Bridge deflection abnormal data processing method and device, electronic equipment and storage medium
The method enhances bridge deflection data processing by preprocessing, time series decomposition, and classification to address noise and abnormal values, improving accuracy and effectiveness.
Patent Information
- Application Number
- CN202411258215.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-09
- Publication Date
- 2025-01-03
AI Technical Summary
Current bridge deflection monitoring systems struggle with noise and abnormal values due to environmental factors, leading to low-performance data processing and high-latency feedback, making long-term and multi-dimensional monitoring ineffective.
A method involving preprocessing, time series decomposition, and classification using a bootstrap aggregation algorithm to eliminate noise and abnormal data from bridge deflection data, utilizing wavelet transform and a classification model trained on historical data.
Improves the accuracy and effectiveness of bridge deflection data processing, enhancing the safety of bridge use by removing noise and abnormal values.
Smart Images
Figure CN119249065A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of data processing, and in particular to a method, device, electronic equipment and storage medium for processing abnormal bridge deflection data. Background Art
[0002] Since the change of bridge deflection value is affected by its own materials and many external factors, there will be many abnormal values in the collected bridge deflection values, which directly affects the effectiveness of bridge platform monitoring. Common deflection value monitoring only monitors at a certain moment, and it is difficult to cope with long-term and multi-dimensional bridge deflection value monitoring. Its low-performance data processing and high-latency application feedback have become the main problems of bridge monitoring platforms.
[0003] The deflection value of the bridge comes from the deflection sensor, but this device for monitoring the deflection of the bridge is easily affected by environmental factors, such as temperature, wind speed, etc. Therefore, the deflection value monitored by the sensor often contains noise. In order to achieve accurate assessment of the deflection value, noise elimination is required. However, it is very difficult to directly eliminate the noise, and the deflection value after noise removal will still contain abnormal values.
[0004] Therefore, how to effectively remove abnormal values of bridge deflection has become a technical problem that needs to be solved urgently. Summary of the invention
[0005] In view of this, it is necessary to provide a method, device, electronic device and storage medium for processing abnormal bridge deflection data to solve the problem that abnormal values in current bridge deflection values are difficult to effectively remove.
[0006] In order to solve the above problems, the present invention provides a method for processing abnormal bridge deflection data, comprising: Preprocessing the real-time bridge deflection data, and performing time series decomposition on the preprocessed real-time bridge deflection data; Based on the time series decomposition result of the preprocessed real-time bridge deflection data, the noise data in the preprocessed real-time bridge deflection data is eliminated to obtain the target bridge deflection data; The target bridge deflection data is classified based on a classification model to eliminate abnormal data in the target bridge deflection data. The classification model is based on a bootstrap aggregation algorithm for data classification, and the classification model is trained based on historical bridge deflection data containing abnormal data.
[0007] In a possible implementation, the preprocessing of the real-time bridge deflection data includes: Invalid data in the real-time bridge deflection data is filtered out, and the filtered real-time bridge deflection data is standardized and digitized.
[0008] In a possible implementation, the time series decomposition of the preprocessed real-time bridge deflection data includes: The preprocessed real-time bridge deflection data are subjected to wavelet transform.
[0009] In a possible implementation, the time series decomposition result based on the preprocessed real-time bridge deflection data is used to remove noise data in the preprocessed real-time bridge deflection data to obtain target bridge deflection data, including: Signals whose wavelet coefficients are less than or equal to a preset threshold are determined as noise data and eliminated to obtain the target bridge deflection data.
[0010] In a possible implementation, classifying the target bridge deflection data based on a classification model and removing abnormal data in the target bridge deflection data includes: Randomly selecting a first number of data from the target bridge deflection data each time to construct a second number of subtrees; A feature is randomly selected in each subtree, and binary split is performed based on the preset split threshold corresponding to the randomly selected feature until each subtree reaches a preset height or each leaf node of each subtree has only one data; Based on the final splitting results of all subtrees, the abnormal data in the target bridge deflection data are determined and eliminated.
[0011] In a possible implementation, the training of the classification model includes: The first quantity, the second quantity, and a preset splitting threshold corresponding to each feature are determined based on historical bridge deflection data including abnormal data.
[0012] In a possible implementation manner, in the historical bridge deflection data containing abnormal data, the proportion of abnormal data is greater than a preset proportion.
[0013] The present invention also provides a bridge deflection abnormal data processing device, comprising: A preprocessing module, used for preprocessing the real-time bridge deflection data and performing time series decomposition on the preprocessed real-time bridge deflection data; A denoising module is used to remove noise data in the preprocessed real-time bridge deflection data based on the time series decomposition result of the preprocessed real-time bridge deflection data to obtain target bridge deflection data; A classification module is used to classify the target bridge deflection data based on a classification model and eliminate abnormal data in the target bridge deflection data. The classification model is based on a bootstrap aggregation algorithm for data classification, and the classification model is trained based on historical bridge deflection data containing abnormal data.
[0014] The present invention also provides an electronic device, including a memory and a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the bridge deflection abnormality data processing method as described above is implemented.
[0015] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the bridge deflection abnormal data processing method as described above is implemented.
[0016] The beneficial effects of the present invention are as follows: the bridge deflection abnormal data processing method, device, electronic device and storage medium provided by the present invention remove noise in the data by performing time series decomposition on the bridge deflection data, and further eliminate other abnormal data in the bridge deflection data through a bootstrap aggregation algorithm. While realizing the bridge deflection abnormal data processing, it improves the accuracy and effectiveness of the bridge deflection data, thereby improving the safety of bridge use. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] Figure 1 A schematic diagram of a flow chart of an embodiment of a method for processing abnormal bridge deflection data provided by the present invention; Figure 2 A schematic diagram of a flow chart of an embodiment of a bridge deflection abnormal data processing process provided by the present invention; Figure 3 A schematic structural diagram of an embodiment of a device for processing abnormal bridge deflection data provided by the present invention; Figure 4 A schematic structural diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION
[0018] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.
[0019] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.
[0020] In the description of the present invention, reference to an "embodiment" means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive of other embodiments. It is explicitly and implicitly understood by those skilled in the art that the described embodiments may be combined with other embodiments.
[0021] Since the change of bridge deflection value is affected by its own materials and many external factors, there will be many abnormal values in the collected bridge deflection values, which directly affects the effectiveness of bridge platform monitoring. Common deflection value monitoring only monitors at a certain moment, and it is difficult to cope with long-term and multi-dimensional bridge deflection value monitoring. Its low-performance data processing and high-latency application feedback have become the main problems of bridge monitoring platforms.
[0022] The deflection value of the bridge comes from the deflection sensor, but this device for monitoring the deflection of the bridge is easily affected by environmental factors, such as temperature, wind speed, etc. Therefore, the deflection value monitored by the sensor often contains noise. In order to achieve accurate assessment of the deflection value, noise elimination is required. However, it is very difficult to directly eliminate the noise, and the deflection value after noise removal will still contain abnormal values.
[0023] In order to solve the above problems, the present invention provides a method for processing abnormal bridge deflection data.
[0024] The specific embodiments are described in detail below: A specific embodiment of the present invention discloses a method for processing abnormal bridge deflection data, combining Figure 1 Come and see, Figure 1 The flowchart of an embodiment of the bridge deflection abnormal data processing method provided by the present invention includes steps S101 to S103, wherein: In step S101, the real-time bridge deflection data is preprocessed, and the preprocessed real-time bridge deflection data is time-series decomposed; In step S102, based on the time series decomposition result of the preprocessed real-time bridge deflection data, noise data in the preprocessed real-time bridge deflection data is eliminated to obtain target bridge deflection data; In step S103, the target bridge deflection data is classified based on a classification model to eliminate abnormal data in the target bridge deflection data. The classification model performs data classification based on a bootstrap aggregation algorithm, and the classification model is trained based on historical bridge deflection data containing abnormal data.
[0025] During implementation, the acquired real-time bridge deflection data can be preprocessed first to make the format of the real-time bridge deflection data uniform, and then the preprocessed real-time bridge deflection data can be time-series decomposed. According to the time-series decomposition result of the preprocessed real-time bridge deflection data, the noise in the data can be eliminated, thereby filtering out some abnormal data and obtaining the target bridge deflection data.
[0026] There are still some abnormal data in the target bridge deflection data caused by the collection equipment or collection environment. At this time, the target bridge deflection data can be classified through a classification model based on the bootstrap aggregation algorithm, and the abnormal data in the target bridge deflection data can be eliminated to finally obtain valid bridge deflection data.
[0027] The bridge deflection abnormal data processing method provided by the present invention can be applied to the bridge deflection abnormal data processing scenarios of large bridges, and can also be applied to the bridge deflection abnormal data processing scenarios of small and medium-sized bridges. The present invention does not make specific limitations on this.
[0028] Compared with the prior art, the method for processing abnormal bridge deflection data provided in this embodiment removes noise in the data by performing time series decomposition on the bridge deflection data, and further eliminates other abnormal data in the bridge deflection data through a bootstrap aggregation algorithm. While realizing the processing of abnormal bridge deflection data, it improves the accuracy and effectiveness of the bridge deflection data, thereby improving the safety of bridge use.
[0029] Exemplarily, the preprocessing of the real-time bridge deflection data includes: Invalid data in the real-time bridge deflection data is filtered out, and the filtered real-time bridge deflection data is standardized and digitized.
[0030] Specifically, when preprocessing the real-time bridge deflection data, invalid data (such as blank values and values with obviously abnormal magnitudes) in the real-time bridge deflection data can be filtered out first, and then the filtered real-time bridge deflection data can be standardized (such as normalized), and finally the standardized data can be converted into digital signals to facilitate subsequent time series decomposition.
[0031] Exemplarily, the time series decomposition of the preprocessed real-time bridge deflection data includes: The preprocessed real-time bridge deflection data are subjected to wavelet transform.
[0032] Specifically, when the preprocessed real-time bridge deflection data is time-series decomposed, the preprocessed real-time bridge deflection data can be subjected to wavelet transformation. In addition, the preprocessed real-time bridge deflection data can also be time-series decomposed by other signal processing methods, which is not specifically limited in the present invention.
[0033] Exemplarily, the time series decomposition result based on the preprocessed real-time bridge deflection data is used to remove noise data in the preprocessed real-time bridge deflection data to obtain the target bridge deflection data, including: Signals whose wavelet coefficients are less than or equal to a preset threshold are determined as noise data and eliminated to obtain the target bridge deflection data.
[0034] Specifically, after the preprocessed real-time bridge deflection data is subjected to wavelet transform, since the wavelet coefficient of the noise data is small, the signal whose wavelet coefficient is less than or equal to the preset threshold can be determined as noise data and eliminated according to the preset threshold to obtain the target bridge deflection data.
[0035] Exemplarily, classifying the target bridge deflection data based on the classification model and eliminating abnormal data in the target bridge deflection data includes: Randomly selecting a first number of data from the target bridge deflection data each time to construct a second number of subtrees; A feature is randomly selected in each subtree, and binary split is performed based on the preset split threshold corresponding to the randomly selected feature until each subtree reaches a preset height or each leaf node of each subtree has only one data; Based on the final splitting results of all subtrees, the abnormal data in the target bridge deflection data are determined and eliminated.
[0036] Specifically, when classifying the target bridge deflection data according to the classification model, firstly, a first number of data may be randomly selected from the target bridge deflection data each time to construct a second number of subtrees.
[0037] For each subtree, a signal feature can be randomly selected during each splitting process, and binary splitting is performed based on a preset splitting threshold corresponding to the randomly selected signal feature until each subtree reaches a preset height or each leaf node of each subtree has only one data.
[0038] Finally, the abnormal data in the target bridge deflection data are determined and eliminated based on the final splitting results of all subtrees.
[0039] Exemplarily, the training of the classification model includes: The first quantity, the second quantity, and a preset splitting threshold corresponding to each feature are determined based on historical bridge deflection data including abnormal data.
[0040] Specifically, the first quantity, the second quantity, and the preset splitting threshold corresponding to each feature in the classification model can be obtained by training based on historical bridge deflection data containing abnormal data.
[0041] Exemplarily, in the historical bridge deflection data containing abnormal data, the proportion of abnormal data is greater than a preset proportion.
[0042] Specifically, in order to ensure the training effect, the proportion of abnormal data in the historical bridge deflection data can be adjusted so that the proportion of abnormal data is greater than a preset proportion (for example, 0.3).
[0043] The following is a specific application scenario to better illustrate the technical solution of the present invention: The present invention receives bridge deflection values from different sources and in different formats in real time, schedules complex event processing provided by Apache Flink to extract event patterns, and applies Sql of Apache Flink to convert event data.
[0044] Afterwards, through a specific time series decomposition method, the appropriate parameters and thresholds are adjusted to split the deflection value and filter out the noise. Then it is sent to the random forest model, the specific model is debugged and trained, the outliers in the deflection are detected and cleaned, and the accurate deflection value is obtained.
[0045] Combination Figure 2 Come and see, Figure 2 This is a flow chart of an embodiment of a bridge deflection abnormal data processing process provided by the present invention, and the process specifically includes the following steps: 1. Create a Flink execution environment and configure Kafka connection information to read the bridge deflection, parse the bridge deflection, and convert it into a DeflectionData object. Then, filter out invalid bridge deflection data. Next, calculate the statistical information of the bridge deflection, such as the average value, maximum value, etc. Finally, send the statistical information to the time series decomposition model.
[0046] 2. After the signal is transformed by wavelet, the wavelet coefficients generated by the signal contain important information of the signal. After the signal is decomposed by wavelet, the wavelet coefficients are larger, and the wavelet coefficients of the noise are smaller, and the wavelet coefficients of the noise are smaller than the wavelet coefficients of the signal. By selecting a suitable threshold, the wavelet coefficients greater than the threshold are considered to be generated by the signal and should be retained, while those less than the threshold are considered to be generated by noise and set to zero to achieve the purpose of denoising.
[0047] 3. The deflection value after denoising is used as the input value and added to the debugged and trained random forest model. Random forest is a bagging algorithm with decision tree as the estimator. It combines multiple decision trees together. Each data set is randomly selected with replacement. At the same time, some features are randomly selected as input. The observed value is compared with the estimated conditional quartile boundary, and finally the detection and elimination of outliers are realized.
[0048] At the same time, in order to monitor the deflection value of bridges, the Internet of Things, Apache Flink architecture, digital twins and other technologies can also be used to build a bridge group platform. The main functions of the platform include: 1. Real-time Internet of Things.
[0049] The scene is monitored in real time through sensors and cameras installed at the front end.
[0050] 2. Real-time data processing.
[0051] Providing an interactive interface, the platform displays received data and continuously adjusts the front-end display page information by combining the real-time IoT data automatically acquired by the platform, including on-site videos, bridge deflection values, etc.
[0052] 3. Data display.
[0053] The bridge deflection information is displayed in a three-dimensional visual form, which is convenient for users to view at any time.
[0054] The present invention improves the accuracy of bridge deflection value assessment by removing noise and abnormal values in the deflection value, realizes the effectiveness of deflection monitoring, and achieves low-latency and high-performance feedback of the system.
[0055] The embodiment of the present invention also provides a bridge deflection abnormal data processing device, combined with Figure 3 Come and see, Figure 3 This is a schematic diagram of the structure of an embodiment of a bridge deflection abnormality data processing device provided by the present invention. The bridge deflection abnormality data processing device 300 includes: A preprocessing module 301 is used to preprocess the real-time bridge deflection data and perform time series decomposition on the preprocessed real-time bridge deflection data; A denoising module 302 is used to remove noise data in the preprocessed real-time bridge deflection data based on the time series decomposition result of the preprocessed real-time bridge deflection data to obtain target bridge deflection data; The classification module 303 is used to classify the target bridge deflection data based on a classification model to eliminate abnormal data in the target bridge deflection data. The classification model is based on a bootstrap aggregation algorithm for data classification, and the classification model is trained based on historical bridge deflection data containing abnormal data.
[0056] The specific implementation of each module of the bridge deflection abnormal data processing device can refer to the description of the above-mentioned bridge deflection abnormal data processing method, and has similar beneficial effects, which will not be repeated here.
[0057] It should be noted that the bridge deflection abnormal data processing device can be set at the back end of the bridge deflection value acquisition equipment, and can also be set at the bridge data monitoring center, and the present invention does not make specific limitations on this.
[0058] The embodiment of the present invention further provides an electronic device, Figure 4 Come and see, Figure 4 This is a structural diagram of an embodiment of an electronic device provided by the present invention. The electronic device 400 includes a processor 401, a memory 402, and a computer program stored in the memory 402 and executable on the processor 401. When the processor 401 executes the program, the bridge deflection abnormality data processing method described above is implemented.
[0059] As a preferred embodiment, the electronic device 400 further includes a display 403 for displaying that the processor 401 executes the bridge deflection abnormality data processing method as described above.
[0060] Exemplarily, the computer program may be divided into one or more modules / units, one or more modules / units are stored in the memory 402, and are executed by the processor 401 to complete the present invention. One or more modules / units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device 400. For example, the computer program may be divided into the preprocessing module 301, the denoising module 302, and the classification module 303 in the above embodiment, and the specific functions of each module are as described above, and are not described one by one here.
[0061] The electronic device 400 may be a desktop computer, a notebook, a PDA or a smart phone with an adjustable camera module.
[0062] Among them, the processor 401 may be an integrated circuit chip with signal processing capabilities. The above-mentioned processor 401 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.
[0063] The memory 402 may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electric erasable programmable read-only memory (EEPROM), etc. The memory 402 is used to store programs, and the processor 401 executes the program after receiving the execution instruction. The process definition method disclosed in any of the embodiments of the present invention may be applied to the processor 401 or implemented by the processor 401.
[0064] The display 403 may be an LCD display screen or an LED display screen, for example, a display screen on a mobile phone.
[0065] Understandably, Figure 4 The structure shown is only a schematic diagram of the structure of the electronic device 400. The electronic device 400 may also include Figure 4 More or fewer components as shown. Figure 4 Each component shown in the figure can be implemented by hardware, software or a combination thereof.
[0066] The electronic device provided according to the above embodiment of the present invention can be implemented with reference to the specific description of the bridge deflection abnormal data processing method as described above according to the present invention, and has similar beneficial effects as the bridge deflection abnormal data processing method as described above, which will not be repeated here.
[0067] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the above-mentioned bridge deflection abnormal data processing method is implemented.
[0068] Generally speaking, the computer instructions for implementing the method of the present invention can be carried by any combination of one or more computer-readable storage media. Non-transitory computer-readable storage media can include any computer-readable media except for the signal itself that is temporarily propagating.
[0069] Computer-readable storage media may be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium that contains or stores a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.
[0070] Computer program codes for performing the operations of the present invention may be written in one or more programming languages or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages, in particular, Python suitable for neural network computing and platform frameworks based on TensorFlow, PyTorch, etc. may be used. The program code may be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0071] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.
[0072] The present invention discloses a method, device, electronic device and storage medium for processing abnormal bridge deflection data. The method removes noise in the data by performing time series decomposition on the bridge deflection data, and further eliminates other abnormal data in the bridge deflection data through a bootstrap aggregation algorithm. While realizing the processing of abnormal bridge deflection data, the accuracy and effectiveness of the bridge deflection data are improved, thereby improving the safety of bridge use.
[0073] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.
Claims
1. A method for processing abnormal bridge deflection data, characterized in that: include: Preprocessing the real-time bridge deflection data, and performing time series decomposition on the preprocessed real-time bridge deflection data; Based on the time series decomposition result of the preprocessed real-time bridge deflection data, the noise data in the preprocessed real-time bridge deflection data is eliminated to obtain the target bridge deflection data; The target bridge deflection data is classified based on a classification model to eliminate abnormal data in the target bridge deflection data. The classification model is based on a bootstrap aggregation algorithm for data classification, and the classification model is trained based on historical bridge deflection data containing abnormal data.
2. The bridge deflection abnormal data processing method according to claim 1 is characterized in that: The preprocessing of the real-time bridge deflection data includes: Invalid data in the real-time bridge deflection data is filtered out, and the filtered real-time bridge deflection data is standardized and digitized.
3. The bridge deflection abnormal data processing method according to claim 1 is characterized in that: The time series decomposition of the preprocessed real-time bridge deflection data includes: The preprocessed real-time bridge deflection data are subjected to wavelet transform.
4. The bridge deflection abnormal data processing method according to claim 3 is characterized in that: The method of removing noise data in the preprocessed real-time bridge deflection data based on the time series decomposition result of the preprocessed real-time bridge deflection data to obtain target bridge deflection data includes: Signals whose wavelet coefficients are less than or equal to a preset threshold are determined as noise data and eliminated to obtain the target bridge deflection data.
5. The bridge deflection abnormal data processing method according to claim 1 is characterized in that: Classifying the target bridge deflection data based on the classification model and eliminating abnormal data in the target bridge deflection data includes: Randomly selecting a first number of data from the target bridge deflection data each time to construct a second number of subtrees; A feature is randomly selected in each subtree, and binary split is performed based on the preset split threshold corresponding to the randomly selected feature until each subtree reaches a preset height or each leaf node of each subtree has only one data; Based on the final splitting results of all subtrees, the abnormal data in the target bridge deflection data are determined and eliminated.
6. The bridge deflection abnormal data processing method according to claim 5 is characterized in that: The training of the classification model includes: The first quantity, the second quantity, and a preset splitting threshold corresponding to each feature are determined based on historical bridge deflection data including abnormal data.
7. The bridge deflection abnormal data processing method according to claim 6 is characterized in that: In the historical bridge deflection data containing abnormal data, the proportion of abnormal data is greater than a preset proportion.
8. A bridge deflection abnormality data processing device, characterized in that: include: A preprocessing module, used for preprocessing the real-time bridge deflection data and performing time series decomposition on the preprocessed real-time bridge deflection data; A denoising module is used to remove noise data in the preprocessed real-time bridge deflection data based on the time series decomposition result of the preprocessed real-time bridge deflection data to obtain target bridge deflection data; A classification module is used to classify the target bridge deflection data based on a classification model and eliminate abnormal data in the target bridge deflection data. The classification model is based on a bootstrap aggregation algorithm for data classification, and the classification model is trained based on historical bridge deflection data containing abnormal data.
9. An electronic device, characterized in that: The invention comprises a memory and a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the method for processing abnormal bridge deflection data according to any one of claims 1 to 7 is implemented.
10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the method for processing abnormal bridge deflection data as described in any one of claims 1 to 7 is implemented.