A method and system for detecting validity of two-dimensional displacement sensor data

Abstract

The present application relates to the field of electronic digital data processing technology, and specifically to a method and system for detecting the validity of two-dimensional displacement sensor data, the method comprising: obtaining the two-dimensional displacement data, axial force load data, horizontal force load data, vertical displacement and horizontal displacement of any measuring point on a structure at each acquisition time; combining the change trend of the two-dimensional data points in the time period of each acquisition time, and the discrete degree of the distribution of the two-dimensional data points, determining the vertical displacement characteristic value of the time period of each acquisition time; determining the first displacement abnormal value and the second displacement abnormal value of each acquisition time, and combining the abnormal degree of the two-dimensional displacement data at each acquisition time, obtaining the outlier correction value of the two-dimensional displacement data at each acquisition time; performing validity detection on all two-dimensional displacement data. The present application aims to improve the validity of two-dimensional displacement data detection and reduce the possibility of identifying abnormal two-dimensional displacement data as normal data.

Description

Technical Field

[0001] The present application relates to the technical field of electrical digital data processing, and in particular to a method and system for detecting the validity of two-dimensional displacement sensor data. Background Art

[0002] The two-dimensional displacement sensor is a high-precision measurement tool widely used in civil engineering structural tests. It is used to measure the bidirectional displacement caused by the deformation of the structure during the stress process. The two-dimensional displacement sensor provides an accurate and reliable method to monitor the displacement changes of the structure under various environmental and load conditions, which is essential for understanding the mechanical behavior of the structure. If there are abnormal data collected by the two-dimensional displacement sensor, it will affect the subsequent data analysis and structural evaluation results. Therefore, the validity test of the collected data is a key step to ensure the accuracy and reliability of its analysis results.

[0003] The existing technology usually uses the Local Outlier Factor (LOF) algorithm to detect abnormal data in two-dimensional data. However, the traditional LOF algorithm only considers the numerical difference between the detected data, and does not consider the influence of other data that are intrinsically related to the detected data and the detected data. For example, the change of the two-dimensional displacement data of a structure collected by a two-dimensional displacement sensor is usually related to the load applied to the structure. Therefore, when the LOF algorithm is directly used to detect the validity of the two-dimensional displacement sensor data, it is difficult to effectively detect the abnormal data, resulting in the inability to ensure the accuracy and reliability of the two-dimensional displacement sensor data analysis results. Summary of the invention

[0004] In view of the above, it is necessary to provide a two-dimensional displacement sensor data validity detection method and system, which improves the effectiveness of two-dimensional displacement data detection and reduces the possibility of identifying abnormal two-dimensional displacement data as normal data compared with the traditional two-dimensional displacement sensor data validity detection method:

[0005] In a first aspect, an embodiment of the present application provides a method for detecting validity of two-dimensional displacement sensor data, the method comprising the following steps:

[0006] Obtain the two-dimensional displacement data, axial force load data and horizontal force load data of any measuring point on the structure at each acquisition time;

[0007] Based on the initial position of any measuring point and the two-dimensional displacement data, obtaining the vertical displacement and horizontal displacement of any measuring point at each acquisition moment;

[0008] The axial force load data and vertical displacement at each acquisition moment are combined into two-dimensional data points, each acquisition moment and its multiple neighboring acquisition moments are combined into time periods, and the vertical displacement characteristic value of the time period at each acquisition moment is determined by combining the change trend of the two-dimensional data points in the time period at each acquisition moment and the discrete degree of the distribution of the two-dimensional data points;

[0009] Multiple neighboring collection moments of each collection moment are grouped into each neighborhood time period, and based on the difference in the change trend and the difference in the degree of dispersion between each neighborhood time period and the corresponding time period, and in combination with the vertical displacement characteristic value, the first displacement anomaly value of each collection moment is determined;

[0010] Based on the horizontal force load data and the horizontal displacement, the second displacement abnormal value at each acquisition time is obtained by adopting the same method as that for obtaining the first displacement abnormal value;

[0011] Based on the abnormality degree of the two-dimensional displacement data at each acquisition time, combined with the first displacement abnormality value and the second displacement abnormality value, determine the outlier correction value of the two-dimensional displacement data at each acquisition time;

[0012] Based on the outlier correction value, validity detection is performed on all two-dimensional displacement data, and all two-dimensional displacement data are divided into abnormal error data and normal data.

[0013] In one embodiment, the process of determining the vertical displacement and the horizontal displacement is:

[0014] A rectangular coordinate system is constructed with the initial position of any measuring point as the origin, the direction of the sliding rod of the two-dimensional displacement sensor as the x-axis, and the vertical direction as the y-axis;

[0015] Convert all two-dimensional displacement data into a rectangular coordinate system to obtain coordinate points corresponding to each two-dimensional displacement data;

[0016] The absolute value of the ordinate value and the absolute value of the abscissa value of any coordinate point are respectively used as the vertical displacement and the horizontal displacement of the coordinate point corresponding to the acquisition time.

[0017] In one embodiment, the process of determining the vertical displacement characteristic value is:

[0018] Obtain the fitting straight line of all two-dimensional data points in each time period, recorded as the first fitting straight line;

[0019] Calculate the average of the distances between all two-dimensional data points and the first fitting straight line in each time period, and record it as the first distance average;

[0020] The vertical displacement characteristic value is inversely proportional to the slope of the first fitting straight line and is proportional to the first distance mean.

[0021] In one embodiment, the expression of the vertical displacement characteristic value is:

[0022] ; In the formula, represents the vertical displacement characteristic value of the i-th time period; represents the mean value of the distance between all two-dimensional data points and the first fitting straight line in the i-th time period; represents the slope of the first fitting straight line in the ith time period; exp() represents an exponential function with a natural constant as the base.

[0023] In one embodiment, the process of determining the first displacement abnormal value is:

[0024] Obtain the fitted straight line of all two-dimensional data points in each neighborhood time period, recorded as the second fitted straight line;

[0025] Calculate the average value of the distance between all two-dimensional data points and the second fitting straight line in each neighborhood time period, and record it as the second distance average value;

[0026] Calculate the difference between the second distance mean and the first distance mean, and record it as the distance difference;

[0027] Calculate the difference between the slope of the second fitting straight line and the slope of the first fitting straight line, and record it as the slope difference;

[0028] The first displacement abnormal value is positively correlated with the vertical displacement characteristic value and the slope difference, and negatively correlated with the distance difference.

[0029] In one embodiment, the expression of the first displacement abnormal value is:

[0030] );where, represents the first displacement anomaly value at the i-th acquisition moment; represents the vertical displacement characteristic value of the i-th time period; represents the slope of the second fitting straight line in the i-th neighborhood time period; represents the slope of the first fitting straight line in the i-th time period; represents the mean value of the distance between all two-dimensional data points and the second fitting straight line in the i-th neighborhood time period; represents the mean of the distances between all two-dimensional data points and the first fitting straight line in the i-th time period; exp() represents an exponential function with a natural constant as the base; norm() is a normalization function.

[0031] In one embodiment, the process of determining the outlier correction value is as follows:

[0032] The fusion result of the first displacement abnormal value and the second displacement abnormal value is used as the displacement data abnormal value at each acquisition time;

[0033] Anomaly detection algorithm is used to obtain outliers of the two-dimensional displacement data at each acquisition moment;

[0034] The outlier correction value of the two-dimensional displacement data at each acquisition time is obtained by combining the abnormal value of the displacement data with the outlier value.

[0035] In one embodiment, the outlier correction value is the product of the displacement data abnormal value and the outlier value.

[0036] In one embodiment, the method for dividing all two-dimensional displacement data into abnormal error data and normal data is: the two-dimensional displacement data with an outlier correction value greater than a preset outlier threshold is regarded as abnormal error data, and the remaining two-dimensional displacement data is regarded as normal data.

[0037] In a second aspect, an embodiment of the present application further provides a two-dimensional displacement sensor data validity detection system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of any one of the above-mentioned two-dimensional displacement sensor data validity detection methods when executing the computer program.

[0038] This application has at least the following beneficial effects:

[0039] The present application determines the first displacement abnormal value and the second displacement abnormal value at each acquisition time by analyzing the influence of the axial force load and the horizontal force load of the structure on the vertical displacement and the horizontal displacement of the measuring point, and then determines the displacement data abnormal value, thereby improving the distinction between the normal two-dimensional displacement data that conforms to the normal change law between the load applied to the structure and the bidirectional displacement of the measuring point, and the abnormal two-dimensional displacement data that does not conform to the normal change law, among all the two-dimensional displacement data collected by the two-dimensional displacement sensor;

[0040] Furthermore, based on the outliers of the displacement data, the outliers of the two-dimensional displacement data collected by the two-dimensional displacement sensor in the LOF algorithm are corrected, and the abnormal data in the two-dimensional displacement sensor data is detected according to the corrected outliers, so as to realize the validity detection of the two-dimensional displacement sensor data, and consider the influence of the axial force load and the horizontal force load of the structure on the vertical displacement and the horizontal displacement of the measuring point on the structure, thereby improving the validity of the two-dimensional displacement data detection, and reducing the possibility that the LOF algorithm identifies the abnormal data in the two-dimensional displacement sensor data that does not conform to the normal change law between the bidirectional displacement and the load applied to the target object as normal data, thereby improving the accuracy and reliability of the two-dimensional displacement sensor data. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0042] Figure 1 A flowchart of a method for detecting validity of two-dimensional displacement sensor data provided by one embodiment of the present application;

[0043] Figure 2 This is the distribution diagram of measuring points of steel-reinforced concrete components;

[0044] Figure 3 It is a schematic diagram of collecting data of two-dimensional displacement sensor;

[0045] Figure 4 It is a schematic diagram of the process of obtaining vertical displacement and horizontal displacement;

[0046] Figure 5 It is a schematic diagram of the process of determining the vertical displacement eigenvalue;

[0047] Figure 6 is a schematic diagram of the process of determining the first displacement abnormal value;

[0048] Figure 7 Schematic diagram of the process of determining the outlier correction value. DETAILED DESCRIPTION

[0049] In the description of the embodiments of the present application, words such as "exemplary", "or", "for example" and the like are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "or", "for example" and the like is intended to present related concepts in a concrete manner.

[0050] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art in the present application. The terms used in the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. It should be understood that, unless otherwise specified, " / " means or.

[0051] It should also be noted that the terms "first" and "second" in the present application are used to distinguish similar objects rather than to describe a specific order or sequence.

[0052] The following is a detailed description of a two-dimensional displacement sensor data validity detection method and system provided by the present application in conjunction with the accompanying drawings.

[0053] See also Figure 1 , which shows a flowchart of a method for detecting the validity of two-dimensional displacement sensor data provided by an embodiment of the present application, the method comprising the following steps:

[0054] Step 1: Obtain the two-dimensional displacement data, axial force load data and horizontal force load data of any measuring point on the structure at each acquisition time.

[0055] In order to monitor the deformation of the structure under load, measuring points are arranged at key parts of the structure. For example, when monitoring the deformation of steel-reinforced concrete components under load, measuring points are usually arranged on the steel side of the steel-reinforced concrete components. The displacement of the measuring points is measured by a two-dimensional displacement sensor to monitor the bidirectional displacement generated when the structure is strained during the load application. The measuring point distribution diagram of the steel-reinforced concrete component is shown in the figure below. Figure 2 As shown, Figure 2 Here, 1, 2, 3, and 4 represent the measuring point, web steel frame, flange steel frame, and concrete, respectively.

[0056] Therefore, this application takes any measuring point on the structure as an example, fixes the two-dimensional displacement sensor next to the structure, and connects the end of the sliding rod of the two-dimensional displacement sensor to the any measuring point. Figure 3 As shown, Figure 3 5, 6, and 7 represent a two-dimensional displacement sensor, a sliding rod end of the two-dimensional displacement sensor, and a measuring point, respectively. The two-dimensional displacement sensor is used to collect two-dimensional displacement data of any measuring point during the period when the structure is loaded, and to collect load data during the period when the structure is loaded, and the load data includes axial force load data and horizontal force load data.

[0057] In this embodiment, when collecting two-dimensional displacement data and load data, the sampling frequency and collection time are 10 Hz and 10 seconds respectively. The values ​​of the sampling frequency and collection time are preset manually and can be set by the implementer. This application does not impose any special restrictions.

[0058] Step 2: Based on the initial position of any measuring point and the two-dimensional displacement data, obtain the vertical displacement and horizontal displacement of any measuring point at each acquisition time.

[0059] All collected axial force load data and horizontal force load data are normalized respectively.

[0060] In this embodiment, the Min-Max normalization method is used to normalize the data. As other implementation methods, on the basis of being able to realize normalization of the data, the implementer can use other existing technologies to normalize the data, such as the Z-Score normalization method, the decimal calibration normalization method, etc., and this application does not make any special restrictions.

[0061] Take the initial position of any measuring point as the origin, the direction of the sliding bar of the two-dimensional displacement sensor as the x-axis, and the vertical direction as the y-axis to construct a rectangular coordinate system, convert all the collected two-dimensional displacement data into the rectangular coordinate system, obtain the coordinate points corresponding to each two-dimensional displacement data, and take the absolute value of the ordinate value and the absolute value of the abscissa value of any coordinate point as the vertical displacement and horizontal displacement of any coordinate point at the corresponding collection time. The schematic diagram of the process of obtaining vertical displacement and horizontal displacement is shown in the figure. Figure 4 shown.

[0062] Step 3, the axial force load data and vertical displacement of each acquisition moment are combined into two-dimensional data points, each acquisition moment and its multiple neighboring acquisition moments are combined into time periods, and the vertical displacement characteristic value of the time period of each acquisition moment is determined by combining the change trend of the two-dimensional data points in the time period of each acquisition moment and the discrete degree of the distribution of the two-dimensional data points.

[0063] Under normal circumstances, when a load is applied to a structure, the greater the axial force load applied, the greater the deformation of the structure in the vertical direction, so that when the measuring point is strained during the period when the structure is loaded, the vertical displacement generated will increase with the increase of the axial force load, and the vertical displacement and the axial force load usually have a good linear relationship. Similarly, when the measuring point is strained during the period when the structure is loaded, the horizontal displacement generated and the horizontal force load also have this relationship.

[0064] Based on the above analysis, each collection moment and a preset number of collection moments with the shortest time interval therebetween form a time period in which each collection moment is located.

[0065] In this embodiment, the value of the preset number is 20. The value of the preset number is preset manually and can be set by the implementer. This application does not impose any special restrictions.

[0066] The axial force load data and vertical displacement at each acquisition time are combined into two-dimensional data points, and a fitting straight line of all two-dimensional data points in each time period is obtained, which is recorded as the first fitting straight line.

[0067] In this embodiment, the least squares straight line fitting method is used to obtain the fitting straight line of all two-dimensional data points in the time period. As other implementation methods, on the basis of obtaining the fitting straight line of all two-dimensional data points in the time period, the implementer can use other existing technologies to obtain the fitting straight line, such as linear regression analysis, weighted least squares method, etc., and this application does not make any special restrictions.

[0068] Based on the slope of the first fitting straight line in each time period and the degree of dispersion of all two-dimensional data points around the first fitting straight line in each time period, the vertical displacement characteristic value of each time period is determined to characterize the possibility of abnormal vertical displacement when any measuring point is strained during the period when the structure is loaded in each time period. The expression is:

[0069] ; In the formula, represents the vertical displacement characteristic value of the i-th time period; represents the mean value of the distance between all two-dimensional data points and the first fitting straight line in the i-th time period; represents the slope of the first fitting straight line in the i-th time period; exp() represents an exponential function with a natural constant as the base, in order to prevent the denominator from being 0.

[0070] It should be noted that: in the i-th time period, when any measuring point is strained, the vertical displacement generated tends to increase with the increase of the axial force load applied to the structure, that is, The larger the vertical displacement, the stronger the linear relationship between the vertical displacement and the axial force load, i.e. The smaller the vertical displacement is, the smaller the possibility of abnormal vertical displacement will be when any measuring point is strained during the period when the structure is loaded. That is, the smaller the vertical displacement characteristic value is. The flow chart of determining the vertical displacement characteristic value is as follows: Figure 5 shown.

[0071] Step 4: Group multiple neighboring collection moments of each collection moment into neighborhood time periods, and determine the first displacement anomaly value of each collection moment based on the difference in the change trend and the difference in the degree of discreteness between each neighborhood time period and the corresponding time period, and in combination with the vertical displacement characteristic value.

[0072] Furthermore, if any of the measuring points is strained during the period when the structure is loaded, and the vertical displacement generated at the i-th acquisition moment is abnormal, then for the time period in which the i-th acquisition moment is located, the i-th acquisition moment is removed from the time period to obtain a neighboring time period. In the i-th neighboring time period, when any of the measuring points is strained, the vertical displacement generated tends to increase with the increase of the axial force load applied to the structure, which is more significant than before the removal, and the linear relationship between the vertical displacement and the axial force load is stronger than before the removal.

[0073] Based on the above analysis, a fitting straight line of all two-dimensional data points in each neighborhood time period is obtained and recorded as a second fitting straight line.

[0074] In this embodiment, the least squares straight line fitting method is used to obtain the fitting straight line of all two-dimensional data points in each neighborhood time period. As other implementation methods, on the basis of being able to obtain the fitting straight line of all two-dimensional data points in each neighborhood time period, the implementer can use other existing technologies to obtain the fitting straight line, such as linear regression analysis, weighted least squares method, etc., and this application does not make any special restrictions.

[0075] Based on the difference in slope between the second fitting straight line in each neighborhood time period and the first fitting straight line in the corresponding time period, and the difference in the degree of dispersion of all two-dimensional data points around the second fitting straight line in each neighborhood time period relative to the degree of dispersion of all two-dimensional data points around the first fitting straight line in the corresponding time period, and combined with the vertical displacement characteristic value, the first displacement abnormal value corresponding to the acquisition time of each neighborhood time period is determined, which is used to characterize the possibility of abnormal vertical displacement generated at each acquisition time when any measuring point is strained during the period when the structure is loaded, and the expression is:

[0076] );where, represents the first displacement anomaly value at the i-th acquisition moment; represents the vertical displacement characteristic value of the i-th time period; represents the slope of the second fitting straight line in the i-th neighborhood time period; represents the slope of the first fitting straight line in the i-th time period; represents the mean value of the distance between all two-dimensional data points and the second fitting straight line in the i-th neighborhood time period; It represents the mean of the distances between all two-dimensional data points and the first fitting straight line in the i-th time period; exp() represents an exponential function with a natural constant as the base, in order to prevent the denominator from being 0; norm() is a normalization function.

[0077] In this embodiment, the normalization function refers to the Min-Max normalization method. As other implementation methods, on the basis of achievable normalization processing, the implementer can adopt other existing technologies for normalization processing, such as the Z-Score normalization method, the decimal calibration normalization method, etc., and this application does not make any special restrictions.

[0078] It should be noted that: when any measuring point is strained during the period when the structure is loaded, the greater the possibility of abnormal vertical displacement in the time period of the i-th acquisition moment, that is, the greater the vertical displacement characteristic value; and the trend of the vertical displacement increasing with the increase of the axial force load in the neighboring time period is more significant than the trend of the vertical displacement increasing with the increase of the axial force load in the time period, that is, The larger the value is, the stronger the linear relationship between the vertical displacement and the axial force load in the neighborhood time period is relative to the linear relationship between the vertical displacement and the axial force load in the time period, that is, The smaller it is, the greater the possibility that the vertical displacement generated at the i-th acquisition moment is abnormal, that is, the larger the first displacement abnormal value is. The schematic diagram of the process of determining the first displacement abnormal value is as follows: Figure 6 shown.

[0079] Step 5: Based on the horizontal force load data and the horizontal displacement, the second displacement abnormal value at each acquisition moment is obtained by adopting the same method as that for obtaining the first displacement abnormal value.

[0080] According to the same acquisition method as the first displacement anomaly value, the second displacement anomaly value at each acquisition moment is obtained for the horizontal force load data and the horizontal displacement, which is used to characterize the possibility of an abnormality in the horizontal displacement generated at the i-th acquisition moment when any measuring point is strained during the period when the structure is loaded. Among them, it is only necessary to replace the axial force load data with the horizontal force load data, and the vertical displacement with the horizontal displacement.

[0081] Step 6: Based on the abnormality degree of the two-dimensional displacement data at each acquisition moment, combined with the first displacement abnormality value and the second displacement abnormality value, determine the outlier correction value of the two-dimensional displacement data at each acquisition moment.

[0082] Step 6.1: based on the first displacement abnormal value and the second displacement abnormal value, obtain the displacement data abnormal value at each acquisition time.

[0083] Furthermore, the fusion result of the first displacement abnormal value and the second displacement abnormal value at each acquisition moment is used as the displacement data abnormal value at each acquisition moment.

[0084] It should be understood that fusion refers to combining multiple independent variables in a way that enhances the overall effect, such as an additive relationship, a multiplicative relationship, etc. The implementer may limit it according to the actual situation, and this application does not impose any special restrictions.

[0085] In this embodiment, the sum of the first displacement abnormal value and the second displacement abnormal value at each acquisition moment is used as the displacement data abnormal value at each acquisition moment.

[0086] In another embodiment, the product of the first displacement abnormal value and the second displacement abnormal value at each acquisition moment is used as the displacement data abnormal value at each acquisition moment.

[0087] It should be noted that the displacement data abnormal value is used to characterize the possibility that when any measuring point is strained during the period when the structure is loaded, there is an abnormality in the changing pattern between the bidirectional displacement generated and the load applied to the target object; the larger the first displacement abnormal value and the second displacement abnormal value are, the greater the possibility that the changing pattern is abnormal, and the larger the displacement data abnormal value is.

[0088] Step 6.2, based on the abnormal degree of the two-dimensional displacement data at each acquisition moment and the abnormal value of the displacement data, obtain the outlier correction value of the two-dimensional displacement data at each acquisition moment.

[0089] All the two-dimensional displacement data collected by the two-dimensional displacement sensor at any measuring point are used as the input of the local outlier factor (LOF) algorithm, the outlier ratio parameter in the LOF algorithm is set to 0.1, the metric distance is the Euclidean distance, and the outlier value of the two-dimensional displacement data at each collection time is output. The LOF algorithm is a well-known technology and will not be described in detail in this application.

[0090] The product of the outlier value of the two-dimensional displacement data at each acquisition moment and the abnormal value of the displacement data at each acquisition moment is used as the outlier correction value of the two-dimensional displacement data at each acquisition moment, which is used to characterize the correction result of the outlier value of each two-dimensional displacement data in the LOF algorithm. When any measuring point is strained during the period when the structure is loaded, the greater the possibility that the change law between the generated bidirectional displacement and the load applied to the target object is abnormal, that is, the larger the abnormal value of the displacement data, the greater the possibility that the two-dimensional displacement data is abnormal erroneous data, and the larger the outlier value of the two-dimensional displacement data in the LOF algorithm should be, that is, the larger the outlier correction value. The schematic diagram of the process of determining the outlier correction value is shown in the figure below. Figure 7 shown.

[0091] Step 7: Perform validity detection on all two-dimensional displacement data based on the outlier correction value, and divide all two-dimensional displacement data into abnormal error data and normal data.

[0092] Furthermore, an outlier threshold is set, the two-dimensional displacement data whose outlier correction value is greater than the preset outlier threshold is regarded as abnormal error data, the remaining two-dimensional displacement data is regarded as normal data, and the abnormal error data and normal data are stored separately.

[0093] In this embodiment, the value of the outlier threshold is 1.2. The value of the outlier threshold is preset manually and can be set by the implementer. This application does not impose any special restrictions.

[0094] Based on the same inventive concept as the above method, an embodiment of the present application also provides a two-dimensional displacement sensor data validity detection system, including a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, the steps of any one of the above-mentioned two-dimensional displacement sensor data validity detection methods are implemented.

[0095] In summary, the present application determines the first displacement abnormal value and the second displacement abnormal value at each acquisition time by analyzing the influence of the axial force load and the horizontal force load of the structure on the vertical displacement and the horizontal displacement of the measuring point, and then determines the abnormal value of the displacement data, thereby improving the distinction between the normal two-dimensional displacement data that conforms to the normal change law between the load applied to the structure and the bidirectional displacement of the measuring point, and the abnormal two-dimensional displacement data that does not conform to the normal change law, among all the two-dimensional displacement data collected by the two-dimensional displacement sensor;

[0096] Furthermore, based on the outliers of the displacement data, the outliers of the two-dimensional displacement data collected by the two-dimensional displacement sensor in the LOF algorithm are corrected, and the abnormal data in the two-dimensional displacement sensor data is detected according to the corrected outliers, so as to realize the validity detection of the two-dimensional displacement sensor data, and consider the influence of the axial force load and the horizontal force load of the structure on the vertical displacement and the horizontal displacement of the measuring point on the structure, thereby improving the validity of the two-dimensional displacement data detection, and reducing the possibility that the LOF algorithm identifies the abnormal data in the two-dimensional displacement sensor data that does not conform to the normal change law between the bidirectional displacement and the load applied to the target object as normal data, thereby improving the accuracy and reliability of the two-dimensional displacement sensor data.

[0097] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

[0098] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the basic features of the present application. Therefore, no matter from which point of view, the above embodiments of the present application should be regarded as exemplary and non-restrictive.

Claims

1. A method for detecting the validity of two-dimensional displacement sensor data, characterized in that: The method comprises the following steps: Obtain the two-dimensional displacement data, axial force load data and horizontal force load data of any measuring point on the structure at each acquisition time; Based on the initial position of any measuring point and the two-dimensional displacement data, obtaining the vertical displacement and horizontal displacement of any measuring point at each acquisition moment; The axial force load data and vertical displacement at each acquisition moment are combined into two-dimensional data points, each acquisition moment and its multiple neighboring acquisition moments are combined into time periods, and the vertical displacement characteristic value of the time period at each acquisition moment is determined by combining the change trend of the two-dimensional data points in the time period at each acquisition moment and the discrete degree of the distribution of the two-dimensional data points; Multiple neighboring collection moments of each collection moment are grouped into each neighborhood time period, and based on the difference in the change trend and the difference in the degree of dispersion between each neighborhood time period and the corresponding time period, and in combination with the vertical displacement characteristic value, the first displacement anomaly value of each collection moment is determined; Based on the horizontal force load data and the horizontal displacement, the second displacement abnormal value at each acquisition time is obtained by adopting the same method as that for obtaining the first displacement abnormal value; Based on the abnormality degree of the two-dimensional displacement data at each acquisition time, combined with the first displacement abnormality value and the second displacement abnormality value, determine the outlier correction value of the two-dimensional displacement data at each acquisition time; Based on the outlier correction value, validity detection is performed on all two-dimensional displacement data, and all two-dimensional displacement data are divided into abnormal error data and normal data.

2. A two-dimensional displacement sensor data validity detection method as claimed in claim 1, characterized in that: The determination process of the vertical displacement and the horizontal displacement is: A rectangular coordinate system is constructed with the initial position of any measuring point as the origin, the direction of the sliding rod of the two-dimensional displacement sensor as the x-axis, and the vertical direction as the y-axis; Convert all two-dimensional displacement data into a rectangular coordinate system to obtain coordinate points corresponding to each two-dimensional displacement data; The absolute value of the ordinate value and the absolute value of the abscissa value of any coordinate point are respectively used as the vertical displacement and the horizontal displacement of the coordinate point corresponding to the acquisition time.

3. A two-dimensional displacement sensor data validity detection method as claimed in claim 1, characterized in that: The process of determining the vertical displacement characteristic value is as follows: Obtain the fitting straight line of all two-dimensional data points in each time period, recorded as the first fitting straight line; Calculate the average of the distances between all two-dimensional data points and the first fitting straight line in each time period, and record it as the first distance average; The vertical displacement characteristic value is inversely proportional to the slope of the first fitting straight line and is proportional to the first distance mean.

4. A two-dimensional displacement sensor data validity detection method as claimed in claim 3, characterized in that: The expression of the vertical displacement eigenvalue is: ; In the formula, represents the vertical displacement characteristic value of the i-th time period; represents the mean value of the distance between all two-dimensional data points and the first fitting straight line in the i-th time period; represents the slope of the first fitting straight line in the ith time period; exp() represents an exponential function with a natural constant as the base.

5. A two-dimensional displacement sensor data validity detection method as claimed in claim 3, characterized in that: The process of determining the first displacement abnormal value is as follows: Obtain the fitted straight line of all two-dimensional data points in each neighborhood time period, recorded as the second fitted straight line; Calculate the average value of the distance between all two-dimensional data points and the second fitting straight line in each neighborhood time period, and record it as the second distance average value; Calculate the difference between the second distance mean and the first distance mean, and record it as the distance difference; Calculate the difference between the slope of the second fitting straight line and the slope of the first fitting straight line, and record it as the slope difference; The first displacement abnormal value is positively correlated with the vertical displacement characteristic value and the slope difference, and negatively correlated with the distance difference.

6. A two-dimensional displacement sensor data validity detection method as claimed in claim 5, characterized in that: The expression of the first displacement anomaly value is: );where, represents the first displacement anomaly value at the i-th acquisition moment; represents the vertical displacement characteristic value of the i-th time period; represents the slope of the second fitting straight line in the i-th neighborhood time period; represents the slope of the first fitting straight line in the i-th time period; represents the mean value of the distance between all two-dimensional data points and the second fitting straight line in the i-th neighborhood time period; represents the mean of the distances between all two-dimensional data points and the first fitting straight line in the i-th time period; exp() represents an exponential function with a natural constant as the base; norm() is a normalization function.

7. A two-dimensional displacement sensor data validity detection method as claimed in claim 1, characterized in that: The process of determining the outlier correction value is as follows: The fusion result of the first displacement abnormal value and the second displacement abnormal value is used as the displacement data abnormal value at each acquisition time; Anomaly detection algorithm is used to obtain outliers of the two-dimensional displacement data at each acquisition moment; The outlier correction value of the two-dimensional displacement data at each acquisition time is obtained by combining the abnormal value of the displacement data with the outlier value.

8. A two-dimensional displacement sensor data validity detection method as claimed in claim 7, characterized in that: The outlier correction value is the product of the displacement data abnormal value and the outlier value.

9. A two-dimensional displacement sensor data validity detection method as claimed in claim 1, characterized in that: The method for dividing all two-dimensional displacement data into abnormal error data and normal data is: taking the two-dimensional displacement data whose outlier correction value is greater than a preset outlier threshold as abnormal error data, and taking the remaining two-dimensional displacement data as normal data.

10. A two-dimensional displacement sensor data validity detection system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of a two-dimensional displacement sensor data validity detection method as described in any one of claims 1-9 are implemented.

Images