Transmission tower deformation prediction method and device and computer program product

Abstract

The invention discloses a power transmission tower deformation prediction method and device and a computer program product, and the method comprises the steps: S1, obtaining the multi-source monitoring data of a power transmission tower, including key node strain data, tower body distributed deflection data and inclination monitoring data; s2, performing data fusion processing on the multi-source monitoring data, including dynamic load interference separation, temperature compensation and multi-source data filtering, and generating deformation state data; and S3, inputting the deformation state data into a pre-trained deformation prediction model, outputting an iron tower deformation prediction result, and identifying an abnormal type. According to the invention, a transmission tower full-scale deformation sensing system is constructed by fusing high-density distributed strain monitoring of an ultra-weak fiber grating array, vector stress sensing of a three-dimensional strain rosette and a multi-source heterogeneous data intelligent fusion technology; the technical bottlenecks of temperature-strain cross sensitivity, difficulty in dynamic load interference separation, insufficient local complex stress field analysis and the like in a traditional monitoring method are effectively solved.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and particularly relates to a method, device and computer program product for predicting the deformation of transmission towers. Background Art

[0002] With the continuous expansion of the scale of power systems, the structural integrity of transmission towers, as the core infrastructure of the power grid, faces severe challenges. Traditional deformation monitoring technologies have significant technical bottlenecks in practical applications: resistance strain gauges are vulnerable to strong electromagnetic environments, and complex wiring is difficult to meet the long-term stable monitoring requirements of high-voltage transmission scenarios; optical devices such as total stations are limited by meteorological conditions, and the measurement accuracy drops sharply in low visibility environments such as rain, snow, fog and haze; although GPS positioning technology has the ability of wide-area coverage, its spatial resolution is not sufficient to identify millimeter-level local deformations, and the multipath effect is likely to cause data distortion. The above methods are difficult to meet the requirements of the smart grid for high-precision structural health monitoring in terms of real-time performance, environmental adaptability and monitoring density.

[0003] The breakthrough of fiber optic sensing technology provides a new technical path for the monitoring of transmission towers. Among them, the fiber Bragg grating (FBG) technology realizes distributed strain measurement through wavelength modulation, but its inherent characteristics limit the engineering application effect. The high reflectivity characteristic of traditional FBG sensors results in limited single-fiber multiplexing capacity, making it difficult to achieve high-density layout; at the same time, the cross-sensitivity problem between temperature and strain is likely to cause data demodulation errors in complex environment monitoring. Although the ultra-weak fiber grating (UW-FBG) technology realizes large-scale multiplexing of tens of thousands of sensing points on a single fiber by reducing the reflectivity, and significantly improves the monitoring spatial resolution by combining optical time domain reflectometry and wavelength division multiplexing technology, there are still systematic technical obstacles in the engineering application under the special working conditions of transmission towers.

[0004] The current technical bottlenecks are mainly reflected in the precise analysis level of multi-physical field coupling interference. The axial temperature gradient formed by transmission towers in a wide temperature range environment will cause the accumulation of distributed strain inversion errors, and the existing temperature compensation methods are difficult to achieve dynamic correction of the three-dimensional temperature field; in terms of dynamic load interference, there is an aliasing phenomenon between the high-frequency signals of wind vibration and the low-frequency characteristics of ice-covered deformation in the time-frequency domain, and traditional filtering methods cannot effectively separate the strain baseline drift under composite working conditions; in the dimension of structural damage identification, conventional single-mode fiber optic sensors can only obtain uniaxial strain information, and lack the vector sensing ability for typical faults such as shear deformation of bolt connection surfaces and multi-directional stress concentration in weld areas; in addition, existing monitoring systems mostly adopt a single physical quantity analysis mode and fail to build a collaborative analysis model of strain, vibration, tilt and environmental parameters, resulting in a high false alarm rate in structural anomaly diagnosis. These technical defects seriously restrict the in-depth application of fiber optic sensing technology in the monitoring of transmission towers, and there is an urgent need to establish a new monitoring system that combines multi-dimensional perception and intelligent analysis. Summary of the Invention

[0005] The technical problem to be solved by the embodiments of the present invention is to provide a method, device and computer program product for predicting the deformation of a transmission tower, so as to realize the full-dimensional deformation monitoring of the transmission tower, with high precision, strong anti-interference and long-term stability.

[0006] To solve the above technical problem, the present invention provides a method for predicting the deformation of a transmission tower, including:

[0007] Step S1, obtaining multi-source monitoring data of the transmission tower, including key node strain data, tower body distributed deflection data and inclination monitoring data;

[0008] Step S2, performing data fusion processing on the multi-source monitoring data, including dynamic load interference separation, temperature compensation and multi-source data filtering, to generate deformation state data;

[0009] Step S3, inputting the deformation state data into a pre-trained deformation prediction model, and outputting the tower deformation prediction result and identifying the abnormal type.

[0010] Preferably, the step S2 specifically includes:

[0011] Obtaining acceleration data;

[0012] Performing Fourier transform on the acceleration data to obtain a frequency-domain signal, and determining the vibration frequency of the dynamic event from the frequency-domain signal;

[0013] Performing wavelet transform on the acceleration data to obtain a time-frequency signal, and performing time-frequency analysis on the time-frequency signal to locate the start and end times of the dynamic event;

[0014] Filtering the tower body distributed deflection monitoring data to separate the dynamic event, and obtaining the filtered tower body distributed deflection monitoring data.

[0015] Preferably, after obtaining the filtered tower body distributed deflection monitoring data, the method further includes:

[0016] According to the temperature-wavelength monitoring data, using the double-grating differential method to correct the filtered tower body distributed deflection monitoring data, and obtaining the corrected tower body distributed deflection monitoring data.

[0017] Preferably, the correcting the filtered tower body distributed deflection monitoring data according to the temperature-wavelength monitoring data by using the double-grating differential method includes:

[0018] Obtaining the temperature-wavelength monitoring data according to the following formula:

[0019] Δλ T =K TΔT

[0020] wherein, Δλ T represents the wavelength drift caused by temperature change; K T represents the temperature sensitivity coefficient of the temperature compensation grating; ΔT represents the temperature change;

[0021] According to the following formula, correct the filtered tower body distributed deflection monitoring data:

[0022]

[0023] wherein, με represents the corrected tower body distributed deflection monitoring data; λ t represents the wavelength of the currently stressed grating; λ0 represents the initial wavelength of the currently stressed grating; λ r represents the wavelength of the current temperature compensation grating; λ r0 represents the initial wavelength of the current temperature compensation grating; K ε represents the strain sensitivity coefficient of the optical fiber.

[0024] Preferably, after obtaining the corrected tower body distributed deflection monitoring data, the method further includes:

[0025] Based on the simply supported beam bending theory, convert the corrected tower body distributed deflection monitoring data into curvature, and then generate the three-dimensional deflection curve of the iron tower by point-by-point integration through the tangent angle recursion algorithm.

[0026] Preferably, the converting the corrected tower body distributed deflection monitoring data into curvature includes:

[0027] According to the following formula, convert the corrected tower body distributed deflection monitoring data into the curvature:

[0028]

[0029] wherein, K represents the curvature; Δλ B represents the total drift of the grating center wavelength; h represents the vertical distance from the grating neutral layer to the measurement surface; K ε represents the strain sensitivity coefficient of the grating, λ B represents the initial wavelength of the grating center.

[0030] Preferably, after obtaining the corrected tower body distributed deflection monitoring data, the method further includes:

[0031] Determine the inclination angle of the iron tower according to the inclination monitoring data through the angle recursion algorithm;

[0032] Correspondingly, the fusing the monitoring data includes:

[0033] Fuse the strain monitoring data of the key nodes, the three-dimensional deflection curve of the iron tower, and the inclination angle of the iron tower.

[0034] The present invention also provides a transmission tower deformation prediction device, including:

[0035] An acquisition module, which is configured to acquire multi-source monitoring data of a transmission tower, including key node strain data, tower body distributed deflection data, and inclination monitoring data;

[0036] A preprocessing module, which is configured to perform data fusion processing on the multi-source monitoring data, including dynamic load interference separation, temperature compensation, and multi-source data filtering, to generate deformation state data;

[0037] A processing module, which is configured to input the deformation state data into a pre-trained deformation prediction model, output the transmission tower deformation prediction result, and identify the abnormal type.

[0038] The present invention also provides a transmission tower deformation prediction device, including:

[0039] One or more processors;

[0040] A memory;

[0041] One or more applications, wherein the one or more applications are stored in the memory and are configured to be executed by the one or more processors, and the one or more applications are configured to execute the transmission tower deformation prediction method described above.

[0042] The present invention also provides a computer program product, including computer instructions, and the computer instructions instruct a computer device to perform the operations corresponding to the method.

[0043] Implementing the present invention has the following beneficial effects: By integrating the high-density distributed strain monitoring of the ultra-weak fiber Bragg grating array, the vector stress perception of the three-dimensional strain rosette, and the intelligent fusion technology of multi-source heterogeneous data, a full-scale deformation perception system for transmission towers is constructed, effectively solving the technical bottlenecks such as temperature-strain cross-sensitivity, difficulty in separating dynamic load interference, and insufficient analysis of local complex stress fields in traditional monitoring methods. Based on the dual-grating differential temperature compensation mechanism and the dynamic signal adaptive filtering algorithm, the strain inversion accuracy and anti-interference ability are significantly improved; combined with the time series prediction model of the long short-term memory neural network and the multi-physical field collaborative classifier, the accurate prediction of the deformation trend of the iron tower and the intelligent identification of abnormal types (such as bolt loosening, ice overload) are realized, providing a highly reliable and all-weather monitoring solution for the structural health assessment and risk warning of transmission towers, and greatly improving the safe operation and maintenance level of power grid infrastructure. Description of the Drawings

[0044] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0045] Figure 1 It is a schematic flowchart of a method for predicting the deformation of a transmission tower in Embodiment 1 of the present invention.

[0046] Figure 2 It is a specific flowchart of step S2 in Embodiment 1 of the present invention.

[0047] Figure 3 It is a specific flowchart of step S3 in Embodiment 1 of the present invention.

[0048] Figure 4 It is a schematic structural diagram of a device for predicting the deformation of a transmission tower in Embodiment 2 of the present invention.

[0049] Figure 5 It is a schematic structural diagram of an electronic device provided by the embodiments of the present invention. Specific embodiments

[0050] The following descriptions of the embodiments refer to the drawings to exemplify specific embodiments in which the present invention can be implemented.

[0051] Please refer to Figure 1 As shown, Embodiment 1 of the present invention provides a method for predicting the deformation of a transmission tower, including:

[0052] Step S1, obtaining multi-source monitoring data of the transmission tower, including key node strain data, tower body distributed deflection data, and inclination monitoring data;

[0053] Step S2, performing data fusion processing on the multi-source monitoring data, including dynamic load interference separation, temperature compensation, and multi-source data filtering, to generate deformation state data;

[0054] Step S3, inputting the deformation state data into a pre-trained deformation prediction model, and outputting the tower deformation prediction result and identifying the abnormal type.

[0055] Specifically, in step S1, the strain monitoring data of key nodes is obtained by setting ultra-weak fiber Bragg grating (UW-FBG) strain rosette sensors in the stress concentration areas and collecting the data of the UW-FBG strain rosette sensors. The stress concentration areas include the tower corners, cross-arm joints, and cross-bracing points of the iron tower. Each UW-FBG strain rosette sensor includes 3 UW-FBG sensing units, and the wavelengths of the 3 UW-FBG sensing units are 1536 nm, 1542 nm, and 1548 nm in sequence, covering 0°, 60°, and 120° respectively.

[0056] A strain rosette sensor is a measurement tool based on strain sensors, composed of multiple wires with equal lengths and intersecting each other, forming a grid-like structure. When the strain rosette is subjected to strain, the wires will deform, thereby changing the distance between the wires, resulting in a change in the output voltage of the strain sensor, thus realizing the measurement of the deformation of an object. There are different types of strain rosettes, including biaxial 90° strain rosettes, triaxial strain rosettes, and quadraxial strain rosettes, etc. Biaxial 90° strain rosettes are used in occasions where the principal stress direction is known, while triaxial and quadraxial strain rosettes are used in occasions where the principal stress direction is unknown.

[0057] The distributed deflection monitoring data of the tower body is obtained by continuously arranging fiber optic sensors longitudinally on the main members of the tower body and collecting the data of the fiber optic sensors. The spacing of the fiber optic sensors is 1 - 2 m.

[0058] The strain data obtained by the UW-FBG sensors, also called UW-FBG strain data, is the above-mentioned distributed deflection monitoring data of the tower body. A single UW-FBG sensor can measure the strain in a certain direction. By arranging a dense array of UW-FBG sensors along the optical fiber, long-distance and high-density continuous strain monitoring can be achieved (such as the overall deflection monitoring of transmission iron towers).

[0059] The tilt monitoring data is obtained by setting UW-FBG tilt sensors at the top and the base of the tower and collecting the data of the UW-FBG tilt sensors.

[0060] In step S2, perform data fusion processing on the multi-source monitoring data, and use Kalman filtering to filter the fused monitoring data to generate deformation state data.

[0061] In actual operation, after obtaining the monitoring data, dynamic load separation can also be introduced to separate the instantaneous fluctuations caused by short-term dynamic loads (such as wind vibration, ice coating) from the long-term static deformations (such as foundation settlement, material fatigue), and retain the long-term deformation signal. Specifically, as Figure 2 shown, after the above step S1, step S2 of the embodiment of the present invention may further include the following steps S210 to S240:

[0062] Step 210, obtain acceleration data.

[0063] Among them, the acceleration data can be obtained by installing triaxial accelerometers at key positions such as the tower top and cross arms; the accelerometers can measure vibration acceleration (frequency range 0.1 - 50 Hz) and capture dynamic events such as wind vibration and mechanical shock. In actual operation, external parameters such as wind speed, temperature, humidity, ice coating thickness, etc. can also be synchronously recorded to assist in load classification.

[0064] Step S220: Perform Fourier transform on the acceleration data to obtain a frequency-domain signal, and determine the vibration frequency of the dynamic event from the frequency-domain signal.

[0065] Among them, the Fourier transform is to transform the signal in the time domain into a signal in the frequency domain. As the domain changes, the understanding angle of the same thing also changes accordingly. Therefore, some places that are difficult to process in the time domain can be processed more simply in the frequency domain.

[0066] In this step, the vibration frequency of the dynamic event can be obtained by determining the main vibration frequency from the frequency-domain signal; for example, the wind vibration energy is concentrated in 0.1 - 2 Hz (low-frequency swing), and strong wind turbulence may trigger high-frequency vibrations of 5 - 10 Hz; therefore, determining the main vibration frequency means determining the dynamic event.

[0067] Step S230: Perform wavelet transform on the acceleration data to obtain a time-frequency signal, and perform time-frequency analysis on the time-frequency signal to locate the start and end times of the dynamic event.

[0068] Among them, the wavelet transform (WT) can provide a "time-frequency" window that changes with frequency and is an ideal tool for signal time-frequency analysis and processing. Its main feature is that through the transform, it can fully highlight the characteristics of certain aspects of the problem, perform local analysis of time (space) frequency, gradually perform multi-scale refinement on the signal (function) through stretching and translation operations, and finally achieve time subdivision at high frequencies and frequency subdivision at low frequencies, and can automatically adapt to the requirements of time-frequency signal analysis, so as to focus on any details of the signal.

[0069] In this step, the start and end times of the dynamic event can be located by performing time-frequency analysis on the non-stationary signals (such as instantaneous strong wind) in the time-frequency signal.

[0070] Step S240: Filter the tower body distributed deflection monitoring data to separate the dynamic event and obtain the filtered tower body distributed deflection monitoring data.

[0071] Among them, filtering can adopt low-pass filtering, band-pass filtering, adaptive filtering, etc.; specifically, the cut-off frequency of low-pass filtering can be 0.1 Hz to retain long-term deformation; band-pass filtering can retain frequencies from 1 to 10 Hz to extract strain fluctuations related to wind vibration; adaptive filtering can use the accelerometer data as a reference signal to eliminate strain interference caused by vibration through the least mean square algorithm (LMS).

[0072] The wavelength change of the UW-FBG sensor is affected by both strain and temperature at the same time. The original data (i.e., wavelength change) contains the combined effects of strain and temperature and cannot be directly used for structural deformation analysis. Therefore, after the above step S240, a temperature compensation mechanism can be adopted to eliminate the influence of temperature on the wavelength and correct the original data. Specifically, after the above step S240, the embodiments of the present invention can further include the following steps:

[0073] According to the temperature-wavelength monitoring data, the double-grating difference method is used to correct the filtered tower body distributed deflection monitoring data to obtain the corrected tower body distributed deflection monitoring data.

[0074] Among them, the temperature-wavelength monitoring data can be obtained by arranging independent temperature compensation gratings in non-loaded areas (such as the tower base), and the wavelength change thereof is only caused by temperature (without strain interference); then, using the data of the temperature compensation grating, the temperature influence is deducted from the total wavelength change of the grating in the loaded area; specifically, as Figure 3 shown, the above steps can further include the following step S310 and step S320:

[0075] Step S310, according to the following formula (1), obtain the temperature-wavelength monitoring data;

[0076] Δλ T =K T ΔT (1)

[0077] Among them, Δλ T represents the wavelength drift amount caused by temperature change; K T represents the temperature sensitivity coefficient of the temperature compensation grating; ΔT represents the temperature change amount.

[0078] Step S320, according to the following formula (2), correct the filtered tower body distributed deflection monitoring data;

[0079]

[0080] Among them, με represents the corrected tower body distributed deflection monitoring data; λ t represents the wavelength of the current loaded grating; λ0 represents the initial wavelength of the current loaded grating; λ r represents the wavelength of the current temperature compensation grating; λ r0represents the initial wavelength of the current temperature-compensated grating; K ε represents the strain sensitivity coefficient of the optical fiber.

[0081] In the monitoring of transmission towers, if the temperature is not compensated, the low temperature in winter may cause the grating wavelength to contract, which may be misjudged as the compression deformation of the tower body; the high temperature in summer may mask the true structural tension. Through the temperature compensation mechanism, the true deformation caused by mechanical loads (such as wind vibration and icing) can be accurately identified. After temperature compensation, the interference of environmental temperature fluctuations on the monitoring data can be eliminated, avoiding misjudgments (such as mistaking temperature expansion for structural deformation); improving the calculation accuracy of key parameters such as strain and deflection; ensuring the stability of long-term monitoring and adapting to the seasonal temperature changes (-20°C to 60°C) of transmission towers.

[0082] The measured data after temperature compensation is με, which represents the structural deformation amount caused only by strain. Based on this, physical quantities such as deflection and tilt angle can be further inversely calculated through algorithms; specifically, after the above step S320, this embodiment may further include the following steps:

[0083] Based on the simple-supported beam bending theory, the corrected distributed deflection monitoring data of the tower body is converted into curvature, and then the three-dimensional deflection curve of the tower is generated by point-by-point integration through the tangent angle recurrence algorithm.

[0084] Among them, the simple-supported beam bending theory mainly involves the bending deformation of a simple-supported beam under external forces and its calculation methods. A simple-supported beam refers to a beam with both ends resting on supports, where the supports only restrict the vertical displacement of the beam, and the beam ends can rotate freely. In order to prevent the entire beam from moving horizontally, a horizontal constraint is added at one end, and the support at this place is called a hinge support, and the support at the other end without a horizontal constraint is called a roller support.

[0085] The bending deformation of a simple-supported beam can be calculated by the integral method and the superposition method. The integral method is to solve the angle of rotation equation and the deflection equation by successively integrating the approximate differential equation of the deflection curve. The superposition method is to divide the beam into several segments, calculate the deflection and angle of rotation for each segment separately, and then superimpose the results.

[0086] In actual operation, the above steps first convert the corrected distributed deflection monitoring data of the tower body into curvature; then, through the relationship between curvature and arc length, the change amount of the central angle is determined; then the change amount of the central angle is gradually accumulated to obtain the current tangent angle; finally, the coordinate increments of each point are calculated using the tangent angle to generate the deflection curve.

[0087] Specifically, the step of "converting the corrected distributed deflection monitoring data of the tower body into curvature" in the above steps may further include the following steps:

[0088] According to the following formula (3), convert the corrected distributed deflection monitoring data of the tower body into curvature:

[0089]

[0090] Among them, K represents curvature; Δλ B represents the total drift of the central wavelength of the grating; h represents the vertical distance from the neutral layer of the grating to the measurement surface; K ε represents the strain sensitivity coefficient of the grating, and λ B represents the initial central wavelength of the grating.

[0091] After the above step S320, the tilt angle can be calculated through the following steps:

[0092] Determine the tilt angle of the iron tower according to the tilt monitoring data through the angle recursion algorithm.

[0093] Among them, the angle recursion algorithm is similar to the above-mentioned chamfer recursion algorithm. Through known conditions, the result is gradually deduced; for example: when calculating the sum of interior angles of a polygon, each interior angle can be gradually accumulated through the recursion algorithm to finally obtain the total sum of interior angles of the polygon. For example, for an n-sided polygon, its sum of interior angles can be calculated by the recursion formula as (n - 2) × 180°.

[0094] The tilt monitoring data in this step is obtained through a UW-FBG tilt sensor. The UW-FBG tilt sensor can convert the tilt angle into the axial strain (tension or compression) of the grating. Furthermore, according to the variation relationship between the tilt angle and the grating wavelength, the tilt angle is inversely calculated; repeating the above steps (i.e., the angle recursion algorithm), the current tilt angle of the iron tower can be obtained.

[0095] In the embodiments of the present invention, the fused monitoring data is the fused key node strain monitoring data, the tower body distributed deflection monitoring data, and the tilt monitoring data; filtering the fused monitoring data can eliminate vibration noise.

[0096] Kalman filtering is an algorithm that uses the state equation of a linear system to optimally estimate the system state through system input and output observation data. Since the observation data includes the influence of noise and interference in the system, the optimal estimate can also be regarded as a filtering process. Data filtering is a data processing technology for removing noise and restoring real data. Kalman filtering can estimate the state of a dynamic system from a series of measurement data with measurement noise when the measurement variance is known.

[0097] Correspondingly, the "fused monitoring data" in the above steps includes: fused key node strain monitoring data, the three-dimensional deflection curve of the iron tower, and the tilt angle of the iron tower.

[0098] In step S3, the filtered fused monitoring data is input into a long short-term memory artificial neural network and a classifier to predict the deformation of the iron tower and identify the abnormal types, so as to obtain the predicted value of the iron tower deformation and the abnormal types.

[0099] Among them, the long short-term memory artificial neural network is trained by the iron tower deformation-strain sample data; the iron tower deformation-strain sample data is obtained by a finite element model; the classifier is trained by the labeled abnormal type samples.

[0100] In actual operation, after obtaining the predicted value of the iron tower deformation through the long short-term memory artificial neural network, the real-time data can be compared with the predicted value, and an early warning is given when the residual exceeds the threshold; for example: the threshold is set as the deflection > L / 500 and the inclination angle > 0.5°.

[0101] The classifier can be obtained through supervised learning, and in actual operation, it can also be obtained through unsupervised learning; for example: the abnormal types are divided by clustering (such as K-means).

[0102] The abnormal types include: local stress concentration (bolt looseness), dynamic wind vibration overload, and progressive inclination.

[0103] Furthermore, multi-sensor data and external environment information (such as wind speed, ice coating) can be combined to infer the cause of the abnormality; for example: if the abnormal strain area is accompanied by a high-frequency vibration signal, it may be caused by wind vibration; if the inclination angle continues to increase and the foundation humidity is high, it may be caused by foundation settlement.

[0104] The identification of abnormal types is the core function of the intelligent monitoring of transmission iron towers. By integrating fiber optic sensing data, machine learning algorithms and physical models, the transformation from data to knowledge is realized, and finally the safety and reliability of power grid infrastructure are guaranteed.

[0105] As Figure 4 shown, corresponding to the method for predicting the deformation of a transmission iron tower according to the first embodiment of the present invention described above, the second embodiment of the present invention provides a device for predicting the deformation of a transmission iron tower, including:

[0106] An acquisition module 410, where the acquisition module 410 is configured to acquire multi-source monitoring data of the transmission iron tower, including key node strain data, tower body distributed deflection data, and inclination monitoring data;

[0107] A preprocessing module 420, where the preprocessing module 420 is configured to perform data fusion processing on the multi-source monitoring data, including dynamic load interference separation, temperature compensation, and multi-source data filtering, to generate deformation state data;

[0108] A processing module 430, which is configured to input the deformation state data into a pre-trained deformation prediction model, output a deformation prediction result of the iron tower, and identify the type of anomaly.

[0109] In one embodiment, the preprocessing module 420 is configured to: obtain acceleration data; perform Fourier transform on the acceleration data to obtain a frequency-domain signal, and determine the vibration frequency of the dynamic event from the frequency-domain signal; perform wavelet transform on the acceleration data to obtain a time-frequency signal, and perform time-frequency analysis on the time-frequency signal to locate the start and end times of the dynamic event; filter the distributed tower deflection monitoring data to separate the dynamic event, and obtain the filtered distributed tower deflection monitoring data.

[0110] In one embodiment, the preprocessing module 420 is configured to: according to the temperature-wavelength monitoring data, adopt a double-grating differential method to correct the filtered distributed tower deflection monitoring data to obtain the corrected distributed tower deflection monitoring data.

[0111] In one embodiment, the preprocessing module 420 is configured to: obtain temperature-wavelength monitoring data according to the following formula;

[0112] Δλ T =K T ΔT

[0113] where, Δλ T represents the wavelength drift caused by temperature change; K T represents the temperature sensitivity coefficient of the temperature compensation grating; ΔT represents the temperature change.

[0114] Correct the filtered distributed tower deflection monitoring data according to the following formula;

[0115]

[0116] where, με represents the corrected distributed tower deflection monitoring data; λ t represents the wavelength of the current stressed grating; λ0 represents the initial wavelength of the current stressed grating; λ r represents the wavelength of the current temperature compensation grating; λ r0 represents the initial wavelength of the current temperature compensation grating; K ε represents the strain sensitivity coefficient of the optical fiber.

[0117] In one embodiment, the preprocessing module 420 is configured to: based on the simply supported beam bending theory, convert the corrected distributed tower deflection monitoring data into curvature, and then generate a three-dimensional deflection curve of the iron tower by point-by-point integration through a tangent angle recurrence algorithm.

[0118] In one embodiment, the preprocessing module 420 is configured to convert the corrected tower body distributed deflection monitoring data into the curvature according to the following formula:

[0119]

[0120] where K represents the curvature; Δλ B represents the total drift of the grating center wavelength; h represents the vertical distance from the grating neutral layer to the measurement surface; K ε represents the strain sensitivity coefficient of the grating, and λ B represents the initial wavelength of the grating center.

[0121] In one embodiment, the preprocessing module 420 is configured to determine the tilt angle of the iron tower according to the tilt monitoring data through an angle recurrence algorithm; and fuse the key node strain monitoring data, the three-dimensional deflection curve of the iron tower, and the tilt angle of the iron tower.

[0122] In one embodiment, the key node strain monitoring data is obtained by setting UW-FBG strain rosette sensors in the stress concentration areas and collecting the data of the UW-FBG strain rosette sensors; the stress concentration areas include the tower corners, cross arm joints, and cross bracing points of the iron tower; each UW-FBG strain rosette sensor includes 3 UW-FBG sensing units, and the wavelengths of the 3 UW-FBG sensing units are 1536 nm, 1542 nm, and 1548 nm in sequence, covering 0°, 60°, and 120° respectively.

[0123] In one embodiment, the tower body distributed deflection monitoring data is obtained by continuously arranging fiber Bragg grating sensors longitudinally on the main members of the tower body and collecting the data of the fiber Bragg grating sensors; the spacing of the fiber Bragg grating sensors is 1 - 2 m.

[0124] The above device is used to execute the method provided in the foregoing embodiment, and its implementation principle and technical effects are similar, which will not be elaborated here.

[0125] The above-mentioned modules may be one or more integrated circuits configured to implement the above methods. For example: one or more Application Specific Integrated Circuits (ASICs), or, one or more microprocessors, or, one or more Field Programmable Gate Arrays (FPGAs), etc. Again, when a certain above-mentioned module is implemented in the form of a processing element scheduler code, the processing element may be a general-purpose processor, such as a Central Processing Unit (CPU) or other processors that can call program code. Again, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0126] Corresponding to the transmission tower deformation prediction method described in the first embodiment of the present invention, the third embodiment of the present invention further provides a transmission tower deformation prediction device, including:

[0127] One or more processors;

[0128] A memory;

[0129] One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more applications are configured to execute the transmission tower deformation prediction method described in the first embodiment of the present invention.

[0130] Corresponding to the transmission tower deformation prediction method described in the first embodiment of the present invention, the fourth embodiment of the present invention further provides a computer program product, including computer instructions, and the computer instructions instruct a computer device to execute the operations corresponding to the transmission tower deformation prediction method described in the first embodiment of the present invention.

[0131] Preferably, the processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor, or the processor may also be any conventional processor. The processor is the control center of the device, and connects various parts of the device through various interfaces and lines.

[0132] The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function, etc., and the data storage area can store relevant data, etc. In addition, the memory may be a high-speed random access memory, or may also be a non-volatile memory, such as a plug-in hard disk, a SmartMedia Card (SMC), a Secure Digital (SD) card, a Flash Card, etc., or the memory may also be other volatile solid-state storage devices.

[0133] It should be noted that the above device may include but is not limited to a processor and a memory, which can be understood by those skilled in the art.

[0134] As Figure 5 shown, an embodiment of the present invention further provides a computer device, which can be integrated into a terminal device or a chip of a terminal device, and the terminal can be a computing device with data processing capabilities. The device includes: a processor 501, a storage medium 502, and a bus 503.

[0135] The storage medium 502 stores program instructions executable by the processor 501. When the computer device 500 runs, the processor 501 communicates with the storage medium 502 through the bus 503, and the processor 501 executes the program instructions to execute the above method embodiments. The specific implementation manners and technical effects are similar and will not be elaborated here.

[0136] As can be seen from the above description, compared with the prior art, the beneficial effects of the present invention are as follows: By integrating the high-density distributed strain monitoring of ultra-weak fiber grating arrays, the vector stress perception of three-dimensional strain rosettes, and the intelligent fusion technology of multi-source heterogeneous data, a full-scale deformation perception system for transmission towers is constructed, effectively solving the technical bottlenecks such as temperature-strain cross-sensitivity, difficulty in separating dynamic load interference, and insufficient analysis of local complex stress fields in traditional monitoring methods. Based on the dual-grating differential temperature compensation mechanism and the dynamic signal adaptive filtering algorithm, the strain inversion accuracy and anti-interference ability are significantly improved; combined with the time-series prediction model of the long short-term memory neural network and the multi-physical field collaborative classifier, accurate prediction of the deformation trend of the tower and intelligent identification of abnormal types (such as bolt loosening, ice overload) are realized, providing a highly reliable and all-weather monitoring solution for the structural health assessment and risk warning of transmission towers, and greatly improving the safe operation and maintenance level of power grid infrastructure.

[0137] The foregoing disclosure is only for the preferred embodiments of the present invention, and of course cannot be used to limit the scope of the rights of the present invention. Therefore, equivalent changes made according to the claims of the present invention still fall within the scope covered by the present invention.

Claims

1. A method for predicting the deformation of a transmission tower, characterized in that, Including: Step S1, obtaining multi-source monitoring data of a transmission tower, including key node strain data, tower body distributed deflection data, and inclination monitoring data; Step S2, performing data fusion processing on the multi-source monitoring data, including dynamic load interference separation, temperature compensation, and multi-source data filtering, to generate deformation state data; Step S3, inputting the deformation state data into a pre-trained deformation prediction model, outputting a tower deformation prediction result, and identifying the type of anomaly.

2. The method according to claim 1, characterized in that, The specific steps of Step S2 include: Obtaining acceleration data; Performing Fourier transform on the acceleration data to obtain a frequency-domain signal, and determining the vibration frequency of a dynamic event from the frequency-domain signal; Performing wavelet transform on the acceleration data to obtain a time-frequency signal, and performing time-frequency analysis on the time-frequency signal to locate the start and end times of the dynamic event; Filtering the tower body distributed deflection monitoring data to separate the dynamic event, and obtaining filtered tower body distributed deflection monitoring data.

3. The method according to claim 2, characterized in that, After obtaining the filtered tower body distributed deflection monitoring data, the method further includes: According to temperature-wavelength monitoring data, using the double-grating differential method to correct the filtered tower body distributed deflection monitoring data, and obtaining corrected tower body distributed deflection monitoring data.

4. The method according to claim 3, wherein The step of correcting the filtered tower body distributed deflection monitoring data according to temperature-wavelength monitoring data using the double-grating differential method includes: Obtaining temperature-wavelength monitoring data according to the following formula: Δλ T = K T ΔT Among them, Δλ T represents the wavelength drift caused by temperature change; K T represents the temperature sensitivity coefficient of the temperature compensation grating; ΔT represents the temperature change amount; Correcting the filtered tower body distributed deflection monitoring data according to the following formula: Among them, με represents the corrected distributed deflection monitoring data of the tower body; λ t represents the wavelength of the currently stressed grating; λ0 represents the initial wavelength of the currently stressed grating; λ r represents the wavelength of the current temperature compensation grating; λ r0 represents the initial wavelength of the current temperature compensation grating; K ε represents the strain sensitivity coefficient of the optical fiber.

5. The method according to claim 3, wherein After obtaining the corrected tower body distributed deflection monitoring data, the method further includes: Based on the simply supported beam bending theory, converting the corrected tower body distributed deflection monitoring data into curvature, and then generating a three-dimensional deflection curve of the tower through point-by-point integration using the tangent angle recurrence algorithm.

6. The method according to claim 5, characterized in that, The step of converting the corrected tower body distributed deflection monitoring data into curvature includes: Converting the corrected tower body distributed deflection monitoring data into the curvature according to the following formula: Among them, K represents curvature; Δλ B represents the total drift of the grating center wavelength; h represents the vertical distance from the grating neutral layer to the measurement surface; K ε represents the strain sensitivity coefficient of the grating, and λ B represents the initial wavelength of the grating center.

7. The method according to claim 3, characterized in that After obtaining the corrected tower body distributed deflection monitoring data, the method further includes: Determining the tower inclination angle according to the inclination monitoring data through the angle recurrence algorithm; Correspondingly, the step of fusing the monitoring data includes: Fusing the key node strain monitoring data, the three-dimensional deflection curve of the tower, and the tower inclination angle.

8. A transmission tower deformation prediction device, characterized in that, Including: An acquisition module configured to obtain multi-source monitoring data of a transmission tower, including key node strain data, tower body distributed deflection data, and inclination monitoring data; A preprocessing module configured to perform data fusion processing on the multi-source monitoring data, including dynamic load interference separation, temperature compensation, and multi-source data filtering, to generate deformation state data; A processing module configured to input the deformation state data into a pre-trained deformation prediction model, output a tower deformation prediction result, and identify the type of anomaly.

9. A transmission tower deformation prediction device, characterized in that, Including: One or more processors; A memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more applications are configured to perform the transmission tower deformation prediction method according to any one of claims 1 to 7.

10. A computer program product, characterized in that, Including computer instructions, the computer instructions instructing the computer device to perform the operations corresponding to the method according to any one of claims 1 to 7.

Images