CN115479949B - Bridge safety monitoring and early warning method and system based on big data - Google Patents
Bridge safety monitoring and early warning method and system based on big data Download PDFInfo
- Publication number
- CN115479949B CN115479949B CN202211116579.9A CN202211116579A CN115479949B CN 115479949 B CN115479949 B CN 115479949B CN 202211116579 A CN202211116579 A CN 202211116579A CN 115479949 B CN115479949 B CN 115479949B
- Authority
- CN
- China
- Prior art keywords
- bearing
- bridge
- threshold value
- appearance defect
- value set
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/04—Analysing solids
- G01N29/043—Analysing solids in the interior, e.g. by shear waves
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
- G01N2021/0106—General arrangement of respective parts
- G01N2021/0112—Apparatus in one mechanical, optical or electronic block
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Acoustics & Sound (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention provides a bridge safety monitoring and early warning method and system based on big data, which are applied to the technical field of bridge safety monitoring, and the method comprises the following steps: and (4) carrying out set delineation on of the main bearing area of the bridge by receiving a bridge monitoring instruction. Traversing the set of the main bearing area of the bridge, and matching the set of the first-level bearing threshold value and the set of the second-level bearing threshold value. And acquiring an appearance defect set through an image acquisition device. And acquiring an internal defect set through an ultrasonic flaw detection device. And carrying out bearing analysis according to the appearance defect set and the internal defect set to generate a bearing limit value set. And traversing the bearing limit value set, comparing the first-level bearing threshold value set with the second-level bearing threshold value set to generate a bearing abnormal region set. And sending the force bearing abnormal area set to a display interface of a management terminal to generate a safety early warning signal. The bridge safety monitoring and early warning method solves the technical problem that the actual state of the bridge cannot be accurately evaluated due to certain hysteresis of the bridge safety monitoring and early warning method in the prior art.
Description
Technical Field
The invention relates to the technical field of bridge safety monitoring, in particular to a bridge safety monitoring and early warning method and system based on big data.
Background
The bridge safety monitoring is an important means for realizing the safe operation of the bridge, and in the prior art, the bridge safety monitoring means evaluates and analyzes the possible development potential of the bridge under the environmental condition and the possible potential threat to the structure safety operation mainly by monitoring external factors such as the load, the environment and the like of the bridge. Because the bridge safety is monitored by adopting an indirect evaluation mode, the actual defects and quality decay of the bridge cannot be directly obtained, and certain hysteresis exists in the evaluation of the current state of the bridge.
Therefore, the bridge safety monitoring and early warning method in the prior art has certain hysteresis, so that the technical problem that the actual state of the bridge cannot be accurately evaluated is solved.
Disclosure of Invention
The application provides a bridge safety monitoring and early warning method and system based on big data, which are used for solving the technical problem that the actual state of a bridge cannot be accurately evaluated due to certain hysteresis of the bridge safety monitoring and early warning method in the prior art.
In view of the above problems, the application provides a bridge safety monitoring and early warning method and system based on big data.
In a first aspect of the present application, a bridge safety monitoring and early warning method based on big data is provided, where the method applies a bridge safety monitoring and early warning system based on big data, and the method includes: when a bridge monitoring instruction is received, sending a railway bridge design drawing to be monitored to a display interface of a management terminal, and defining a main bridge bearing area set by workers; traversing the main bearing area set of the bridge, and matching a primary bearing threshold value set and a secondary bearing threshold value set, wherein the primary bearing threshold value set and the secondary bearing threshold value set are in one-to-one correspondence, and the primary bearing threshold value of any group is smaller than the secondary bearing threshold value; traversing the bridge main bearing area set through an image acquisition device to acquire appearance defects to generate an appearance defect set; traversing the set of the main bearing area of the bridge through an ultrasonic flaw detection device to acquire internal flaws and generating an internal flaw set; traversing the main bearing area set of the bridge according to the appearance defect set and the internal defect set to carry out bearing analysis, and generating a bearing limit value set; traversing the bearing limit value set, the primary bearing threshold value set and the secondary bearing threshold value set for comparison to generate a bearing abnormal region set; and generating a safety early warning signal according to the display interface sent to the management terminal by the bearing abnormal area set.
In a second aspect of the present application, a bridge safety monitoring and early warning system based on big data is provided, the system includes: the system comprises a bearing area set acquisition module, a management terminal and a monitoring module, wherein the bearing area set acquisition module is used for sending a railway bridge design drawing to be monitored to a display interface of the management terminal when a bridge monitoring instruction is received, and a main bearing area set of the bridge is defined by workers; the bearing threshold value set matching module is used for traversing the main bearing area set of the bridge and matching a primary bearing threshold value set and a secondary bearing threshold value set, wherein the primary bearing threshold value set and the secondary bearing threshold value set are in one-to-one correspondence, and the primary bearing threshold value of any group is smaller than the secondary bearing threshold value; the appearance defect set acquisition module is used for traversing the bridge main bearing area set through an image acquisition device to acquire appearance defects and generate an appearance defect set; the internal defect set acquisition module is used for traversing the bridge main bearing area set through an ultrasonic flaw detection device to acquire internal defects and generate an internal defect set; the bearing limit value set acquisition module is used for traversing the main bearing area set of the bridge according to the appearance defect set and the internal defect set to carry out bearing analysis so as to generate a bearing limit value set; the bearing abnormal region set acquisition module is used for traversing the bearing limit value set, comparing the primary bearing threshold value set with the secondary bearing threshold value set and generating a bearing abnormal region set; and the safety early warning signal generating module is used for generating a safety early warning signal according to the display interface sent to the management terminal by the force bearing abnormal area set.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
according to the method provided by the embodiment of the application, the set delineation of the main bearing area of the bridge is carried out by receiving the bridge monitoring instruction. Traversing the set of the main bearing area of the bridge, and matching the set of the first-level bearing threshold value and the set of the second-level bearing threshold value. And traversing the set of the main bearing area of the bridge through the image acquisition device to acquire the appearance defects to generate an appearance defect set. And traversing the set of the main bearing area of the bridge through an ultrasonic flaw detection device to acquire internal flaws and generating an internal flaw set. And carrying out bearing analysis according to the appearance defect set and the internal defect set to generate a bearing limit value set. And traversing the bearing limit value set, comparing the first-level bearing threshold value set with the second-level bearing threshold value set to generate a bearing abnormal region set. And sending the force bearing abnormal area set to a display interface of a management terminal to generate a safety early warning signal. By analyzing and comparing the bearing limit of the bearing area and generating an early warning signal according to the analysis and comparison result, the railway bridge can be early warned in time, and the safety accident of the bridge can be further avoided. The early warning to the railway bridge is realized in time, and the safety accident of the bridge is avoided in time. The bridge safety monitoring and early warning method solves the technical problem that the actual state of the bridge cannot be accurately evaluated due to certain hysteresis of the bridge safety monitoring and early warning method in the prior art.
The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.
Drawings
Fig. 1 is a schematic flow diagram of a bridge safety monitoring and early warning method based on big data provided by the present application;
fig. 2 is a schematic flow chart illustrating matching of a primary bearing threshold value set and a secondary bearing threshold value set in the bridge safety monitoring and early warning method based on big data provided by the present application;
fig. 3 is a schematic flow chart of a method for monitoring and warning bridge safety based on big data according to the present application, wherein a force-bearing abnormal area set is obtained;
fig. 4 is a schematic structural diagram of a bridge safety monitoring and early warning system based on big data according to the present application.
Description of the reference numerals: the system comprises a bearing region set acquisition module 11, a bearing threshold value set matching module 12, an appearance defect set acquisition module 13, an internal defect set acquisition module 14, a bearing limit value set acquisition module 15, a bearing abnormal region set acquisition module 16 and a safety early warning signal generation module 17.
Detailed Description
The application provides a bridge safety monitoring and early warning method and system based on big data, which are used for solving the technical problem that the actual state of a bridge cannot be accurately evaluated due to certain hysteresis of the bridge safety monitoring and early warning method in the prior art.
The technical solution in the present application will be described clearly and completely with reference to the accompanying drawings. The embodiments described are only a part of the disclosure that can be realized by the present application, and not the entire disclosure of the present application.
Example one
As shown in fig. 1, the present application provides a bridge safety monitoring and early warning method based on big data, where the method uses a bridge safety monitoring and early warning system based on big data, and the method includes:
step 100: when a bridge monitoring instruction is received, sending a railway bridge design drawing to be monitored to a display interface of a management terminal, and defining a main bridge bearing area set by workers;
step 200: traversing the main bearing area set of the bridge, and matching a primary bearing threshold value set and a secondary bearing threshold value set, wherein the primary bearing threshold value set and the secondary bearing threshold value set are in one-to-one correspondence, and the primary bearing threshold value of any group is smaller than the secondary bearing threshold value;
the railway bridge safety monitoring system has the advantages that the railway bridge is large in load capacity and driving density, the standard that natural disasters can be resisted is high, the structural strength of the bridge is required to be certain, the safety monitoring of the railway bridge is an important part in daily maintenance of the bridge in order to guarantee safe operation of the railway bridge, the safety monitoring of the bridge is guaranteed, and potential risks existing in the bridge are pre-warned. When a bridge monitoring instruction is received, the bridge to be monitored needs to be safely monitored, the railway bridge design drawing to be monitored is sent to a display interface of a management terminal, the railway bridge is a bridge containing rail transit or railway traffic requirements, and a main bearing area of the bridge is obtained by defining a main bearing area set of the bridge by workers. And traversing the set of the main bearing areas of the bridge, and matching the set of the first-level bearing threshold values and the set of the second-level bearing threshold values, namely matching the no-load bearing capacity and the load bearing capacity of each bearing area, wherein the set of the first-level bearing threshold values is the bearing capacity of the bridge when the bridge is no-load, and the set of the second-level bearing threshold values is the bearing capacity of the bridge when the bridge is loaded. The primary bearing threshold value set corresponds to the secondary bearing threshold value set one by one, and the primary bearing threshold value of any group is smaller than the secondary bearing threshold value.
As shown in fig. 2, the method steps 200 provided in the embodiment of the present application further include:
step 210: sending the railway bridge design drawing to be monitored, which defines the set of the main bearing area of the bridge, to a first sub-table of a bearing threshold calibration table to generate a bearing threshold calibration result of the trackless vehicle;
step 220: sending the railway bridge design drawing to be monitored, which defines the main bearing area set of the bridge, to a second sub-table of the bearing threshold calibration table to generate a bearing threshold calibration result of the railcar;
step 230: adding the force bearing threshold value calibration result of the trackless vehicle into the primary force bearing threshold value set;
step 240: and adding the force bearing threshold value calibration result of the railcar into the secondary force bearing threshold value set.
Specifically, a railway bridge design drawing to be monitored, which is collected in a main bearing area of a bound bridge, is sent to a first sub-table of a bearing threshold calibration table to generate a bearing threshold calibration result of the trackless vehicle, wherein the bearing threshold calibration result of the trackless vehicle is a bearing threshold of the bearing area in a traffic-tool-free state, namely a no-load bearing threshold. When the bridge is unloaded, the load-bearing areas need to bear the weight of the bridge. The bearing threshold calibration table is a bearing threshold of each bearing area and comprises a first sub-table and a second sub-table, wherein the first sub-table comprises a set bearing threshold of each bearing area under the state that no vehicle passes through, and the second sub-table comprises a set bearing threshold of each bearing area under the state that the vehicle passes through. And sending the railway bridge design drawing to be monitored, which defines the set of the main bearing area of the bridge, to a second sub-table of the bearing threshold calibration table to generate a bearing threshold calibration result of the railcar, namely obtaining the bearing threshold of each bearing area under the traffic vehicle passing state, wherein the bearing threshold calibration result of the railcar is the maximum bearing threshold of the bearing area. And finally, adding the force-bearing threshold calibration result of the trackless vehicle into the primary force-bearing threshold set, and adding the force-bearing threshold calibration result of the trackless vehicle into the secondary force-bearing threshold set.
The method steps 200 provided by the embodiment of the present application further include:
step 250: judging whether the bearing threshold calibration table meets a preset updating period or not;
step 260: if the first design side and the second design side reach the Nth design side, uploading a first data set and a second data set, wherein the first data set comprises multiple sets of railway bridge design drawings and trackless vehicle bearing threshold value recording data, and the second data set comprises multiple sets of railway bridge design drawings and trackless vehicle bearing threshold value recording data;
step 270: updating the first sub-table of the bearing threshold calibration table according to the first data set;
step 280: and updating the second sub-table of the stressed threshold calibration table according to the second data set.
Specifically, whether the bearing threshold calibration table meets the preset updating period is judged, and the bearing threshold calibration table contains a range for reflecting the bearing capacity of a bearing area, and the initially set bearing range changes along with the increase of the service life of the bridge, so that the bearing threshold calibration table needs to be updated for a certain period to ensure that the bearing threshold calibration table can better reflect the real bearing condition of the bridge. If the preset updating period is met, the bearing threshold calibration table needs to be updated, the first data set and the second data set are uploaded through the first designer, the second designer and the Nth designer, namely, the bearing data of the bearing points are uploaded according to the designer. The first data set comprises multiple sets of railway bridge design drawings and trackless vehicle bearing threshold value recording data, and the second data set comprises multiple sets of railway bridge design drawings and trackless vehicle bearing threshold value recording data. And updating a first sub-table of the stressed threshold calibration table according to the first data set, and updating a second sub-table of the stressed threshold calibration table according to the second data set.
Step 300: traversing the bridge main bearing area set through an image acquisition device to acquire appearance defects to generate an appearance defect set;
step 400: traversing the set of the main bearing area of the bridge through an ultrasonic flaw detection device to acquire internal flaws and generating an internal flaw set;
step 500: traversing the main bearing area set of the bridge according to the appearance defect set and the internal defect set to carry out bearing analysis, and generating a bearing limit value set;
specifically, the image acquisition device traverses the set of the main bearing area of the bridge to acquire the appearance defects, and the appearance defect set is generated, wherein the appearance defects include defects in the appearance aspect such as structural deformation and structural erosion which can be acquired through images. And traversing the set of the main bearing area of the bridge through an ultrasonic flaw detection device to acquire internal defects to generate an internal defect set, wherein the internal defects are internal defects which cannot be directly acquired through an appearance image, such as internal cracks and other internal defects. And traversing the main bearing area set of the bridge according to the appearance defect set and the internal defect set to carry out bearing analysis, namely carrying out bearing analysis on the bearing areas with defects to generate a bearing limit value set.
The method steps 500 provided by the embodiment of the present application further include:
step 510: traversing the appearance defect set to extract features, and generating an appearance defect length feature, an appearance defect width feature, an appearance defect depth feature and an appearance defect coordinate feature;
step 520: traversing the internal defect set to extract features, and generating internal defect volume features and internal defect coordinate features;
step 530: constructing a bearing analysis model, wherein the bearing analysis model comprises a first bearing analysis module and a second bearing analysis module;
step 540: inputting the appearance defect length characteristic, the appearance defect width characteristic, the appearance defect depth characteristic and the appearance defect coordinate characteristic into the first bearing analysis module to obtain a first bearing limit value;
step 550: inputting the first bearing limit value, the internal defect volume characteristic and the internal defect coordinate characteristic into the second bearing analysis module to obtain a second bearing limit value;
step 560: adding the second bearing limit value into the bearing limit value set.
Specifically, the appearance defect set is traversed to extract features, the appearance defect length, the appearance defect width, the appearance defect depth and the appearance defect coordinate are extracted, and the appearance defect length feature, the appearance defect width feature, the appearance defect depth feature and the appearance defect coordinate feature are generated. And traversing the internal defect set to extract features, and generating internal defect volume features and internal defect coordinate features, wherein the internal defects are internal cracks of the force bearing region to obtain crack volumes and specific position coordinates. Further, a bearing capacity analysis model is constructed, wherein the bearing capacity analysis model comprises a first bearing capacity analysis module and a second bearing capacity analysis module. The first bearing analysis module is used for obtaining the bearing limit of the bearing area through the appearance defect, and the second bearing analysis module is used for obtaining the bearing limit of the bearing area according to the internal defect. And finally, inputting the length characteristic of the appearance defect, the width characteristic of the appearance defect, the depth characteristic of the appearance defect and the coordinate characteristic of the appearance defect into the first bearing analysis module to obtain a first bearing limit value. And inputting the first bearing limit value, the internal defect volume characteristic and the internal defect coordinate characteristic into the second bearing analysis module to obtain a second bearing limit value. And adding the second bearing limit value into the bearing limit value set to finish the evaluation of the bearing limit of the bearing area with defects.
The method steps 530 provided by the embodiment of the present application further include:
step 531: uploading a third data set and a fourth data set by the first designer, the second designer, and up to the Nth designer;
step 532: extracting an appearance defect characteristic record data set and a first bearing limit calibration value set from the third data set;
step 533: extracting an internal defect characteristic record data set and a second bearing limit calibration value set from the fourth data set;
step 534: constructing the first bearing analysis module based on a regression decision forest according to the appearance defect characteristic record data set and the first bearing limit calibration value set;
step 535: constructing a second bearing analysis module based on a regression decision forest according to the internal defect feature record data set, the first bearing limit calibration value set and the second bearing limit calibration value set;
step 536: and combining the first bearing capacity analysis module and the second bearing capacity analysis module to generate the bearing capacity analysis model.
Specifically, a third data set and a fourth data set are uploaded through the first designer, the second designer, and up to the nth designer. And extracting an appearance defect feature record data set and a first bearing limit calibration value set from the third data set, and obtaining the appearance defect feature record and the corresponding first bearing limit calibration value by obtaining the third data set. And extracting an internal defect characteristic record data set and a second bearing limit calibration value set from the fourth data set, and extracting the internal defect characteristic record data and a corresponding second bearing limit calibration value through the fourth data set. And then, constructing the first bearing analysis module based on a regression decision forest according to the appearance defect characteristic record data set and the first bearing limit calibration value set, wherein the first bearing analysis module is used for acquiring corresponding first bearing limit data according to the appearance defect characteristic. And constructing a second bearing analysis module based on a regression decision forest according to the internal defect characteristic record data set, the first bearing limit calibration value set and the second bearing limit calibration value set, wherein the second bearing analysis module is used for acquiring a second bearing limit according to the internal defect characteristic and the first bearing limit calibration value, and the finally output second bearing limit is the final bearing limit. And finally, combining the first bearing capacity analysis module and the second bearing capacity analysis module to generate the bearing capacity analysis model. Because the bearing limit of the bearing area is influenced by the internal defect and the external defect, the influence of the internal defect and the external defect on the bearing limit is obtained by constructing a bearing analysis model, and the accurate analysis of the bearing of the bridge is convenient to follow.
The method steps 534 provided by the embodiment of the present application further include:
step 534-1: dividing the appearance defect characteristic record data set and the first bearing limit calibration value set into k equal parts, and taking out the k times after replacing to generate a first training data set;
step 534-2: repeating the steps for M times to generate a second training data set and a third training data set until an Mth training data set;
step 534-3: taking the appearance defect characteristic record data set of the first training data set as input data, taking the first force bearing limit calibration value set of the first training data set as output identification information, and constructing a first decision tree;
step 534-4: taking the appearance defect characteristic record data set of the Mth training data set as input data, taking the first force bearing limit calibration value set of the Mth training data set as output identification information, and constructing an Mth decision tree;
step 534-5: and combining the first decision tree to the Mth decision tree to generate the first force bearing analysis module, wherein the output of the first force bearing analysis module is the average value of the outputs of the first decision tree to the Mth decision tree.
Specifically, when a first bearing analysis module is constructed, an appearance defect characteristic record data set and the first bearing limit calibration value set are divided into k equal parts, the first training data set is generated by taking out the first training data set after being replaced for k times, the second training data set and the third training data set are generated until the Mth training data set, and the process is random extraction after being replaced, so that the constructed data set has randomness, and the training effect of a subsequent model is further improved. And taking the appearance defect characteristic record data set of the first training data set as input data, and taking the first force bearing limit calibration value set of the first training data set as output identification information to construct a first decision tree. And then, taking the appearance defect characteristic record data set of the Mth training data set as input data, taking the first force-bearing limit calibration value set of the Mth training data set as output identification information, and constructing an Mth decision tree. And combining the first decision tree and the Mth decision tree to generate the first force bearing analysis module, wherein the output of the first force bearing analysis module is the average value of the outputs of the first decision tree and the Mth decision tree. And when a second bearing analysis module is constructed, dividing an internal defect characteristic record data set, the first bearing limit calibration value set and the second bearing limit calibration value set into k equal parts in the same mode, taking out the k times after the k equal parts are replaced, and repeating the M times to generate a training data set of the second bearing analysis module. And then, taking the obtained internal defect characteristic record data set and the first bearing limit calibration value set in the training data set of the second bearing analysis module as input data, and taking the second bearing limit calibration value set as output identification information to construct a first decision tree. And acquiring the first decision tree of the second bearing analysis module till the Mth decision tree, and combining to generate the second bearing analysis module. Wherein the output of the second force-bearing analysis module is the average value of the output of the decision tree.
Step 600: traversing the bearing limit value set, the primary bearing threshold value set and the secondary bearing threshold value set for comparison to generate a bearing abnormal region set;
step 700: and generating a safety early warning signal according to the display interface sent to the management terminal by the bearing abnormal area set.
Specifically, traversing the bearing limit value set, the first-level bearing threshold value set and the second-level bearing threshold value set for comparison, namely traversing the bearing limit, the first-level bearing threshold value set and the second-level bearing threshold value set, and carrying out numerical comparison, when the bearing limit does not satisfy the first-level bearing threshold value set and the second-level bearing threshold value set, generating a bearing abnormal region set, wherein when the bearing limit does not satisfy the first-level bearing threshold value set, the bridge may have the risk of collapse when no transportation means pass. And when the bearing capacity limit does not meet the secondary bearing capacity threshold set, the bridge may have the risk of collapse when the vehicles pass. And finally, sending the force bearing abnormal region set to a display interface of the management terminal, wherein the early warning signals generated by different comparison results have differences, when the force bearing limit does not satisfy the primary force bearing threshold set, the early warning method is a first type of early warning method, when the force bearing limit does not satisfy the secondary force bearing threshold set, the early warning method is a second type of early warning method, the early warning level of the first type of early warning method is higher than that of the second type of early warning method, and a safety early warning signal is generated. By analyzing and comparing the bearing limit of the bearing area and generating an early warning signal according to the analysis and comparison result, the railway bridge can be early warned in time, and the safety accident of the bridge can be further avoided.
As shown in fig. 3, the method steps 600 provided in the embodiment of the present application further include:
step 610: traversing the bearing limit value set and the primary bearing threshold value set for comparison, and adding the primary bearing area of the bridge, of which the bearing limit value is less than or equal to the primary bearing threshold value, into a primary bearing abnormal area set;
step 620: comparing the bearing limit value set with the bearing limit value set larger than the primary bearing threshold value with the secondary bearing threshold value set, and adding the main bearing area of the bridge with the bearing limit value smaller than or equal to the primary bearing threshold value into a secondary bearing abnormal area set;
step 630: and adding the primary bearing abnormal area set and the secondary bearing abnormal area set into the bearing abnormal area set.
Specifically, the bearing limit value set and the primary bearing threshold value set are traversed and compared, the primary bearing area of the bridge with the bearing limit value smaller than or equal to the primary bearing threshold value is added into the primary bearing area set, and the bearing limit can not meet the bearing requirements of the self structure of the bridge at this moment. And comparing the bearing limit value set with the secondary bearing threshold value set, wherein the bearing limit value set is greater than the primary bearing threshold value, and adding the primary bearing area of the bridge, which is less than or equal to the primary bearing threshold value, into the secondary bearing abnormal area set, wherein the bearing limit can meet the bearing requirements of the self structure of the bridge, but when a vehicle passes through the bridge, the bearing capacity of each bearing area cannot be met, and certain safety risk exists. And finally, adding the primary bearing abnormal region set and the secondary bearing abnormal region set into the bearing abnormal region set.
In summary, the method provided by the embodiment of the application sends the railway bridge design drawing to be monitored to the display interface of the management terminal by receiving the bridge monitoring instruction, and defines the main bearing area set of the bridge by the staff. Traversing the set of the main bearing area of the bridge, and matching the set of the first-level bearing threshold value and the set of the second-level bearing threshold value. And traversing the set of the main bearing area of the bridge through the image acquisition device to acquire the appearance defects to generate an appearance defect set. And traversing the set of the main bearing area of the bridge through an ultrasonic flaw detection device to acquire internal flaws and generating an internal flaw set. And carrying out bearing analysis according to the appearance defect set and the internal defect set to generate a bearing limit value set. And traversing the bearing limit value set, comparing the first-level bearing threshold value set with the second-level bearing threshold value set to generate a bearing abnormal region set. And sending the force bearing abnormal area set to a display interface of a management terminal to generate a safety early warning signal. By analyzing and comparing the bearing limit of the bearing area and generating an early warning signal according to the analysis and comparison result, the railway bridge is early warned in time, and the occurrence of bridge safety accidents is further avoided. The early warning to the railway bridge is realized in time, and the safety accident of the bridge is avoided in time. Example two
Based on the same inventive concept as the bridge safety monitoring and early warning method based on big data in the foregoing embodiment, as shown in fig. 4, the present application provides a bridge safety monitoring and early warning system based on big data, and the system includes:
the bearing area set acquisition module 11 is used for sending the railway bridge design drawing to be monitored to a display interface of the management terminal when a bridge monitoring instruction is received, and defining a main bearing area set of the bridge through workers;
the bearing threshold value set matching module 12 is used for traversing the bridge main bearing area set and matching a primary bearing threshold value set and a secondary bearing threshold value set, wherein the primary bearing threshold value set and the secondary bearing threshold value set are in one-to-one correspondence, and the primary bearing threshold value of any group is smaller than the secondary bearing threshold value;
the appearance defect set acquisition module 13 is used for traversing the bridge main bearing area set through an image acquisition device to acquire appearance defects and generate an appearance defect set;
the internal defect set acquisition module 14 is used for traversing the bridge main bearing area set through an ultrasonic flaw detection device to acquire internal defects and generate an internal defect set;
a bearing limit value set acquisition module 15, configured to traverse the bridge main bearing area set according to the appearance defect set and the internal defect set to perform bearing analysis, so as to generate a bearing limit value set;
a bearing abnormal region set acquisition module 16, configured to traverse the bearing limit value set, compare the primary bearing threshold value set with the secondary bearing threshold value set, and generate a bearing abnormal region set;
and the safety early warning signal generating module 17 is configured to generate a safety early warning signal according to the display interface sent to the management terminal by the force bearing abnormal region set.
Further, the force bearing threshold set matching module 12 is further configured to:
sending the railway bridge design drawing to be monitored, which defines the bridge main bearing area set, to a first sub-table of a bearing threshold value calibration table to generate a trackless vehicle bearing threshold value calibration result;
sending the railway bridge design drawing to be monitored, which defines the bridge main bearing area set, to a second sub-table of the bearing threshold calibration table to generate a bearing threshold calibration result of the railcar;
adding the force bearing threshold value calibration result of the trackless vehicle into the primary force bearing threshold value set;
and adding the force bearing threshold value calibration result of the railcar into the secondary force bearing threshold value set.
Further, the hard threshold set matching module 12 is further configured to:
judging whether the bearing threshold calibration table meets a preset updating period or not;
if the first design side and the second design side reach the Nth design side, uploading a first data set and a second data set, wherein the first data set comprises multiple sets of railway bridge design drawings and trackless vehicle bearing threshold value recording data, and the second data set comprises multiple sets of railway bridge design drawings and trackless vehicle bearing threshold value recording data;
updating the first sub-table of the bearing threshold calibration table according to the first data set;
and updating the second sub-table of the bearing threshold calibration table according to the second data set.
Further, the messenger limit value set acquisition module 15 is further configured to:
traversing the appearance defect set to extract features, and generating an appearance defect length feature, an appearance defect width feature, an appearance defect depth feature and an appearance defect coordinate feature;
traversing the internal defect set to extract features, and generating internal defect volume features and internal defect coordinate features;
constructing a bearing capacity analysis model, wherein the bearing capacity analysis model comprises a first bearing capacity analysis module and a second bearing capacity analysis module;
inputting the appearance defect length characteristic, the appearance defect width characteristic, the appearance defect depth characteristic and the appearance defect coordinate characteristic into the first bearing analysis module to obtain a first bearing limit value;
inputting the first bearing limit value, the internal defect volume characteristic and the internal defect coordinate characteristic into the second bearing analysis module to obtain a second bearing limit value;
adding the second hard-bound limit to the hard-bound limit set.
Further, the messenger limit value set acquisition module 15 is further configured to:
uploading, by the first designer, the second designer, through to the Nth designer, a third data set and a fourth data set;
extracting an appearance defect characteristic record data set and a first bearing limit calibration value set from the third data set;
extracting an internal defect characteristic record data set and a second bearing limit calibration value set from the fourth data set;
according to the appearance defect characteristic record data set and the first bearing limit calibration value set, constructing a first bearing analysis module based on a regression decision forest;
constructing a second bearing analysis module based on a regression decision forest according to the internal defect characteristic record data set, the first bearing limit calibration value set and the second bearing limit calibration value set;
and combining the first bearing analysis module and the second bearing analysis module to generate the bearing analysis model.
Further, the bearing limit value set acquiring module 15 is further configured to:
dividing the appearance defect characteristic record data set and the first bearing limit calibration value set into k equal parts, and taking out the k times after replacing to generate a first training data set;
repeating the steps for M times to generate a second training data set and a third training data set till an Mth training data set;
taking the appearance defect characteristic record data set of the first training data set as input data, taking the first force bearing limit calibration value set of the first training data set as output identification information, and constructing a first decision tree;
taking the appearance defect characteristic record data set of the Mth training data set as input data, taking the first force bearing limit calibration value set of the Mth training data set as output identification information, and constructing an Mth decision tree;
and combining the first decision tree to the Mth decision tree to generate the first bearing analysis module, wherein the output of the first bearing analysis module is the average value of the outputs of the first decision tree to the Mth decision tree.
Further, the force-bearing abnormal region set acquiring module 16 is further configured to:
traversing the bearing limit value set and the primary bearing threshold value set for comparison, and adding the primary bearing area of the bridge with the bearing limit value less than or equal to the primary bearing threshold value into a primary bearing abnormal area set;
comparing the bearing limit value set with the secondary bearing threshold value set, wherein the bearing limit value set is greater than the primary bearing threshold value, and adding the main bearing area of the bridge, of which the bearing limit value is less than or equal to the primary bearing threshold value, into a secondary bearing abnormal area set;
and adding the primary bearing abnormal area set and the secondary bearing abnormal area set into the bearing abnormal area set.
The second embodiment is used for executing the method as in the first embodiment, and both the execution principle and the execution basis can be obtained through the content recorded in the first embodiment, which is not described in detail herein. Although the present application has been described in connection with particular features and embodiments thereof, the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application, and the content thus obtained also falls within the scope of protection of the present application.
Claims (7)
1. A bridge safety monitoring and early warning method based on big data is characterized in that the method applies a bridge safety monitoring and early warning system based on big data, and the method comprises the following steps:
when a bridge monitoring instruction is received, sending a railway bridge design drawing to be monitored to a display interface of a management terminal, and defining a main bridge bearing area set by workers;
traversing the main bearing area set of the bridge, and matching a primary bearing threshold value set and a secondary bearing threshold value set, wherein the primary bearing threshold value set and the secondary bearing threshold value set are in one-to-one correspondence, and the primary bearing threshold value of any group is smaller than the secondary bearing threshold value;
traversing the main bearing area set of the bridge through an image acquisition device to acquire appearance defects to generate an appearance defect set;
traversing the set of the main bearing area of the bridge through an ultrasonic flaw detection device to collect internal flaws and generate an internal flaw set;
traversing the main bearing area set of the bridge according to the appearance defect set and the internal defect set to carry out bearing analysis, and generating a bearing limit value set;
traversing the bearing limit value set, the primary bearing threshold value set and the secondary bearing threshold value set for comparison to generate a bearing abnormal region set;
sending the force bearing abnormal region set to a display interface of the management terminal to generate a safety early warning signal;
wherein, the traversing the main bearing area set of the bridge according to the appearance defect set and the internal defect set to perform bearing analysis, and generating a bearing limit value set, comprises:
traversing the appearance defect set to extract features, and generating appearance defect length features, appearance defect width features, appearance defect depth features and appearance defect coordinate features;
traversing the internal defect set to extract features, and generating internal defect volume features and internal defect coordinate features;
constructing a bearing analysis model, wherein the bearing analysis model comprises a first bearing analysis module and a second bearing analysis module;
inputting the appearance defect length characteristic, the appearance defect width characteristic, the appearance defect depth characteristic and the appearance defect coordinate characteristic into the first bearing analysis module to obtain a first bearing limit value;
inputting the first bearing limit value, the internal defect volume characteristic and the internal defect coordinate characteristic into the second bearing analysis module to obtain a second bearing limit value;
adding the second bearing limit value into the bearing limit value set.
2. The method of claim 1, wherein said traversing said set of primary force-bearing areas of the bridge, matching a set of primary force-bearing thresholds and a set of secondary force-bearing thresholds, comprises:
sending the railway bridge design drawing to be monitored, which defines the set of the main bearing area of the bridge, to a first sub-table of a bearing threshold calibration table to generate a bearing threshold calibration result of the trackless vehicle;
sending the railway bridge design drawing to be monitored, which defines the bridge main bearing area set, to a second sub-table of the bearing threshold calibration table to generate a bearing threshold calibration result of the railcar;
adding the force bearing threshold value calibration result of the trackless vehicle into the primary force bearing threshold value set;
and adding the force bearing threshold value calibration result of the railcar into the secondary force bearing threshold value set.
3. The method of claim 2, further comprising:
judging whether the bearing threshold calibration table meets a preset updating period or not;
if the first data set and the second data set are met, uploading the first data set and the second data set through a first designer, a second designer and an Nth designer, wherein the first data set comprises multiple sets of railway bridge design drawings and trackless vehicle bearing threshold recording data, and the second data set comprises multiple sets of railway bridge design drawings and trackless vehicle bearing threshold recording data;
updating the first sub-table of the stressed threshold calibration table according to the first data set;
and updating the second sub-table of the bearing threshold calibration table according to the second data set.
4. The method of claim 3, wherein the constructing the stressed analysis model comprises:
uploading, by the first designer, the second designer, through to the Nth designer, a third data set and a fourth data set;
extracting an appearance defect characteristic record data set and a first bearing limit calibration value set from the third data set;
extracting an internal defect characteristic record data set and a second bearing limit calibration value set from the fourth data set;
constructing the first bearing analysis module based on a regression decision forest according to the appearance defect characteristic record data set and the first bearing limit calibration value set;
constructing a second bearing analysis module based on a regression decision forest according to the internal defect feature record data set, the first bearing limit calibration value set and the second bearing limit calibration value set;
and combining the first bearing capacity analysis module and the second bearing capacity analysis module to generate the bearing capacity analysis model.
5. The method of claim 4, wherein said constructing said first force-bearing analysis module based on a regression decision forest from said appearance defect feature record dataset and said first force-bearing limit calibration value set comprises:
dividing the appearance defect characteristic record data set and the first bearing limit calibration value set into k equal parts, and taking out the k times after replacing to generate a first training data set;
repeating the steps for M times to generate a second training data set and a third training data set until an Mth training data set;
taking the appearance defect characteristic record data set of the first training data set as input data, taking the first force bearing limit calibration value set of the first training data set as output identification information, and constructing a first decision tree;
taking the appearance defect characteristic record data set of the Mth training data set as input data, taking the first force bearing limit calibration value set of the Mth training data set as output identification information, and constructing an Mth decision tree;
and combining the first decision tree to the Mth decision tree to generate the first force bearing analysis module, wherein the output of the first force bearing analysis module is the average value of the outputs of the first decision tree to the Mth decision tree.
6. The method of claim 1, wherein said traversing said set of force-bearing limit values against said set of primary force-bearing thresholds and said set of secondary force-bearing thresholds to generate a set of force-bearing abnormal regions comprises:
traversing the bearing limit value set and the primary bearing threshold value set for comparison, and adding the primary bearing area of the bridge with the bearing limit value less than or equal to the primary bearing threshold value into a primary bearing abnormal area set;
comparing the bearing limit value set with the bearing limit value set larger than the primary bearing threshold value with the secondary bearing threshold value set, and adding the main bearing area of the bridge with the bearing limit value smaller than or equal to the primary bearing threshold value into a secondary bearing abnormal area set;
and adding the primary bearing abnormal region set and the secondary bearing abnormal region set into the bearing abnormal region set.
7. The utility model provides a bridge safety monitoring early warning system based on big data which characterized in that, the system includes:
the system comprises a bearing area set acquisition module, a management terminal and a monitoring module, wherein the bearing area set acquisition module is used for sending a railway bridge design drawing to be monitored to a display interface of the management terminal when a bridge monitoring instruction is received, and a main bearing area set of the bridge is defined by workers;
the bearing threshold value set matching module is used for traversing the main bearing area set of the bridge and matching a primary bearing threshold value set and a secondary bearing threshold value set, wherein the primary bearing threshold value set and the secondary bearing threshold value set are in one-to-one correspondence, and the primary bearing threshold value of any group is smaller than the secondary bearing threshold value;
the appearance defect set acquisition module is used for traversing the bridge main bearing area set through an image acquisition device to acquire appearance defects and generate an appearance defect set;
the internal defect set acquisition module is used for traversing the bridge main bearing area set through an ultrasonic flaw detection device to acquire internal defects and generate an internal defect set;
the bearing limit value set acquisition module is used for traversing the main bearing area set of the bridge according to the appearance defect set and the internal defect set to carry out bearing analysis so as to generate a bearing limit value set;
the bearing abnormal region set acquisition module is used for traversing the bearing limit value set, the primary bearing threshold value set and the secondary bearing threshold value set for comparison to generate a bearing abnormal region set;
the safety early warning signal generating module is used for generating a safety early warning signal according to the display interface sent to the management terminal by the force bearing abnormal area set;
wherein, the bearing limit value set acquisition module includes:
traversing the appearance defect set to extract features, and generating an appearance defect length feature, an appearance defect width feature, an appearance defect depth feature and an appearance defect coordinate feature;
traversing the internal defect set to extract features, and generating internal defect volume features and internal defect coordinate features;
constructing a bearing analysis model, wherein the bearing analysis model comprises a first bearing analysis module and a second bearing analysis module;
inputting the appearance defect length characteristic, the appearance defect width characteristic, the appearance defect depth characteristic and the appearance defect coordinate characteristic into the first bearing analysis module to obtain a first bearing limit value;
inputting the first bearing limit value, the internal defect volume characteristic and the internal defect coordinate characteristic into the second bearing analysis module to obtain a second bearing limit value;
adding the second bearing limit value into the bearing limit value set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211116579.9A CN115479949B (en) | 2022-09-14 | 2022-09-14 | Bridge safety monitoring and early warning method and system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211116579.9A CN115479949B (en) | 2022-09-14 | 2022-09-14 | Bridge safety monitoring and early warning method and system based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115479949A CN115479949A (en) | 2022-12-16 |
| CN115479949B true CN115479949B (en) | 2023-04-07 |
Family
ID=84393041
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211116579.9A Active CN115479949B (en) | 2022-09-14 | 2022-09-14 | Bridge safety monitoring and early warning method and system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115479949B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116182943B (en) * | 2023-01-31 | 2023-12-15 | 扬州丰筑建设工程有限公司 | Large-span steel structure health monitoring method and system based on data reconstruction |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113916673A (en) * | 2021-10-28 | 2022-01-11 | 安阳市蓝海安全工程师事务所有限公司 | Safety early warning method and system based on container state monitoring |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4859521B2 (en) * | 2006-05-02 | 2012-01-25 | 三菱重工業株式会社 | Program, processing apparatus and processing method for processing ultrasonic flaw detection data |
| JP5342619B2 (en) * | 2011-08-30 | 2013-11-13 | 三菱重工業株式会社 | Program, processing apparatus and processing method for processing ultrasonic flaw detection data |
| JP6546826B2 (en) * | 2015-10-08 | 2019-07-17 | 株式会社日立パワーソリューションズ | Defect inspection method and apparatus therefor |
| CN112734702A (en) * | 2020-12-28 | 2021-04-30 | 詹晨 | Bridge safety monitoring method based on big data analysis and machine vision and cloud platform |
| CN113029229A (en) * | 2021-02-04 | 2021-06-25 | 泉州市泽锐航科技有限公司 | Bridge detection safety system based on big data of Internet of things |
| CN113408396B (en) * | 2021-06-15 | 2022-03-18 | 广西交科集团有限公司 | Bridge intelligent sensing system based on cloud computing |
-
2022
- 2022-09-14 CN CN202211116579.9A patent/CN115479949B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113916673A (en) * | 2021-10-28 | 2022-01-11 | 安阳市蓝海安全工程师事务所有限公司 | Safety early warning method and system based on container state monitoring |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115479949A (en) | 2022-12-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108569607B (en) | Elevator fault early warning method based on bidirectional gating cyclic neural network | |
| CN107153914B (en) | System and method for evaluating automobile operation risk | |
| CN111486893A (en) | Bridge structure health monitoring and early warning system and early warning method | |
| Rizvi et al. | Crack detection in railway track using image processing | |
| CN106556498B (en) | Damage Identification Methods for Bridge Structures and system | |
| CN111896625A (en) | Real-time monitoring method and monitoring system for rail damage | |
| CN113467420B (en) | Method and device for detecting zone controller fault | |
| CN111444252A (en) | Bridge monitoring system | |
| CN115479949B (en) | Bridge safety monitoring and early warning method and system based on big data | |
| CN108170925A (en) | A kind of bridge damnification method for early warning based on arma modeling | |
| CN106198749B (en) | A kind of data fusion method of the multiple sensor based on Metal Crack monitoring | |
| CN108763966B (en) | Tail gas detection cheating supervision system and method | |
| CN106650113A (en) | Method for recognizing abnormal condition of bridge monitoring data based on fuzzy clustering | |
| CN113255188A (en) | Bridge safety early warning method and system based on accident tree | |
| CN111144485A (en) | Vehicle accident judgment method and system based on xgboost classification algorithm | |
| Yaman et al. | A vision based diagnosis approach for multi rail surface faults using fuzzy classificiation in railways | |
| Ghiasi et al. | An unsupervised anomaly detection framework for onboard monitoring of railway track geometrical defects using one-class support vector machine | |
| CN113538971A (en) | Risk ship detection method based on multi-source heterogeneous data fusion | |
| CN116380496B (en) | Automobile door fatigue endurance test method, system and medium | |
| Purnomo et al. | Initial implementation of structural health monitoring system of a railway bridge | |
| Zeng et al. | Rail break prediction and cause analysis using imbalanced in-service train data | |
| Asplund et al. | Assessment of the data quality of wayside wheel profile measurements. | |
| Vincent et al. | A Cognitive Rail Track Breakage Detection System Using Artificial Neural Network | |
| CN117345344B (en) | Intelligent prediction method and system for mine acoustic and electric signals | |
| CN115314401B (en) | Contact net state monitoring method and device, electronic equipment and storage medium |
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 |