Power equipment foundation settlement prediction method and system

Abstract

The invention discloses a power equipment foundation settlement prediction method and system, and the method comprises the steps: dividing at least one settlement observation data sequence according to each settlement correlation degree, and obtaining at least one settlement observation data sequence set; selecting a certain target settlement observation data sequence from a certain settlement observation data sequence set by adopting a preset sequence selection rule according to the position information of each monitoring point; inputting a certain target settlement observation data sequence into a preset settlement prediction model, and outputting by the settlement prediction model to obtain certain target settlement prediction data corresponding to a certain target monitoring point position; and according to other settlement observation data sequences in a certain settlement observation data sequence set, correcting certain target settlement prediction data to obtain other settlement prediction data corresponding to other monitoring point positions. And efficient monitoring and early warning are performed on the settlement condition of the power equipment foundation, and powerful support is provided for safe operation and maintenance decision making of the equipment.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of power equipment settlement analysis, and particularly relates to a power equipment foundation settlement prediction method and system. BACKGROUND

[0002] The long-term stable and safe operation of power equipment foundations, such as transformer substation foundations, power transmission tower foundations, etc., is crucial to the reliability of the entire power grid. Foundation settlement is a key factor affecting the structural stability thereof, and uneven settlement can cause the equipment framework to tilt, redistribute internal stress, and even cause structural damage, seriously threatening the safety of the power grid. Therefore, continuous and accurate settlement prediction and monitoring of power equipment foundations is an important means to achieve condition-based maintenance and prevent accidents.

[0003] At present, common settlement prediction methods mainly rely on analyzing the settlement observation data sequences of each monitoring point independently, such as using regression analysis, time series models (such as ARIMA) or machine learning algorithms (such as support vector machines, neural networks) to establish independent prediction models for each point. However, this method has obvious limitations in practical application: first, a large transformer substation or a power transmission line often has dozens or even hundreds of monitoring points, and establishing and training a prediction model for each point requires a huge amount of computing resources, resulting in low prediction efficiency and making it difficult to meet the real-time or high-frequency prediction requirements. Second, this method ignores the internal correlation and spatial correlation of settlement deformation between different monitoring points under the same power equipment foundation. Due to the continuity of geological conditions and load distribution, adjacent or similar geological unit monitoring points often show certain synergy or proportional relationship in settlement trend, and independent prediction models cannot effectively utilize this information, which may lead to deviation of the prediction results from the actual overall deformation law. SUMMARY

[0004] The present application provides a power equipment foundation settlement prediction method and system to solve the technical problem of requiring a huge amount of computing resources to establish and train a prediction model for each point.

[0005] In a first aspect, the present application provides a power equipment foundation settlement prediction method, comprising: obtaining settlement observation data of at least one monitoring point within a preset time period, and sorting each settlement observation data of the same monitoring point to obtain at least one settlement observation data sequence; determining the settlement correlation degree of each settlement observation data sequence, and dividing the at least one settlement observation data sequence according to the settlement correlation degree to obtain at least one settlement observation data sequence set; obtain monitoring point position information corresponding to each subsidence observation data sequence in a certain subsidence observation data sequence set, and select a target subsidence observation data sequence in the certain subsidence observation data sequence set according to each monitoring point position information and by using a preset sequence selection rule; input the target subsidence observation data sequence into a preset subsidence prediction model, and obtain a target subsidence prediction data corresponding to a target monitoring point from the subsidence prediction model; correct the target subsidence prediction data according to other subsidence observation data sequences in the certain subsidence observation data sequence set, and obtain other subsidence prediction data corresponding to other monitoring points.

[0006] In a second aspect, the present application provides a power equipment foundation subsidence prediction system, comprising: a obtaining module configured to obtain subsidence observation data of at least one monitoring point in a preset time period, and sort each subsidence observation data of the same monitoring point to obtain at least one subsidence observation data sequence; a dividing module configured to determine subsidence correlation degrees of each subsidence observation data sequence, and divide the at least one subsidence observation data sequence according to each subsidence correlation degree to obtain at least one subsidence observation data sequence set; a selecting module configured to obtain monitoring point position information corresponding to each subsidence observation data sequence in a certain subsidence observation data sequence set, and select a target subsidence observation data sequence in the certain subsidence observation data sequence set according to each monitoring point position information and by using a preset sequence selection rule; an output module configured to input the target subsidence observation data sequence into a preset subsidence prediction model, and obtain a target subsidence prediction data corresponding to a target monitoring point from the subsidence prediction model; a correcting module configured to correct the target subsidence prediction data according to other subsidence observation data sequences in the certain subsidence observation data sequence set, and obtain other subsidence prediction data corresponding to other monitoring points.

[0007] In a third aspect, an electronic device is provided, comprising at least one processor and a memory connected with the at least one processor in communication, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the steps of the power equipment foundation subsidence prediction method of any embodiment of the present application.

[0008] Fourthly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor performs the steps of the power equipment foundation settlement prediction method according to any embodiment of the present invention.

[0009] The power equipment foundation settlement prediction method and system of this application, by calculating the settlement correlation of settlement observation data sequences at each monitoring point and performing clustering, can identify monitoring areas with similar or related settlement trends, laying the foundation for subsequent collaborative prediction. Furthermore, combining the spatial location information of the monitoring points, a circle is drawn with the two furthest points as diameters, and the core point with the largest settlement is selected as the prediction target. This ensures that the selected target sequence represents the overall settlement characteristics of the area and possesses significance and centrality, thereby improving the accuracy and reliability of the initial prediction. Finally, by utilizing the accurate prediction results of the target point and correcting it based on the historical settlement ratio between other points in the set and the target point, settlement prediction data for all points in the group can be obtained efficiently and accurately. This method minimizes the computational resource consumption of independently and complexly modeling each monitoring point, greatly improving the overall efficiency of large-scale, multi-point settlement prediction. While ensuring prediction accuracy, it achieves efficient monitoring and early warning of power equipment foundation settlement, providing strong support for equipment safety operation and maintenance decisions. Attached Figure Description

[0010] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 A flowchart illustrating a method for predicting the settlement of power equipment foundations according to an embodiment of the present invention; Figure 2 This is a structural block diagram of a power equipment foundation settlement prediction system provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0012] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0013] Please see Figure 1 The diagram shows a flowchart of a method for predicting the settlement of power equipment foundations according to this application.

[0014] like Figure 1 As shown, the method for predicting the settlement of power equipment foundations specifically includes the following steps: Step S101: Obtain settlement observation data of at least one monitoring point within a preset time period, and sort the settlement observation data of the same monitoring point to obtain at least one settlement observation data sequence.

[0015] In this step, monitoring points refer to settlement observation points set up on the foundations of electrical equipment (such as transformer foundations, distribution equipment column foundations, and tower foundations). These points are usually pre-set during the foundation construction phase, for example, as settlement observation markers. After obtaining settlement observation data within a pre-set time period, the settlement observation data of each monitoring point are sorted according to the chronological order to obtain at least one settlement observation data sequence.

[0016] Step S102: Determine the settlement correlation degree of each settlement observation data sequence, and divide the at least one settlement observation data sequence according to each settlement correlation degree to obtain at least one set of settlement observation data sequences.

[0017] In this step, the settlement difference between two adjacent settlement observation data in a certain settlement observation data sequence is obtained, and the settlement differences are sorted according to the time sequence to obtain a certain settlement difference sequence corresponding to a certain settlement observation data sequence. The first settlement difference in a certain settlement difference sequence is defined as the initial settlement difference, and it is determined whether the target difference between the other settlement differences in the certain settlement difference sequence and the initial settlement difference is greater than a preset threshold. The other settlement differences are any settlement differences in the certain settlement difference sequence excluding the initial settlement difference. If the target difference between at least one settlement difference and the initial settlement difference is not greater than the preset threshold, the target differences corresponding to at least one settlement difference are added together, and the result of the addition is defined as a certain settlement correlation degree of a certain settlement difference sequence. If the differences between all settlement differences and the initial settlement difference are greater than the preset threshold, the certain settlement correlation degree of a certain settlement difference sequence is defined as zero.

[0018] It should be noted that by dividing the settlement observation data sequences corresponding to each settlement correlation degree in a certain settlement correlation degree set into the same settlement observation data sequence set, at least one settlement observation data sequence set is obtained.

[0019] In one specific embodiment, assuming there exists a settlement observation data sequence Si = (s(t1), s(t2), s(t3), ..., s(tn)) for the i-th monitoring point, then the difference between two adjacent observation data in the sequence is calculated as: Δdk = s(tk+1) - s(tk), where k = 1, 2, ..., n-1; thus, the settlement difference sequence Di = (Δd1, Δd2, Δd3, ..., Δdn-1) for the i-th monitoring point is obtained. This sequence reflects the settlement change at this point over different time intervals.

[0020] The first difference Δd1 in the settlement difference sequence Di is defined as the initial settlement difference. It represents the settlement rate in the early observation stage.

[0021] Set a threshold ε. This threshold is a key parameter and can be determined based on historical data, engineering experience, or settlement sensitivity (e.g., ε = 0.5 mm). Its significance lies in determining whether the subsequent settlement rate has deviated "significantly".

[0022] Iterate through all other differences Δdj (j=2, 3, ..., n-1) in the settlement difference sequence Di except Δd1, calculate the absolute difference between each Δdj and the initial settlement difference Δd1, i.e. the target difference: δj=|Δdj-Δd1|, and compare each target difference δj with the preset threshold ε.

[0023] If there exists at least one target difference δj not greater than ε (i.e., the settlement difference does not significantly deviate from the initial rate), then all δj values ​​that satisfy this condition are summed. The larger the sum, the closer the settlement rate at that point is to the initial rate for most of the time, the more stable the settlement process, and the higher the correlation.

[0024] If all target differences δj are greater than ε, then the settlement correlation at that point is directly defined as 0. This indicates that the settlement rate at that point underwent a drastic or continuous change in the later stages, completely inconsistent with the initial trend, and exhibits poor stability; therefore, its correlation is considered to be zero.

[0025] In this embodiment, the settlement behavior of multiple monitoring points under a large power equipment foundation (such as a substation) is not entirely independent. They are constrained by common geological conditions, foundation load distribution, and overall structural stiffness. Therefore, the settlement trends of these points will naturally form several sets with similar patterns. Dividing these points by settlement correlation utilizes a data-driven approach to automatically identify these sets with similar settlement behaviors, rather than subjectively grouping them by geographical distance. Furthermore, when the target difference between at least one settlement difference and the initial settlement difference is not greater than a preset threshold, the target differences corresponding to at least one settlement difference are added together, and the sum is defined as a certain settlement correlation degree of a certain settlement difference sequence. This means that even if there are individual abrupt changes in the sequence caused by measurement errors or brief external disturbances (whose target differences will be much greater than ε), as long as the settlement is stable for most of the time period, these abrupt changes will not be included in the cumulative correlation degree value. This avoids the decisive influence of random noise on the correlation degree evaluation results, making the evaluation results more stable and reliable. By clustering settlement correlation degrees, it is possible to illustrate that the points within the set have similar change patterns (stable settlement or synchronous acceleration / deceleration) throughout the entire process from the start of settlement to the present. Therefore, their future settlement development is also very likely to maintain this proportional relationship. Thus, using historical proportions to correct future predictions is reasonable and reliable.

[0026] It should be noted that the settlement observation data sequences corresponding to zero settlement correlation can be input into the subsequent settlement prediction model for prediction one by one. This can improve the accuracy of the prediction compared to the subsequent correction method.

[0027] Step S103: Obtain the location information of monitoring points corresponding to each settlement observation data sequence in a certain settlement observation data sequence set, and select a target settlement observation data sequence in the certain settlement observation data sequence set according to the location information of each monitoring point and a preset sequence selection rule.

[0028] In this step, the location information of monitoring points corresponding to each settlement observation data sequence in a certain settlement observation data sequence set is mapped to a preset two-dimensional coordinate system. A circle is drawn with the distance between the first monitoring point and the second monitoring point as the diameter to obtain a closed region. The first and second monitoring points are the two monitoring points that are farthest apart from each settlement observation data sequence in the certain settlement observation data sequence set. With the center of the closed region as the center point, it is determined whether the number of monitoring points to be determined that are less than a preset distance threshold from the center point is less than a preset number threshold. If it is not less than the preset number threshold, the settlement observation data sequence to be determined corresponding to at least one monitoring point to be determined is obtained. The settlement difference sequences corresponding to each settlement observation data sequence to be determined are added together to obtain each settlement amount. The settlement observation data sequence to be determined corresponding to the maximum settlement amount is defined as a target settlement observation data sequence.

[0029] It should be noted that the monitoring points to be determined are those whose distance from the center point is less than a preset distance threshold, the settlement observation data sequence to be determined is the settlement observation data sequence obtained at the monitoring points to be determined, and the maximum settlement amount is the settlement amount with the largest value among all settlement amounts.

[0030] Furthermore, if the number is less than a preset threshold, the nearest target monitoring point to the center point is directly obtained, and the settlement observation data sequence corresponding to the target monitoring point is directly defined as the target settlement observation data sequence.

[0031] In one specific embodiment, a preset two-dimensional coordinate system is established. Typically, this is a Cartesian coordinate system (e.g., using a national geodetic coordinate system such as CGCS2000, or an independent coordinate system based on the construction site). The latitude and longitude or construction grid coordinates of all monitoring points in the current sequence set are accurately mapped to this coordinate system to obtain the two-dimensional coordinates of each monitoring point.

[0032] Calculate the Euclidean distance between all pairs of points in the set, find the two points with the greatest distance, and denote them as the first monitoring point P1 and the second monitoring point P2.

[0033] Draw a circular region with the line connecting P1 and P2 as its diameter. The center O of this circular region is the midpoint of the line connecting P1 and P2, and its radius R is half the distance between P1 and P2. This circular region is a minimal approximation of a "minimum enclosing circle" that covers all points. It defines the spatial distribution range of the current point group, and the center O represents the geometric center of this distribution range.

[0034] Set a preset distance threshold and a preset quantity threshold. The preset distance threshold is used to define the "core area," for example, it can be set to 1 / 3 of the circle's radius R or a fixed value (such as 50 meters). It indicates how close to the center of the circle is considered the "central area." The preset quantity threshold is used to determine whether there are monitoring points within the core area, for example, it can be set to 1.

[0035] Step S104: Input the settlement observation data sequence of a certain target into a preset settlement prediction model, and the settlement prediction model outputs the settlement prediction data of a certain target corresponding to the monitoring point of a certain target.

[0036] In this step, the settlement prediction model can be obtained by training an LSTM network or a GRU network with a large amount of settlement monitoring data from historical projects. The training process is a conventional iterative training method, so it will not be described in detail here.

[0037] Specifically, assume that in step S103, the sequence of monitoring point P3 is selected as the target sequence. This sequence is the cumulative settlement data over the past 100 days.

[0038] Choose a model that can effectively learn long-term dependencies, such as LSTM. Assume a pre-trained LSTM model is stored on a server, with the following structure: an input layer (receiving sequences from the past 30 days), two LSTM layers, and a fully connected output layer. The system loads this pre-trained LSTM model (including its network structure and weight parameters) from storage.

[0039] Obtain the 100-day settlement sequence SP3 for point P3.

[0040] Normalization: Calculate the minimum and maximum values ​​of SP3 and normalize the entire sequence to the interval [0, 1].

[0041] Input sample construction: A sliding window method is used. Data from days 1-30 is used to predict day 31, data from days 2-31 is used to predict day 32, and so on, ultimately generating 70 training samples. The last sample (data from days 71-100) will be used to actually predict the future (i.e., day 101).

[0042] Perform prediction: Input the last sample (normalized data from days 71 to 100, with shape (1, 30, 1)) into the loaded LSTM model.

[0043] The model performs forward propagation calculations and outputs a normalized predicted value (corresponding to the settlement on day 101).

[0044] Post-processing and output of results: The normalized predicted values ​​output by the model are denormalized using the previously recorded min and max values ​​to obtain the actual predicted settlement values ​​(unit: millimeters).

[0045] Step S105: Correct the settlement prediction data of a certain target based on other settlement observation data sequences in the certain settlement observation data sequence set to obtain other settlement prediction data corresponding to other monitoring points.

[0046] In this step, a first settlement amount corresponding to a first settlement observation data sequence and a target settlement amount corresponding to a target settlement observation data sequence are obtained, wherein the first settlement observation data sequence is a settlement observation data sequence corresponding to a first monitoring point, and the first monitoring point is any one of the other monitoring points; the ratio between the first settlement amount and the target settlement amount is calculated to obtain a first ratio; the first ratio is multiplied by the settlement prediction value in the target settlement prediction data to obtain the first settlement prediction data corresponding to the first monitoring point.

[0047] In summary, the method presented in this application, by calculating the settlement correlation of settlement observation data sequences at each monitoring point and performing clustering, can identify monitoring areas with similar or related settlement trends, laying the foundation for subsequent collaborative prediction. Furthermore, by combining the spatial location information of the monitoring points, drawing a circle with the two furthest points as diameters and selecting the core point with the largest settlement as the prediction target, it ensures that the selected target sequence represents the overall settlement characteristics of the area while also possessing significance and centrality, thereby improving the accuracy and reliability of the initial prediction. Finally, by utilizing the accurate prediction results of the target point and correcting it based on the historical settlement ratio between other points in the set and the target point, settlement prediction data for all points in the group can be obtained efficiently and accurately. This method minimizes the computational resource consumption of independently and complexly modeling each monitoring point, greatly improving the overall efficiency of large-scale, multi-point settlement prediction. While ensuring prediction accuracy, it achieves efficient monitoring and early warning of the settlement status of power equipment foundations, providing strong support for equipment safety operation and maintenance decisions.

[0048] Please see Figure 2 The diagram shows a structural block diagram of a power equipment foundation settlement prediction system according to this application.

[0049] like Figure 2 As shown, the power equipment foundation settlement prediction system 200 includes an acquisition module 210, a division module 220, a selection module 230, an output module 240, and a correction module 250.

[0050] The acquisition module 210 is configured to acquire settlement observation data of at least one monitoring point within a preset time period, and sort the settlement observation data of the same monitoring point to obtain at least one settlement observation data sequence; the partitioning module 220 is configured to determine the settlement correlation of each settlement observation data sequence, and partition the at least one settlement observation data sequence according to the settlement correlation to obtain at least one set of settlement observation data sequences; the selection module 230 is configured to acquire the location information of the monitoring points corresponding to each settlement observation data sequence in a certain set of settlement observation data sequences, and select the points according to the settlement correlation of each settlement observation data sequence in a certain set of settlement observation data sequences. The system uses location information of monitoring points and selects a target settlement observation data sequence from a certain set of settlement observation data sequences using a preset sequence selection rule. An output module 240 is configured to input the target settlement observation data sequence into a preset settlement prediction model, which outputs target settlement prediction data corresponding to the target monitoring point. A correction module 250 is configured to correct the target settlement prediction data based on other settlement observation data sequences in the set of settlement observation data sequences, obtaining other settlement prediction data corresponding to other monitoring points.

[0051] It should be understood that Figure 2 The modules and references described in the document Figure 1 The steps described in the text correspond to those in the method described above. Therefore, the operations, features, and corresponding technical effects described above also apply to the method described in the text. Figure 2 The various modules in the document will not be described in detail here.

[0052] In other embodiments, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor performs the power equipment foundation settlement prediction method in any of the above method embodiments. In one embodiment, the computer-readable storage medium of the present invention stores computer-executable instructions, which are configured as follows: Acquire settlement observation data of at least one monitoring point within a preset time period, and sort the settlement observation data of the same monitoring point to obtain at least one settlement observation data sequence. Determine the settlement correlation degree of each settlement observation data sequence, and divide the at least one settlement observation data sequence according to each settlement correlation degree to obtain at least one set of settlement observation data sequences. Obtain the location information of monitoring points corresponding to each settlement observation data sequence in a certain settlement observation data sequence set, and select a target settlement observation data sequence in the certain settlement observation data sequence set according to the location information of each monitoring point and a preset sequence selection rule. The settlement observation data sequence of a certain target is input into a preset settlement prediction model, and the settlement prediction model outputs the settlement prediction data of a certain target corresponding to the monitoring point of the target. The settlement prediction data for a certain target is corrected based on other settlement observation data sequences in the set of settlement observation data sequences to obtain other settlement prediction data corresponding to other monitoring points.

[0053] Computer-readable storage media may include a stored program area and a stored data area, wherein the stored program area may store an operating system and an application program required for at least one function; the stored data area may store data created based on the use of the power equipment foundation settlement prediction system, etc. Furthermore, the computer-readable storage medium may include high-speed random access memory, and may also include memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the computer-readable storage medium may optionally include memory remotely located relative to a processor, and this remote memory may be connected to the power equipment foundation settlement prediction system via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0054] Figure 3 This is a schematic diagram of the structure of the electronic device provided in the embodiment of the present invention, such as... Figure 3 As shown, the device includes a processor 310 and a memory 320. The electronic device may also include an input device 330 and an output device 340. The processor 310, memory 320, input device 330, and output device 340 can be connected via a bus or other means. Figure 3 Taking a bus connection as an example, the memory 320 is the computer-readable storage medium described above. The processor 310 executes various server functions and data processing by running non-volatile software programs, instructions, and modules stored in the memory 320, thereby implementing the power equipment foundation settlement prediction method described in the above embodiment. The input device 330 can receive input digital or character information and generate key signal inputs related to user settings and function control of the power equipment foundation settlement prediction system. The output device 340 may include a display screen or other display device.

[0055] The aforementioned electronic device can execute the method provided in the embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the method. Technical details not described in detail in this embodiment can be found in the method provided in the embodiments of the present invention.

[0056] In one implementation, the aforementioned electronic device is applied in a power equipment foundation settlement prediction system for a client, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to: Acquire settlement observation data of at least one monitoring point within a preset time period, and sort the settlement observation data of the same monitoring point to obtain at least one settlement observation data sequence. Determine the settlement correlation degree of each settlement observation data sequence, and divide the at least one settlement observation data sequence according to each settlement correlation degree to obtain at least one set of settlement observation data sequences. Obtain the location information of monitoring points corresponding to each settlement observation data sequence in a certain settlement observation data sequence set, and select a target settlement observation data sequence in the certain settlement observation data sequence set according to the location information of each monitoring point and a preset sequence selection rule. The settlement observation data sequence of a certain target is input into a preset settlement prediction model, and the settlement prediction model outputs the settlement prediction data of a certain target corresponding to the monitoring point of the target. The settlement prediction data for a certain target is corrected based on other settlement observation data sequences in the set of settlement observation data sequences to obtain other settlement prediction data corresponding to other monitoring points.

[0057] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of various embodiments or some parts of embodiments.

[0058] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting settlement of power equipment foundations, characterized in that, include: Acquire settlement observation data of at least one monitoring point within a preset time period, and sort the settlement observation data of the same monitoring point to obtain at least one settlement observation data sequence. Determine the settlement correlation degree of each settlement observation data sequence, and divide the at least one settlement observation data sequence according to each settlement correlation degree to obtain at least one set of settlement observation data sequences. Obtain the location information of monitoring points corresponding to each settlement observation data sequence in a certain settlement observation data sequence set, and select a target settlement observation data sequence in the certain settlement observation data sequence set according to the location information of each monitoring point and a preset sequence selection rule. The settlement observation data sequence of a certain target is input into a preset settlement prediction model, and the settlement prediction model outputs the settlement prediction data of a certain target corresponding to the monitoring point of the target. The settlement prediction data for a certain target is corrected based on other settlement observation data sequences in the set of settlement observation data sequences to obtain other settlement prediction data corresponding to other monitoring points.

2. The method for predicting settlement of power equipment foundations according to claim 1, characterized in that, The determination of the settlement correlation degree of each settlement observation data sequence includes: The settlement difference between two adjacent settlement observation data in a certain settlement observation data sequence is obtained, and the settlement differences are sorted according to the time sequence to obtain a certain settlement difference sequence corresponding to the certain settlement observation data sequence. The first settlement difference in the certain settlement difference sequence is defined as the initial settlement difference, and it is determined whether the target difference between the other settlement differences in the certain settlement difference sequence and the initial settlement difference is greater than a preset threshold, wherein the other settlement differences are any settlement difference in the certain settlement difference sequence excluding the initial settlement difference; If the target difference between at least one settlement difference and the initial settlement difference is not greater than a preset threshold, then the target differences corresponding to the at least one settlement difference are added together, and the result of the addition is defined as a certain settlement correlation degree of a certain settlement difference sequence. If the difference between all settlement differences and the initial settlement difference is greater than a preset threshold, then the settlement correlation of a certain settlement difference sequence will be defined as zero.

3. The method for predicting settlement of power equipment foundations according to claim 1, characterized in that, The step of dividing the at least one settlement observation data sequence according to each settlement correlation degree to obtain at least one set of settlement observation data sequences includes: At least one settlement correlation degree within the same range is assigned to the same settlement correlation degree set to obtain at least one settlement correlation degree set; The settlement observation data sequences corresponding to each settlement correlation degree in a certain settlement correlation degree set are divided into the same settlement observation data sequence set to obtain at least one settlement observation data sequence set.

4. The method for predicting the settlement of power equipment foundations according to claim 2, characterized in that, The step of selecting a target settlement observation data sequence from a certain settlement observation data sequence set according to the location information of each monitoring point and using a preset sequence selection rule includes: The location information of monitoring points corresponding to each settlement observation data sequence in a certain settlement observation data sequence set is mapped to a preset two-dimensional coordinate system, and a circle is drawn with the distance between the first monitoring point and the second monitoring point as the diameter to obtain a certain closed region. The first monitoring point and the second monitoring point are the two monitoring points that are farthest apart from each other among the monitoring points corresponding to each settlement observation data sequence in the certain settlement observation data sequence set. Using the center of a certain closed region as the center point, determine whether the number of monitoring points to be determined that are less than a preset distance threshold from the center point is less than a preset number threshold. If the number is not less than a preset threshold, then the settlement observation data sequence corresponding to the at least one monitoring point to be determined is obtained, and the settlement difference sequence corresponding to each settlement observation data sequence to be determined is added together to obtain each settlement amount. The settlement observation data sequence corresponding to the maximum settlement is defined as the settlement observation data sequence of a certain target.

5. The method for predicting settlement of power equipment foundations according to claim 4, characterized in that, The step of correcting the target settlement prediction data based on other settlement observation data sequences in the set of settlement observation data sequences to obtain other settlement prediction data corresponding to other monitoring points includes: Obtain a first settlement amount corresponding to a first settlement observation data sequence, and a target settlement amount corresponding to a certain target settlement observation data sequence, wherein the first settlement observation data sequence is a settlement observation data sequence corresponding to a first monitoring point, and the first monitoring point is any one of the other monitoring points; Calculate the ratio between the first settlement amount and the settlement amount of the target, and obtain the first ratio; The first ratio is multiplied by the settlement prediction value in the settlement prediction data of a certain target to obtain the first settlement prediction data corresponding to the first monitoring point.

6. A power equipment foundation settlement prediction system, characterized in that, include: The acquisition module is configured to acquire settlement observation data of at least one monitoring point within a preset time period, and sort the settlement observation data of the same monitoring point to obtain at least one settlement observation data sequence. The partitioning module is configured to determine the settlement correlation degree of each settlement observation data sequence, and partition the at least one settlement observation data sequence according to each settlement correlation degree to obtain at least one set of settlement observation data sequences. The selection module is configured to acquire the location information of monitoring points corresponding to each settlement observation data sequence in a certain settlement observation data sequence set, and select a target settlement observation data sequence in the certain settlement observation data sequence set according to the location information of each monitoring point and a preset sequence selection rule. The output module is configured to input the settlement observation data sequence of a certain target into a preset settlement prediction model, and the settlement prediction model outputs the settlement prediction data of a certain target corresponding to the monitoring point of a certain target. The correction module is configured to correct the settlement prediction data of a certain target based on other settlement observation data sequences in the certain settlement observation data sequence set, so as to obtain other settlement prediction data corresponding to other monitoring points.

7. An electronic device, characterized in that, include: At least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method described in any one of claims 1 to 5.

Images