CN118013636A - Masonry structure compressive property detection equipment and detection method - Google Patents
Masonry structure compressive property detection equipment and detection method Download PDFInfo
- Publication number
- CN118013636A CN118013636A CN202410409299.XA CN202410409299A CN118013636A CN 118013636 A CN118013636 A CN 118013636A CN 202410409299 A CN202410409299 A CN 202410409299A CN 118013636 A CN118013636 A CN 118013636A
- Authority
- CN
- China
- Prior art keywords
- compression
- resistant
- data point
- data points
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 25
- 230000006835 compression Effects 0.000 claims abstract description 269
- 238000007906 compression Methods 0.000 claims abstract description 269
- 238000000034 method Methods 0.000 claims abstract description 40
- 238000005259 measurement Methods 0.000 claims abstract description 32
- 239000006185 dispersion Substances 0.000 claims description 33
- 238000004422 calculation algorithm Methods 0.000 claims description 13
- 238000013507 mapping Methods 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 12
- 238000010606 normalization Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 4
- UXFQFBNBSPQBJW-UHFFFAOYSA-N 2-amino-2-methylpropane-1,3-diol Chemical compound OCC(N)(C)CO UXFQFBNBSPQBJW-UHFFFAOYSA-N 0.000 claims 1
- 101150035093 AMPD gene Proteins 0.000 claims 1
- 238000009826 distribution Methods 0.000 abstract description 22
- 230000002159 abnormal effect Effects 0.000 abstract description 12
- 239000000463 material Substances 0.000 abstract description 3
- 230000000704 physical effect Effects 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 7
- 230000007547 defect Effects 0.000 description 6
- 230000004927 fusion Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000005070 sampling Methods 0.000 description 4
- 206010000117 Abnormal behaviour Diseases 0.000 description 3
- 239000011449 brick Substances 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000977 initiatory effect Effects 0.000 description 2
- 239000004570 mortar (masonry) Substances 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 238000012827 research and development Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000004566 building material Substances 0.000 description 1
- 239000004567 concrete Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N3/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N3/08—Investigating strength properties of solid materials by application of mechanical stress by applying steady tensile or compressive forces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2203/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N2203/0014—Type of force applied
- G01N2203/0016—Tensile or compressive
- G01N2203/0019—Compressive
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Chemical & Material Sciences (AREA)
- Immunology (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Biochemistry (AREA)
- Software Systems (AREA)
- Analytical Chemistry (AREA)
- Pathology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Architecture (AREA)
- Civil Engineering (AREA)
- Structural Engineering (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Investigating Strength Of Materials By Application Of Mechanical Stress (AREA)
Abstract
The invention relates to the technical field of materials analyzed by means of physical properties, in particular to a masonry structure compressive property detection device and a masonry structure compressive property detection method. According to the method, a discrete metric value is obtained by obtaining a sample compression time number of a target masonry structure according to the size difference and the instability metric value difference of a kth distance neighborhood between compression data points; according to the difference between the reference measurement value and the corresponding discrete measurement value corresponding to the compression-resistant data point, the kth distance neighborhood is adjusted, and the adjusted kth distance neighborhood is obtained; and further acquiring an outlier data point set of the target masonry structure, and finally acquiring the compression resistance curve of the target masonry structure. According to the method, the k-th distance neighborhood is adjusted by combining the data point distribution condition and the data fluctuation condition, the adjusted k-th distance neighborhood which more reasonably reflects the reference range of the outlier condition is obtained, outlier abnormal data can be accurately screened out, and the accuracy of the compressive property of the masonry structure is improved.
Description
Technical Field
The invention relates to the technical field of materials analyzed by means of physical properties, in particular to a masonry structure compressive property detection device and a masonry structure compressive property detection method.
Background
Masonry is a building material consisting of bricks or stones bonded by mortar. Masonry is commonly used in the walls, columns, partitions, etc. of buildings, and is one of the basic materials of building structures. In the masonry process, mortar is generally used to bond bricks or stones, so that the structural strength and stability of the masonry are improved. The brickwork needs to accord with current building strength demand, and a plurality of brickwork samples that await measuring produce different pressure data changes in compressive testing process, need fuse the test data of multisamples in order to analyze brickwork structure compressive property.
Because the data distribution conditions of the fusion data of the masonry structure are different, the outlier abnormal data in the fusion data is detected by a common LOF algorithm in the prior art, and the accuracy of the fusion data is improved. Because the existing k-th distance neighborhood can not reflect the distribution condition of the fusion data, the numerical accuracy of the determined local outlier factors is affected, outlier abnormal data can not be screened accurately, and finally the accuracy of analyzing the compressive property of the masonry structure is reduced.
Disclosure of Invention
In order to solve the technical problems that outlier abnormal data cannot be accurately screened out and accuracy of analyzing compressive property of a masonry structure is reduced, the invention aims to provide masonry structure compressive property detection equipment and detection method, and the adopted technical scheme is as follows:
the invention provides a masonry structure compressive property detection method, which comprises the following steps:
acquiring sample compression-resistant time sequence data of a target masonry structure;
according to the difference of all the sample compression-resistant time sequence data at the same time, obtaining an instability measurement value corresponding to each time of the target masonry structure;
constructing an initial compression-resistant data point set of the target masonry structure according to all the sample compression-resistant time sequence data, and acquiring a kth distance neighborhood of all compression-resistant data points in the initial compression-resistant data point set;
acquiring dispersion metric values of all compression-resistant data points in an initial compression-resistant data point set according to the size difference and the instability metric value difference of the kth distance neighborhood between the compression-resistant data points; acquiring reference metric values of all compression-resistant data points according to the dispersion metric values of the compression-resistant data points in a preset reference range;
In an initial compression-resistant data point set, adjusting a kth distance neighborhood according to the difference between the reference measurement value and the dispersion measurement value corresponding to the compression-resistant data point, and acquiring an adjusted kth distance neighborhood of all compression-resistant data points in the initial compression-resistant data point set;
Acquiring an outlier data point set of the target masonry structure according to the adjusted kth distance neighborhood of all the compression data points in the initial compression data point set; and acquiring the compressive property curve of the target masonry structure according to the initial compressive data point set and the outlier data point set.
Further, the obtaining formula of the instability measurement value is as follows:
; wherein/> For/>The instability measurement values corresponding to the moments; for/> The time corresponds to the number of all masonry samples; /(I)For initial time to the/>The time period between moments; /(I)Is the firstEach masonry sample corresponds to the sample compression time sequence data in the/>A time-of-day compression resistance value; /(I)For/>The sample compression resistant time series data of individual masonry samples are in a time period/>The average value of all compression resistance values; /(I)For/>Each masonry sample corresponds to the sample compression-resistant time sequence data in a time period/>Standard deviation of all compression resistance values in (2); /(I)Is a parameter adjusting factor of denominator.
Further, the method for acquiring the initial compression-resistant data point set comprises the following steps:
taking time as a horizontal axis of the two-dimensional data space, and taking the compression resistance value as a vertical axis of the two-dimensional data space; mapping all compression values in all the sample compression time sequence data to a two-dimensional data space to obtain compression data points, and taking a set formed by all the compression data points as an initial compression data point set of the target masonry structure.
Further, the method for obtaining the dispersion metric value comprises the following steps:
Normalizing the k-th distance neighborhood radius of the target compression-resistant data point to obtain a neighborhood characteristic value of the target compression-resistant data point;
Taking the compression-resistant data point in the kth distance neighborhood of the target compression-resistant data point as a reference data point of the target compression-resistant data point;
Calculating the instability measurement value difference between the target compression-resistant data point and the reference data point, and obtaining a first instability difference value of the reference data point;
normalizing the accumulated values of the first unstable difference values of all the reference data points to obtain a second unstable difference value of the target compression-resistant data point;
acquiring the dispersion metric value of the target compression-resistant data point according to the neighborhood characteristic value and the second unstable difference value; the neighborhood characteristic value and the dispersion metric value are in positive correlation, and the second unstable difference value and the dispersion metric value are in positive correlation.
Further, the method for obtaining the reference metric value specifically includes:
constructing a two-dimensional reference coordinate system by taking a dispersion measurement value as a horizontal axis and the number of compression-resistant data points as a vertical axis;
Mapping all compression-resistant data points into the two-dimensional reference coordinate system in a preset reference range of the initial compression-resistant data point set to obtain each mapping point, and performing curve fitting on the mapping points to obtain a fitting curve to be processed of target compression-resistant data points;
And acquiring all peak points in the fitting curve to be processed based on an AMPD algorithm, and taking a discrete metric value corresponding to the peak points as the reference metric value of the target compression-resistant data point.
Further, the adjusted k-th distance neighborhood obtaining formula:
; wherein/> For/>A plurality of compression-resistant data points correspond to the adjusted kth distance neighborhood; /(I)For/>The plurality of compression-resistant data points correspond to the discrete metric values; /(I)For/>The compression-resistant data points correspond to the/>A plurality of reference metric values; /(I)For/>The compression-resistant data points correspond to the total number of reference measurement values; /(I)For/>A kth distance neighborhood corresponding to the compressive data point; /(I)Is an upward rounding function; /(I)Is a normalization function.
Further, the method for acquiring the outlier data point set comprises the following steps:
Obtaining local outliers of all the compression-resistant data points according to the adjusted k-th distance neighborhood of all the compression-resistant data points in the initial compression-resistant data point set based on an LOF algorithm;
Marking the compression-resistant data points with the local outlier factors larger than a preset outlier threshold as outlier data points;
and counting all the outlier data points, and acquiring the outlier data point set.
Further, the method for acquiring the preset reference range includes:
In the kth distance neighborhood of the target compression-resistant data point, taking the kth distance neighborhood of all compression-resistant data points as a first reference neighborhood range set;
taking the minimum value of the time corresponding to the k-th distance neighborhood in the first reference neighborhood range set as a first initial reference time;
taking the maximum value of the time corresponding to the k-th distance neighborhood in the first reference neighborhood range set as a first ending reference time;
and taking a time interval formed by the first initial reference time to the first ending reference time as a preset reference range of the target compression-resistant data point.
The invention provides a masonry structure compressive property detection device, which comprises a processor, wherein the processor realizes the steps of any one of the masonry structure compressive property detection methods when executing a computer program.
The invention has the following beneficial effects:
In the embodiment of the invention, through deep excavation of the sample compression-resistant time sequence data of the target masonry structure, when the quality of the masonry sample is defective, the detected compression-resistant condition of the masonry sample can generate larger fluctuation, and the instability measurement value corresponding to each moment of the target masonry structure is obtained. The instability metric may reflect the volatility of the target masonry structure to produce data under the effect of the defect. And fusing the compression-resistant time sequence data of all samples to construct an initial compression-resistant data point set of the target masonry structure. Simply adopting the k-th distance neighborhood may make the neighborhood range of the compression-resistant data points too large or too small, and when the judgment of the outlier is performed, the size of the neighborhood range can influence the distance measurement between the compression-resistant data points, so that the normal compression-resistant data points are misjudged as the outlier, and therefore the k-th distance neighborhood needs to be adjusted. The outlier characteristics of the compression-resistant data points are reflected more accurately through the distribution discrete condition and the data fluctuation difference of the compression-resistant data points, the k-th distance neighborhood is adjusted, the adjusted k-th distance neighborhood is obtained, and the adjusted k-th distance neighborhood can describe the analysis outlier condition reference range of the compression-resistant data points more accurately. Screening out and taking an outlier data point set; the outlier data point set may reflect data points in the data that are significantly different from other data points, which may represent abnormal behavior, erroneous recordings, or other deviations from the normal data distribution, and the effects of these abnormal data are stripped off to obtain a compressive property curve for the target masonry structure. The compressive property curve can more accurately reflect the compressive property of the target masonry structure, so that research and development personnel can analyze the compressive property parameters of the target masonry structure to adjust the structural proportion.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for detecting compressive property of a masonry structure according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a preset reference range according to an embodiment of the invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of a concrete implementation, a structure, characteristics and effects of the masonry structure compressive property detection device and the detection method according to the invention in combination with the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The invention provides a masonry structure compressive property detection device and a masonry structure compressive property detection method.
Referring to fig. 1, a flowchart of a method for detecting compressive property of a masonry structure according to an embodiment of the present invention is shown, the method includes the following steps:
Step S1, sample compression-resistant time sequence data of a target masonry structure are obtained.
In order to obtain the compressive property capable of accurately reflecting the target masonry structure, the sample compressive time sequence data set of the target masonry structure is deeply excavated for subsequent analysis of outliers in different sample compressive time sequence data, so that the data capable of truly reflecting the compressive property of the target masonry structure is obtained.
In one embodiment of the invention, a target masonry structure is manufactured into a plurality of masonry samples with the same size by the same preparation process, after preparation is completed, the masonry samples are respectively placed on a test stand, a test program is started, and gentle pressure set by the test program is applied to the masonry samples through the test stand; and the pressure sensor records the compression resistance and time of the detection equipment according to the preset sampling frequency, and acquires the sampling data of the masonry sample. Taking a discrete sequence formed by sampling data of all masonry samples in the testing process of the masonry samples as sample compression-resistant time sequence data, taking data points in the sample compression-resistant time sequence data as compression-resistant numerical values, and counting the sample compression-resistant time sequence data of all the masonry samples as a sample compression-resistant time sequence data set of a target masonry structure.
It should be noted that, because all the masonry samples are tested by the same test program, all the masonry samples are synchronously sampled, and the obtained compression resistance values at the same position in the compression resistance time series data of different samples correspond to the same sampling time, the test time of the compression resistance time series data of the samples is the same, and the applied pressure of different masonry samples is gradually increased in the test process. The corresponding time of the sample compression-resistant time sequence data is from the initial time to the ending time of the test, the initial time is zero, and the ending time is the duration of the test time. The masonry sample is manufactured through the same target masonry structure and the same manufacturing process, and the masonry sample is high in similarity.
It should be noted that, in order to facilitate the operation, all index data involved in the operation in the embodiment of the present invention is subjected to data preprocessing, so as to cancel the dimension effect. The specific means for removing the dimension influence is a technical means well known to those skilled in the art, and is not limited herein.
And S2, acquiring an instability measurement value corresponding to each moment of the target masonry structure according to the difference of all the sample compression-resistant time sequence data at the same moment.
Because the pressure applied to the masonry sample is gradually increased, the pressure applying condition and the pressure resisting condition of the masonry sample are always consistent in change, but the masonry sample can reach the limit condition to be damaged along with the increase of the applied pressure, when the quality of the masonry sample is defective, the detected pressure resisting condition of the masonry sample can generate larger fluctuation, the masonry sample is always similar, the abnormal condition of the target masonry structure is reflected more accurately by analyzing the pressure resisting time sequence data of all samples, and the unstable measurement value corresponding to each moment of the target masonry structure is acquired according to the difference of the pressure resisting time sequence data of all samples at the same moment. The instability metric may reflect the volatility of the target masonry structure to produce data under the effect of the defect.
Preferably, in one embodiment of the present invention, the method for obtaining the instability measurement value specifically includes:
Since the fluctuation of the sample compression-resistant time sequence data can reflect the defect condition, the method comprises the following steps of analyzing The fluctuation of the data in the time range corresponding to each moment is obtainedThe formula of the instability metric corresponding to each moment in one embodiment of the present invention includes:
; wherein/> For/>An unstable metric value corresponding to each moment; /(I)For/>The time corresponds to the number of all masonry samples; /(I)For initial time to the/>A time range corresponding to each moment; /(I)For/>The compressive time sequence data of the corresponding samples of each masonry sample is shown in the/>A time-of-day compression resistance value; /(I)For/>Sample compression-resistant time sequence data of each masonry sample are in time range/>The average value of all compression resistance values; /(I)For/>The pressure-resistant time sequence data of the corresponding samples of each masonry sample is in a time range/>Standard deviation of all compression resistance values in (2); /(I)Is a parameter adjusting factor of denominator. It should be noted that, the initial time is 1 st time, the masonry samples are often similar, but the quality difference exists between the masonry samples, the time from the initiation of the masonry sample test to the damage is longer, the masonry samples existing at part of the time are smaller than the masonry sample number at the initiation of the test, and the corresponding masonry sample number/>, under the passing timeThe calculation is more in line with the data fluctuation stability condition corresponding to each moment.
In the formula of the instability metric value,Reflect the/>Time of day compared to time range/>Since the abnormal fluctuation condition generated by the defect condition is larger than the normal fluctuation of the sample compression time sequence data in the time range, the larger the relative deviation is, the greater the possibility of the abnormal condition is; /(I)Comprehensive reflection of the/>The fluctuation in the time range corresponding to the moment, when the fluctuation is larger, the possibility of the abnormal situation of the corresponding time range is larger; by integrating the fluctuation of all masonry samples, the fluctuation of the data generated by the target masonry structure under the defect action can be reflected more accurately, so that the fluctuation data generated under the defect action should be prevented from being judged as outliers in the subsequent outlier identification.
Step S3, constructing an initial compression-resistant data point set of the target masonry structure according to compression-resistant time sequence data of all samples; a kth distance neighborhood of all the compression data points in the initial compression data point set is acquired.
In order to accurately reflect the compression resistance of the target masonry structure, as different masonry sample masonry structures have the same compression resistance and the same test program applied pressure, sample compression resistance time sequence data are similar, all sample compression resistance time sequence data are fused, an initial compression resistance data point set of the target masonry structure is constructed according to all sample compression resistance time sequence data, and the initial compression resistance data point set can comprehensively reflect the distribution of all sample compression resistance time sequence data for subsequent analysis of the data accuracy in the initial compression resistance data point set; the k-th distance neighborhood of all compression-resistant data points in the initial compression-resistant data point set is obtained, the k-th distance neighborhood is simply adopted, the neighborhood range of the compression-resistant data points can be too large or too small, when the judgment of the outlier is carried out, the size of the neighborhood range can influence the distance measurement between the compression-resistant data points, and the normal compression-resistant data points are misjudged as the outlier, so that the k-th distance neighborhood is obtained for subsequent adjustment of the k-th distance neighborhood.
Preferably, in one embodiment of the present invention, the method for acquiring the initial compression-resistant data point set specifically includes:
In order to comprehensively analyze compression-resistant time sequence data of all samples, firstly taking time as a horizontal axis of a two-dimensional data space and compression-resistant values as a vertical axis of the two-dimensional data space; mapping all compression values in all sample compression time sequence data to a two-dimensional data space to obtain compression data points, and taking a set formed by all compression data points as an initial compression data point set of a target masonry structure. It should be noted that the compression-resistant time sequence data of different samples have similarity, and after the compression-resistant time sequence data are mapped to the two-dimensional space in the same mode, the mapped data still have similarity, so that the distribution of the compression-resistant time sequence data of all samples can be better comprehensively analyzed.
Specifically, a kth distance neighborhood of all the compression-resistant data points in the initial compression-resistant data point set is obtained based on a LOF (Local Outlier Factor ) algorithm. The LOF algorithm is a technical means well known to those skilled in the art, and will not be described in detail herein. It should be noted that, the kth distance neighborhood in the LOF algorithm is a technical concept well known to those skilled in the art, and the kth distance neighborhood in the LOF algorithm mainly reflects the local data distribution situation around each data point, which is important for anomaly detection.
S4, obtaining the dispersion metric values of all compression-resistant data points in the initial compression-resistant data point set according to the size difference and the instability metric value difference of the kth distance neighborhood between the compression-resistant data points; and obtaining the reference metric values of all the compression-resistant data points according to the dispersion metric values of the compression-resistant data points in the preset reference range.
Because the pressure applied by the test program is smoothly changed, the distribution of the initial compression-resistant data points in a single initial compression-resistant data point set is concentrated, the masonry structures of different masonry samples are the same as the pressure applied by the test program, so that the sample compression-resistant time sequence data are similar, the distribution of the data in the initial compression-resistant data point set is concentrated, and the distribution discrete condition of the compression-resistant data points can be reflected more comprehensively due to the size difference of the k-th distance neighborhood among the compression-resistant data points. Different masonry sample masonry structures are the same as the test program applies pressure, fluctuation of sample compression time sequence data generated in abnormal conditions and normal conditions is similar, and the fluctuation difference of data reflecting the target masonry structure can be reflected by the instability measurement value difference between compression data points. The discrete characteristic of the compression-resistant data points is reflected more accurately through the distribution discrete condition and the data fluctuation difference of the compression-resistant data points, the k-th distance neighborhood is adjusted, the adjusted k-th distance neighborhood is obtained, in the initial compression-resistant data point set, the discrete metric values of all compression-resistant data points in the initial compression-resistant data point set are obtained according to the size difference and the instability metric value difference of the k-th distance neighborhood between the compression-resistant data points, and the discrete metric values can comprehensively reflect the discrete characteristic of the compression-resistant data points for subsequent adjustment of the k-th distance neighborhood.
Preferably, in one embodiment of the present invention, the method for obtaining a dispersion metric value includes:
normalizing the k-distance neighborhood radius of the target compression-resistant data point to obtain a neighborhood characteristic value of the target compression-resistant data point;
Taking the compression data point in the kth distance neighborhood of the target compression data point as a reference data point of the target compression data point;
Calculating the instability measurement value difference between the target compression-resistant data point and the reference data point, and acquiring a first instability difference value of the reference data point;
Normalizing the accumulated values of the first unstable difference values of all the reference data points to obtain a second unstable difference value of the target compression-resistant data point;
Acquiring a dispersion value of the target compression-resistant data point according to the neighborhood characteristic value and the second unstable difference value; the neighborhood characteristic value and the discrete metric value are in positive correlation, and the second unstable difference value and the discrete metric value are in positive correlation.
The data distribution in the initial compression-resistant data point set is concentrated, and the first is comprehensively analyzedThe compression-resistant data points correspond to the difference of data distribution and fluctuation degree in the k-distance neighborhood, and the/>The plurality of compression-resistant data points corresponds to a discrete metric value. In one embodiment of the invention, the formula of the dispersion metric value is:
; wherein/> For the/>, in the initial set of pressure-resistant data pointsThe compressive data points correspond to discrete metric values; /(I)For/>The compression-resistant data points correspond to the kth distance neighborhood radius; /(I)For/>A reference radius set of all compression-resistant data points in the k-th distance neighborhood of the compression-resistant data points corresponding to the k-th distance neighborhood radius; /(I)For reference radius set/>Is the minimum value of (a); /(I)For reference radius set/>Maximum value of (2); /(I)For/>The number of crush-resistant data points corresponds to the total number of crush-resistant data points in the kth distance neighborhood; /(I)For/>An instability measurement value at a moment corresponding to each compression-resistant data point; /(I)For/>An instability measurement value at a moment corresponding to each compression-resistant data point; to take the minimum function; /(I) Is a maximum function; /(I)Is a normalization function. In the embodiment of the present invention, the following is the description of the embodiments of the present inventionPair/>Normalization is performed, and other normalization pairs/>, may be used in other embodiments of the inventionNormalized to the value range [0,1], and will not be described in detail herein.
In the formula of the discrete metric value,Reflecting the/>The larger the relative difference between the compressive data points and the surrounding k-th distance neighborhood size, the more/>The more discrete the distribution of the pressure-resistant data points, the greater the value of the dispersion. /(I)The fluctuation difference of the data is reflected, because the fluctuation of the sample compression-resistant time sequence data in the abnormal condition and the normal condition is similar, the fluctuation difference is larger and is more likely to be an outlier, the larger the dispersion value is, the dispersion value integrates the distribution dispersion condition and the fluctuation difference, the degree of the dispersion of the compression-resistant data point is reflected more comprehensively, and the larger the dispersion value is more likely to be the outlier.
And S5, adjusting the kth distance neighborhood according to the difference between the corresponding reference measurement value and the corresponding discrete measurement value of the compression-resistant data points, and obtaining the adjusted kth distance neighborhood of all compression-resistant data points in the initial compression-resistant data point set.
In order to adjust the kth distance neighborhood of the data point according to the surrounding concentration condition of the data point, acquiring reference metric values of all the compression-resistant data points according to the dispersion metric values of the compression-resistant data points in a preset reference range; the reference metric value can reflect a discrete metric value of high frequency occurrence of surrounding data points of the compression-resistant data point, and in the initial compression-resistant data point set, the kth distance neighborhood is adjusted according to the difference between the corresponding reference metric value and the corresponding discrete metric value of the compression-resistant data point, so as to obtain the adjusted kth distance neighborhood of all compression-resistant data points in the initial compression-resistant data point set. The k-th distance neighborhood after adjustment can more accurately describe the analysis outlier condition reference range of the compression-resistant data points, so that a more accurate outlier data point set can be obtained later.
Preferably, in one embodiment of the present invention, the method for acquiring the preset reference range specifically includes:
According to the surrounding concentration condition of the data points, the k-th distance neighborhood of the data points is adjusted, a reference surrounding range needs to be determined, and in the k-th distance neighborhood of the target compression-resistant data points, the k-th distance neighborhood of all the compression-resistant data points is used as a first reference neighborhood range set;
taking the minimum value of the time corresponding to the k-th distance neighborhood in the first reference neighborhood range set as a first initial reference time;
taking the maximum value of the time corresponding to the k-th distance neighborhood in the first reference neighborhood range set as a first ending reference time;
And taking a time interval formed by the first initial reference time to the first ending reference time as a preset reference range of the target compression-resistant data point. Referring to fig. 2, a schematic diagram of a preset reference range provided by an embodiment of the present invention is shown, a thickened circle is a kth distance neighborhood of a target compression-resistant data point, an un-thickened circle is a kth distance neighborhood in a first reference neighborhood range set, a minimum time corresponding to a leftmost point of the kth distance neighborhood is used as a first initial reference time, and a maximum time corresponding to a rightmost point of the kth distance neighborhood is used as a first ending reference time.
Preferably, in one embodiment of the present invention, the method for obtaining the reference metric value specifically includes:
In order to adjust the kth distance neighborhood of the data point according to the surrounding concentration condition of the data point, the surrounding concentration condition is needed to be analyzed, a dispersion value is used as a horizontal axis, the number of the compression-resistant data points is used as a vertical axis, and a two-dimensional reference coordinate system is constructed;
Mapping all the compression-resistant data points into a two-dimensional reference coordinate system in a preset reference range of an initial compression-resistant data point set to obtain each mapping point, and performing curve fitting on the mapping points to obtain a fitting curve to be processed of the target compression-resistant data points; and acquiring all peak points in the fitting curve to be processed based on an AMPD (Automatic Multiscale Peak Detection automatic multiscale peak detection) algorithm, and taking a dispersion metric value corresponding to the peak points as a reference metric value of the target compression-resistant data points. The reference metric reflects the high frequency of occurrence of discrete metrics around the data point, reflecting the concentration around the data point. It should be noted that, the AMPD algorithm is a technical means well known to those skilled in the art, and will not be described herein.
Preferably, in one embodiment of the present invention, the method for acquiring the adjusted kth distance neighborhood includes:
In order to make the range of the kth distance neighborhood more reasonable, according to the kth Concentration around the compressive data points versus the/>The k-th distance neighborhood of each compression-resistant data point is adjusted to obtain/>The number of compression-resistant data points corresponds to the adjusted kth distance neighborhood. The adjusted kth distance neighborhood formula in one embodiment of the invention comprises:
; wherein/> For/>The compression-resistant data points correspond to the adjusted kth distance neighborhood; /(I)For/>The compressive data points correspond to discrete metric values; /(I)For/>The compression-resistant data points correspond to the/>A plurality of reference metric values; /(I)For/>The compression-resistant data points correspond to the total number of reference measurement values; /(I)For/>A kth distance neighborhood corresponding to the compressive data point; /(I)Is an upward rounding function; /(I)Is a normalization function.
In the adjusted kth distance neighborhood formula,Reflecting the/>The difference between the discrete metric values of the compressive data points and the reference metric value is the/>The dispersion metric of each compression-resistant data point is larger than the reference metric, and the/>The compression-resistant data points are smaller than the surrounding discrete degree, which means that the current data points are in a discrete distribution interval, and the k-th distance neighborhood after adjustment is larger; first/>The dispersion metric of each compression-resistant data point is smaller than the reference metric, and the/>The compression-resistant data points are larger than the surrounding discrete degree, which indicates that the current data points are in a more concentrated distribution interval, the k-th distance neighborhood does not need to be adjusted too much, and the adjustment degree of the k-th distance neighborhood after adjustment is smaller; the adjusted k-th distance neighborhood integrates the differences of all reference metric values and corresponding compression-resistant data points to adjust the k-th distance neighborhood so as to ensure that enough neighborhood data points are provided for reference of outlier conditions.
Step S6, acquiring an outlier data point set of the target masonry structure according to the adjusted k-th distance neighborhood of all the compression data points in the initial compression data point set; and acquiring the compressive property curve of the target masonry structure according to the initial compressive data point set and the outlier data point set.
In order to accurately reflect the compressive property of the target masonry structure, the k-th distance neighborhood is adjusted so as to provide enough neighborhood data points for reference of outlier conditions. Acquiring an outlier data point set of the target masonry structure according to the adjusted kth distance neighborhood of all the compression data points in the initial compression data point set; the outlier data point set may reflect data points in the data that are significantly different from other data points, which may represent abnormal behavior, erroneous recordings, or other deviations from the normal data distribution, the effects of which are stripped off, and the compressive property curve of the target masonry structure is obtained from the initial compressive data point set and the outlier data point set. The compressive property curve can more accurately reflect the compressive property of the target masonry structure.
Preferably, in one embodiment of the present invention, the method for acquiring an outlier data point set includes:
It should be noted that, the LOF algorithm is a technical means well known to those skilled in the art, and is not described herein in detail, but only a brief process of acquiring an outlier data point set by using the LOF algorithm in one embodiment of the present invention is described briefly:
Since the size of the k-th distance neighborhood can influence the calculation of outlier factors, in the k-th distance neighborhood after the adjustment of the compression-resistant data points, calculating the average value of the distances according to the distances from the rest compression-resistant data points to the compression-resistant data points, and obtaining local reachable density; and obtaining local outliers of all the compression-resistant data points by the ratio of the local density to the average value of the local density in the adjusted k-th distance neighborhood, wherein the local outliers can measure the degree of abnormality. Marking the compression-resistant data points with the local outlier factors larger than a preset outlier threshold as outlier data points; and counting all the outlier data points, and acquiring an outlier data point set. The outlier data point set can reflect data points deviating from normal data distribution so as to be used for stripping data in the outlier data point set subsequently, and further accurately reflect the compression resistance of the target masonry structure. In one embodiment of the present invention, the preset outlier threshold is 2, and the implementer can set itself according to the implementation scenario.
Preferably, in one embodiment of the present invention, the method for acquiring the compression resistance curve includes:
In order to accurately reflect the compressive property of the target masonry structure, since the discrete data may represent abnormal behavior, erroneous recordings or other conditions deviating from normal data distribution, the discrete data needs to be stripped, and the corresponding compressive data points in the outlier data point set are removed from the initial compressive data point set, so as to obtain remaining compressive data points; and the data reliability of the residual compression-resistant data points is high, and the residual compression-resistant data points are subjected to curve fitting to obtain the compression-resistant performance curve of the target masonry structure. The compression resistance curve can more accurately reflect the fusion data of the target masonry structure, and the corresponding compression resistance curve is output to the visual equipment of the manager through the visual display equipment, so that the research and development personnel can analyze the compression resistance parameters of the target masonry structure to adjust the structural proportion.
The invention also provides masonry structure compressive property detection equipment, which comprises a processor, wherein the processor is used for running corresponding computer programs, and the masonry structure compressive property detection method described in the steps S1-S6 can be realized when the computer programs run in the processor.
In summary, the embodiment of the invention obtains the dispersion metric values of all compression-resistant data points in the initial compression-resistant data point set according to the size difference and the instability metric value difference of the k-th distance neighborhood between the compression-resistant data points by obtaining the sample compression-resistant time number of the target masonry structure; according to the difference between the corresponding reference measurement value and the corresponding discrete measurement value of the compression-resistant data points, the k-th distance neighborhood is adjusted, and the adjusted k-th distance neighborhood of all compression-resistant data points in the initial compression-resistant data point set is obtained; and further acquiring an outlier data point set of the target masonry structure, and finally acquiring the compression resistance curve of the target masonry structure. According to the method, the k-th distance neighborhood is adjusted by combining the data point distribution condition and the data fluctuation condition, the adjusted k-th distance neighborhood which more reasonably reflects the reference range of the outlier condition is obtained, outlier abnormal data can be accurately screened out, and the accuracy of the compressive property of the masonry structure is improved.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
Claims (10)
1. The method for detecting the compressive property of the masonry structure is characterized by comprising the following steps of:
acquiring sample compression-resistant time sequence data of a target masonry structure;
according to the difference of all the sample compression-resistant time sequence data at the same time, obtaining an instability measurement value corresponding to each time of the target masonry structure;
constructing an initial compression-resistant data point set of the target masonry structure according to all the sample compression-resistant time sequence data, and acquiring a kth distance neighborhood of all compression-resistant data points in the initial compression-resistant data point set;
acquiring dispersion metric values of all compression-resistant data points in an initial compression-resistant data point set according to the size difference and the instability metric value difference of the kth distance neighborhood between the compression-resistant data points; acquiring reference metric values of all compression-resistant data points according to the dispersion metric values of the compression-resistant data points in a preset reference range;
According to the difference between the reference measurement value and the dispersion measurement value corresponding to the compression-resistant data point, the k-distance neighborhood is adjusted, and the adjusted k-distance neighborhood of all compression-resistant data points in an initial compression-resistant data point set is obtained;
Acquiring an outlier data point set of the target masonry structure according to the adjusted kth distance neighborhood of all the compression data points in the initial compression data point set; and acquiring the compressive property curve of the target masonry structure according to the initial compressive data point set and the outlier data point set.
2. The method for detecting compressive property of a masonry structure according to claim 1, wherein the obtaining formula of the instability metric value is:
; wherein/> For/>The instability measurement values corresponding to the moments; /(I)For/>The time corresponds to the number of all masonry samples; /(I)For initial time to the/>The time period between moments; /(I)For/>Each masonry sample corresponds to the sample compression time sequence data in the/>A time-of-day compression resistance value; /(I)For/>The sample compression resistant time series data of individual masonry samples are in a time period/>The average value of all compression resistance values; /(I)For/>Each masonry sample corresponds to the sample compression-resistant time sequence data in a time period/>Standard deviation of all compression resistance values in (2); /(I)Is a parameter adjusting factor of denominator.
3. The masonry structure compressive property testing method of claim 1, wherein the initial set of compressive data points acquisition method comprises:
taking time as a horizontal axis of the two-dimensional data space, and taking the compression resistance value as a vertical axis of the two-dimensional data space; mapping all compression values in all the sample compression time sequence data to a two-dimensional data space to obtain compression data points, and taking a set formed by all the compression data points as an initial compression data point set of the target masonry structure.
4. The method for detecting compressive property of a masonry structure according to claim 1, wherein the method for obtaining the dispersion metric value comprises:
Normalizing the k-th distance neighborhood radius of the target compression-resistant data point to obtain a neighborhood characteristic value of the target compression-resistant data point;
Taking the compression-resistant data point in the kth distance neighborhood of the target compression-resistant data point as a reference data point of the target compression-resistant data point;
Calculating the instability measurement value difference between the target compression-resistant data point and the reference data point, and obtaining a first instability difference value of the reference data point;
normalizing the accumulated values of the first unstable difference values of all the reference data points to obtain a second unstable difference value of the target compression-resistant data point;
acquiring the dispersion metric value of the target compression-resistant data point according to the neighborhood characteristic value and the second unstable difference value; the neighborhood characteristic value and the dispersion metric value are in positive correlation, and the second unstable difference value and the dispersion metric value are in positive correlation.
5. The method for detecting the compressive property of a masonry structure according to claim 1, wherein the method for obtaining the reference metric value comprises the following steps:
constructing a two-dimensional reference coordinate system by taking a dispersion measurement value as a horizontal axis and the number of compression-resistant data points as a vertical axis;
Mapping all compression-resistant data points into the two-dimensional reference coordinate system in a preset reference range of the initial compression-resistant data point set to obtain each mapping point, and performing curve fitting on the mapping points to obtain a fitting curve to be processed of target compression-resistant data points;
And acquiring all peak points in the fitting curve to be processed based on an AMPD algorithm, and taking a discrete metric value corresponding to the peak points as the reference metric value of the target compression-resistant data point.
6. The method for detecting compressive property of masonry structure according to claim 1, wherein the adjusted k-th distance neighborhood is obtained by the formula:
; wherein/> For/>A plurality of compression-resistant data points correspond to the adjusted kth distance neighborhood; /(I)For/>The plurality of compression-resistant data points correspond to the discrete metric values; /(I)For/>The compression-resistant data points correspond to the/>A plurality of reference metric values; /(I)For/>The compression-resistant data points correspond to the total number of reference measurement values; /(I)For/>A kth distance neighborhood corresponding to the compressive data point; /(I)Is an upward rounding function; /(I)Is a normalization function.
7. The method for detecting compressive property of a masonry structure according to claim 1, wherein the method for acquiring the outlier data point set comprises:
Obtaining local outliers of all the compression-resistant data points according to the adjusted k-th distance neighborhood of all the compression-resistant data points in the initial compression-resistant data point set based on an LOF algorithm;
Marking the compression-resistant data points with the local outlier factors larger than a preset outlier threshold as outlier data points;
and counting all the outlier data points, and acquiring the outlier data point set.
8. The method for detecting the compressive property of a masonry structure according to claim 1, wherein the method for obtaining the compressive property curve comprises:
Removing corresponding compression-resistant data points in the outlier data point set from the initial compression-resistant data point set, and obtaining residual compression-resistant data points;
And performing curve fitting on the residual compression-resistant data points to obtain a compression-resistant performance curve of the target masonry structure.
9. The method for detecting the compressive property of a masonry structure according to claim 1, wherein the method for obtaining the preset reference range comprises:
In the kth distance neighborhood of the target compression-resistant data point, taking the kth distance neighborhood of all compression-resistant data points as a first reference neighborhood range set;
taking the minimum value of the time corresponding to the k-th distance neighborhood in the first reference neighborhood range set as a first initial reference time;
taking the maximum value of the time corresponding to the k-th distance neighborhood in the first reference neighborhood range set as a first ending reference time;
and taking a time interval formed by the first initial reference time to the first ending reference time as a preset reference range of the target compression-resistant data point.
10. A masonry structure compression resistance detection device comprising a processor, said processor executing a computer program to perform the steps of a masonry structure compression resistance detection method according to any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410409299.XA CN118013636B (en) | 2024-04-07 | 2024-04-07 | Masonry structure compressive property detection equipment and detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410409299.XA CN118013636B (en) | 2024-04-07 | 2024-04-07 | Masonry structure compressive property detection equipment and detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118013636A true CN118013636A (en) | 2024-05-10 |
| CN118013636B CN118013636B (en) | 2024-06-18 |
Family
ID=90956738
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410409299.XA Active CN118013636B (en) | 2024-04-07 | 2024-04-07 | Masonry structure compressive property detection equipment and detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118013636B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118858977A (en) * | 2024-09-26 | 2024-10-29 | 洛阳微栎科技有限公司 | A distributed charging pile energy storage battery intelligent testing method and system |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB544612A (en) * | 1939-04-01 | 1942-04-21 | Financ De Transp S Et D Entpr | Improvement in processes of manufacturing agglomerates from a coal base utilised as the only binder |
| US7346736B1 (en) * | 2004-12-13 | 2008-03-18 | Sun Microsystems, Inc. | Selecting basis functions to form a regression model for cache performance |
| CN109934354A (en) * | 2019-03-12 | 2019-06-25 | 北京信息科技大学 | An abnormal data detection method based on active learning |
| CN112257722A (en) * | 2020-11-11 | 2021-01-22 | 南京工业大学 | Point cloud fitting method based on robust nonlinear Gaussian-Hummer model |
| WO2023004595A1 (en) * | 2021-07-27 | 2023-02-02 | 中国科学院深圳先进技术研究院 | Parking data recovery method and apparatus, and computer device and storage medium |
| CN116108339A (en) * | 2023-02-21 | 2023-05-12 | 大连理工大学 | Actual measurement data outlier detection and correction method for tunnel boring machine |
| CN116975958A (en) * | 2023-06-26 | 2023-10-31 | 中国建筑第五工程局有限公司 | Method for evaluating earthquake-resistant safety of town masonry structure based on Cokriging multi-fidelity substitution model |
| CN117171695A (en) * | 2023-11-02 | 2023-12-05 | 北京建工环境修复股份有限公司 | Method and system for evaluating ecological restoration effect of antibiotic contaminated soil |
| CN117274240A (en) * | 2023-11-17 | 2023-12-22 | 资阳建工建筑有限公司 | Bearing platform foundation concrete surface crack identification method |
| US11852771B1 (en) * | 2022-08-02 | 2023-12-26 | Institute Of Geology And Geophysics, Chinese Academy Of Sciences | Method and system for optimally selecting carbon storage site based on multi-frequency band seismic data and equipment |
| CN117349781A (en) * | 2023-12-06 | 2024-01-05 | 东莞市郡嘉电子科技有限公司 | Intelligent diagnosis method and system for faults of transformer |
| CN117451493A (en) * | 2023-09-04 | 2024-01-26 | 辽宁省建设科学研究院有限责任公司 | Method for detecting strength grade of wall sintering common brick |
-
2024
- 2024-04-07 CN CN202410409299.XA patent/CN118013636B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB544612A (en) * | 1939-04-01 | 1942-04-21 | Financ De Transp S Et D Entpr | Improvement in processes of manufacturing agglomerates from a coal base utilised as the only binder |
| US7346736B1 (en) * | 2004-12-13 | 2008-03-18 | Sun Microsystems, Inc. | Selecting basis functions to form a regression model for cache performance |
| CN109934354A (en) * | 2019-03-12 | 2019-06-25 | 北京信息科技大学 | An abnormal data detection method based on active learning |
| CN112257722A (en) * | 2020-11-11 | 2021-01-22 | 南京工业大学 | Point cloud fitting method based on robust nonlinear Gaussian-Hummer model |
| WO2023004595A1 (en) * | 2021-07-27 | 2023-02-02 | 中国科学院深圳先进技术研究院 | Parking data recovery method and apparatus, and computer device and storage medium |
| US11852771B1 (en) * | 2022-08-02 | 2023-12-26 | Institute Of Geology And Geophysics, Chinese Academy Of Sciences | Method and system for optimally selecting carbon storage site based on multi-frequency band seismic data and equipment |
| CN116108339A (en) * | 2023-02-21 | 2023-05-12 | 大连理工大学 | Actual measurement data outlier detection and correction method for tunnel boring machine |
| CN116975958A (en) * | 2023-06-26 | 2023-10-31 | 中国建筑第五工程局有限公司 | Method for evaluating earthquake-resistant safety of town masonry structure based on Cokriging multi-fidelity substitution model |
| CN117451493A (en) * | 2023-09-04 | 2024-01-26 | 辽宁省建设科学研究院有限责任公司 | Method for detecting strength grade of wall sintering common brick |
| CN117171695A (en) * | 2023-11-02 | 2023-12-05 | 北京建工环境修复股份有限公司 | Method and system for evaluating ecological restoration effect of antibiotic contaminated soil |
| CN117274240A (en) * | 2023-11-17 | 2023-12-22 | 资阳建工建筑有限公司 | Bearing platform foundation concrete surface crack identification method |
| CN117349781A (en) * | 2023-12-06 | 2024-01-05 | 东莞市郡嘉电子科技有限公司 | Intelligent diagnosis method and system for faults of transformer |
Non-Patent Citations (7)
| Title |
|---|
| XU, XUEFANG等: "An Incorrect Data Detection Method for Big Data Cleaning of Machinery Condition Monitoring", IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 31 March 2020 (2020-03-31) * |
| ZHOU, LEI等: "A new online quality monitoring method of chain resistance upset butt welding based on Isolation Forest and Local Outlier Factor", JOURNAL OF MANUFACTURING PROCESSES, 31 August 2021 (2021-08-31) * |
| 周鹏;程艳云;: "一种改进的LOF异常点检测算法", 计算机技术与发展, no. 12, 27 September 2017 (2017-09-27) * |
| 常鸿雁;: "建筑工程检测过程中数据处理的分析与探讨", 山西建筑, no. 20, 10 July 2018 (2018-07-10) * |
| 杨娜等: "基于局部离群因子的数据异常识别方法及其在古建结构监测中的应用", 建筑结构学报, 31 December 2022 (2022-12-31) * |
| 缑鹏飞等: "基于自适应邻居图的离群点检测方法", 计算机应用研究, 31 December 2023 (2023-12-31) * |
| 陈则黄等: "基于集成算法和普通机器学习算法的岩爆分级预测及选择", 有色金属(矿山部分), 31 December 2023 (2023-12-31) * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118858977A (en) * | 2024-09-26 | 2024-10-29 | 洛阳微栎科技有限公司 | A distributed charging pile energy storage battery intelligent testing method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118013636B (en) | 2024-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220381744A1 (en) | Method for determining whole macro-micro process of rock deformation and failure based on four-parameter test | |
| CN118013636B (en) | Masonry structure compressive property detection equipment and detection method | |
| CN109374870B (en) | Method and device for evaluating repairing performance of cement-based self-repairing material | |
| CN118464810B (en) | Archaeological environment detection method and system based on spectral component analysis | |
| CN118332919A (en) | Building curtain wall engineering detection method | |
| CN116609255B (en) | Weather resistance testing method and system for building paint | |
| WO2023072086A1 (en) | Workpiece end face attitude assessment method | |
| CN111141472B (en) | Anti-seismic support and hanger detection method and system | |
| CN119197362A (en) | A method and device for monitoring deformation of a structure based on a laser measuring device | |
| CN116298765A (en) | High-temperature high-humidity reverse bias test system | |
| CN110333506B (en) | Method for extracting inhaul cable position parameters of cable force measurement radar | |
| CN118010753B (en) | Scaffold plate buckle quality defect detection method based on water glass casting process | |
| CN118549632A (en) | Concrete structure defect monitoring system and method based on piezoelectric intelligent aggregate | |
| CN109709060B (en) | Method for measuring asphalt softening point, penetration degree and mass loss | |
| CN117491608A (en) | Self-compaction core column construction concrete detection system based on data analysis | |
| CN104278990B (en) | Log data quality restoration methods and device | |
| CN117232644A (en) | Transformer sound monitoring fault diagnosis method and system based on acoustic principle | |
| CN118758233B (en) | Concrete crack detection methods in high-rise buildings | |
| CN110455922B (en) | K-nearest neighbor method-based anchor rod anchoring quality grade evaluation method | |
| CN117571164B (en) | Automatic collection system of multi-functional concrete sample surface stress | |
| CN119044336B (en) | Method and system for detecting compressive strength of concrete for constructional engineering | |
| CN117420011B (en) | Concrete brick multipoint compressive strength detection system | |
| CN119397331A (en) | A method for rapid identification and fine characterization of rock mass structural planes | |
| CN114737621A (en) | Nondestructive foundation pile detection method based on outer cross hole of pile | |
| CN119334951A (en) | A high wall glass falling risk detection method and system based on drone |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |