Ice piton monitoring method and system based on pasted optical fiber

Abstract

The invention discloses an ice piton monitoring method and system based on a pasted optical fiber, and relates to the technical field of optical fiber sensing technology and building safety monitoring. The method comprises the following steps: acquiring a temperature signal, a strain signal and a vibration signal of a to-be-detected eave surface by adopting a pasted optical fiber; constructing an ice piton growth condition of an ice piton growth model; determining the risk index of the current risk index according to the real-time growth condition of the ice piton; performing multi-parameter fusion analysis according to the risk index, and evaluating the ice piton falling risk; and performing risk decision and early warning according to a falling risk result in combination with a dynamic threshold method, and performing calibration and dynamic baseline correction regularly according to the falling risk result. According to the invention, the condition of the eave ice piton is monitored in real time by using the pasted optical fiber sensor, multi-parameter fusion analysis and anti-interference design are carried out based on the ice piton influence factors, and real-time monitoring and risk early warning of the eave ice piton of the building in the cold region are realized.

Description

Technical Field

[0001] The present invention relates to the fields of optical fiber sensing technology and building safety monitoring technology, and in particular to an ice cone monitoring method and system based on adhesive optical fiber. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] In cold regions, the formation of icicles on eaves in winter poses a serious threat to the structural safety of buildings and the safety of pedestrians. Traditional monitoring methods for the growth of icicles mainly rely on manual inspections or single temperature sensors, which have many limitations, including low efficiency, lack of real-time performance, and limited coverage. The cycle of manual inspections is limited by both weather conditions and human resources. Usually, only a limited number of inspections can be carried out on key areas every day, which cannot effectively capture the dynamic process of the rapid growth of icicles. In extreme weather conditions (such as blizzards or strong winds), inspections are often forced to be interrupted, resulting in the appearance of monitoring blind spots, further increasing safety hazards. Existing electronic temperature sensors (such as thermocouples and infrared sensors) are usually only deployed in local areas of eaves, and the risk of icing is indirectly inferred by monitoring the ambient temperature. However, when the temperature is close to the freezing point, these sensors cannot accurately distinguish between dry and wet surface states, and are prone to misjudge the presence of condensed water as icing, making it difficult to provide risk warnings. In addition, temperature sensors can only provide ambient temperature data and cannot directly evaluate the actual weight, stress distribution, and bonding strength of icicles with building structures. This makes it extremely difficult to set the warning threshold, which in turn leads to insufficient accuracy and reliability of the warning system. Therefore, traditional monitoring methods are difficult to meet actual needs when dealing with the problem of icicles on eaves, and it is urgent to develop more efficient, accurate and reliable monitoring technologies to effectively protect the safety of buildings and pedestrians in cold regions.

[0004] In recent years, fiber optic sensing technology has gradually been widely used in various fields due to its significant advantages such as anti-electromagnetic interference, distributed measurement, high sensitivity and resistance to harsh environments. For example, in the monitoring of large infrastructure such as bridges, tunnels, oil and gas pipelines, fiber optic sensing technology has shown extremely high application value. However, existing fiber optic monitoring systems are mostly aimed at the deformation or temperature changes of large structures (such as bridges and pipelines). Their installation methods are complicated and difficult to adapt to the narrow space and complex surfaces of eaves. The particularity of eaves ice cone monitoring lies in its limited space and complex environment, which puts higher requirements on the size, installation method and measurement accuracy of the sensor. In addition, the application of existing fiber optic sensing technology in building structure health monitoring is mostly concentrated on the stress, strain or temperature monitoring of the overall structure, which is difficult to directly apply to eaves ice cone monitoring.

[0005] In summary, how to overcome the defect that existing fiber optic sensing technology is difficult to apply on eaves, conduct accurate quantitative assessment of ice cone risks, and realize dynamic monitoring and early warning of the entire process of ice cones has become a technical problem that needs to be urgently solved by existing technologies. Summary of the invention

[0006] In view of the shortcomings of the prior art, the purpose of the present invention is to provide an ice cone monitoring method and system based on adhesive optical fiber, which utilizes adhesive optical fiber sensors to monitor the status of icicles on the eaves in real time, and performs multi-parameter fusion analysis and anti-interference design based on the ice cone influencing factors, so as to realize real-time monitoring and risk warning of icicles on the eaves of buildings in cold regions.

[0007] In order to achieve the above object, the present invention is implemented through the following technical solutions: A first aspect of the present invention provides an ice cone monitoring method based on a glued optical fiber, comprising the following steps: Adhesive optical fiber is used to obtain the temperature signal, strain signal and vibration signal of the eaves surface to be tested, and the collected signals are preprocessed; An ice cone growth model is constructed according to the collected signals, and the growth status of the ice cone is monitored based on the ice cone growth model; Select risk indicators and determine the risk index of the current risk indicator based on the real-time growth status of the ice cone; Conduct multi-parameter fusion analysis based on risk index to assess ice cone fall risk; Risk decisions and early warnings are made based on the fall risk results combined with the dynamic threshold method, and calibration and dynamic baseline corrections are performed regularly based on the fall risk results.

[0008] Furthermore, the specific steps of using the adhesive optical fiber to obtain the temperature signal, strain signal and vibration signal of the surface of the eaves to be detected are as follows: Design the fiber layout density and fiber Bragg grating node spacing; According to the design results, optical fibers are attached to the surface of the eaves, and signals are collected based on changes in the wavelength of the optical fibers.

[0009] Furthermore, when the optical fiber is pasted on the surface of the eave according to the design results, ensure that the pasting area is flat and clean, and then apply the base adhesive to paste the optical fiber in an array to the lower surface of the eave.

[0010] Furthermore, the specific steps of preprocessing the collected signals are as follows: Using discrete wavelet denoising to capture ice cone micro-vibration; The peak value of the ice cone point is further amplified through temperature-strain decoupling.

[0011] Furthermore, the specific steps of constructing the ice cone growth model based on the collected signals are as follows: The freezing rate of ice cones is used to reflect the expansion rate of ice layer; The strain mutation is used to reflect the severity of the local deformation of the optical fiber; Quantifying vibration energy to describe cracks inside ice cones.

[0012] Furthermore, the specific steps of determining the risk index of the current risk indicator according to the real-time growth status of the ice cone are as follows: Use the classic random forest algorithm to divide the risk index according to the risk indicators; Calculate the risk index based on the real-time growth status of the ice cone and adjust the risk weight adaptively; Dynamically adjust the warning threshold according to different ambient temperatures.

[0013] Furthermore, the specific steps for regular calibration and dynamic baseline correction based on the fall risk results are as follows: Perform heating calibration on the fiber optic temperature sensor; Set up a sliding window to dynamically update the ice-free period data baseline.

[0014] A second aspect of the present invention provides an ice cone monitoring system based on adhesive optical fiber, comprising: The data acquisition module is configured to acquire the temperature signal, strain signal and vibration signal of the surface of the eaves to be detected by using a sticky optical fiber, and pre-process the acquired signals; A growth status monitoring module is configured to construct an ice cone growth model according to the collected signals, and monitor the growth status of the ice cone based on the ice cone growth model; A risk index determination module is configured to select a risk index and determine a risk index of a current risk index according to the real-time growth status of the ice cone; A risk assessment module is configured to perform multi-parameter fusion analysis based on the risk index to assess the risk of ice pick falling; The decision-making and warning module is configured to make risk decisions and warnings based on the fall risk results in combination with the dynamic threshold method, and to perform regular calibration and dynamic baseline correction based on the fall risk results.

[0015] The third aspect of the present invention provides a medium having a program stored thereon, which, when executed by a processor, implements the steps of the ice cone monitoring method based on adhesive optical fiber as described in the first aspect of the present invention.

[0016] The fourth aspect of the present invention provides a device, including a memory, a processor, and a program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the ice cone monitoring method based on adhesive optical fiber as described in the first aspect of the present invention are implemented.

[0017] One or more of the above technical solutions have the following beneficial effects: The present invention discloses an ice cone monitoring method and system based on adhesive optical fiber, which comprehensively considers the full cycle requirements of eaves ice cone monitoring, performs dynamic monitoring and early warning from the formation, growth to shedding of ice cones, collects temperature, strain and vibration signals in real time through an adhesive optical fiber sensor network, and combines multi-parameter fusion analysis with machine learning algorithms to achieve accurate quantitative assessment of ice cone risks. Compared with traditional manual inspections or single sensor monitoring methods, the present invention solves the problems of monitoring fragmentation, early warning lag, high false alarm and missed alarm rates, significantly improves monitoring efficiency and early warning accuracy, and provides reliable protection for building safety in cold regions.

[0018] The present invention can adapt to the complex surfaces of various roof structures through the convenient deployment and flexible design of adhesive optical fiber, without drilling or mechanical fixation, significantly reducing the installation cost and construction difficulty. At the same time, the optimized design of the waterproof adhesive layer and protective coating ensures the long-term stability of the optical fiber in low temperature and high humidity environments, solving the pain points of traditional monitoring equipment that is easily affected by the environment and has high maintenance costs, and has broad application prospects.

[0019] The present invention uses the coordinated mechanism of heating calibration and baseline correction to regularly eliminate sensor zero drift, dynamically update the ice-free period data baseline, adapt to environmental gradual changes and seasonal changes, and ensure the long-term reliability of monitoring data. In addition, the multi-sensor data fusion and anomaly detection mechanism effectively improves the system's anti-interference ability and fault tolerance, avoids monitoring interruptions caused by single point failures, and ensures the continuous and stable operation of the system.

[0020] The present invention realizes intelligent graded warning of ice cone risk through random forest classifier and dynamic threshold adjustment mechanism. The warning threshold is adjusted adaptively in combination with ambient temperature, avoiding the limitation of traditional methods that rely on fixed thresholds, and significantly reducing false alarm rate and missed alarm rate. At the same time, the warning information is pushed in real time through sound and light alarm and wireless communication module, supporting remote monitoring and rapid response, and providing efficient technical means for building safety management.

[0021] The present invention improves the accuracy of risk prediction by constructing and optimizing the ice cone growth model, combining historical data with real-time monitoring feedback, and dynamically adjusting model parameters. Compared with the traditional empirical threshold method, the present invention is more scientific and adaptable, can cope with complex and changeable climate conditions, and provides an innovative solution for the field of ice cone monitoring.

[0022] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0024] Figure 1 This is a flow chart of an ice cone monitoring method based on adhesive optical fiber in Embodiment 1 of the present invention; Figure 2 This is a cross-sectional view of the adhesive optical fiber in the first embodiment of the present invention. DETAILED DESCRIPTION

[0025] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0026] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "include" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or their combinations; Terminology explanation: Adhesive fiber: A special type of optical fiber coated with a flexible adhesive layer, specifically designed to be directly attached to the surface of buildings or other structures. It is designed to achieve real-time and continuous monitoring of distributed physical quantities (such as temperature, strain, vibration, etc.). Through the adhesion of the flexible adhesive layer, the optical fiber can fit tightly to the surface of the monitored object, thereby accurately sensing changes in its physical state.

[0027] Fiber Bragg grating (FBG): A periodic refractive index modulation structure formed by writing in the core of an optical fiber using an ultraviolet laser. Its working principle is to use the periodic arrangement of the grating to reflect light of a specific wavelength, and the reflected wavelength will shift with the change of external physical quantities (such as temperature and strain). This characteristic enables the fiber Bragg grating to convert the change of physical quantities into the change of light wavelength, thereby achieving high-precision sensing measurement.

[0028] Distributed acoustic sensing (DAS): uses the phase change of backward Rayleigh scattered light in the optical fiber to detect the vibration signal distributed along the optical fiber. DAS technology can monitor the tiny vibrations along the optical fiber in real time by analyzing the changes in the optical signal inside the optical fiber. Its core principle is to use the optical fiber itself as a sensor to detect vibration events along the optical fiber to achieve distributed monitoring of long-distance areas.

[0029] Ice cone growth model: A mathematical model based on thermodynamics and mechanics principles, used to describe the formation, growth and shedding of icicles on the eaves surface. The model comprehensively considers external conditions such as ambient temperature, humidity, wind speed, solar radiation, as well as internal factors such as the heat conduction characteristics of the eaves surface, the weight distribution of icicles, and stress changes.

[0030] Embodiment 1: Embodiment 1 of the present invention provides an ice cone monitoring method based on adhesive optical fiber, such as Figure 1 As shown, the following steps are included: Step 1: Use adhesive optical fiber to obtain the temperature signal, strain signal and vibration signal of the eaves surface to be detected, and pre-process the collected signals.

[0031] Step 1.1: Use adhesive optical fiber to obtain the temperature signal, strain signal and vibration signal of the eaves surface to be tested.

[0032] Step 1.1.1: Design the fiber layout density and fiber Bragg grating node spacing.

[0033] In a specific implementation, the fiber optic deployment density is calculated based on the eave length and the maximum predicted length of the ice cone: .

[0034] in, is the fiber optic cable density, is the eaves length; is the maximum predicted length of the ice cone, which is calculated based on historical meteorological data (such as snow accumulation, average daily temperature) and the eaves inclination angle; 0.8 is the redundancy factor, which ensures that there is a 20% overlap in the adjacent optical fiber coverage areas to avoid monitoring blind spots. Make corrections.

[0035] Step 1.2: Design of fiber Bragg grating (FBG) node spacing, determined by the spatial resolution requirements: .

[0036] in, is the FBG node spacing, is the sampling frequency, is the speed of light, is the effective refractive index of the optical fiber.

[0037] Step 1.1.2: According to the design results, optical fiber is attached to the surface of the eaves, and the signal is collected according to the change of the optical fiber wavelength.

[0038] In a specific implementation, when the optical fiber is pasted on the eave surface according to the design results, it is ensured that the pasting area is flat and clean, without oil stains and other factors that affect the optical fiber adhesion, and then the bottom adhesive is applied, and the optical fiber is pasted to the lower surface of the eave in an array form (such as a V shape or an S shape), such as Figure 2 shown.

[0039] In this embodiment, flexible optical fibers are attached to the surface of the eaves in an array to form a dense monitoring grid. By using fiber grating (FBG) or distributed acoustic sensing (DAS) technology, the sensor network can monitor the temperature, strain and vibration signals of the eaves surface in real time. Fiber grating technology uses the change of grating reflection wavelength to sense small changes in temperature and strain, while distributed acoustic sensing technology captures vibration signals by detecting the propagation characteristics of sound waves along the optical fiber.

[0040] Step 1.2: Preprocess the acquired signals.

[0041] Step 1.2.1: Use discrete wavelet denoising to capture the micro-vibration of the ice cone, avoid signal aliasing, and retain the waveform characteristics without damaging the mutation value.

[0042] In a specific implementation, discrete wavelet denoising is used for preprocessing, the wavelet base is Db4, the decomposition level is 5, and the 1-100 Hz frequency band signal is retained: .

[0043] in, represents the processed waveform, is the wavelet basis function; is the scale factor, which is used to determine the noise reduction range; is the translation factor, used to correct the waveform.

[0044] Step 1.2.2: The strain error caused by thermal expansion of the optical fiber is corrected by temperature-strain decoupling to further amplify the peak value of the ice cone point.

[0045] In a specific implementation, the temperature-strain decoupling formula is: , .

[0046] in, is the corrected optical fiber strain; is the measured optical fiber strain; is the thermal expansion coefficient of optical fiber, generally ; is the temperature change; is the wavelength shift; is the temperature sensitivity, generally .

[0047] Step 2: Construct an ice cone growth model according to the collected signals, and monitor the ice cone growth status based on the ice cone growth model.

[0048] Step 2.1: Construct an ice cone growth model based on the collected signals.

[0049] Combining the freezing rate, strain mutation and accumulated vibration energy changes, an ice cone growth model is constructed to identify the key characteristics of ice cone formation, growth and shedding. The ice cone growth state is quantified through the ice cone growth model, and the vibration energy integration method is used to distinguish natural vibration from risk signals. The ice cone state is described from three perspectives: thermodynamics, mechanics and vibration characteristics, which together constitute a risk index.

[0050] Step 2.1.1: Use the ice cone freezing rate to reflect the ice layer expansion rate.

[0051] In a specific embodiment, the ice cone freezing rate is calculated to directly reflect the ice layer expansion rate: , .

[0052] in, Indicates the ice cone freezing rate, It represents the rate of change of temperature with time; is the thermal conductivity of ice; is the latent heat of ice, generally ; It is one of the criteria for measuring the speed of ice expansion and the risk of ice cone falling off.

[0053] Step 2.1.2: Use the strain mutation to reflect the severity of the local deformation of the optical fiber.

[0054] In a specific implementation, the strain mutation is calculated to reflect the severity of the local deformation of the optical fiber: .

[0055] in, for The corrected strain at the moment; is the strain value at adjacent moments, It is the mutation coefficient, one of the criteria for measuring the risk of ice screw falling off.

[0056] Step 2.1.3: Quantify the vibration energy to describe the internal cracks in the ice cone.

[0057] In a specific embodiment, the vibration energy is quantified to describe the internal cracks of the ice cone: .

[0058] in, is the Fourier transform of the moving signal, which represents the energy distribution of the signal in the frequency domain; Indicates the accumulated vibration energy and is one of the criteria for measuring the risk of ice screw falling off.

[0059] Step 2.2: Monitor the growth of the ice cone based on the ice cone growth model. Specifically, monitor whether the ice layer expands, whether the optical fiber is partially deformed, and whether the accumulated vibration energy reaches a threshold, thereby monitoring the growth of the ice cone.

[0060] Step 3: Select the risk indicator and determine the risk index of the current risk indicator based on the real-time growth status of the ice cone.

[0061] This embodiment takes the icing rate as the main factor, takes into account the mechanical and vibration characteristics, evaluates the fall risk through multi-parameter fusion, and then combines it with the dynamic threshold method to make decisions. In addition, the random forest algorithm is used to classify the monitoring data to achieve dynamic graded warning and adaptive weight adjustment of ice cone risk.

[0062] Step 3.1: Select risk indicators.

[0063] This embodiment uses the ice layer expansion speed, the local deformation speed of the optical fiber and the accumulated vibration energy level as risk indicators.

[0064] Step 3.2: Determine the risk index of the current risk indicator based on the real-time growth status of the ice cone.

[0065] In a specific implementation, the risk index is calculated and the risk weight is adaptively adjusted: , .

[0066] in, represents the risk index, The weights corresponding to the ice layer expansion speed, mutation coefficient, and accumulated vibration energy are roughly set during the initial calculation and then adaptively adjusted. Indicates The risk index prediction value of group data; Represents the true risk index, which is calculated by the classic random forest algorithm.

[0067] Step 3.3: Use the classic random forest algorithm to divide the risk index according to the risk indicators.

[0068] In a specific implementation, the risk index is divided by the classic random forest algorithm, and the input features are: risk index , Risk index change rate , vibration peak , the output is: the real risk index , used for weight adaptation described in step 3.2.

[0069] Step 3.4: Calculate the risk index based on the real-time growth status of the ice cone and adaptively adjust the risk weight.

[0070] Specifically, when Alarm the corresponding location. is the dynamic threshold; when When the data is used as feedback, the weights are modified according to steps 3.2 and 3.3.

[0071] Step 3.5: Adjust the dynamic warning threshold according to different ambient temperatures.

[0072] In a specific implementation, dynamic threshold adjustment is performed according to different ambient temperatures: .

[0073] in, is the dynamic threshold, is the baseline threshold, set according to environmental conditions; It is the temperature sensitivity factor, which is set according to the sensitivity requirement of early warning; is the current ambient temperature; The reference ambient temperature is recommended to be 0°C (ice melting limit temperature).

[0074] Step 4: Perform multi-parameter fusion analysis based on the risk index to assess the risk of ice cone falling.

[0075] Step 5: Make risk decisions and early warnings based on the fall risk results combined with the dynamic threshold method, and regularly perform calibration and dynamic baseline correction based on the fall risk results.

[0076] This embodiment eliminates sensor drift and environmental interference through regular calibration and dynamic baseline correction, ensures data reliability and warning accuracy, and ensures long-term stable operation of the monitoring system.

[0077] Step 5.1: Make risk decisions and early warnings based on the fall risk results combined with the dynamic threshold method, such as informing pedestrians on the roadside of the risk of falling icicles through sound and light alarms.

[0078] Step 5.2: Perform calibration and dynamic baseline correction regularly based on fall risk results.

[0079] Step 5.2.1: Perform heating calibration on the fiber optic temperature sensor.

[0080] This embodiment performs heating calibration on the optical fiber temperature sensor to eliminate zero drift and ensure temperature measurement accuracy. Specifically, the zero drift of the temperature sensor is corrected by recording the FBG wavelength offset before and after heating.

[0081] Step 5.2.2: Set a sliding window and dynamically update the ice-free period data baseline. The ice-free period data baseline is the data when there is no ice, which is used to compare with the data after ice formation to achieve ice cone monitoring.

[0082] In a specific implementation, a sliding window (periodic calibration period) is set to dynamically update the ice-free period data baseline to eliminate the impact of environmental changes (such as seasonal changes) on the monitoring results. The baseline calculation formula is as follows: .

[0083] in, It is the variance baseline of the current sliding window of a certain monitoring data of the optical fiber; It is the variance baseline of a window of a certain monitoring data of the optical fiber; is the variance of the current sliding window of a certain monitoring data of the optical fiber. It is the forgetting factor and needs to be adjusted according to different monitoring requirements.

[0084] Step 5.3: Calculate whether to start calibration; if Then start manual calibration; if Then the variance baseline is updated for subsequent calculations.

[0085] in, To calibrate the sensitivity coefficient, set it according to the actual situation.

[0086] This embodiment introduces an environmental noise filtering algorithm and a temperature-based strain compensation mechanism to eliminate the influence of interference factors such as wind and sunshine on the monitoring results.

[0087] In order to better illustrate the effect of the method of this embodiment, a commercial building in a northern city is taken as an example for illustration: Eaves length , install 13-channel adhesive fiber optic sensor ( ); the average daily temperature in winter is −5∘C, and the lowest temperature at night is −15∘C; S1: Clean the eaves surface, apply the base adhesive, paste the optical fiber, and adjust the node spacing. .

[0088] S2: Temperature and strain signals are collected through fiber Bragg grating (FBG), and vibration signals are collected through distributed acoustic sensing (DAS), with a sampling frequency of 2kHz.

[0089] S3: Perform wavelet denoising and temperature-strain decoupling.

[0090] S4: Calculate the freezing rate : Temperature change rate .

[0091] Ice contact area .

[0092] Freezing rate , indicating that the ice cone is growing slowly.

[0093] S5: Calculation of strain mutation coefficient , assuming , indicating that the deformation of the eaves has intensified.

[0094] S6: Calculate the accumulated vibration energy , assuming , indicating that the crack energy inside the ice cone is low.

[0095] S7: Calculate risk factor , assuming the weight factor They are 0.6, 0.3, 0.1 respectively. .

[0096] S8: Input random forest classification, assuming the output is low risk.

[0097] S9: Adjust the dynamic threshold, assuming ,but .

[0098] S10: Early warning execution, , no warning is triggered.

[0099] S11: Heating calibration, baseline correction.

[0100] Embodiment 2: Embodiment 2 of the present invention provides an ice cone monitoring system based on adhesive optical fiber, including: The data acquisition module is configured to acquire the temperature signal, strain signal and vibration signal of the surface of the eaves to be detected by using a sticky optical fiber, and pre-process the acquired signals; A growth status monitoring module is configured to construct an ice cone growth model according to the collected signals, and monitor the growth status of the ice cone based on the ice cone growth model; A risk index determination module is configured to select a risk index and determine a risk index of a current risk index according to the real-time growth status of the ice cone; A risk assessment module is configured to perform multi-parameter fusion analysis based on the risk index to assess the risk of ice pick falling; The decision-making and warning module is configured to make risk decisions and warnings based on the fall risk results in combination with the dynamic threshold method, and to perform regular calibration and dynamic baseline correction based on the fall risk results.

[0101] Embodiment three: Embodiment 3 of the present invention provides a medium on which a program is stored. When the program is executed by a processor, the steps of the ice cone monitoring method based on adhesive optical fiber as described in Embodiment 1 of the present invention are implemented.

[0102] Embodiment 4: Embodiment 4 of the present invention provides a device, including a memory, a processor, and a program stored in the memory and executable on the processor. When the processor executes the program, the steps in the ice cone monitoring method based on adhesive optical fiber as described in Embodiment 1 of the present invention are implemented.

[0103] The steps involved in the above embodiments 2, 3 and 4 correspond to the method embodiment 1. For the specific implementation methods, please refer to the relevant description part of embodiment 1.

[0104] Those skilled in the art should understand that the modules or steps of the present invention described above can be implemented by a general-purpose computer device, or alternatively, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.

[0105] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. An ice cone monitoring method based on adhesive optical fiber, characterized in that: The following steps are involved: Adhesive optical fiber is used to obtain the temperature signal, strain signal and vibration signal of the eaves surface to be tested, and the collected signals are preprocessed; An ice cone growth model is constructed according to the collected signals, and the growth status of the ice cone is monitored based on the ice cone growth model; Select risk indicators and determine the risk index of the current risk indicator based on the real-time growth status of the ice cone; Conduct multi-parameter fusion analysis based on risk index to assess ice cone fall risk; Risk decisions and early warnings are made based on the fall risk results combined with the dynamic threshold method, and calibration and dynamic baseline corrections are performed regularly based on the fall risk results.

2. The ice cone monitoring method based on adhesive optical fiber according to claim 1, characterized in that: The specific steps of using adhesive optical fiber to obtain the temperature signal, strain signal and vibration signal of the eaves surface to be detected are as follows: Design the fiber layout density and fiber Bragg grating node spacing; According to the design results, optical fibers are attached to the surface of the eaves, and signals are collected based on changes in the wavelength of the optical fibers.

3. The ice cone monitoring method based on adhesive optical fiber according to claim 2, characterized in that: When sticking optical fibers on the eaves surface according to the design results, ensure that the sticking area is flat and clean, then apply the base adhesive and stick the optical fibers in an array to the lower surface of the eaves.

4. The ice cone monitoring method based on adhesive optical fiber according to claim 1, characterized in that: The specific steps for preprocessing the collected signals are as follows: Using discrete wavelet denoising to capture ice cone micro-vibration; The peak value of the ice cone point is further amplified through temperature-strain decoupling.

5. The ice cone monitoring method based on adhesive optical fiber according to claim 1, characterized in that: The specific steps of constructing the ice cone growth model based on the collected signals are: The freezing rate of ice cones is used to reflect the expansion rate of ice layer; The strain mutation is used to reflect the severity of the local deformation of the optical fiber; Quantifying vibration energy to describe cracks inside ice cones.

6. The ice cone monitoring method based on adhesive optical fiber according to claim 1, characterized in that: The specific steps for determining the risk index of the current risk indicator based on the real-time growth status of the ice cone are: Use the classic random forest algorithm to divide the risk index according to the risk indicators; Calculate the risk index based on the real-time growth status of the ice cone and adjust the risk weight adaptively; Dynamically adjust the warning threshold according to different ambient temperatures.

7. The ice cone monitoring method based on adhesive optical fiber according to claim 1, characterized in that: The specific steps for regular calibration and dynamic baseline correction based on fall risk results are: Perform heating calibration on the fiber optic temperature sensor; Set up a sliding window to dynamically update the ice-free period data baseline.

8. An ice cone monitoring system based on adhesive optical fiber, characterized in that: include: The data acquisition module is configured to acquire the temperature signal, strain signal and vibration signal of the surface of the eaves to be detected by using a sticky optical fiber, and pre-process the acquired signals; A growth status monitoring module is configured to construct an ice cone growth model according to the collected signals, and monitor the growth status of the ice cone based on the ice cone growth model; A risk index determination module is configured to select a risk index and determine a risk index of a current risk index according to the real-time growth status of the ice cone; A risk assessment module is configured to perform multi-parameter fusion analysis based on the risk index to assess the risk of ice pick falling; The decision-making and warning module is configured to make risk decisions and warnings based on the fall risk results in combination with the dynamic threshold method, and to perform regular calibration and dynamic baseline correction based on the fall risk results.

9. A computer-readable storage medium, characterized in that: A plurality of instructions are stored therein, and the instructions are suitable for being loaded by a processor of a terminal device and executing the ice cone monitoring method based on adhesive optical fiber as described in any one of claims 1-7.

10. A terminal device, characterized in that: It includes a processor and a computer-readable storage medium, the processor is used to implement various instructions; the computer-readable storage medium is used to store multiple instructions, and the instructions are suitable for being loaded by the processor and executing the ice cone monitoring method based on adhesive optical fiber as described in any one of claims 1-7.

Images