CN108536200A - A kind of freeze-wellboring engineering based on BP neural network freezes control strategy - Google Patents
A kind of freeze-wellboring engineering based on BP neural network freezes control strategy Download PDFInfo
- Publication number
- CN108536200A CN108536200A CN201810241115.8A CN201810241115A CN108536200A CN 108536200 A CN108536200 A CN 108536200A CN 201810241115 A CN201810241115 A CN 201810241115A CN 108536200 A CN108536200 A CN 108536200A
- Authority
- CN
- China
- Prior art keywords
- neural network
- freeze
- wellboring
- brine
- development
- 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
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D27/00—Simultaneous control of variables covered by two or more of main groups G05D1/00 - G05D25/00
- G05D27/02—Simultaneous control of variables covered by two or more of main groups G05D1/00 - G05D25/00 characterised by the use of electric means
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH DRILLING; MINING
- E21D—SHAFTS; TUNNELS; GALLERIES; LARGE UNDERGROUND CHAMBERS
- E21D1/00—Sinking shafts
- E21D1/10—Preparation of the ground
- E21D1/12—Preparation of the ground by freezing
- E21D1/14—Freezing apparatus
Abstract
The invention discloses a kind of, and the freeze-wellboring engineering based on BP neural network freezes control strategy, by the relational model for establishing the frost wall rule of development and the salt water for Freezing Station output of freezing, frost wall, which is calculated, using model develops required brine temp and flow, to which using the operating of brine energy-saving control system control freezing station equipment, theories integration is provided for optimization freeze design, development freezing engineering automation control engineering application.Relational model in the present invention is established using the theoretical method of BP neural network, directly finds out the inherent non-linear relation between salt water size and the frost wall rule of development by the self-learning capability of neural network according to test data.
Description
Technical field
The present invention relates to freeze-wellboring engineerings to freeze control field, particularly a kind of jelly based on BP neural network
Connection sinking operation freezes control strategy.
Background technology
Pit shaft is built in thick surface soil or incompetent bed or builds other underground engineerings, and freezing process is to pass through astatically
Effective construction method of layer.Frozen Deep difficulty of construction is larger, and there are many influence factor, after Frozen Deep engineering thaws, due to applying
Work design has been determined, most important to the control freezed with the progress of excavation, and the country occurred a lot of due to freezing control not
When, cause disconnected pipe to run leakage salt watered-out well or even the case where pit shaft is scrapped, the quality of control directly influence pit shaft construction at
It loses.In recent years due to the stagnation of coal industry, freezing engineering correlative study is less for foreign countries, and domestic a large amount of engineering constructions are to freezing
Technological progress plays progradation, but is mostly directed to one to two problems and carries out, and is mainly reflected in frozen temperature field, frost-heave force
Etc., the achievement of acquirement plays directive function to freezing control, helps frozen construction unit to improve construction technology, freezes
Depth constantly breaks through record.With the development of science and technology, freezing engineering monitoring means is also constantly progressive, the monitoring that scene obtains
Data are more and more, how to make good use of these data, analysis and summary rule, and to instruct to freeze control the problem of is more and more prominent
Go out.As a whole, domestic frozen construction unit is being freezed to control according further to solidification point field analysis, related monitoring data
Analysis is carried out plus construction experience, but unit in charge of construction's technology is very different, it is difficult to be realized that control experience is shared, be lacked unified mark
Standard, control effect are bad.The present invention proposes a kind of freezing sinking shaft control strategy based on BP neural network, by establishing frost wall
The rule of development with refrigeration Freezing Station output salt water relational model, realize using salt water as the freezing engineering closed loop of variable from
Dynamicization controls.Improve the science of control, rational allocation Freezing Station equipment operation, improve frozen construction informationization, from
Dynamicization is horizontal, ensures the safe and smooth progress of engineering construction, while saving a large amount of electric energy, meets the development of national energy conservation and emission reduction
Direction.
Invention content
The invention discloses a kind of, and the freeze-wellboring engineering based on BP neural network freezes control strategy, is frozen by establishing
The relational model for tying the wall rule of development and the salt water for Freezing Station output of freezing, is calculated using model needed for frost wall development
Then brine temp and flow control refrigeration Freezing Station by brine energy-saving control system and provide corresponding brine temp and stream
Amount for optimization freeze design, carries out freezing engineering automation control to achieve the purpose that automatically control Freezing Station equipment operation
Engineer application provides theories integration.
In order to realize that above-mentioned technical problem, the technical solution that freezing sinking shaft engineering of the present invention freezes control strategy are to use BP
The method of neural network, it is input to correspond to parameter with the frost wall rule of development, and brine temp and flow are output, establish frost wall
The relational model of the rule of development and the salt water of refrigeration Freezing Station output develops required salt using the calculated frost wall of model
Then coolant-temperature gage and flow control brine temp and flow by brine energy-saving control system, jelly are automatically controlled to reach
Tie the purpose of station equipment.
Description of the drawings
Fig. 1 is to freeze strategic process figure.
Fig. 2 is BP neural network relational model.
Fig. 3 is brine energy-saving control system structure chart.
Specific implementation mode
It is better understood from the present invention for convenience, the present invention is described in further details below in conjunction with the accompanying drawings.
The present invention discloses a kind of freeze-wellboring engineering based on BP neural network and freezes control strategy, and key is to freeze
The foundation of the wall rule of development and the relational model of the salt water of refrigeration Freezing Station output, can be effective using the method for BP neural network
Construct the relational model.As shown in Fig. 2, first, obtaining the frost wall rule of development by respective sensor and corresponding to parameter：Freeze
Wall humidity freezes the monitoring data such as wall temperature, the interior outside spreading range of each crucial stratum frost wall, frost wall effective thickness, whole
Reason analyzes actual parameter data, and as the input of BP neural network relational model, model of the present invention is using only there are one implicit
3 layer network structures of layer, output unit are frigo brine temp, frigo brine flow, the two parameters can pass through brine
Temperature sensor and flow sensor on circulation path monitor to obtain.The present invention chooses training sample of 20 groups of data as model
This, is by the forward-propagating process and error back propagation process of e-learning, constantly regulate network weight and threshold value, until defeated
Go out and met the requirements with the error of desired output, then illustrates that this cyberrelationship model training is completed, while separately taking 3 groups of data as inspection
Sample is tested, with the predictive ability of cyberrelationship model after inspection training.Then will in the model use to Practical Project, input pair
It answers in parameter to relational model, by the calculated required brine temp of model and flow, then passes through salt water Energy Saving Control
System controls brine temp and flow as shown in figure 3, with practical brine temp and current capacity contrast, to control freezing station equipment
Operation.
Claims (5)
1. a kind of freeze-wellboring engineering based on BP neural network freezes control strategy, it is characterised in that：Freezed by establishing
The relational model of the wall rule of development and the salt water of refrigeration Freezing Station output calculates frost wall using model and develops required salt
Then coolant-temperature gage and flow control refrigeration Freezing Station by brine energy-saving control system and provide corresponding brine temp and stream
Amount, to achieve the purpose that automatically control Freezing Station equipment operation.
2. a kind of freeze-wellboring engineering based on BP neural network according to claim 1 freezes control strategy, special
Sign is：The relational model is established using the method for BP neural network, is input, brine temp with the frost wall rule of development
It is output with flow, while chooses 20 groups of corresponding datas as training sample training pattern, separately takes 3 groups of data as inspection sample
This, with the predictive ability of network after inspection training.
3. a kind of freeze-wellboring engineering based on BP neural network according to claim 1 freezes control strategy, special
Sign is：The frost wall rule of development monitors following gain of parameter by respective sensor：Frost wall humidity freezes wall temperature
Outside spreading range, effective thickness in degree, each crucial stratum frost wall, and as the input parameter of relational model.
4. a kind of freeze-wellboring engineering based on BP neural network according to claim 1 freezes control strategy, special
Sign is：The brine temp and flow are monitored by respective sensor to be obtained, and as the output parameter of relational model.
5. a kind of freeze-wellboring engineering based on BP neural network according to claim 1 freezes control strategy, special
Sign is：The operating for freezing station equipment is controlled by brine energy-saving control system, passes through the calculated required brine of model
Temperature and flow, and practical brine temp and current capacity contrast, to which control freezing station equipment provides corresponding brine temp and salt
Water flow.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810241115.8A CN108536200A (en) | 2018-03-22 | 2018-03-22 | A kind of freeze-wellboring engineering based on BP neural network freezes control strategy |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810241115.8A CN108536200A (en) | 2018-03-22 | 2018-03-22 | A kind of freeze-wellboring engineering based on BP neural network freezes control strategy |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108536200A true CN108536200A (en) | 2018-09-14 |
Family
ID=63484176
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810241115.8A Pending CN108536200A (en) | 2018-03-22 | 2018-03-22 | A kind of freeze-wellboring engineering based on BP neural network freezes control strategy |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108536200A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112943220A (en) * | 2021-03-03 | 2021-06-11 | 安徽理工大学 | Monitoring device for freezing general profile of stratum well wall |
| CN113216982A (en) * | 2021-05-25 | 2021-08-06 | 中铁一局集团有限公司 | Tunnel freezing intelligent end head and application method, system, equipment and medium thereof |
| CN113515880A (en) * | 2021-03-11 | 2021-10-19 | 中国市政工程中南设计研究总院有限公司 | Freeze swelling and thaw collapse deformation mechanism research method and device based on deep learning near-sea large shield tunnel freezing method |
| CN113515877A (en) * | 2021-03-11 | 2021-10-19 | 中国市政工程中南设计研究总院有限公司 | Method and device for optimizing temperature characteristics of frozen soil body of oversized shield section based on Gaussian process machine learning |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB190416415A (en) * | 1904-07-25 | 1905-05-18 | Anton Raky | Improvements in Tubbing or Lining for Shaft Sinking by the Employment of the Freezing Process. |
| CN103132535A (en) * | 2012-12-28 | 2013-06-05 | 神华集团有限责任公司 | Frozen earth boundary control system and method for controlling frozen earth boundary |
| CN104453911A (en) * | 2014-12-02 | 2015-03-25 | 淮南矿业(集团)有限责任公司 | Freezer and vertical shaft freezing system |
| CN104594908A (en) * | 2015-02-04 | 2015-05-06 | 安徽理工大学 | Automatic control method of heat exchange scale of freezing shaft sinking engineering |
-
2018
- 2018-03-22 CN CN201810241115.8A patent/CN108536200A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB190416415A (en) * | 1904-07-25 | 1905-05-18 | Anton Raky | Improvements in Tubbing or Lining for Shaft Sinking by the Employment of the Freezing Process. |
| CN103132535A (en) * | 2012-12-28 | 2013-06-05 | 神华集团有限责任公司 | Frozen earth boundary control system and method for controlling frozen earth boundary |
| CN104453911A (en) * | 2014-12-02 | 2015-03-25 | 淮南矿业(集团)有限责任公司 | Freezer and vertical shaft freezing system |
| CN104594908A (en) * | 2015-02-04 | 2015-05-06 | 安徽理工大学 | Automatic control method of heat exchange scale of freezing shaft sinking engineering |
Non-Patent Citations (1)
| Title |
|---|
| 卫建军: "基于神经网络模型的立井冻结施工预测研究", 《采矿与安全工程学报》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112943220A (en) * | 2021-03-03 | 2021-06-11 | 安徽理工大学 | Monitoring device for freezing general profile of stratum well wall |
| CN112943220B (en) * | 2021-03-03 | 2023-06-20 | 安徽理工大学 | Monitoring device for stratum well wall freezing profile |
| CN113515880A (en) * | 2021-03-11 | 2021-10-19 | 中国市政工程中南设计研究总院有限公司 | Freeze swelling and thaw collapse deformation mechanism research method and device based on deep learning near-sea large shield tunnel freezing method |
| CN113515877A (en) * | 2021-03-11 | 2021-10-19 | 中国市政工程中南设计研究总院有限公司 | Method and device for optimizing temperature characteristics of frozen soil body of oversized shield section based on Gaussian process machine learning |
| CN113515877B (en) * | 2021-03-11 | 2023-12-29 | 中国市政工程中南设计研究总院有限公司 | Super-large shield section frozen soil body temperature characteristic optimizing method and device based on Gaussian process machine learning |
| CN113216982A (en) * | 2021-05-25 | 2021-08-06 | 中铁一局集团有限公司 | Tunnel freezing intelligent end head and application method, system, equipment and medium thereof |
| CN113216982B (en) * | 2021-05-25 | 2022-06-17 | 中铁一局集团有限公司 | Tunnel freezing intelligent end head and application method, system, equipment and medium thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108536200A (en) | A kind of freeze-wellboring engineering based on BP neural network freezes control strategy | |
| Lai et al. | A state-of-the-art review of sustainable energy based freeze proof technology for cold-region tunnels in China | |
| Spitler | Ground-source heat pump system research—past, present, and future | |
| CN104597222A (en) | Large frozen soil model test system with moisturizing function and frost heaving test function | |
| JP2021534337A (en) | Freezing method and freezing system for connecting passages | |
| CN105045307B (en) | A kind of mass concrete overall process intelligent temperature control system and method | |
| CN110080202B (en) | Horizontal freezing reinforcement structure for foundation pit bottom and construction method | |
| CN206052685U (en) | Screw thread freezing pipe | |
| CN103823043A (en) | Multifunctional model test box for frozen soil retaining wall | |
| CN106706697A (en) | Model test device for simulating pre-cooling freezing method construction under flowing effect of underground water | |
| CN208476921U (en) | A kind of ponding Frozen-thawed cycled effect simulation of permafrost region tunnel-liner behind part, monitoring device | |
| CN102879552A (en) | Freeze thawing and frost heaving model test device and testing method thereof | |
| CN105908696A (en) | Foundation pit frozen soil retaining wall device and freezing method thereof | |
| CN104404952A (en) | Pile quality control method based on synchronization of drill lifting and pile-forming speeds for long spiral pile machine | |
| CN101270572B (en) | Dam construction method using refrigeration technique | |
| CN109024605B (en) | Temperature control system for gridding concrete dam | |
| CN102680027A (en) | Method for calculating displacement and discharging time in dynamical precipitation process of pressure-load fully penetrating well or well group | |
| CN205808785U (en) | The producing device of concrete Contact Frozen Soil face direct shear test sample | |
| CN102778260B (en) | Calculation method for water drainage and water drainage time in dynamic precipitation process of submersible fully penetrating well or well group | |
| CN112083025A (en) | Servo type soil body frost heaving and thawing sinking test device and test method thereof | |
| CN114150718B (en) | Early warning treatment and detection process for underground structure non-uniform settlement diseases | |
| Huang et al. | Influence of seepage flow on temperature field around an artificial frozen soil through model testing and numerical simulations | |
| CN115308022A (en) | Subway connection channel freezes analogue test system | |
| CN107290981B (en) | Freezing ring control system used in tunnel engineering freezing method construction | |
| CN210049232U (en) | Intelligent construction system for large-diameter deep mixing composite pile |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180914 |