CN110608711A - Method for predicting deformation of rail-crossing tunnel through big data - Google Patents
Method for predicting deformation of rail-crossing tunnel through big data Download PDFInfo
- Publication number
- CN110608711A CN110608711A CN201910730525.3A CN201910730525A CN110608711A CN 110608711 A CN110608711 A CN 110608711A CN 201910730525 A CN201910730525 A CN 201910730525A CN 110608711 A CN110608711 A CN 110608711A
- Authority
- CN
- China
- Prior art keywords
- data
- deformation
- period
- rail
- tunnel
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000009499 grossing Methods 0.000 claims abstract description 17
- 238000010801 machine learning Methods 0.000 claims abstract description 4
- 238000012544 monitoring process Methods 0.000 claims description 10
- 238000004140 cleaning Methods 0.000 claims description 6
- 229910000831 Steel Inorganic materials 0.000 claims description 3
- 238000009412 basement excavation Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 3
- 230000003287 optical effect Effects 0.000 claims description 3
- 238000002360 preparation method Methods 0.000 claims description 3
- 239000010959 steel Substances 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 abstract description 2
- 238000012549 training Methods 0.000 abstract description 2
- 238000012502 risk assessment Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B21/00—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant
- G01B21/32—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant for measuring the deformation in a solid
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of tunnel maintenance, in particular to a method for predicting deformation of a rail-crossing tunnel through big data; a method for predicting deformation of a rail-traffic tunnel through big data comprises the following steps: s1 data acquisition and arrangement step, acquiring and arranging data related to deformation prediction; s2 unified scale; s3 machine learning modeling; deformation which is possibly generated in the future is predicted through daily monitored deformation data, and due to the adoption of an exponential smoothing method, a deformation predicted value in a certain time in the future can be established only through a small number of training samples and an automatic parameter value.
Description
Technical Field
The invention relates to the technical field of tunnel maintenance, in particular to a method for predicting deformation of a rail-crossing tunnel through big data.
Background
Because rail transit may need to pass through the tunnel, and the geological conditions in different areas differ greatly, industry tries to use big data to carry out risk assessment, and certainly mainly evaluates deformation. For example, chinese patent discloses a deep foundation pit monitoring risk assessment system and assessment method based on big data, application No. 201910162464.5. However, the method does not record a specific data processing method and a specific algorithm, and the skilled person cannot effectively predict the tunnel deformation according to the technical scheme.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a method for predicting the deformation of a rail-crossing tunnel through big data.
The technical scheme of the invention is as follows:
a method for predicting deformation of a rail transit tunnel through big data is characterized by comprising the following steps: it comprises the following steps:
s1 data acquisition and arrangement step, acquiring and arranging data related to deformation prediction;
in the data sorting step, data related to deformation prediction is collected and sorted, so that the corresponding deformation condition can be predicted through an algorithm.
Specifically, the data acquiring and sorting step includes the following steps:
s101, a data preparation step, namely acquiring data related to the use of the rail transit cable;
in this step, the deformation data includes monitoring data, and the monitoring data is collected once per second; the monitoring data are supporting stress and form deformation data collected by excavation supporting piles, underground continuous walls, inner supports, steel supports, sensing optical cables pre-buried in a bottom plate and FBG sensors.
s102, data arrangement, namely cleaning the data related to the deformation and constructing the cleaned data related to the deformation based on a time unit; the cleaning rules include: performing vacant assignment, error value removal and cross inspection; after the data are cleaned, data construction is carried out based on time units, namely, the collected data are integrated according to the time sequence; time units may be based on milliseconds, seconds, minutes, etc.;
s2 unified scale;
because data at different positions may be obtained by different sensing methods, it is meaningful to calculate the data uniformly on a dimensionless coordinate scale.
Specifically, let xijIs the original data, the new data after transformation is:
in the formulaAnd σjThe minimum value and the sample standard deviation of the jth variable are respectively.
s3 machine learning modeling;
the deformation data is far away from the current time, and obviously, the reference meaning is definitely not large when the data is close to the current time, so that the adaptability of the model is improved through exponential smoothing;
linear quadratic exponential smoothing equation:
St (1)＝aYt-1+(1-a)St-1 (1)
St (2)＝aSt (1)-(1-a)St-1 (2)
wherein St and St-1 are respectively the secondary exponential smoothing values of the accumulated deformation data in the t period and the t-1 period, a is a smoothing coefficient, Yt-1 is the single-period deformation value in the previous period of the t period, and under the condition that St (1) and St (2) are known, the prediction model of the secondary exponential smoothing method is as follows:
Ft+T＝at+btT
at＝2St (1)-St (2)
bt＝a(St (1)-St (2))/(1-a)
wherein T is the predicted lead period number, Ft-T is the deformation accumulated predicted value of the T-T period, and at and bt are parameters of T period data.
The invention has the beneficial effects that: deformation which is possibly generated in the future is predicted through daily monitored deformation data, and due to the adoption of an exponential smoothing method, a deformation predicted value in a certain time in the future can be established only through a small number of training samples and an automatic parameter value.
Drawings
FIG. 1 is a schematic structural diagram of the present invention.
Detailed Description
The following further describes embodiments of the present invention with reference to the accompanying drawings:
as shown in fig. 1, a method for predicting deformation of a rail transit tunnel through big data is characterized in that: it comprises the following steps:
s1 data acquisition and arrangement step, acquiring and arranging data related to deformation prediction;
in the data sorting step, data related to deformation prediction is collected and sorted, so that the corresponding deformation condition can be predicted through an algorithm.
Specifically, the data acquiring and sorting step includes the following steps:
s101, a data preparation step, namely acquiring data related to the use of the rail transit cable;
in this step, the deformation data includes monitoring data, and the monitoring data is collected once per second; the monitoring data are supporting stress and form deformation data collected by excavation supporting piles, underground continuous walls, inner supports, steel supports, sensing optical cables pre-buried in a bottom plate and FBG sensors.
s102, data arrangement, namely cleaning the data related to the deformation and constructing the cleaned data related to the deformation based on a time unit; the cleaning rules include: performing vacant assignment, error value removal and cross inspection; after the data are cleaned, data construction is carried out based on time units, namely, the collected data are integrated according to the time sequence; time units may be based on milliseconds, seconds, minutes, etc.;
s2 unified scale;
because data at different positions may be obtained by different sensing methods, it is meaningful to calculate the data uniformly on a dimensionless coordinate scale.
Specifically, let xijIs the original data, the new data after transformation is:
in the formulaAnd σjRespectively, the minimum sum of the j variableSample standard deviations.
s3 machine learning modeling;
the deformation data is far away from the current time, and obviously, the reference meaning is definitely not large when the data is close to the current time, so that the adaptability of the model is improved through exponential smoothing;
linear quadratic exponential smoothing equation:
St (1)＝aYt-1+(1-a)St-1 (1)
St (2)＝aSt (1)-(1-a)St-1 (2)
wherein St and St-1 are respectively the secondary exponential smoothing values of the accumulated deformation data in the t period and the t-1 period, a is a smoothing coefficient, Yt-1 is the single-period deformation value in the previous period of the t period, and under the condition that St (1) and St (2) are known, the prediction model of the secondary exponential smoothing method is as follows:
Ft+T＝at+btT
at＝2St (1)-St (2)
bt＝a(St (1)-St (2))/(1-a)
wherein T is the predicted lead period number, Ft-T is the deformation accumulated predicted value of the T-T period, and at and bt are parameters of T period data.
In this embodiment, the value of the smoothing parameter a obviously plays an important role, and reflects the closeness of the predicted value and the actual measured value, so how to give this value will have a decisive influence on the whole prediction activity, and the method adopted in this embodiment is as follows: and confirming the value of a by using the research result of the predecessor.
The foregoing embodiments and description have been presented only to illustrate the principles and preferred embodiments of the invention, and various changes and modifications may be made therein without departing from the spirit and scope of the invention as hereinafter claimed.
Claims (3)
1. A method for predicting deformation of a rail transit tunnel through big data is characterized by comprising the following steps: it comprises the following steps:
s1 data acquisition and arrangement step, acquiring and arranging data related to deformation prediction;
s2 unified scale;
s3 machine learning modeling;
linear quadratic exponential smoothing equation:
St (1)＝aYt-1+(1-a)St-1 (1)
St (2)＝aSt (1)-(1-a)St-1 (2)
wherein St and St-1 are respectively the secondary exponential smoothing values of the accumulated deformation data in the t period and the t-1 period, a is a smoothing coefficient, Yt-1 is the single-period deformation value in the previous period of the t period, and under the condition that St (1) and St (2) are known, the prediction model of the secondary exponential smoothing method is as follows:
Ft+T＝at+btT
at＝2St (1)-St (2)
bt＝a(St (1)-St (2))/(1-a)
wherein T is the predicted lead period number, Ft-T is the deformation accumulated predicted value of the T-T period, and at and bt are parameters of T period data.
2. The method for predicting deformation of the rail-to-rail tunnel through big data according to claim 1, wherein: the data acquisition and sorting step comprises the following processes:
s101, a data preparation step, namely acquiring data related to the use of the rail transit cable;
in this step, the deformation data includes monitoring data, and the monitoring data is collected once per second; the monitoring data are supporting stress and form deformation data collected by excavation supporting piles, underground diaphragm walls, inner supports, steel supports, sensing optical cables pre-buried in a bottom plate and FBG sensors;
s102, data arrangement, namely cleaning the data related to the deformation and constructing the cleaned data related to the deformation based on a time unit; the cleaning rules include: performing vacant assignment, error value removal and cross inspection; after the data are cleaned, data construction is carried out based on time units, namely, the collected data are integrated according to the time sequence; time units may be based on milliseconds, seconds, minutes, and the like.
3. The method for predicting deformation of the rail-to-rail tunnel through big data according to claim 1, wherein:
specifically, let xijIs the original data, the new data after transformation is:
in the formulaAnd σjThe minimum value and the sample standard deviation of the jth variable are respectively.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910730525.3A CN110608711A (en) | 2019-08-08 | 2019-08-08 | Method for predicting deformation of rail-crossing tunnel through big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910730525.3A CN110608711A (en) | 2019-08-08 | 2019-08-08 | Method for predicting deformation of rail-crossing tunnel through big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110608711A true CN110608711A (en) | 2019-12-24 |
Family
ID=68889959
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910730525.3A Pending CN110608711A (en) | 2019-08-08 | 2019-08-08 | Method for predicting deformation of rail-crossing tunnel through big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110608711A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112836789A (en) * | 2020-12-27 | 2021-05-25 | 苏州大学 | Ground connection wall deformation dynamic prediction method based on composite neural network algorithm |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107273985A (en) * | 2017-05-04 | 2017-10-20 | 吉林大学 | The numerical characteristic measure and system of a kind of geologic body |
| CN107453396A (en) * | 2017-08-02 | 2017-12-08 | 安徽理工大学 | A kind of Multiobjective Optimal Operation method that distributed photovoltaic power is contributed |
| CN107858883A (en) * | 2017-11-29 | 2018-03-30 | 北京交通大学 | A kind of rail system safe condition comprehensive monitoring and intelligent analysis method |
-
2019
- 2019-08-08 CN CN201910730525.3A patent/CN110608711A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107273985A (en) * | 2017-05-04 | 2017-10-20 | 吉林大学 | The numerical characteristic measure and system of a kind of geologic body |
| CN107453396A (en) * | 2017-08-02 | 2017-12-08 | 安徽理工大学 | A kind of Multiobjective Optimal Operation method that distributed photovoltaic power is contributed |
| CN107858883A (en) * | 2017-11-29 | 2018-03-30 | 北京交通大学 | A kind of rail system safe condition comprehensive monitoring and intelligent analysis method |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112836789A (en) * | 2020-12-27 | 2021-05-25 | 苏州大学 | Ground connection wall deformation dynamic prediction method based on composite neural network algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2020262969B2 (en) | Detection of structural anomalies in a pipeline network | |
| JP6949060B2 (en) | Systems and methods for rapid prediction of hydrogen-induced cracking (HIC) in pipelines, pressure vessels and piping systems and for taking action on it. | |
| CN107895014B (en) | Time series bridge monitoring data analysis method based on MapReduce framework | |
| CN111141517B (en) | Fan fault diagnosis method and system | |
| CN112685950B (en) | Method, system and equipment for detecting abnormality of ocean time sequence observation data | |
| CN111027193A (en) | Short-term water level prediction method based on regression model | |
| CN111611294B (en) | Star sensor data anomaly detection method | |
| CN114002334A (en) | Structural damage acoustic emission signal identification method and device and storage medium | |
| CN116308211B (en) | Enterprise intelligent management system and method based on big data | |
| CN116651971A (en) | Online detection method and system for automobile stamping die | |
| CN110608711A (en) | Method for predicting deformation of rail-crossing tunnel through big data | |
| CN116822115A (en) | Environment management method and system for intelligent park based on digital twin technology | |
| CN109598309B (en) | Detection system and monitoring method of metal packaging punching machine | |
| CN111062827B (en) | Engineering supervision method based on artificial intelligence mode | |
| CN107506832B (en) | Hidden danger mining method for assisting monitoring tour | |
| US11906678B2 (en) | Seismic observation device, seismic observation method, and recording medium on which seismic observation program is recorded | |
| CN115063337A (en) | Intelligent maintenance decision-making method and device for buried pipeline | |
| CN110726542B (en) | Analysis method for fatigue life of spring | |
| CN116328004B (en) | Cleaning and disinfecting method and system for medicine production equipment | |
| CN116775741A (en) | Auditing method and related device for completion resolution of engineering | |
| CN116070105A (en) | Combined beam damage identification method and system based on wavelet transformation and residual error network | |
| CN114155072B (en) | Financial prediction model construction method and system based on big data analysis | |
| CN111368257B (en) | Analysis and prediction method and device for coal-to-electricity load characteristics | |
| Shahsavari et al. | Structural health monitoring of a vertical lift bridge using vibration data | |
| Ojeda | MATLAB implementation of an operational modal analysis technique for vibration-based structural health monitoring |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191224 |