Infrastructure project safety early warning triggering method based on multistage threshold dynamic adjustment

Abstract

The invention provides an infrastructure project safety early warning triggering method based on multistage threshold dynamic adjustment, and relates to the technical field of infrastructure project intelligent safety risk monitoring, and the method comprises the steps: stripping an environment noise component in an original monitoring signal through an environment interference stripping model, and obtaining a net structure response signal; respectively generating a physical rule-dominated rigid security boundary threshold and a data-driven dynamic risk identification interval threshold, and fusing to obtain a dynamic risk threshold; calculating a real-time risk entropy based on the net structure response signal and the dynamic risk threshold, and determining a risk quantification level according to an interval corresponding to the real-time risk entropy; and determining a decision subject, an execution action and a notification object according to the risk quantification level, and outputting text early warning information to complete safety early warning triggering. According to the invention, continuous, accurate and compliant early warning decision support can be provided for a high-risk construction scene, the false alarm rate is effectively reduced, and the response speed and the progressive dangerous case capture rate are improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent safety risk monitoring technology for infrastructure projects, and in particular to a method for triggering safety early warnings for infrastructure projects based on dynamic adjustment of multi-level thresholds. Background Technology

[0002] As infrastructure projects extend to high-risk scenarios such as tunnel excavation, deep foundation pit support, and construction of super high-rise buildings, the safety risks faced by engineering structures, such as collapse, overturning, and settlement, are becoming increasingly complex. Real-time and accurate safety early warning has become a core requirement for ensuring the safety of construction workers and reducing project losses. This requires safety early warning technology to be able to adapt to harsh construction environments, accurately capture the evolution of risks, and effectively integrate multi-source monitoring data.

[0003] Currently, various products for safety monitoring in infrastructure projects have emerged on the market. Among them, AI visual recognition systems can intuitively monitor structural deformation through optical acquisition and image analysis technology, and are widely used in visualization scenarios such as bridge erection and super high-rise construction. Static threshold alarm terminals rely on sensor data such as GNSS displacement and stress gauges to trigger alarms by preset fixed safety thresholds, providing basic risk warnings for scenarios such as deep foundation pit support and tunnel excavation. In addition, BIM integrated monitoring platforms and multi-source sensor fusion equipment also play a monitoring role under specific working conditions.

[0004] However, these similar products generally suffer from key technical defects. On the one hand, their environmental adaptability is severely insufficient. For example, mainstream AI vision systems rely on optical sensors and lack physical compensation mechanisms, resulting in a high false alarm rate in dust / rain and fog scenarios, making it easy to miss major risks such as deformation of support structures. On the other hand, the continuity of risk assessment is lacking. Current graded alarm systems mostly use fixed threshold triggering mechanisms. Taking a 40mm displacement threshold for foundation pits as an example, a progressive danger of 39.5mm will be ignored, while an instantaneous vibration disturbance of 40.5mm will trigger a false alarm. Inclination monitoring equipment has a high frequency of false triggers per day under wind loads. At the same time, there are also problems of data silos and fusion failures. When existing fusion systems integrate GNSS displacement, vibration sensor, and stress gauge data, the timestamp error of multi-source data is high, leading to causal misjudgment of the peak stress of surrounding rock and vibration of support structures in tunnel monitoring. Moreover, the multi-source data has a high damage rate, making it difficult to meet the requirements of accuracy, continuity, and data validity for early warning in high-risk infrastructure scenarios. Summary of the Invention

[0005] This invention provides a method for triggering safety early warnings for infrastructure projects based on dynamic adjustment of multi-level thresholds. This method can provide continuous, accurate, and compliant early warning decision support for high-risk construction scenarios, effectively reduce false alarm rates, and weaken the dispersion and lag of risk assessment, thereby improving response speed and the rate of gradual hazard capture.

[0006] To achieve the above objectives, the embodiments of the present invention adopt the following technical solutions: Firstly, a method for triggering safety early warnings for infrastructure projects based on dynamic adjustment of multi-level thresholds is provided. The method includes: acquiring the original monitoring signal of the infrastructure project; removing environmental noise components from the original monitoring signal using an environmental interference stripping model to obtain a net structural response signal; the environmental interference stripping model being established based on a preset database of intrinsic parameters of construction materials; generating a rigid safety boundary threshold dominated by physical rules and a data-driven dynamic risk identification interval threshold using a dual-modal risk threshold engine; allocating dynamic weights according to the intensity of environmental fluctuations in the current monitoring scenario; fusing these to obtain a dynamic risk threshold; calculating a real-time risk entropy based on the net structural response signal and the dynamic risk threshold; determining a risk quantification level based on the interval corresponding to the real-time risk entropy; the risk quantification level including levels corresponding to four consecutive intervals, with different risk quantification levels corresponding to different numerical intervals of the real-time risk entropy; determining the decision-making body, the action to be performed, and the notification recipient based on the risk quantification level; and outputting a text warning message, which prompts the decision-making body to perform the action and notifies the notification recipient to complete the safety early warning trigger.

[0007] The method provided by this invention addresses the common shortcomings of existing products, such as insufficient environmental adaptability, lack of continuity in risk assessment, and failure of data fusion, through a comprehensive design that includes environmental noise stripping, dual-modal dynamic thresholding, risk entropy quantification and grading, and responsibility-matching early warning. On one hand, the environmental interference stripping model can remove noise to obtain the net structural response signal, avoiding false alarms and missed detections caused by environmental temperature interference. On the other hand, the dual-modal thresholding combined with dynamic weight fusion overcomes the limitations of fixed thresholds, achieving dynamic and accurate risk identification. Simultaneously, the four-level risk entropy grading and responsibility-matching mechanism ensures the targeted nature and enforceability of the early warning response, ultimately providing real-time and accurate safety warnings for high-risk infrastructure scenarios such as tunnels and deep foundation pits, protecting the lives of construction personnel and reducing project losses.

[0008] In one possible implementation of the first aspect, the intrinsic parameter database of construction materials includes physical property parameters of infrastructure engineering materials, including strain coefficients of infrastructure engineering materials under different temperature conditions, for quantifying the interference effect of temperature fluctuations on monitoring signals.

[0009] The method provided by this invention clearly defines the intrinsic parameter database of construction materials, which includes the strain coefficients of infrastructure engineering materials under different temperature conditions. This parameter is used to quantify the interference effect of temperature fluctuations on monitoring signals, solving the problem that existing monitoring systems lack correlation with material temperature characteristics and cannot quantify environmental interference. By focusing on temperature as the core source of environmental interference, it provides accurate material characteristic support for subsequent environmental interference stripping models, ensuring that the models can calculate interference components based on objective temperature strain coefficients rather than relying on subjective experience. This significantly improves the accuracy of environmental noise stripping, avoids the distortion of monitoring signals caused by temperature fluctuations, and provides a reliable data foundation for subsequent risk assessment.

[0010] In one possible implementation of the first aspect, the step of acquiring the original monitoring signal of the infrastructure project and removing the environmental noise component from the original monitoring signal using an environmental interference stripping model to obtain the net structural response signal includes: acquiring the original monitoring signal of the infrastructure project, wherein the original monitoring signal at least covers structural strain, displacement, vibration, and stress monitoring data; establishing a physical law-driven environmental-signal transfer function based on the temperature strain coefficient in the intrinsic parameter database of the construction materials, and calculating the systematic interference component caused by temperature fluctuations in the original monitoring signal through the environmental-signal transfer function; performing wavelet transform on the original monitoring signal to obtain a frequency domain spectrum, and dividing the noise frequency band of the non-structural response according to the vibration frequency of the construction machinery operation and the turbulence frequency of the airflow disturbance, wherein the frequency range of the noise frequency band matches the characteristic frequency of the interference source; performing energy suppression processing on the noise frequency band using a wavelet packet threshold denoising algorithm, and calculating the high-frequency random noise component corresponding to the noise frequency band; and removing the systematic interference component and the high-frequency random noise component from the original monitoring signal to obtain the net structural response signal.

[0011] The method provided by this invention clearly breaks down the steps of acquiring the original monitoring signal, calculating the systematic temperature interference, dividing the noise frequency band, suppressing high-frequency random noise, and eliminating dual interferences. This solves the problem of vague steps and single-dimensional noise removal in existing environmental interference stripping processes: First, it clarifies that the original monitoring signal covers key data such as strain and displacement, ensuring comprehensive monitoring dimensions; second, it calculates temperature interference through a transfer function driven by physical laws, and combines it with wavelet packet algorithm to suppress high-frequency mechanical / airflow noise, achieving full-dimensional stripping of systematic interferences and random noise; finally, it obtains the net structural response signal through dual interference removal, completely solving the problem of misjudging the true state of the structure due to noise pollution in existing systems, and providing a clean data source for risk assessment.

[0012] In one possible implementation of the first aspect, the environment-signal transfer function is: ; in, β is the systematic interference component caused by temperature fluctuations in the original monitoring signal; γ is the material temperature sensitivity coefficient; t is the environmental influence attenuation coefficient; t is the current monitoring time; t0 is the initial monitoring time; τ is the integral variable; and T is the ambient temperature during the monitoring period.

[0013] The transfer function provided by the method of this invention correlates the material temperature sensitivity coefficient, the environmental influence attenuation coefficient, and temperature change in an integral form. It can dynamically quantify the systematic interference components caused by temperature fluctuations during different monitoring periods, rather than using static estimation. Compared with existing fixed-coefficient denoising, this function can accurately calculate the interference based on real-time temperature changes, further improving the authenticity of the net structural response signal and providing accurate data support for subsequent threshold comparison and risk entropy calculation.

[0014] In one possible implementation of the first aspect, the rigid safety boundary threshold is generated based on the design parameters of the infrastructure project, the material strength limit, and the structural stress verification results. The dynamic risk identification interval threshold is generated by analyzing the clustering characteristics of historical monitoring data of the infrastructure project. The generation of the rigid safety boundary threshold dominated by physical rules and the dynamic risk identification interval threshold driven by data through a dual-modal risk threshold engine includes: calculating the maximum allowable response value of the structure under safe conditions using a finite element analysis model, and using the maximum allowable response value as the rigid safety boundary threshold; performing Gaussian mixture clustering on the normal operating condition data in the historical monitoring data to obtain the distribution interval of the monitoring data under normal operating conditions, and using the upper limit of the distribution interval as the dynamic risk identification interval threshold.

[0015] The method provided by this invention clearly defines the rigid safety boundary threshold as generated based on finite element analysis and the dynamic risk identification interval threshold as generated based on Gaussian mixture clustering. This solves the problems of ambiguous logic and lack of scientific basis in the existing bimodal threshold generation: On the one hand, finite element analysis, combined with design parameters and material strength, ensures that the rigid threshold meets the physical limits of structural safety, avoiding over-warning due to excessively low thresholds or safety hazards due to excessively high thresholds; on the other hand, Gaussian mixture clustering analysis of historical normal working condition data can capture the dynamic change patterns of working conditions, making the dynamic threshold fit the actual construction scenario, rather than relying on fixed empirical values; the bimodal threshold generated by the combination of the two not only meets the physical bottom line of structural safety but also adapts to the dynamic changes of working conditions, laying a scientific foundation for the fusion of dynamic risk thresholds.

[0016] In one possible implementation of the first aspect, the step of allocating dynamic weights based on the intensity of environmental fluctuations in the current monitoring scenario and fusing them to obtain a dynamic risk threshold includes: determining the intensity of environmental fluctuations in the current monitoring scenario using temperature fluctuation data obtained during the environmental interference stripping model processing; when the intensity of environmental fluctuations is less than or equal to a preset threshold, the weight ratio of the rigid safety boundary threshold is greater than the weight ratio of the dynamic risk identification interval threshold; when the intensity of environmental fluctuations is greater than the preset threshold, the weight ratio of the rigid safety boundary threshold is less than or equal to the weight ratio of the dynamic risk identification interval threshold; and performing weighted fusion based on the weight ratios of the rigid safety boundary threshold and the dynamic risk identification interval threshold to obtain the dynamic risk threshold. The formula for determining the dynamic risk threshold is: ; in, For dynamic risk thresholds, As a rigid safety boundary threshold, For dynamic risk identification range thresholds, This represents the weighting percentage of the rigid safety boundary threshold.

[0017] The method provided by this invention distinguishes fluctuation intensity by setting a preset threshold, and realizes adaptive adjustment of low fluctuation with rigid threshold and high fluctuation with dynamic threshold. This avoids the failure of existing fixed weights in extreme environments, and can significantly improve the accuracy and reliability of dynamic risk thresholds, adapting to the risk identification needs under different environmental fluctuations.

[0018] In one possible implementation of the first aspect, the calculation of real-time risk entropy based on the net structural response signal and the dynamic risk threshold includes: comparing the net structural response signal with the dynamic risk threshold to obtain a deviation value, wherein the deviation value reflects the degree of deviation between the current structural response and the safety threshold; constructing a four-level trust assignment function based on DS evidence theory to map the deviation value to the trust level of the corresponding risk level, wherein the trust level is used to quantify the probability that the current structure is at each risk level; The trust level is calculated to obtain the real-time risk entropy; The formula for calculating the real-time risk entropy is: ; in, For real-time risk entropy, Let be the trust level corresponding to the i-th risk level, and =1.

[0019] The method provided by this invention calculates real-time risk entropy through steps of deviation value calculation, DS evidence theory trust allocation, and risk entropy formula operation. This solves the problems of lack of continuity and inability to reflect the ambiguity of existing risk quantification methods: First, the deviation value directly reflects the degree of deviation between the structural response and the safety threshold, providing an intuitive basis for risk quantification; second, the four-level trust allocation of DS evidence theory can quantify the ambiguity of risk; finally, the risk entropy formula transforms risk into a continuous numerical value rather than a discrete level through trust degree calculation, which not only reflects the continuous evolution of risk but also provides a precise quantitative standard for the subsequent four-level classification, ensuring the fineness and accuracy of risk identification.

[0020] In one possible implementation of the first aspect, determining the risk quantification level based on the interval corresponding to the real-time risk entropy includes: when the real-time risk entropy value ranges from 0 to H... r When the risk entropy is less than 1.5, the risk quantification level is determined as the first risk quantification level; when the real-time risk entropy value is within the range of 1.5 ≤ H... r When the value is less than 2.0, the risk quantification level is determined to be the second risk quantification level; when the real-time risk entropy value is within the range of 2.0 ≤ H r When the value is less than 3.0, the risk quantification level is determined to be the third risk quantification level; when the real-time risk entropy value ranges from H... r When the value is ≥3.0, the risk quantification level is determined to be the fourth risk quantification level.

[0021] The method provided by this invention clearly defines the real-time risk entropy value range corresponding to the four-level risk quantification levels, solving the problems of unclear boundaries and inconsistent judgment standards in existing risk level classifications. By using specific intervals, the abstract risk entropy is transformed into a directly measurable level, avoiding subjective differences in understanding low and high risks among different personnel. At the same time, the continuous interval division covers the entire range from safe to extremely high risk, ensuring that slight fluctuations in low risk do not trigger over-response, while also promptly capturing emergency states of high risk. This provides a clear basis for subsequent matching of responsibilities and execution actions, improving the consistency and efficiency of early warning response.

[0022] In one possible implementation of the first aspect, determining the notification recipients, decision-making bodies, and execution actions based on the risk quantification level includes: when the risk quantification level is the first risk quantification level, the notification and decision-making body is the project department's safety officer, and the execution action is to archive the risk data into a safety log; when the risk quantification level is the second risk quantification level, the notification recipients are the project manager and the project department's safety officer, the decision-making body is the project department's project manager, and the execution action includes going to the risk site for on-site verification and collecting on-site video evidence; when the risk quantification level is the third risk quantification level, the notification recipients are the engineering construction management unit and the project department, the decision-making body is the engineering construction management unit, and the execution action includes initiating a partial work stoppage for rectification and compiling a risk analysis report; when the risk quantification level is the fourth risk quantification level, the notification recipients are the enterprise headquarters' safety supervision department, the engineering construction management unit, and the project department, the decision-making body is the enterprise headquarters' safety supervision department, and the execution action includes initiating a full-area work stoppage and organizing an expert review to formulate a disposal plan.

[0023] The method provided by this invention matches corresponding notification recipients, decision-making bodies, and execution actions according to different risk quantification levels, solving the problems of unclear responsibilities and chaotic responses in existing early warning systems: For low risks (Level 1 / 2), only internal project personnel (project manager and project safety officer) perform log archiving or on-site verification and collect on-site video evidence, avoiding resource waste; for medium risks (Level 3), the engineering construction management unit and project department are notified, and the project manager initiates partial work stoppage and rectification and prepares a risk analysis report to ensure that the risk is controllable; for extremely high risks (Level 4), the notification recipients are the enterprise headquarters safety supervision department, engineering construction management unit, and project department, and the enterprise headquarters safety supervision department initiates a full-area construction stoppage and organizes expert review to formulate a disposal plan, achieving rapid handling of emergency risks; this hierarchical responsibility mechanism ensures that each level of risk has a corresponding responsible entity and execution path, significantly improving the pertinence and effectiveness of early warning response.

[0024] Secondly, this invention provides a safety early warning triggering system for infrastructure projects based on multi-level threshold dynamic adjustment. The system includes: a signal processing module for acquiring the original monitoring signal of the infrastructure project, removing environmental noise components from the original monitoring signal using an environmental interference stripping model to obtain a net structural response signal, wherein the environmental interference stripping model is established based on a preset database of intrinsic parameters of construction materials; a threshold generation module for generating a rigid safety boundary threshold dominated by physical rules and a dynamic risk identification interval threshold driven by data using a dual-modal risk threshold engine, allocating dynamic weights according to the intensity of environmental fluctuations in the current monitoring scenario, and fusing them to obtain a dynamic risk threshold; a level determination module for calculating real-time risk entropy based on the net structural response signal and the dynamic risk threshold, determining a risk quantification level according to the interval corresponding to the real-time risk entropy, wherein the risk quantification level includes levels corresponding to four consecutive intervals, and different risk quantification levels correspond to different numerical intervals of real-time risk entropy; and an early warning triggering module for determining the decision-making body, the action to be performed, and the notification object according to the risk quantification level, and outputting text early warning information, wherein the text early warning information is used to prompt the decision-making body to perform the action and to notify the notification object to complete the safety early warning triggering.

[0025] Thirdly, an electronic device is provided, the electronic device including a memory and one or more processors; the memory is coupled to the processors; wherein the memory stores computer program code, the computer program code including computer instructions, which, when executed by the processor, cause the electronic device to perform the method as described in any implementation of the first aspect.

[0026] Fourthly, a computer-readable storage medium is provided, including computer instructions that, when executed on an electronic device, cause the electronic device to perform a method as described in any implementation of the first aspect.

[0027] Fifthly, a computer program product is provided that, when run on a computer, causes the computer to perform the method in any implementation of the first aspect.

[0028] Understandably, the beneficial effects achieved by the system of the second aspect, the electronic device of the third aspect, the computer-readable storage medium of the fourth aspect, and the computer program product of the fifth aspect provided above can be referred to with reference to the beneficial effects of the first aspect and any of its possible design embodiments, which will not be repeated here. Attached Figure Description

[0029] Figure 1 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention; Figure 2 A flowchart illustrating a method for triggering safety early warnings for infrastructure projects based on dynamic adjustment of multi-level thresholds, provided in an embodiment of the present invention; Figure 3 A flowchart of another infrastructure engineering safety early warning triggering method based on multi-level threshold dynamic adjustment provided by an embodiment of the present invention; Figure 4 A schematic diagram illustrating the generation process of a net structural response signal provided in an embodiment of the present invention; Figure 5 A schematic diagram illustrating the generation process of a dynamic risk threshold provided in an embodiment of the present invention; Figure 6 A schematic diagram illustrating the process of generating a risk quantification level including four continuous intervals, provided for an embodiment of the present invention; Figure 7 This is a schematic diagram of a safety early warning triggering system provided in an embodiment of the present invention. Detailed Implementation

[0030] The technical solutions of the embodiments of the present invention will be described below with reference to the accompanying drawings. In the description of the present invention, unless otherwise stated, " / " indicates that the objects before and after are in an "or" relationship. For example, A / B can represent A or B. The "or" in the present invention is merely a description of the relationship between the related objects, indicating that three relationships can exist. For example, A or B can represent: A alone, A and B simultaneously, and B alone. A and B can be singular or plural. Furthermore, in the description of the present invention, unless otherwise stated, "multiple" refers to two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items.

[0031] Furthermore, to facilitate a clear description of the technical solutions of the embodiments of the present invention, the terms "first" and "second" are used in the embodiments of the present invention to distinguish identical or similar items with essentially the same function and effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and that the terms "first" and "second" are not necessarily different.

[0032] In this embodiment of the invention, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" or "for example" in this embodiment of the invention should not be construed as superior or more advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner for ease of understanding.

[0033] As infrastructure projects extend to high-risk scenarios such as tunnel excavation, deep foundation pit support, and construction of super high-rise buildings, the safety risks faced by engineering structures, such as collapse, overturning, and settlement, are becoming increasingly complex. Real-time and accurate safety early warning has become a core requirement for ensuring the safety of construction workers and reducing project losses. This requires safety early warning technology to be able to adapt to harsh construction environments, accurately capture the evolution of risks, and effectively integrate multi-source monitoring data.

[0034] Currently, various products for safety monitoring in infrastructure projects have emerged on the market. Among them, AI visual recognition systems can intuitively monitor structural deformation through optical acquisition and image analysis technology, and are widely used in visualization scenarios such as bridge erection and super high-rise construction. Static threshold alarm terminals rely on sensor data such as GNSS displacement and stress gauges to trigger alarms by preset fixed safety thresholds, providing basic risk warnings for scenarios such as deep foundation pit support and tunnel excavation. In addition, BIM integrated monitoring platforms and multi-source sensor fusion equipment also play a monitoring role under specific working conditions.

[0035] However, these similar products generally suffer from key technical defects. On the one hand, their environmental adaptability is severely insufficient. For example, mainstream AI vision systems rely on optical sensors and lack physical compensation mechanisms, resulting in a high false alarm rate in dust / rain and fog scenarios, making it easy to miss major risks such as deformation of support structures. On the other hand, the continuity of risk assessment is lacking. Current graded alarm systems mostly use fixed threshold triggering mechanisms. Taking a 40mm displacement threshold for foundation pits as an example, a progressive danger of 39.5mm will be ignored, while an instantaneous vibration disturbance of 40.5mm will trigger a false alarm. Inclination monitoring equipment has a high frequency of false triggers per day under wind loads. At the same time, there are also problems of data silos and fusion failures. When existing fusion systems integrate GNSS displacement, vibration sensor, and stress gauge data, the timestamp error of multi-source data is high, leading to causal misjudgment of the peak stress of surrounding rock and vibration of support structures in tunnel monitoring. Moreover, the multi-source data has a high damage rate, making it difficult to meet the requirements of accuracy, continuity, and data validity for early warning in high-risk infrastructure scenarios.

[0036] In view of this, embodiments of the present invention provide a method for triggering safety early warnings for infrastructure projects based on dynamic adjustment of multi-level thresholds. The method includes: acquiring the original monitoring signal of the infrastructure project; removing environmental noise components from the original monitoring signal using an environmental interference stripping model to obtain a net structural response signal, wherein the environmental interference stripping model is established based on a preset database of intrinsic parameters of construction materials; generating a rigid safety boundary threshold dominated by physical rules and a dynamic risk identification interval threshold driven by data using a dual-modal risk threshold engine; allocating dynamic weights according to the intensity of environmental fluctuations in the current monitoring scenario and fusing them to obtain a dynamic risk threshold; calculating a real-time risk entropy based on the net structural response signal and the dynamic risk threshold; determining a risk quantification level according to the interval corresponding to the real-time risk entropy, wherein the risk quantification level includes levels corresponding to four consecutive intervals, and different risk quantification levels correspond to different numerical intervals of the real-time risk entropy; determining the decision-making body, the action to be performed, and the notification object according to the risk quantification level, and outputting text warning information, wherein the text warning information is used to prompt the decision-making body to perform the action and to notify the notification object to complete the triggering of the safety early warning.

[0037] The method provided by this invention addresses the common shortcomings of existing products, such as insufficient environmental adaptability, lack of continuity in risk assessment, and failure of data fusion, through a comprehensive design that includes environmental noise stripping, dual-modal dynamic thresholding, risk entropy quantification and grading, and responsibility-matching early warning. On one hand, the environmental interference stripping model can remove noise to obtain the net structural response signal, avoiding false alarms and missed detections caused by environmental temperature interference. On the other hand, the dual-modal thresholding combined with dynamic weight fusion overcomes the limitations of fixed thresholds, achieving dynamic and accurate risk identification. Simultaneously, the four-level risk entropy grading and responsibility-matching mechanism ensures the targeted nature and enforceability of the early warning response, ultimately providing real-time and accurate safety warnings for high-risk infrastructure scenarios such as tunnels and deep foundation pits, protecting the lives of construction personnel and reducing project losses.

[0038] In some embodiments, the infrastructure project safety early warning triggering method based on multi-level threshold dynamic adjustment provided by the present invention can be executed by an infrastructure project safety early warning triggering system 100 based on multi-level threshold dynamic adjustment (hereinafter referred to as the safety early warning triggering system 100).

[0039] As an example, the security warning triggering system 100 can be any electronic device 200 with data processing capabilities, such as a general-purpose computer, personal computer, laptop computer, switch, or tablet computer. The specific implementation method of the security warning triggering system 100 is not limited here.

[0040] Figure 1 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention is shown. The electronic device 200 includes a processor 210, a memory 220, and a communication interface 230.

[0041] Processor 210 may include one or more processing cores. Processor 210 connects to various parts within electronic device 200 using various interfaces and lines, and performs various functions and processes data of electronic device 200 by running or executing instructions, programs, code sets, or instruction sets stored in memory 220, and by calling data stored in memory 220. Optionally, processor 210 may be implemented using at least one of the following hardware forms: Central Processing Unit (CPU), Graphics Processing Unit (GPU), Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA).

[0042] The memory 220 may include random access memory (RAI) or read-only memory (ROI). Optionally, the memory 220 may include non-transitory computer-readable storage ledger. The memory 220 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 220 may include a stored program area. The stored program area may store instructions for implementing an operating system, instructions for implementing at least one function, instructions for implementing the various method embodiments described above, etc.

[0043] Communication interface 230 is used to communicate with other devices, equipment or communication networks, such as data storage devices, image processing devices or Ethernet, wireless access network (RAN), wireless local area network (WLAN), etc.

[0044] In terms of physical implementation, the aforementioned devices (such as processor 210, memory 220, and communication interface 230) can each be devices within the same device (such as a laptop computer). Alternatively, at least two of these devices can be located within the same device, i.e., as different devices within the same device, similar to the deployment of devices or components in a distributed system.

[0045] It is understood that the structure illustrated in this embodiment does not constitute a specific limitation on the electronic device 200. In other embodiments of the present invention, the electronic device 200 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0046] The following description, in conjunction with the accompanying drawings, illustrates a method for triggering safety early warnings for infrastructure projects based on dynamic adjustment of multi-level thresholds, according to an embodiment of the present invention.

[0047] Figure 2 This is a flowchart illustrating a method for triggering safety early warnings for infrastructure projects based on dynamic adjustment of multi-level thresholds, provided by an embodiment of the present invention. Optionally, this method can be... Figure 1 The illustrated electronic device 200 performs this operation. The method may include the following steps: S1. Obtain the original monitoring signals of the infrastructure project, and remove the environmental noise components from the original monitoring signals using the environmental interference stripping model to obtain the net structural response signal.

[0048] The environmental interference stripping model is established based on a pre-set database of intrinsic parameters of construction materials. In one possible implementation, the intrinsic parameter database of construction materials includes physical property parameters of infrastructure engineering materials, including strain coefficients of infrastructure engineering materials under different temperature conditions, to quantify the interference effect of temperature fluctuations on monitoring signals.

[0049] The method provided by this invention clearly defines the intrinsic parameter database of construction materials, which includes the strain coefficients of infrastructure engineering materials under different temperature conditions. This parameter is used to quantify the interference effect of temperature fluctuations on monitoring signals, solving the problem that existing monitoring systems lack correlation with material temperature characteristics and cannot quantify environmental interference. By focusing on temperature as the core source of environmental interference, it provides accurate material characteristic support for subsequent environmental interference stripping models, ensuring that the models can calculate interference components based on objective temperature strain coefficients rather than relying on subjective experience. This significantly improves the accuracy of environmental noise stripping, avoids the distortion of monitoring signals caused by temperature fluctuations, and provides a reliable data foundation for subsequent risk assessment.

[0050] In some embodiments, see Figure 3 The above S1 includes: S11. Obtain the original monitoring signals of the infrastructure project, wherein the original monitoring signals shall at least cover structural strain, displacement, vibration and stress monitoring data; S12. Based on the temperature strain coefficient in the intrinsic parameter database of the construction materials, establish a physical law-driven environment-signal transfer function, and calculate the systematic interference component caused by temperature fluctuation in the original monitoring signal through the environment-signal transfer function. Furthermore, the environment-signal transfer function is: ; in, β is the systematic interference component caused by temperature fluctuations in the original monitoring signal; γ is the material temperature sensitivity coefficient; t is the environmental influence attenuation coefficient; t is the current monitoring time; t0 is the initial monitoring time; τ is the integral variable; and T is the ambient temperature during the monitoring period.

[0051] It should be noted that the above environment-signal transfer functions are merely illustrative examples. The method provided by this invention can also isolate the interference of environmental noise such as rain, fog, and dust on monitoring data by constructing different environment-signal transfer functions. The determination method of the systematic interference components corresponding to environmental noise such as rain, fog, and dust has the same principle as the determination method of the systematic interference components of temperature-varying noise mentioned above, and will not be repeated here.

[0052] The transfer function provided by the method of this invention correlates the material temperature sensitivity coefficient, the environmental influence attenuation coefficient, and temperature change in an integral form. It can dynamically quantify the systematic interference components caused by temperature fluctuations during different monitoring periods, rather than using static estimation. Compared with existing fixed-coefficient denoising, this function can accurately calculate the interference based on real-time temperature changes, further improving the authenticity of the net structural response signal and providing accurate data support for subsequent threshold comparison and risk entropy calculation.

[0053] The method provided by this invention clearly breaks down the steps of acquiring the original monitoring signal, calculating the systematic temperature interference, dividing the noise frequency band, suppressing high-frequency random noise, and eliminating dual interferences. This solves the problem of vague steps and single-dimensional noise removal in existing environmental interference stripping processes: First, it clarifies that the original monitoring signal covers key data such as strain and displacement, ensuring comprehensive monitoring dimensions; second, it calculates temperature interference through a transfer function driven by physical laws, and combines it with wavelet packet algorithm to suppress high-frequency mechanical / airflow noise, achieving full-dimensional stripping of systematic interferences and random noise; finally, it obtains the net structural response signal through dual interference removal, completely solving the problem of misjudging the true state of the structure due to noise pollution in existing systems, and providing a clean data source for risk assessment.

[0054] S13. Perform wavelet transform on the original monitoring signal to obtain the frequency domain spectrum. Based on the vibration frequency of the construction machinery operation and the turbulence frequency of the airflow disturbance, divide the noise frequency band of the non-structure response. The frequency range of the noise frequency band matches the characteristic frequency of the interference source. S14. The wavelet packet threshold denoising algorithm is used to perform energy suppression processing on the noise frequency band, and the high-frequency random noise component corresponding to the noise frequency band is calculated. S15. Remove the systematic interference component and the high-frequency random noise component from the original monitoring signal to obtain the net structural response signal.

[0055] Specifically, a dedicated database (intrinsic parameter database of construction materials) is established based on the characteristics of engineering materials. For example, C40 grade concrete exhibits a surface strain change of 12 microstrains for every 1°C increase in temperature, while the temperature coefficient of Grade III surrounding rock is 8.5 microstrains / °C. See also Figure 4 Based on these physical parameters, the core process of the safety early warning triggering system 100 for implementing environmental interference stripping includes three key steps: after the original signal is acquired, the environmental noise components are separated through a temperature compensation calculation module, followed by wavelet frequency domain analysis, and finally, energy threshold suppression technology is used to attenuate the power spectrum of the high-frequency noise band (greater than 50Hz) by more than 90%. The entire process strictly follows the physical correction formula: true strain = measured value - temperature effect compensation value.

[0056] S2. The dual-modal risk threshold engine generates a rigid safety boundary threshold dominated by physical rules and a dynamic risk identification interval threshold driven by data. Dynamic weights are assigned according to the intensity of environmental fluctuations in the current monitoring scenario, and the dynamic risk threshold is obtained by fusion.

[0057] For details, see Figure 5 The dynamic risk threshold generation employs a unique dual-engine dynamic fusion mechanism. The physical model threshold is derived from an engineering design parameter database, including key indicators such as material strength and structural dimensions, which are updated synchronously as construction conditions change. The data-driven threshold analyzes historical monitoring data clustering characteristics in real time, refreshing the calculation results every second. The two engines work collaboratively through an intelligent weight allocator. When sensor confidence reaches 90% or higher, the physical model takes precedence; however, in scenarios with severe environmental fluctuations such as heavy rain or blasting, the safety warning trigger system automatically switches to the data-driven dominant mode.

[0058] In some embodiments, the rigid safety boundary threshold is generated based on the design parameters of the infrastructure project, the material strength limit, and the structural stress verification results, while the dynamic risk identification interval threshold is generated by analyzing the clustering characteristics of historical monitoring data of the infrastructure project. Furthermore, the generation of a rigid safety boundary threshold dominated by physical rules and a dynamic risk identification interval threshold driven by data through a dual-modal risk threshold engine includes: The maximum allowable response value of the structure under safe conditions is calculated using a finite element analysis model, and this maximum allowable response value is used as the rigid safety boundary threshold. Gaussian mixture clustering is performed on the normal operating condition data in the historical monitoring data to obtain the distribution range of the monitoring data under normal operating conditions, and the upper limit of the distribution range is used as the dynamic risk identification range threshold.

[0059] The method provided by this invention clearly defines the rigid safety boundary threshold as generated based on finite element analysis and the dynamic risk identification interval threshold as generated based on Gaussian mixture clustering. This solves the problems of ambiguous logic and lack of scientific basis in the existing bimodal threshold generation: On the one hand, finite element analysis, combined with design parameters and material strength, ensures that the rigid threshold meets the physical limits of structural safety, avoiding over-warning due to excessively low thresholds or safety hazards due to excessively high thresholds; on the other hand, Gaussian mixture clustering analysis of historical normal working condition data can capture the dynamic change patterns of working conditions, making the dynamic threshold fit the actual construction scenario, rather than relying on fixed empirical values; the bimodal threshold generated by the combination of the two not only meets the physical bottom line of structural safety but also adapts to the dynamic changes of working conditions, laying a scientific foundation for the fusion of dynamic risk thresholds.

[0060] In other embodiments, the step of allocating dynamic weights based on the intensity of environmental fluctuations in the current monitoring scenario and fusing them to obtain a dynamic risk threshold includes: The intensity of environmental fluctuations in the current monitoring scenario is determined by using the temperature fluctuation data obtained during the environmental interference stripping model processing. When the intensity of environmental fluctuations is less than or equal to a preset threshold, the weight of the rigid safety boundary threshold is greater than that of the dynamic risk identification interval threshold. When the intensity of environmental fluctuations is greater than a preset threshold, the weight of the rigid safety boundary threshold is less than or equal to that of the dynamic risk identification interval threshold. The dynamic risk threshold is obtained by weighting and fusing the rigid safety boundary threshold and the dynamic risk identification interval threshold according to their respective weights. The formula for determining the dynamic risk threshold is: ; in, For dynamic risk thresholds, As a rigid safety boundary threshold, For dynamic risk identification range thresholds, This represents the weighting percentage of the rigid safety boundary threshold.

[0061] The method provided by this invention distinguishes fluctuation intensity by setting a preset threshold, and realizes adaptive adjustment of low fluctuation with rigid threshold and high fluctuation with dynamic threshold. This avoids the failure of existing fixed weights in extreme environments, and can significantly improve the accuracy and reliability of dynamic risk thresholds, adapting to the risk identification needs under different environmental fluctuations.

[0062] S3. Calculate the real-time risk entropy based on the net structural response signal and the dynamic risk threshold, and determine the risk quantification level according to the interval corresponding to the real-time risk entropy.

[0063] The risk quantification level includes four levels corresponding to continuous intervals, with different risk quantification levels corresponding to different numerical intervals of real-time risk entropy.

[0064] In one possible implementation, the step of calculating the real-time risk entropy based on the net structural response signal and the dynamic risk threshold includes: comparing the net structural response signal with the dynamic risk threshold to obtain a deviation value, wherein the deviation value reflects the degree of deviation between the current structural response and the safety threshold; and constructing a four-level trust assignment function based on DS evidence theory to map the deviation value to the trust level of the corresponding risk level, wherein the trust level is used to quantify the probability that the current structure is at each risk level. The trust level is calculated to obtain the real-time risk entropy; The formula for calculating the real-time risk entropy is: ; in, For real-time risk entropy, Let be the trust level corresponding to the i-th risk level, and =1.

[0065] The method provided by this invention calculates real-time risk entropy through steps of deviation value calculation, DS evidence theory trust allocation, and risk entropy formula operation. This solves the problems of lack of continuity and inability to reflect the ambiguity of existing risk quantification methods: First, the deviation value directly reflects the degree of deviation between the structural response and the safety threshold, providing an intuitive basis for risk quantification; second, the four-level trust allocation of DS evidence theory can quantify the ambiguity of risk; finally, the risk entropy formula transforms risk into a continuous numerical value rather than a discrete level through trust degree calculation, which not only reflects the continuous evolution of risk but also provides a precise quantitative standard for the subsequent four-level classification, ensuring the fineness and accuracy of risk identification.

[0066] In some embodiments, determining the risk quantification level based on the interval corresponding to the real-time risk entropy includes: when the real-time risk entropy value ranges from 0 to H... r When the risk entropy is less than 1.5, the risk quantification level is determined as the first risk quantification level; when the real-time risk entropy value is within the range of 1.5 ≤ H... r When the value is less than 2.0, the risk quantification level is determined to be the second risk quantification level; when the real-time risk entropy value is within the range of 2.0 ≤ H r When the value is less than 3.0, the risk quantification level is determined to be the third risk quantification level; when the real-time risk entropy value ranges from H... rWhen the value is ≥3.0, the risk quantification level is determined to be the fourth risk quantification level.

[0067] For details, see Figure 6 The safety early warning triggering system 100 adopts a four-level continuous quantization architecture. A risk entropy (H) is designed. r The calculation model divides risk values ​​into four continuous intervals: 0 to 1.5 is Level 1 (safety log recording), 1.5 to 2.0 is Level 2 (manual on-site verification), 2.0 to 3.0 is Level 3 (partial shutdown for rectification), and above 3.0 is Level 4 (full-area emergency response). In terms of technical implementation, a boundary smoothing mechanism has been specially developed, which improves the ability to judge risk continuity by establishing a ±0.15 buffer zone within the critical domain and using a probability transition algorithm.

[0068] The method provided by this invention clearly defines the real-time risk entropy value range corresponding to the four-level risk quantification levels, solving the problems of unclear boundaries and inconsistent judgment standards in existing risk level classifications. By using specific intervals, the abstract risk entropy is transformed into a directly measurable level, avoiding subjective differences in understanding low and high risks among different personnel. At the same time, the continuous interval division covers the entire range from safe to extremely high risk, ensuring that slight fluctuations in low risk do not trigger over-response, while also promptly capturing emergency states of high risk. This provides a clear basis for subsequent matching of responsibilities and execution actions, improving the consistency and efficiency of early warning response.

[0069] S4. Determine the decision-making body, execution action, and notification object based on the risk quantification level, and output text warning information. The text warning information is used to prompt the decision-making body to perform the action and notify the notification object to complete the safety warning trigger.

[0070] In one possible implementation, exemplarily referring to Table 1, the determination of the notification recipient, decision-making body, and execution action based on the risk quantification level includes: when the risk quantification level is the first risk quantification level, the notification recipient and decision-making body are both the project department's safety officer, and the execution action is to archive the risk data into a safety log; when the risk quantification level is the second risk quantification level, the notification recipient is the project manager and the project department's safety officer, the decision-making body is the project department's project manager, and the execution action includes going to the risk site for on-site verification and collecting on-site video evidence; when the risk quantification level is the third risk quantification level, the notification recipient is the engineering construction management unit and the project department, the decision-making body is the engineering construction management unit, and the execution action includes initiating a partial construction stoppage for rectification and compiling a risk analysis report; when the risk quantification level is the fourth risk quantification level, the notification recipient is the enterprise headquarters' safety supervision department, the engineering construction management unit, and the project department, the decision-making body is the enterprise headquarters' safety supervision department, and the execution action includes initiating a full-area construction stoppage and organizing an expert review to formulate a disposal plan.

[0071] Table 1 The method provided by this invention matches corresponding notification recipients, decision-making bodies, and execution actions according to different risk quantification levels, solving the problems of unclear responsibilities and chaotic responses in existing early warning systems: For low risks (Level 1 / 2), only internal project personnel (project manager and project safety officer) perform log archiving or on-site verification and collect on-site video evidence, avoiding resource waste; for medium risks (Level 3), the engineering construction management unit and project department are notified, and the project manager initiates partial work stoppage and rectification and prepares a risk analysis report to ensure that the risk is controllable; for extremely high risks (Level 4), the notification recipients are the enterprise headquarters safety supervision department, engineering construction management unit, and project department, and the enterprise headquarters safety supervision department initiates a full-area construction stoppage and organizes expert review to formulate a disposal plan, achieving rapid handling of emergency risks; this hierarchical responsibility mechanism ensures that each level of risk has a corresponding responsible entity and execution path, significantly improving the pertinence and effectiveness of early warning response.

[0072] This safety warning triggering system has demonstrated excellent performance indicators through multi-scenario engineering verification. In terms of economy, by eliminating downtime losses due to false triggers, a single project can save millions of yuan in costs annually.

[0073] As shown in S1-S4, the method provided by this invention addresses the common defects of existing products, such as insufficient environmental adaptability, lack of continuity in risk assessment, and failure of data fusion, through a full-process design including environmental noise stripping, dual-modal dynamic thresholding, risk entropy quantification and grading, and responsibility matching early warning. On the one hand, the environmental interference stripping model can strip noise to obtain the net structural response signal, avoiding false alarms and missed detections caused by environmental temperature interference; on the other hand, the dual-modal thresholding combined with dynamic weight fusion breaks through the limitations of fixed thresholds, achieving dynamic and accurate risk identification; at the same time, the four-level risk entropy grading and responsibility matching mechanism ensures the pertinence and enforceability of the early warning response, ultimately providing real-time and accurate safety early warnings for high-risk infrastructure scenarios such as tunnels and deep foundation pits, protecting the lives of construction personnel and reducing project losses.

[0074] In other words, the beneficial effects of the method provided in the embodiments of the present invention are as follows: 1. Significantly improves monitoring reliability in complex environments. Through a signal correction mechanism driven by physical laws, it effectively eliminates interference from temperature-induced noise in monitoring data. Furthermore, it effectively filters out interference from environmental noise such as rain, fog, and dust through different types of environment-signal transfer functions. In extreme weather conditions and complex construction scenarios, the system maintains signal resolution accuracy, reducing false alarms and missed alarms caused by environmental interference with traditional optical equipment and vibration sensors, thus significantly improving the accuracy of early warning decisions.

[0075] 2. Achieve continuous quantitative identification of risks. Breaking through the static threshold discrimination mode, a dual-modal evaluation engine integrating physical laws and dynamic data is established, which can accurately capture the progressive risk evolution process, eliminate the identification blind spots of traditional systems in the critical interval, avoid frequent false triggers caused by discrete grading, and ensure that risk judgment is strictly synchronized with engineering practice.

[0076] 3. Construct a legally compliant response system. A human-machine decision-making physical isolation framework ensures compliance from three dimensions: first, binding responsible parties, mandating the transfer of high-risk events to the human decision-making level; second, equipment control circuit breaking, filtering control commands at the data transmission level, allowing only text-based warning information output; and third, judicial traceability support, establishing a three-tiered audit mechanism of command issuance, dual verification, and regulatory filing to avoid secondary risks and legal disputes arising from automated responses.

[0077] 4. Optimize the safety and economic benefits of engineering projects. Eliminate losses from unintended downtime, eradicate downtime caused by misjudgments in traditional systems due to graded transitions, reduce accident handling costs, and compress the scale of accident handling through early and accurate warnings.

[0078] 5. Promote the upgrading of industry technical standards. In the determination of liability for engineering accidents, use the system responsibility separation agreement as a technical precedent to promote the industry to shift from a "passive handling" model to a "proactive prevention + precise control" model.

[0079] This technology provides technical support for high-risk construction projects by enhancing the environmental adaptability of risk identification, continuously quantifying the risk identification mechanism, and ensuring compliance with the rights and responsibilities framework for emergency response. It also improves the early warning capabilities for major accidents and reduces project operation and maintenance costs and accident losses.

[0080] It should be understood that the technical implementation of the method provided by the present invention adopts a layered deployment architecture: after the on-site sensor data is initially processed by the edge computing node, it is uploaded to the proprietary IoT platform, then analyzed and decided through the business platform, and finally the instructions are transmitted to the headquarters safety supervision center and simultaneously distributed to the project department and the management terminal of the regulatory unit.

[0081] Furthermore, the present invention does not impose any special restrictions on the operating system of the safety warning triggering system 100, and users can flexibly choose the corresponding operating system according to the actual use scenario.

[0082] The above mainly describes the solution of the embodiments of the present invention from a methodological perspective. It is understood that, in order to achieve the above functions, the security warning triggering system 100 includes at least one of the hardware structures and software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments disclosed herein, the embodiments of the present invention can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments of the present invention.

[0083] In this embodiment of the invention, the safety warning triggering system 100 can be divided into functional units according to the above method example. For example, the safety warning triggering system 100 can be divided into functional units corresponding to each function, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional unit. It should be noted that the unit division in this embodiment of the invention is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0084] For example, Figure 7 This diagram illustrates the hardware structure of a safety early warning triggering system according to an embodiment of the present invention. The safety early warning triggering system 100 includes: a signal processing module 110, used to acquire the original monitoring signal of the infrastructure project, and remove environmental noise components from the original monitoring signal using an environmental interference stripping model to obtain a net structural response signal. The environmental interference stripping model is established based on a preset database of intrinsic parameters of construction materials; a threshold generation module 120, used to generate a rigid safety boundary threshold dominated by physical rules and a dynamic risk identification interval threshold driven by data using a dual-modal risk threshold engine, and to allocate dynamic weights according to the intensity of environmental fluctuations in the current monitoring scenario, fusing them to obtain a dynamic risk threshold; a level determination module 130, used to calculate the real-time risk entropy based on the net structural response signal and the dynamic risk threshold, and to determine the risk quantification level according to the interval corresponding to the real-time risk entropy. The risk quantification level includes levels corresponding to four consecutive intervals, with different risk quantification levels corresponding to different numerical intervals of the real-time risk entropy; and an early warning triggering module 140, used to determine the decision-making body, the action to be performed, and the notification recipient according to the risk quantification level, and to output text early warning information. The text early warning information is used to prompt the decision-making body to perform the action and to notify the notification recipient to complete the safety early warning triggering.

[0085] It should be understood that specific descriptions of the above-mentioned optional methods can be found in the foregoing method embodiments, and will not be repeated here. Furthermore, explanations of any of the security warning triggering systems 100 provided above, as well as descriptions of their beneficial effects, can be found in the corresponding method embodiments described above, and will not be repeated here.

[0086] This invention also provides a computer-readable storage medium storing at least one computer instruction, which is loaded and executed by a processor to implement the methods of the various embodiments described above. Explanations of the relevant content and descriptions of the beneficial effects of any of the computer-readable storage media provided above can be found in the corresponding embodiments described above, and will not be repeated here.

[0087] This invention also provides a chip. This chip integrates a control circuit for implementing the functions of the aforementioned safety warning triggering system 100 and one or more ports. Optionally, the functions supported by this chip are as described above and will not be repeated here.

[0088] Those skilled in the art will understand that the program for implementing all or part of the steps of the above embodiments, which can be executed by a program instructing related hardware, can be stored in a computer-readable storage medium. The storage medium mentioned above can be a read-only memory, a random access memory, etc. The processing unit or processor mentioned above can be a central processing unit, a general-purpose processor, an application-specific integrated circuit (ASIC), a microprocessor (DSP), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof.

[0089] This invention also provides a computer program product containing instructions that, when executed on a computer, cause the computer to perform any of the methods described in the above embodiments. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this invention is generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions may be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., SSD), etc.

[0090] It should be noted that the devices for storing computer instructions or computer programs provided in the embodiments of the present invention, such as, but not limited to, the aforementioned memory, computer-readable storage medium, and communication chip, are all non-transitory. Those skilled in the art should recognize that the functions described in the embodiments of the present invention in one or more of the above examples can be implemented using hardware, software, firmware, or any combination thereof. When implemented using software, these functions can be stored in a computer-readable storage medium or transmitted as one or more instructions or code on a computer-readable storage medium. Computer-readable storage media include computer storage media and communication media, wherein communication media include any medium that facilitates the transmission of computer programs from one place to another. Storage media can be any available medium accessible to general-purpose or special-purpose computers.

[0091] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for triggering safety early warning in infrastructure projects based on dynamic adjustment of multi-level thresholds, characterized in that, The method includes: The original monitoring signals of the infrastructure project are obtained, and the environmental noise component in the original monitoring signals is removed by an environmental interference stripping model to obtain the net structural response signal. The environmental interference stripping model is established based on a preset database of intrinsic parameters of construction materials. The dual-modal risk threshold engine generates rigid safety boundary thresholds dominated by physical rules and dynamic risk identification interval thresholds driven by data. Dynamic weights are assigned according to the intensity of environmental fluctuations in the current monitoring scenario, and the dynamic risk thresholds are obtained by fusion. Real-time risk entropy is calculated based on the net structural response signal and the dynamic risk threshold. The risk quantification level is determined according to the interval corresponding to the real-time risk entropy. The risk quantification level includes the level corresponding to four consecutive intervals. Different risk quantification levels correspond to different numerical intervals of real-time risk entropy. Based on the risk quantification level, the decision-making body, the action to be performed, and the notification recipient are determined, and a text warning message is output. The text warning message is used to prompt the decision-making body to perform the action and to notify the notification recipient, so as to complete the triggering of the safety warning.

2. The method according to claim 1, characterized in that, The intrinsic parameter database of construction materials contains physical property parameters of infrastructure engineering materials, including the strain coefficient of infrastructure engineering materials under different temperature conditions, which is used to quantify the interference effect of temperature fluctuations on monitoring signals.

3. The method according to claim 2, characterized in that, The process of acquiring the original monitoring signals of the infrastructure project, and then removing the environmental noise component from the original monitoring signals using an environmental interference stripping model to obtain the net structural response signal includes: Acquire the original monitoring signals of the infrastructure project, wherein the original monitoring signals shall at least cover structural strain, displacement, vibration and stress monitoring data; Based on the temperature strain coefficient in the intrinsic parameter database of the construction materials, a physical law-driven environment-signal transfer function is established, and the systemic interference component caused by temperature fluctuations in the original monitoring signal is calculated through the environment-signal transfer function. The original monitoring signal is subjected to wavelet transform to obtain the frequency domain spectrum. Based on the vibration frequency of the construction machinery operation and the turbulence frequency of the airflow disturbance, the noise frequency band of the non-structure response is divided. The frequency range of the noise frequency band matches the characteristic frequency of the interference source. The noise frequency band is subjected to energy suppression processing using a wavelet packet threshold denoising algorithm, and the high-frequency random noise component corresponding to the noise frequency band is calculated. The systematic interference component and the high-frequency random noise component are removed from the original monitoring signal to obtain the net structural response signal.

4. The method according to claim 3, characterized in that, The environment-signal transfer function is: ； in, β is the systematic interference component caused by temperature fluctuations in the original monitoring signal; γ is the material temperature sensitivity coefficient; t is the environmental influence attenuation coefficient; t is the current monitoring time; t0 is the initial monitoring time; τ is the integral variable; and T is the ambient temperature during the monitoring period.

5. The method according to claim 4, characterized in that, The rigid safety boundary threshold is generated based on the design parameters of the infrastructure project, the material strength limit, and the structural stress verification results. The dynamic risk identification interval threshold is generated by analyzing the clustering characteristics of historical monitoring data of the infrastructure project. The process of generating a rigid safety boundary threshold governed by physical rules and a dynamic risk identification interval threshold driven by data through a dual-modal risk threshold engine includes: The maximum permissible response value of the structure under safe conditions is calculated using a finite element analysis model, and the maximum permissible response value is used as the rigid safety boundary threshold. Gaussian mixture clustering is performed on the normal operating condition data in the historical monitoring data to obtain the distribution range of the monitoring data under normal operating conditions. The upper limit of the distribution range is used as the threshold of the dynamic risk identification range.

6. The method according to claim 5, characterized in that, The process of allocating dynamic weights based on the intensity of environmental fluctuations in the current monitoring scenario and fusing them to obtain a dynamic risk threshold includes: The intensity of environmental fluctuations in the current monitoring scenario is determined by using the temperature fluctuation data obtained during the environmental interference stripping model processing. When the intensity of environmental fluctuations is less than or equal to a preset threshold, the weight of the rigid safety boundary threshold is greater than that of the dynamic risk identification interval threshold. When the intensity of environmental fluctuations is greater than a preset threshold, the weight of the rigid safety boundary threshold is less than or equal to that of the dynamic risk identification interval threshold. The dynamic risk threshold is obtained by weighting and fusing the rigid safety boundary threshold and the dynamic risk identification interval threshold according to their respective weights. The formula for determining the dynamic risk threshold is: ； in, For dynamic risk thresholds, As a rigid safety boundary threshold, For dynamic risk identification range thresholds, This represents the weighting percentage of the rigid safety boundary threshold.

7. The method according to claim 6, characterized in that, The calculation of real-time risk entropy based on the net structural response signal and the dynamic risk threshold includes: The net structural response signal is compared with the dynamic risk threshold to obtain the deviation value, which reflects the degree of deviation between the current structural response and the safety threshold. A four-level trust allocation function is constructed based on the DS evidence theory, which maps the deviation value to the trust level of the corresponding risk level. The trust level is used to quantify the probability that the current structure is in each risk level. The trust level is calculated to obtain the real-time risk entropy; The formula for calculating the real-time risk entropy is: ； in, For real-time risk entropy, Let be the trust level corresponding to the i-th risk level, and =1.

8. The method according to claim 7, characterized in that, The step of determining the risk quantification level based on the interval corresponding to the real-time risk entropy includes: When the real-time risk entropy ranges from 0 to H r When the risk level is less than 1.5, the risk level is determined to be the first risk level. When the real-time risk entropy ranges from 1.5 to H r When the risk level is less than 2.0, the risk quantification level is determined to be the second risk quantification level. When the real-time risk entropy ranges from 2.0 to H r When the risk level is less than 3.0, the risk quantification level is determined to be the third risk quantification level. When the real-time risk entropy value is within the range of H r When the value is ≥3.0, the risk quantification level is determined to be the fourth risk quantification level.

9. The method according to claim 8, characterized in that, The process of determining the notification recipients, decision-making bodies, and execution actions based on the risk quantification level includes: When the risk level is the highest risk level, the notification and decision-making body is the project safety officer, and the action to be taken is to archive the risk data into a safety log. When the risk level is the second risk level, the notification recipients are the project manager and the project safety officer, the decision-making body is the project manager, and the actions to be taken include going to the risk site for on-site verification and collecting on-site video evidence. When the risk quantification level is the third risk quantification level, the notification recipients are the engineering construction management unit and the project department, the decision-making body is the engineering construction management unit, and the actions to be taken include initiating a partial work stoppage for rectification and preparing a risk analysis report. When the risk level is the fourth level, the notification recipients are the enterprise headquarters safety supervision department, the engineering construction management unit, and the project department. The decision-making body is the enterprise headquarters safety supervision department, and the actions to be taken include initiating a full-area construction shutdown and organizing an expert review to formulate a disposal plan.

10. A safety early warning triggering system for infrastructure projects based on multi-level threshold dynamic adjustment, characterized in that, The system includes: The signal processing module is used to acquire the original monitoring signals of the infrastructure project, and to remove the environmental noise components from the original monitoring signals through an environmental interference stripping model to obtain the net structural response signal. The environmental interference stripping model is established based on a preset database of intrinsic parameters of construction materials. The threshold generation module is used to generate rigid safety boundary thresholds dominated by physical rules and dynamic risk identification interval thresholds driven by data through a dual-modal risk threshold engine. Dynamic weights are assigned according to the intensity of environmental fluctuations in the current monitoring scenario, and the dynamic risk thresholds are obtained by fusion. The level determination module is used to calculate the real-time risk entropy based on the net structural response signal and the dynamic risk threshold, and determine the risk quantification level according to the interval corresponding to the real-time risk entropy. The risk quantification level includes the level corresponding to four consecutive intervals, and different risk quantification levels correspond to different numerical intervals of the real-time risk entropy. The early warning triggering module is used to determine the decision-making body, the action to be performed, and the notification object based on the risk quantification level, and output text early warning information. The text early warning information is used to prompt the decision-making body to perform the action and to notify the notification object to complete the safety early warning triggering.

Images