CN109779649A - Shield driving axis real-time deviation correcting system and method based on big data - Google Patents
Shield driving axis real-time deviation correcting system and method based on big data Download PDFInfo
- Publication number
- CN109779649A CN109779649A CN201910112244.1A CN201910112244A CN109779649A CN 109779649 A CN109779649 A CN 109779649A CN 201910112244 A CN201910112244 A CN 201910112244A CN 109779649 A CN109779649 A CN 109779649A
- Authority
- CN
- China
- Prior art keywords
- module
- data
- oil pressure
- shield
- construction
- 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
Landscapes
- Excavating Of Shafts Or Tunnels (AREA)
Abstract
The invention discloses a kind of shield driving axis real-time deviation correcting system and method based on big data, system includes data preprocessing module, track policy module, oil pressure gesture module, oil pressure optimization module, real-time monitoring module and automatic study module, the big data that can be acquired based on construction site considers to influence the factor of shield attitude variation, track policy module provides the target position of next construction cell, subregion oil pressure value needed for oil pressure gesture module exports arrival target position according to target position；Considering shield oil pressure simultaneously allows output area, optimizes to the oil cylinder pressure theoretical value of system-computed；When the model calculation occurs abnormal, emergency-stop signal is exported.For method for correcting error compared with general axis line control method, the factor that not only can comprehensively consider influence shield axial line control guarantees that correction process will not cause the disturbance of surrounding soil, but also considers the stability of model, and emergency trouble shooting measures are arranged.
Description
Technical field
The present invention relates to shield machine control technology fields, more particularly to the shield driving axis real-time deviation correcting based on big data
System and method.
Background technique
In shield machine tunneling process, the control effect of driving attitude is the key that influence one of constructing tunnel quality.Due to
Underground environment situation is complicated in Analysis on Shield Tunnel Driven Process, has multiple coupled property between construction parameter, so establishing construction environment ginseng
It counts and the shield attitude amount of directly controlling --- the mathematical model between oil pressure amount is extremely difficult.The side of common shield axial line control
Method point has following three classes:
(1) the axis method for correcting error based on fitting of a polynomial propulsion track
The axial line control method deviation posture current according to shield based on track is promoted with fitting of a polynomial, use is multinomial
Formula fits the track that shield returns Tunnel Design axis.The characteristic for following fitting track qualitatively provides shield structure jack oil
The allocation plan of cylinder pressure instructs shield driver to carry out axis correction.
(2) to load the axis method for correcting error based on carrying out force analysis to shield machine
Force analysis is carried out by the load to shield machine, establishes kinetics equation and the kinematics side of attitude of shield machine
Journey.According to the deviation value of shield attitude, the oil pressure value of shield structure jack needed for posture is rectified a deviation is exported.
(3) the axial line control method based on fuzzy control
Axial line control method based on fuzzy control is accumulated according to construction experience, mostly with shield attitude correction amount or thousand
Jin top oil pressure value establishes the rule list of axis correction as controlled device, obtains the fuzzy controller of axis correction.
But above-mentioned three classes method is based on geometrical fit or construction experience more, considers that the factor for influencing to promote is more unilateral,
Do not account for whether shield correction process can cause surrounding soil to disturb and whether model output value is no more than shield machine
Oil pressure valve maximum opening, controller are directed to the emergency measure to abnormal conditions.So this above method practical application is caused to be imitated
Fruit is poor.
In view of this, nowadays there is an urgent need to design a kind of new shield driving axis real-time deviation correcting system and method, with gram
Take the drawbacks described above of existing method.
Summary of the invention
For overcome the deficiencies in the prior art, the purpose of the present invention is to provide the shield driving axis based on big data is real
When deviation-rectifying system and method.
The purpose of the present invention is implemented with the following technical solutions:
Shield driving axis real-time deviation correcting system based on big data, including data preprocessing module, track policy module,
Oil pressure gesture module, oil pressure optimization module, real-time monitoring module and automatic study module；The real-time monitoring module includes whole station
Instrument, prism and gyroscope, the real-time monitoring module are used for real-time detection construction data, and the construction data includes shield machine
Attitude data and Tunnel Design axis data；Big data of the system based on real-time monitoring module acquisition construction site, by described
Data preprocess module, track policy module, oil pressure gesture module, oil pressure optimization module and automatic study module calculate shield machine
Rated hydraulic data needed for axis correction each subregion jack of process, while the maximum oil pressure value allowed according to shield machine, to institute
Rated hydraulic data is stated to optimize；When calculated result appearance exception, i.e. when attitude of shield machine, which deviates design axis, exceeds threshold value,
Export emergency-stop signal.
Preferably, the data preprocessing module receive construction data and to construction data be removed outlier processing and
Low-and high-frequency data fusion.
Preferably, wherein high-frequency data is shield machine operating parameter, including cutter head of shield machine torque, cutterhead revolving speed, propulsion
Speed, subregion jack stroke, gross thrust, subregion oil pressure valve opening, subregion output oil pressure value, the horizontal direction of notch are inclined
Difference, notch vertical direction deviation, the horizontal direction deviation of shield tail, the vertical direction deviation of shield tail, the shield angle of gradient and excavation face
Soil pressure；Low-frequency data includes Tunnel Design axis coordinate, gap of the shield tail and the excavation face soil texture information with low frequency characteristic；With
Construction cell is at equal intervals, high-frequency data to be corresponded to low-frequency data and carries out data fusion, so that every record of fused data contains
There is the shield machine operation data of high frequency to correspond to the construction information of low frequency characteristic.
Preferably, the track policy module receives the data of data preprocessing module processing, exports next construction cell
The targeted attitude position that shield machine reaches.
Preferably, the targeted attitude position includes the horizontal direction deviation of notch, notch vertical direction deviation, shield tail
The vertical direction deviation of horizontal direction deviation and shield tail.
Preferably, the control echo signal of the oil pressure gesture module receiving locus policy module transmission, exports with current
Oil cylinder working-pressure theoretical value needed for fltting speed reaches each subregion jack in targeted attitude position at the end of next construction cell.
Preferably, the oil pressure optimization module optimizes the oil cylinder working-pressure theoretical value that oil pressure gesture module exports, when
When oil cylinder working-pressure theoretical value is more than the regulation characteristic of shield machine jack oil pressure, based on descending method in proportion to subregion oil pressure into
Row optimization distribution, output meet the oil pressure value of shield oil pressure allowed band.
Preferably, the automatic study module includes the LSTM self learning model and corresponding oil pressure of corresponding track policy module
The BP neural network self learning model of gesture module, the automatic study module receive history construction data and data prediction mould
Block conveying currentlys propel the new construction data of process, is rolled by LSTM self learning model and BP neural network self learning model
Training improves the counting accuracy of targeted attitude position and oil cylinder working-pressure theoretical value.
Preferably, the automatic study module updates the K construction cell in interval, and K value is selected as 60.
A kind of method for correcting error according to above system, comprising:
Construction big data is obtained, real-time monitoring module acquisition construction big data is passed through based on construction site；
Data prediction, the construction big data that data preprocessing module obtains, which removes exceptional value and carries out low-and high-frequency data, melts
It closes；Exceptional value is removed using formula dkq-dkq+1≤100, wherein d is deviation；{ notch is horizontal, and notch is vertical, shield tail by k=
Level, shield tail are vertical }；Q is current q-th of construction cell；Using the relative coordinate of every ring design axis as median, according to preceding
One ring terminates the construction cell number for locating relative coordinate and every ring includes, and carries out linear interpolation:
Wherein, (xab, yab, zab) be b-th of construction cell of a ring space relative coordinate, (xa-1, ya-1, za-1) it is the
Space relative coordinate at the construction cell of a-1 ring end, m are the number of construction cell contained by every ring, (xam/2, yam/2, zam/2) be
In a ring in the m/2 construction cell space relative coordinate, that is, low-frequency data every ring Tunnel Design axis coordinate；
It calculates and exports the targeted attitude position that next construction cell shield machine reaches, track policy module receives data and locates in advance
The data of resume module are managed, the targeted attitude position includes the horizontal direction deviation of notch, notch vertical direction deviation, shield tail
Horizontal direction deviation and shield tail vertical direction deviation；
Oil cylinder working-pressure theoretical value is calculated, oil pressure gesture module is transmitted according to the receiving locus policy module of targeted attitude position
Control echo signal, it is very heavy that output reaches each subregion in targeted attitude position to currently propel speed at the end of next construction cell
Oil cylinder working-pressure theoretical value needed for top；
Optimize oil cylinder working-pressure theoretical value, oil pressure optimization module carries out the oil cylinder working-pressure theoretical value that oil pressure gesture module exports
Optimization, optimizes distribution to subregion oil pressure based on descending method in proportion, i.e., very heavy beyond shield when oil cylinder working-pressure theoretical value
When pushing up the maximum oil pressure value allowed, subregion oil pressure maximum theoretical is zoomed to the maximum value of shield oil pressure permission, other are each
Subregion oil pressure theoretical value is scaled in proportion according to the scaling, and the suggestion oil for meeting jack oil pressure range is exported with this
Pressure value；
Automatic study module carries out track policy module and oil pressure gesture module according to the new data that construction site generates
Roll training, the accuracy that hoisting module calculates；
Abnormal signal emergent management, when the shield machine shield body central point of calculating, which deviates design axial line distance D, is more than threshold value,
Export emergency-stop signal.
Compared with prior art, the beneficial effects of the present invention are the shield picks that the present invention provides a kind of based on big data
Into axis real-time deviation correcting system and method for correcting error, the big data that can be acquired based on construction site is complete using data driven technique
The considerations of face, influences the factor of shield attitude variation, and track policy module can provide the target position of next construction cell, oil
The setting value of subregion oil pressure needed for pressing gesture module to export arrival target position according to target position；Shield machine oil is considered simultaneously
The regulation characteristic of pressure valve optimizes the oil pressure theoretical value of system-computed；When the model calculation occurs abnormal, output
Emergency-stop signal.For method for correcting error compared with general axis line control method, not only can comprehensively consider influences shield axis
The factor of control guarantees that correction process will not cause the disturbance of surrounding soil, and considers the stability of model, setting emergency
Treatment measures.
Detailed description of the invention
Fig. 1 is the shield driving axis real-time deviation correcting system schematic based on big data；
Fig. 2 is the corresponding LSTM self learning model of track policy module；
Fig. 3 is the corresponding BP neural network self learning model of oil pressure gesture module；
Fig. 4 is the schematic diagram that shield machine shield body central point deviates design axial line distance D.
Specific embodiment
With reference to the attached drawing in the embodiment of the present invention, technical solution in the embodiment of the present invention carries out clear, complete
Ground description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Based on this
Embodiment in invention, every other reality obtained by those of ordinary skill in the art without making creative efforts
Example is applied, shall fall within the protection scope of the present invention.
It should be noted that it can be directly on another component when component is referred to as " being fixed on " another component
Or there may also be components placed in the middle.When a component is considered as " connection " another component, it, which can be, is directly connected to
To another component or it may be simultaneously present component placed in the middle.When a component is considered as " being set to " another component, it
It can be and be set up directly on another component or may be simultaneously present component placed in the middle.Term as used herein is " vertical
", " horizontal ", "left", "right" and similar statement for illustrative purposes only.
Unless otherwise defined, all technical and scientific terms used herein and belong to technical field of the invention
The normally understood meaning of technical staff is identical.Term as used herein in the specification of the present invention is intended merely to description tool
The purpose of the embodiment of body, it is not intended that in the limitation present invention.Term " and or " used herein includes one or more phases
Any and all combinations of the listed item of pass.
A kind of shield driving axis real-time deviation correcting system based on big data, what which can be acquired based on construction site
Big data, the factor of shield attitude variation is influenced using the comprehensive consideration of data driven technique, and integrating tunnel designs the spy of axis
Oil pressure value needed for point more accurately calculates axis correction each subregion jack of process ensure that shield correction process will not be right
Surrounding soil generates biggish disturbance, while according to the regulation characteristic of shield machine oil pressure valve, theoretical to the oil pressure of system-computed
Value optimizes；When the model calculation occurs abnormal, emergency-stop signal is exported.Concrete scheme is as follows.
A kind of new shield driving axis real-time deviation correcting system, referring to Fig. 1, system includes:
Data preprocessing module construction data is removed exceptional value, and carries out low-and high-frequency data fusion.By to this
Module input have the cutter head of shield machine torque of high frequency characteristics, cutterhead revolving speed, fltting speed, subregion jack stroke, gross thrust,
Subregion oil pressure valve opening, notch/shield tail level/vertical direction deviation, the shield angle of gradient, is excavated subregion output oil pressure value
The shields operating parameter such as face soil pressure, and the Tunnel Design axis coordinate with low frequency characteristic, gap of the shield tail, excavation face soil property
Information is obtained with construction cell as equally spaced fused data, and every record of the fused data contains high-frequency operation data institute
Corresponding low frequency construction information.
As a preferred solution of the present invention, whether data preprocessing module is more than setting according to shield change of error amount
Threshold value (100mm) removes abnormal data.
Dkq-dkq+1≤100 --- formula (1)
Wherein, d is deviation；K={ notch is horizontal, and notch is vertical, and shield tail is horizontal, and shield tail is vertical }；Q is current q-th
Construction cell.
As a preferred solution of the present invention, Tunnel Design axis coordinate and high frequency of the low-and high-frequency data fusion low frequency
Construction environment data and the shield operation data of high frequency merged.Wherein using the relative coordinate of every ring design axis in
Digit terminates the construction cell number for locating relative coordinate and every ring includes according to previous ring, carries out linear interpolation.
Wherein (xab,yab,zab) be b-th of construction cell of a ring space relative coordinate, (xa-1,ya-1,za-1) it is a-
Space relative coordinate at 1 ring end construction cell, m are the number of construction cell contained by every ring, (xam/2,yam/2,zam/2) it is the
In a ring in the m/2 construction cell space relative coordinate, that is, low-frequency data every ring Tunnel Design axis coordinate.
Track policy module exports next construction cell shield machine according to the data that initial data preprocessing module is handled
The targeted attitude position of arrival.By inputting current cutter head of shield machine torque, cutterhead revolving speed, fltting speed, subregion to the module
Jack stroke, gross thrust, subregion oil pressure valve opening, subregion output oil pressure value, notch/shield tail level/vertical direction are inclined
The ginseng such as difference, the shield angle of gradient, excavation face soil pressure, Tunnel Design axis changes in coordinates amount, gap of the shield tail, excavation face soil texture information
Number, track policy module directly export shield machine and answer in next construction cell, notch and shield tail in horizontal and vertical direction deviation
When the target position being adjusted to.
Therefore, the input feature vector of track policy module are as follows: current cutter head of shield machine torque, fltting speed, divides cutterhead revolving speed
Area's jack stroke, gross thrust, subregion oil pressure valve opening, subregion output oil pressure value, notch/shield tail level/vertical direction
Deviation, the shield angle of gradient, excavation face soil pressure, Tunnel Design axis changes in coordinates amount, gap of the shield tail, excavation face soil texture information；
The output feature of track policy module are as follows: shield machine is answered in next construction cell, notch/shield tail level/vertical direction deviation
When the targeted attitude position being adjusted to.
As a preferred solution of the present invention, track policy module is trained using LSTM self learning model, training
Model basic structure is shown in attached drawing 2.
Wherein, it is 1 layer that the time step of the single sample of LSTM self learning model, which is 12, LSTM layers,.
Oil pressure gesture module exports shield machine according to the target position that track policy module obtains to currently propel speed
Oil cylinder working-pressure theoretical value needed for reaching targeted attitude position at the end of next construction cell.By inputting shield to the module
The machine target position that notch/shield tail level/vertical direction deviation should be adjusted at the end of next construction cell, oil pressure appearance
Morphotype block exports shield machine, and to reach each subregion in targeted attitude position to currently propel speed at the end of next construction cell very heavy
Oil cylinder working-pressure theoretical value needed for top.
Specifically, when the oil pressure theoretical value of oil pressure gesture module output is more than the regulation characteristic of shield machine jack oil pressure
When, oil pressure optimization module is based on descending method in proportion and optimizes to the distribution of subregion oil pressure, exports the oil with enforceability
Pressure value.
Therefore, the input feature vector of oil pressure gesture module are as follows: currently propel speed and reach mesh at the end of next construction cell
Oil cylinder working-pressure needed for marking posture position.By inputting shield machine notch/shield tail at the end of next construction cell to the module
The target position that should be adjusted to of level/vertical direction deviation；The output feature of oil pressure gesture module are as follows: shield machine is with current
Oil cylinder working-pressure theoretical value needed for fltting speed reaches each subregion jack in targeted attitude position at the end of next construction cell.
As a preferred solution of the present invention, BP neural network self learning model is carried out to oil pressure gesture module to instruct
Practice, the basic structure of BP neural network self learning model is shown in attached drawing 3.
Oil pressure optimization module optimizes the oil cylinder working-pressure theoretical value that oil pressure gesture module exports, and complies with shield machine
The regulation characteristic of oil cylinder.Pass through oil cylinder working-pressure theoretical value needed for inputting each subregion jack to the module, oil pressure optimization module
The regulation characteristic for whether meeting shield oil cylinder to required oil pressure theoretical value verifies, and manages the oil pressure for not meeting regulation characteristic
It is optimized by value, complies with shield oil cylinder regulation characteristic.
System monitors shield attitude and Tunnel Design axis in real time, exceeds when attitude of shield machine deviates design axis
When threshold value, stopping signal is exported.
Automatic study module carries out track policy module and oil pressure gesture module according to the new data that construction site generates
Roll training, the accuracy that hoisting module calculates.By being spaced K construction cell, produced to module input is new compared with last time training
Raw shield supplemental characteristic carries out background update to track policy module and oil pressure gesture module, to improve the calculating essence of model
Degree.
As a preferred solution of the present invention, construction cell is selected as the advance distance of 100mm.
As a preferred solution of the present invention, automatic study module updates the K construction cell in interval, and K value is selected as 60.
As a preferred solution of the present invention, deviate whether design axial line distance D surpasses according to shield machine shield body central point
It crosses threshold value 30mm to judge whether to export emergency-stop signal, sees attached drawing 4.
As a preferred solution of the present invention, the automatic study module is based on a large amount of history construction data and current
The new construction data of progradation, using track policy module and the input of oil pressure gesture module, output feature as neural network
Input, output variable is trained respectively.Due to constantly there is new construction data to be added in the training of neural network, so
Under the action of automatic study module, the output prograin of track policy module and oil pressure gesture module can be improved constantly.
Correspondingly, present invention also provides a kind of method for correcting error according to above system, method includes:
Construction big data is obtained, real-time monitoring module acquisition construction big data is passed through based on construction site.
Data prediction, the construction big data that data preprocessing module obtains, which removes exceptional value and carries out low-and high-frequency data, melts
It closes；Exceptional value is removed using formula dkq-dkq+1≤100, wherein d is deviation；{ notch is horizontal, and notch is vertical, shield tail by k=
Level, shield tail are vertical }；Q is current q-th of construction cell；Using the relative coordinate of every ring design axis as median, according to preceding
One ring terminates the construction cell number for locating relative coordinate and every ring includes, and carries out linear interpolation:
Wherein, (xab, yab, zab) be b-th of construction cell of a ring space relative coordinate, (xa-1, ya-1, za-1) it is the
Space relative coordinate at the construction cell of a-1 ring end, m are the number of construction cell contained by every ring, (xam/2, yam/2, zam/2) be
In a ring in the m/2 construction cell space relative coordinate, that is, low-frequency data every ring Tunnel Design axis coordinate.
It calculates and exports the targeted attitude position that next construction cell shield machine reaches, track policy module receives data and locates in advance
The data of resume module are managed, the targeted attitude position includes the horizontal direction deviation of notch, notch vertical direction deviation, shield tail
Horizontal direction deviation and shield tail vertical direction deviation.
Oil cylinder working-pressure theoretical value is calculated, oil pressure gesture module is transmitted according to the receiving locus policy module of targeted attitude position
Control echo signal, it is very heavy that output reaches each subregion in targeted attitude position to currently propel speed at the end of next construction cell
Oil cylinder working-pressure theoretical value needed for top.
Optimize oil cylinder working-pressure theoretical value, oil pressure optimization module carries out the oil cylinder working-pressure theoretical value that oil pressure gesture module exports
Optimization, when oil cylinder working-pressure theoretical value is more than the regulation characteristic of shield machine jack oil pressure, based on descending method in proportion to point
Area's oil pressure optimizes distribution, and exporting has the enforceability oil pressure value for meeting regulation characteristic.
Automatic study module carries out track policy module and oil pressure gesture module according to the new data that construction site generates
Roll training, the accuracy that hoisting module calculates.
Abnormal signal emergent management, when the shield machine shield body central point of calculating, which deviates design axial line distance D, is more than threshold value,
Export emergency-stop signal.
This method compared with general axis line control method, not only can comprehensively consider influence shield axial line control because
Element guarantees that correction process will not cause the disturbance of surrounding soil, and considers the stability of model, and emergency trouble shooting measures are arranged.
The aforementioned description to specific exemplary embodiment of the invention is in order to illustrate and illustration purpose.These descriptions
It is not wishing to limit the invention to disclosed precise forms, and it will be apparent that a variety of reorganizations can be carried out according to appeal introduction
And variation.The purpose of selecting and describing the exemplary embodiment is that explaining specific principle of the invention and its actually answering
With so that those skilled in the art can be realized and utilize a variety of different exemplary implementation schemes of the invention and
Various chooses and changes, i.e., according to the above description of the technical scheme and ideas, those skilled in the art can be done
Various other corresponding changes and deformation out, and all these change and deformation all should belong to the claims in the present invention
Protection scope within.
Claims (10)
1. the shield driving axis real-time deviation correcting system based on big data, including data preprocessing module, track policy module, oil
Press gesture module, oil pressure optimization module, real-time monitoring module and automatic study module, it is characterised in that:
The real-time monitoring module includes total station, prism and gyroscope, and the real-time monitoring module is constructed for real-time detection
Data, the construction data include the attitude data and Tunnel Design axis coordinate of shield machine；System is based on real-time monitoring module
The big data for acquiring construction site is optimized by the Data preprocess module, track policy module, oil pressure gesture module, oil pressure
Rated hydraulic data needed for module and automatic study module calculate shield machine axis correction each subregion jack of process, while root
Allow output area according to shield oil pressure, the rated hydraulic data is optimized；When calculated result appearance is abnormal, works as shield
When machine pose deviation designs axis beyond threshold value, emergency-stop signal is exported.
2. system according to claim 1, it is characterised in that: the data preprocessing module receives construction data and to applying
Number evidence is removed outlier processing and low-and high-frequency data fusion.
3. system according to claim 2, it is characterised in that: wherein, high-frequency data is shield machine operating parameter, including shield
Structure machine cutter head torque, cutterhead revolving speed, fltting speed, subregion jack stroke, gross thrust, subregion output oil pressure value, notch water
The flat deviation of directivity, notch vertical direction deviation, the horizontal direction deviation of shield tail, the vertical direction deviation of shield tail, the shield angle of gradient
With excavation face soil pressure；Low-frequency data includes Tunnel Design axis coordinate, gap of the shield tail and the excavation face soil with low frequency characteristic
Matter information；It is at equal intervals, high-frequency data to be corresponded into low-frequency data and carries out data fusion, so that fused data is every with construction cell
Shield machine operation data of the item record containing high frequency corresponds to the construction information of low frequency characteristic.
4. system according to claim 3, it is characterised in that: the track policy module receives at data preprocessing module
The data of reason export the targeted attitude position that next construction cell shield machine reaches.
5. system according to claim 4, it is characterised in that: the targeted attitude position includes that the horizontal direction of notch is inclined
Difference, notch vertical direction deviation, the vertical direction deviation of the horizontal direction deviation of shield tail and shield tail.
6. system according to claim 5, it is characterised in that: the oil pressure gesture module receiving locus policy module transmission
Control echo signal, output to currently propel speed at the end of next construction cell reaches each subregion thousand in targeted attitude position
Oil cylinder working-pressure theoretical value needed for jin top.
7. system according to claim 6, it is characterised in that: what the oil pressure optimization module exported oil pressure gesture module
Oil cylinder working-pressure theoretical value optimizes, when oil cylinder working-pressure theoretical value is more than the maximum opening value of shield machine jack oil pressure, base
Distribution is optimized to subregion oil pressure in descending method in proportion, output is no more than the optimization oil pressure of the maximum allowable oil pressure value of oil cylinder
Value.
8. system according to claim 6, it is characterised in that: the automatic study module includes corresponding track policy module
LSTM self learning model and corresponding oil pressure gesture module BP neural network self learning model, the automatic study module receives
What history construction data and data preprocessing module conveyed currentlys propel the new construction data of process, passes through LSTM self learning model
The counting accuracy that training improves targeted attitude position and oil cylinder working-pressure theoretical value is rolled with BP neural network self learning model.
9. system according to claim 8, it is characterised in that: the automatic study module updates the K construction cell in interval,
K value is selected as 60.
10. the method for correcting error of any one of -9 systems according to claim 1, it is characterised in that:
Construction big data is obtained, real-time monitoring module acquisition construction big data is passed through based on construction site；
Data prediction, the construction big data that data preprocessing module obtains remove exceptional value and carry out low-and high-frequency data fusion；
Using formula dkq-dkq+1≤ 100 removal exceptional values, wherein d is deviation；K=notch is horizontal, and notch is vertical, and shield tail is horizontal,
Shield tail is vertical }；Q is current q-th of construction cell；Using the relative coordinate of every ring design axis as median, according to previous ring
The construction cell number that relative coordinate and every ring include at end carries out linear interpolation:
Wherein, (xab,yab,zab) be b-th of construction cell of a ring space relative coordinate, (xa-1,ya-1,za-1) it is a-1 ring
Space relative coordinate at the construction cell of end, m are the number of construction cell contained by every ring, (xam/2,yam/2,zam/2) it is a ring
In in the m/2 construction cell space relative coordinate, that is, low-frequency data every ring Tunnel Design axis coordinate；
It calculates and exports the targeted attitude position that next construction cell shield machine reaches, track policy module receives data prediction mould
The data of block processing, the targeted attitude position includes the water of the horizontal direction deviation of notch, notch vertical direction deviation, shield tail
The vertical direction deviation of the flat deviation of directivity and shield tail；
Calculate oil cylinder working-pressure theoretical value, the control that oil pressure gesture module is transmitted according to the receiving locus policy module of targeted attitude position
Echo signal, output reach each subregion jack institute in targeted attitude position to currently propel speed at the end of next construction cell
The oil cylinder working-pressure theoretical value needed；
Optimize oil cylinder working-pressure theoretical value, oil pressure optimization module carries out the oil cylinder working-pressure theoretical value that oil pressure gesture module exports excellent
Change, when oil cylinder working-pressure theoretical value is more than the maximum permissible value of shield machine jack oil pressure, based on descending method in proportion to point
Area's oil pressure optimizes distribution, and output is no more than the optimization oil pressure value of maximum allowable oil pressure；
The new data that automatic study module is generated according to construction site rolls track policy module and oil pressure gesture module
Training, the accuracy that hoisting module calculates；
Abnormal signal emergent management, when the shield machine shield body central point of calculating, which deviates design axial line distance D, is more than threshold value, output
Emergency-stop signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910112244.1A CN109779649A (en) | 2019-02-13 | 2019-02-13 | Shield driving axis real-time deviation correcting system and method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910112244.1A CN109779649A (en) | 2019-02-13 | 2019-02-13 | Shield driving axis real-time deviation correcting system and method based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109779649A true CN109779649A (en) | 2019-05-21 |
Family
ID=66503259
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910112244.1A Pending CN109779649A (en) | 2019-02-13 | 2019-02-13 | Shield driving axis real-time deviation correcting system and method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109779649A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110067568A (en) * | 2019-05-30 | 2019-07-30 | 上海隧道工程有限公司 | The self-adaptation control method and system of shield correction oil pressure output |
| CN110067566A (en) * | 2019-05-30 | 2019-07-30 | 上海隧道工程有限公司 | The prediction technique and system of shield correction torque |
| CN110185463A (en) * | 2019-07-01 | 2019-08-30 | 西安电子科技大学 | A kind of control method of shield excavation attitude |
| CN110242310A (en) * | 2019-06-14 | 2019-09-17 | 西安电子科技大学 | Shield axis method for correcting error based on deep neural network in conjunction with association analysis |
| CN110578529A (en) * | 2019-09-20 | 2019-12-17 | 上海隧道工程有限公司 | Shield tunneling machine excavation attitude vector self-adaptive adjustment method and system |
| CN111179677A (en) * | 2019-12-25 | 2020-05-19 | 中交天和机械设备制造有限公司 | Shield constructs quick-witted operative employee training evaluation system |
| CN111636891A (en) * | 2020-06-08 | 2020-09-08 | 中铁高新工业股份有限公司 | Real-time shield attitude prediction system and construction method of prediction model |
| CN112922609A (en) * | 2021-02-05 | 2021-06-08 | 中国铁建重工集团股份有限公司 | Intelligent tunneling method of shield tunneling machine |
| CN113236271A (en) * | 2021-05-21 | 2021-08-10 | 上海隧道工程有限公司 | Shield intelligent control system and method |
| CN113311750A (en) * | 2021-05-21 | 2021-08-27 | 上海大学 | Automatic tunneling target cooperative control system and method |
| CN113344256A (en) * | 2021-05-21 | 2021-09-03 | 上海隧道工程有限公司 | System and method for predicting movement characteristics and evaluating control performance of multiple degrees of freedom of shield attitude |
| CN113982605A (en) * | 2021-05-21 | 2022-01-28 | 上海隧道工程有限公司 | Multi-level shield tunnel safety protection system and method |
| CN114578713A (en) * | 2022-03-17 | 2022-06-03 | 山东拓新电气有限公司 | Attitude control method and device for push bench |
| CN116881673A (en) * | 2023-09-06 | 2023-10-13 | 山东济矿鲁能煤电股份有限公司阳城煤矿 | Shield tunneling machine operation and maintenance method based on big data analysis |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101446201A (en) * | 2008-12-19 | 2009-06-03 | 上海隧道工程股份有限公司 | Method for rectifying and selecting tunnel segment |
| JP2014025293A (en) * | 2012-07-27 | 2014-02-06 | Kajima Corp | Shield machine |
| CN104683294A (en) * | 2013-11-27 | 2015-06-03 | 阿里巴巴集团控股有限公司 | Data processing method and system |
| CN205338929U (en) * | 2015-12-23 | 2016-06-29 | 马林伟 | On --spot rescue system of earthquake relief |
| CN105909270A (en) * | 2016-04-19 | 2016-08-31 | 上海建科工程咨询有限公司 | Shield machine axis control system |
| CN106652637A (en) * | 2017-03-02 | 2017-05-10 | 西安电子科技大学 | Virtual training system and method for collaborative operation of shield tunneling machine |
| CN108614944A (en) * | 2018-05-10 | 2018-10-02 | 西安电子科技大学 | A kind of shield track axis correction parameter prediction technique |
| CN108868807A (en) * | 2018-09-07 | 2018-11-23 | 上海隧道工程有限公司 | The intelligent control method of shield driving correction |
| CN108868805A (en) * | 2018-06-08 | 2018-11-23 | 西安电子科技大学 | Shield method for correcting error based on statistical analysis in conjunction with XGboost |
-
2019
- 2019-02-13 CN CN201910112244.1A patent/CN109779649A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101446201A (en) * | 2008-12-19 | 2009-06-03 | 上海隧道工程股份有限公司 | Method for rectifying and selecting tunnel segment |
| JP2014025293A (en) * | 2012-07-27 | 2014-02-06 | Kajima Corp | Shield machine |
| CN104683294A (en) * | 2013-11-27 | 2015-06-03 | 阿里巴巴集团控股有限公司 | Data processing method and system |
| CN205338929U (en) * | 2015-12-23 | 2016-06-29 | 马林伟 | On --spot rescue system of earthquake relief |
| CN105909270A (en) * | 2016-04-19 | 2016-08-31 | 上海建科工程咨询有限公司 | Shield machine axis control system |
| CN106652637A (en) * | 2017-03-02 | 2017-05-10 | 西安电子科技大学 | Virtual training system and method for collaborative operation of shield tunneling machine |
| CN108614944A (en) * | 2018-05-10 | 2018-10-02 | 西安电子科技大学 | A kind of shield track axis correction parameter prediction technique |
| CN108868805A (en) * | 2018-06-08 | 2018-11-23 | 西安电子科技大学 | Shield method for correcting error based on statistical analysis in conjunction with XGboost |
| CN108868807A (en) * | 2018-09-07 | 2018-11-23 | 上海隧道工程有限公司 | The intelligent control method of shield driving correction |
Non-Patent Citations (3)
| Title |
|---|
| 何承: "《城市交通大数据》", 31 January 2015, 上海科学技术出版社 * |
| 李万莉: "《机电液控制基础理论及应用》", 31 December 2015, 上海科学技术出版社 * |
| 贾利民: "《铁路运输安全工程》", 30 June 2013, 中国铁道出版社 * |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110067566A (en) * | 2019-05-30 | 2019-07-30 | 上海隧道工程有限公司 | The prediction technique and system of shield correction torque |
| CN110067568A (en) * | 2019-05-30 | 2019-07-30 | 上海隧道工程有限公司 | The self-adaptation control method and system of shield correction oil pressure output |
| CN110067566B (en) * | 2019-05-30 | 2020-06-05 | 上海隧道工程有限公司 | Method and system for predicting shield deviation rectifying moment |
| CN110067568B (en) * | 2019-05-30 | 2020-06-23 | 上海隧道工程有限公司 | Self-adaptive control method and system for shield deviation-correcting oil pressure output |
| CN110242310A (en) * | 2019-06-14 | 2019-09-17 | 西安电子科技大学 | Shield axis method for correcting error based on deep neural network in conjunction with association analysis |
| CN110242310B (en) * | 2019-06-14 | 2020-08-11 | 西安电子科技大学 | Shield axis deviation rectifying method based on combination of deep neural network and correlation analysis |
| CN110185463B (en) * | 2019-07-01 | 2020-10-09 | 西安电子科技大学 | Control method for shield tunneling attitude |
| CN110185463A (en) * | 2019-07-01 | 2019-08-30 | 西安电子科技大学 | A kind of control method of shield excavation attitude |
| CN110578529A (en) * | 2019-09-20 | 2019-12-17 | 上海隧道工程有限公司 | Shield tunneling machine excavation attitude vector self-adaptive adjustment method and system |
| CN110578529B (en) * | 2019-09-20 | 2021-02-09 | 上海隧道工程有限公司 | Shield tunneling machine excavation attitude vector self-adaptive adjustment method and system |
| CN111179677A (en) * | 2019-12-25 | 2020-05-19 | 中交天和机械设备制造有限公司 | Shield constructs quick-witted operative employee training evaluation system |
| CN111636891A (en) * | 2020-06-08 | 2020-09-08 | 中铁高新工业股份有限公司 | Real-time shield attitude prediction system and construction method of prediction model |
| CN112922609A (en) * | 2021-02-05 | 2021-06-08 | 中国铁建重工集团股份有限公司 | Intelligent tunneling method of shield tunneling machine |
| CN113236271A (en) * | 2021-05-21 | 2021-08-10 | 上海隧道工程有限公司 | Shield intelligent control system and method |
| CN113311750A (en) * | 2021-05-21 | 2021-08-27 | 上海大学 | Automatic tunneling target cooperative control system and method |
| CN113344256A (en) * | 2021-05-21 | 2021-09-03 | 上海隧道工程有限公司 | System and method for predicting movement characteristics and evaluating control performance of multiple degrees of freedom of shield attitude |
| CN113982605A (en) * | 2021-05-21 | 2022-01-28 | 上海隧道工程有限公司 | Multi-level shield tunnel safety protection system and method |
| CN113236271B (en) * | 2021-05-21 | 2024-01-19 | 上海隧道工程有限公司 | Intelligent shield control system and method |
| CN113344256B (en) * | 2021-05-21 | 2024-03-22 | 上海隧道工程有限公司 | System and method for predicting multiple degrees of freedom motion characteristics of shield attitude and evaluating control performance |
| CN114578713A (en) * | 2022-03-17 | 2022-06-03 | 山东拓新电气有限公司 | Attitude control method and device for push bench |
| CN114578713B (en) * | 2022-03-17 | 2022-09-13 | 山东拓新电气有限公司 | Attitude control method and device for push bench |
| CN116881673A (en) * | 2023-09-06 | 2023-10-13 | 山东济矿鲁能煤电股份有限公司阳城煤矿 | Shield tunneling machine operation and maintenance method based on big data analysis |
| CN116881673B (en) * | 2023-09-06 | 2023-12-19 | 山东济矿鲁能煤电股份有限公司阳城煤矿 | Shield tunneling machine operation and maintenance method based on big data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109779649A (en) | Shield driving axis real-time deviation correcting system and method based on big data | |
| CN102909148B (en) | Spraying path automatic generating method for adaptive modeling of multiple spray guns | |
| CN102905848B (en) | Automated determination of jet orientation parameters in three-dimensional fluid jet cutting | |
| CN100513997C (en) | Multiple angle movement target detection, positioning and aligning method | |
| CN111271071A (en) | Shield tunneling machine attitude control method based on fuzzy adaptive neural network | |
| CN109635406B (en) | Tunnel full-automatic guniting track planning method based on point cloud slicing | |
| CN105909270B (en) | A kind of shield machine axis control system | |
| CN114329810B (en) | Real-time prediction method for working posture of shield tunneling machine based on big data | |
| CN106647770A (en) | Field turning path planning and control method used for farm machinery driverless driving | |
| CN110185463A (en) | A kind of control method of shield excavation attitude | |
| CN113156954B (en) | Multi-agent cluster obstacle avoidance method based on reinforcement learning | |
| CN113738390B (en) | Time-sharing migration space attitude fine-adjustment deviation-rectifying method of rectangular pipe jacking machine | |
| CN110688701A (en) | Tunnel structure model modeling method based on Dynamo | |
| CN106703823B (en) | The posture deviation-rectifying system and method for large-scale digging device | |
| CN108951374A (en) | Roll the control method and device of engineering truck | |
| CN110242310A (en) | Shield axis method for correcting error based on deep neural network in conjunction with association analysis | |
| CN112647957A (en) | Earth pressure intelligent control method and system for earth pressure balance shield | |
| CN107220798A (en) | A kind of construction monitoring and managing method based on BIM | |
| CN113378466A (en) | DQN-based radar countermeasure intelligent decision-making method | |
| CN115629575A (en) | Method for recommending manual regulation and control strategy after automation of hydraulic support | |
| CN114385765A (en) | Drag suction dredger production time estimation method based on track data | |
| CN110426045A (en) | A kind of farmland spray machine device people vision guided navigation parameter acquiring method | |
| CN110309957A (en) | It is a kind of towards in the car-haul time pre-judging method with the unmanned transportation system of mine car | |
| CN108639177A (en) | A kind of autonomous full traversal climbing robot | |
| CN109006749A (en) | A kind of field canopy consistency detection system and its scaling method based on branch's resistance |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190521 |
|
| WD01 | Invention patent application deemed withdrawn after publication |