Thermal imaging monitoring system based on digital twinning

Abstract

The invention relates to the technical field of computer-aided monitoring and simulation, in particular to a thermal imaging monitoring system based on digital twinning, which comprises a sensing and edge calculation module used for acquiring a temperature matrix from a thermal imaging sensor and calculating the temperature matrix to obtain a regional-level thermal instability index; the data processing module is also used for judging a risk level corresponding to the regional-level thermal instability index, and generating a thermal anomaly feature vector when the risk level is greater than a preset normal level; and the twinborn platform quick response module is used for receiving the thermal anomaly feature vector, positioning virtual assets in the digital twinborn scene according to the thermal anomaly feature vector, and then executing a hierarchical response decision on the virtual assets according to a risk level in the thermal anomaly feature vector. And the method is converted into an autonomous safety guarantee capability with perspectiveness and instantaneity.

Description

Technical Field

[0001] The present invention relates to the field of computer-aided monitoring and simulation technology, and in particular to a thermal imaging monitoring system based on digital twins. Background Art

[0002] Digital twin technology monitors and optimizes the entire life cycle of the physical world by building virtual images of physical entities. In the field of security monitoring, digital twin systems combined with thermal imaging sensors are used for fire warning. Existing technical solutions generally follow the process of perception-transmission-analysis-decision-making, transmitting thermal imaging video streams to a central server for analysis. This process has problems such as data transmission redundancy, central computing bottlenecks, and decision logic lags, resulting in a system reaction time of generally seconds (about 10 seconds) from the discovery of an anomaly to the triggering of a response. 3 ms), for sudden and sudden dangers such as electrical fires, this delay will miss the best opportunity for intervention. Therefore, this field urgently needs a method that can compress the response time to milliseconds (about 10 2 ms) to achieve heat-reflective safety protection that is almost biologically instinctive. Summary of the Invention

[0003] The purpose of the present invention is to provide a thermal imaging monitoring system based on digital twins to solve the problems existing in the background technology.

[0004] To solve the above technical problems, the present invention provides a thermal imaging monitoring system based on digital twins, comprising: The perception and edge computing module is used to obtain the temperature matrix from the thermal imaging sensor and calculate the temperature matrix to obtain the regional thermal instability index. It is also used to determine the risk level corresponding to the regional thermal instability index and generate a thermal anomaly feature vector when the risk level is greater than the preset normal level. The twin platform's rapid response module is used to receive thermal anomaly feature vectors and locate virtual assets in the digital twin scenario based on the thermal anomaly feature vectors. It then makes graded response decisions on virtual assets based on the risk level in the thermal anomaly feature vectors.

[0005] Preferably, the process of calculating the regional thermal instability index by the perception and edge computing module is as follows: For each pixel in the temperature matrix, the pixel-level thermal instability index is calculated; and for a preset region of interest, the maximum value of the pixel-level thermal instability index of all pixels in the region is taken to determine the regional-level thermal instability index.

[0006] Preferably, the pixel-level thermal instability index is a comprehensive risk index obtained by performing a weighted linear combination of the following physical quantities: Absolute temperature from the temperature matrix; The temperature time change rate is calculated by using the forward difference method on the historical temperature; And the temperature spatial gradient modulus is obtained by calculating the single frame temperature matrix using the image processing gradient operator.

[0007] Preferably, the risk level determination process is as follows: Compare the regional thermal instability index with pre-set concern thresholds, warning thresholds, and critical thresholds; If the regional thermal instability index is greater than the critical threshold, the risk level is determined to be critical; If the regional thermal instability index is less than or equal to the critical threshold and greater than the warning threshold, the risk level is determined to be warning; If the regional thermal instability index is less than or equal to the warning threshold and greater than the concern threshold, the risk level is determined to be concern; If the regional thermal instability index is less than or equal to the attention threshold, the risk level is judged to be normal.

[0008] Preferably, the process of generating the thermal anomaly feature vector is as follows: Obtain sensor IDs, anomaly coordinates, and event timestamps for addressing in the digital twin scenario; combine risk level, regional thermal instability index, absolute temperature when the alarm is triggered, temperature time rate of change, and temperature spatial gradient modulus; To generate thermal anomaly feature vector.

[0009] Preferably, the hierarchical response decision includes: If the risk level is "concern", the virtual assets will be highlighted in the twin model and the data refresh rate will be increased; If the risk level is warning, the response of the attention level is executed and the alarm information is pushed to the operation and maintenance platform; If the risk level is critical, autonomous safety procedures are triggered.

[0010] Preferably, the execution process of the autonomous safety regulations is as follows: Switch the state of the virtual asset to the preset emergency shutdown or electrical isolation state; call the lightweight simulation model, use the absolute temperature, temperature time change rate and temperature spatial gradient modulus in the thermal anomaly feature vector as initial conditions, and deduce the abnormal development trend; based on the deduction results, issue control instructions to the actuators in the physical world.

[0011] Compared with the prior art, the present invention has the following beneficial effects: (1) The response speed is improved by an order of magnitude. By setting up the perception and edge computing modules, the temperature matrix is ​​analyzed instantly at the data source, and only when the risk level is determined to exceed the normal state, the byte-level thermal anomaly feature vector is generated for transmission, avoiding the delay of massive data transmission, so that the twin platform rapid response module can receive the risk signal almost synchronously; ultimately, the end-to-end time from the occurrence of physical anomaly to the execution of graded response decision in the digital twin world is compressed from seconds to milliseconds, which wins a key intervention window for defending against instantaneous sudden dangers such as electrical fires, and improves the safety level.

[0012] (2) The intelligence and precision of decision-making have reached a new level. The thermal instability index model introduced converts isolated physical quantities into a dynamic, multi-dimensional risk insight. The model not only considers the current value of the absolute temperature, but also incorporates the temperature time change rate reflecting the warming trend and the temperature spatial gradient modulus characterizing the concentration of hot spots. This shift from state monitoring to trend prediction enables the system to identify potential risks earlier; the execution of autonomous safety regulations is carried out by calling a lightweight simulation model and using the real-time physical parameters in the thermal anomaly feature vector as the initial conditions for deduction, ensuring that the control instructions finally issued to the physical actuator are optimized for the current specific abnormal scenario. Therefore, the decision-making has both speed and accuracy.

[0013] (3) The system resource efficiency and scalability are greatly optimized, and the continuous transmission of the original video stream is transformed into a lightweight thermal anomaly feature vector that is transmitted only when an anomaly occurs. This greatly saves network bandwidth and reduces the dependence on high-specification network infrastructure. The computing load is shared from a single central server to distributed perception and edge computing modules, which not only reduces the processing pressure of the central platform, but also makes the entire monitoring system more scalable and can smoothly access more monitoring points without causing performance bottlenecks.

[0014] (4) The model has excellent interpretability and environmental adaptability. Based on the statistical analysis and optimization algorithm solution of the specific scenario data set, the entire decision-making process is logically clear, traceable and verifiable. This transparency and parameterized design enable this solution to flexibly adapt to the background noise of different industrial environments and the protection requirements of different security levels by adjusting the weights and thresholds. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention, and those skilled in the art can derive other drawings based on these drawings without inventive effort. Figure 1 It is a logic block diagram of the system of the present invention; Figure 2 The following is a logic block diagram for calculating the regional thermal instability index according to the present invention; Figure 3 This is a logic block diagram of the comprehensive risk indicator of the present invention; Figure 4 This is a logic block diagram for determining risk level in the present invention. DETAILED DESCRIPTION

[0016] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0017] Example 1 See also Figure 1 The present invention provides a thermal imaging monitoring system based on digital twins, comprising: The perception and edge computing module is used to obtain the temperature matrix from the thermal imaging sensor and calculate the temperature matrix to obtain the regional thermal instability index. It is also used to determine the risk level corresponding to the regional thermal instability index and generate a thermal anomaly feature vector when the risk level is greater than the preset normal level. The twin platform rapid response module is used to receive thermal anomaly feature vectors and locate virtual assets in the digital twin scenario based on the thermal anomaly feature vectors. It then makes graded response decisions for the virtual assets based on the risk level in the thermal anomaly feature vectors. In this embodiment, the thermal imaging monitoring system based on digital twins aims to overcome the data transmission redundancy and central computing bottleneck problems inherent in the perception-transmission-analysis-decision-making link in the existing technology. To achieve this goal, the system pre-places the core analysis capabilities in the perception and edge computing modules at the monitoring site and establishes an efficient edge-center collaboration mechanism. The final technical effect is reflected in: the previously common second-level safety response time is successfully compressed to the millisecond level. This magnitude of speed increase enables the system to intervene in instantaneous dangerous situations such as electrical fires in quasi-real time. Its response mode surpasses the traditional lagging alarm and is transformed into an autonomous safety assurance capability with foresight and immediacy. The overall architecture of the system is optimized, so that the perception and edge computing modules focus on real-time data processing and risk prediction, while the twin platform rapid response module focuses on accurate and hierarchical disposal after receiving lightweight instructions. The two work together to significantly improve the system's resource efficiency and the level of intelligent decision-making.

[0018] Example 2 See also Figure 2 ,The process of calculating the regional thermal instability index by the perception and edge computing module is as follows: For each pixel in the temperature matrix, the pixel-level thermal instability index is calculated; and for a preset region of interest, the maximum value of the pixel-level thermal instability index of all pixels in the region is taken to determine the regional thermal instability index; See also Figure 3 The pixel-level thermal instability index is a comprehensive risk indicator obtained by weighted linear combination of the following physical quantities: Absolute temperature from the temperature matrix; The temperature time change rate is calculated by using the forward difference method on the historical temperature; and the temperature spatial gradient modulus obtained by calculating the temperature matrix of a single frame using the image processing gradient operator; In this embodiment, the core of the risk assessment performed by the perception and edge computing module is to abandon the traditional static temperature threshold judgment and instead adopt a more dynamic predictive and customized thermal instability index. The technical motivation for this design is that a single absolute temperature value cannot effectively distinguish between normal temperature rise and early signs of danger, and a comprehensive risk indicator can provide deeper insights. The internal logic is that the thermal instability index The model's theoretical foundations are based on the first law of thermodynamics and existing theories of critical conditions for thermal runaway in fire science. This invention aims to construct a composite indicator capable of predicting the immediate probability of a disaster by quantifying multiple key physical dimensions strongly associated with the thermal runaway process, namely the absolute value of temperature, the temporal rate of change, and the steepness of the spatial distribution, thereby achieving a shift from passive response to active prediction. Pixel-level thermal instability index Calculated using the following formula: ; in, is the time t and spatial position The dimensionless comprehensive risk score is the final output of the formula, and its value is directly related to the risk level; The absolute temperature is directly derived from the temperature matrix obtained by the edge computing unit from the thermal imaging sensor at time t. The corresponding pixel value in ; The partial derivative of temperature with respect to time, i.e. the temperature time rate of change, is calculated by the edge computing unit in discrete implementation based on the current frame and the previous time step. The temperature difference is approximately calculated using the forward difference method in numerical analysis. The data source is the internal cache and calculation of the continuously collected temperature data by the unit. is the spatial gradient of temperature, and its mode length Reflects the degree of temperature difference between the hotspot and the surrounding environment. This parameter is calculated by the edge computing unit using a standard image processing gradient operator, such as the Sobel operator, on a single-frame temperature matrix. are dimensionless weight coefficients, and their sum is always 1. Their specific values ​​are obtained by offline training on historical or simulation data sets containing normal and various fault scenarios, and by iteratively solving them using algorithms such as grid search with the optimization goal of maximizing the early detection rate and minimizing the false alarm rate. is the maximum and minimum normalized function, and its mathematical expression is , the function is to uniformly map input parameters with different physical dimensions, such as temperature (K), temperature time change rate (K / s) and temperature spatial gradient modulus (K / m), to The dimensionless value in the interval ensures the consistency of the physical dimensions on both sides of the formula, where the parameters corresponding to each physical quantity are and It is obtained by collecting baseline data for a specific monitoring scenario under normal working conditions for a sufficiently long period of time and then statistically analyzing it; In the actual deployment of the technical solution, the perception and edge computing module first calculates the temperature matrix Calculate the pixel-level thermal instability index for each pixel in ; Then, according to the monitoring requirements, for example, for a specific device or a key line connection point, the kth region of interest pre-set by those skilled in the art , its regional thermal instability index By executing The direct technical effect of using the aggregation logic of taking the maximum value rather than the average value is to ensure the highest sensitivity of the monitoring system to the most dangerous points in the monitoring area, effectively avoiding the possibility of missing key risk signals due to data smoothing or dilution; this series of calculations enables the system to make accurate judgments based on an interpretable and multi-dimensional quantitative indicator, greatly improving the intelligence and accuracy of decision-making.

[0019] Example 3 See also Figure 4 , the risk level determination process is as follows: Compare the regional thermal instability index with pre-set concern thresholds, warning thresholds, and critical thresholds; If the regional thermal instability index is greater than the critical threshold, the risk level is determined to be critical; If the regional thermal instability index is less than or equal to the critical threshold and greater than the warning threshold, the risk level is determined to be warning; If the regional thermal instability index is less than or equal to the warning threshold and greater than the concern threshold, the risk level is determined to be concern; If the regional thermal instability index is less than or equal to the concern threshold, the risk level is judged to be normal; In this embodiment, the risk level determination logic is to convert the continuous regional thermal instability index calculated in the above steps into Values ​​are mapped to discrete risk levels with clear operational instructions This process constitutes the key bridge from risk quantification to decision-making; its decision logic follows the following rules: ;

[0020] when When the level is determined to be level 3, it is critical; when When the level is judged as Level 2, it is a warning; when When the level is judged as level 1, it is a concern; when When , the level is 0, which is normal; A key implementation detail is that the threshold The setting of is not arbitrary, but has a scientific calibration source; to ensure the feasibility of the threshold, technical personnel need to use a labeled data set containing multiple scenarios in the offline stage, analyze the receiver operating characteristic curve (ROC curve), and scientifically set it according to the specific requirements of sensitivity and specificity for different security levels; the technical contribution of this hierarchical processing mechanism is that it makes the risk response strategy no longer single and extensive, but realizes refined hierarchical management, which can mobilize resources at the corresponding level according to the severity of the risk, avoid unnecessary system interference and alarm fatigue of operation and maintenance personnel, and make decision-making more accurate and efficient.

[0021] Example 4 The process of generating thermal anomaly feature vectors is as follows: Obtain sensor IDs, anomaly coordinates, and event timestamps for addressing in the digital twin scenario; combine risk level, regional thermal instability index, absolute temperature when the alarm is triggered, temperature time rate of change, and temperature spatial gradient modulus; To generate thermal anomaly feature vector; In this embodiment, once the risk level If it is judged to be greater than 0, the core task of the perception and edge computing module switches to generating a highly structured and information-condensed thermal anomaly feature vector This vector is the fundamental carrier for the present invention to achieve low-latency communication and accurate response; its composition is as follows: ;

[0022] Each parameter in the vector has a clear origin and purpose: They are the unique sensor identifier, the coordinates of the anomaly point in the monitoring matrix, and the precise timestamp of the event. These are derived from the edge computing unit's own configuration information and system clock. Together, they constitute the key index for spatial and temporal addressing in the digital twin platform. The risk level determined by the aforementioned logical relationship serves as the direct basis for subsequent graded response decisions; This set of parameters is a snapshot of the core physical quantities at the moment the alarm is triggered. They are derived from the calculation process of the thermal instability index and will serve as the initial conditions for the subsequent simulation deduction in the twin body's refined response. Based on this design, the direct technical consequence is that the data that needs to be transmitted is sharply reduced from MB-level thermal imaging video streams containing massive redundant information to B-level feature vectors of only dozens of bytes; data compression at this order of magnitude fundamentally eliminates the network transmission bottleneck, is one of the core prerequisites for achieving millisecond-level response, and greatly saves network bandwidth resources.

[0023] Example 5 Tiered response decisions include: If the risk level is "concern", the virtual assets will be highlighted in the twin model and the data refresh rate will be increased; If the risk level is warning, the response of the attention level is executed and the alarm information is pushed to the operation and maintenance platform; If the risk level is critical, the autonomous safety procedures are triggered; According to the thermal imaging monitoring system based on digital twins described in the above solution, the execution process of the autonomous safety regulations is as follows: Switch the virtual asset to a preset emergency shutdown or electrical isolation state. Invoke a lightweight simulation model, using the absolute temperature, temperature time rate of change, and temperature spatial gradient modulus in the thermal anomaly feature vector as initial conditions to deduce the anomaly development trend. Based on the deduction results, issue control instructions to the physical actuators. In this embodiment, the twin platform rapid response module receives the thermal anomaly feature vector Immediately initiate a Strictly bound hierarchical response decision process; if If it is level 1 attention, the virtual asset corresponding to the abnormal point will be highlighted in the twin model, and its data refresh frequency will be increased for closer observation. This level will not trigger intervention actions in the physical world. For a Level 2 warning, in addition to executing a Level 1 response, the system will automatically push a general alarm message to the operation and maintenance platform to notify relevant personnel to pay attention; When the system faces the most urgent situation, that is, When the emergency reaches level 3, the highest priority autonomous safety procedure will be triggered. This procedure is a set of pre-programmed procedures designed to achieve rapid intervention. The execution process of this procedure demonstrates the technical core of the system's rapid closed-loop response: First, the system After locating the virtual asset using the addressing information in the system, the system immediately switches its digital state to a preset safety state such as electrical isolation or emergency shutdown. Next, the system calls a lightweight, localized simulation model bound to the asset and decisively The physical quantity snapshot T carried in , and As the initial condition of the simulation model, the development trend of the thermal anomaly over the next few hundred milliseconds is quickly deduced within a few milliseconds, and the effects of different intervention measures are simulated. Finally, based on the evaluation results of this micro-simulation, the system issues optimized control instructions to the corresponding actuators in the physical world, such as smart switches or solenoid valves, to perform physical intervention. The entire process, from receiving vectors to issuing physical instructions, achieves an end-to-end millisecond-level closed loop, building an intelligent safety protection system that not only responds quickly, but also makes accurate decisions and has autonomous closed-loop capabilities.

[0024] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. A thermal imaging monitoring system based on digital twins, characterized in that: include: The perception and edge computing module is used to obtain the temperature matrix from the thermal imaging sensor and calculate the temperature matrix to obtain the regional thermal instability index; It is also used to determine the risk level corresponding to the regional thermal instability index and generate a thermal anomaly feature vector when the risk level is greater than the preset normal level; The twin platform's rapid response module is used to receive thermal anomaly feature vectors and locate virtual assets in the digital twin scenario based on the thermal anomaly feature vectors. It then makes graded response decisions on virtual assets based on the risk level in the thermal anomaly feature vectors.

2. A thermal imaging monitoring system based on digital twins according to claim 1, characterized in that: The process of calculating the regional thermal instability index by the perception and edge computing module is as follows: For each pixel in the temperature matrix, the pixel-level thermal instability index is calculated; and for a preset region of interest, the maximum value of the pixel-level thermal instability index of all pixels in the region is taken to determine the regional-level thermal instability index.

3. The thermal imaging monitoring system based on digital twin according to claim 2, characterized in that: The pixel-level thermal instability index is a comprehensive risk indicator obtained by performing a weighted linear combination of the following physical quantities: Absolute temperature from the temperature matrix; The temperature time change rate is calculated by using the forward difference method on the historical temperature; And the temperature spatial gradient modulus is obtained by calculating the single frame temperature matrix using the image processing gradient operator.

4. The thermal imaging monitoring system based on digital twin according to claim 1, characterized in that: The risk level determination process is as follows: Compare the regional thermal instability index with pre-set concern thresholds, warning thresholds, and critical thresholds; If the regional thermal instability index is greater than the critical threshold, the risk level is determined to be critical; If the regional thermal instability index is less than or equal to the critical threshold and greater than the warning threshold, the risk level is determined to be warning; If the regional thermal instability index is less than or equal to the warning threshold and greater than the concern threshold, the risk level is determined to be concern; If the regional thermal instability index is less than or equal to the attention threshold, the risk level is judged to be normal.

5. The thermal imaging monitoring system based on digital twin according to claim 1, characterized in that: The process of generating the thermal anomaly feature vector is as follows: Obtain sensor IDs, anomaly coordinates, and event timestamps for addressing in the digital twin scenario; combine risk level, regional thermal instability index, absolute temperature when the alarm is triggered, temperature time rate of change, and temperature spatial gradient modulus; To generate thermal anomaly feature vector.

6. The thermal imaging monitoring system based on digital twin according to claim 1, characterized in that: The hierarchical response decisions include: If the risk level is "concern", the virtual assets will be highlighted in the twin model and the data refresh rate will be increased; If the risk level is warning, the response level of concern is executed and the alarm information is pushed to the operation and maintenance platform; If the risk level is critical, autonomous safety procedures are triggered.

7. The thermal imaging monitoring system based on digital twin according to claim 6, characterized in that: The execution process of the autonomous safety regulations is as follows: Switch the state of the virtual asset to the preset emergency shutdown or electrical isolation state; call the lightweight simulation model, use the absolute temperature, temperature time change rate and temperature spatial gradient modulus in the thermal anomaly feature vector as initial conditions, and deduce the abnormal development trend; based on the deduction results, issue control instructions to the actuators in the physical world.

Images