CN113916183A - PBA structure deformation risk prediction system and use method thereof - Google Patents
PBA structure deformation risk prediction system and use method thereof Download PDFInfo
- Publication number
- CN113916183A CN113916183A CN202111173770.2A CN202111173770A CN113916183A CN 113916183 A CN113916183 A CN 113916183A CN 202111173770 A CN202111173770 A CN 202111173770A CN 113916183 A CN113916183 A CN 113916183A
- Authority
- CN
- China
- Prior art keywords
- data
- monitoring
- soil pressure
- steel bar
- arch
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000012544 monitoring process Methods 0.000 claims abstract description 164
- 239000002689 soil Substances 0.000 claims abstract description 159
- 229910000831 Steel Inorganic materials 0.000 claims abstract description 109
- 230000005540 biological transmission Effects 0.000 claims abstract description 109
- 239000010959 steel Substances 0.000 claims abstract description 109
- 229910001294 Reinforcing steel Inorganic materials 0.000 claims abstract description 37
- 230000008859 change Effects 0.000 claims abstract description 36
- 238000012545 processing Methods 0.000 claims abstract description 36
- 230000008569 process Effects 0.000 claims abstract description 27
- 238000010276 construction Methods 0.000 claims abstract description 21
- 238000005259 measurement Methods 0.000 claims abstract description 20
- 238000013507 mapping Methods 0.000 claims description 22
- 230000002431 foraging effect Effects 0.000 claims description 20
- 238000005070 sampling Methods 0.000 claims description 20
- 230000001580 bacterial effect Effects 0.000 claims description 19
- 238000013508 migration Methods 0.000 claims description 16
- 230000005012 migration Effects 0.000 claims description 16
- 238000005096 rolling process Methods 0.000 claims description 16
- 230000001681 protective effect Effects 0.000 claims description 14
- 238000012843 least square support vector machine Methods 0.000 claims description 13
- 230000010415 tropism Effects 0.000 claims description 11
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 10
- 230000010076 replication Effects 0.000 claims description 5
- 238000013480 data collection Methods 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 3
- 230000007547 defect Effects 0.000 abstract description 5
- 230000002035 prolonged effect Effects 0.000 abstract description 4
- 230000006870 function Effects 0.000 description 10
- 239000011435 rock Substances 0.000 description 8
- 238000012706 support-vector machine Methods 0.000 description 7
- 230000008093 supporting effect Effects 0.000 description 7
- 238000009412 basement excavation Methods 0.000 description 6
- 230000004044 response Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000006073 displacement reaction Methods 0.000 description 5
- 238000005457 optimization Methods 0.000 description 5
- 238000003466 welding Methods 0.000 description 5
- 239000010963 304 stainless steel Substances 0.000 description 4
- 229910000589 SAE 304 stainless steel Inorganic materials 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 239000004575 stone Substances 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000003014 reinforcing effect Effects 0.000 description 3
- 238000004544 sputter deposition Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000005422 blasting Methods 0.000 description 2
- 230000019771 cognition Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 239000000428 dust Substances 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 238000004148 unit process Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000008033 biological extinction Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000003399 chemotactic effect Effects 0.000 description 1
- 230000035605 chemotaxis Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000012938 design process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000033001 locomotion Effects 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000004078 waterproofing Methods 0.000 description 1
Images
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Abstract
The invention discloses a PBA structure deformation risk prediction system and a use method thereof, wherein the PBA structure deformation risk prediction system comprises the following steps: the device comprises a data acquisition unit, a data transmission unit and a data processing unit; the data acquisition unit is used for acquiring the soil pressure at the vault, arch shoulder and arch waist of the tunnel and the change monitoring data of the steel bar stress at the vault and arch waist; and the data processing unit is used for predicting the soil pressure and the steel bar stress in the construction process. The invention can make up the defects of high risk, low frequency and large error of manual measurement, thereby realizing real-time automatic and accurate monitoring of tunnel soil pressure and reinforcing steel bar stress and providing guarantee for tunnel safe construction; meanwhile, the fixing, instrument water-proof and anti-collision protection of the collection box and the transmission box are considered, and the service lives of the collection box and the transmission box are prolonged; the short-distance wireless transmission system and the GPRS information transmission assembly are used, the use of a long-distance signal data line is replaced, the monitoring cost is effectively reduced, and the applicability of the equipment is improved.
Description
Technical Field
The invention relates to the technical field of tunnel data monitoring and parameter identification, in particular to a PBA structure deformation risk prediction system and a use method thereof.
Background
The stability of the surrounding rock is of great importance in the subway construction process. At present, the stability of tunnel surrounding rocks is mainly judged in a surrounding rock displacement mode of manual measurement, and the manual measurement method has high risk, low frequency and large human error. Compared with manual measurement, automatic monitoring has higher precision and monitoring frequency with a higher encryption set, but the automatic monitoring applied in the current tunnel engineering mostly uses one monitoring section as a monitoring target, belongs to the category of two-dimensional monitoring, causes that the monitoring data can not reflect the overall stable state of the engineering space, and has certain limitation.
The detection equipment in the current subway tunnel engineering is greatly influenced by the environmental factors of the subway engineering, and mainly has the following problems: (1) the measurement target is positioned on a two-dimensional plane, the distance between the current monitoring position and the face is neglected, and the space effect caused by the forward movement of the face cannot be determined; (2) the monitoring equipment needs workers to measure on site, and automatic monitoring cannot be achieved. (3) In the subway construction process, the environment is complex and severe (such as broken stone splashing and water seepage caused by blasting), and a corresponding instrument protection device and a corresponding fixing device are not designed. (4) Few automated collection facilities can only be connected to the outside of the tunnel by using a data line with a considerable length due to signal problems in the tunnel, the cost is high, and the data line in the tunnel is easy to be damaged.
Disclosure of Invention
The invention provides a system and a method for predicting deformation risk of a PBA structure, which aim to overcome the problems.
The system of the invention comprises: the device comprises a data acquisition unit, a data transmission unit and a data processing unit;
the data acquisition unit is used for acquiring soil pressure at the vault, arch shoulder and arch waist of the tunnel and change monitoring data of the stress of the steel bars at the vault and the arch waist;
the data transmission unit is used for integrating the soil pressure and the steel bar stress data collected by the data collection unit to form time series monitoring data and sending the time series monitoring data to the data processing unit;
and the data processing unit is used for establishing a nonlinear mapping relation between the monitoring data and the tunnel soil pressure and the steel bar stress through a fitting algorithm based on a least square support vector machine, and predicting the soil pressure and the steel bar stress in the construction process by adopting a bacterial foraging algorithm based on a time sequence.
Further, the data acquisition unit includes: the device comprises a data monitoring part, a data acquisition part, a protection structure part and a support structure part;
the data monitoring part is used for monitoring and acquiring soil pressure at the arch crown, the arch shoulder and the arch waist and change monitoring data of the steel bar stress at the arch crown and the arch waist;
the data acquisition unit is used for collecting and sending the data monitoring unit to the data transmission unit;
the protection structure part is used for accommodating each data acquisition part;
the support structure portion is used to secure the protective structure portion to the tunnel sidewall.
Further, the data monitoring section includes: the device comprises a soil pressure vault measuring module, a soil pressure arch measurement module, a steel bar stress vault measuring module and a steel bar stress arch measurement module;
the soil pressure vault measurement module is used for acquiring sampling data corresponding to the vault monitoring direction;
the soil pressure arch shoulder measuring module is used for acquiring sampling data corresponding to the monitoring direction of the arch shoulder;
the soil pressure arch waist measuring module is used for acquiring sampling data corresponding to the arch waist monitoring direction;
the steel bar stress vault measurement module is used for acquiring sampling data corresponding to the vault monitoring direction;
the steel bar stress arch waist measuring module is used for acquiring sampling data corresponding to the arch waist monitoring direction;
further, the data acquisition section includes: the automatic data acquisition module and the automatic data transmission module are connected with the data acquisition module;
the data automatic acquisition module is used for monitoring the data monitoring part in real time.
The data automatic transmission module is connected with the data automatic acquisition module through a data line, so that the acquired data can be transmitted to the data transmission unit in real time.
Further, the data acquisition unit includes: the device comprises a data receiving part, a data transmission part, a protection structure part and a support structure part;
the data receiving part is used for receiving the data wirelessly transmitted by the data acquisition unit;
the data transmission part is used for transmitting the data received by the data receiving part to the data processing unit;
each data acquisition part is accommodated in the protection structure part;
the support structure portion is capable of securing the protective structure portion to the tunnel sidewall.
Further, the data receiving section includes: the data wireless receiver is connected with the transmission box signal receiving antenna through a data line;
the transmission box signal receiving antenna can realize short-distance data wireless transmission.
The method comprises the following steps:
s1, the data processing unit receives the monitoring data transmitted by the data transmission unit and establishes sample data based on the time sequence, and the sample data comprises: the values of arch crown soil pressure, arch shoulder soil pressure, arch waist soil pressure, arch crown reinforcing steel bar stress and arch waist reinforcing steel bar stress at the ith day;
s2, the data processing unit learns the time series data by using the least square support vector machine theory to obtain the nonlinear relation between the soil pressure value and the reinforcing steel bar stress value change sequence;
s3, the data processing unit determines a mapping relation corresponding to a training set formed by the monitoring data of the time series to obtain a nonlinear prediction model, and based on the nonlinear prediction model, optimizes the nonlinear mapping model through the tropism operation, the replication operation and the migration operation of the bacterial foraging algorithm to realize the rolling prediction of the structural deformation risk.
Further, S2 includes:
s21, acquiring soil pressure and steel bar stress data of the monitoring section of the tunnel face based on the data of the distance between the determined monitoring position and the tunnel face;
s22, predicting the nonlinear change sequence, namely obtaining the relation between the soil pressure and the steel bar stress at the moment p +1 and the soil pressure and the steel bar stress at the previous p moments;
s23, training the relation between the soil pressure and the stress change of the steel bars through time sequence data by using a least square support vector machine theory to obtain a nonlinear relation between the soil pressure and the stress change sequence of the steel bars:
wherein, y (x)p+1) The soil pressure and the steel bar stress value at the moment p +1 are obtained; b is an offset;
as kernel function, K (x, x)k)＝exp{||x-xi||2/σ2}，σ2Is the square bandwidth pass in the gaussian RBF kernel.
Further, S3 includes:
s31, establishing a nonlinear prediction model by utilizing a nonlinear relation between the soil pressure value and the stress value change sequence of the steel bar, wherein the nonlinear prediction model is used for predicting data of a current position P +1 through previous P pieces of historical data;
s32, adding underground water level influence parameters in the input process, and correcting the prediction process in each step:
s321, tropism operation: carrying out any possible increase or decrease change on the data value within a set range on the group of time series monitoring data to obtain a group of new time series monitoring data, and repeatedly operating;
s322, copy operation: when the trending operation reaches the set critical times, all time series monitoring data are sequentially arranged from large to small by taking the absolute value of the predicted value from the monitoring value as an evaluation index, the data of 50% of the last time series monitoring data are deleted, and the data of 50% of the first time series monitoring data are copied.
S323, migration operation: when the migration operation occurs in the process of needing to predict the next data, the execution reference point is used for keeping the data after the copying operation is carried out to the set limit step, and if the data meets the requirements; and if the data does not meet the requirements, deleting the data.
S33, carrying out corresponding rolling prediction on the sampling data obtained by the data acquisition unit based on the nonlinear prediction model optimized by the bacterial foraging algorithm.
The invention can make up the defects of high risk, low frequency and large error of manual measurement, thereby realizing real-time automatic and accurate monitoring of tunnel soil pressure and reinforcing steel bar stress and providing guarantee for tunnel safe construction; meanwhile, the fixing, instrument water-proof and anti-collision protection of the collection box and the transmission box are considered, and the service lives of the collection box and the transmission box are prolonged; the short-distance wireless transmission system and the GPRS information transmission assembly are used, the use of a long-distance signal data line is replaced, the monitoring cost is effectively reduced, and the applicability of the equipment is improved. The data transmission unit can upload data to the cloud end, and multi-terminal real-time acquisition can be realized; and the data processing unit can train a nonlinear prediction model according to the monitoring data of the cloud, so that the rolling prediction of the structural deformation risk is realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is an overall flow diagram of the present invention;
FIG. 2 is a schematic structural view of the soil pressure cell of the present invention;
FIG. 3 is a schematic view of the structure of the reinforcing bar gauge of the present invention;
FIG. 4 is a schematic view of the construction of the collection box of the present invention;
FIG. 5 is a schematic view of the structure of the transmission box of the present invention;
FIG. 6 is a schematic structural view of the horizontal support of the present invention;
FIG. 7 is a schematic view of a monitoring profile setup in one embodiment;
FIG. 8 is a schematic view of monitoring points of a monitored cross section in one embodiment;
FIG. 9 is an overall schematic view of the arrangement of a device for monitoring a fracture in one embodiment;
FIG. 10 is a flow chart of the implementation of the PBA structure deformation risk prediction method based on the intelligent response surface method;
FIG. 11 is a block diagram of the operational flow of the collection box of the present invention;
FIG. 12 is a block diagram illustrating a process for implementing the operation of the transmission box according to the present invention;
FIG. 13 is a stratigraphic diagram in one embodiment;
FIG. 14 is a data processing unit earth pressure time series data line graph in one embodiment.
The reference numbers illustrate:
1. a soil pressure cell; 2. a soil pressure cell support; 3. a soil pressure cell signal output line; 4. reinforcing steel bars; 5. a steel bar meter; 6. a rebar meter signal output line; 7. a collection box signal transmitting antenna; 8. a collection box; 9. a data wireless transmitter; 10. a bracket expansion screw; 11. a support; 12. a power line; 13. a soil pressure cell signal input line; 14. a steel bar meter signal input line; 15. a collection box power supply; 16. an automated collector; 17. a waterproof outer edge of the collection box; 18. a transmission box signal receiving antenna 19 and a transmission box; 20. a waterproof outer edge of the transmission box, 21, a GPRS signal transmitter; 22. a GPRS signal transmitting antenna; 23. a transmission box power line; 24. a transmission box power supply; 25. a data wireless receiver; 26. monitoring the section at 40 m; 27. monitoring the cross section at 75 m; 28. monitoring the section at 110 m; 29. vault soil pressure monitoring points; 30. monitoring points of arch shoulder soil pressure; 31. an arch soil pressure monitoring point; 32. vault reinforcing steel stress monitoring points; 33. and (5) monitoring the stress of the steel bars at the arch waist.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
Example 1
Aiming at the problems that the artificial measurement risk is high, the frequency is low, the error is large and the advanced early warning of the surrounding rock deformation risk cannot be carried out in the current tunnel soil pressure and reinforcing steel bar stress monitoring process, in the embodiment, a PBA structure deformation risk prediction method based on an intelligent response surface method is developed, and the method has the following characteristics: the collecting box and the launching box can be arranged on the wall surface of a primary lining of a tunnel through a bracket, are of closed structures, have the functions of preventing water and placing concrete guniting flystones, and can adapt to complex and severe engineering environments; (2) the soil pressure at the vault, the arch shoulder and the arch waist of the tunnel and the change monitoring data of the steel bar stress at the vault and the arch waist can be simultaneously obtained, and errors caused by tunnel excavation space effects can be made up; (3) the information acquisition unit is matched with the acquisition box and the transmission box formed by the data transmission unit to use wireless data transmission to replace the traditional wired transmission, so that the practicability of the device is improved; (4) the data processing unit can utilize a vector machine and a bacterial foraging algorithm to construct a prediction model, and real-time prediction is carried out according to soil pressure and reinforcing steel bar stress data obtained through monitoring, so that more visual data reference is provided for engineers. Meanwhile, the device is convenient to mount and dismount, can be recycled, and has the advantage of high cost.
Based on the above design points, it can be known that the PBA structure deformation risk system based on the intelligent response surface method described in this embodiment includes:
(1) the data acquisition unit can simultaneously acquire the soil pressure at the vault, the arch shoulder and the arch waist of the tunnel and the change monitoring data of the steel bar stress at the vault and the arch waist, and more comprehensively reflect the soil pressure and steel bar stress change process of the tunnel under the influence of the space effect in the tunnel excavation process; meanwhile, the data acquisition unit processes the tunnel guniting construction, blasting construction and water-rich environment, and the protection structure can realize the functions of water prevention and flying stone sputtering prevention; the data acquisition unit is also provided with an independent support fixing structure, so that a stable support and a support structure convenient to disassemble can be provided for the longitudinal extension characteristic of tunnel engineering in space, and after the construction of the current area is finished, the device can be disassembled and moved and used for the next target position, so that the utilization efficiency of the structure is improved;
(2) and the data transmission unit can collect and remotely transmit the monitoring information of the soil pressure and the reinforcing steel bar stress, which are output by the data acquisition unit and obtained through the soil pressure cell and the reinforcing steel bar meter. And the data transmission unit sends data to the data processing unit through the GPRS module. The early warning information realizes synchronous data release of multiple terminals such as a webpage, a mobile phone, a software platform and the like through a server, meets the data cognition requirements of different construction participation departments, and provides more visual and comprehensive surrounding rock state data for engineering management personnel;
(3) the data processing unit can receive the data transmitted by the data transmission unit; establishing a nonlinear mapping relation between monitoring data and tunnel soil pressure and reinforcing steel bar stress through a fitting algorithm based on a least square support vector machine, predicting the soil pressure and the reinforcing steel bar stress in the construction process by adopting a bacterial foraging algorithm based on a time sequence, and sending out monitoring and early warning if a predicted value exceeds a warning value continuously for three times in a day; the early warning information is synchronously issued by the server through data of multiple terminals such as a webpage, a mobile phone, a software platform and the like, the data cognition requirements of different construction participation departments are met, and more visual and comprehensive soil pressure and steel bar stress state data are provided for engineering management personnel.
The PBA structure deformation risk prediction method based on the intelligent response surface method, which is formed by the three units, can realize the release of soil pressure and reinforcing steel bar stress monitoring data and the release of risk early warning information in the forward construction process of the tunnel face, and the combined working form and the specific data flow of each unit are shown in the figures 10, 11 and 12.
As shown in fig. 1-7, 13 and 14, based on the above solutions, it can be seen that the present invention first develops a PBA structural deformation risk prediction system based on an intelligent response surface method to be applied to the monitoring process of the soil pressure at the vault, shoulder and arch of the tunnel section and the stress of the steel bars at the vault and arch of the tunnel section of the present device, whereas in the conventional structural deformation risk prediction and early warning process, the distance from the monitoring section to the tunnel face is not taken into account. However, the change of the distance between the monitoring section and the tunnel face affects the data of soil pressure and steel bar stress, which represents the space effect of tunnel excavation, along with the tunnel excavation, the rock which originally has the supporting effect on the upper stratum is excavated, the supporting balance of the surrounding rock is damaged, new balance can be established between the soil pressure and the steel bar stress of the primary lining, and the balance can bring the displacement of the surrounding rock; with the advance of the excavation section, the old balance is broken continuously, the new balance is established continuously, and the new displacement is generated continuously by the displacement. A soil pressure and steel bar stress prediction model is established in a data processing unit by using a vector machine and a bacterial foraging algorithm, the rolling prediction of a project is realized, the prediction and early warning data are uploaded to a cloud end, and the real-time acquisition of multi-terminal data can be realized.
The data acquisition unit mainly comprises four parts: 1. a data monitoring section; 2. a data acquisition section; 3. A protective structural portion; 4. a support structure portion. The data monitoring part 1 can monitor the soil pressure at the vault, arch shoulder and arch waist of the tunnel section and the stress of steel bars at the vault and arch waist, collect corresponding tunnel space characteristic information, and preferably adopt a soil pressure cell and a steel bar meter; the data acquisition part 2 is connected with a monitoring instrument through a data line, collects corresponding monitoring data and transmits the monitoring data through an antenna in a wireless mode.
The data monitoring part 1 and the data acquisition part 2 are contained in the protection structure part 3, the protection structure part 2 can realize the protection of instruments, and the main protection targets are the water outlet environment, the high dust particle environment, the collision of engineering equipment and the like in a tunnel; the support structure portion 4 is capable of securing the data monitoring portion 1, the data acquisition portion 2 and the protective structure portion 3 to the side walls of the tunnel. The collection box operational flow diagram is shown in FIG. 12.
In a specific embodiment, as shown in fig. 2 and 3, the data monitoring part includes: the soil pressure cell comprises a soil pressure cell 1, a pressure cell bracket 2, a soil pressure cell signal output line 3, a steel bar 4, a steel bar meter 5, a steel bar meter signal output line 6, a vault soil pressure monitoring point 29, a vault soil pressure monitoring point 30, a vault soil pressure monitoring point 31, a vault steel bar stress monitoring point 32 and a vault steel bar stress monitoring point 33; the soil pressure box 1 is fixed on a vault soil pressure monitoring point 29, an arch shoulder soil pressure monitoring point 30 and an arch waist soil pressure monitoring point 31 through a pressure box support 2 welded on a primary lining steel bar, and is used for acquiring soil pressure monitoring data corresponding to the vault, the arch shoulder and the arch waist; the reinforcing steel bar meter 5 is used for acquiring reinforcing steel bar stress monitoring data corresponding to the arch crown and the arch waist by welding two ends of reinforcing steel bars 4 on primary lining reinforcing steel bars of the arch crown reinforcing steel bar stress monitoring point 32 and the arch waist reinforcing steel bar stress monitoring point 33;
in a more specific embodiment, as shown in fig. 8, after the soil pressure cell 1 and the steel bar gauge 5 are fixed to the arch crown soil pressure monitoring point 29, the arch shoulder soil pressure monitoring point 30, the arch waist soil pressure monitoring point 31, the arch crown steel bar stress monitoring point 32 and the arch waist steel bar stress monitoring point 33, the positions of the soil pressure cell signal output line 3 and the steel bar gauge signal output line 6 need to be adjusted to ensure that the signal output lines are not damaged on site, and more to ensure that the signal output lines have enough length outside the lining of the tunnel.
In a more specific embodiment, the specific type and properties of the monitoring instrument can be defined, namely, the soil pressure box 1 and the reinforcing steel bar meter 5 adopt vibrating wire type instruments, so that the data acquisition equipment can acquire data conveniently.
In a specific embodiment, as shown in fig. 4, the data acquisition part includes: the system comprises a collecting box signal transmitting antenna 7, a collecting box 8, a data wireless transmitter 9, a power line 12, a soil pressure cell signal input line 13, a steel bar meter signal input line 14, a collecting box power supply (220v to 24v)15 and an automatic collector 16; the data wireless transmitter 9, the power line 12, the collection box power supply (220v to 24v)15 and the automatic collector 16 are all arranged inside the collection box 8, and the collection box power supply (220v to 24v)15 is responsible for supplying power to the data wireless transmitter 9 and the automatic collector 16; the automatic collector 16 is connected with a steel bar meter signal input line 14 through a soil pressure cell signal input line 13 so as to collect soil pressure at the arch crown, arch shoulder and arch waist and steel bar stress at the arch crown and arch waist; the data wireless transmitter 9 is connected with the automatic acquisition device 16 through a data line, and realizes wireless transmission of the data of the automatic acquisition device 16 through an acquisition box signal transmitting antenna 7 outside the acquisition box.
In a more specific embodiment, the soil pressure cell signal input line 13 and the steel bar meter signal input line 14 are respectively connected with the soil pressure cell signal output line 3 and the steel bar meter signal output line 6, and the signal lines can only adopt 1-to-1 connection.
In a particular embodiment, as shown in fig. 4, the protective structure comprises a box structure consisting of a collection box 8 and a collection box waterproof outer edge 17; the collecting box 8 is integrally formed by welding 304 stainless steel with the thickness of 3mm, and one side of the cover plate is fixed on the collecting box 8 through a rotating shaft, so that the cover plate can rotate around the rotating shaft; the top of the collection box 8 is provided with a water-proof collection box outer edge 17 which prevents water from dripping in the hole. 304 stainless steel with the thickness of 3mm has certain impact resistance, and prevents flying stones generated by tunnel guniting from sputtering and damaging instruments.
In a more specific embodiment, as shown in fig. 4 and 6, the support structure comprises a bracket expansion screw 10, wherein the bracket expansion screw 10 is fixed in the lining of the tunnel, and the bracket 11 is fixed on the side wall of the tunnel through the bracket expansion screw 10, so as to ensure that the collection box has a certain height from the bottom of the tunnel.
The soil pressure and the steel bar stress data measured by the data acquisition unit are wirelessly transmitted to the data transmission unit through the acquisition box signal transmitting antenna.
The data transmission unit mainly comprises four parts: 1. a data receiving section; 2. a data transmitting section; 3. A protective structural portion; 4. a support structure portion. The data receiving part 1 can receive data wirelessly transmitted by the acquisition box and transmit the data to the data transmission part through a data line; the data transmission part 2 is mainly composed of a GPRS signal transmitter and transmits monitoring data to a remote data processing unit through an antenna in a wireless mode. The data receiving part 1 and the data transmission part 2 are contained in the protection structure part 3, the protection structure part 3 can realize the protection of instruments, and the main protection targets are a water outlet environment, a high dust particle environment, engineering equipment collision and the like in a tunnel; the support structure portion 4 is capable of securing the data receiving portion 1, the data transmitting portion 2 and the protective structure portion 3 to the side wall of the tunnel. The transmission workflow is shown in fig. 12.
In a specific embodiment, as shown in fig. 5, the data receiving part includes: a transmission box signal receiving antenna 18, a transmission box 19, a transmission box power line 23, a transmission box power supply (220v to 24v)24 and a data wireless receiver 25; wherein, the transmission box power supply (220v to 24v)24 and the data wireless receiver 25 are arranged inside the transmission box 19; the transmission box signal receiving antenna 18 monitors data by receiving soil pressure and reinforcing steel bar stress wirelessly transmitted by the collection box signal transmitting antenna 7 and transmits the monitored data to the data wireless receiver 25; the data wireless receiver 25 is powered by a transmission box power supply (220v to 24v) 24;
in a specific embodiment, as shown in fig. 5, the data transmission part includes: a transmission box 19, a GPRS signal transmitter 21, a GPRS signal transmitting antenna 22, a transmission box power line 23 and a transmission box power supply (220v to 24v) 24; the GPRS signal transmitter 21 and the transmission box power supply (220v to 24v)24 are arranged in the transmission box 19, and the transmission box power supply (220v to 24v)24 is responsible for supplying power to the GPRS signal transmitter 21; the GPRS signal transmitter 21 receives the signal of the data wireless receiver 25 through a data line, and wirelessly transmits the received monitoring data to a remote data processing unit through the GPRS signal transmitting antenna 22.
In a specific embodiment, as shown in the figure, the protective structure comprises a box structure consisting of a transmission box 19 and a waterproof outer edge 20 of the transmission box; the transmission box 19 is integrally formed by welding 304 stainless steel with the thickness of 3mm, and one side of the cover plate is fixed on the transmission box 19 through a rotating shaft, so that the cover plate can rotate around the rotating shaft; the top of the transport box 19 is provided with a waterproof outer edge 20 of the box, which prevents dripping in the hole. 304 stainless steel with the thickness of 3mm has certain impact resistance, and prevents flying stones generated by tunnel guniting from sputtering and damaging instruments.
In a more specific embodiment, as shown in fig. 5 and 6, the support structure portion includes: and the water support expansion screw 10 is fixed in the position lining of the tunnel, the support 11 is fixed on the side wall of the tunnel through the support expansion screw 10, and the transmission box 19 is ensured to have a certain height from the bottom of the tunnel.
In a specific embodiment, the method of the present invention comprises:
s1, establishing sample data { x based on time seriesi}＝{x1,x2,…,xnThe sample data comprises vault soil pressure, arch shoulder soil pressure, arch waist soil pressure, vault steel bar stress and arch waist steel bar stress;
s2, according to the least square support vector machine theory, the nonlinear deformation relation can obtain the nonlinear relation between the soil pressure value and the steel bar stress value change sequence by learning the obtained actual soil pressure value and the steel bar stress value through the support vector machine;
s3, determining the mapping relation corresponding to the training set to obtain a nonlinear mapping model, and optimizing the nonlinear mapping model through the tropism operation, the copying operation and the migration operation of the bacterial foraging algorithm based on the nonlinear mapping model to realize rolling prediction of the structural deformation risk.
Optionally, in one embodiment, the S2 includes:
s21, acquiring soil pressure and steel bar stress data of a monitoring section corresponding to each advancing one-grade of the tunnel face based on the data of the distance between the determined monitoring position and the tunnel face;
s22, predicting the nonlinear change sequence, namely searching the soil pressure and the steel bar stress at the moment p +1 and the soil pressure and the steel bar stress x at the previous moments1,x2,…,xpA relation of (1), i.e. xp+1＝f(x1,x2,…,xp) The non-linear relationship between the soil pressure and the stress change sequence of the steel bars is represented as a learning function.
S23, learning the time series data by using the least square support vector machine theory: for n-p deformed sequences xi,xi+1,…,xi+pAnd (i is 1, 2, …, n-p), obtaining a nonlinear relation between the soil pressure and the stress change sequence of the reinforcing steel bars,
in the formula, y (x)p+1) The soil pressure and the stress value x of the steel bar at the p +1 th momentp+1P soil pressures and the stress value of the steel bar at the moment p +1, xp+1＝f(x1,x2,…,xp+1) The first p soil pressures and the stress value of the steel bar at the p + k moment position, xk＝(xk,xk+1,…,xk+p+1)。
Optionally, in one embodiment, the S3 includes:
s31, aboveUnder the condition described above, the mapping form of the learning sample is set to { x }1,x2,…,xp}→{xp+1}， {x2,x3,…,xp+1}→{xp+2}…{xn-p,xn-p+1,…,xn-1}→{xn}. The result of the learning of the vector machine is that the data of the current position can be predicted by P historical data before the prediction point, for example, x needs to be predictedn+1Only need to input, { xn-p+1,xn-p+2,…,xnObtaining a prediction result; then will predict the obtained xn+1As a known quantity, { x }n-p+2,xn-p+3,…,xn+1As a new timing pair xn+2And (6) performing prediction.
S32, but some errors still exist in each prediction step in the prediction process, and the errors are accumulated continuously with the increase of the number of the prediction steps, and finally the prediction result cannot accurately express the real working condition. In order to reduce the influence of the error, Q accurately determined influence parameters are added into the input time sequence, and the prediction process of each step is effectively corrected. And (3) searching for optimal parameters by using a bacterial foraging optimization algorithm BFOA through a tropism operation, a replication operation and a migration operation, and optimally solving the problem that the non-linear prediction algorithm of the minimum two-times support vector machine has high dependence on two parameters, namely the optimal historical step number p and the influence factor Q.
And S33, performing corresponding rolling prediction on the sampling data obtained by the data acquisition unit based on the optimized nonlinear prediction model.
Example 2
Firstly, mounting a monitoring device and acquiring measurement data:
firstly, mounting a soil pressure cell and a reinforcing steel bar meter to corresponding measuring points (as shown in figure 8) during tunnel construction, and protecting corresponding soil pressure cell signal output lines and reinforcing steel bar meter signal output lines; installing (as shown in figure 6) a collecting box bracket at the side wall of the tunnel at a proper position near the set monitoring section (as shown in figure 7), installing a transmission box bracket at the entrance of the tunnel, fixing the bracket on the side wall by using an expansion bolt, and after the collecting box and the transmission box are placed on the bracket, passing a steel wire through a hole at the bottom of the box body to ensure that the bracket is firmly installed; secondly, a soil pressure cell signal input line and a steel bar meter signal input line of the collection box are respectively connected with a soil pressure cell signal output line and a steel bar meter signal output line which are exposed outside the liner, and an instrument is debugged to ensure that the automatic collector can collect data; and thirdly, adjusting the positions of the signal transmitting antenna of the acquisition box, the signal receiving antenna of the transmission box and the GPRS signal transmitting antenna to ensure that the transmission box can receive the signals of the acquisition box, a remote computer can receive the signals of the transmission box, and finally the connectivity of the data acquisition unit, the data transmission unit and the data processing unit.
And step two, monitoring data transmission and data integration:
firstly, collecting vibration string values of a soil pressure box and a reinforcing steel bar meter, and utilizing a formula
Calculating soil pressure and reinforcing steel bar stress; secondly, the data wireless transmitter transmits the soil pressure and the steel bar stress measured by the automatic collector to a transmission box through a signal transmitting antenna of the collection box; secondly, the data wireless receiver of the transmission box receives monitoring data through the transmission box signal receiving antenna, then the monitoring data is transmitted to the data processing unit through the GPRS signal transmitting antenna by using the GPRS signal transmitter, and the data processing unit processes the data into event sequence monitoring data.
Thirdly, calculating time series monitoring data based on a vector machine and a bacterial foraging algorithm to obtain an optimized prediction model, and performing rolling prediction on soil pressure and reinforcing steel stress: the creation process of the rolling prediction comprises the following steps:
s1, establishing sample data { x based on time seriesi}＝{x1,x2,…,xnThe sample data comprises vault soil pressure, arch shoulder soil pressure, arch waist soil pressure, vault steel bar stress and arch waist steel bar stress;
s2, according to the least square support vector machine theory, the nonlinear deformation relation can obtain the nonlinear relation between the soil pressure value and the steel bar stress value change sequence by learning the obtained actual soil pressure value and the steel bar stress value through the support vector machine; the S2 includes:
s21, acquiring soil pressure and steel bar stress data of a monitoring section corresponding to each advancing one-grade of the tunnel face based on the data of the distance between the determined monitoring position and the tunnel face;
s22, predicting the nonlinear change sequence, namely searching the soil pressure and the steel bar stress at the moment p +1 and the soil pressure and the steel bar stress x at the previous moments1,x2,…,xpA relation of (1), i.e. xp+1＝f(x1,x2,…,xp) The non-linear relationship between the soil pressure and the stress change sequence of the steel bars is represented as a learning function.
S23, using least squares support vector machine theory, for a given N training samples { x }i,yi}i＝1…N(wherein xi∈RnTraining input sample y for n dimensionsi∈RnFor training output samples), the objective optimization function is
Learning the time series data with the target optimization parameters: for n-p deformed sequences xi,xi+1,…,xi+pAnd (i is 1, 2, …, n-p), and obtaining a nonlinear relation (LSSVM regression function) between the soil pressure and the stress change sequence of the reinforcing steel bars:
in the formula: k (x, x)k)＝exp{||x-xi||2/σ2And (the kernel function adopts a radial basis kernel function).
In the formula, y (x)p+1) The soil pressure and the stress value x of the steel bar at the p +1 th momentp+1P soil pressures and the stress value of the steel bar at the moment p +1, xp+1＝f(x1,x2,…,xp+1) The first p soil pressures and the stress value of the steel bar at the p + k moment position, xk＝(xk,xk+1,…,xk+p+1)。
S3, determining the mapping relation corresponding to the training set to obtain a nonlinear mapping model, and optimizing the nonlinear mapping model through the tropism operation, the copying operation and the migration operation of the bacterial foraging algorithm based on the nonlinear mapping model to realize rolling prediction of the structural deformation risk.
S31, setting the mapping form of the learning sample as { x1,x2,…,xp}→{xp+1}， {x2,x3,…,xp+1}→{xp+2}…{xn-p,xn-p+1,…,xn-1}→{xn}. The result of the learning of the vector machine is that the data of the current position can be predicted by P historical data before the prediction point, for example, x needs to be predictedn+1Only need to input, { xn-p+1,xn-p+2,…,xnObtaining a prediction result; then will predict the obtained xn+1As a known quantity, { x }n-p+2,xn-p+3,…,xn+1As a new timing pair xn+2And (6) performing prediction.
S32, but some errors still exist in each prediction step in the prediction process, and the errors are accumulated continuously with the increase of the number of the prediction steps, and finally the prediction result cannot accurately express the real working condition. In order to reduce the influence of the error, Q accurately determined influence parameters are added into the input time sequence, and the prediction process of each step is effectively corrected. And (3) searching for optimal parameters by using a bacterial foraging optimization algorithm BFOA through a tropism operation, a replication operation and a migration operation, and optimally solving the problem that the non-linear prediction algorithm of the minimum two-times support vector machine has high dependence on two parameters, namely the optimal historical step number p and the influence factor Q.
S321, a tendency operation, namely for a community with a population size S, representing the position information of an individual i after g times of chemotaxis operation, n times of copying operation and m times of migration operation by theta (i, g, n, m), C (i) represents the step size, and delta represents [ -1,1]The unit random vector of the above arbitrary is,
indicating after random adjustmentOrientation, then the positional formula for the chemotactic cycle can be expressed as:
s322, copy operation: the duplication operation follows the natural selection rule of high-priority and low-priority, when the tropism operation reaches the critical times, all the data are sequentially arranged from large to small by taking the adaptive value as an evaluation index, and the total data number is recorded as 2Sr(ii) a S with smaller adaptive value arranged in the latter halfrPerforming extinction operation on the data, and reserving the previous SrData with larger adaptation value; and copying the retained excellent individuals to obtain data with the same foraging capacity. A copy operation is completed.
S323, migration operation: the migration operation is carried out when the resource environment changes, and the execution reference point carries out N for the copy operationreAfter step (c). Migration operations imply two different outcomes: the data is migrated in its entirety to another area or the group of data is cancelled.
And S33, performing corresponding rolling prediction on the sampling data obtained by the data acquisition unit based on the optimized nonlinear prediction model.
Fourthly, predicting and issuing an early warning result: and formally using the obtained optimized prediction early warning model pair, installing the prediction early warning model pair to a data acquisition processing module, integrating and calculating real-time acquired data, obtaining a prediction early warning result, sending the prediction early warning result to a cloud end, and realizing real-time access and query of a plurality of terminals on a calculation result.
According to the embodiment of the invention, firstly, a PBA structure deformation risk prediction method based on an intelligent response surface method is developed on the basis of automatic acquisition of the Internet of things, so that the defects of high risk, low frequency and large error of manual measurement are overcome by the method, the real-time automatic accurate monitoring of tunnel soil pressure and steel bar stress is realized, and the guarantee is provided for the safe construction of the tunnel; meanwhile, the fixing, instrument water proofing and anti-collision protection of the collection box and the transmission box are considered, so that the service lives of the collection box and the transmission box are prolonged; the short-distance wireless transmission system and the GPRS information transmission assembly are used, the use of a long-distance signal data line is replaced, the monitoring cost is effectively reduced, and the applicability of the equipment is improved. The data transmission unit can upload data to the cloud end, and multi-terminal real-time acquisition can be realized; and the data processing unit can train a nonlinear prediction model according to the monitoring data of the cloud end, so that the rolling prediction of the structural deformation risk is realized. The method is suitable for the dynamic design process of tunnel construction, and the intelligent process of tunnel engineering is improved.
Example 3
The data acquisition unit can simultaneously acquire the soil pressure at the vault, arch shoulder and arch waist of the tunnel and the change monitoring data of the steel bar stress at the vault and arch waist;
the data transmission unit can integrate the soil pressure and the steel bar stress data collected by the data collection unit to form time series monitoring data and send the time series monitoring data to the data processing unit;
and the data processing unit establishes a nonlinear mapping relation between the monitoring data and the tunnel soil pressure and the steel bar stress through a fitting algorithm based on a least square support vector machine, predicts the soil pressure and the steel bar stress in the construction process by adopting a bacterial foraging algorithm based on a time sequence, and sends out monitoring and early warning if the predicted value exceeds a warning value continuously for three times in one day.
Optionally, in one embodiment, the data acquisition unit includes:
the measuring structure is respectively used for monitoring and acquiring displacement change monitoring data in three directions of vault settlement, hole circumference convergence and distance between a monitoring position and a tunnel face;
a protective structure housing each of the measurement structures therein;
and the supporting structure can fix the protection structure on the side wall of the tunnel.
Optionally, in one embodiment, the data acquisition unit includes:
the data monitoring part is used for monitoring and acquiring soil pressure at the arch crown, the arch shoulder and the arch waist and change monitoring data of the steel bar stress at the arch crown and the arch waist;
the data acquisition part is used for collecting and sending the data monitoring unit to the data transmission unit;
a protection structure portion housing each of the data acquisition portions therein;
a support structure portion capable of securing the protective structure portion to a tunnel sidewall.
Optionally, in one embodiment, the data monitoring part includes: the device comprises a soil pressure vault measuring module, a soil pressure arch shoulder measuring module, a soil pressure arch measuring module, a steel bar stress vault measuring module and a steel bar stress arch measuring module; the soil pressure vault measurement module is fixed on the vertical support frame through a support and used for acquiring sampling data corresponding to the vault monitoring direction; the soil pressure arch shoulder measuring module is fixed on the vertical supporting frame through a support and is used for acquiring sampling data corresponding to the monitoring direction of the arch shoulder; the soil pressure arch waist measuring module is fixed on the vertical supporting frame through a bracket and used for acquiring sampling data corresponding to the arch waist monitoring direction; the steel bar stress vault measuring module is fixed on the vertical supporting frame through welding and used for acquiring sampling data corresponding to the vault monitoring direction; the reinforcing steel bar stress arch waist measuring module is fixed on the vertical supporting frame through welding and used for acquiring sampling data corresponding to the arch waist monitoring direction;
optionally, in one embodiment, the data acquisition part
The method comprises the following steps: the automatic data acquisition module and the automatic data transmission module are connected with the data acquisition module; the soil pressure cell signal input line of the automatic data acquisition module is connected with the soil pressure cell signal output line, and the automatic data acquisition module is connected with the reinforcing bar meter signal output line through the reinforcing bar meter signal input line, so that the real-time monitoring of the data monitoring part is realized. The automatic data transmission module is connected with the automatic data acquisition module through a data line, so that the acquired data can be transmitted to the data transmission unit in real time.
Optionally, in one embodiment, the data automatic transmission module includes an automatic collector and a collection box signal transmitting antenna, and the automatic collector is connected to the collection box signal transmitting antenna through a data line; the signal transmitting antenna of the collection box can realize short-distance data wireless transmission.
Optionally, in one embodiment, the protective structure portion includes a box structure composed of a top plate, side plates, and a bottom plate, and a waterproof outer edge of the collection box; the front side plate is fixed on the side plate through a rotating shaft, so that the front side plate can rotate around the rotating shaft, and the box body structure is opened for installation and adjustment; and the waterproof outer edge of the collection box is positioned at the outer edge of the top plate, so that water drops in the hole can be prevented from permeating into the collection box.
Optionally, in one embodiment, the support structure portion comprises bracket bolts, wherein the brackets are fixed to the side walls of the tunnel by the bracket bolts, and two brackets are arranged under one collection box.
Optionally, in one embodiment, the data acquisition unit includes:
a data receiving section for receiving data wirelessly transmitted by the data acquisition unit of claim 2;
a data transmitting section for transmitting the data received by the data receiving section to the data processing unit;
a protection structure portion housing each of the data acquisition portions therein;
a support structure portion capable of securing the protective structure portion to a tunnel sidewall.
Optionally, in one embodiment, the data receiving portion includes a data wireless receiver and a transmission box signal receiving antenna, and the data wireless receiver is connected to the transmission box signal receiving antenna through a data line; the transmission box signal receiving antenna can realize short-distance data wireless transmission.
Optionally, in one embodiment, the data transmission part includes a GPRS signal transmitter and a GPRS signal transmitting antenna, and the GPRS signal transmitter is connected to the data wireless receiver through a data line and configured to receive data; the GPRS signal transmitter is connected with the GPRS signal transmitting antenna through a data line, and transmits data to the data processing unit through the GPRS signal transmitting antenna.
Optionally, in one embodiment, the structural deformation risk prediction and early warning based on a vector machine and a bacterial foraging algorithm corresponding to the data processing unit includes:
s1, establishing sample data { x based on time seriesi}＝{x1,x2,…,xnThe sample data comprises vault soil pressure, arch shoulder soil pressure, arch waist soil pressure, vault steel bar stress and arch waist steel bar stress;
s2, according to the least square support vector machine theory, the nonlinear deformation relation can obtain the nonlinear relation between the soil pressure value and the steel bar stress value change sequence by learning the obtained actual soil pressure value and the steel bar stress value through the support vector machine;
s3, determining the mapping relation corresponding to the training set to obtain a nonlinear mapping model, and optimizing the nonlinear mapping model through the tropism operation, the copying operation and the migration operation of the bacterial foraging algorithm based on the nonlinear mapping model to realize rolling prediction of the structural deformation risk.
Optionally, in one embodiment, the S2 includes:
s21, acquiring soil pressure and steel bar stress data of a monitoring section corresponding to each advancing one-grade of the tunnel face based on the data of the distance between the determined monitoring position and the tunnel face;
s22, predicting the nonlinear change sequence, namely searching the soil pressure and the steel bar stress at the moment p +1 and the soil pressure and the steel bar stress x at the previous moments1,x2,…,xpA relation of (1), i.e. xp+1＝f(x1,x2,…,xp) The non-linear relationship between the soil pressure and the stress change sequence of the steel bars is represented as a learning function.
S23, using the theory of least square support vector machine to process the time series dataAnd (4) learning: for n-p deformed sequences xi,xi+1,…,xi+pAnd (i is 1, 2, …, n-p), obtaining a nonlinear relation between the soil pressure and the stress change sequence of the reinforcing steel bars,
in the formula, y (x)p+1) The soil pressure and the stress value x of the steel bar at the p +1 th momentp+1P soil pressures and the stress value of the steel bar at the moment p +1, xp+1＝f(x1,x2,…,xp+1) The first p soil pressures and the stress value of the steel bar at the p + k moment position, xk＝(xk,xk+1,…,xk+p+1)。
Optionally, in one embodiment, the S3 includes:
s31, setting the mapping form of the learning sample as { x1,x2,…,xp}→{xp+1}， {x2,x3,…,xp+1}→{xp+2}…{xn-p,xn-p+1,…,xn-1}→{xn}. The result of the learning of the vector machine is that the data of the current position can be predicted by P historical data before the prediction point, for example, x needs to be predictedn+1Only need to input, { xn-p+1,xn-p+2,…,xnObtaining a prediction result; then will predict the obtained xn+1As a known quantity, { x }n-p+2,xn-p+3,…,xn+1As a new timing pair xn+2And (6) performing prediction.
S32, but some errors still exist in each prediction step in the prediction process, and the errors are accumulated continuously with the increase of the number of the prediction steps, and finally the prediction result cannot accurately express the real working condition. In order to reduce the influence of the error, Q accurately determined influence parameters are added into the input time sequence, and the prediction process of each step is effectively corrected. And (3) searching for optimal parameters by using a bacterial foraging optimization algorithm BFOA through a tropism operation, a replication operation and a migration operation, and optimally solving the problem that the non-linear prediction algorithm of the minimum two-times support vector machine has high dependence on two parameters, namely the optimal historical step number p and the influence factor Q.
And S33, performing corresponding rolling prediction on the sampling data obtained by the data acquisition unit based on the optimized nonlinear prediction model.
Has the advantages that:
1. the invention makes up the defects of high risk, low frequency and large error of manual measurement, thereby realizing real-time automatic and accurate monitoring of tunnel soil pressure and reinforcing steel bar stress and providing guarantee for tunnel safe construction; meanwhile, the fixing, instrument water-proof and anti-collision protection of the collection box and the transmission box are considered, and the service lives of the collection box and the transmission box are prolonged; the short-distance wireless transmission system and the GPRS information transmission assembly are used, the use of a long-distance signal data line is replaced, the monitoring cost is effectively reduced, and the applicability of the equipment is improved. The data transmission unit can upload data to the cloud end, and multi-terminal real-time acquisition can be realized; and the data processing unit can train a nonlinear prediction model according to the monitoring data of the cloud, so that the rolling prediction of the structural deformation risk is realized.
2. A set of monitoring system of the internet of things suitable for a hole pile method (PBA) underground excavation station is constructed, real-time monitoring of soil pressure and reinforcing steel bar stress and automatic uploading of monitoring data are achieved, and the defects of high risk, low frequency and large error of manual measurement are overcome.
3. The short-distance wireless transmission system and the GPRS information transmission assembly are used, the use of a long-distance signal data line is replaced, the monitoring cost is effectively reduced, and the applicability of the equipment is improved.
4. The detection box and the transmission box are provided with corresponding waterproof and dustproof protective cases and placing supports, and the practicability of the equipment in a complex limited space construction environment is improved.
5. The remote data processing unit uses a vector machine optimized by a bacterial foraging algorithm to form a non-linear prediction model trained according to monitoring data of a cloud end, can predict soil pressure and reinforcing steel stress in advance, and carries out structural deformation risk early warning on data exceeding an early warning value.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. A system for predicting risk of deformation of a PBA structure, comprising: the device comprises a data acquisition unit, a data transmission unit and a data processing unit;
the data acquisition unit is used for acquiring the soil pressure at the vault, arch shoulder and arch waist of the tunnel and the change monitoring data of the steel bar stress at the vault and arch waist;
the data transmission unit is used for integrating the soil pressure and the steel bar stress data collected by the data collection unit to form time series monitoring data and sending the time series monitoring data to the data processing unit;
and the data processing unit is used for establishing a nonlinear mapping relation between the monitoring data and the tunnel soil pressure and the steel bar stress through a fitting algorithm based on a least square support vector machine, and predicting the soil pressure and the steel bar stress in the construction process by adopting a bacterial foraging algorithm based on a time sequence.
2. The system of claim 1, in which the data acquisition unit comprises: the device comprises a data monitoring part, a data acquisition part, a protection structure part and a support structure part;
the data monitoring part is used for monitoring and acquiring soil pressure at the arch crown, the arch shoulder and the arch waist and change monitoring data of the steel bar stress at the arch crown and the arch waist;
the data acquisition unit is used for collecting and sending the data monitoring unit to the data transmission unit;
the protection structure part is used for accommodating each data acquisition part;
the support structure portion is used to secure the protective structure portion to the tunnel sidewall.
3. The system for predicting the risk of deformation of a PBA structure according to claim 2, wherein the data monitoring section comprises: the device comprises a soil pressure vault measuring module, a soil pressure arch measurement module, a steel bar stress vault measuring module and a steel bar stress arch measurement module;
the soil pressure vault measurement module is used for acquiring sampling data corresponding to the vault monitoring direction;
the soil pressure arch shoulder measuring module is used for acquiring sampling data corresponding to the monitoring direction of the arch shoulder;
the soil pressure arch waist measuring module is used for acquiring sampling data corresponding to the arch waist monitoring direction;
the steel bar stress vault measurement module is used for acquiring sampling data corresponding to the vault monitoring direction;
the steel bar stress arch waist measuring module is used for acquiring sampling data corresponding to the arch waist monitoring direction.
4. The system for predicting the risk of deformation of a PBA structure according to claim 2, wherein the data collection part comprises: the automatic data acquisition module and the automatic data transmission module are connected with the data acquisition module;
the data automatic acquisition module is used for monitoring the data monitoring part in real time;
the data automatic transmission module is connected with the data automatic acquisition module through a data line, so that the acquired data can be transmitted to the data transmission unit in real time.
5. The system for predicting the risk of deformation of a PBA structure according to claim 2, wherein the data receiving section comprises: a data wireless receiver and a transmission box signal receiving antenna,
the data wireless receiver is connected with the signal receiving antenna of the transmission box through a data line;
the transmission box signal receiving antenna is used for wireless transmission of data.
6. The method for using the PBA structure deformation risk prediction system is characterized by comprising the following steps of:
s1, the data processing unit receives the monitoring data transmitted by the data transmission unit and establishes sample data based on the time sequence, and the sample data comprises: the values of arch crown soil pressure, arch shoulder soil pressure, arch waist soil pressure, arch crown reinforcing steel bar stress and arch waist reinforcing steel bar stress at the ith day;
s2, the data processing unit learns the time series data by using the least square support vector machine theory to obtain the nonlinear relation between the soil pressure value and the reinforcing steel bar stress value change sequence;
s3, the data processing unit determines a mapping relation corresponding to a training set formed by relying on time series monitoring data to obtain a nonlinear prediction model, and based on the nonlinear prediction model, the nonlinear prediction model is optimized through the tropism operation, the replication operation and the migration operation of a bacterial foraging algorithm, so that the rolling prediction of the structural deformation risk is realized.
7. The method of using the PBA structure deformation risk prediction system of claim 6, wherein the S2 includes:
s21, acquiring soil pressure and steel bar stress data of the monitoring section of the tunnel face based on the data of the distance between the determined monitoring position and the tunnel face;
s22, predicting the nonlinear change sequence, namely obtaining the relation between the soil pressure and the steel bar stress at the moment p +1 and the soil pressure and the steel bar stress at the previous p moments;
s23, training the relation between the soil pressure and the stress change of the steel bars through time sequence data by using a least square support vector machine theory to obtain the nonlinear relation between the soil pressure and the stress change sequence of the steel bars:
wherein, y (x)p+1) The soil pressure and the steel bar stress value at the moment p +1 are obtained; b is an offset;
as kernel function, K (x, x)k)＝exp{||x-xi||2/σ2}，σ2Is the square bandwidth in the gaussian RBF kernel.
8. The method of predicting risk of deformation of PBA structure according to claim 6, characterized in that said data processing unit, said S3 comprises:
s31, establishing a nonlinear prediction model by utilizing a nonlinear relation between the soil pressure value and the stress value change sequence of the steel bar, wherein the nonlinear prediction model is used for predicting data of the current position P +1 through the previous P pieces of historical data;
s32, adding underground water level influence parameters in the input process, and correcting the prediction process in each step:
s321, tropism operation: carrying out any possible increase or decrease change on the data value within a set range on the group of time series monitoring data to obtain a group of new time series monitoring data, and repeatedly operating;
s322, copy operation: when the trending operation reaches a set critical time, all time series monitoring data are sequentially arranged from large to small by taking the absolute value of the predicted value from the monitoring value as an evaluation index, the data of 50% of the last time series monitoring data are deleted, and the data of 50% of the first time series monitoring data are copied;
s323, migration operation: when the migration operation occurs in the process of needing to predict the next data, the execution reference point is used for keeping the data after the copying operation is carried out to the set limit step, and if the data meets the requirements; if the data does not meet the requirements, deleting the data;
s33, carrying out corresponding rolling prediction on the sampling data obtained by the data acquisition unit based on the nonlinear prediction model optimized by the bacterial foraging algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111173770.2A CN113916183B (en) | 2021-10-09 | 2021-10-09 | PBA structure deformation risk prediction system and application method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111173770.2A CN113916183B (en) | 2021-10-09 | 2021-10-09 | PBA structure deformation risk prediction system and application method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113916183A true CN113916183A (en) | 2022-01-11 |
| CN113916183B CN113916183B (en) | 2023-11-28 |
Family
ID=79238340
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111173770.2A Active CN113916183B (en) | 2021-10-09 | 2021-10-09 | PBA structure deformation risk prediction system and application method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113916183B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102587986A (en) * | 2012-03-12 | 2012-07-18 | 西安建筑科技大学 | Tunnel construction informatization dynamic monitoring system and monitoring method thereof |
| CN102610055A (en) * | 2011-12-19 | 2012-07-25 | 大连海事大学 | Wireless intelligent alarming system for automatically monitoring multivariate information of tunnel |
| CN103075195A (en) * | 2012-12-28 | 2013-05-01 | 西北大学 | Measurement system and method for stress of surrounding rock of hipparion red soil tunnel under influence of crack water |
| CN105070175A (en) * | 2015-08-05 | 2015-11-18 | 三峡大学 | Two-dimensional landslide model |
| CN105696633A (en) * | 2016-03-31 | 2016-06-22 | 中国电建集团华东勘测设计研究院有限公司 | Monitoring system and monitoring method for support effect of slide-resistant piles |
| CN106958460A (en) * | 2017-05-16 | 2017-07-18 | 山东大学 | A kind of wisdom sensory perceptual system and method suitable for tunneling and underground engineering monitoring measurement information |
| CN109145463A (en) * | 2018-08-27 | 2019-01-04 | 北京住总集团有限责任公司 | A kind of deformation analysis method for during tunnel excavation |
| CN109165406A (en) * | 2018-07-20 | 2019-01-08 | 大连海事大学 | The quick dynamic classification prediction technique of country rock during a kind of constructing tunnel |
| CN210375219U (en) * | 2019-10-15 | 2020-04-21 | 中铁建大桥工程局集团第六工程有限公司 | Engineering stability thing networking real-time monitoring system suitable for tunnel entrance to a cave section |
| CN112879025A (en) * | 2021-02-04 | 2021-06-01 | 中铁十六局集团北京轨道交通工程建设有限公司 | Earth pressure balance shield earth pressure intelligent regulation and control method based on GRU deep learning |
-
2021
- 2021-10-09 CN CN202111173770.2A patent/CN113916183B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102610055A (en) * | 2011-12-19 | 2012-07-25 | 大连海事大学 | Wireless intelligent alarming system for automatically monitoring multivariate information of tunnel |
| CN102587986A (en) * | 2012-03-12 | 2012-07-18 | 西安建筑科技大学 | Tunnel construction informatization dynamic monitoring system and monitoring method thereof |
| CN103075195A (en) * | 2012-12-28 | 2013-05-01 | 西北大学 | Measurement system and method for stress of surrounding rock of hipparion red soil tunnel under influence of crack water |
| CN105070175A (en) * | 2015-08-05 | 2015-11-18 | 三峡大学 | Two-dimensional landslide model |
| CN105696633A (en) * | 2016-03-31 | 2016-06-22 | 中国电建集团华东勘测设计研究院有限公司 | Monitoring system and monitoring method for support effect of slide-resistant piles |
| CN106958460A (en) * | 2017-05-16 | 2017-07-18 | 山东大学 | A kind of wisdom sensory perceptual system and method suitable for tunneling and underground engineering monitoring measurement information |
| CN109165406A (en) * | 2018-07-20 | 2019-01-08 | 大连海事大学 | The quick dynamic classification prediction technique of country rock during a kind of constructing tunnel |
| CN109145463A (en) * | 2018-08-27 | 2019-01-04 | 北京住总集团有限责任公司 | A kind of deformation analysis method for during tunnel excavation |
| CN210375219U (en) * | 2019-10-15 | 2020-04-21 | 中铁建大桥工程局集团第六工程有限公司 | Engineering stability thing networking real-time monitoring system suitable for tunnel entrance to a cave section |
| CN112879025A (en) * | 2021-02-04 | 2021-06-01 | 中铁十六局集团北京轨道交通工程建设有限公司 | Earth pressure balance shield earth pressure intelligent regulation and control method based on GRU deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 郑帅等: "基于机器学习与可靠度算法的围岩动态分级方法及其工程应用", 《岩土力学》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113916183B (en) | 2023-11-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101477207B (en) | Intelligent geological calamity synthetic monitoring system and multi-stage prediction analysis method | |
| CN101813478B (en) | Ground sedimentation monitoring system | |
| CN104236626B (en) | The integrated on-line monitoring system of drainage pipeline liquid level and flow | |
| CN109708688A (en) | A kind of monitoring of history culture building safety and early warning system and method | |
| CN108154651A (en) | A kind of device and method for landslide disaster Monitoring and forecasting system in real-time | |
| CN113779835A (en) | AI and intelligent monitoring system based deep and large foundation pit safety early warning method | |
| CN106205061A (en) | A kind of geological hazards prediction system | |
| US11619556B1 (en) | Construction monitoring method and system for v-shaped column in underground foundation pit, terminal and storage medium | |
| CN106224007A (en) | Safety for tunnel engineering monitoring and warning management system | |
| CN206768889U (en) | A kind of subway foundation pit automates DEFORMATION MONITORING SYSTEM | |
| CN105096532A (en) | Geological disaster predication system | |
| CN103743441A (en) | Multi-factor coupling on-line monitoring system and multi-factor coupling on-line monitoring system method for slope safety | |
| CN206987892U (en) | A kind of prior-warning device for being used to monitor Propagation in Tunnel Disaster | |
| CN113554849A (en) | Air-ground monitoring slope system and instability risk assessment method thereof | |
| CN201331378Y (en) | Vibration tester | |
| CN104950782A (en) | Remote deformation characteristic monitoring system for mountain highway tunnel construction | |
| CN106703086A (en) | Online security monitoring system for foundation pit | |
| CN110173305B (en) | Method for monitoring and early warning whole service life of tunnel structure at fault | |
| CN109183861A (en) | A kind of foundation pit intelligent monitoring method and monitoring system based on mems sensor | |
| CN113847948A (en) | Dynamic compaction automatic monitoring and analyzing method and digital integrated system | |
| CN111504261A (en) | Tunnel three-dimensional automatic laser ranging device with parameter identification function | |
| RU2467298C1 (en) | System of satellite monitoring of engineering facilities displacements using satellite navigation systems glonass/gps | |
| CN209639759U (en) | A kind of downstream Tailings Dam dam inside ess-strain comprehensive monitor system | |
| CN104504769A (en) | Electronic disease collection system for rail transit bridge and tunnel structure and collection and analysis method | |
| CN110307036B (en) | Variable cross-section tunnel structure full-life monitoring and early warning method |
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 |