CN113744503B - Distributed flexible edge intelligent early warning and forecasting system and method for karst ground collapse - Google Patents
Distributed flexible edge intelligent early warning and forecasting system and method for karst ground collapse Download PDFInfo
- Publication number
- CN113744503B CN113744503B CN202111008923.8A CN202111008923A CN113744503B CN 113744503 B CN113744503 B CN 113744503B CN 202111008923 A CN202111008923 A CN 202111008923A CN 113744503 B CN113744503 B CN 113744503B
- Authority
- CN
- China
- Prior art keywords
- measuring tube
- early warning
- soil
- forecasting
- measuring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/10—Alarms for ensuring the safety of persons responsive to calamitous events, e.g. tornados or earthquakes
-
- E—FIXED CONSTRUCTIONS
- E02—HYDRAULIC ENGINEERING; FOUNDATIONS; SOIL SHIFTING
- E02D—FOUNDATIONS; EXCAVATIONS; EMBANKMENTS; UNDERGROUND OR UNDERWATER STRUCTURES
- E02D1/00—Investigation of foundation soil in situ
- E02D1/08—Investigation of foundation soil in situ after finishing the foundation structure
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B7/00—Measuring arrangements characterised by the use of electric or magnetic techniques
- G01B7/16—Measuring arrangements characterised by the use of electric or magnetic techniques for measuring the deformation in a solid, e.g. by resistance strain gauge
- G01B7/18—Measuring arrangements characterised by the use of electric or magnetic techniques for measuring the deformation in a solid, e.g. by resistance strain gauge using change in resistance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Environmental & Geological Engineering (AREA)
- Chemical & Material Sciences (AREA)
- Medical Informatics (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Geology (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Computing Systems (AREA)
- Analytical Chemistry (AREA)
- Soil Sciences (AREA)
- Mining & Mineral Resources (AREA)
- Paleontology (AREA)
- Civil Engineering (AREA)
- Structural Engineering (AREA)
- Pit Excavations, Shoring, Fill Or Stabilisation Of Slopes (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
- Investigating Or Analyzing Materials By The Use Of Electric Means (AREA)
Abstract
The invention discloses a karst ground collapse distributed flexible edge intelligent early warning and forecasting system and a method, wherein the system comprises a polymer measuring tube, a flexible conductive film, a signal processing module and a multi-source data fusion and early warning and forecasting module; the polymer measuring tube is laid below the critical depth of the karst soil cave in a horizontal directional drilling mode, and a plurality of flexible conductive films and metal electrodes on two sides of the flexible conductive films are distributed on the surface of the polymer measuring tube; the metal electrode is connected to the signal processing module through a lead; the signal processing module acquires resistance signals of all flexible conducting films on the measuring tube and calculates bending and shearing deformation of the measuring tube, the distribution of soil deformation fields and soil cave boundaries around the measuring tube are estimated through a multivariate Taylor series expansion Kalman filtering algorithm in the multi-source data fusion module, the depth and the boundary development rate of the soil cave are forecasted through a Bayesian optimization random forest Kalman filtering algorithm in the early warning forecasting module, and when the forecast soil cave development depth reaches the critical depth of the soil cave, a karst ground collapse early warning signal is triggered.
Description
Technical Field
The invention relates to the technical field of geological disaster monitoring and early warning, and mainly relates to a karst ground collapse distributed flexible edge intelligent early warning and forecasting system and method.
Background
The ground collapse is one of the geological disasters which are most widely distributed and have the highest occurrence frequency in China. The wide distribution of the soluble rock stratum is one of the main reasons for frequent ground collapse in China, and according to statistics, the karst area in China approximately occupies over 1/3 of the area of the national soil. The filling of the soil body on the underground karst cave causes the gradual development of the soil cave in the covering layer and finally causes the whole collapse from the top plate of the soil cave to the earth surface, which is the most main damage form of the collapse of the karst ground. Urban karst ground collapse often occurs in densely populated areas, and serious casualties and property loss can be caused due to concealment and burstiness of the ground collapse.
The 'positioning, timing and quantifying' for detecting the development state of the karst soil cave is always the bottleneck problem of accurate monitoring and early warning. By using traditional geophysical prospecting methods such as geological radar, cross-hole seismic CT, high-density electrical method and ultrasonic method, automatic monitoring and unmanned remote measurement cannot be realized, so that it is always difficult to timely identify karst ground subsidence and accurately monitor and early warn.
The distributed photoelectric sensing technology such as a Time Domain Reflectometer (TDR) or a Brillouin Optical Time Domain Reflectometer (BOTDR) and the like adopts cables such as coaxial cables or communication optical cables and the like as distributed sensors to be implanted into rock and soil bodies, and can realize distributed automatic monitoring of soil body settlement deformation. However, the coupling degree of the cable and the soil body is not high, so that the cable and the soil body deform and relatively slide after the soil body is settled; and the ultimate tensile deformation of the optical cable is only 1.3%, the optical cable is easy to break after the soil body is settled and deformed greatly, the factors can cause the frequent occurrence of false alarm and missing alarm, and the timeliness and the accuracy of monitoring and early warning of the subsidence of the karst ground are reduced.
Machine learning is the core of artificial intelligence, and the method does not need an explicit mathematical expression, but establishes a mapping relation according to hidden causal connection among a large amount of data through repeated training to realize data mining or knowledge discovery, and provides a chance for improving the accuracy of geological disaster monitoring and early warning by applying the machine learning. Edge computing is an extension of cloud computing, and refers to an advanced technology for providing computing power near a sensing end or a data source side. The edge intelligence is the last kilometer of artificial intelligence, and is that a machine learning algorithm is deployed on edge equipment to provide edge calculation with functions of scene perception, data analysis, real-time decision and the like nearby. Edge intelligence has been widely applied to many industrial fields such as security protection and robot, but still has not been applied to the monitoring and early warning field that karst ground collapses at present.
Disclosure of Invention
The purpose of the invention is as follows: aiming at the problems in the background technology, the invention provides a karst ground collapse distributed flexible edge intelligent early warning and forecasting system and method, which aim to solve the bottleneck problem of positioning, timing and quantifying for representing the development state of a karst soil cave close to the ground in real time.
The technical scheme is as follows: in order to achieve the purpose, the invention adopts the technical scheme that:
a distributed flexible edge intelligent early warning and forecasting system for karst ground collapse comprises a polymer measuring tube, a flexible conductive film, a signal processing module, a multi-source data fusion module and an early warning and forecasting module; the polymer measuring pipe is laid below the critical depth of the soil cave in a horizontal directional drilling mode; a plurality of conductive films are distributed on the surface of the polymer measuring tube, metal electrodes are distributed on two sides of each conductive film, and the metal electrodes are connected to the signal processing module through leads; the signal processing module obtains resistance signals of all flexible conducting films on the measuring tube and calculates bending and shearing deformation of the measuring tube, soil deformation and a soil cave boundary around the measuring tube are estimated through a multivariate Taylor series expansion Kalman filtering algorithm in the multisource data fusion module, the depth and the boundary development rate of the soil cave are forecasted through a Bayesian optimization random forest Kalman filtering algorithm in the early warning forecasting module, and when the forecast soil cave development depth reaches the vicinity of the soil cave critical depth or the soil cave boundary develops to a control position, a karst ground collapse early warning signal is triggered.
Furthermore, each section of polymer measuring tube is provided with a plurality of monitoring sections, and at least two groups of flexible conductive films and metal electrodes at two ends of each flexible conductive film are arranged on each monitoring section, wherein one group of flexible conductive films is coated on the bottom of the measuring tube and is parallel to the ground, and the other group of flexible conductive films is coated on the side surface of the measuring tube and is vertical to the ground.
Furthermore, the flexible conductive film is prepared by mixing a powdery conductive material and an auxiliary agent by taking an organic high molecular polymer as an adhesive; the powdery conductive material is carbon powder or metal powder: the adhesive is silicate gel material or elastic polyester organic high molecular polymer; each section of flexible conductive film is longer than 40mm and wider than 20 mm.
Furthermore, the signal processing module comprises an amplifier chip, a microcontroller, a signal conditioning module, a memory and a temperature compensation chip; the amplifier chip and the signal conditioning module are used for measuring the resistance value of the flexible conducting film, the microcontroller is used for operating the multi-source data fusion and early warning prediction module, the memory is used for storing sensor calibration data and an edge machine learning algorithm, and the temperature compensation chip is used for measuring the ambient temperature of the measuring tube and performing temperature compensation on the resistance measurement value of the flexible conducting film; the signal processing module adopts miniature low-power consumption structure, and every signal processing module is connected with a plurality of conductive films, installs one by one inside every section survey pipe after waterproof packaging, through arranging the cable power supply inside surveying the pipe, realizes 485 bus communication simultaneously.
Furthermore, calibration data of 'resistance change rate-strain' of the flexible conductive film are stored in the memory, the microcontroller can calculate the strain capacity of the flexible conductive film in real time according to the resistance measurement value, and estimate the strain field of the measuring tube and the bending and shearing strain values of the free surface according to the strain data of the flexible conductive film group at different positions on the surface of the measuring tube; the memory also stores calibration data of 'pipe-soil coordinated deformation' of the measuring pipe, and the multi-source data fusion module estimates the distribution of the soil deformation field around the measuring pipe according to the distribution data of the integral strain field of the measuring pipe.
Furthermore, the polymer measuring tube comprises a plurality of sections of PVC material measuring tubes which are rigidly connected, the length of each section of measuring tube is more than 1.5m, and the nominal diameter is more than 50 mm.
An early warning and forecasting method adopting the karst ground collapse distributed flexible edge intelligent early warning and forecasting system comprises the following steps:
step S1, according to actual requirements, arranging a plurality of monitoring sections on the polymer measuring tube, coating a plurality of conducting films on the outer wall of the measuring tube, and connecting each conducting film with a signal processing module through electrodes and leads;
s2, laying a measuring pipe by adopting horizontal directional drilling and dragging pipe construction near the stratum to be monitored, wherein the pipe body is horizontal to the ground, and the depth is determined according to the critical soil cave depth;
step S3, when the soil cave collapses, the top plate of the soil cave continuously grows upwards, the lower part of the measuring tube gradually faces the air and the upper part of the measuring tube is covered, and the empty section of the measuring tube generates obvious bending deformation; meanwhile, in a soil cave boundary area, a relative deformation trend exists between a soil cave top plate and soil bodies on two sides, so that the measuring tube generates obvious shearing deformation, and the resistance change rate of the flexible conductive film is abnormal;
s4, the signal processing module collects the flexible conductive film resistance signal and runs a machine learning algorithm to carry out edge intelligent calculation; specifically, the method comprises the following steps:
the internal memory of the signal processing module stores the calibration data of 'resistance change rate-strain' of the flexible conductive film, and the calibration data is used for the microcontroller to estimate the strain field of the measuring tube and the bending and shearing strain values of the free surface in real time;
the internal memory of the signal processing module stores calibration data of 'pipe-soil coordinated deformation' of the measuring pipe, the multi-source data fusion module realizes multi-source data fusion according to the overall strain field distribution data of the measuring pipe, and the multi-element Taylor series expansion Kalman filtering algorithm is used for estimating the distribution of the soil deformation field around the measuring pipe;
the early warning forecasting module forecasts the depth of the soil cavern and the development rate of the boundary through a Bayesian optimization random forest Kalman filtering forecasting algorithm; and when the soil cave development depth reaches the critical soil cave depth early warning value, immediately triggering an early warning signal.
Furthermore, the multi-source data fusion module adopts a multivariate Taylor series expansion Kalman filtering algorithm, adopts Taylor series to decompose a classic Kalman filtering equation and then carries out data fusion, simultaneously considers a plurality of flexible conducting film monitoring data distributed at different sections and different positions of the measuring tube, and estimates the soil deformation and the soil cave boundary around the measuring tube through data fusion.
Furthermore, the early warning and forecasting module decomposes time sequence data fused by a Bayes optimization random forest Kalman filtering forecasting algorithm into a period item and a trend item, forecasts the period item by the random forest algorithm, forecasts the trend item based on the Kalman filtering, optimizes and adjusts parameters of the model parameter by the Bayes optimization algorithm, and forecasts the depth of the soil cave and the development rate of the boundary according to the fuzzy time sequence fused with multi-source data.
Has the advantages that:
the maximum relative deformation of the flexible conductive film adopted by the invention can reach 80 percent, and the sensor can still effectively work when the karst ground subsidence stratum large deformation suddenly occurs; in addition, the early warning and forecasting system provided by the invention can effectively carry out dynamic tracking and early warning on progressive collapse damage by identifying the distribution of the deformation field of the soil body and measuring the bending and shearing strain values of the pipe free face, estimating the development depth and boundary of the soil cave and forecasting the development trend and speed of the soil cave, thereby realizing disaster prevention and reduction.
Drawings
FIG. 1 is a schematic diagram of pipe-soil coordination deformation of a measuring pipe according to the present invention;
FIG. 2 is a schematic structural diagram of a sensor in the distributed flexible edge intelligent early warning and forecasting system for karst ground collapse according to the present invention;
FIG. 3 is a schematic diagram of an underground layout form of measuring tubes in the karst ground collapse distributed flexible edge intelligent early warning and forecasting system provided by the invention;
FIG. 4 is a schematic diagram of a signal processing module and a main chip in the karst ground collapse distributed flexible edge intelligent early warning and forecasting system provided by the invention;
FIG. 5 is a calibration curve of the resistance change rate-dependent variable correlation of a flexible conductive film used in the intelligent early warning and forecasting system for karst ground collapse distributed flexible edges provided by the invention;
FIG. 6 is a set of experimental data of a model in the distributed flexible edge intelligent early warning and forecasting system for karst ground collapse according to the present invention;
FIG. 7 is a schematic structural diagram of a distributed flexible edge intelligent early warning and forecasting system for karst ground collapse according to the present invention;
FIG. 8 is a flow chart of a multivariate Taylor series expansion Kalman filtering algorithm in a multi-source data fusion module in the karst ground collapse distributed flexible edge intelligent early warning and forecasting system provided by the invention;
FIG. 9 is a flow chart of a Bayesian optimization random forest Kalman filtering algorithm in the karst ground subsidence distributed flexible edge intelligent early warning and forecasting system provided by the invention.
Detailed Description
The present invention will be further described with reference to the accompanying drawings.
The invention provides a distributed flexible edge intelligent early warning and forecasting method and system for karst ground collapse, and a specific application scene is shown in figure 3.
The intelligent early warning and forecasting system adopted by the invention is shown in fig. 7 and comprises a polymer measuring tube, a flexible conducting film, a signal processing module, a multi-source data fusion module and an early warning and forecasting module. The polymer measuring pipe is laid below the critical depth of the soil cave in a horizontal directional drilling mode, a plurality of conducting films and metal electrodes on two sides are distributed on the surface of the polymer measuring pipe, and the electrodes are connected to the signal acquisition and processing module through leads. The signal processing module obtains resistance signals of all flexible conducting films on the measuring tube and calculates bending and shearing deformation of the measuring tube, soil deformation and a soil cave boundary around the measuring tube are estimated through a multivariate Taylor series expansion Kalman filtering algorithm in the multisource data fusion module, the depth and the boundary development rate of the soil cave are forecasted through a Bayesian optimization random forest Kalman filtering algorithm in the early warning forecasting module, and when the forecast soil cave development depth reaches the vicinity of the soil cave critical depth or the soil cave boundary develops to a control position, a karst ground collapse early warning signal is triggered.
The polymer measuring tube adopts a plurality of sections of PVC material measuring tubes which are rigidly connected, the length of each section of measuring tube is more than 1.5m, and the nominal diameter is more than 50 mm.
The method for arranging the flexible conductive film is shown in figure 2, a plurality of monitoring sections are arranged on each section of the polymer measuring tube, at least two groups of flexible conductive films and metal electrodes at two ends of each flexible conductive film are arranged on each monitoring section, one group of flexible conductive films is coated on the bottom of the measuring tube and is parallel to the ground, and the other group of flexible conductive films is coated on the side surface of the measuring tube and is perpendicular to the ground. The organic high molecular polymer is used as a binder and is prepared by mixing a powdery conductive material and an auxiliary agent. The powdery conductive material is carbon powder or metal powder: the adhesive is silicate gel material or elastic polyester organic high molecular polymer. Each section of flexible conductive film is longer than 100cm and wider than 20 cm. The flexible conductive film is made of the additive silicon three-component modified polysiloxane conductive coating, the maximum relative deformation of the flexible conductive film can reach 80%, and the sensor can still work effectively when the karst ground collapses and deforms greatly.
The signal processing module adopted by the invention comprises an amplifier chip, a microcontroller, a signal conditioning module, a memory and a temperature compensation chip. The main chip is shown in fig. 4. The amplifier chip is AD620 chip, and the microcontroller is STM32 singlechip, and the temperature compensation chip is DS18B20 temperature measurement chip. The self-made signal conditioning module is used for measuring the resistance value of the flexible conductive film, the microcontroller is used for operating an early warning algorithm, the memory is used for storing sensor calibration data and an edge machine learning algorithm, and the temperature compensation chip is used for measuring the ambient temperature of the tube and performing temperature compensation on the resistance measurement value of the flexible conductive film. The signal acquisition and storage module adopts a miniature low-power-consumption structure, each signal processing module is connected with a plurality of conductive films, is installed inside each section of the measuring tube one by one after waterproof packaging, and is powered through a cable arranged inside the measuring tube, and meanwhile, 485 bus communication is realized.
The memory stores calibration data of "rate of change of resistance-strain" of the flexible conductive film, as shown in fig. 5. The microcontroller can calculate the strain capacity of the flexible conductive film in real time according to the measured value of the resistance, and estimate the strain field of the measuring tube and the bending and shearing strain values of the free surface according to the strain data of the flexible conductive film group at different positions on the surface of the measuring tube. The memory also stores calibration data of 'pipe-soil coordinated deformation' of the measuring pipe, and the multi-source data fusion module can estimate the distribution of the soil deformation field around the measuring pipe according to the distribution data of the integral strain field of the measuring pipe.
The resistance value of the flexible conducting film of the signal processing module is calculated by a single chip microcomputer, a machine learning algorithm is operated, and the development depth and the development boundary of the soil cave can be identified and the development trend and the development rate of the soil cave can be forecasted according to the measured pipe-soil cooperative deformation principle (shown in figure 1) and the measured values of bending and shearing deformation of the free face and the strain field of the pipe.
The principle of pipe-soil cooperative deformation is shown in figure 1, and before collapse occurs, in the upward development process of a karst soil cave, soil bodies on the top plate of the soil cave are gradually damaged similar to surrounding rocks on the top of an underground cavern, and tension and shear coupling deformation is mainly used. The soil body below the measuring pipe is gradually reduced, the buried measuring pipe can be regarded as an elastic foundation beam, the rigidity of a soil spring below the buried measuring pipe is continuously reduced, the measuring pipe generates settlement deformation, and the flexible conductive film of the PVC pipeline is deformed.
The invention provides a matched early warning and forecasting method based on an early warning and forecasting system of a distributed flexible edge intelligent early warning and forecasting system for karst ground collapse, which specifically comprises the following steps:
step S1, according to actual requirements, arranging a plurality of monitoring sections on the polymer measuring tube, coating a plurality of conducting films on the outer wall of the measuring tube, and connecting each conducting film with a signal processing module through electrodes and leads;
s2, laying a measuring pipe by adopting horizontal directional drilling and dragging pipe construction near the stratum to be monitored, wherein the pipe body is horizontal to the ground, and the depth is determined according to the critical soil cave depth;
step S3, when the soil cave collapses, the top plate of the soil cave continuously grows upwards, the lower part of the measuring tube gradually faces the air and the upper part of the measuring tube is covered, and the empty section of the measuring tube generates obvious bending deformation; meanwhile, in a soil cave boundary area, a relative deformation trend exists between a soil cave top plate and soil bodies on two sides, so that the measuring tube generates obvious shearing deformation, and the resistance change rate of the flexible conductive film is abnormal;
s4, the signal processing module collects the flexible conductive film resistance signal and runs a machine learning algorithm to carry out edge intelligent calculation; specifically, the method comprises the following steps:
the internal memory of the signal processing module stores the calibration data of 'resistance change rate-strain' of the flexible conductive film, and the calibration data is used for the microcontroller to estimate the strain field of the measuring tube and the bending and shearing strain values of the free surface in real time;
the internal memory of the signal processing module stores calibration data of 'pipe-soil coordinated deformation' of the measuring pipe, the multi-source data fusion module realizes multi-source data fusion according to the overall strain field distribution data of the measuring pipe, and the multi-element Taylor series expansion Kalman filtering algorithm is used for estimating the distribution of the soil deformation field around the measuring pipe;
the multi-source data fusion module adopts a multivariate Taylor series expansion Kalman filtering algorithm, the specific algorithm is shown in figure 8, a classical Kalman filtering equation is decomposed by adopting Taylor series and then subjected to data fusion, meanwhile, the monitoring data of a plurality of flexible conductive films distributed at different sections and different positions of the measuring tube are considered, and the deformation of the soil body around the measuring tube and the boundary of a soil cave are estimated through data fusion.
The early warning forecasting module forecasts the depth of the soil cavern and the development rate of the boundary through a Bayesian optimization random forest Kalman filtering forecasting algorithm, and the early warning forecasting module is specifically shown in figure 9; and when the soil cave development depth reaches the critical soil cave depth early warning value, immediately triggering an early warning signal.
The maximum relative deformation of the flexible conductive film adopted by the invention can reach 80 percent, and the sensor can still effectively work when the karst ground subsidence stratum large deformation suddenly occurs; in addition, the multi-source data fusion system provided by the invention estimates the development depth and boundary of the soil cave by identifying the distribution of the deformation field of the soil body and measuring the bending and shearing strain values of the pipe free face, and forecasts the development trend and the development speed of the soil cave by the early warning and forecasting system, so that dynamic tracking early warning can be effectively carried out on progressive collapse damage, and disaster prevention and reduction are realized.
The above description is only of the preferred embodiments of the present invention, and it should be noted that: it will be apparent to those skilled in the art that various modifications and adaptations can be made without departing from the principles of the invention and these are intended to be within the scope of the invention.
Claims (7)
1. A distributed flexible edge intelligent early warning and forecasting system for karst ground collapse is characterized by comprising a polymer measuring tube, a flexible conductive film, a signal processing module, a multi-source data fusion module and an early warning and forecasting module; the polymer measuring pipe is laid below the critical depth of the soil cave in a horizontal directional drilling mode; a plurality of conductive films are distributed on the surface of the polymer measuring tube, metal electrodes are distributed on two sides of each conductive film, and the metal electrodes are connected to the signal processing module through leads; the signal processing module comprises an amplifier chip, a microcontroller, a signal conditioning module, a memory and a temperature compensation chip; the amplifier chip and the signal conditioning module are used for measuring the resistance value of the flexible conductive film, the microcontroller is used for operating the multi-source data fusion and early warning forecasting module, the memory is used for storing sensor calibration data and an edge machine learning algorithm, and the temperature compensation chip is used for measuring the ambient temperature of the measuring tube and performing temperature compensation on the resistance measured value of the flexible conductive film; the microcontroller can calculate the strain capacity of the flexible conductive film in real time according to the resistance measurement value and estimate the strain field of the measuring tube and the bending and shearing strain values of the free surface according to the strain data of the flexible conductive film group at different positions on the surface of the measuring tube; the memory also stores calibration data of 'pipe-soil coordinated deformation' of the measuring pipe, and the multi-source data fusion module estimates the distribution of the soil deformation field around the measuring pipe according to the distribution data of the integral strain field of the measuring pipe; the signal processing modules adopt a miniature low-power-consumption structure, each signal processing module is connected with a plurality of conductive films, and are installed inside each section of the measuring tube one by one after waterproof packaging, and the 485 bus communication is realized simultaneously by supplying power through cables arranged inside the measuring tube; the signal processing module acquires resistance signals of all flexible conducting films on the measuring tube and calculates bending and shearing deformation of the measuring tube, soil deformation and a soil cave boundary around the measuring tube are estimated through a multivariate Taylor series expansion Kalman filtering algorithm in the multisource data fusion module, the depth and the boundary development rate of the soil cave are forecasted through a Bayesian optimization random forest Kalman filtering algorithm in the early warning forecasting module, and a karst ground collapse early warning signal is triggered when the forecast soil cave development depth reaches the vicinity of the soil cave critical depth or the soil cave boundary develops to a control position.
2. The karst ground collapse distributed flexible edge intelligent early warning and forecasting system as claimed in claim 1, wherein each polymer measuring tube is provided with a plurality of monitoring sections, each monitoring section is provided with at least two groups of flexible conductive films and metal electrodes at two ends thereof, one group of the flexible conductive films is coated on the bottom of the measuring tube and is parallel to the ground, and the other group of the flexible conductive films is coated on the side surface of the measuring tube and is perpendicular to the ground.
3. The karst ground collapse distributed flexible edge intelligent early warning and forecasting system as claimed in claim 1, wherein the flexible conductive film is prepared by mixing a powdery conductive material and an auxiliary agent by using an organic high molecular polymer as an adhesive; the powdery conductive material is carbon powder or metal powder: the adhesive is a silicate cementing material or an elastic polyester organic high molecular polymer; each section of flexible conductive film is longer than 30mm and wider than 10 mm.
4. The karst ground collapse distributed flexible edge intelligent early warning and forecasting system as claimed in claim 1, wherein the polymer measuring tubes comprise a plurality of sections of PVC material measuring tubes rigidly connected, each section of measuring tube is longer than 1.5m, and the nominal diameter is greater than 50 mm.
5. An early warning and forecasting method adopting the karst ground collapse distributed flexible edge intelligent early warning and forecasting system as claimed in any one of claims 1 to 4, characterized by comprising the following steps:
step S1, according to the actual requirement, arranging a plurality of monitoring sections on the polymer measuring tube, coating a plurality of conducting films on the outer wall of the measuring tube, and connecting each conducting film with a signal processing module through an electrode and a lead;
s2, laying a measuring pipe by adopting horizontal directional drilling and dragging pipe construction near the stratum to be monitored, wherein the pipe body is horizontal to the ground, and the depth is determined according to the critical soil cave depth;
step S3, when the soil cave collapses, the top plate of the soil cave continuously grows upwards, the lower part of the measuring tube gradually faces the air and the upper part of the measuring tube is covered, and the empty section of the measuring tube generates obvious bending deformation; meanwhile, in a soil cave boundary area, a relative deformation trend exists between a soil cave top plate and soil bodies on two sides, so that the measuring tube generates obvious shearing deformation, and the resistance change rate of the flexible conductive film is abnormal;
s4, the signal processing module collects the flexible conductive film resistance signal and runs a machine learning algorithm to carry out edge intelligent calculation; specifically, the method comprises the following steps:
the calibration data of 'resistance change rate-strain' of a flexible conducting film is stored in the memory of the signal processing module and is used for the microcontroller to estimate the strain field of the measuring tube and the bending and shearing strain values of the free surface in real time;
the internal memory of the signal processing module stores calibration data of 'pipe-soil coordinated deformation' of the measuring pipe, the multi-source data fusion module realizes multi-source data fusion according to the overall strain field distribution data of the measuring pipe, and the deformation field distribution of the soil body around the measuring pipe is estimated based on a multivariate Taylor series expansion Kalman filtering algorithm;
the early warning forecasting module forecasts the depth of the soil cavern and the development rate of the boundary through a Bayesian optimization random forest Kalman filtering forecasting algorithm; and when the soil cave development depth reaches the critical soil cave depth early warning value, immediately triggering an early warning signal.
6. The karst ground collapse distributed flexible edge intelligent early warning and forecasting method as claimed in claim 5, characterized in that the multi-source data fusion module adopts a multivariate Taylor series expansion Kalman filtering algorithm, adopts Taylor series to decompose a classical Kalman filtering equation and then performs data fusion, simultaneously considers monitoring data of a plurality of flexible conductive films distributed at different sections of the measuring tube and different positions, and estimates deformation of soil around the measuring tube and the soil cavity boundary through data fusion.
7. The karst ground collapse distributed flexible edge intelligent early warning and forecasting method as claimed in claim 5, wherein the early warning and forecasting module decomposes time series data fused by a Bayesian optimization random forest Kalman filtering forecasting algorithm into a period item and a trend item, forecasts the period item by the random forest algorithm, forecasts the trend item based on the Kalman filtering, optimizes and adjusts parameters of a model by the Bayesian optimization algorithm, and finally forecasts the depth of a soil cave and the development rate of a boundary according to a fuzzy time series fused by multi-source data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111008923.8A CN113744503B (en) | 2021-08-31 | 2021-08-31 | Distributed flexible edge intelligent early warning and forecasting system and method for karst ground collapse |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111008923.8A CN113744503B (en) | 2021-08-31 | 2021-08-31 | Distributed flexible edge intelligent early warning and forecasting system and method for karst ground collapse |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113744503A CN113744503A (en) | 2021-12-03 |
| CN113744503B true CN113744503B (en) | 2022-06-21 |
Family
ID=78734145
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111008923.8A Active CN113744503B (en) | 2021-08-31 | 2021-08-31 | Distributed flexible edge intelligent early warning and forecasting system and method for karst ground collapse |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113744503B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2617339B (en) * | 2022-04-04 | 2024-06-05 | Anglo American Technical & Sustainability Services Ltd | Method of and system for predicting strata-related risk in an underground environment |
| CN114821976B (en) * | 2022-06-24 | 2022-09-30 | 山东省地质矿产勘查开发局八〇一水文地质工程地质大队(山东省地矿工程勘察院) | Intelligent forecasting system for multi-element karst collapse |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020160667A1 (en) * | 2001-04-26 | 2002-10-31 | Bbnt Solutions Llc | Load measurement device |
| US20070187067A1 (en) * | 2006-02-15 | 2007-08-16 | Hitachi Cable, Ltd. | Heat transfer tube and heat exchanger using same |
| CN102522148A (en) * | 2011-11-15 | 2012-06-27 | 中国计量学院 | Rock-soil body deformation distribution type sensing measuring cable of parallel spiral transmission line structure |
| CN110044710A (en) * | 2019-05-09 | 2019-07-23 | 中国科学院武汉岩土力学研究所 | Soil cave collapse experiment simulator under a kind of precipitation funnel |
| CN110823426A (en) * | 2019-11-13 | 2020-02-21 | 中煤科工集团重庆研究院有限公司 | Dynamic monitoring device and method for mining stress of coal face in hard rock environment |
| CN211015843U (en) * | 2019-05-30 | 2020-07-14 | 南昌大学 | Early warning and protection system for misplaced geological disasters |
| CN111778793A (en) * | 2020-06-23 | 2020-10-16 | 盐城工学院 | Cavity collapse prevention and control structure and construction method |
-
2021
- 2021-08-31 CN CN202111008923.8A patent/CN113744503B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020160667A1 (en) * | 2001-04-26 | 2002-10-31 | Bbnt Solutions Llc | Load measurement device |
| US20070187067A1 (en) * | 2006-02-15 | 2007-08-16 | Hitachi Cable, Ltd. | Heat transfer tube and heat exchanger using same |
| CN102522148A (en) * | 2011-11-15 | 2012-06-27 | 中国计量学院 | Rock-soil body deformation distribution type sensing measuring cable of parallel spiral transmission line structure |
| CN110044710A (en) * | 2019-05-09 | 2019-07-23 | 中国科学院武汉岩土力学研究所 | Soil cave collapse experiment simulator under a kind of precipitation funnel |
| CN211015843U (en) * | 2019-05-30 | 2020-07-14 | 南昌大学 | Early warning and protection system for misplaced geological disasters |
| CN110823426A (en) * | 2019-11-13 | 2020-02-21 | 中煤科工集团重庆研究院有限公司 | Dynamic monitoring device and method for mining stress of coal face in hard rock environment |
| CN111778793A (en) * | 2020-06-23 | 2020-10-16 | 盐城工学院 | Cavity collapse prevention and control structure and construction method |
Non-Patent Citations (1)
| Title |
|---|
| 地层塌陷作用下埋地管道光纤监测试验研究;王德洋 等;《岩土工程学报》;20200615;第42卷(第6期);第1125-1131页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113744503A (en) | 2021-12-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113744503B (en) | Distributed flexible edge intelligent early warning and forecasting system and method for karst ground collapse | |
| CN103743441B (en) | The polynary of a kind of side slope safety is coupling in line monitoring system and method | |
| CN108154651A (en) | A kind of device and method for landslide disaster Monitoring and forecasting system in real-time | |
| CN106706029B (en) | Soil body performance monitoring device for underground structure construction and working method thereof | |
| CN103026394A (en) | Surface-mounted monitoring system | |
| CN110608691B (en) | Landslide deep displacement real-time monitoring system and method based on sound source positioning | |
| US20210109248A1 (en) | System, method, and device for real-time sinkhole detection | |
| JPH11230791A (en) | Monitor | |
| CN111623733A (en) | Multi-field coupling monitoring and early warning system for underground oil and gas pipelines in frozen soil area | |
| CN104075756A (en) | Multiple unit compound wireless monitoring system for service durability of concrete structure | |
| CN204457878U (en) | Without cable, the landslide disaster monitor and early warning system that can work alone for a long time | |
| CN105714842B (en) | Well sinking method for early warning and system | |
| CN103899357A (en) | System and method for real-time visual monitoring and early warning of mine floor water disasters | |
| CN106033637A (en) | Cable-free independent long-term working landslide hazard landslide hazard monitoring early warning method and system | |
| CN106323223B (en) | Highway cutting slope deformation monitoring and early warning system | |
| CN103471647A (en) | Long-distance automatic monitoring method for shield tunnel | |
| Zhang et al. | Real time remote monitoring and pre-warning system for Highway landslide in mountain area | |
| CN204903698U (en) | Insulator pollution flashover early warning device based on meteorological phenomena and neural network | |
| CN113155071A (en) | Foundation pit slope horizontal displacement safety monitoring system | |
| CN206833669U (en) | A kind of slope geological monitoring and warning system | |
| CN109889600A (en) | A kind of groundwater in arid region matter monitoring device | |
| CN103033159B (en) | A kind of shallow-layer geologic shifts monitoring index system system and method | |
| CN107916678B (en) | Immersed tube construction system and method based on BIM | |
| CN206684904U (en) | A kind of Mine production monitoring device | |
| CN215447745U (en) | Monitoring system for tunnel exit side slope |
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 |