CN116699723B - Data processing system and early warning method based on tunnel lining arch part falling block - Google Patents
Data processing system and early warning method based on tunnel lining arch part falling block Download PDFInfo
- Publication number
- CN116699723B CN116699723B CN202310988659.1A CN202310988659A CN116699723B CN 116699723 B CN116699723 B CN 116699723B CN 202310988659 A CN202310988659 A CN 202310988659A CN 116699723 B CN116699723 B CN 116699723B
- Authority
- CN
- China
- Prior art keywords
- data
- microcontroller
- strip
- tunnel lining
- interface
- 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
- 238000012545 processing Methods 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 title claims abstract description 33
- 230000002159 abnormal effect Effects 0.000 claims abstract description 25
- 230000008569 process Effects 0.000 claims abstract description 5
- 238000001514 detection method Methods 0.000 claims description 54
- 238000004364 calculation method Methods 0.000 claims description 21
- 238000013527 convolutional neural network Methods 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 11
- 238000007781 pre-processing Methods 0.000 claims description 11
- 238000004458 analytical method Methods 0.000 claims description 9
- 238000013145 classification model Methods 0.000 claims description 7
- 230000001186 cumulative effect Effects 0.000 claims description 5
- 239000002184 metal Substances 0.000 claims description 5
- 229910052751 metal Inorganic materials 0.000 claims description 5
- 238000003491 array Methods 0.000 claims description 3
- 229910044991 metal oxide Inorganic materials 0.000 claims description 3
- 150000004706 metal oxides Chemical class 0.000 claims description 3
- 239000004065 semiconductor Substances 0.000 claims description 3
- 230000000875 corresponding effect Effects 0.000 description 20
- 238000012544 monitoring process Methods 0.000 description 8
- 230000008439 repair process Effects 0.000 description 8
- 230000008859 change Effects 0.000 description 5
- 238000003709 image segmentation Methods 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 5
- 238000011176 pooling Methods 0.000 description 5
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 4
- PXHVJJICTQNCMI-UHFFFAOYSA-N Nickel Chemical compound [Ni] PXHVJJICTQNCMI-UHFFFAOYSA-N 0.000 description 4
- 230000003321 amplification Effects 0.000 description 4
- 239000003086 colorant Substances 0.000 description 4
- 230000001276 controlling effect Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000003199 nucleic acid amplification method Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 201000010099 disease Diseases 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 238000006073 displacement reaction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 210000002569 neuron Anatomy 0.000 description 3
- 230000001105 regulatory effect Effects 0.000 description 3
- 230000002787 reinforcement Effects 0.000 description 3
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 2
- 230000004913 activation Effects 0.000 description 2
- 239000000956 alloy Substances 0.000 description 2
- 229910045601 alloy Inorganic materials 0.000 description 2
- 230000000903 blocking effect Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 229910052802 copper Inorganic materials 0.000 description 2
- 239000010949 copper Substances 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 2
- 238000005336 cracking Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000005669 field effect Effects 0.000 description 2
- 229910052742 iron Inorganic materials 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 229910052759 nickel Inorganic materials 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000003466 welding Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000009423 ventilation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21F—SAFETY DEVICES, TRANSPORT, FILLING-UP, RESCUE, VENTILATION, OR DRAINING IN OR OF MINES OR TUNNELS
- E21F17/00—Methods or devices for use in mines or tunnels, not covered elsewhere
- E21F17/18—Special adaptations of signalling or alarm devices
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
- G01B11/022—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness by means of tv-camera scanning
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/16—Measuring arrangements characterised by the use of optical techniques for measuring the deformation in a solid, e.g. optical strain gauge
-
- 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
- G01B7/003—Measuring arrangements characterised by the use of electric or magnetic techniques for measuring position, not involving coordinate determination
-
- 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
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V11/00—Prospecting or detecting by methods combining techniques covered by two or more of main groups G01V1/00 - G01V9/00
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V3/00—Electric or magnetic prospecting or detecting; Measuring magnetic field characteristics of the earth, e.g. declination, deviation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V8/00—Prospecting or detecting by optical means
- G01V8/10—Detecting, e.g. by using light barriers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/20—Hydro energy
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Geophysics (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Mining & Mineral Resources (AREA)
- Geology (AREA)
- Remote Sensing (AREA)
- Environmental & Geological Engineering (AREA)
- Geochemistry & Mineralogy (AREA)
- Investigating Or Analyzing Materials By The Use Of Electric Means (AREA)
- Image Analysis (AREA)
Abstract
A data processing system based on tunnel lining arch falling blocks and an early warning method thereof relate to the technical field of data processing, and the data processing system based on tunnel lining arch falling blocks is characterized in that a plurality of strip resistors are arranged in the longitudinal direction and the transverse direction of the inside or the surface of the tunnel lining arch, a microcontroller calculates the resistance value of the strip resistor and compares historical data of the resistance value of the same strip resistor, and an image acquisition device is controlled to acquire image data of an area where the corresponding strip resistor is located according to whether the resistance value of the strip resistor is abnormal or not and process the image data. A method for early warning of a data processing system based on tunnel lining arch dropping includes the steps that S1, resistance values of strip-shaped resistors are measured; s2, the image acquisition device acquires images of the occurrence positions of abnormal resistance value data of the strip resistor; s3, obtaining classification result data; and S4, judging the early warning level.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a data processing system and an early warning method based on tunnel lining arch dropping.
Background
The tunnel built in China has the characteristics of complex and changeable geological condition, various structural forms and great technical difficulty. Due to the limitation of the technical level and conditions in the construction period, the tunnel is often imperfect and unreasonable in the design and construction period; meanwhile, the maintenance management in the operation period is often unreasonable due to the restriction of various factors, and the road tunnel cracking disease is continuously caused by the factors; if the crack detection is inaccurate or incomplete, countermeasures can be used untimely, water leakage can be caused in the tunnel when serious, the internal structure of the tunnel and ventilation, lighting and fire-fighting equipment are corroded and damaged, water on the road surface is caused, normal operation of the tunnel is affected, concrete blocks fall off and other phenomena even occur during the operation, and the safety of the tunnel is directly reduced. The tunnel falling blocks often have burstiness, and under the existing tunnel maintenance technology level, the occurrence of the falling blocks is difficult to be prejudged. Traditional detection relies on manual coordination movable detection equipment to detect the inner wall of a tunnel on the ground regularly, but based on the burstiness of crack diseases, the detection result of the detection mode is not ideal, if the detection period is too short, the manual workload is increased, if the detection period is too long, the burst crack diseases cannot be dealt with.
Disclosure of Invention
The invention aims to solve at least one of the problems, and provides a data processing system and a pre-warning method based on tunnel lining arch falling blocks.
The technical solution for realizing the purpose of the invention is as follows:
a data processing system based on tunnel lining arch dropping, comprising: the digital-to-analog converter DAC comprises a serial detection unit, a digital ammeter, a digital-to-analog converter DAC, a microcontroller, an image acquisition device and a direct current power supply, wherein the serial detection unit comprises strip resistors and MOS tubes, and each strip resistor is connected with each MOS tube in series; a plurality of strip resistors are arranged in the tunnel lining arch part or in the longitudinal direction and the transverse direction of the surface, a plurality of series detection units are connected in parallel and sequentially connected with a digital ammeter and a direct current power supply in series to form a current loop, a digital output end of the digital ammeter is connected with a microcontroller to an input interface through a digital-analog converter DAC, an output interface of the microcontroller is connected to a grid electrode of a MOS tube, the output interfaces of the microcontroller are in one-to-one correspondence with the array sequence of the MOS tube, further, each output interface of the microcontroller is in one-to-one correspondence with each strip resistor, the interface positions of the microcontroller are in one-to-one correspondence with the space positions of the strip resistors in the tunnel lining arch part, the output interfaces of the microcontroller are connected with a control interface of an image acquisition device, the interface positions of the microcontroller are in one-to-one correspondence with the space positions of the image acquisition device in the tunnel lining arch part, and further, the strip resistors are in association with the space positions of the image acquisition device; the microcontroller controls the MOS tube array, sequentially and circularly turns on the MOS tube arrays according to the clock sequence, only turns on the MOS tube of one serial detection unit in the same time period, and the digital ammeter sequentially and circularly detects the current value of each serial detection unit and transmits the current value to the microcontroller in real time to calculate the resistance value of the strip resistor, the microcontroller calculates the resistance value of the strip resistor and compares the historical data of the resistance value of the same strip resistor, and the image acquisition device is controlled to acquire the image data of the area where the corresponding strip resistor is positioned according to whether the resistance value of the strip resistor is abnormal or not and processes the image data; it should be noted that the strip resistor is made of a narrow and long metal strip, and is characterized by having a small resistance, being capable of rapidly reacting to current changes, and being made of a metal or alloy having good elasticity, such as copper, iron, nickel, etc., and being capable of generating a certain resistance change when the strip resistor is deformed by external force or pressure, and the change can be monitored by measuring current and voltage; the elasticity of the strip resistor is limited, and the deformation range and the recovery capability of the strip resistor are limited, so that the strip resistor corresponds to the tunnel lining arch part to be cracked and blocked one by one; the purpose of arranging a plurality of strip resistors inside or on the surface of the tunnel lining arch part is to detect dropping conditions, deformation conditions and potential dropping risks of the arch part can be monitored in real time through the resistors, the strip resistors are arranged in the longitudinal direction inside the tunnel lining arch part, radial deformation conditions of the arch part can be detected, namely whether inward collapse or external expansion and the like of the arch occur or not, and the information can be used for predicting dropping risks and timely taking measures to carry out reinforcement repair; the strip-shaped resistor is arranged in the transverse direction of the tunnel lining arch part, so that the transverse deformation condition of the arch part, namely whether transverse displacement or inclination occurs or not can be detected, the information can help to predict the position and degree of the falling block, and measures are taken in time to repair or support; the strip-shaped resistor is arranged on the surface of the arch part of the tunnel lining, so that the crack and damage condition of the arch surface can be detected, and when the crack or damage occurs on the surface of the lining, the value of the resistor can be changed, thereby prompting the overhaul and maintenance work and preventing the occurrence of falling blocks; the strip resistors can be connected with a monitoring system through connecting wires and are provided with corresponding data acquisition and analysis software, deformation conditions of the arch parts are monitored and recorded in real time, and if the risk of falling blocks of the arch parts is detected, measures are taken in time to repair and support so as to ensure safe operation of the tunnel; the purpose of connecting each strip resistor and each MOS tube in series is to form a controlled circuit, the MOS tube is used for controlling the disconnection and connection of the strip resistor, the voltage for conducting the MOS tube is fixed to be a fixed value and higher than the starting voltage, the purpose is to eliminate the effect of the regulating current of the MOS tube, improve the precision of measuring the current value passing through the strip resistor, further calculate the resistance value of the strip resistor with high precision, the starting voltage of the MOSFET (metal oxide semiconductor field effect transistor) is the voltage for starting the conducting current of the MOS tube when the control voltage (also called gate voltage) of the MOS tube reaches a certain voltage, the starting voltage is usually called gate threshold voltage (Vth) for the N-channel MOSFET (NMOS), the starting voltage is the conducting current when the gate voltage is higher than the gate threshold voltage, and normally the gate threshold voltage of the NMOS is a negative number, usually between-0.5V and-3V, for a P-channel MOSFET (PMOS), the turn-on voltage also refers to a gate threshold voltage (Vth), which means that when the gate voltage is smaller than the gate threshold voltage, the PMOS starts to conduct current, usually the gate threshold voltage of the PMOS is positive, usually between 0.5V and 3V, the amplification region of the MOS transistor means that when the MOS transistor is in operation, the change of the input signal causes the amplification degree of the output signal, usually, in the amplification region of the MOS transistor, the current between the drain and the source is controlled by adjusting the gate voltage, so as to realize the amplification of the input signal, however, when the MOS transistor is used as a switch, the operation of adjusting the current is not needed, and the MOS transistor can be switched between on and off only by controlling the gate voltage at a fixed turn-on voltage, specifically when the MOS transistor is used as a switch, when the gate voltage is higher than the critical voltage (also called as the starting voltage), the MOS tube is in an on state, the drain electrode is conducted with the source electrode, when the gate voltage is lower than the critical voltage, the MOS tube is in an off state, the drain electrode is cut off from the source electrode, and the MOS tube can be used as a switch to control the on and off of an output signal by properly adjusting the height of the gate voltage, and the on and off process can be used for realizing the application of digital circuits or switching power supplies and the like; the digital ammeter and the DC power supply are connected in parallel in series in sequence to form a current loop, for example, 2000 or 3000 series detection units are connected in parallel, in the same time period, only one series detection unit is in a conducting state or a working state, the digital ammeter and the DC power supply are connected in series in sequence to form the current loop in the simplified mode, the voltage of the DC power supply is limited to a fixed value, the precision of measuring the voltage value passing through the strip resistor is improved, and then the resistance value of the high-precision strip resistor is calculated; the microcontroller is composed of a Central Processing Unit (CPU), a nonvolatile memory, a volatile memory, peripheral equipment and a supporting circuit, the microcontroller adopts a model for processing Analog signals, a Digital output end of a Digital ammeter is connected to an input interface of the microcontroller through a Digital-to-Analog Converter (DAC), the reading of the Digital ammeter is transmitted to the microcontroller for processing and analysis, and the following is a specific connection mode: firstly, determining the type of an input interface of a microcontroller, finding out a proper DAC chip, selecting the proper DAC chip according to the requirement, for example, 8-bit, 10-bit or 12-bit resolution, connecting a digital input/output Pin between the microcontroller and the DAC chip, which pins may be marked as a Data Pin (Data Pin) or a DIN, ensuring that the connection is correct so that the numerical value can be transmitted correctly, connecting a Clock signal Pin between the microcontroller and the DAC chip, which pins may be marked as a Clock (Clock) or a CLK, for synchronous conversion, ensuring the accuracy of Data, connecting a Reset Pin between the microcontroller and the DAC chip, which pins may be marked as a Reset Pin (Reset) or a RST, for resetting the DAC chip to an initial state, connecting a Vref Pin of the DAC chip to a Vref voltage source, VREF being a reference voltage Pin, vref voltage determining the maximum output voltage of the DAC, connecting a power Pin of the microcontroller and a power Pin of the DAC chip to a proper power voltage, setting the microcontroller to read out a current table, which requires the microcontroller to read and the output the DAC chip to be written and read by a read-out method, and a program for further reading the digital-to be able to read and read by a program; the output interface of the microcontroller can be connected to the grid electrode of the MOS tube to control the on and off of the MOS tube, and the specific connection method is as follows: firstly, determining an output interface of a microcontroller and a gate pin of a MOS tube, wherein the output interface of the microcontroller adopts an analog signal output pin, the gate pin of the MOS tube is usually a control pin, the output pin of the microcontroller is connected to the gate pin of the MOS tube, the connection pin can be ensured to be correctly connected through a wire connection, the connection between the microcontroller and the MOS tube is ensured to be reliable without loosening or short circuit, the connection is performed by using a proper tool and technology, such as welding or using a plug, the output signal of the microcontroller is ensured to be compatible with the working voltage of the MOS tube, the output signal of the microcontroller is matched with the control voltage requirement of the MOS tube, so as to ensure that the signal can correctly control the on and off of the MOS tube, and the following matters are adopted: ensuring that the microcontroller and MOS transistors are in a powered-down state prior to connection to avoid shorts or other damage, carefully researching and understanding the specifications of the microcontroller and MOS transistors prior to connection to ensure proper connection and operation, and possibly also requiring the use of voltage level shifters or level shifters if necessary to ensure level compatibility between the microcontroller and MOS transistors, depending on the electrical characteristics and signal requirements between the microcontroller and MOS transistors; through carrying out digital sequencing to the array of microcontroller output interface and MOS pipe, realize microcontroller output interface and MOS pipe's array order one-to-one, for example connect the microcontroller output interface of MOS pipe 100, the digital serial number of microcontroller output interface is: 001 number interface, 002 number interface, 003 number interface, … …, 100 number interface, and so on, expands to n number interface, and n represents natural number, and the array of MOS pipe has 100 MOS pipes, and the number of MOS pipe is: from the first row to the last row, the numbers are ordered as: no. 001 MOS pipe, 002 MOS pipe, 003 MOS pipe, … …, no. 100 MOS pipe, and so on, expands to n number interface, and n represents natural number, and microcontroller output interface and MOS pipe's array order one-to-one's control relation is: the 001 interface of the microcontroller controls the grid of the 001 MOS tube, the 002 interface of the microcontroller controls the grid of the 002 MOS tube, the 003 interface of the microcontroller controls the grid of the 003 MOS tube, … …, the 100 interface of the microcontroller controls the grid of the 100 MOS tube, and so on, and the n interface of the microcontroller controls the grid of the n MOS tube; because the serial detection unit comprises strip resistors and MOS tubes, each strip resistor is connected with each MOS tube in series, for example, 100 strip resistors are arranged, the number 001 of the strip resistor is matched with the number 001 MOS tube to form a number 001 serial detection unit, the number 001 interface of the microcontroller, the grid electrode of the number 001 MOS tube and the number 001 of the strip resistor are in one-to-one correspondence, the number 002 of the strip resistor is matched with the number 002 MOS tube to form a number 002 serial detection unit, the number 002 interface of the microcontroller, the grid electrode of the number 002 MOS tube and the number 002 of the strip resistor are in one-to-one correspondence, the number 003 of the strip resistor is matched with the number 003 MOS tube to form a number 003 serial detection unit, the interface 003 of the microcontroller, the grid electrode of the MOS tube 003 and the strip resistor 003 are in one-to-one correspondence, … …, the strip resistor 100 is matched with the MOS tube 100 to form a serial detection unit 100, the interface 100 of the microcontroller, the grid electrode of the MOS tube 100 and the strip resistor 100 are in one-to-one correspondence, and so on, the strip resistor n is matched with the MOS tube n to form a serial detection unit n, and the interface n of the microcontroller, the grid electrode of the MOS tube n and the strip resistor n are in one-to-one correspondence, so that the space position of the strip resistor in the tunnel lining arch part is represented by the number serial number of the output interface of the microcontroller or the number serial number of the MOS tube; the microcontroller output interface is connected with the control end of the image acquisition device, the microcontroller input interface is connected with the data output interface of the image acquisition device, the microcontroller output interface and the input interface both adopt unified digital serial numbers, for example, 10 microcontroller output interfaces connected with the control end of the image acquisition device are provided, and the digital serial numbers of the corresponding microcontroller output interfaces are as follows: the number 101 interface, the number 102 interface, the number 103 interface, the number … … interface and the number 110 interface, a plurality of image acquisition devices are matched with a plurality of strip resistors and are arranged inside the tunnel lining arch part, for example, one image acquisition device can shoot 10 or 5 areas distributed inside the tunnel lining arch part, taking 10 image acquisition devices as an example, the number serial numbers of the image acquisition devices are as follows: the image acquisition device No. 001, the image acquisition device No. 002, the image acquisition device No. 003, the image acquisition device No. … … and the image acquisition device No. 010, the number of the microcontroller input interfaces connected with the data output interfaces of the image acquisition device is 10, and the number serial numbers of the corresponding microcontroller input interfaces are as follows: no. 111 interface, no. 112 interface, no. 113 interface, no. … …, no. 120 interface; a No. 101 interface of the microcontroller controls a No. 001 image acquisition device control end, a No. 102 interface of the microcontroller controls a No. 002 image acquisition device control end, a No. 103 interface of the microcontroller controls a No. 003 image acquisition device control end, a No. … … interface of the microcontroller controls a No. 110 interface of the microcontroller controls a No. 010 image acquisition device control end; the No. 111 interface of the microcontroller is connected with the No. 001 image acquisition device data output interface, the No. 112 interface of the microcontroller is connected with the No. 002 image acquisition device data output interface, the No. 113 interface of the microcontroller is connected with the No. 003 image acquisition device data output interface, the No. … … interface of the microcontroller is connected with the No. 010 image acquisition device data output interface; for example, an image acquisition device can shoot an area in which 10 strip resistors are distributed in the arch part of a tunnel lining, a program association interface is adopted in the microcontroller, for example, the 001-number image acquisition device can shoot an area in which the strip resistors No. 001 to No. 010 are positioned, the 001-number interface to No. 010 interface, the 101-number interface and the 111-number interface of the microcontroller are associated, any one or more (not more than 10) of the 001-number interface to the 010-number interface of the microcontroller is abnormal, the 101-number interface of the microcontroller starts the 001-number image acquisition device, and the 111-number interface of the microcontroller receives image data of the 001-number image acquisition device; the 002 number image acquisition device can shoot the area from the 011 number of the strip resistor to the 020 number of the strip resistor, the 011 number interface of the microcontroller is related to the 020 number interface, the 102 number interface and the 112 number interface, any one or more (not more than 10) of the 011 number interface of the microcontroller to the 020 number interface is abnormal, the 102 number interface of the microcontroller starts the 002 number image acquisition device, and the 112 number interface of the microcontroller receives the image data of the 002 number image acquisition device; and so on, the image acquisition device can shoot the number of the strip-shaped resistors to be determined and correlated according to specific situations.
A pre-warning method of a data processing system based on tunnel lining arch dropping comprises the following specific steps:
s1, measuring the resistance value of a strip resistor, and positioning the position information of a falling block of the tunnel lining arch part; the principle of the method is as follows: a plurality of strip-shaped resistors are arranged in the tunnel lining arch part or in the longitudinal direction and the transverse direction of the surface of the tunnel lining arch part, the strip-shaped resistors respectively form a plurality of current loops, each current loop is connected to the input end of an analog input channel of the microcontroller, the microcontroller carries out digital coding on each current loop, and each digital coding corresponds to the physical position of one strip-shaped resistor;
s2, an image acquisition device acquires images of abnormal data of the resistance value of the strip resistor, wherein the images of the abnormal data generation position are acquired by the image acquisition device, and feature extraction and classification are carried out according to an image recognition model to obtain a classification result;
step S3, uploading the obtained classification result data M to a database, and forming a historical data set together with the past data; it should be noted that M represents classification result data;
s4, calculating a deformation rate v and an accumulated value L through data in the historical data set, judging an early warning level K, and sending position data of the data to a control end for warning when the early warning level K reaches a threshold value; v represents a deformation rate, and L represents an integrated value of deformation;
In the step S2, the specific process steps of extracting the image recognition model features are as follows:
s201, importing an image of an abnormal data generation position into an image recognition model, and preprocessing the image, wherein the preprocessing comprises image enhancement, image segmentation and noise removal;
s202, extracting characteristic information of an image through a convolutional neural network CNN, wherein the characteristic information comprises edges, colors, shapes and widths;
s203, inputting the extracted features into a classification model, classifying the images, and separating the images identified as cracks according to the classification result to obtain crack data;
s204, analyzing crack parameters of the crack data, wherein the crack parameters at least comprise one of width, length, crack position and dislocation amount.
Further, in the step S4, the specific flow steps for calculating the deformation rate v are as follows: width deformation data { L0, L1, L2, … …, ln } in the deformation data set V and days d from the day of occurrence of the data Ln-1 to the distance of the day of occurrence of the data Ln are extracted from the past data set, and deformation rate V of Ln-1 data to Ln data is calculated by the calculation formula:
v=△L/d
△L=Ln- Ln-1
wherein { L0, L1, L2, … …, ln } represents a width deformation amount data set, ln represents width deformation amount data on the nth day, n is a natural number, Δl represents a width deformation amount, and d=1.
Further, in the step S4, the specific flow steps of calculating the accumulated value L are as follows: width deformation data { L0, L1, L2, … …, ln } in the deformation data set V are extracted from the past data set, and the cumulative value L of L0 data to Ln data is calculated by the following calculation formula:
L=Ln- L0
wherein { L0, L1, L2, … …, ln } represents a width deformation amount data set, ln represents width deformation amount data on the nth day, and n is a natural number.
Further, in the step S1, the method specifically includes the following steps:
s101, equidistantly mounting strip-shaped resistors on the arch part of the tunnel lining, and connecting the strip-shaped resistors to a power supply and a detector;
s102, setting an early warning threshold value of the strip resistor;
s103, monitoring the tunnel lining arch part, wherein when the crack is not deformed, the resistance value of the strip resistor is a normal value; when the crack is deformed, the resistance value of the strip resistor is changed; when the resistance value of the strip resistor exceeds the early warning threshold value, the detector sends early warning data;
s104, positioning the detection position of the strip resistor according to the early warning data, wherein the detection position of the strip resistor is the abnormal data generation position.
Further, in the step S4, a specific step flow of determining the early warning level is as follows:
S401, setting early warning grades K= { K1, K2 and K3}, and respectively setting judgment standards and judgment limits of corresponding indexes for the K1, the K2 and the K3, wherein the judgment standards comprise deformation rate judgment standards and accumulated value judgment standards, and the judgment limits are specifically as follows:
k1 is determined that the deformation rate and the accumulated value at the crack do not exceed a specified threshold value;
the judgment limit of K2 is that one item of data of the deformation rate or the accumulated value at the crack exceeds a specified threshold value;
k3, judging that the deformation rate and the accumulated value at the crack exceed a specified threshold value;
s402, classifying the data according to the obtained deformation rate v and the accumulated value L and corresponding judgment standards and judgment limits;
s403, when the data belong to the K1 early warning level, the deformation rate and the accumulated value at the crack do not exceed the specified threshold value, and early warning is not carried out; when the data belong to the K2 early warning grade, one item of data of deformation rate or accumulated value at the crack exceeds a specified threshold value, and early warning is carried out; when the data belong to the K3 early warning grade, the deformation rate and the accumulated value at the crack position exceed the specified threshold value, and warning is carried out.
Further, the image acquisition module specifically includes:
The data preprocessing unit is used for importing an image of an abnormal data generation position into the image recognition model and preprocessing the image, wherein the preprocessing comprises image enhancement, image segmentation and noise removal;
the characteristic extraction unit is used for extracting characteristic information of the image through a convolutional neural network CNN, wherein the characteristic information comprises edges, colors, shapes and widths;
the classification recognition unit inputs the extracted features into a classification model, classifies the images, and separates the images recognized as cracks according to classification results to obtain crack data;
and the data analysis unit is used for carrying out crack parameter analysis on the crack data, wherein the crack parameter at least comprises one of width, length, crack position and dislocation amount. Among them, feature extraction is a very important step in image recognition models, which are typically implemented using Convolutional Neural Network (CNN) or other algorithms. Preferably, the convolution layer is one of the most important components in the CNN, and it can extract feature information of the image.
The convolution layer includes a plurality of convolution kernels, each of which scans a local region of the input image and outputs a signature. The size and number of convolution kernels may be adjusted as desired. The output of the convolutional layer needs to be processed by an activation function to add nonlinear characteristics. Common activation functions include ReLU, sigmoid, tanh, etc.
The pooling layer is used to reduce the size and number of feature maps to reduce the computational effort and risk of overfitting. Common pooling operations include maximum pooling and average pooling.
The full connection layer is used for classifying the output of the pooling layer. Each neuron in the fully connected layer is connected to all neurons in the previous layer, and thus requires adjustment of weights and offsets to accommodate different classification tasks.
Dropout is a common regularization method used to reduce the risk of overfitting in the network. Dropout will randomly set some neurons to 0, increasing the robustness of the network.
The final feature extraction result is the output of the fully connected layer. These features may be used for training of classification models, as well as for other tasks such as object detection and image segmentation. Feature extraction is a very important step in image recognition models, and can extract useful information from images to assist in subsequent classification and prediction tasks. Different feature extraction methods and algorithms can be applied to different application scenes, and selection and adjustment are required according to specific situations.
Further, the analysis alarm module specifically includes:
A deformation rate calculation unit for extracting width deformation amount data { L0, L1, L2, … …, ln } in the deformation data set V and a number d (d=1 day) of days from a day of occurrence of the data Ln-1 to a distance of occurrence of the data Ln from the past data set, and calculating a deformation rate V of the Ln-1 data to the Ln data, the calculation formula of which is:
v=△L/d
△L=Ln- Ln-1
wherein { L0, L1, L2, … …, ln } represents a width deformation amount data set, ln represents width deformation amount data on the nth day, n is a natural number, Δl represents a width deformation amount, d represents a time day, d=1;
an accumulated value calculating unit for extracting width deformation data { L0, L1, L2, … …, ln } in the deformation data set v from the past data set, and calculating an accumulated value L from the L0 data to the Ln data, wherein the calculation formula is as follows:
L=Ln- L0
wherein { L0, L1, L2, … …, ln } represents a width deformation amount data set, ln represents width deformation amount data on the nth day, and n is a natural number;
the device comprises a grade judging unit, a data processing unit and a data processing unit, wherein the grade judging unit sets early warning grades K= { K1, K2 and K3}, and sets judging standards and judging limits of corresponding indexes for K1, K2 and K3 respectively, wherein the judging standards comprise deformation rate judging standards and accumulated value judging standards, and carries out early warning grade classification on data according to the obtained deformation rate v and accumulated value L and the corresponding judging standards and judging limits; when the data belong to the K1 early warning grade, the deformation rate and the accumulated value at the crack do not exceed the specified threshold value, and early warning is not carried out; when the data belong to the K2 early warning grade, one item of data of deformation rate or accumulated value at the crack exceeds a specified threshold value, and early warning is carried out; when the data belong to the K3 early warning grade, the deformation rate and the accumulated value at the crack position exceed the specified threshold value, and warning is carried out.
Further, the decision boundary is specifically:
k1 is determined that the deformation rate and the accumulated value at the crack do not exceed a specified threshold value;
the judgment limit of K2 is that one item of data of the deformation rate or the accumulated value at the crack exceeds a specified threshold value;
k3 is determined by determining that the deformation rate and the cumulative value at the crack exceed a predetermined threshold value, and d=1.
Compared with the prior art, the invention has the beneficial effects that:
(1) The MOS tube is used for controlling the disconnection and the connection of the strip resistor, the voltage for conducting the MOS tube is fixed to be a fixed value and higher than the starting voltage, and the purpose is to eliminate the effect of the regulating current of the MOS tube, improve the precision of measuring the current value passing through the strip resistor and further calculate the resistance value of the strip resistor with high precision; the voltage of the direct current power supply is limited to a fixed value, the precision of measuring the voltage value passing through the strip resistor is improved, and then the resistance value of the strip resistor with high precision is calculated;
(2) The purpose of arranging a plurality of strip resistors inside or on the surface of the tunnel lining arch part is to detect dropping conditions, deformation conditions and potential blocking risks of the arch part can be monitored in real time through the resistors, the strip resistors are arranged in the longitudinal direction inside the tunnel lining arch part, radial deformation conditions of the arch part can be detected, namely whether inward collapse or outward expansion of the arch and the like occur or not, the information can be used for predicting blocking risks, and measures can be taken in time to carry out reinforcement repair; the strip-shaped resistor is arranged in the transverse direction of the tunnel lining arch part, so that the transverse deformation condition of the arch part, namely whether transverse displacement or inclination occurs or not can be detected, the information can help to predict the position and degree of the falling block, and measures are taken in time to repair or support; the strip-shaped resistor is arranged on the surface of the arch part of the tunnel lining, so that the crack and damage condition of the arch surface can be detected, and when the crack or damage occurs on the surface of the lining, the value of the resistor can be changed, thereby prompting the overhaul and maintenance work and preventing the occurrence of falling blocks; the strip-shaped resistors can be connected with a monitoring system through connecting wires and are provided with corresponding data acquisition and analysis software to monitor and record the deformation condition of the arch part in real time;
(3) Detecting the cracks of the tunnel lining through the image recognition classification model, calculating the deformation rate and the accumulated value according to the detection result, and effectively evaluating the cracking degree of the tunnel cracks through accurate calculation data obtained through calculation, so that early warning is more accurate and detection is more comprehensive;
(4) The early warning grade is set, the grade of the deformation rate and the accumulated value obtained through calculation is judged, the data is subjected to non-early warning operation according to the early warning grade, the content of the data object is finer, the hazard degree of the data is evaluated in a classified mode, and the early warning function of the detection system is more accurate.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of the distribution of strip resistances of a data processing system based on tunnel lining arch dropping;
FIG. 2 is a circuit diagram of a series detection unit of a data processing system based on tunnel lining arch dropping;
FIG. 3 is a flow chart of a method of early warning of a data processing system based on tunnel lining arch dropping.
In the drawings, the reference numerals and corresponding part names: 101-band resistor.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. It will be apparent that the described embodiments are some, but not all, embodiments of the invention.
Thus, the following detailed description of the embodiments of the invention is not intended to limit the scope of the invention, as claimed, but is merely representative of some embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that, under the condition of no conflict, the embodiments of the present invention and the features and technical solutions in the embodiments may be combined with each other.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
The present invention will be described in further detail with reference to examples.
Embodiment 1 as shown in fig. 1 to 2, a data processing system based on a tunnel lining arch dropping block, comprising: the digital-to-analog converter DAC comprises a serial detection unit, a digital ammeter, a digital-to-analog converter DAC, a microcontroller, an image acquisition device and a direct current power supply, wherein the serial detection unit comprises strip resistors and MOS tubes, and each strip resistor is connected with each MOS tube in series; a plurality of strip resistors are arranged in the tunnel lining arch part or in the longitudinal direction and the transverse direction of the surface, a plurality of series detection units are connected in parallel and sequentially connected with a digital ammeter and a direct current power supply in series to form a current loop, a digital output end of the digital ammeter is connected with a microcontroller to an input interface through a digital-analog converter DAC, an output interface of the microcontroller is connected to a grid electrode of a MOS tube, the output interfaces of the microcontroller are in one-to-one correspondence with the array sequence of the MOS tube, further, each output interface of the microcontroller is in one-to-one correspondence with each strip resistor, the interface positions of the microcontroller are in one-to-one correspondence with the space positions of the strip resistors in the tunnel lining arch part, the output interfaces of the microcontroller are connected with a control interface of an image acquisition device, the interface positions of the microcontroller are in one-to-one correspondence with the space positions of the image acquisition device in the tunnel lining arch part, and further, the strip resistors are in association with the space positions of the image acquisition device; the microcontroller controls the MOS tube array, sequentially and circularly controls the MOS tube array according to the clock sequence, only conducts the MOS tube of one serial detection unit in the same time period, and the digital ammeter sequentially circularly detects the current value of each serial detection unit and transmits the current value to the microcontroller to calculate the resistance value of the band resistor in real time, and the microcontroller calculates the band resistor The resistance value of the same strip resistor is compared with the historical data of the resistance value of the same strip resistor, and according to whether the resistance value of the strip resistor is abnormal or not, the image acquisition device is controlled to acquire image data of the area where the corresponding strip resistor is located, and the image data is processed; it should be noted that the strip resistor is made of a narrow and long metal strip, and is characterized by having a small resistance, being capable of rapidly reacting to current changes, and being made of a metal or alloy having good elasticity, such as copper, iron, nickel, etc., and being capable of generating a certain resistance change when the strip resistor is deformed by external force or pressure, and the change can be monitored by measuring current and voltage; the elasticity of the strip resistor is limited, and the deformation range and the recovery capability of the strip resistor are limited, so that the strip resistor corresponds to the tunnel lining arch part to be cracked and blocked one by one; the purpose of arranging a plurality of strip resistors inside or on the surface of the tunnel lining arch part is to detect dropping conditions, deformation conditions and potential dropping risks of the arch part can be monitored in real time through the resistors, the strip resistors are arranged in the longitudinal direction inside the tunnel lining arch part, radial deformation conditions of the arch part can be detected, namely whether inward collapse or external expansion and the like of the arch occur or not, and the information can be used for predicting dropping risks and timely taking measures to carry out reinforcement repair; the strip-shaped resistor is arranged in the transverse direction of the tunnel lining arch part, so that the transverse deformation condition of the arch part, namely whether transverse displacement or inclination occurs or not can be detected, the information can help to predict the position and degree of the falling block, and measures are taken in time to repair or support; the strip-shaped resistor is arranged on the surface of the arch part of the tunnel lining, so that the crack and damage condition of the arch surface can be detected, and when the crack or damage occurs on the surface of the lining, the value of the resistor can be changed, thereby prompting the overhaul and maintenance work and preventing the occurrence of falling blocks; the strip resistors can be connected with a monitoring system through connecting wires and are provided with corresponding data acquisition and analysis software, deformation conditions of the arch parts are monitored and recorded in real time, and if the risk of falling blocks of the arch parts is detected, measures are taken in time to repair and support so as to ensure safe operation of the tunnel; the purpose of connecting each strip resistor in series with each MOS transistor is to form a controlled circuit by MO The S-tube controls the turn-off and turn-on of the strip resistor, the voltage of the turn-on MOS tube is fixed to a fixed value and higher than the turn-on voltage, the purpose is to remove the effect of the regulating current of the MOS tube, improve the precision of measuring the current value passing through the strip resistor, further calculate the resistance value of the strip resistor with high precision, the turn-on voltage of the MOSFET (metal oxide semiconductor field effect transistor) refers to the voltage of the MOS tube starting to turn-on current when the control voltage (also called gate voltage) of the MOS tube reaches a certain voltage, the turn-on voltage is usually called gate threshold voltage (Vth) for the N-channel MOSFET (NMOS), it refers to the turn-on current when the gate voltage is higher than the gate threshold voltage, usually, the gate threshold voltage of the NMOS is negative, usually between-0.5V and-3V, the turn-on voltage is also called gate threshold voltage (Vth) for the P-channel MOSFET (PMOS), the MOS transistor is switched between on and off by controlling the gate voltage at a fixed opening voltage when the MOS transistor is used as a switch, specifically, when the MOS transistor is used as a switch and the gate voltage is higher than a critical voltage (also called an opening voltage), the MOS transistor is in an on state, when the gate voltage is lower than the critical voltage, the MOS tube is in a closed state, and the drain electrode is cut off, so that the MOS tube can be used as a switch to control the opening and closing of an output signal by properly adjusting the height of the gate voltage, and the opening and closing process can be used for realizing the application of digital circuits or switching power supplies and the like; referring to FIG. 2, a strip resistor 101 is installed at the arch of tunnel lining, and a 001-numbered MOS transistor is MOS transistor Q 1 No. 002 MOS tube, namely MOS tube Q 2 By analogy, n-number MOS tube is MOS tube Q n The band resistor 001 is the band resistor Q 1 Band-shaped resistor002 is the band resistor Q 2 By analogy, the number n of the strip resistor is the strip resistor Q n N is a natural number, a plurality of serial detection units are connected in parallel, and are sequentially connected in series with a digital ammeter and a direct current power supply to form a current loop, for example, 2000 or 3000 serial detection units are connected in parallel, in the same time period, only one serial detection unit is in a conducting state or a working state, the serial detection unit is simplified to be sequentially connected in series with the digital ammeter and the direct current power supply to form the current loop, the voltage of the direct current power supply is limited to be a fixed value, the precision of measuring the voltage value passing through the strip resistor is improved, and the resistance value of the high-precision strip resistor is calculated, and the principle is that according to the formula U=IR of voltage, current and resistance, U represents voltage, I represents current, and R represents resistance; the microcontroller is composed of a Central Processing Unit (CPU), a nonvolatile memory, a volatile memory, peripheral equipment and a supporting circuit, the microcontroller adopts a model for processing Analog signals, a Digital output end of a Digital ammeter is connected to an input interface of the microcontroller through a Digital-to-Analog Converter (DAC), the reading of the Digital ammeter is transmitted to the microcontroller for processing and analysis, and the following is a specific connection mode: first, the input interface type of the microcontroller is determined and the appropriate DAC chip is found, the appropriate DAC chip is selected according to the need, for example, 8-bit, 10-bit or 12-bit resolution, the digital input/output pins between the microcontroller and DAC chip are connected, these pins may be marked as "Data pins (Data Pin)" or "DIN", ensuring that the connection is correct so that the values can be properly transferred, the Clock signal pins between the microcontroller and DAC chip are connected, these pins may be marked as "Clock" or "CLK", the Clock signal is used for synchronous conversion, ensuring the accuracy of the Data, the Reset pins between the microcontroller and DAC chip are connected, these pins may be marked as "Reset" or "RST", the Reset signal is used for resetting the DAC chip to an initial state, the Vref Pin of the DAC chip is connected to the Vref voltage source, VREF is a reference voltage reference The pin, vref voltage determines the maximum output voltage of the DAC, connects the power pin of the microcontroller and the power pin of the DAC chip to the appropriate power voltage, programs the microcontroller to read the data output of the DAC chip according to the DAC chip specification, which requires programming code to access and read the DAC registers, through this connection method, the microcontroller can read and use the readings of the digital ammeter, which can be used to make further calculations, control and decisions; the output interface of the microcontroller can be connected to the grid electrode of the MOS tube to control the on and off of the MOS tube, and the specific connection method is as follows: firstly, determining an output interface of a microcontroller and a gate pin of a MOS tube, wherein the output interface of the microcontroller adopts an analog signal output pin, the gate pin of the MOS tube is usually a control pin, the output pin of the microcontroller is connected to the gate pin of the MOS tube, the connection pin can be ensured to be correctly connected through a wire connection, the connection between the microcontroller and the MOS tube is ensured to be reliable without loosening or short circuit, the connection is performed by using a proper tool and technology, such as welding or using a plug, the output signal of the microcontroller is ensured to be compatible with the working voltage of the MOS tube, the output signal of the microcontroller is matched with the control voltage requirement of the MOS tube, so as to ensure that the signal can correctly control the on and off of the MOS tube, and the following matters are adopted: ensuring that the microcontroller and MOS transistors are in a powered-down state prior to connection to avoid shorts or other damage, carefully researching and understanding the specifications of the microcontroller and MOS transistors prior to connection to ensure proper connection and operation, and possibly also requiring the use of voltage level shifters or level shifters if necessary to ensure level compatibility between the microcontroller and MOS transistors, depending on the electrical characteristics and signal requirements between the microcontroller and MOS transistors; through carrying out digital sequencing to the array of microcontroller output interface and MOS pipe, realize microcontroller output interface and MOS pipe's array order one-to-one, for example connect the microcontroller output interface of MOS pipe 100, the digital serial number of microcontroller output interface is: the number 001, 002, 003, … … and 100 interfaces and so on, and extends to the number n interfaces, n represents a natural number, and the number of the arrays of the MOS tubes is 100 The MOS tube, the number of MOS tube is: from the first row to the last row, the numbers are ordered as: no. 001 MOS pipe, 002 MOS pipe, 003 MOS pipe, … …, no. 100 MOS pipe, and so on, expands to n number interface, and n represents natural number, and microcontroller output interface and MOS pipe's array order one-to-one's control relation is: the 001 interface of the microcontroller controls the grid of the 001 MOS tube, the 002 interface of the microcontroller controls the grid of the 002 MOS tube, the 003 interface of the microcontroller controls the grid of the 003 MOS tube, … …, the 100 interface of the microcontroller controls the grid of the 100 MOS tube, and so on, and the n interface of the microcontroller controls the grid of the n MOS tube; because the serial detection unit comprises strip resistors and MOS tubes, each strip resistor is connected with each MOS tube in series, for example, 100 strip resistors are arranged, the number 001 of the strip resistor is matched with the number 001 MOS tube to form a number 001 serial detection unit, the number 001 interface of the microcontroller, the grid electrode of the number 001 MOS tube and the number 001 of the strip resistor are in one-to-one correspondence, the number 002 of the strip resistor is matched with the number 002 MOS tube to form a number 002 serial detection unit, the number 002 interface of the microcontroller, the grid electrode of the number 002 MOS tube and the number 002 of the strip resistor are in one-to-one correspondence, the number 003 of the strip resistor is matched with the number 003 MOS tube to form a number 003 serial detection unit, the interface 003 of the microcontroller, the grid electrode of the MOS tube 003 and the strip resistor 003 are in one-to-one correspondence, … …, the strip resistor 100 is matched with the MOS tube 100 to form a serial detection unit 100, the interface 100 of the microcontroller, the grid electrode of the MOS tube 100 and the strip resistor 100 are in one-to-one correspondence, and so on, the strip resistor n is matched with the MOS tube n to form a serial detection unit n, and the interface n of the microcontroller, the grid electrode of the MOS tube n and the strip resistor n are in one-to-one correspondence, so that the space position of the strip resistor in the tunnel lining arch part is represented by the number serial number of the output interface of the microcontroller or the number serial number of the MOS tube; the microcontroller output interface is connected with the control end of the image acquisition device, the microcontroller input interface is connected with the data output interface of the image acquisition device, the microcontroller output interface and the input interface both adopt uniform digital serial numbers, for example, 10 microcontroller output interfaces connected with the control end of the image acquisition device are provided, and the corresponding microcontroller outputs are connected The number of the port is: the number 101 interface, the number 102 interface, the number 103 interface, the number … … interface and the number 110 interface, a plurality of image acquisition devices are matched with a plurality of strip resistors and are arranged inside the tunnel lining arch part, for example, one image acquisition device can shoot 10 or 5 areas distributed inside the tunnel lining arch part, taking 10 image acquisition devices as an example, the number serial numbers of the image acquisition devices are as follows: the image acquisition device No. 001, the image acquisition device No. 002, the image acquisition device No. 003, the image acquisition device No. … … and the image acquisition device No. 010, the number of the microcontroller input interfaces connected with the data output interfaces of the image acquisition device is 10, and the number serial numbers of the corresponding microcontroller input interfaces are as follows: no. 111 interface, no. 112 interface, no. 113 interface, no. … …, no. 120 interface; a No. 101 interface of the microcontroller controls a No. 001 image acquisition device control end, a No. 102 interface of the microcontroller controls a No. 002 image acquisition device control end, a No. 103 interface of the microcontroller controls a No. 003 image acquisition device control end, a No. … … interface of the microcontroller controls a No. 110 interface of the microcontroller controls a No. 010 image acquisition device control end; the No. 111 interface of the microcontroller is connected with the No. 001 image acquisition device data output interface, the No. 112 interface of the microcontroller is connected with the No. 002 image acquisition device data output interface, the No. 113 interface of the microcontroller is connected with the No. 003 image acquisition device data output interface, the No. … … interface of the microcontroller is connected with the No. 010 image acquisition device data output interface; for example, an image acquisition device can shoot an area in which 10 strip resistors are distributed in the arch part of a tunnel lining, a program association interface is adopted in the microcontroller, for example, the 001-number image acquisition device can shoot an area in which the strip resistors No. 001 to No. 010 are positioned, the 001-number interface to No. 010 interface, the 101-number interface and the 111-number interface of the microcontroller are associated, any one or more (not more than 10) of the 001-number interface to the 010-number interface of the microcontroller is abnormal, the 101-number interface of the microcontroller starts the 001-number image acquisition device, and the 111-number interface of the microcontroller receives image data of the 001-number image acquisition device; 002 number image acquisition device can shoot band resistance 011 number to band resistance 020 place region, and microcontroller's 011 number interface to 020 number interface, 102 number interface, and 112 number interface In association, any one or more (not more than 10) of No. 011 interfaces to No. 020 interfaces of the microcontroller are abnormal, no. 102 interfaces of the microcontroller start No. 002 image acquisition devices, and No. 112 interfaces of the microcontroller receive image data of the No. 002 image acquisition devices; and so on, the image acquisition device can shoot the number of the strip-shaped resistors to be determined and correlated according to specific situations.
Further, the interfaces of the microcontroller are expanded, and it is to be noted that, because the total number of the strip resistor, the MOS tube and the image acquisition device is far greater than the number of the interfaces of the microcontroller, the one-to-one matching of the number of the interfaces of the microcontroller and the total number of the strip resistor, the MOS tube and the image acquisition device is realized by adopting a method for expanding the interfaces of the microcontroller; the method is characterized in that the number of interfaces of the microcontroller is expanded in a hierarchical interface mode, the interface expansion can be performed by adding a new interface module or using an existing interface module to connect, so that the microcontroller can output more signals or data, for example, a new output interface module can be added to connect the new interface module to an output pin on the microcontroller, so that the output interface of the microcontroller is expanded, and therefore, the microcontroller can control a plurality of external devices simultaneously and output different signals; another way is to extend the output interface of the microcontroller by using a hierarchical interface, which refers to dividing one interface into a plurality of levels, each level can output a different type of signal or data, for example, a general analog output interface can be divided into a plurality of levels, each level can output a different analog signal; by adopting the mode of interface expansion and grading interface, the output interface of the microcontroller can be expanded according to the actual demand so as to meet different application scenes, thus the flexibility and the expandability of the system can be improved, and the microcontroller is more suitable for various different external equipment and signal requirements.
Embodiment 2, as shown in fig. 3, is an integrated method of a data processing system based on a tunnel lining arch dropping block, and the specific steps of implementing the method are as follows:
a pre-warning method of a data processing system based on tunnel lining arch dropping comprises the following specific steps:
s1, measuring the resistance value of a strip resistor, and positioning the position information of a falling block of the tunnel lining arch part;
s2, an image acquisition device acquires images of abnormal data of the resistance value of the strip resistor, wherein the images of the abnormal data generation position are acquired by the image acquisition device, and feature extraction and classification are carried out according to an image recognition model to obtain a classification result;
step S3, uploading the obtained classification result data M to a database, and forming a historical data set together with the past data;
and S4, calculating a deformation rate v and an accumulated value L through data in the historical data set, judging an early warning level K, and sending the position data of the data to a control end for warning when the early warning level K reaches a threshold value.
S1, measuring the resistance value of a strip resistor, and positioning the position information of a falling block of an arch part of a tunnel lining; the principle of the method is as follows: a plurality of strip-shaped resistors are arranged in the tunnel lining arch part or in the longitudinal direction and the transverse direction of the surface of the tunnel lining arch part, the strip-shaped resistors respectively form a plurality of current loops, each current loop is connected to the input end of an analog input channel of the microcontroller, the microcontroller carries out digital coding on each current loop, and each digital coding corresponds to the physical position of one strip-shaped resistor;
S2, an image acquisition device acquires images of abnormal data of the resistance value of the strip resistor, wherein the images of the abnormal data generation position are acquired by the image acquisition device, and feature extraction and classification are carried out according to an image recognition model to obtain a classification result;
step S3, uploading the obtained classification result data M to a database, and forming a historical data set together with the past data; it should be noted that M represents classification result data;
s4, calculating a deformation rate v and an accumulated value L through data in the historical data set, judging an early warning level K, and sending position data of the data to a control end for warning when the early warning level K reaches a threshold value; v represents a deformation rate, and L represents an integrated value of deformation;
in the step S2, the specific process steps of extracting the image recognition model features are as follows:
s201, importing an image of an abnormal data generation position into an image recognition model, and preprocessing the image, wherein the preprocessing comprises image enhancement, image segmentation and noise removal;
s202, extracting characteristic information of an image through a convolutional neural network CNN, wherein the characteristic information comprises edges, colors, shapes and widths;
S203, inputting the extracted features into a classification model, classifying the images, and separating the images identified as cracks according to the classification result to obtain crack data;
s204, analyzing crack parameters of the crack data, wherein the crack parameters at least comprise one of width, length, crack position and dislocation amount.
Further, in the step S4, the specific flow steps for calculating the deformation rate v are as follows: width deformation data { L0, L1, L2, … …, ln } in the deformation data set V and days d from the day of occurrence of the data Ln-1 to the distance of the day of occurrence of the data Ln are extracted from the past data set, and deformation rate V of Ln-1 data to Ln data is calculated by the calculation formula:
v=△L/d
△L=Ln- Ln-1
wherein { L0, L1, L2, … …, ln } represents a width deformation amount data set, ln represents width deformation amount data on the nth day, n is a natural number, Δl represents a width deformation amount, and d=1.
Further, in the step S4, the specific flow steps of calculating the accumulated value L are as follows: width deformation data { L0, L1, L2, … …, ln } in the deformation data set V are extracted from the past data set, and the cumulative value L of L0 data to Ln data is calculated by the following calculation formula:
L=Ln- L0
Wherein { L0, L1, L2, … …, ln } represents a width deformation amount data set, ln represents width deformation amount data on the nth day, and n is a natural number.
Further, in the step S1, the method specifically includes the following steps:
s101, equidistantly mounting strip-shaped resistors on the arch part of the tunnel lining, and connecting the strip-shaped resistors to a power supply and a detector;
s102, setting an early warning threshold value of the strip resistor;
s103, monitoring the tunnel lining arch part, wherein when the crack is not deformed, the resistance value of the strip resistor is a normal value; when the crack is deformed, the resistance value of the strip resistor is changed; when the resistance value of the strip resistor exceeds the early warning threshold value, the detector sends early warning data;
s104, positioning the detection position of the strip resistor according to the early warning data, wherein the detection position of the strip resistor is the abnormal data generation position.
Preferably, in monitoring the resistance value, the following details need to be noted:
1. selecting a proper band resistor: different crack sizes, materials, and environmental conditions may require different types or specifications of ribbon resistances. Therefore, the actual situation of the crack needs to be considered when selecting the strip resistor.
2. Mounting a strip resistor: the ribbon resistor needs to be properly installed around the crack to ensure that the deformation of the crack can be accurately detected. The position and orientation of the resistor need to be carefully adjusted during installation to ensure maximum perception of crack deformation.
3. Measuring the resistance value: after the band resistor is mounted, a test instrument such as a multimeter is required to measure the resistance value. This value is usually a standard value, but may also be a range. When the early warning threshold is recorded or set, the resistance value range of the strip resistor needs to be determined according to actual conditions.
4. Monitoring resistance value changes: when the crack is deformed, the resistance value of the strip resistor changes. Therefore, it is necessary to periodically monitor the resistance value of the strip resistor so as to find the deformation condition of the crack in time.
5. Calibrating the ribbon resistance: the sensitivity and accuracy of the ribbon resistor may vary with time of use. To ensure that the deformation of the crack can be accurately detected, the strip resistor needs to be calibrated regularly.
Further, in the step S4, a specific step flow of determining the early warning level K is as follows:
s401, setting early warning grades K= { K1, K2 and K3}, and respectively setting judgment standards and judgment limits of corresponding indexes for the K1, the K2 and the K3, wherein the judgment standards comprise deformation rate judgment standards and accumulated value judgment standards, and the judgment limits are specifically as follows:
k1 is determined that the deformation rate and the accumulated value at the crack do not exceed a specified threshold value;
The judgment limit of K2 is that one item of data of the deformation rate or the accumulated value at the crack exceeds a specified threshold value;
k3, judging that the deformation rate and the accumulated value at the crack exceed a specified threshold value;
s402, classifying the data according to the obtained deformation rate v and the accumulated value L and corresponding judgment standards and judgment limits;
s403, when the data belong to the K1 early warning level, the deformation rate and the accumulated value at the crack do not exceed the specified threshold value, and early warning is not carried out; when the data belong to the K2 early warning grade, one item of data of deformation rate or accumulated value at the crack exceeds a specified threshold value, and early warning is carried out; when the data belong to the K3 early warning grade, the deformation rate and the accumulated value at the crack position exceed the specified threshold value, and warning is carried out.
As a preferred embodiment, a concrete embodiment is proposed, wherein a tunnel lining arch drop detection early warning system based on image classification acquires crack images on day 1, day 4, day 5, day 6 and day 7, and the widths of the obtained cracks are 1.01mm, 1.08mm, 1.11mm, 1.13mm and 1.38mm, respectively, according to analysis.
By calculation and analysis, the deformation rate is as follows:
（1.38-1.13）/1=0.25mm/d；
The term "divided by" means,
the cumulative value is:
1.38-1.01=0.37mm；
setting a level threshold, specifically:
setting the K1 deformation rate to be less than or equal to 0.2mm/d and the accumulated value to be less than or equal to 3mm;
setting K2 deformation rate to be more than 0.2mm/d or accumulated value to be more than 3mm;
setting K3 deformation rate to be more than 0.2mm/d and the accumulated value to be more than or equal to 3mm;
and judging the early warning level at the moment as the early warning level according to the threshold value, the calculated deformation rate and the accumulated value, and carrying out early warning by the system.
It should be noted that, the threshold setting in the above embodiment may be adaptively changed according to actual specifications, requirements, and the like, or may be adaptively changed according to the stress level of the tunnel, the construction specification, and the like, and the setting of the data is a conventional technical means of those skilled in the art, which is not described herein again.
Further, in the step S4, the embodiment described above uses the crack width as the detection variable, and in another specific embodiment, the variables may be selectively modified according to the actual situation, for example, the detected variables such as the crack length, the crack position, the crack dislocation amount, etc. are selected and modified, and the detection calculation of the crack length and the crack dislocation amount is consistent with the calculation mode of the crack width in the embodiment described above, and for the crack position, the dangerous position setting may be performed on the tunnel where the accident is likely to occur according to the actual experience and the knowledge of common sense, and when the number of cracks at the set position reaches the threshold value, the alarm is performed.
Preferably, in the above embodiment, a plurality of parameters may be combined, features may be extracted to perform feature calculation, and classification may be performed based on the calculation result.
Further, the image acquisition module specifically includes:
the data preprocessing unit is used for importing an image of an abnormal data generation position into the image recognition model and preprocessing the image, wherein the preprocessing comprises image enhancement, image segmentation and noise removal;
the characteristic extraction unit is used for extracting characteristic information of the image through a convolutional neural network CNN, wherein the characteristic information comprises edges, colors, shapes and widths;
the classification recognition unit inputs the extracted features into a classification model, classifies the images, and separates the images recognized as cracks according to classification results to obtain crack data;
and the data analysis unit is used for carrying out crack parameter analysis on the crack data, wherein the crack parameter at least comprises one of width, length, crack position and dislocation amount.
Further, the analysis alarm module specifically includes:
a deformation rate calculation unit for extracting width deformation amount data { L0, L1, L2, … …, ln } in the deformation data set V and a number d (d=1 day) of days from a day of occurrence of the data Ln-1 to a distance of occurrence of the data Ln from the past data set, and calculating a deformation rate V of the Ln-1 data to the Ln data, the calculation formula of which is:
v=△L/d
△L=Ln- Ln-1
Wherein { L0, L1, L2, … …, ln } represents a width deformation amount data set, ln represents width deformation amount data on the nth day, n is a natural number, Δl represents a width deformation amount, d represents a time day, d=1;
an accumulated value calculating unit for extracting width deformation data { L0, L1, L2, … …, ln } in the deformation data set V from the past data set, and calculating an accumulated value L from the L0 data to the Ln data, wherein the calculation formula is as follows:
L=Ln- L0
wherein { L0, L1, L2, … …, ln } represents a width deformation amount data set, ln represents width deformation amount data on the nth day, and n is a natural number;
the device comprises a grade judging unit, a data processing unit and a data processing unit, wherein the grade judging unit sets early warning grades K= { K1, K2 and K3}, and sets judging standards and judging limits of corresponding indexes for K1, K2 and K3 respectively, wherein the judging standards comprise deformation rate judging standards and accumulated value judging standards, and carries out early warning grade classification on data according to the obtained deformation rate v and accumulated value L and the corresponding judging standards and judging limits; when the data belong to the K1 early warning grade, the deformation rate and the accumulated value at the crack do not exceed the specified threshold value, and early warning is not carried out; when the data belong to the K2 early warning grade, one item of data of deformation rate or accumulated value at the crack exceeds a specified threshold value, and early warning is carried out; when the data belong to the K3 early warning grade, the deformation rate and the accumulated value at the crack position exceed the specified threshold value, and warning is carried out.
Further, the decision boundary is specifically:
k1 is determined that the deformation rate and the accumulated value at the crack do not exceed a specified threshold value;
the judgment limit of K2 is that one item of data of the deformation rate or the accumulated value at the crack exceeds a specified threshold value;
k3 is determined by exceeding a predetermined threshold value for both the deformation rate and the integrated value at the crack.
Preferably, the threshold value is specifically set as follows: according to the result of the statistical analysis, some grade thresholds, such as low, medium and high grade, or more grade according to specific conditions, may be set according to preset rules or indexes, and the set grade thresholds are applied to the actual data to determine the grade of the data. For example, if a statistical indicator of certain data exceeds a set high threshold, it may be marked as high; if it is below the set low threshold, it may be marked as low. The application effect of the threshold value is monitored regularly, and the threshold value is adjusted according to actual conditions. For example, if a certain level of data is found to be too sparse or too dense, the threshold may be reset to better reflect the actual situation. According to the set grade threshold value, the data can be classified and judged rapidly and accurately, and corresponding decisions can be made based on the classification and judgment. For example, by classifying the monitoring data, abnormal conditions can be found in time and corresponding measures can be taken to ensure the normal operation of the system. And continuously optimizing a threshold setting flow according to actual application conditions and feedback information so as to improve the accuracy and reliability of the threshold setting flow. For example, more data sources may be added, data processing algorithms may be optimized, threshold setting rules may be improved, etc., to improve the accuracy and applicability of threshold setting.
The above embodiments are only for illustrating the present invention and not for limiting the technical solutions described in the present invention, and although the present invention has been described in detail in the present specification with reference to the above embodiments, the present invention is not limited to the specific embodiments, and thus any modifications or equivalent substitutions are made to the present invention; all technical solutions and modifications thereof that do not depart from the spirit and scope of the invention are intended to be included in the scope of the appended claims.
Claims (8)
1. A data processing system based on tunnel lining arch dropping, comprising: the system comprises a serial detection unit, a digital ammeter, a digital-to-analog converter DAC, a microcontroller, an image acquisition device and a direct current power supply, wherein the serial detection unit comprises strip resistors and MOS (metal oxide semiconductor) tubes, the strip resistors are made of a strip of narrow and long metal strip, each strip resistor is connected with each MOS tube in series, and the system is characterized in that a plurality of strip resistors are arranged in the tunnel lining arch part or in the longitudinal and transverse directions of the surface of the tunnel lining arch part, the plurality of serial detection units are connected in parallel and sequentially form a current loop through the digital ammeter and the direct current power supply, the digital output end of the digital ammeter is connected with the microcontroller to an input interface through the digital-to-analog converter DAC, the microcontroller output interface is connected to the grid electrode of the MOS tubes, the microcontroller output interfaces are in one-to-one correspondence with the array sequence of the MOS tubes, the microcontroller output interfaces and the array of the MOS tubes are in one-to-one correspondence, the interface positions of the microcontroller and the strip resistors are mapped in one-to-one in the spatial positions of the tunnel lining arch part, the microcontroller output interfaces and the control interfaces of the image acquisition device are connected with the image acquisition device in one-to-one correspondence with the strip resistors in the spatial positions of the tunnel lining arch part, and the image acquisition device is further related to the image acquisition device; the interfaces of the microcontroller are expanded, so that the one-to-one matching of the number of the interfaces of the microcontroller and the total number of the strip resistors, the MOS tubes and the image acquisition device is realized; the method is characterized in that the number of interfaces of the microcontroller is expanded in a hierarchical interface mode, and the interfaces are expanded by adding new interface modules or using the existing interface modules for connection, so that the microcontroller can output more signals or data; the microcontroller controls the MOS tube array, sequentially and circularly turns on the MOS tube arrays according to the clock sequence, only turns on the MOS tube of one serial detection unit in the same time period, the digital ammeter sequentially circularly detects the current value of each serial detection unit and transmits the current value to the microcontroller in real time to calculate the resistance value of the strip resistor, the microcontroller calculates the resistance value of the strip resistor and compares the historical data of the resistance value of the same strip resistor, and the image acquisition device is controlled to acquire the image data of the area where the corresponding strip resistor is located according to whether the resistance value of the strip resistor is abnormal or not and processes the image data.
2. The data processing system based on tunnel lining arch dropping according to claim 1, wherein the voltage of the on MOS transistor is fixed to a constant value and higher than the turn-on voltage.
3. The data processing system based on tunnel lining arch dropping according to claim 1, wherein a plurality of series detection units are connected in parallel and sequentially connected in series with a digital ammeter and a direct current power supply to form a current loop, and the data processing system is simplified in that one series detection unit sequentially connected in series with the digital ammeter and the direct current power supply to form the current loop.
4. A data processing system based on tunnel lining arch dropping according to claim 3, wherein the voltage of the dc power supply is defined to be a constant value.
5. A data processing system based on tunnel lining arch dropping according to claim 1, wherein the microcontroller output interface is connected to the control end of the image acquisition device.
6. A data processing system based on tunnel lining arch dropping according to claim 1, wherein the microcontroller input interface is connected to the data output interface of the image acquisition device.
7. A method for early warning of a data processing system based on tunnel lining arch dropping, based on the data processing system based on tunnel lining arch dropping according to any one of claims 1 to 6, characterized in that the specific steps for realizing the method are as follows:
S1, measuring the resistance value of a strip resistor, and positioning the position information of a falling block of the tunnel lining arch part; the microcontroller carries out digital coding on each current loop, and each digital coding corresponds to the physical position of one strip resistor;
s2, an image acquisition device acquires images of abnormal data of the resistance value of the strip resistor, wherein the images of the abnormal data generation position are acquired by the image acquisition device, and feature extraction and classification are carried out according to an image recognition model to obtain a classification result;
step S3, uploading the obtained classification result data M to a database, and forming a historical data set together with the past data;
s4, calculating a deformation rate v and an accumulated value L through data in the historical data set, judging an early warning level K, and sending position data of the data to a control end for warning when the early warning level K reaches a threshold value; the specific flow steps for calculating the deformation rate v are as follows: width deformation data { L0, L1, L2, … …, ln } in the deformation data set V and days d from the day of occurrence of the data Ln-1 to the distance of the day of occurrence of the data Ln are extracted from the past data set, and deformation rate V of Ln-1 data to Ln data is calculated by the calculation formula:
v=△L/d
△L=Ln- Ln-1
Wherein { L0, L1, L2, … …, ln } represents a width deformation amount data set, ln represents width deformation amount data on the nth day, n is a natural number, Δl represents a width deformation amount, d represents a time day, d=1;
the specific flow steps for calculating the accumulated value L are as follows: width deformation data { L0, L1, L2, … …, ln } in the deformation data set V are extracted from the past data set, and the cumulative value L of L0 data to Ln data is calculated by the following calculation formula:
L=Ln- L0
wherein { L0, L1, L2, … …, ln } represents a width deformation amount data set, ln represents width deformation amount data on the nth day, and n is a natural number.
8. The early warning method of a data processing system based on tunnel lining arch dropping according to claim 7, wherein in step S2, the specific flow steps of image recognition model feature extraction are as follows:
s201, importing an image of an abnormal data generation position into an image recognition model, and preprocessing the image;
s202, extracting characteristic information of an image through a convolutional neural network CNN;
s203, inputting the extracted features into a classification model, classifying the images, and separating the images identified as cracks according to the classification result to obtain crack data;
S204, performing crack parameter analysis on the crack data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310988659.1A CN116699723B (en) | 2023-08-08 | 2023-08-08 | Data processing system and early warning method based on tunnel lining arch part falling block |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310988659.1A CN116699723B (en) | 2023-08-08 | 2023-08-08 | Data processing system and early warning method based on tunnel lining arch part falling block |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116699723A CN116699723A (en) | 2023-09-05 |
| CN116699723B true CN116699723B (en) | 2023-10-31 |
Family
ID=87841958
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310988659.1A Active CN116699723B (en) | 2023-08-08 | 2023-08-08 | Data processing system and early warning method based on tunnel lining arch part falling block |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116699723B (en) |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2002067015A1 (en) * | 2001-02-21 | 2002-08-29 | Macquarie Research Ltd | An apparatus and method for detecting an object in a medium |
| KR100634487B1 (en) * | 2006-05-08 | 2006-10-19 | (주)테스콤엔지니어링 | Examin system for searching the crack in the tunnel |
| CN102288101A (en) * | 2011-08-02 | 2011-12-21 | 中国矿业大学 | Bending deformation test sensor |
| CN202794092U (en) * | 2012-09-14 | 2013-03-13 | 于百勇 | Metro tunnel concrete crack monitoring device based on flexible conductive coating |
| CN202870022U (en) * | 2012-08-23 | 2013-04-10 | 武汉利德测控技术股份有限公司 | System for detecting tunnel lining crack |
| JP2014084613A (en) * | 2012-10-23 | 2014-05-12 | Okumura Corp | Method for curing tunnel lining concrete |
| CN104019742A (en) * | 2014-06-05 | 2014-09-03 | 武汉武大卓越科技有限责任公司 | Method for rapidly detecting cracks of tunnel lining |
| CN104697432A (en) * | 2015-02-04 | 2015-06-10 | 浙江大学 | Tube cable with deformation self-checking function |
| CN106841216A (en) * | 2017-02-28 | 2017-06-13 | 浙江工业大学 | Tunnel defect automatic identification equipment based on panoramic picture CNN |
| CN107064172A (en) * | 2017-06-12 | 2017-08-18 | 黄成� | A kind of Tunnel Lining Cracks rapid detection system |
| CN113674216A (en) * | 2021-07-27 | 2021-11-19 | 南京航空航天大学 | Subway tunnel disease detection method based on deep learning |
| CN113958369A (en) * | 2021-11-10 | 2022-01-21 | 重庆科技学院 | Tunnel lining structure health monitoring method and system based on digital twinning |
| CN114623776A (en) * | 2022-05-16 | 2022-06-14 | 四川省公路规划勘察设计研究院有限公司 | Tunnel damage prediction method based on tunnel deformation monitoring |
| CN114821922A (en) * | 2022-04-01 | 2022-07-29 | 重庆工程职业技术学院 | Intelligent tunnel construction safety detection equipment |
| CN115035141A (en) * | 2022-06-13 | 2022-09-09 | 长安大学 | Tunnel crack remote monitoring and early warning method based on image processing |
| CN115326809A (en) * | 2022-08-02 | 2022-11-11 | 山西省智慧交通研究院有限公司 | Apparent crack detection method and detection device for tunnel lining |
| CN115761613A (en) * | 2022-08-10 | 2023-03-07 | 中铁隧道局集团有限公司 | Automatic tunnel crack detection method based on convolutional network |
| CN116399812A (en) * | 2023-05-31 | 2023-07-07 | 张磊 | Highway tunnel detecting system |
| CN116520831A (en) * | 2023-04-14 | 2023-08-01 | 广西交通工程检测有限公司 | Device and method for correcting synchronization of geological radar walking track and radar image |
-
2023
- 2023-08-08 CN CN202310988659.1A patent/CN116699723B/en active Active
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2002067015A1 (en) * | 2001-02-21 | 2002-08-29 | Macquarie Research Ltd | An apparatus and method for detecting an object in a medium |
| KR100634487B1 (en) * | 2006-05-08 | 2006-10-19 | (주)테스콤엔지니어링 | Examin system for searching the crack in the tunnel |
| CN102288101A (en) * | 2011-08-02 | 2011-12-21 | 中国矿业大学 | Bending deformation test sensor |
| CN202870022U (en) * | 2012-08-23 | 2013-04-10 | 武汉利德测控技术股份有限公司 | System for detecting tunnel lining crack |
| CN202794092U (en) * | 2012-09-14 | 2013-03-13 | 于百勇 | Metro tunnel concrete crack monitoring device based on flexible conductive coating |
| JP2014084613A (en) * | 2012-10-23 | 2014-05-12 | Okumura Corp | Method for curing tunnel lining concrete |
| CN104019742A (en) * | 2014-06-05 | 2014-09-03 | 武汉武大卓越科技有限责任公司 | Method for rapidly detecting cracks of tunnel lining |
| CN104697432A (en) * | 2015-02-04 | 2015-06-10 | 浙江大学 | Tube cable with deformation self-checking function |
| CN106841216A (en) * | 2017-02-28 | 2017-06-13 | 浙江工业大学 | Tunnel defect automatic identification equipment based on panoramic picture CNN |
| CN107064172A (en) * | 2017-06-12 | 2017-08-18 | 黄成� | A kind of Tunnel Lining Cracks rapid detection system |
| CN113674216A (en) * | 2021-07-27 | 2021-11-19 | 南京航空航天大学 | Subway tunnel disease detection method based on deep learning |
| CN113958369A (en) * | 2021-11-10 | 2022-01-21 | 重庆科技学院 | Tunnel lining structure health monitoring method and system based on digital twinning |
| CN114821922A (en) * | 2022-04-01 | 2022-07-29 | 重庆工程职业技术学院 | Intelligent tunnel construction safety detection equipment |
| CN114623776A (en) * | 2022-05-16 | 2022-06-14 | 四川省公路规划勘察设计研究院有限公司 | Tunnel damage prediction method based on tunnel deformation monitoring |
| CN115035141A (en) * | 2022-06-13 | 2022-09-09 | 长安大学 | Tunnel crack remote monitoring and early warning method based on image processing |
| CN115326809A (en) * | 2022-08-02 | 2022-11-11 | 山西省智慧交通研究院有限公司 | Apparent crack detection method and detection device for tunnel lining |
| CN115761613A (en) * | 2022-08-10 | 2023-03-07 | 中铁隧道局集团有限公司 | Automatic tunnel crack detection method based on convolutional network |
| CN116520831A (en) * | 2023-04-14 | 2023-08-01 | 广西交通工程检测有限公司 | Device and method for correcting synchronization of geological radar walking track and radar image |
| CN116399812A (en) * | 2023-05-31 | 2023-07-07 | 张磊 | Highway tunnel detecting system |
Non-Patent Citations (3)
| Title |
|---|
| Research on crack identification of tunnel lining based on image processing;Yang Xiang;《2022 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI)》;318-322 * |
| 基于隧道断面面积变化的围岩稳定性判别;刘小俊 等;《铁道标准设计》;119-123 * |
| 超长联络通道冻结温度场发展规律及其对隧道变形的影响;陈军浩 等;《长江科学院院报》;104-111 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116699723A (en) | 2023-09-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210110262A1 (en) | Method and system for semi-supervised deep anomaly detection for large-scale industrial monitoring systems based on time-series data utilizing digital twin simulation data | |
| ES2688196T3 (en) | Condition Monitoring Procedure | |
| CN111737909B (en) | Structural health monitoring data anomaly identification method based on space-time graph convolutional network | |
| US10977568B2 (en) | Information processing apparatus, diagnosis method, and program | |
| CN116625438B (en) | Gas pipe network safety on-line monitoring system and method thereof | |
| CN105675038B (en) | fault prediction device of instrument | |
| CN104952753A (en) | Measurement Sampling Method | |
| JP2017010232A (en) | Plant diagnostic device and plant diagnostic method | |
| CN116699723B (en) | Data processing system and early warning method based on tunnel lining arch part falling block | |
| JP5104567B2 (en) | Energy demand forecasting device | |
| JP2010218394A (en) | Energy demand prediction device | |
| CN113283113B (en) | Solar cell array power generation current prediction model training method, abnormality detection method, device and medium | |
| CN112418529B (en) | Outdoor advertisement online collapse prediction method based on LSTM neural network | |
| CN113484817A (en) | Intelligent electric energy meter automatic verification system abnormity detection method based on TSVM model | |
| CN111354496A (en) | Nuclear power plant accident online diagnosis and state tracking prediction method | |
| CN117312769A (en) | BiLSTM-based method for detecting abnormality of time sequence data of Internet of things | |
| CN109308395B (en) | Wafer-level space measurement parameter anomaly identification method based on LOF-KNN algorithm | |
| CN117168861A (en) | Abnormality monitoring method and abnormality monitoring system for sewage treatment equipment | |
| CN116189802A (en) | Transformer fault early warning method based on gas concentration time sequence data | |
| KR20240003469A (en) | Predictive diagnosis method and system of nuclear power plant equipment | |
| CN112861957B (en) | Method and device for detecting running state of oil well | |
| TWI754911B (en) | System and method for determining cause of abnormality in semiconductor manufacturing processes | |
| CN109376451B (en) | Automatic equipment failure rate calculation method based on fitting association | |
| CN112381235A (en) | Auxiliary method for monitoring state change of preheater in cement plant | |
| CN115980890B (en) | Rainfall station abnormal data detection method based on space-time elements |
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 |