Power transmission tower flood post-disaster damage analysis method and related device

Abstract

The invention belongs to the field of power transmission towers, and discloses a power transmission tower flood post-disaster damage analysis method and related device.The method comprises the steps that design information, service time and flood intensity information of a power transmission tower are obtained; according to the design information, the service time and the flood intensity information of the power transmission tower, obtaining a flood post-disaster damage state of the power transmission tower through a preset power transmission tower flood post-disaster damage machine learning model; the power transmission tower post-flood damage machine learning model is obtained by the following steps: constructing a numerical analysis probability model of a power transmission tower under different service times; performing flood static pushing and covering analysis on the basis of the numerical analysis probability model of the power transmission tower under different service times, obtaining a flood post-disaster damage state of the power transmission tower under different flood intensities, and generating a training sample; and training a machine learning model according to the training sample to obtain a power transmission tower flood post-disaster damage machine learning model. Repeated calculation of a traditional method is avoided, and the speed of power transmission tower group flood post-disaster damage assessment is greatly improved.

Description

Technical Field

[0001] The invention belongs to the field of transmission towers and relates to a method for analyzing damage of transmission towers after flood disasters and related devices. Background Art

[0002] Power safety is the cornerstone of urban safety. As the lifeline of the city, its stability is of vital importance. As the key node of power transmission, transmission towers play a core role in dense transmission lines. However, the transmission towers on the transmission lines are very dense, and these transmission tower groups are extremely susceptible to the chain effects of geological disasters. Once a disaster occurs, a large number of transmission towers may be damaged, seriously impacting the safe operation of the power grid, and even inducing large-scale power outages, which will have a profound impact on the lives of urban residents and the social economy.

[0003] As global climate change intensifies, extreme weather events occur frequently, especially severe floods, which pose a huge threat to UHV transmission towers. At present, when assessing the damage of transmission towers after flood disasters, we face the problems of complex methods and cumbersome calculations. This not only makes it difficult to quickly and accurately determine the specific damage status of transmission towers at different service stages and flood disaster intensities, but also restricts the effectiveness and pertinence of subsequent safety protection work. Summary of the invention

[0004] The purpose of the present invention is to overcome the above-mentioned shortcomings of the prior art and provide a method for analyzing damage of a transmission tower after a flood and related devices.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] In a first aspect, the present invention provides a method for analyzing post-flood damage of a transmission tower, comprising: obtaining design information, service time and flood intensity information of the transmission tower; obtaining the post-flood damage state of the transmission tower through a preset post-flood damage machine learning model for the transmission tower according to the design information, service time and flood intensity information of the transmission tower; wherein the post-flood damage machine learning model for the transmission tower is obtained by the following manner: constructing a numerical analysis probability model for the transmission tower under different service times; performing a static pushover analysis of the flood based on the numerical analysis probability model for the transmission tower under different service times, obtaining the post-flood damage state of the transmission tower under different flood intensities, and generating training samples; training the machine learning model according to the training samples to obtain the machine learning model for the post-flood damage of the transmission tower.

[0007] Optionally, the design information of the transmission tower includes one or more of the following: three-dimensional size, foundation burial depth, foundation type, steel yield strength, steel ultimate strength and steel corrosion rate; the flood intensity information includes flood depth and flood flow rate.

[0008] Optionally, constructing a numerical analysis probability model for a transmission tower at different service times includes: performing probability distribution fitting on the design information of the transmission tower to obtain a design information probability distribution function, and obtaining a number of transmission tower samples by a Latin hypercube sampling method according to the design information probability distribution function; based on the number of transmission tower samples, and based on the relationship between service time and steel corrosion rate, the relationship between steel corrosion rate and steel yield strength, and the relationship between steel corrosion rate and steel ultimate strength, modeling a numerical analysis probability model for the transmission tower at different service times.

[0009] Optionally, the relationship between the service time and the steel corrosion rate is:

[0010] v(t)=i 3 (t)+j 2 (t)+k(t)+Z

[0011] Where v(t) is the corrosion rate of steel at service time t; i, j, k and Z are fitting coefficients.

[0012] The relationship between steel corrosion rate and steel yield strength is:

[0013] f y (v) = f y (0)(1-0.005v)

[0014] Among them, f y (v) is the yield strength of the steel when the corrosion rate of the steel is v, f y (0) is the yield strength of the steel when the corrosion rate of the steel is 0.

[0015] The relationship between steel corrosion rate and steel ultimate strength is:

[0016] f u (v) = f u (0)(1-0.005v)

[0017] Among them, f u (v) is the ultimate strength of steel when the corrosion rate of steel is v, f u (0) is the ultimate strength of the steel when the corrosion rate of the steel is 0.

[0018] Optionally, the flood static pushover analysis is performed based on the numerical analysis probability model of the transmission tower at different service times to obtain the post-flood damage state of the transmission tower at different flood intensities, including: calculating the flood load of the transmission tower at different flood intensities by the following formula:

[0019]

[0020] Among them, p flood is the simplified uniform pressure of flood load, ρ sis the flood density, D s is the flood dynamic coefficient, u s Flood flow rate.

[0021] When the depth of the flood is h, the flood load is simplified to the uniformly distributed pressure p flood It is applied to all components of the transmission tower from the ground to the height h in the same direction; the maximum horizontal displacement Δ of the transmission tower at different service times after the flood load is applied is obtained, and the post-flood damage state of the transmission tower at different service times is obtained by the following method: When , the post-flood damage state of the transmission tower is slightly damaged; when When , the post-flood damage state of the transmission tower is light to medium damage state; when When , the post-flood damage state of the transmission tower is the collapse state; where H is the overall height of the transmission tower.

[0022] Optionally, the method of training a machine learning model according to training samples to obtain a machine learning model for post-flood damage of a transmission tower includes: dividing the training samples into a training set and a test set; training several machine learning models according to the training set; wherein the machine learning model takes the design information and service time of the transmission tower and the flood intensity information as input, and takes the post-flood damage status of the transmission tower as output; the machine learning model adopts a machine learning model based on the Boosting framework; obtaining the accuracy of several trained machine learning models on the test set, and using the trained machine learning model with the highest accuracy as the machine learning model for post-flood damage of the transmission tower.

[0023] According to a second aspect of the present invention, a system for analyzing post-flood damage of a transmission tower is provided, comprising: a data acquisition module for acquiring design information, service time and flood intensity information of the transmission tower; a model processing module for obtaining the post-flood damage status of the transmission tower through a preset post-flood damage machine learning model of the transmission tower according to the design information, service time and flood intensity information of the transmission tower; wherein the machine learning model of post-flood damage of the transmission tower is obtained by the following method: constructing a numerical analysis probability model of the transmission tower under different service times; performing static pushover analysis of the flood based on the numerical analysis probability model of the transmission tower under different service times, obtaining the post-flood damage status of the transmission tower under different flood intensities, and generating training samples; training the machine learning model according to the training samples to obtain the machine learning model of post-flood damage of the transmission tower.

[0024] Optionally, constructing a numerical analysis probability model for a transmission tower at different service times includes: performing probability distribution fitting on the design information of the transmission tower to obtain a design information probability distribution function, and obtaining a number of transmission tower samples by a Latin hypercube sampling method according to the design information probability distribution function; based on the number of transmission tower samples, and based on the relationship between service time and steel corrosion rate, the relationship between steel corrosion rate and steel yield strength, and the relationship between steel corrosion rate and steel ultimate strength, modeling a numerical analysis probability model for the transmission tower at different service times.

[0025] According to a third aspect of the present invention, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned method for analyzing post-flood damage to transmission towers when executing the computer program.

[0026] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned method for analyzing post-flood damage of transmission towers are implemented.

[0027] Compared with the prior art, the present invention has the following beneficial effects:

[0028] The method for analyzing the damage of a transmission tower after a flood disaster of the present invention can comprehensively and accurately evaluate the damage status of a large-scale group of transmission towers after a disaster in a short time by integrating the design information, service time and flood intensity information of the transmission towers and using an advanced machine learning model for rapid analysis, thereby providing key information for rescue and recovery work. For a large-scale group of transmission towers on a line or within a certain area, a machine learning model for damage after a flood disaster of a transmission tower based on a machine learning model can be used for rapid analysis based only on the design information, service time and flood intensity information of the transmission towers, thereby avoiding repeated calculations of traditional methods and greatly improving the speed of post-disaster damage assessment of the transmission tower group. This rapid response capability is crucial for emergency rescue work after a disaster occurs. It can help rescuers quickly locate severely damaged transmission towers and give priority to repair and recovery work, thereby minimizing the impact of disasters on power grid operation. It can also provide strong support for power grid operators to formulate long-term disaster resistance plans and strategies. By conducting in-depth analysis of the damage status of transmission towers under different service times and flood intensities, it is possible to more accurately identify the weak links in the power grid and take corresponding reinforcement and transformation measures to improve the overall disaster resistance of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 This is a flow chart of a method for analyzing damage to a transmission tower after a flood disaster according to an embodiment of the present invention.

[0030] Figure 2 It is the design information of the transmission tower and the schematic diagram of flood load application according to the embodiment of the present invention.

[0031] Figure 3 Schematic diagram of determining the damage status of a transmission tower after a flood according to an embodiment of the present invention.

[0032] Figure 4 This is a structural block diagram of a system for analyzing damage to a transmission tower after a flood disaster according to an embodiment of the present invention. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0034] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0035] The present invention is further described in detail below in conjunction with the accompanying drawings:

[0036] See also Figure 1 In one embodiment of the present invention, a method for analyzing the damage of a transmission tower after a flood disaster is provided, which can quickly provide the disaster damage status of a group of transmission towers under different service times and different flood disaster intensities, thereby guiding disaster rescue planning and improving the disaster resistance of the power grid.

[0037] Specifically, the method for analyzing the damage of a transmission tower after a flood disaster of the present invention comprises the following steps:

[0038] S1: Obtain the design information and service time of the transmission towers and the flood intensity information.

[0039] S2: According to the design information, service time and flood intensity information of the transmission tower, the post-flood damage status of the transmission tower is obtained through the preset post-flood damage machine learning model of the transmission tower.

[0040] Among them, the machine learning model of transmission tower post-flood damage is obtained in the following way:

[0041] Construct a numerical analysis probability model for transmission towers at different service times; conduct static pushover analysis of floods based on the numerical analysis probability model for transmission towers at different service times, obtain the post-flood damage status of transmission towers under different flood intensities, and generate training samples; train a machine learning model based on the training samples to obtain a machine learning model for post-flood damage of transmission towers.

[0042] The method for analyzing the damage of a transmission tower after a flood disaster of the present invention can comprehensively and accurately evaluate the damage status of a large-scale group of transmission towers after a disaster in a short time by integrating the design information, service time and flood intensity information of the transmission towers and using an advanced machine learning model for rapid analysis, thereby providing key information for rescue and recovery work. For a large-scale group of transmission towers on a line or within a certain area, a machine learning model for damage after a flood disaster of a transmission tower based on a machine learning model can be used for rapid analysis based only on the design information, service time and flood intensity information of the transmission towers, thereby avoiding repeated calculations of traditional methods and greatly improving the speed of post-disaster damage assessment of the transmission tower group. This rapid response capability is crucial for emergency rescue work after a disaster occurs. It can help rescuers quickly locate severely damaged transmission towers and give priority to repair and recovery work, thereby minimizing the impact of disasters on power grid operation. It can also provide strong support for power grid operators to formulate long-term disaster resistance plans and strategies. By conducting in-depth analysis of the damage status of transmission towers under different service times and flood intensities, it is possible to more accurately identify the weak links in the power grid and take corresponding reinforcement and transformation measures to improve the overall disaster resistance of the power grid.

[0043] In a possible implementation manner, the design information of the transmission tower includes one or more of the following: three-dimensional size, foundation burial depth, foundation type, steel yield strength, steel ultimate strength and steel corrosion rate.

[0044] See also Figure 2 For example, the design information of the transmission tower in this embodiment includes: the overall height H of the transmission tower, the width W1 and length W2 of the transmission tower in the horizontal direction, the foundation burial depth d, the foundation type, the geometric width B1 of the main rods around the transmission tower, the geometric width B2 of the oblique support rods of the transmission tower, the yield strength f of the steel material of the transmission tower yand the transmission tower steel corrosion rate v. Among them, the foundation types include massive concrete foundation FD1, thin shell foundation FD2, cast-in-place pile foundation FD3 and spiral foundation FD4.

[0045] Exemplarily, the flood intensity information includes flood depth and flood flow rate.

[0046] In a possible implementation, the construction of the numerical analysis probability model of the transmission tower at different service times includes: performing probability distribution fitting on the design information of the transmission tower to obtain a design information probability distribution function, and obtaining a number of transmission tower samples by a Latin hypercube sampling method according to the design information probability distribution function; based on the relationship between the service time and the steel corrosion rate, the relationship between the steel corrosion rate and the steel yield strength, and the relationship between the steel corrosion rate and the steel ultimate strength, the numerical analysis probability model of the transmission tower at different service times is modeled according to the number of transmission tower samples.

[0047] For example, the design information of the transmission tower is subjected to probability distribution fitting, and the fitting generally adopts normal distribution or uniform distribution. The probability distribution function of the normal distribution is:

[0048]

[0049] The probability distribution function of the uniform distribution is:

[0050]

[0051] Among them, f(xμ,σ) is the probability density of normal distribution, F(x) is the probability density of uniform distribution, μ is the center parameter, σ is the shape parameter, b is the upper limit of uniform distribution, and a is the lower limit of uniform distribution.

[0052] Explanatory, based on the design information of the transmission tower, the probability distribution fitting is performed to obtain the design information probability distribution function, and then the Latin hypercube sampling method is used to sample M transmission tower samples X m =[X1,X2...X n ],X1,X2...X n The specific parameter values ​​are obtained by sampling based on the probability distribution function of the design information, that is, each parameter samples M corresponding values, and finally forms M transmission tower samples. The service time parameter is introduced into each transmission tower sample, and then the numerical analysis probability model of the transmission tower is modeled in SAP2000 software (an advanced structural analysis and design software developed by Computers and Structures, Inc. (CSI)) based on the M transmission tower samples. The relationship between service time and steel corrosion rate, the relationship between steel corrosion rate and steel yield strength, and the relationship between steel corrosion rate and steel ultimate strength are considered during modeling.

[0053] For example, a cubic function is used to establish the relationship between service time and steel corrosion rate:

[0054] v(t)=i 3 (t)+j 2 (t)+k(t)+Z

[0055] Among them, v(t) is the corrosion rate of steel at service time t; i, j, k and Z are fitting coefficients obtained by simulating the acquired parameters.

[0056] The relationship between the corrosion rate of steel and the yield strength of steel, as well as the relationship between the corrosion rate of steel and the ultimate strength of steel, the mechanical properties attenuation conversion of the yield strength and ultimate strength of steel is carried out considering the corrosion rate of steel.

[0057] For the steel corrosion rate and steel yield strength, the specific attenuation conversion method is:

[0058] f y (v) = f y (0)(1-0.005v)

[0059] Among them, f y (v) is the yield strength of the steel when the corrosion rate of the steel is v, f y (0) is the yield strength of the steel when the corrosion rate of the steel is 0.

[0060] For the steel corrosion rate and steel ultimate strength, the specific attenuation conversion method is:

[0061] f u (v) = f u (0)(1-0.005v)

[0062] Among them, f u (v) is the ultimate strength of steel when the corrosion rate of steel is v, f u (0) is the ultimate strength of the steel when the corrosion rate of the steel is 0.

[0063] In a possible implementation, the static pushover analysis of floods is performed based on the numerical analysis probability model of the transmission tower at different service times to obtain the post-flood damage state of the transmission tower at different flood intensities, including: calculating the flood load of the transmission tower at different flood intensities by the following formula:

[0064]

[0065] Among them, p flood is the simplified uniform pressure of flood load, ρ s is the flood density (kg / m 3 ), assuming uniform distribution U1[1000,1250], Ds is the flood dynamic coefficient, assuming normal distribution U2[1.5,3], u s is the flood velocity (m / s). When the depth of the flood is h, the flood load is simplified to the uniformly distributed pressure p flood It is applied to all components of the transmission tower from the ground to the height h and the application direction is the same.

[0066] See also Figure 3 , obtain the maximum horizontal displacement Δ of the transmission tower under different service times after applying the flood load, and obtain the post-flood damage state of the transmission tower under different service times by the following method: When , the post-flood damage state of the transmission tower is slightly damaged; when When , the post-flood damage state of the transmission tower is light to medium damage state; when When , the post-flood damage state of the transmission tower is the collapse state; where H is the overall height of the transmission tower.

[0067] Explanatory, the post-flood damage state of the transmission tower is defined as three states, namely, slight damage state S, light-moderate damage state M, and collapse damage state C; the different states are determined by the ratio between the maximum horizontal displacement Δ of the transmission tower under flood load and the overall height H of the transmission tower.

[0068] Explanatory, flood intensity is characterized by two parameters: flood depth d and flood velocity u. For example, when conducting static pushover analysis of floods, the flood depth is generally in intervals of 0.5m, from 0m to 5m; the flood velocity is in intervals of 1m / s, from 0m / s to 20m / s.

[0069] In a possible implementation manner, training a machine learning model according to training samples to obtain a machine learning model of post-flood damage to transmission towers includes:

[0070] The training samples are divided into a training set and a test set; several machine learning models are trained based on the training set; the machine learning model takes the design information, service time and flood intensity information of the transmission tower as input, and the post-flood damage status of the transmission tower as output; the machine learning model adopts a machine learning model based on the Boosting framework; the accuracy of several trained machine learning models on the test set is obtained, and the trained machine learning model with the highest accuracy is used as the machine learning model for post-flood damage of transmission towers.

[0071] Explanatory, the design information and service time of the transmission tower and the flood intensity information are used as input variables, and the damage status of the transmission tower after the flood is used as the output variable. The training samples are randomly divided into training sets and test sets; exemplary, the training set and test set division method is: 70% of the training samples are randomly selected as training sets, and 30% as test sets. Then different machine learning models are used for training and learning on the training sets.

[0072] Input variables: X=[X1,X2...X n ], the output variable is: Y = [S, M, C]. Among them, X = [X1, X2...X n ] is the design information, service time and flood intensity information of the transmission tower, Y=[S,M,C] is the post-flood damage state of the transmission tower. For example, a value of 0 indicates that it is not in this state, and a value of 1 indicates that it is in this state; for example, Y=[0,0,1] indicates that the post-flood damage state of the transmission tower is a collapsed damage state.

[0073] Exemplarily, the machine learning model uses a machine learning model based on the Boosting framework, such as the XGBoost model, the Adaboost model, and the GBDT model. XGBoost is an efficient implementation of GBDT, which makes many optimizations based on GBDT, including the second-order Taylor expansion of the loss function, the addition of regularization terms, column sampling, and row sampling. These optimizations enable XGBoost to have better computational efficiency and scalability while maintaining high accuracy. Adaboost is an adaptive Boosting algorithm that adjusts the weight of each training sample based on the error rate of the previous round of learners. Misclassified samples will receive higher weights in the next round of training, so that subsequent learners will pay more attention to these difficult-to-classify samples. GBDT is a decision tree ensemble learning algorithm based on gradient boosting. It continuously optimizes the prediction results of the model by fitting the residuals of the previous round of learners. GBDT performs well on both regression and classification problems.

[0074] Explanatory, when training several machine learning models based on the training set, each machine learning model undergoes k rounds of iterations, and each round of iteration introduces a weak learner. For example, CART (Classification and Regression Tree) can be selected, and finally a total strong learner H composed of k CARTs is formed. k (X):

[0075]

[0076] in, is the prediction result of the strong learner, f k (X i ) is the kth weak learner added.

[0077] The specific training process is as follows:

[0078] 1) First, define an initialized strong learner, f0(X i ), the overall integrated model is:

[0079]

[0080] in, For a strong learner f0(X i ) in sample X i The prediction result on f0(X i ) is the 0th weak learner.

[0081] 2) Gradually add new weak learners. After adding k weak learners, the total number of strong learners is H k (X):

[0082]

[0083] Among them, f k (X i ) is the kth learner added.

[0084] At this time, the objective function is:

[0085]

[0086] Among them, y i is the real output result, L(.) is the loss function, Penalty for the preset rule item.

[0087] 3) Optimize the objective function to make it have the minimum value. The above objective function can be written as:

[0088]

[0089] in, Add the prediction results of the previous strong learner to the kth weak learner.

[0090] In order to minimize the objective function, we need to find the optimal weak learner f k Therefore, traversing f k The structure of f can be used to find the minimum value of the objective function. k , as a weak learner introduced in the next iteration.

[0091] By obtaining the accuracy of different trained machine learning models on the test set, the optimal model, that is, the trained machine learning model with the highest accuracy, is obtained as the machine learning model for post-flood damage to transmission towers. For example, the prediction accuracy of different models on the test set can be judged by the confusion matrix method, and then the accuracy of different models can be compared to obtain the optimal trained machine learning model.

[0092] The design information, service time and flood intensity information of the new transmission tower to be analyzed are input into the trained machine learning model of transmission tower post-flood damage. The machine learning model of transmission tower post-flood damage can then output the damage status of the transmission tower under the corresponding flood intensity.

[0093] In general, the method for analyzing the post-flood damage of transmission towers of the present invention collects the design information of transmission towers in the target line and range area; fits the probability distribution of the collected design information of the transmission towers; generates transmission tower samples by Latin hypercube sampling method based on the probability distribution function of the design information obtained by fitting; models the numerical analysis probability model of the transmission tower based on the transmission tower group samples; performs flood static pushover analysis on the numerical analysis probability model of the transmission tower to obtain the post-flood damage state of the transmission tower under different flood intensities, and then generates training samples; uses the basic information and service time of the transmission tower, as well as the flood intensity information as input variables, and uses the post-flood damage state of the transmission tower as the output variable, and adopts a machine learning model for training and learning; then evaluates the accuracy of different machine learning models, and obtains the optimal machine learning model as the machine learning model for post-flood damage of the transmission tower; and finally uses the machine learning model for post-flood damage of the transmission tower to quickly evaluate the post-flood damage state of regional transmission towers. The present invention avoids a large amount of simulation or calculation required by traditional methods, and can be suitable for rapid analysis of post-flood damage of a certain transmission line or a transmission tower within a certain area.

[0094] The following are device embodiments of the present invention, which can be used to implement the method embodiments of the present invention. For details not disclosed in the device embodiments, please refer to the method embodiments of the present invention.

[0095] See also Figure 4 In another embodiment of the present invention, a transmission tower post-flood damage analysis system is provided, which can be used to implement the above-mentioned transmission tower post-flood damage analysis method. Specifically, the transmission tower post-flood damage analysis system includes a data acquisition module and a model processing module.

[0096] Among them, the data acquisition module is used to obtain the design information, service time and flood intensity information of the transmission tower; the model processing module is used to obtain the post-flood damage status of the transmission tower according to the design information, service time and flood intensity information of the transmission tower through a preset post-flood damage machine learning model of the transmission tower; wherein the machine learning model of post-flood damage of the transmission tower is obtained in the following way: constructing a numerical analysis probability model of the transmission tower under different service times; performing a static pushover analysis of the flood based on the numerical analysis probability model of the transmission tower under different service times, obtaining the post-flood damage status of the transmission tower under different flood intensities, and generating training samples; training the machine learning model according to the training samples to obtain the machine learning model of post-flood damage of the transmission tower.

[0097] In a possible implementation, the construction of the numerical analysis probability model of the transmission tower at different service times includes: performing probability distribution fitting on the design information of the transmission tower to obtain a design information probability distribution function, and obtaining a number of transmission tower samples by a Latin hypercube sampling method according to the design information probability distribution function; based on the relationship between the service time and the steel corrosion rate, the relationship between the steel corrosion rate and the steel yield strength, and the relationship between the steel corrosion rate and the steel ultimate strength, the numerical analysis probability model of the transmission tower at different service times is modeled according to the number of transmission tower samples.

[0098] All relevant contents of each step involved in the embodiment of the above-mentioned transmission tower post-flood damage analysis method can be referred to the functional description of the functional modules corresponding to the transmission tower post-flood damage analysis system in the embodiment of the present invention, and will not be repeated here.

[0099] The division of modules in the embodiments of the present invention is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present invention may be integrated into one processor, or may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0100] In another embodiment of the present invention, a computer device is provided, the computer device comprising a processor and a memory, the memory being used to store a computer program, the computer program comprising program instructions, and the processor being used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions in the computer storage medium to implement the corresponding method flow or corresponding function; the processor described in the embodiment of the present invention can be used for the operation of the method for analyzing the damage of a transmission tower after a flood disaster.

[0101] In another embodiment of the present invention, the present invention further provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device for storing programs and data. It is understandable that the computer-readable storage medium here can include both built-in storage media in the computer device and, of course, extended storage media supported by the computer device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the method for analyzing the post-flood damage of the transmission tower in the above embodiment.

[0102] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0103] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0104] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0105] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0106] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for analyzing damage to transmission towers after floods, characterized in that: include: Obtain design information and service time of transmission towers and flood intensity information; According to the design information, service time and flood intensity information of the transmission tower, the post-flood damage status of the transmission tower is obtained through the preset post-flood damage machine learning model of the transmission tower; Among them, the machine learning model of transmission tower post-flood damage is obtained in the following way: Construct a numerical analysis probability model for transmission towers at different service times; Based on the numerical analysis probability model of transmission towers with different service times, static pushover analysis of floods is carried out to obtain the post-flood damage status of transmission towers under different flood intensities and generate training samples. The machine learning model is trained according to the training samples to obtain a machine learning model of transmission tower post-flood damage.

2. The method for analyzing damage of a transmission tower after a flood according to claim 1, characterized in that: The design information of the transmission tower includes one or more of the following: three-dimensional size, foundation depth, foundation type, steel yield strength, steel ultimate strength and steel corrosion rate; The flood intensity information includes flood depth and flood flow rate.

3. The method for analyzing damage of a transmission tower after a flood according to claim 1, characterized in that: The construction of the numerical analysis probability model of the transmission tower under different service times includes: The design information of the transmission tower is subjected to probability distribution fitting to obtain a design information probability distribution function, and a number of transmission tower samples are obtained by a Latin hypercube sampling method according to the design information probability distribution function; According to several transmission tower samples, a numerical analysis probability model of transmission towers under different service times was built based on the relationship between service time and steel corrosion rate, the relationship between steel corrosion rate and steel yield strength, and the relationship between steel corrosion rate and steel ultimate strength.

4. The method for analyzing damage to a transmission tower after a flood according to claim 3 is characterized in that: The relationship between the service time and the steel corrosion rate is: v(t)=i 3 (t)+j 2 (t)+k(t)+Z Where v(t) is the corrosion rate of steel at service time t; i, j, k and Z are fitting coefficients; The relationship between steel corrosion rate and steel yield strength is: f y (v)=f y (0)(1-0.005v) Among them, f y (v) is the yield strength of the steel when the corrosion rate of the steel is v, f y (0) is the yield strength of the steel when the corrosion rate of the steel is 0; The relationship between steel corrosion rate and steel ultimate strength is: f u (v)=f u (0)(1-0.005v) Among them, f u (v) is the ultimate strength of steel when the corrosion rate of steel is v, f u (0) is the ultimate strength of the steel when the corrosion rate of the steel is 0.

5. The method for analyzing damage to a transmission tower after a flood according to claim 1, characterized in that: The flood static pushover analysis is performed based on the numerical analysis probability model of the transmission tower at different service times to obtain the post-flood damage state of the transmission tower at different flood intensities, including: The flood load of the transmission tower under different flood intensities is calculated by the following formula: Among them, p flood is the simplified uniform pressure of flood load, ρ s is the flood density, D s is the flood dynamic coefficient, u s is the flood flow velocity; When the depth of the flood is h, the flood load is simplified to the uniformly distributed pressure p flood Applied to all components of the transmission tower from the ground to the height h and in the same direction; The maximum horizontal displacement Δ of the transmission tower under different service times after the flood load is applied is obtained, and the post-flood damage state of the transmission tower under different service times is obtained by the following method: When , the post-flood damage state of the transmission tower is slightly damaged; when When , the post-flood damage state of the transmission tower is light to medium damage state; when When , the post-flood damage state of the transmission tower is the collapse state; where H is the overall height of the transmission tower.

6. The method for analyzing damage to a transmission tower after a flood according to claim 1, characterized in that: The training of the machine learning model according to the training samples to obtain the machine learning model of the damage of the transmission tower after the flood disaster includes: Divide the training samples into training set and test set; Several machine learning models are trained based on the training set; the machine learning model takes the design information, service time and flood intensity information of the transmission tower as input, and takes the post-flood damage status of the transmission tower as output; the machine learning model adopts a machine learning model based on the Boosting framework; The accuracy of several trained machine learning models on the test set is obtained, and the trained machine learning model with the highest accuracy is used as the machine learning model for transmission tower post-flood damage.

7. A transmission tower post-flood damage analysis system, characterized in that: include: Data acquisition module, used to obtain the design information and service time of transmission towers and flood intensity information; A model processing module is used to obtain the post-flood damage status of the transmission tower through a preset post-flood damage machine learning model of the transmission tower according to the design information and service time of the transmission tower and the flood intensity information; Among them, the machine learning model of transmission tower post-flood damage is obtained in the following way: Construct a numerical analysis probability model for transmission towers at different service times; Based on the numerical analysis probability model of transmission towers with different service times, static pushover analysis of floods is carried out to obtain the post-flood damage status of transmission towers under different flood intensities and generate training samples. The machine learning model is trained according to the training samples to obtain a machine learning model of transmission tower post-flood damage.

8. The transmission tower post-flood damage analysis system according to claim 7, characterized in that: The construction of the numerical analysis probability model of the transmission tower under different service times includes: The design information of the transmission tower is subjected to probability distribution fitting to obtain a design information probability distribution function, and a number of transmission tower samples are obtained by a Latin hypercube sampling method according to the design information probability distribution function; According to several transmission tower samples, a numerical analysis probability model of transmission towers under different service times was built based on the relationship between service time and steel corrosion rate, the relationship between steel corrosion rate and steel yield strength, and the relationship between steel corrosion rate and steel ultimate strength.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for analyzing damage to a transmission tower after a flood disaster as claimed in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for analyzing damage to a transmission tower after a flood disaster as claimed in any one of claims 1 to 6 are implemented.

Images