), K(k) is the Kalman gain, and H(k) is the observation matrix.
[0064] In one embodiment, the adaptive calibration unit employs an online dual-frequency calibration method, which involves introducing a standard blackbody radiation source (emissivity ε = 0.995) and performing calibration in real time during system operation.
[0065] High-frequency calibration: Perform a rapid calibration every 10 minutes to correct the drift error ΔT_drift;
[0066] Low-frequency calibration: A comprehensive calibration is performed every 24 hours to correct the system error ΔT_system;
[0067] The total calibration error ΔT_calib = ΔT_drift + ΔT_system, and the system metrological accuracy after calibration reaches ±0.05℃.
[0068] In one embodiment, the metrology traceability engine establishes a complete traceability chain from sensor measurements to national temperature benchmarks, satisfying the formula:
[0069] T_measured=T_true+ΣΔT_i+ε;
[0070] Where T_true is the true temperature, ΣΔT_i is the sum of all errors (including sensor error, environmental interference error, and transmission error), and ε is the random error that satisfies ε~N(0,σ) 2 ), σ<0.02℃.
[0071] A method for monitoring temperature in complex environments includes the following steps:
[0072] Physical layer deployment: Install fiber optic grating sensor arrays, infrared thermal imaging modules, and wireless temperature nodes in a π-shaped layout in complex environments to build a multi-dimensional sensing network;
[0073] Twin model construction: A three-dimensional point cloud of the environment is acquired by laser scanning, a geometric model is constructed, and a digital twin model of the coupled heat flow field and temperature field is established by combining the thermal parameters of the materials with the initial temperature distribution.
[0074] Real-time data acquisition: Simultaneously acquire wavelength signals from fiber optic sensors, infrared thermal image data, and temperature values from wireless nodes, and preprocess them through edge computing nodes;
[0075] Data fusion processing: A spatiotemporal attention fusion network is used to fuse multi-source data, extract spatiotemporal features, and perform anomaly detection;
[0076] Dynamic metrology and calibration: Real-time metrology and calibration are achieved by using Kalman filtering for dynamic error compensation and combining it with online dual-frequency calibration.
[0077] Visualization and Application: Display the dynamic distribution of the temperature field on a 3D visualization platform and provide temperature control suggestions through a decision support system.
[0078] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various variations or substitutions within the technical scope disclosed in the present invention, and these should all be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.
Claims
1. A dynamic monitoring and measurement system for thermal temperature in complex environments integrating digital twin technology, characterized in that: It includes a physical perception layer, a digital twin modeling layer, a data fusion layer, a dynamic measurement layer, and an application interaction layer; The physical sensing layer includes a distributed fiber optic sensor array, an infrared thermal imaging module, and a miniature wireless temperature node, used to collect multi-dimensional temperature data in complex environments. The digital twin modeling layer includes a geometric modeling engine, a thermal property mapping module, and a real-time rendering engine, which are used to construct a virtual thermal image that is synchronized with the physical environment in real time. The data fusion layer includes a spatiotemporal feature extraction module, an anomaly detection unit, and a multi-source data fusion network, which are used to process multimodal sensor data and extract key thermal features. The dynamic metrology layer includes a dynamic compensation algorithm module, an adaptive calibration unit, and a metrology traceability engine, which are used to achieve high-precision temperature metrology and error correction. The application interaction layer includes a 3D visualization platform, a data interface module, and a decision support system, which are used for user interaction and application of monitoring results.
2. The complex environment thermal temperature dynamic monitoring and measurement system integrating digital twin technology according to claim 1, characterized in that: The distributed fiber Bragg grating sensor array adopts a π-type layout, with a sensing point every 0.5m along the X, Y, and Z axes in three-dimensional space. The wavelength drift is 1525-1565nm, the temperature measurement range is -50℃ to 1200℃, and the resolution is 0.01℃. The infrared thermal imaging module has an infrared detector with a resolution of 1280×1024, a frame rate of 50Hz, a temperature measurement range of -20℃ to 1500℃, and a spatial resolution of 1mrad. The miniature wireless temperature node uses the LoRaWAN protocol for communication, has an adjustable sampling frequency of 1-10kHz, a built-in MEMS temperature sensor, and a measurement accuracy of ±0.1℃.
3. The complex environment thermal temperature dynamic monitoring and measurement system integrating digital twin technology according to claim 1, characterized in that: The virtual thermal image constructed by the digital twin modeling layer satisfies the following characteristics: The 3D dimensional error between the geometric model and the physical environment is <0.1%; The thermal parameter mapping includes the spatiotemporal distribution of thermal conductivity λ(x,y,z,t), specific heat capacity c(x,y,z,t), and density ρ(x,y,z,t); In terms of real-time performance, the synchronization latency between the virtual image and the physical environment is <10ms; Dynamic evolution is achieved using a coupled equation of heat flow field and temperature field, wherein the coupled equation is: Where T(x,y,z,t) is the temperature at position (x,y,z) at time t, α=λ / (ρc) is the thermal diffusivity, and Q(x,y,z,t) is the heat source intensity. For the Laplace operator.
4. The complex environment thermal temperature dynamic monitoring and measurement system integrating digital twin technology according to claim 1, characterized in that: The multi-source data fusion network is an improved spatiotemporal attention fusion network, including: a temporal attention module: extracting the temporal dependence features of the temperature sequence through a gated recurrent unit (GRU); and a spatial attention module: capturing spatial correlation features using a graph convolutional network (GCN).
5. The complex environment thermal temperature dynamic monitoring and measurement system integrating digital twin technology according to claim 1, characterized in that: The dynamic compensation algorithm module adopts a dynamic error compensation model based on Kalman filtering, and the compensation formula is as follows: in, The compensated temperature estimate is T_m(k), the sensor measurement is T_d(k), the digital twin model prediction is T_d(k), K(k) is the Kalman gain, and H(k) is the observation matrix.
6. The complex environment thermal temperature dynamic monitoring and measurement system integrating digital twin technology according to claim 1, characterized in that: The adaptive calibration unit employs an online dual-frequency calibration method, which involves introducing a standard blackbody radiation source (emissivity ε = 0.995) and performing calibration in real time during system operation. High-frequency calibration: Perform a rapid calibration every 10 minutes to correct the drift error ΔT_drift; Low-frequency calibration: A comprehensive calibration is performed every 24 hours to correct the system error ΔT_system; The total calibration error ΔT_calib = ΔT_drift + ΔT_system, and the system metrological accuracy after calibration reaches ±0.05℃.
7. The complex environment thermal temperature dynamic monitoring and measurement system integrating digital twin technology according to claim 1, characterized in that: The metrological traceability engine establishes a complete traceability chain from sensor measurements to national temperature standards, satisfying the formula: T_measured=T_true+ΣΔT_i+ε; Where T_true is the true temperature, ΣΔT_i is the sum of all errors (including sensor error, environmental interference error, and transmission error), and ε is the random error that satisfies ε~N(0,σ) 2 ), σ<0.02℃.
8. A method for monitoring complex environmental temperature using a complex environmental thermal temperature dynamic monitoring and measurement system incorporating digital twin technology as described in any one of claims 1-7, characterized in that, Includes the following steps: Physical layer deployment: Install fiber optic grating sensor arrays, infrared thermal imaging modules, and wireless temperature nodes in a π-shaped layout in complex environments to build a multi-dimensional sensing network; Twin model construction: A three-dimensional point cloud of the environment is acquired by laser scanning, a geometric model is constructed, and a digital twin model of the coupled heat flow field and temperature field is established by combining the thermal parameters of the materials with the initial temperature distribution. Real-time data acquisition: Simultaneously acquire wavelength signals from fiber optic sensors, infrared thermal image data, and temperature values from wireless nodes, and preprocess them through edge computing nodes; Data fusion processing: A spatiotemporal attention fusion network is used to fuse multi-source data, extract spatiotemporal features, and perform anomaly detection; Dynamic metrology and calibration: Real-time metrology and calibration are achieved by using Kalman filtering for dynamic error compensation and combining it with online dual-frequency calibration. Visualization and Application: Display the dynamic distribution of the temperature field on a 3D visualization platform and provide temperature control suggestions through a decision support system.