A bridge construction monitoring data anomaly identification method and system and related equipment

Abstract

The application discloses a kind of bridge construction monitoring data anomaly identification method, system and related equipment, the first data stream of this scheme is filtered, then the statistical characteristic value of several is calculated and extracted to the data stream after filtering, and form a vector based on several statistical characteristic values, form one-dimensional feature vector X;Then the statistical characteristic value of determined feature vector X is selected according to the new feature vector Y of several corresponding characteristic values according to pre-set standard;Then the SVDD model single-class support vector machine is used, the basic classification library is called, and the feature vector Y after dimension reduction is identified, to determine whether it belongs to abnormal data;Finally, the binary classification support vector machine based on SMO algorithm is used, the basic classification library is called, and the data determined as abnormal is judged again.The scheme given by the application can realize high-precision construction monitoring abnormal data identification, improve the early warning efficiency, and can effectively avoid false alarm and false alarm.

Description

Technical Field

[0001] This invention relates to engineering construction monitoring technology, specifically to bridge construction monitoring technology. Background Technology

[0002] Currently, in infrastructure construction processes, such as hydraulic climbing formwork for bridge piers and hanging basket casting for bridge beams, the current methods for checking the operational status of most construction equipment are usually on-site feedback from construction personnel and regular inspections by management personnel. These methods are somewhat lagging and cannot provide timely feedback or implement corresponding emergency measures in the event of an emergency, posing certain safety hazards.

[0003] Existing real-time safety monitoring systems can effectively overcome the problems of manual monitoring. However, most existing real-time safety monitoring systems rely on manually setting thresholds for certain values ​​to provide early warnings. This often results in missed alarms or false alarms due to occasional anomalies in construction equipment, the environment, or data acquisition devices. Summary of the Invention

[0004] To address the problems of accuracy and reliability in existing real-time safety monitoring schemes for bridge construction, the present invention aims to provide a scheme for identifying anomalies in bridge construction monitoring data. This scheme is based on a joint machine learning model that improves and optimizes single-class support vector machine and binary support vector machine to achieve high-precision identification of construction monitoring anomalies, effectively improving early warning efficiency and effectively avoiding missed or false alarms.

[0005] To achieve the above objectives, the present invention provides a method for identifying anomalies in bridge construction monitoring data, the method comprising:

[0006] (1) Data filtering: Filter the incoming data stream to remove sharp data from the data stream;

[0007] (2) Generate feature vectors. Calculate and extract several statistical feature values ​​for the data stream after filtering in step (1), and form a composition vector based on the several statistical feature values ​​to form a one-dimensional feature vector X.

[0008] (3) Data dimensionality reduction: Select several corresponding feature values ​​from the feature vector X determined in step (2) according to the preset standard to form a new feature vector Y.

[0009] (4) Initial analysis: Using the SVDD model single-class support vector machine, the basic classification library is called to identify the feature vector Y after dimensionality reduction and determine whether it belongs to abnormal data.

[0010] (5) Optimization analysis: a binary support vector machine based on the SMO algorithm is used to call the basic classification library to re-determine the data that was determined to be abnormal in step (4). If it is determined to be abnormal data, it is finally determined to be abnormal data; if it is determined to be normal data, it is manually confirmed whether it is abnormal.

[0011] In some embodiments of the present invention, wavelet denoising is used to filter the data in step (1).

[0012] In some embodiments of the present invention, step (3) involves calling the dimensionality reduction target features determined in the basic classification library to extract the corresponding feature values.

[0013] In some embodiments of the present invention, in step (5), all feature vectors Y1 formed by normal data and after dimensionality reduction and all feature vectors Y2 formed by abnormal data and after dimensionality reduction are called in the basic classification library to form two point groups in the vector space; on this basis, the feature vector Y to be classified is placed in the formed vector space, and its data type is determined according to which point group it is in.

[0014] To achieve the above objectives, the present invention provides a bridge construction monitoring data anomaly identification system, the identification system comprising:

[0015] A data filtering module is configured to filter the incoming data stream and remove sharp data from the data stream.

[0016] The feature vector generation module is configured to interact with the data filtering module and can calculate and extract several statistical feature values ​​for the filtered data stream, and form a component vector based on the several statistical feature values ​​to form a one-dimensional feature vector X.

[0017] The data dimensionality reduction module is configured to interact with the feature vector generation module and to select several corresponding feature values ​​from the feature vector X generated by the feature vector generation module according to a preset standard to form a new feature vector Y.

[0018] The initial analysis module is configured to interact with the data dimensionality reduction module and the basic classification library, and can use the SVDD model single-class support vector machine to call the basic classification library to perform anomaly identification on the feature vector Y after dimensionality reduction by the data dimensionality reduction module.

[0019] The optimization analysis module is configured to interact with the initial analysis module and the basic classification library, and can use the binary classification support vector machine of the SMO algorithm to call the basic classification library to re-identify and judge the data that was judged as abnormal by the initial analysis module: if it is judged as abnormal data, it is finally judged as abnormal data; if it is judged as normal data, it is manually confirmed whether it is abnormal.

[0020] A basic classification library, which contains several feature vectors Y1 formed from normal data and reduced in dimensionality, and several feature vectors Y2 formed from abnormal data and reduced in dimensionality.

[0021] In some embodiments of the present invention, wavelet denoising is used in the data filtering module to filter the data.

[0022] In some embodiments of the present invention, the data dimensionality reduction module calls the dimensionality reduction target features determined in the basic classification library to extract the corresponding feature values.

[0023] In some embodiments of the present invention, the optimization analysis module calls all feature vectors Y1 formed from normal data and after dimensionality reduction, and all feature vectors Y2 formed from abnormal data and after dimensionality reduction, in the basic classification library to form two point groups in the vector space; on this basis, the feature vector Y to be classified is placed in the formed vector space, and its data type is determined according to which point group it is in.

[0024] To achieve the above objectives, the present invention also provides a computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the steps of the above-described method for identifying anomalies in bridge construction monitoring data.

[0025] To achieve the above objectives, the present invention also provides a processor for running a program, which executes the steps of the above-described method for identifying anomalies in bridge construction monitoring data.

[0026] To achieve the above objectives, the present invention also provides a terminal device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. The program code is loaded and executed by the processor to implement the steps of the above-described method for identifying anomalies in bridge construction monitoring data.

[0027] To achieve the above objectives, the present invention also provides a computer program product that, when executed on a data processing device, is adapted to perform the steps of the above-described method for identifying anomalies in bridge construction monitoring data.

[0028] The bridge construction monitoring data anomaly identification scheme provided by this invention can significantly improve the identification accuracy and reduce the misclassification rate compared with existing methods, and can effectively overcome the problems existing in the prior art.

[0029] The bridge construction monitoring data anomaly identification scheme provided by this invention has a wide range of applications and can be promoted and applied in the vast majority of bridge construction monitoring. Specifically, it can adapt to various construction environments such as bridge hydraulic climbing formwork, hanging basket construction, beam jacking, and scaffolding pouring. At the same time, it can generate considerable social and economic benefits in project construction. Attached Figure Description

[0030] The present invention will be further described below with reference to the accompanying drawings and specific embodiments.

[0031] Figure 1 This is a basic flowchart of the bridge construction monitoring data anomaly identification method in this invention;

[0032] Figure 2 This is a system schematic diagram of the bridge construction monitoring data anomaly identification system of the present invention;

[0033] Figure 3 This is a schematic diagram illustrating the initial analysis performed in this invention;

[0034] Figure 4 This is a schematic diagram illustrating the optimization analysis performed in this invention;

[0035] Figure 5 This is a flowchart illustrating the specific implementation of the bridge construction monitoring data anomaly identification method in this invention. Detailed Implementation

[0036] To make the technical means, creative features, objectives and effects of this invention easier to understand, the invention will be further described below with reference to specific illustrations.

[0037] In response to the characteristics of bridge construction safety monitoring data, the present invention proposes an improved and optimized joint machine learning algorithm based on single-class support vector machine and binary support vector machine, thereby achieving high-precision identification of abnormal construction monitoring data, improving early warning efficiency, and effectively avoiding missed or false alarms.

[0038] Based on this, the present invention innovatively incorporates dimensionality reduction methods and outlier dynamic storage methods into the joint machine learning algorithm, thereby further improving detection accuracy.

[0039] The present invention can effectively overcome the shortcomings of single classification method, such as lack of data dimensionality reduction and optimization methods and excessively high error warning rate, as well as the shortcomings of binary classification method, such as excessive requirements on basic training database, thereby achieving high-precision identification and early warning.

[0040] It should be noted that the bridge construction monitoring data addressed in this invention involves various data during the bridge construction process. Taking high-altitude hanging basket casting of bridges as an example, this mainly includes: suspender tension, stress of main members, on-site temperature and humidity, wind speed, acceleration, tilt angle, etc.

[0041] In response, this invention provides a method for anomaly identification in bridge construction monitoring data, such as... Figure 1 As shown, this anomaly detection method consists of the following steps:

[0042] S1: Data filtering.

[0043] This step filters the incoming bridge construction monitoring data stream, removing a few sharp data points to reduce noise and improve the accuracy of subsequent anomaly identification.

[0044] S2: Generate feature vectors.

[0045] This step involves calculating and extracting several statistical feature values ​​from the filtered data stream in step S1, and forming a component vector based on these statistical feature values ​​to create a one-dimensional feature vector X. Each statistical feature value in the one-dimensional feature vector X reflects a certain characteristic of the data in a specific dimension. This transforms the filtered data stream into a one-dimensional feature vector X.

[0046] Since a data stream consists of dozens, hundreds, or even thousands of values, this step extracts and statistically analyzes these values ​​to convert them into a small number of feature vector values, thereby representing the data stream from different perspectives, in order to improve the accuracy and efficiency of subsequent data processing.

[0047] Each value of the one-dimensional feature vector X generated here is a statistical feature value of this data stream, specifically including the mean x1, maximum value x2, minimum value x3, peak-to-peak value x4, rectified mean x5, standard deviation x6, skewness x7, kurtosis x8, root mean square x9, and waveform index x1. 10 Peak index x 11 Pulse index x 12 Frequency center x 13 Root mean square frequency x 14 Frequency standard deviation x 15 .

[0048] The resulting one-dimensional feature vector X uses these 15 values ​​to represent this data stream from different perspectives.

[0049] S3: Data dimensionality reduction.

[0050] This step selects several corresponding feature values ​​from the feature vector X determined in step (2) according to a preset standard to form a new feature vector Y.

[0051] Since the feature vector X generated in step (2) includes multiple feature vector values, in order to better adapt to the current project, the most suitable feature values ​​are selected by dimensionality reduction based on the current project, and feature values ​​with poor distinguishability are removed, thereby forming a new vector Y.

[0052] S4: Initial Analysis.

[0053] In this step, the SVDD model single-class support vector machine is used to call the basic classification library to identify the feature vector Y after dimensionality reduction in step S3 and determine whether it belongs to abnormal data. If it is determined to be abnormal data, proceed to the next section.

[0054] S5: Optimization Analysis.

[0055] This step uses a binary support vector machine with the SMO algorithm, calls the basic classification library, and re-determines the data that was judged as abnormal in step S4: if it is judged as abnormal data, it is finally judged as abnormal data; if it is judged as normal data, it is manually confirmed whether it is abnormal.

[0056] This step, based on the initial analysis in step (4), further optimizes the analysis based on the basic classification library, effectively overcoming the drawbacks of single classification method (lack of data dimensionality reduction optimization method, high error warning rate) and binary classification method (high requirements for basic training database), thereby achieving high-precision identification and warning.

[0057] Meanwhile, data that is ultimately determined to be abnormal will be entered into the basic classification library for subsequent anomaly identification.

[0058] As further explanation, this anomaly identification method preferably employs wavelet denoising for data filtering in step S1. Here, wavelet denoising is used to efficiently filter data such as wind speed, acceleration, and dynamic tilt angle, ensuring effective filtering.

[0059] As a further explanation, in step S3 of this anomaly identification method, the corresponding statistical features selected as the target features for dimensionality reduction in the feature vector X are preferably determined when establishing the basic classification library to ensure the efficiency of subsequent data reduction processing.

[0060] As further explanation, in step S4, when the anomaly identification method performs initial analysis based on the SVDD model single-class support vector machine, it specifically maps the corresponding feature vectors to a high-dimensional feature space and finds a hypersphere that surrounds the target vector in the high-dimensional space.

[0061] Meanwhile, the hypersphere formed in this step satisfies the following two requirements: (1) it encloses the feature vectors as much as possible; (2) the range enclosed by the hypersphere is as small as possible.

[0062] As further explained, this anomaly identification method also includes a basic classification library establishment step. The established basic classification library specifically includes several feature vectors Y1 formed from normal data and after dimensionality reduction, as well as several feature vectors Y2 formed from abnormal data and after dimensionality reduction, so as to provide data category determination for steps S4 and S5.

[0063] The anomaly identification method for bridge construction monitoring data provided in this invention can be configured into a corresponding software program to form a bridge construction monitoring data anomaly identification system. When running, this software program will execute the aforementioned bridge construction monitoring data anomaly identification method and store it in a corresponding storage medium for the processor to retrieve and execute.

[0064] See Figure 2 The bridge construction monitoring data anomaly identification system 100 formed as a result mainly includes six functional modules: data filtering module 110, feature vector generation module 120, data dimensionality reduction module 130, initial analysis module 140, optimization analysis module 150, and basic classification library 160.

[0065] In this system, the data filtering module 110 is configured to filter the incoming bridge construction monitoring data stream and remove a very small number of sharp data points from the data stream.

[0066] Furthermore, the data filtering module 110 is specifically configured to use wavelet noise reduction method for data filtering.

[0067] The feature vector generation module 120 in this system is configured to interact with the data filtering module 110. It can calculate and extract several statistical feature values ​​from the data stream filtered by the data filtering module 110, and form a component vector based on these extracted statistical feature values, resulting in a one-dimensional feature vector X. Thus, the feature vector generation module 120 can convert a filtered data stream into a one-dimensional feature vector X, where each statistical feature value reflects a certain characteristic of the data in a specific dimension.

[0068] The data dimensionality reduction module 130 in this system is configured to interact with the feature vector generation module 120 and to select several corresponding feature values ​​from the feature vector X generated by the feature vector generation module 120 according to a preset standard to form a new feature vector Y.

[0069] Furthermore, the specific statistical features selected by the data dimensionality reduction module 130 from the feature vector X as the target features for dimensionality reduction are determined when the basic classification library is established.

[0070] The initial analysis module 140 in this system is configured to interact with the data dimensionality reduction module 130 and the basic classification library 160. It can use the SVDD model single-class support vector machine to call the basic classification library to perform anomaly identification on the feature vector Y after dimensionality reduction by the data dimensionality reduction module and determine whether it belongs to abnormal data. If it is determined to be abnormal data, it will proceed to the next section.

[0071] Furthermore, when performing initial analysis based on the SVDD model single-class support vector machine, the initial analysis module 140 specifically maps the corresponding feature vectors to a high-dimensional feature space and searches for a hypersphere that encloses the target vector in the high-dimensional space. Simultaneously, the formed hypersphere satisfies the following two requirements: 1. It encloses the feature vector as much as possible within it; 2. The enclosed area of ​​the hypersphere is as small as possible.

[0072] The optimization analysis module 150 in this system is configured to interact with the initial analysis module 140 and the basic classification library 160. It can use the binary classification support vector machine of the SMO algorithm to call the basic classification library and re-identify and judge the data that was judged as abnormal by the initial analysis module: if it is judged as abnormal data, it is finally judged as abnormal data; if it is judged as normal data, it is manually confirmed whether it is abnormal; the data that is finally judged as abnormal will be entered into the basic classification library for subsequent anomaly identification.

[0073] The basic classification library 160 in this system is specifically configured to include several feature vectors Y1 formed from normal data and after dimensionality reduction, as well as several feature vectors Y2 formed from abnormal data and after dimensionality reduction. At the same time, the basic classification library 160 is also configured to interact with the initial analysis module 140 and the optimization analysis module 150 to enable the two analysis modules to determine the data category.

[0074] Regarding the bridge construction monitoring data anomaly identification scheme provided by this invention, the following specific application examples illustrate the implementation process and corresponding technical features of the scheme.

[0075] In the specific implementation of the bridge construction monitoring data anomaly identification scheme provided by this invention, a corresponding bridge construction monitoring data anomaly identification system 100 is constructed based on the aforementioned scheme, such as... Figure 2 As shown.

[0076] The data filtering module 110 in the system filters the bridge construction monitoring data stream.

[0077] The monitored data is a one-dimensional signal, so the data filtering module 110 uses wavelet noise reduction to filter the data.

[0078] Specifically, the wavelet noise reduction process performed by this data filtering module 110 is as follows:

[0079] (1) Select a suitable wavelet basis and determine the decomposition level, and then perform wavelet decomposition on the signal.

[0080] (2) For each layer of high-frequency coefficients, select an appropriate threshold for hard or soft threshold filtering.

[0081] (3) Reconstruct the one-dimensional signal based on the deepest coefficients of wavelet decomposition and the high-frequency coefficients of each processed layer.

[0082] Furthermore, to ensure the data processing efficiency of real-time noise reduction, this example adopts the wavelet threshold noise reduction method, which can further improve the running efficiency of the algorithm on existing devices while ensuring the noise reduction effect.

[0083] Threshold denoising sets the high-frequency coefficients of wavelet decomposition that are less than a threshold to 0. Fixed threshold:

[0084]

[0085] Where N represents the length of the wavelet coefficients in this layer, and σ represents the wavelet noise intensity in this layer, the general calculation formula is:

[0086]

[0087] d i (t) represents the wavelet decomposition coefficients of the i-th layer.

[0088] The feature vector generation module 120 in the system specifically uses the following 15 statistical feature values: mean x1, maximum x2, minimum x3, peak-to-peak value x4, rectified mean x5, standard deviation x6, skewness x7, kurtosis x8, root mean square x9, and waveform index x1. 10 Peak index x 11 Pulse index x 12 Frequency center x 13 Root mean square frequency x 14 Frequency standard deviation x 15 .

[0089] After calculating each statistical characteristic value, a vector X = [x1, x2, x3, x4, x5, x6, x7, x8, x9, x 10 ,x 11 ,x 12 ,x 13 ,x 14 ,x15 This is the feature vector used for subsequent identification. This allows each statistical feature value in the vector to reflect a certain characteristic of the data in a specific dimension.

[0090] The data dimensionality reduction module 130 in the system selects corresponding statistical features as dimensionality reduction target features based on the feature vectors determined when the basic classification library is established. Subsequent data dimensionality reduction can be performed simply by extracting the data according to the determined dimensionality reduction target features.

[0091] Furthermore, in this example, the method for determining the target features for dimensionality reduction when establishing the basic classification library is illustrated below:

[0092] The 10-50 data stream segments are converted into 10-50 feature vectors, and these feature vectors are combined into a feature matrix in column vector form:

[0093]

[0094] Where: x ji Let represent the i-th eigenvalue of the j-th random variable.

[0095] The basic calculation process of the univariate feature selection algorithm is as follows:

[0096] (1) Data standardization

[0097]

[0098] in: The sample mean of each row of the matrix.

[0099] S i : Sample standard deviation of each row of elements in the matrix.

[0100] (2) Set the dimensionality reduction objective and select the evaluation function.

[0101] For each feature value, perform an F-test or chi-square test, and obtain a score for its separability based on these two evaluation functions.

[0102] Then, based on the set target number of dimensionality reduction features, select several statistical feature values ​​with the highest scores to form the feature vector Y.

[0103] (3) Composition of feature vectors

[0104] Based on the selected feature values, the new feature vector Y is used to replace the original feature vector X, and the names of the selected feature values ​​are output in sequence.

[0105] When the initial analysis module 140 in the system performs the initial analysis, such as Figure 3As shown, the specific process involves calling all feature vectors Y1 from the basic classification library, formed from normal data and after dimensionality reduction. These feature vectors form a minimal hypersphere in the vector space. The feature vector Y to be classified is placed in this vector space, and its data type is determined based on whether it lies inside the hypersphere.

[0106] (1) Y is inside the hypersphere: This is normal data;

[0107] (2) Y is outside the hypersphere: This is abnormal data.

[0108] See further Figure 3 In the diagram, black dots represent Y1, circles represent the smallest hypersphere composed of all Y1s, and white dots represent the feature vector Y to be classified.

[0109] The optimization analysis module 150 in the system is used to further determine the data (i.e., the abnormal feature vector Y) that was initially identified as abnormal in the analysis.

[0110] Combination Figure 4 The system retrieves all feature vectors Y1 (formed from normal data and reduced in dimensionality) and Y2 (formed from abnormal data and reduced in dimensionality) from the basic classification library, forming two point clusters in the vector space. The feature vector Y to be classified is then placed in this vector space, and its data type is determined based on which point cluster it belongs to.

[0111] (1) Y is in the Y1 group: This is normal data;

[0112] (2) Y is in the Y2 group: This is abnormal data.

[0113] See further Figure 4 In the diagram, squares represent Y1, circles represent Y2, and the solid line represents the optimal hyperplane. If the feature vector Y to be classified lies on the solid line closer to Y1, it belongs to the Y1 group; otherwise, it belongs to the Y2 group.

[0114] This example uses wind speed monitoring data during bridge construction as an example to illustrate the process of identifying abnormal data in the wind speed monitoring data during bridge construction using the bridge construction monitoring data anomaly identification system 100.

[0115] like Figure 5 As shown, the bridge construction monitoring data anomaly identification system 100 processes a segment of input wind speed monitoring data stream as follows:

[0116] (1) First, determine whether it is used for anomaly identification and early warning or for building a basic classification library.

[0117] (2) If used to establish a basic classification library, calculate 15 feature values ​​to form feature vector X. Combine all feature vectors in the library and select the feature values ​​with the best separability to form a new feature vector Y. Then, label the incoming data to indicate whether it is normal data or abnormal data and store it in the basic classification library.

[0118] (3) If used for anomaly identification and early warning, the data is filtered and then a feature vector X is generated. Based on several feature values ​​determined in the basic classification library, a new feature vector Y is generated by dimensionality reduction.

[0119] (4) For the new feature vector Y generated by dimensionality reduction, perform an initial analysis to determine if the data is abnormal. If there is no abnormality, the process ends directly. If the preliminary analysis indicates that the data is abnormal, proceed to step (5).

[0120] (5) Optimization analysis based on data identified as abnormal:

[0121] (5.1) If it is determined to be abnormal again, it will enter the subsequent early warning process, and be entered into the basic classification library and marked as abnormal data.

[0122] (5.2) If it is determined to be normal again, it will enter the manual identification process to determine its final result.

[0123] As can be seen from the above examples, the bridge construction monitoring data anomaly identification scheme proposed by Benming, based on a joint machine learning model that improves and optimizes single-class support vector machine and binary support vector machine, can achieve high-precision identification of construction monitoring anomaly data, improve early warning efficiency, and effectively avoid missed reports and false reports.

[0124] Based on the above-mentioned scheme for identifying anomalies in bridge construction monitoring data, this embodiment of the invention also provides a computer-readable storage medium storing a program thereon, which, when executed by a processor, implements the steps of the above-mentioned method for identifying anomalies in bridge construction monitoring data.

[0125] This invention also provides a processor for running a program, wherein the program executes the steps of the above-described method for identifying anomalies in bridge construction monitoring data.

[0126] This invention also provides a terminal device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. The program code is loaded and executed by the processor to implement the steps of the above-described method for identifying anomalies in bridge construction monitoring data.

[0127] The present invention also provides a computer program product, which, when executed on a data processing device, is adapted to perform the steps of the above-described method for identifying anomalies in bridge construction monitoring data.

[0128] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0129] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and modules described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0130] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied 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.

[0131] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0132] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0133] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0134] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0135] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0136] Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can store information using any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0137] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0138] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied 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.

[0139] The method, specific system unit, or part thereof of the present invention described above is a pure software architecture. It can be deployed via program code on physical media, such as hard disks, optical discs, or any electronic device (such as smartphones or computer-readable storage media). When a machine loads and executes the program code (e.g., a smartphone loads and executes it), the machine becomes an apparatus for implementing the present invention. The method and apparatus of the present invention can also be transmitted in program code form via transmission media, such as cables, optical fibers, or any transmission method. When the program code is received, loaded, and executed by a machine (e.g., a smartphone), the machine becomes an apparatus for implementing the present invention.

[0140] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. A method for identifying anomalies in bridge construction monitoring data, characterized in that, The identification method includes: (1) Data filtering: Filter the incoming data stream to remove sharp data from the data stream; (2) Generate feature vectors. Calculate and extract several statistical feature values ​​for the data stream after filtering in step (1), and form a composition vector based on the several statistical feature values ​​to form a one-dimensional feature vector X. (3) Data dimensionality reduction: Select several corresponding feature values ​​from the feature vector X determined in step (2) according to the preset standard to form a new feature vector Y; (4) Initial analysis: Using the SVDD model single-class support vector machine, the basic classification library is called to identify the feature vector Y after dimensionality reduction and determine whether it belongs to abnormal data; (5) Optimization analysis: A binary support vector machine based on the SMO algorithm is used. The basic classification library is called to re-determine the data that was judged as abnormal in step (4). If it is judged as abnormal data, it is finally judged as abnormal data; if it is judged as normal data, it is manually confirmed whether it is abnormal. In this step, all feature vectors Y1 formed by normal data and after dimensionality reduction and all feature vectors Y2 formed by abnormal data and after dimensionality reduction are called in the basic classification library to form two point groups in the vector space. On this basis, the feature vector Y to be classified is placed in the vector space formed, and its data type is determined according to which point group it is in.

2. The method for identifying anomalies in bridge construction monitoring data according to claim 1, characterized in that, In step (1), wavelet denoising is used to filter the data.

3. The method for identifying anomalies in bridge construction monitoring data according to claim 1, characterized in that, In step (3), the target features for dimensionality reduction determined in the basic classification library are called to extract the corresponding feature values.

4. A bridge construction monitoring data anomaly identification system, characterized in that, The identification system includes: A data filtering module is configured to filter the incoming data stream and remove sharp data from the data stream. The feature vector generation module is configured to interact with the data filtering module and can calculate and extract several statistical feature values ​​for the filtered data stream, and form a component vector based on the several statistical feature values ​​to form a one-dimensional feature vector X. The data dimensionality reduction module is configured to interact with the feature vector generation module and to select several corresponding feature values ​​from the feature vector X generated by the feature vector generation module according to a preset standard to form a new feature vector Y. The initial analysis module is configured to interact with the data dimensionality reduction module and the basic classification library, and can use the SVDD model single-class support vector machine to call the basic classification library to perform anomaly identification on the feature vector Y after dimensionality reduction by the data dimensionality reduction module. The optimization analysis module is configured to interact with the initial analysis module and the basic classification library, and can use the binary classification support vector machine of the SMO algorithm to call the basic classification library to re-identify and judge the data that was judged as abnormal by the initial analysis module: if it is judged as abnormal data, it is finally judged as abnormal data; if it is judged as normal data, it is manually confirmed whether it is abnormal. A basic classification library, which contains several feature vectors Y1 formed from normal data and reduced in dimensionality, and several feature vectors Y2 formed from abnormal data and reduced in dimensionality.

5. The bridge construction monitoring data anomaly identification system according to claim 4, characterized in that, The data filtering module uses wavelet denoising to filter the data.

6. The bridge construction monitoring data anomaly identification system according to claim 4, characterized in that, The data dimensionality reduction module calls the dimensionality reduction target features determined in the basic classification library to extract the corresponding feature values.

7. The bridge construction monitoring data anomaly identification system according to claim 4, characterized in that, The optimization analysis module calls all feature vectors Y1 formed from normal data and after dimensionality reduction, and all feature vectors Y2 formed from abnormal data and after dimensionality reduction, from the basic classification library to form two point groups in the vector space. Based on this, the feature vector Y to be classified is placed in the formed vector space, and its data type is determined according to which point group it belongs to.

8. A terminal device, comprising a processor, a memory, and a program stored in the memory and executable on the processor, characterized in that, The program is loaded and executed by the processor to implement the steps of the bridge construction monitoring data anomaly identification method according to any one of claims 1-3.

9. A computer program product, characterized in that, When executed on a data processing device, it is suitable for performing the steps of the bridge construction monitoring data anomaly identification method according to any one of claims 1-3.

Images