CN109374631B - Tunnel state evaluation method - Google Patents

Tunnel state evaluation method Download PDF

Info

Publication number
CN109374631B
CN109374631B CN201811154974.XA CN201811154974A CN109374631B CN 109374631 B CN109374631 B CN 109374631B CN 201811154974 A CN201811154974 A CN 201811154974A CN 109374631 B CN109374631 B CN 109374631B
Authority
CN
China
Prior art keywords
data
tunnel
real
analysis result
detection
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
Application number
CN201811154974.XA
Other languages
Chinese (zh)
Other versions
CN109374631A (en
Inventor
杜翠
韩自力
马伟斌
安哲立
王志伟
李尧
许学良
柴金飞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Academy of Railway Sciences Corp Ltd CARS
Railway Engineering Research Institute of CARS
China State Railway Group Co Ltd
Original Assignee
China Academy of Railway Sciences Corp Ltd CARS
Railway Engineering Research Institute of CARS
China Railway Corp
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China Academy of Railway Sciences Corp Ltd CARS, Railway Engineering Research Institute of CARS, China Railway Corp filed Critical China Academy of Railway Sciences Corp Ltd CARS
Priority to CN201811154974.XA priority Critical patent/CN109374631B/en
Publication of CN109374631A publication Critical patent/CN109374631A/en
Application granted granted Critical
Publication of CN109374631B publication Critical patent/CN109374631B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84Systems specially adapted for particular applications
    • G01N21/88Investigating the presence of flaws or contamination
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N25/00Investigating or analyzing materials by the use of thermal means
    • G01N25/72Investigating presence of flaws
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/88Radar or analogous systems specially adapted for specific applications
    • G01S13/89Radar or analogous systems specially adapted for specific applications for mapping or imaging

Abstract

The invention discloses a tunnel state evaluating method, which comprises the following steps: establishing a tunnel information database; collecting tunnel related data and storing the data into the tunnel information database, wherein the tunnel related data comprises real-time monitoring data for risk tunnels, periodic/daily detection data for all tunnels, acceptance detection data for all tunnels and design construction data for all tunnels; analyzing the design construction data, the acceptance detection data, the periodic/daily detection data and/or the real-time monitoring data to generate a tunnel state analysis result; classifying and recombining the tunnel state analysis result according to the type of the tunnel state analysis result, the specific value of the object and the result parameter, and generating a tunnel state evaluation report matched with the user requirement.

Description

Tunnel state evaluation method
Technical Field
The invention relates to the field of rail transit, in particular to a tunnel state evaluation method.
Background
At present, tunnel diseases are mostly detected by devices such as a total station, a theodolite, a hydrostatic level and the like, when the tunnel diseases are detected, a special worker needs to hold the detection device by hand on a machine or a guide rail vehicle to detect the inner wall of the tunnel, and the tunnel diseases can be subjected to data acquisition by walking of the machine or the guide rail vehicle.
However, the existing method has the problems of poor stability, low timeliness, single data acquisition category and the like due to manual operation. Therefore, sudden tunnel diseases cannot be timely and accurately found in many application scenes. In addition, the acquired data cannot be directly applied, and the actual tunnel state can be determined only after manual analysis, so that the timeliness and the accuracy of detection are further reduced.
Disclosure of Invention
The invention provides a tunnel state evaluating method, which comprises the following steps:
establishing a tunnel information database;
collecting tunnel related data and storing the data into the tunnel information database, wherein the tunnel related data comprises real-time monitoring data for risk tunnels, periodic/daily detection data for all tunnels, acceptance detection data for all tunnels and design construction data for all tunnels;
analyzing the design construction data, the acceptance detection data, the periodic/daily detection data and/or the real-time monitoring data to generate a tunnel state analysis result;
classifying and recombining the tunnel state analysis result according to the type of the tunnel state analysis result, the specific value of the object and the result parameter, and generating a tunnel state evaluation report matched with the user requirement.
In one embodiment, the tunnel information database is designed by adopting a mixed architecture combining a relational database and a non-relational database.
In an embodiment, the tunnel information database includes a real-time data area, a big data area, an archived data area, and a sample data area.
In one embodiment, collecting and storing tunnel related data in the tunnel information database includes:
and carrying out data rapid processing on the design construction data, the acceptance detection data, the periodic/daily detection data and/or the real-time monitoring data according to data analysis requirements.
In one embodiment, analyzing the design construction data, the acceptance inspection data, the periodic/daily inspection data, and/or the real-time monitoring data to generate a tunnel state analysis result includes:
generating an initial state analysis result of the tunnel according to the design construction data and/or the acceptance detection data;
generating a tunnel period detection analysis result according to the period/daily detection data based on the tunnel initial state analysis result;
and generating a tunnel real-time monitoring analysis result according to the real-time monitoring data based on the tunnel initial state analysis result and/or the tunnel period detection analysis result.
In an embodiment, the risk tunnel is determined according to the tunnel initial state analysis result and/or the tunnel period detection analysis result.
In one embodiment, analyzing the design construction data, the acceptance inspection data, the periodic/routine inspection data, and/or the real-time monitoring data comprises:
and acquiring the analysis result of the defects, cracks and/or water leakage states of the lining structure of the tunnel, and identifying the tunnel diseases.
In one embodiment, acquiring a lining structure defect, crack and/or water leakage state analysis result of a tunnel, and identifying a tunnel defect, includes:
acquiring tunnel defect characteristics and historical sample data of the related design construction data, the acceptance detection data, the periodic/daily detection data and/or the real-time monitoring data;
performing model training based on the historical sample data to obtain an identification model between the design construction data, the acceptance detection data, the periodic/daily detection data and/or the real-time monitoring data and the tunnel defect;
and analyzing the state of the lining structure defects, cracks and/or water leakage of the tunnel based on the identification model according to the design construction data, the acceptance detection data, the periodic/daily detection data and/or the real-time monitoring data, and identifying the tunnel diseases.
In an embodiment, the method further comprises:
judging whether to perform early warning or not based on the tunnel state analysis result;
and when the early warning is needed, determining an early warning mode according to the tunnel state analysis result, wherein the early warning mode comprises the steps of storing a warning log in a background, actively outputting the early warning to background monitoring personnel and actively outputting the early warning to field workers.
In one embodiment, generating a tunnel status evaluation report matching the user requirement includes:
and determining tunnels/tunnel sections with correlation influence among the tunnels/tunnel sections, and generating an overall tunnel evaluation report.
According to the method, the tunnel state can be comprehensively and timely evaluated integrally, and compared with the prior art, the evaluation result has higher timeliness and accuracy, and the intuitiveness and the fineness of the evaluation result are effectively improved.
Additional features and advantages of the invention will be set forth in the description which follows. Also, some of the features and advantages of the invention will be apparent from the description, or may be learned by practice of the invention. The objectives and some of the advantages of the invention may be realized and attained by the process particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow diagram of a method according to an embodiment of the invention;
FIG. 2 is a simplified database structure according to an embodiment of the present invention;
FIGS. 3-5 are partial flow diagrams of methods according to various embodiments of the invention;
fig. 6 is a schematic diagram of an application scenario according to an embodiment of the present invention.
Detailed Description
The following detailed description will be provided for the embodiments of the present invention with reference to the accompanying drawings and examples, so that the practitioner of the present invention can fully understand how to apply the technical means to solve the technical problems, achieve the technical effects, and implement the present invention according to the implementation procedures. It should be noted that, as long as there is no conflict, the embodiments and the features of the embodiments of the present invention may be combined with each other, and the technical solutions formed are within the scope of the present invention.
At present, tunnel diseases are mostly detected by devices such as a total station, a theodolite, a hydrostatic level and the like, when the tunnel diseases are detected, a special worker needs to hold the detection device by hand on a machine or a guide rail vehicle to detect the inner wall of the tunnel, and the tunnel diseases can be subjected to data acquisition by walking of the machine or the guide rail vehicle.
However, the existing method has the problems of poor stability, low timeliness, single data acquisition category and the like due to manual operation. Therefore, sudden tunnel diseases cannot be timely and accurately found in many application scenes. In addition, the acquired data cannot be directly applied, and the actual tunnel state can be determined only after manual analysis, so that the timeliness and the accuracy of detection are further reduced.
Aiming at the problems in the prior art, the invention provides a tunnel state evaluation method. In the method, not only periodic detection data (such as artificial daily detection data and vehicle periodic detection data) but also real-time monitoring data (such as important monitoring data for a risk tunnel) are collected, so that the problem of poor timeliness caused by only depending on the periodic detection data is solved.
Furthermore, in the method, the initial acceptance detection data and the construction design data of the tunnel are also collected as the reference data and the comparison basis of analysis and evaluation, so that the accuracy and the comprehensiveness of the analysis and evaluation result are greatly improved.
Furthermore, in the method, the analysis of the monitoring/detection data is automatically carried out in real time, and when the user has a viewing demand, the analysis results are automatically combined to form a corresponding evaluation report according to the viewing demand of the user. Therefore, the waiting time for the user to check the evaluation report is greatly reduced, the pertinence of the evaluation report is improved, an evaluation result which meets the requirements better is provided for the user, and the working efficiency of the user is greatly improved.
According to the method, the tunnel state can be comprehensively and timely evaluated integrally, and compared with the prior art, the evaluation result has higher timeliness and accuracy, and the intuitiveness and the fineness of the evaluation result are effectively improved.
Next, an implementation process of the embodiment of the present invention is described in detail based on the flowchart. The steps shown in the flow chart of the figure may be performed in a computer system containing, for example, a set of computer executable instructions. Although a logical order of steps is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
As shown in fig. 1, in an embodiment, the evaluation method includes:
s110, establishing a tunnel information database;
s120, collecting tunnel related data and storing the data into a tunnel information database, wherein:
s121, collecting real-time monitoring data aiming at the risk tunnel and storing the real-time monitoring data into a tunnel information database;
s122, collecting periodic/daily detection data aiming at all tunnels and storing the periodic/daily detection data into a tunnel information database;
s123, collecting acceptance detection data aiming at all tunnels and storing the acceptance detection data into a tunnel information database;
s124, collecting design construction data aiming at all tunnels and storing the design construction data into a tunnel information database;
s130, analyzing design construction data, acceptance detection data, periodic/daily detection data and/or real-time monitoring data to generate a tunnel state analysis result;
and S140, classifying and recombining the tunnel state analysis results according to the type of the tunnel state analysis results, the specific values of the object and the result parameters, and generating a tunnel state evaluation report matched with the user requirements.
In the method of the invention, the tunnel related data comprises real-time monitoring data, periodic/daily detection data, acceptance detection data and design construction data. Due to the fact that the data are various in types and have long time span, some data among the types and the time nodes have relevance (for example, tunnel physical state detection results of linkage relation among the tunnel internal state monitoring data), and some data do not have relevance (for example, tunnel external video monitoring images and tunnel internal state monitoring data which only belong to the same tunnel label). Therefore, in one embodiment, the tunnel information database is designed using a hybrid architecture combining a relational database with a non-relational database.
Further, as shown in fig. 2, in an embodiment, the tunnel information database 200 includes a real-time data area 210, a big data area 220, an archive data area 230, and a sample data area 240.
Specifically, in one embodiment, the large data area is unprocessed raw data, after processing, the raw data is stored in the archive data area because the raw data is almost not accessed, and the processing result is stored in the real-time data area because of the query requirement.
Further, in one embodiment:
real time zone: the number of reading and writing times is large, and the reading and writing quantity is small.
A large data area: the number of reading and writing times is small, and the reading and writing quantity is large.
A filing area: the number of reading and writing times is small, the writing amount is large, and the storage capacity is large.
Sample area: the number of reading and writing times is large, the reading and writing quantity is small, and the data types are large.
Specifically, in an embodiment, the real-time data area stores data (real-time analysis results and intermediate data in an evaluation process) generated by each service module of a service application layer of the evaluation system, and monitoring data (environmental monitoring data in the real-time monitoring data, and video data in the real-time monitoring data is not placed in the area due to a large data volume) collected and transmitted in real time by the key monitoring.
The large data area stores original radar data to be processed acquired by acceptance detection, point cloud data to be processed and image data acquired by vehicle periodic detection and manual daily detection, and radar data and video data acquired by key monitoring. The original data has time labels, tunnel labels and mile labels.
The filing data area stores result data after data analysis processing.
The sample data area stores samples extracted from radar, point cloud, image and video data.
Furthermore, in the data acquisition process, the acquired data is not all valid data (for example, radar data, video data, and image data contain many data irrelevant to a tunnel) that can be used for analysis, and invalid data not only occupies a large data storage space but also interferes with the data analysis, thereby greatly slowing down the data analysis process and affecting the timeliness and accuracy of the data analysis result.
Therefore, in one embodiment, collecting and storing tunnel related data in a tunnel information database includes:
and carrying out data rapid processing on design construction data, acceptance detection data, periodic/daily detection data and/or real-time monitoring data according to data analysis requirements.
Specifically, in an embodiment, the radar data is subjected to the steps of early fourier transform, background denoising and the like, and the cluster computing environment of the cloud platform is utilized to perform fast processing in a parallel computing manner. Compression and image sampling are performed on video data, and compression and cropping are performed on image data.
Further, in one embodiment, the original radar data and the video data are stored in the archival data area by the valid data after the fast data processing.
Furthermore, because the design construction data and the acceptance detection data belong to disposable data, the data can not be changed after the design construction of the tunnel or the acceptance of the tunnel is finished, and the initial state of the tunnel can be reflected. And the periodic/daily detection data and the real-time monitoring data are changed along with the change of the tunnel state, which reflects the current state of the tunnel. Therefore, in one embodiment, the initial state of the tunnel is determined according to the design construction data and/or the acceptance inspection data, and the current state of the tunnel is determined by combining the initial state analysis period/daily inspection data and/or real-time monitoring data (for example, by adopting a contrast verification method) of the tunnel. Compared with the method that the current state of the tunnel is determined only by periodic/daily detection data and/or real-time monitoring data, the accuracy rate is greatly improved.
Further, the timeliness of the real-time monitoring data is far higher than that of the periodic/daily detection data. Therefore, in one embodiment, the real-time monitoring data is analyzed in real time, and the analysis result of the latest periodic/daily detection data is referred to during analysis, so that the accuracy of the analysis result of the real-time monitoring data is further improved.
Specifically, as shown in fig. 3, in an embodiment, analyzing design and construction data, acceptance and detection data, periodic/daily detection data, and/or real-time monitoring data to generate a tunnel state analysis result includes:
analyzing the design construction data and/or the acceptance check data (S311) to generate an initial state analysis result of the tunnel (S312);
generating a tunnel period detection analysis result (S322) based on the tunnel initial state analysis result analysis period/daily detection data (S321);
determining a non-risk tunnel state according to the tunnel period detection analysis result (S323);
analyzing the real-time monitoring data (S331) based on the tunnel initial state analysis result and the tunnel period detection analysis result to generate a tunnel real-time monitoring analysis result (S332);
and determining the state of the risk tunnel according to the real-time tunnel monitoring and analyzing result (S333).
Further, in an embodiment, the risk tunnel is determined according to the tunnel initial state analysis result and/or the tunnel period detection analysis result.
Furthermore, in many application scenarios, the purpose of tunnel detection is to predict tunnel diseases in advance or to find the tunnel diseases in time when the tunnel diseases occur, so that prevention or remediation can be performed as soon as possible. However, in the prior art, the advance, timeliness and effectiveness of tunnel disease identification are difficult to be ensured by adopting a manual analysis and identification mode. In view of the above problems, in one embodiment, the prediction and identification of tunnel defects are automatically performed in the process of analyzing design construction data, acceptance detection data, periodic/daily detection data, and/or real-time monitoring data.
Specifically, in an embodiment, analyzing design construction data, acceptance inspection data, periodic/daily inspection data, and/or real-time monitoring data includes: and acquiring the analysis result of the defects, cracks and/or water leakage states of the lining structure of the tunnel, and identifying the tunnel diseases.
Further, in order to improve the accuracy of tunnel defect prediction and identification, in an embodiment, a deep learning and data mining method is adopted. Specifically, as shown in fig. 4, in an embodiment, obtaining a lining structure defect, crack and/or water leakage state analysis result of a tunnel, and identifying a tunnel defect includes:
s410, acquiring historical sample data of tunnel defect characteristics and related design and construction data, acceptance detection data, periodic/daily detection data and/or real-time monitoring data;
s420, performing model training based on historical sample data to obtain a model for identifying design construction data, acceptance detection data, periodic/daily detection data and/or real-time monitoring data and tunnel defects;
and S430, analyzing the state of the lining structure defects, cracks and/or water leakage of the tunnel based on the identification model according to the design construction data, the acceptance detection data, the periodic/daily detection data and/or the real-time monitoring data, and identifying the tunnel diseases.
Specifically, in an embodiment, the historical sample data includes sample data of various diseases. Specifically, different types of sample data, such as cracks, exist for one type of disease, and the sample data includes linear array camera image data and three-dimensional scanning point cloud data.
Specifically, in one embodiment, the structural defects of the lining are input by radar images. Firstly, extracting radar image samples of various typical lining defects to establish a training sample library, extracting radar image characteristics of various types including time domain, frequency domain, time-frequency domain and associated disease characteristics (whether the position has an apparent disease, whether the lining thickness is insufficient and whether the steel reinforcement frame is insufficiently distributed), training by adopting a mode recognition technology such as deep learning or a support vector machine, and carrying out intelligent disease recognition by utilizing a trained model. Namely, the input is a radar image, and the output is a disease category.
And the cracks and the water leakage adopt a learning and training process similar to the defects of the lining structure. Establishing a sample base, extracting disease characteristics, training a model, and identifying by using the trained model. Specifically, the crack takes an image of the camera and point cloud data as input items. The leakage water takes the infrared image collected by the thermal infrared imager as an input item.
Further, in one embodiment, before training, there is a feature extraction step for training the model, which is not the original data, but features extracted from the data. For example, the tunnel lining structural defect, the sample source is a radar image, and some features such as variance, second moment, entropy and the like are extracted from the radar image.
Further, in an embodiment, further deep learning and data mining are performed for different types of diseases, and whether the diseases in different types have correlation is judged. For example, whether the apparent disease location is inherently defective or not. Whether internal defects will certainly cause apparent disease.
Further, in one embodiment, the result of identifying tunnel diseases is a list of various types of diseases, including starting mileage, ending mileage, and parameters (size, depth).
Further, in an embodiment, the result of the model identification needs to be manually reviewed.
Further, in one embodiment, the tunnel state is intelligently diagnosed based on all relevant data of the tunnel, so that a user can grasp the tunnel state from the whole body instead of monitoring the tunnel one-sidedly based on a certain aspect. Specifically, in one embodiment, the input items for intelligent diagnosis of tunnel state include structural defects, the existing number and density of apparent defects, and the historical development trend of defects; the diagnosis result is a certain length as an evaluation unit, the health status of each evaluation unit is graded, and a corresponding treatment proposal is suggested.
Further, in one embodiment, the final evaluation report is for multiple types of users with different permissions. Specifically, the user includes: management departments at all levels of the railway general/branch company and technicians at all levels. In order to ensure the pertinence of the evaluation report, the evaluation report of the tunnel contained in the corresponding region road section is generated according to different user subordinate units and authorities. And generating evaluation reports corresponding to different requirements according to the job types of different users.
Further, in an embodiment, the method further includes:
uploading and downloading detection data and tracking project progress for information such as entrusted units, detection tunnels, mileage, detection equipment, parameters, detection reports and the like of each project;
and establishing a file for each detected tunnel, wherein the file comprises information such as design data, geological data, construction units, operation units and the like, all detection items and detection data of the file are related, and the file also comprises disease information, treatment measures, treatment results and the like. Further, regions with important attention to diseases and regions with important attention to diseases are marked, and the development and change trends of the same diseases are tracked.
Specifically, in an embodiment, the evaluation report includes:
the tunnel detection project management report comprises information of entrusted units, detection tunnels and mileage, detection equipment and parameters, detection reports and the like of each project, and has the functions of uploading and downloading detection data and tracking project progress.
According to the tunnel health file management report, each detected tunnel establishes a file, the file comprises information of design data, geological data, construction units, operation units and the like, all detection items and detection data of the detected tunnel are related, disease information, treatment measures, treatment results and the like, diseases and regions with important attention can be marked, and the development and change trends of the same disease can be tracked.
The identification report of the lining defects comprises two parts of lining structure defects and apparent defects, and the data result is a disease list comprising disease types, starting and stopping mileage and parameters (crack length, cavity size and the like).
Further, in order to improve the timeliness for dealing with the tunnel abnormal condition, in an embodiment, the method further includes an automatic early warning step. Specifically, as shown in fig. 5, in one embodiment:
s510, judging whether to perform early warning or not based on the tunnel state analysis result;
s511, normally storing the tunnel state analysis result when the early warning is not needed;
s520, when early warning is needed, determining an early warning mode according to a tunnel state analysis result;
and S520, actively carrying out early warning.
Specifically, in one embodiment, the early warning mode is determined according to the severity of the disease and the solution mode. For example:
when the disease is not serious and does not need to be processed immediately, the background saves the warning log and reminds the user to look up;
when the disease is serious but the solution can not be judged, actively outputting early warning to background monitoring personnel;
when the serious disease needs to be solved immediately and timely by field personnel according to a preset solution, early warning is actively output to the field personnel.
In a specific application scenario, the architecture of the evaluation system according to the method of the present invention is shown in fig. 6.
Further, in an embodiment, the method further includes:
collecting disease treatment data of the tunnel and storing the disease treatment data into a tunnel information database;
and in the early warning process, treatment information of similar diseases is given, and reference is provided for formulation of a treatment scheme.
Further, in many application scenarios, multiple tunnels or sections of the same tunnel are not isolated, and have correlation. For this situation, in an embodiment, generating a tunnel status evaluation report matching the user requirement includes: and determining tunnels/tunnel sections with correlation influence among the tunnels/tunnel sections, and generating an overall tunnel evaluation report.
Specifically, in an embodiment, the overall tunnel evaluation report includes not only an overall tunnel state description, but also an overall solution description. For example, the current state of the target tunnel/tunnel segment is highlighted by a comparative description of the tunnel states of the tunnels/tunnel segments of adjacent positions or similar structures; the impact of remedial actions to be considered when remediating a target tunnel/tunnel segment on adjacent tunnels/tunnel segments; overall remediation schemes for multiple target tunnels/tunnel segments, etc.
It should be appreciated that reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Thus, the appearances of the phrase "one embodiment" or "an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment.
Although the embodiments of the present invention have been described above, the above description is only for the convenience of understanding the present invention, and is not intended to limit the present invention. There are various other embodiments of the method of the present invention. Various corresponding changes or modifications may be made by those skilled in the art without departing from the spirit of the invention, and these corresponding changes or modifications are intended to fall within the scope of the appended claims.

Claims (7)

1. A tunnel state evaluating method is characterized by comprising the following steps:
establishing a tunnel information database, wherein the tunnel information database comprises a real-time data area, a big data area, an archived data area and a sample data area;
collecting tunnel related data and storing the data into the tunnel information database, wherein the tunnel related data comprises real-time monitoring data aiming at the risk tunnel, periodic/daily detection data aiming at all tunnels, acceptance detection data aiming at all tunnels and design construction data aiming at all tunnels;
the real-time data area stores data generated by each service module of a service application layer of the evaluation system and focuses on monitoring and collects monitoring data transmitted in real time;
the large data area stores original radar data to be processed acquired by acceptance detection, point cloud data to be processed and image data acquired by vehicle periodic detection and manual daily detection, and radar data and video data acquired by key monitoring;
the filing data area stores result data after data analysis processing;
the sample data area stores samples extracted from radar, point cloud, image and video data;
analyzing the design construction data, the acceptance detection data, the periodic/daily detection data and the real-time monitoring data to generate a tunnel state analysis result; specifically, generating an initial state analysis result of the tunnel according to the design construction data and/or the acceptance detection data; generating a tunnel period detection analysis result according to the period/daily detection data based on the tunnel initial state analysis result; generating a tunnel real-time monitoring analysis result according to the real-time monitoring data based on the tunnel initial state analysis result and/or the tunnel period detection analysis result, wherein the tunnel real-time monitoring analysis result comprises the following steps: acquiring analysis results of the states of defects, cracks and water leakage of the lining structure of the tunnel, and identifying tunnel diseases; further deep learning and data mining are carried out aiming at different types of diseases, and whether the different types of diseases are related or not is judged;
classifying and recombining the tunnel state analysis result according to the type of the tunnel state analysis result, the specific value of the target and the result parameter to generate a tunnel state evaluation report matching the user requirement, wherein the final evaluation report is specific to multiple types of users with different rights.
2. The method of claim 1, wherein the tunnel information database is designed using a hybrid architecture combining a relational database and a non-relational database.
3. The method of claim 1, wherein collecting tunnel related data and storing in the tunnel information database comprises:
and carrying out data rapid processing on the design construction data, the acceptance detection data, the periodic/daily detection data and the real-time monitoring data according to data analysis requirements.
4. The method according to claim 1, wherein the risk tunnel is determined according to the tunnel initial state analysis result and/or the tunnel period detection analysis result.
5. The method of claim 1, wherein obtaining the analysis results of the lining structure defects, cracks and water leakage states of the tunnel and identifying tunnel diseases comprises:
acquiring tunnel defect characteristics and historical sample data of the related design construction data, the acceptance detection data, the periodic/daily detection data and the real-time monitoring data;
performing model training based on the historical sample data to obtain the design construction data, the acceptance detection data, the periodic/daily detection data, the real-time monitoring data and an identification model between the tunnel defects;
and analyzing the states of the defects, cracks and water leakage of the lining structure of the tunnel according to the design construction data, the acceptance detection data, the periodic/daily detection data and the real-time monitoring data based on the identification model, and identifying the tunnel diseases.
6. The method of claim 1, further comprising:
judging whether to perform early warning or not based on the tunnel state analysis result;
and when the early warning is needed, determining an early warning mode according to the tunnel state analysis result, wherein the early warning mode comprises the steps of storing a warning log in a background, actively outputting the early warning to background monitoring personnel and actively outputting the early warning to field workers.
7. The method according to claim 1, wherein generating a tunnel status evaluation report matching the user's requirements comprises:
and determining tunnels/tunnel sections with correlation influence among the tunnels/tunnel sections, and generating an overall tunnel evaluation report.
CN201811154974.XA 2018-09-30 2018-09-30 Tunnel state evaluation method Active CN109374631B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811154974.XA CN109374631B (en) 2018-09-30 2018-09-30 Tunnel state evaluation method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811154974.XA CN109374631B (en) 2018-09-30 2018-09-30 Tunnel state evaluation method

Publications (2)

Publication Number Publication Date
CN109374631A CN109374631A (en) 2019-02-22
CN109374631B true CN109374631B (en) 2021-06-29

Family

ID=65403329

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811154974.XA Active CN109374631B (en) 2018-09-30 2018-09-30 Tunnel state evaluation method

Country Status (1)

Country Link
CN (1) CN109374631B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110254478B (en) * 2019-06-05 2021-07-02 中国铁道科学研究院集团有限公司 Roadbed deformation disease identification method and device
CN111523543A (en) * 2020-04-21 2020-08-11 南京航空航天大学 Tunnel surface defect positioning method based on learning

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103473720A (en) * 2013-09-06 2013-12-25 上海大学 Shield tunnel construction management system based on BIM
CN103544556A (en) * 2013-09-06 2014-01-29 上海大学 Life-cycle management system and method for tunnels
CN104680579A (en) * 2015-03-02 2015-06-03 北京工业大学 Tunnel construction information monitoring system based on three-dimensional scanning point cloud
CN105631154A (en) * 2016-01-11 2016-06-01 中铁隧道集团有限公司 Method for viewing tunnel monitoring and measurement data on BIM (Building Information Modeling) construction management platform
CN106997588A (en) * 2017-03-24 2017-08-01 东北林业大学 Highway pavement based on Computer Image Processing, tunnel defect diagnostic system
CN107451622A (en) * 2017-08-18 2017-12-08 长安大学 A kind of tunnel operation state division methods based on big data cluster analysis
CN108005725A (en) * 2017-12-31 2018-05-08 上海纽建信息科技有限公司 A kind of structural healthy monitoring system for Shield Tunnel in Soft Soil

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103473720A (en) * 2013-09-06 2013-12-25 上海大学 Shield tunnel construction management system based on BIM
CN103544556A (en) * 2013-09-06 2014-01-29 上海大学 Life-cycle management system and method for tunnels
CN104680579A (en) * 2015-03-02 2015-06-03 北京工业大学 Tunnel construction information monitoring system based on three-dimensional scanning point cloud
CN105631154A (en) * 2016-01-11 2016-06-01 中铁隧道集团有限公司 Method for viewing tunnel monitoring and measurement data on BIM (Building Information Modeling) construction management platform
CN106997588A (en) * 2017-03-24 2017-08-01 东北林业大学 Highway pavement based on Computer Image Processing, tunnel defect diagnostic system
CN107451622A (en) * 2017-08-18 2017-12-08 长安大学 A kind of tunnel operation state division methods based on big data cluster analysis
CN108005725A (en) * 2017-12-31 2018-05-08 上海纽建信息科技有限公司 A kind of structural healthy monitoring system for Shield Tunnel in Soft Soil

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
基于BIM技术的铁路工程建设信息化全寿命周期管理研究;王万齐;《中国优秀硕士学位论文全文数据库 工程科技II辑》;20170215;摘要、章节1-5 *

Also Published As

Publication number Publication date
CN109374631A (en) 2019-02-22

Similar Documents

Publication Publication Date Title
US9365217B2 (en) Mobile pothole detection system and method
CN103512762B (en) Image processing method, device and train failure detection system
KR101536410B1 (en) Apparatus and method for managing of data in energy management system
CN109374631B (en) Tunnel state evaluation method
CN1806501B (en) Marine phytoplankton automatic distinguishing method and apparatus
US10937144B2 (en) Pipe feature identification using pipe inspection data analysis
CN110751451B (en) Laboratory big data management system
CN108711148A (en) A kind of wheel tyre defect intelligent detecting method based on deep learning
CN111598040A (en) Construction worker identity identification and safety helmet wearing detection method and system
CN105239608A (en) Landslide displacement prediction method based on wavelet transform-rough set-support vector regression (WT-RS-SVR) combination
CN102915432A (en) Method and device for extracting vehicle-bone microcomputer image video data
CN111368824A (en) Instrument identification method, mobile device and storage medium
CN202815869U (en) Vehicle microcomputer image and video data extraction apparatus
CN110633314A (en) Internet of vehicles data processing method and device
CN106840259A (en) Environmental monitoring system
CN111539358A (en) Working state determination method and device, computer equipment and storage medium
Hamici et al. Assessment of the effect of alligator cracking on pavement condition using WSN-image processing
CN111651753A (en) User behavior analysis system and method
CN111915026A (en) Fault processing method and device, electronic equipment and storage medium
KR20200002433A (en) Statistical quality control system and method using big data analysis
Yan et al. Revisiting the correlation between alerts and software defects: A case study on myfaces, camel, and cxf
KR102185225B1 (en) Method for detecting sinkhole using deep learning and data association and sinkhole detecting system using it
CN114548176A (en) Sample library updating method and device, electronic equipment and storage medium
CN113705547B (en) Dynamic management and control method and device for recognizing false behavior of environment blurring
Panella et al. Smart Image Based Technology and Deep Learning for Tunnel Inspection and Asset Management

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