CN113610274B - Subway construction long-term monitoring abnormal information mining method based on correlation - Google Patents
Subway construction long-term monitoring abnormal information mining method based on correlation Download PDFInfo
- Publication number
- CN113610274B CN113610274B CN202110768010.XA CN202110768010A CN113610274B CN 113610274 B CN113610274 B CN 113610274B CN 202110768010 A CN202110768010 A CN 202110768010A CN 113610274 B CN113610274 B CN 113610274B
- Authority
- CN
- China
- Prior art keywords
- data
- correlation
- monitoring
- depth
- diaphragm wall
- 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.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 115
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 67
- 238000010276 construction Methods 0.000 title claims abstract description 41
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000005065 mining Methods 0.000 title claims abstract description 21
- 230000007774 longterm Effects 0.000 title claims description 20
- 238000011160 research Methods 0.000 claims abstract description 13
- 238000007418 data mining Methods 0.000 claims abstract description 8
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000005856 abnormality Effects 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 claims description 2
- 230000001186 cumulative effect Effects 0.000 description 11
- 238000004590 computer program Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000010835 comparative analysis Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011985 exploratory data analysis Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/283—Multi-dimensional databases or data warehouses, e.g. MOLAP or ROLAP
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2216/00—Indexing scheme relating to additional aspects of information retrieval not explicitly covered by G06F16/00 and subgroups
- G06F2216/03—Data mining
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention provides a subway construction long-time monitoring abnormal information mining method based on a correlation, which comprises the steps of collecting construction site monitoring data and establishing a data warehouse; selecting data aiming at the data warehouse, and determining the accumulated deformation data of the underground diaphragm wall as a research object; calculating correlation coefficients of accumulated deformation of the underground diaphragm wall at different depths of the same measuring point, determining an empirical reference threshold of the correlation coefficients, comparing the correlation coefficients of the underground diaphragm wall at each depth with the empirical reference threshold, and searching and judging abnormal data in monitoring data of the underground diaphragm wall at each depth; dividing time windows of underground diaphragm wall monitoring periods at a certain depth, calculating correlation coefficients of accumulated deformation of the underground diaphragm wall under each time window, and positioning abnormal data; based on the abnormal data positioned at each depth, a data mining result of long-time monitoring abnormal information based on a correlation is obtained, and early warning is carried out on actual engineering risks.
Description
Technical Field
The invention relates to the field of subway construction monitoring and processing, in particular to a method for mining long-term monitoring abnormal information of subway construction based on correlation.
Background
The subway engineering construction faces various geological hydrologic conditions, needs to pass through a large number of sensitive urban construction facilities and life line systems in the city, has high uncertainty of existing underground and overground structures under the action of complex environments, belongs to high-risk production activities at home and abroad, has outstanding engineering construction risks, and is easy to bring serious economic loss, bad social influence and even casualties.
CN112982503a provides a subway foundation pit construction monitoring system, method, equipment and storage medium based, and the relevant data of the construction site is collected through various sensors, but the corresponding effective data processing means are lacked.
CN112069225a provides a data mining method for correlation of multi-source heterogeneous monitoring data in subway construction, which establishes a data mining target and determines a multi-source heterogeneous monitoring data sample set, calculates an average value of the correlation, and thereby determines correlation between the multi-source heterogeneous monitoring data. The theory of this method is to be further investigated.
The data mining is applied to the industrial field at the earliest and is widely applied to fault diagnosis and accurate position positioning in a standard industrial process, and the main steps are data acquisition, data analysis, data application and data feedback, wherein the data application is the most critical, and by analyzing data, the reasons behind the data are subjected to exploratory analysis or hypothesis verification analysis, so that a certain correlation among the data is found. However, the research on abnormal data in the deformation data of the underground continuous wall lacks quantitative basis, and a mature method is not available, so that difficulties are brought to further prediction and control of engineering risks.
Therefore, it is necessary to develop a method for mining information based on long-term monitoring abnormality, which can make full use of the correlation to realize abnormality prediction.
The information disclosed in the background section of the invention is only for enhancement of understanding of the general background of the invention and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person skilled in the art.
Disclosure of Invention
The invention provides a long-time monitoring abnormal information mining method based on a correlation, which can start from actual monitoring data, combine the correlation and improve, and automatically position the space position and the time position of abnormal data.
The technical scheme of the invention provides a subway construction long-term monitoring abnormal information mining method based on a correlation, which comprises the following steps:
1) Collecting construction site monitoring data and establishing a data warehouse;
2) Selecting data aiming at the data warehouse, and determining the accumulated deformation data of the underground diaphragm wall as a research object;
3) Calculating correlation coefficients of accumulated deformation of the underground diaphragm wall at different depths of the same measuring point, determining an empirical reference threshold of the correlation coefficients, comparing the correlation coefficients of the underground diaphragm wall at each depth with the empirical reference threshold, and searching and judging abnormal data in monitoring data of the underground diaphragm wall at each depth;
4) Dividing time windows of the underground diaphragm wall monitoring period at a certain depth according to the judging result of the step 3), calculating the correlation coefficient of the accumulated deformation of the underground diaphragm wall under each time window, and positioning abnormal data;
5) Based on the abnormal data positioned at each depth, a data mining result of long-time monitoring abnormal information based on a correlation is obtained, and early warning is carried out on actual engineering risks.
Moreover, the data warehouse is a collection of job site monitoring data.
And the underground continuous wall deformation data acquisition mode is that a plurality of groups of underground continuous wall monitoring points are arranged along the periphery of the foundation pit, and each monitoring point is provided with one deformation monitoring point from the top to the bottommost end of the wall at fixed intervals.
And in the step 3), calculating the correlation coefficient of the accumulated deformation of the underground diaphragm wall at different depths of the same measuring point and at a specific depth, and if the correlation coefficient of the accumulated deformation of other depths and the accumulated deformation of the underground diaphragm wall at the specific depth is far smaller than an empirical reference threshold value, pre-judging that abnormal data exists in the accumulated deformation data of the underground diaphragm wall at the depth.
And in the step 4), according to the pre-judging result, dividing the time window of the depth with abnormal data and the monitoring period of the underground continuous wall at two positions of the specific depth, calculating and comparing and analyzing the correlation coefficient under each time window, and positioning the abnormal data.
Moreover, the duration of the dividing time window can be determined according to engineering characteristics.
And the implementation mode of the abnormal data positioning is to judge whether the correlation coefficient of a certain time window is far smaller than the correlation coefficient of other time windows, and if so, the abnormal data is considered to be positioned in the monitoring data of the underground continuous wall in the time window.
Moreover, the pearson correlation coefficient is used for the correlation coefficient calculation.
According to the method, a data warehouse is established based on construction site monitoring to select research objects, correlation coefficients of all monitoring periods among the research objects are calculated, an empirical reference threshold S of the correlation coefficients of all monitoring periods is determined, the spatial position of abnormal data is positioned through comparative analysis, then time windows are divided for all monitoring periods, the correlation coefficients under all the time windows are calculated and analyzed, the empirical reference threshold T of the correlation coefficients of the time windows is determined, the time position of the abnormal data is automatically positioned, and early warning is carried out on actual engineering risks. The method is suitable for simultaneously and automatically monitoring engineering risks of multiple subway construction sites in the city, and has the advantages of high instantaneity and high precision.
The scheme of the invention is simple and convenient to implement, has strong practicability, solves the problems of low practicability and inconvenient practical application existing in the related technology, can improve user experience, and has important market value.
Drawings
Fig. 1 is a flowchart of a data mining method for monitoring anomaly information for a long time based on a correlation in an embodiment of the present invention.
FIG. 2 is a graph of correlation coefficients of CX06 measurement point set-5 m or more depth versus cumulative deformation of the full monitoring period of the underground diaphragm wall at-0.5 m depth according to one embodiment of the invention.
FIG. 3 is a graph of correlation coefficients of CX20 site groups over-5 m depth versus cumulative deformation of the full monitoring period of the underground diaphragm wall at-0.5 m depth in accordance with an embodiment of the invention.
FIG. 4 is a graph of correlation coefficients for various time windows for cumulative changes in underground diaphragm wall at-1.5 m depth and-0.5 m depth for CX20 survey point set according to an embodiment of the invention.
Detailed Description
The technical scheme of the invention is specifically described below with reference to the accompanying drawings and examples.
Referring to fig. 1, the method for mining long-term monitoring abnormal information of subway construction based on correlation provided by the embodiment of the invention may include:
1) Collecting construction site monitoring data and establishing a data warehouse;
in the invention, a data warehouse is a collection of construction site monitoring data.
2) Selecting data aiming at the data warehouse, and determining the accumulated deformation data of the underground diaphragm wall as a research object;
in order to identify abnormal monitoring data of the underground diaphragm wall in subway construction, the data are selected to determine accumulated deformation data of the underground diaphragm wall as a study object. (the method is mainly applied to identifying abnormal monitoring data of the underground continuous wall in subway construction).
In the foundation pit construction process, the construction site monitoring data comprise underground continuous wall deformation data, ground surface subsidence deformation data and peripheral building subsidence deformation data, wherein the underground continuous wall deformation data collection mainly comprises 32 groups of underground continuous wall monitoring points arranged along the periphery of the foundation pit, and each monitoring point is provided with a deformation monitoring point from the top of the wall to the bottommost end at intervals of 0.5 m.
3) Calculating correlation coefficients of accumulated deformation of the underground diaphragm wall at different depths of the same measuring point, determining an empirical reference threshold S of the correlation coefficients of the whole monitoring period, judging whether the correlation coefficients of the underground diaphragm wall at each depth are smaller than the empirical reference threshold, and judging that abnormal data exist in the monitoring data of the underground diaphragm wall at the depth if the correlation coefficients of the underground diaphragm wall at each depth are smaller than the empirical reference threshold.
The correlation coefficient of the step is calculated as monitoring data of all time periods, the spatial position of the abnormal data is judged by comparing the correlation coefficient of the underground continuous wall at each depth with an empirical reference threshold S, the time window is divided in the following step 4) based on the judgment result in 3), the time window division is carried out on the monitoring data of all time periods of the underground continuous wall with the certain depth and judged to be provided with the abnormal data, the correlation coefficients under different time windows are calculated, the empirical reference threshold T of the correlation coefficient of the time window is determined, and the time position of the abnormal data is positioned by comparative analysis.
Preferably, calculating correlation coefficients of accumulated deformation of the underground diaphragm wall at different depths and at the depth of-0.5 m of the same measuring point: an empirical reference threshold S for the full monitoring period correlation coefficient is determined.
In specific implementation, the value of S can be obtained by analyzing according to a correlation coefficient calculation principle and a deformation mechanism, the correlation coefficient calculation value is between-1 and 1, the correlation coefficient is a strong correlation over 0.95, and the empirical reference threshold S is determined by combining a diaphragm wall deformation mechanism (-the strong correlation between a diaphragm wall at 0.5m and a diaphragm wall over-5 m).
In the embodiment, calculating the correlation coefficient of the cumulative deformation of the underground diaphragm wall at the depth of more than-5 m and the depth of-0.5 m of the same measuring point: an empirical reference threshold S for the full monitoring period correlation coefficient is determined.
The empirical reference threshold S for correlation coefficients for full time period monitored data is 0.95.
If the correlation coefficient of the accumulated deformation of the underground diaphragm wall at a certain depth and the depth of-0.5 m is smaller than the empirical reference threshold S, the abnormal data in the accumulated deformation data of the underground diaphragm wall at the depth is judged in advance.
In an embodiment, the calculation method of the correlation coefficient preferably adopts a calculation formula of the pearson correlation coefficient, which is specifically as follows:
in an embodiment, R in the above calculation formula is a correlation coefficient of the full-time monitoring data, and X i Accumulated deformation data of the underground diaphragm wall at the depth of-0.5 m,is X I Average value of Y I Accumulating deformation data (Y) for underground diaphragm wall at other depths I Accumulated deformation data of the underground diaphragm wall at depths of-1 m, -1.5m, -2m, -2.5m, -3m, -3.5m, -4m, -4.5m and-5 m respectively, < >>Is Y I Is 1, 2, 3, 4 … N, N is X I Or Y I Number of data, X I And Y is equal to I Equal in number of data).
4) And according to the judging result, dividing time windows of the underground diaphragm wall monitoring period at a certain depth, calculating the correlation coefficient of the accumulated deformation of the underground diaphragm wall under each time window to determine the empirical reference threshold T of the correlation coefficient of the time window, comparing and analyzing, positioning the time position of abnormal data, and realizing actual engineering risk early warning.
The correlation coefficient calculation method in the step is the same as that in the step 3), and is the pearson correlation coefficient calculation formula, the correlation coefficient of the 3 rd time window of the CX20 measuring point group is the correlation coefficient r between monitoring data of the ground connection wall with the depth of-0.5 m and-1.5 m in the 21 st day to the 30 th day of the monitoring period, and the specific calculation formula is as follows:
x i monitoring data at-0.5 m depth from day 21 to day 30 of the monitoring period, +.>Is x i Average value of y i Monitoring data of-1.5 m depth underground continuous wall from 21 st day to 30 th day of monitoring period,/day>Is y i N=10, and the value of n in step 4 varies with the time period set by the user.
In the embodiment, according to the pre-judging result, dividing a time window of a certain depth and a monitoring period of the underground continuous wall at the position of-0.5 m, calculating and comparing and analyzing the correlation coefficient under each time window, determining an empirical reference threshold T of the correlation coefficient of the time window, comparing and analyzing, and positioning the time position of abnormal data.
In an embodiment, the time length for dividing the time window is preferably set to 10 days, and the specific implementation time length can be set by the user. In an embodiment, the correlation coefficient empirical reference threshold T for the time window is 0.75.
In the implementation, according to the pre-judging result of the strong correlation in the step 3, the strong correlation is similar in the change trend of the two deep ground continuous walls, so that after the time windows are divided, the correlation coefficient of each time window is larger than the experience reference threshold T.
In an embodiment, the positioning abnormal data is specifically implemented as: whether the correlation coefficient of a certain time window is smaller than the empirical reference threshold T of the correlation coefficient of the time window, if so, the abnormal data are located in the monitoring data of the underground diaphragm wall in the time window.
In order to facilitate understanding of the solution and the effects of the embodiments of the present invention, a specific application example is given below. It will be understood by those of ordinary skill in the art that the examples are for ease of understanding only and that any particular details thereof are not intended to limit the present invention in any way.
Collecting construction site monitoring data and establishing a data warehouse;
selecting data aiming at the data warehouse, and determining the accumulated deformation data of the underground diaphragm wall as a research object;
calculating the correlation coefficient of the accumulated deformation of the underground diaphragm wall at the depth of more than-5 m and the depth of-0.5 m of the same measuring point, determining an empirical reference threshold S of the correlation coefficient in the full monitoring period, comparing whether the correlation coefficient of the underground diaphragm wall at each depth is smaller than the empirical reference threshold S of the correlation coefficient in the full monitoring period, if so, judging that abnormal data exists in the monitoring data of the underground diaphragm wall at the depth, namely determining the spatial positioning of the abnormal data;
and according to the judging result, dividing time windows of the underground diaphragm wall in the full monitoring period at a certain depth, calculating the correlation coefficient of the accumulated deformation of the underground diaphragm wall under each time window, determining the empirical reference threshold T of the correlation coefficient of the time window, and comparing and analyzing the empirical reference threshold T to determine the time positioning of the abnormal data.
FIG. 2 is a graph of correlation coefficients of CX06 measurement point set-5 m or more depth versus cumulative deformation of the full monitoring period of the underground diaphragm wall at-0.5 m depth according to one embodiment of the invention.
In the correlation coefficient graph of the CX06 measurement point group, as shown in FIG. 2, the correlation coefficients of the cumulative deformation of the underground diaphragm wall at-1 m, -1.5m, -2m, -2.5m, -3m, -3.5m, -4m, -4.5m and the underground diaphragm wall at-0.5 m are respectively 0.999, 0.998, 0.996, 0.995 and 0.990 with the minimum monitoring depth of 0.5m as an interval, the correlation coefficient experience reference threshold S of the whole period is 0.950, the correlation coefficients are all larger than 0.95, and if no large fluctuation occurs, the monitoring data of the underground diaphragm wall between-1 m and-5 m is judged that no abnormal data occurs.
FIG. 3 is a graph of correlation coefficients of CX20 site groups over-5 m depth versus cumulative deformation of the full monitoring period of the underground diaphragm wall at-0.5 m depth in accordance with an embodiment of the invention.
As shown in FIG. 3, in the correlation coefficient graph of the CX20 measurement point group, with the minimum monitoring depth of 0.5m as an interval, -1m, -1.5m, -2m, -2.5m, -3m, -3.5m, -4m, -4.5m, -5m, the correlation coefficients of the cumulative deformation of the underground diaphragm wall at-0.5 m depth and the accumulated deformation of the underground diaphragm wall at-1.5 m depth are respectively 0.999, 0.882, 0.999, 0.998, 0.994, 0.991, 0.980 and 0.968, the correlation coefficient empirical reference threshold S of the whole period is 0.950, the second correlation coefficient is smaller than 0.950, and the abnormal data of the monitoring data of the underground diaphragm wall at-1.5 m depth is pre-determined.
FIG. 4 is a graph of correlation coefficients for various time windows for cumulative changes in underground diaphragm wall at-1.5 m depth and-0.5 m depth for CX20 survey point set according to an embodiment of the invention.
As shown in fig. 4, the effective monitoring period of the CX20 measuring point group is 120 days, the monitoring period is divided by 10 as a time window, the 1 st to 10 th days are time windows, and so on, to obtain 12 time windows altogether, the correlation coefficient of the cumulative change of the underground continuous wall at-1.5 m depth and the underground continuous wall at-0.5 m depth in each time window is respectively 0.917, 0.997, 0.945, 0.800, 0.993, 0.956, 1.000, 0.997, 0.121, 1.000, the correlation coefficient empirical reference threshold T of the time window is 0.750, the correlation coefficient of the 11 th time window is less than 0.75, then it is judged that abnormal data exists in the 11 th time window (i.e. within the 100 th to 110 th days of the monitoring period), the cumulative deformation values of the underground continuous wall at-109 th, 110 th and 11 th days are respectively-21.98 mm, 21.61-22.06 mm, thus the abnormal data can be judged to exist on the two days of the two days before and 110 mm, and the abnormal data can be judged on the two days of the day of the monitoring data.
In summary, the method of establishing a data warehouse to select research objects and applying a correlation relationship is adopted to calculate correlation coefficients of all monitoring periods among the research objects, determine an empirical reference threshold S of the correlation coefficients of all monitoring periods, compare and analyze, locate space positions of abnormal data, divide time windows for all monitoring periods, calculate and analyze the magnitudes of the correlation coefficients under each time window, determine an empirical reference threshold T of the correlation coefficients of the time windows, and locate time positions of the abnormal data.
For ease of reference, the effects now provided are exemplified as follows:
the following table is a correlation coefficient matrix of the full monitoring period above-5 m depth of the CX22 underground continuous wall measuring point group in the engineering example, and the correlation coefficient matrix is compared with a correlation coefficient experience reference threshold value of the full monitoring period to judge that abnormal data exists in the monitoring data at the-1.5 m depth.
In particular, the method according to the technical solution of the present invention may be implemented by those skilled in the art using computer software technology to implement an automatic operation flow, and a system apparatus for implementing the method, such as a computer readable storage medium storing a corresponding computer program according to the technical solution of the present invention, and a computer device including the operation of the corresponding computer program, should also fall within the protection scope of the present invention.
In some possible embodiments, a system for mining information of long-term monitoring anomalies in subway construction based on correlation is provided, which comprises the following modules,
the first module is used for collecting construction site monitoring data and establishing a data warehouse;
the second module is used for selecting data aiming at the data warehouse and determining the accumulated deformation data of the underground diaphragm wall as a research object;
the third module is used for calculating correlation coefficients of accumulated deformation of the underground diaphragm wall at different depths of the same measuring point, determining an empirical reference threshold of the correlation coefficients, comparing the correlation coefficients of the underground diaphragm wall at each depth with the empirical reference threshold, and searching and judging abnormal data in monitoring data of the underground diaphragm wall at each depth;
a fourth module, configured to divide time windows of the monitoring period of the underground diaphragm wall at a certain depth according to the determination result of the third module, calculate correlation coefficients of accumulated deformation of the underground diaphragm wall under each time window, and locate abnormal data;
and a fifth module, configured to obtain a data mining result of long-term monitoring anomaly information based on a correlation based on anomaly data located at each depth, and perform early warning on actual engineering risk.
In some possible embodiments, a metro construction long-term monitoring abnormal information mining system based on a correlation is provided, which comprises a processor and a memory, wherein the memory is used for storing program instructions, and the processor is used for calling the stored instructions in the memory to execute a metro construction long-term monitoring abnormal information mining method based on the correlation.
In some possible embodiments, a metro construction long-term monitoring abnormal information mining system based on a correlation is provided, which comprises a readable storage medium, wherein a computer program is stored on the readable storage medium, and the computer program realizes the metro construction long-term monitoring abnormal information mining method based on the correlation when being executed.
The specific embodiments described herein are offered by way of example only to illustrate the spirit of the invention. Those skilled in the art may make various modifications or additions to the described embodiments or substitutions thereof without departing from the spirit of the invention or exceeding the scope of the invention as defined in the accompanying claims.
Claims (8)
1. A subway construction long-term monitoring abnormal information mining method based on correlation is characterized in that a data warehouse is established based on construction site monitoring to select research objects, correlation relations are utilized, correlation coefficients of all monitoring periods among the research objects are calculated, an empirical reference threshold S of the correlation coefficients of all monitoring periods is determined, comparison analysis is performed, the space position of abnormal data is positioned, time windows are divided for all monitoring periods, the magnitude of the correlation coefficients under each time window is calculated and analyzed, the empirical reference threshold T of the correlation coefficients of the time windows is determined, the time position of the abnormal data is automatically positioned, early warning is performed on actual engineering risks, and the method is used for simultaneously and automatically monitoring engineering risks of subway construction sites in multiple cities, and comprises the following steps:
1) Collecting construction site monitoring data and establishing a data warehouse;
2) Selecting data aiming at the data warehouse, and determining the accumulated deformation data of the underground diaphragm wall as a research object;
3) Calculating correlation coefficients of accumulated deformation of the underground diaphragm wall at different depths of the same measuring point, determining an empirical reference threshold of the correlation coefficients, comparing the correlation coefficients of the underground diaphragm wall at each depth with the empirical reference threshold, searching and judging abnormal data in monitoring data of the underground diaphragm wall at each depth, and judging the spatial position of the abnormal data;
4) According to the judging result of the step 3), dividing a time window of the underground diaphragm wall monitoring period at a certain depth with abnormal data, calculating correlation coefficients of accumulated deformation of the underground diaphragm wall under different time windows, determining an empirical reference threshold T of the correlation coefficients of the time windows, comparing and analyzing, and positioning the time position of the abnormal data; the positioning mode is that according to the pre-judging result of the strong correlation in the step 3), the strong correlation is similar in the change trend of the two deep underground continuous walls, after the time windows are divided, the correlation coefficient of each time window is larger than an empirical reference threshold T, whether the correlation coefficient of a certain time window is smaller than the empirical reference threshold T of the correlation coefficient of the time window is judged, and if the correlation coefficient of the certain time window is smaller than the empirical reference threshold T, the abnormal data are regarded as being located in the monitoring data of the underground continuous walls in the time window;
5) Based on the abnormal data positioned at each depth, a data mining result of long-time monitoring abnormal information based on a correlation is obtained, and early warning is carried out on actual engineering risks.
2. The method for mining long-term monitoring anomaly information of subway construction based on correlation as set forth in claim 1, wherein: the data warehouse is a collection of job site monitoring data.
3. The method for mining long-term monitoring anomaly information of subway construction based on correlation as set forth in claim 2, wherein: the underground continuous wall deformation data acquisition mode is that a plurality of groups of underground continuous wall monitoring points are arranged along the periphery of a foundation pit, and each monitoring point is provided with a deformation monitoring point from the top of the wall to the bottommost end at fixed intervals.
4. The method for mining long-term monitoring anomaly information of subway construction based on correlation as set forth in claim 1, wherein: in the step 3), calculating correlation coefficients of the accumulated deformation of the underground diaphragm wall at different depths of the same measuring point and a certain specific depth, and if the correlation coefficients of the accumulated deformation of the underground diaphragm wall at other depths and the specific depth are far smaller than an empirical reference threshold value, pre-judging that abnormal data exists in the accumulated deformation data of the underground diaphragm wall at the depth; calculating the correlation coefficient of the accumulated deformation of the underground diaphragm wall at the depth of more than-5 m and the depth of-0.5 m of the same measuring point: an empirical reference threshold S for the full monitoring period correlation coefficient is determined.
5. The method for mining long-term monitoring anomaly information of subway construction based on correlation as set forth in claim 4, wherein: and 4) according to the pre-judging result, dividing time windows of the depth with the abnormal data and the underground continuous wall monitoring period at two positions of the specific depth, calculating and comparing and analyzing the correlation coefficient under each time window, and positioning the abnormal data.
6. The method for mining long-term monitoring anomaly information of subway construction based on correlation as set forth in claim 5, wherein: the time length for dividing the time window is determined according to engineering characteristics.
7. The method for mining long-term monitoring anomaly information of subway construction based on correlation as set forth in claim 5, wherein: the implementation mode of the abnormal data positioning is to judge whether the correlation coefficient of a certain time window is far smaller than that of other time windows, and if so, the abnormal data is considered to be positioned in the monitoring data of the underground diaphragm wall in the time window.
8. The method for mining long-term monitoring abnormality information of subway construction based on correlation as set forth in claim 1 or 2 or 3 or 4 or 5 or 6 or 7, characterized in that: the correlation coefficient calculation uses pearson correlation coefficients.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110768010.XA CN113610274B (en) | 2021-07-07 | 2021-07-07 | Subway construction long-term monitoring abnormal information mining method based on correlation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110768010.XA CN113610274B (en) | 2021-07-07 | 2021-07-07 | Subway construction long-term monitoring abnormal information mining method based on correlation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113610274A CN113610274A (en) | 2021-11-05 |
| CN113610274B true CN113610274B (en) | 2024-04-05 |
Family
ID=78304090
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110768010.XA Active CN113610274B (en) | 2021-07-07 | 2021-07-07 | Subway construction long-term monitoring abnormal information mining method based on correlation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113610274B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114897421B (en) * | 2022-06-06 | 2023-02-10 | 深圳大学 | Method, system and storage medium for deep foundation pit excavation and construction safety early warning |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107450426A (en) * | 2017-08-01 | 2017-12-08 | 中国建筑第八工程局有限公司 | Foundation pit construction deformable statistical analysis method and system |
| CN112069225A (en) * | 2020-07-31 | 2020-12-11 | 武汉轻工大学 | Data mining method for correlation relation of multisource heterogeneous monitoring data in subway construction |
| CN112697062A (en) * | 2021-01-26 | 2021-04-23 | 湖南北斗微芯数据科技有限公司 | Railway roadbed deformation monitoring system and method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI390096B (en) * | 2009-08-24 | 2013-03-21 | Nat Applied Res Laboratories | Safety Monitoring System and Method of Bridge Structure |
-
2021
- 2021-07-07 CN CN202110768010.XA patent/CN113610274B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107450426A (en) * | 2017-08-01 | 2017-12-08 | 中国建筑第八工程局有限公司 | Foundation pit construction deformable statistical analysis method and system |
| CN112069225A (en) * | 2020-07-31 | 2020-12-11 | 武汉轻工大学 | Data mining method for correlation relation of multisource heterogeneous monitoring data in subway construction |
| CN112697062A (en) * | 2021-01-26 | 2021-04-23 | 湖南北斗微芯数据科技有限公司 | Railway roadbed deformation monitoring system and method |
Non-Patent Citations (4)
| Title |
|---|
| 宋晓东 ; 杨鸿彬 ; .客运专线梁体竖向变形监测结果影响因素分析.铁道标准设计.2009,(S1),全文. * |
| 柳新强 ; 王涛 ; .时空序列模型在地下管线沉降监测中的应用.北京测绘.2018,(07),810-812. * |
| 程东海 ; 蒲勇 ; 王典 ; .广州地区土层变形模量试验与取值方法研究.广东土木与建筑.2018,(11),全文. * |
| 陈艳茹 ; .基于遗传算法和极限学习机的智能算法在基坑变形预测中的应用.隧道建设(中英文).2018,(06),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113610274A (en) | 2021-11-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108922123B (en) | mine slope slip stability monitoring and early warning method | |
| Fan et al. | Successful early warning and emergency response of a disastrous rockslide in Guizhou province, China | |
| CN104299367A (en) | Landslide hazard multi-stage comprehensive monitoring and early warning method | |
| CN102831752B (en) | Glacial lake burst early-warning method | |
| Campling et al. | Temporal and spatial rainfall analysis across a humid tropical catchment | |
| CN108256172B (en) | Dangerous case early warning and forecasting method in process of pipe jacking and downward passing existing box culvert | |
| CN113610274B (en) | Subway construction long-term monitoring abnormal information mining method based on correlation | |
| CN105067209A (en) | Method for determining rigid change of bridge structure based on deformation data of bridge health monitoring | |
| CN103088803B (en) | Method of distinguishing collapse causing factors of karst collapse | |
| CN103134433B (en) | Method of identifying slip factors causing slope instability by utilizing displacement monitoring | |
| CN111042866A (en) | Multi-physical-field cooperative water inrush monitoring method | |
| Moschetti | A long-term earthquake rate model for the central and eastern United States from smoothed seismicity | |
| CN111563653A (en) | Early warning construction method for water-rich broken stratum of underground engineering | |
| CN117268455B (en) | Monitoring system of engineering construction quality detection equipment | |
| RU2011126886A (en) | METHOD FOR FORECASTING SEISMIC EVENTS | |
| JP5669311B2 (en) | Method and apparatus for predicting ground displacement | |
| CN106777556B (en) | Space analysis method for evaluating stable state of side slope in excavation period | |
| You | Extrapolation of historical coastal storm wave data with best-fit distribution function | |
| CN105222885A (en) | Optical fiber vibration detection method and device | |
| CN117010555A (en) | Method, device and processor for predicting disaster event risk of power transmission line | |
| JP5718186B2 (en) | Method and apparatus for predicting ground displacement | |
| Lee | Estimation of time-dependent damage paths of armors of rubble-mound breakwaters using stochastic processes | |
| CN116045903A (en) | Coal mining area ground deformation identification and evaluation method | |
| CN113009544B (en) | Method for judging peak range of radionuclide in seawater | |
| CN112767656B (en) | Open mine landslide disaster early warning method and system |
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 |