CN110159869A - A kind of detecting robot of pipe and its Multi-sensor Fusion detection method - Google Patents
A kind of detecting robot of pipe and its Multi-sensor Fusion detection method Download PDFInfo
- Publication number
- CN110159869A CN110159869A CN201910417013.1A CN201910417013A CN110159869A CN 110159869 A CN110159869 A CN 110159869A CN 201910417013 A CN201910417013 A CN 201910417013A CN 110159869 A CN110159869 A CN 110159869A
- Authority
- CN
- China
- Prior art keywords
- data
- robot
- sensor
- tube environment
- oneself state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 69
- 230000004927 fusion Effects 0.000 title claims abstract description 40
- 238000000605 extraction Methods 0.000 claims abstract description 18
- 241001269238 Data Species 0.000 claims abstract description 6
- 230000001133 acceleration Effects 0.000 claims description 8
- 230000009184 walking Effects 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 3
- 230000015572 biosynthetic process Effects 0.000 claims description 2
- 238000003786 synthesis reaction Methods 0.000 claims description 2
- 241000208340 Araliaceae Species 0.000 claims 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims 1
- 235000003140 Panax quinquefolius Nutrition 0.000 claims 1
- 235000008434 ginseng Nutrition 0.000 claims 1
- 230000008447 perception Effects 0.000 abstract description 8
- 239000010410 layer Substances 0.000 description 13
- 230000007246 mechanism Effects 0.000 description 10
- 230000033001 locomotion Effects 0.000 description 5
- 230000007547 defect Effects 0.000 description 4
- 238000000034 method Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000006378 damage Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 230000010365 information processing Effects 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 239000011229 interlayer Substances 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F16—ENGINEERING ELEMENTS AND UNITS; GENERAL MEASURES FOR PRODUCING AND MAINTAINING EFFECTIVE FUNCTIONING OF MACHINES OR INSTALLATIONS; THERMAL INSULATION IN GENERAL
- F16L—PIPES; JOINTS OR FITTINGS FOR PIPES; SUPPORTS FOR PIPES, CABLES OR PROTECTIVE TUBING; MEANS FOR THERMAL INSULATION IN GENERAL
- F16L55/00—Devices or appurtenances for use in, or in connection with, pipes or pipe systems
- F16L55/26—Pigs or moles, i.e. devices movable in a pipe or conduit with or without self-contained propulsion means
- F16L55/28—Constructional aspects
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F16—ENGINEERING ELEMENTS AND UNITS; GENERAL MEASURES FOR PRODUCING AND MAINTAINING EFFECTIVE FUNCTIONING OF MACHINES OR INSTALLATIONS; THERMAL INSULATION IN GENERAL
- F16L—PIPES; JOINTS OR FITTINGS FOR PIPES; SUPPORTS FOR PIPES, CABLES OR PROTECTIVE TUBING; MEANS FOR THERMAL INSULATION IN GENERAL
- F16L2101/00—Uses or applications of pigs or moles
- F16L2101/30—Inspecting, measuring or testing
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- Manipulator (AREA)
Abstract
The present invention relates to robotic technology field, a kind of detecting robot of pipe and its Multi-sensor Fusion detection method are provided, can accurately obtain tube environment perception and itself perception, infomation detection is comprehensive, and accuracy rate is high.Above-mentioned fusion detection method includes main control module every preset time, obtains the detection data of each sensor；All detection datas that current time obtains are divided into robot oneself state data and tube environment data；Respectively to the robot oneself state data and the progress feature extraction of tube environment data that current time obtains；Respectively to the robot oneself state data and tube environment data progress parameter Estimation and feature identification after feature extraction；Fusion calculation is carried out to the subsequent time data estimation of robot oneself state data and tube environment data and current time characteristic attribute respectively, obtains the comprehensive situation estimation of robot operating status and tube environment situation.Solve existing pipe robot, the problem that infomation detection is not complete, false detection rate is high.
Description
Technical field
The present invention relates to detecting robot of pipe technical fields, more particularly to a kind of detecting robot of pipe and its more biographies
Sensor fusion detection method.
Background technique
Oil-gas pipeline buries mostly and spreads on underground, for the safe handling for guaranteeing pipeline, finds the damage such as pipe deforming, corrosion in time
Condition of the injury condition needs periodically to carry out detection inside pipeline, finds various defects and damage in advance, understand the degree of danger of each pipeline section,
Corresponding measure is taken, to effectively prevent and reduce pipeline accident, save pipeline maintenance fund.Detecting robot of pipe is to carry out
The ideal equipment of pipeline detection, it can along inner wall of the pipe automatically walk, and usually equipped with one or more sensors,
Under the remote control of operator, carry out detecting operation in pipe.
As disclosed a kind of modularization support track type pipeline inner machine people in Chinese patent literature CN 109483561A,
Including main body mechanism, modularization supporting mechanism, Modular track mechanism.Main body mechanism uses hollow cylindrical rack, circumferentially
Multiple sliding slots are provided with, for carrying the modules being mounted in robot and providing to the module being mounted in robot dynamic
Power；Modularization supporting mechanism is mounted on main body mechanism, actively adapts to mechanism and spring company using leadscrew-nut mechanism composition
The design that the passive adaptation mode of bar sliding block composition combines is used for Modular track mechanism supports in pipeline；Modularization
Pedrail mechanism is driven using single-crawler single and electric machine built-in.Above-mentioned track type pipeline inner machine people, the sensor of carrying is seldom, nothing
Method works independently in pipeline, and not comprehensive enough to the detection of pipeline environment, and detection error is big, and false detection rate is high, is believing
Breath processing aspect only carries out individually simple judgement to the information of sensor passback, can not obtain accurate tube environment
Information and robot oneself state information cause robot all poor to environment sensing in pipeline and itself perception.
Summary of the invention
For this purpose, carrying sensor technical problem to be solved by the present invention lies in the detecting robot of pipe of the prior art
Less, infomation detection is not comprehensive, false detection rate is high and too simple to the processing of sensor back information, and it is accurate to obtain
Pipeline in environment sensing and itself perception, and provide a kind of carrying multiple sensors, infomation detection is comprehensive, returns to sensor
Information carries out comprehensive fusion treatment, can accurately obtain in pipeline the detecting robot of pipe of environment sensing and itself perception and its
Multi-sensor Fusion detection method.
In order to solve the above technical problems, The technical solution adopted by the invention is as follows:
A kind of detecting robot of pipe, including main body rack and the three group walking groups circumferentially uniformly distributed around the main body rack
Part, the Athey wheel that the walking component includes bottom bracket and is arranged on the bottom bracket, the bottom bracket pass through company
It connects bracket to connect with the main body rack, laser radar, camera, gyroscope, temperature and humidity is provided on the main body rack and is passed
Sensor and gas concentration sensor are provided with diaphragm pressure sensor, leakage field module and encoder, institute on each Athey wheel
It states and is respectively arranged with infrared distance sensor and mileage wheel on the first extending bracket and the second extending bracket on the outside of main body rack
Module.
Preferably, the laser radar and the camera are set to side of the main body rack towards direction of travel,
The gyroscope, the Temperature Humidity Sensor and the gas concentration sensor are set to the inside of the main body rack, described
Diaphragm pressure sensor is set in the interlayer of the Athey wheel, and the leakage field module setting is uniformly distributed in the Athey wheel
Inside, the encoder are set on Athey wheel motor gear mounted.
A kind of Multi-sensor Fusion detection method of detecting robot of pipe, comprising:
Step 1, main control module obtain the detection data of each sensor every preset time；
All detection datas that current time obtains are divided into robot oneself state data and tube environment by step 2
Data；
Step 3, respectively to current time obtain the robot oneself state data and the tube environment data into
Row feature extraction；
Step 4, respectively to the robot oneself state data and tube environment data progress after feature extraction
Parameter Estimation obtains the subsequent time data estimation of the robot oneself state data and the tube environment data respectively；
Meanwhile to the robot oneself state data and tube environment data progress feature identification after feature extraction, respectively
Obtain the current time characteristic attribute of the robot oneself state data and the tube environment data；
Step 5, respectively to the subsequent time number of the robot oneself state data and the tube environment data
Fusion calculation is carried out with the current time characteristic attribute according to estimates, obtains the comprehensive of robot operating status and tube environment situation
Close battle field situation.
Preferably, in the step 3, the feature extraction, which refers to, carries out the time to all detection datas at current time
Calibration and space coordinate transformation, with unified time reference point and spatial reference point needed for forming fusion calculation.
Preferably, in the step 4, the parameter Estimation is by the robot oneself state number after feature extraction
According to the tube environment data be respectively formed a row of N column matrix measured value, by the detection data value at current time with
Last moment obtains the robot oneself state data and institute multiplied by weight number to the deviation of the data estimated value at current time
State the subsequent time data estimation of tube environment data；
The feature be identified as according to after feature extraction the robot oneself state data and the tube environment number
According to observed result, the feature vector of a N-dimensional is respectively formed, wherein independent special per one-dimensional represent detected data one
Sign, to obtain the current time characteristic attribute of the robot oneself state data and the tube environment data.
Preferably, the robot oneself state data include caterpillar drive status data, robot travel distance data,
Obstacle principle condition and robot and front obstacle range data in pipeline；
The tube environment data include pipeline detection image, inner wall of the pipe stray field signal, in pipeline environment temperature
Harmful gas concentration data in degree and humidity data and pipeline.
Preferably, the caterpillar drive status data is by the positive pressure force data and crawler belt row between crawler belt and inner wall of the pipe
Walk speed data acquisition.
Preferably, the caterpillar drive status data is by the positive pressure force data and crawler belt row between crawler belt and inner wall of the pipe
Walk speed data, again by robot run acceleration information verify obtaining.
Preferably,
Positive pressure force data between the crawler belt and inner wall of the pipe is obtained by diaphragm pressure sensor；
The crawler travel speed data is obtained by encoder；
The robot operation acceleration information is obtained by gyroscope；
The robot travel distance data are obtained by mileage wheel module；
Obstacle principle condition is obtained by laser radar in the pipeline；
The robot is obtained with front obstacle range data by infrared distance sensor；
The pipeline detection image is obtained by camera；
The inner wall of the pipe stray field signal is obtained by leakage field module；
The temperature and humidity data of environment are obtained by Temperature Humidity Sensor in the pipeline；
Harmful gas concentration data are obtained by gas concentration sensor in the pipeline.
Preferably, the comprehensive situation of the robot operating status and tube environment situation estimation is sent to master control mould
Block carries out decision, obtains corresponding counter-measure；The preset time is 0.2s.
The above technical solution of the present invention has the following advantages over the prior art:
Detecting robot of pipe provided by the invention and its Multi-sensor Fusion detection method, robot is as a flexibility
Platform is equipped with a variety of peripheral modules and sensor, and detection information is comprehensive, and a variety of biographies are handled by the way of Multi-sensor Fusion
The information of sensor passback, can obtain the accurate data of operating status in tube environment situation and robot pipe, substantially increase
Detect accuracy.
Detailed description of the invention
In order to make the content of the present invention more clearly understood, it below according to specific embodiments of the present invention and combines
Attached drawing, the present invention is described in further detail, wherein
Fig. 1 is the schematic diagram one of inventive pipeline detection robot；
Fig. 2 is the schematic diagram two of inventive pipeline detection robot；
Fig. 3 is the control system architecture diagram of inventive pipeline detection robot；
Fig. 4 is the information processing model figure of Multi-sensor Fusion detection method of the present invention.
Appended drawing reference indicates in figure are as follows: 1- main body rack, 2- connecting bracket, 3- bottom bracket, 4- Athey wheel, 5- first prolong
Stretch bracket, 6- electric pushrod, 7- motor gear, the second extending bracket of 8-.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
It as shown in Figure 1, 2, is a kind of preferred embodiment of detecting robot of pipe of the present invention.The detecting robot of pipe
Including main body rack 1 and the three group walking components circumferentially uniformly distributed around the main body rack 1, the walking component includes bottom bracket
3 and the Athey wheel 4 that is arranged on the bottom bracket 3, the bottom bracket 3 connected by connecting bracket 2 and the main body rack 1
It connects.The main body rack 1 is positive triangular prism shape, and the connecting bracket 2 is hinge with the main body rack 1, the bottom bracket 3
It connects.Be additionally provided with electric pushrod 6 between the connecting bracket 2 and the main body rack 1, one end of the electric pushrod 6 with it is described
Main body rack 1 is hinged, and the other end and the middle part of the connecting bracket 2 are hinged, by the stretching motion of electric pushrod, make robot
It can be bonded with inner wall of the pipe in operational process in pipeline, obtain suitable normal pressure.Due to the traveling movement etc. of robot
It will not influence main body rack, therefore multiple sensors, control unit, battery etc. can be set as needed inside main body rack,
Carrying ability is strong.
Laser radar, camera, gyroscope, Temperature Humidity Sensor and gas concentration is provided on the main body rack 1 to pass
Sensor is provided with diaphragm pressure sensor, leakage field module and encoder, 1 outside of main body rack on each Athey wheel 4
The first extending bracket 5 and the second extending bracket 8 on be respectively arranged with infrared distance sensor and mileage wheel module.
Specifically, the laser radar and the camera are set to the main body rack 1 towards the side of direction of travel；
The gyroscope, the Temperature Humidity Sensor and the gas concentration sensor are set to the inside of the main body rack 1, preferably
The ground gyroscope is set to the center inside the main body rack 1；The diaphragm pressure sensor is set to the shoe
In the interlayer of belt wheel 4；The leakage field module setting is uniformly distributed in the inside of the Athey wheel 4；The encoder is set to institute
It states on the motor gear 7 mounted of Athey wheel 4.
The laser radar, for carrying out 360 ° of scannings of two dimension, building pipe to inner wall of the pipe in robot traveling process
Road inner wall two dimension point cloud chart picture realizes the detection of barrier situation.The camera, for returning and storing pipeline detection figure
Picture.The gyroscope, for detecting the operation acceleration of robot.The Temperature Humidity Sensor, for detecting pipeline inner ring border
Temperature and humidity, as measure corrosive pipeline situation foundation.The gas concentration sensor is harmful in pipeline for detecting
The concentration of gas (such as methane).The diaphragm pressure sensor, for detecting the positive pressure between each crawler belt and inner wall of the pipe
Power.The leakage field module, for detecting inner wall of the pipe stray field signal, to judge defect of pipeline position.The encoder, is used for
Detect the speed of travel of crawler belt.The infrared distance sensor, for detecting the robot at a distance from the obstacle of front, and
When adjustment the robot speed of service pass through bend pipe.The mileage wheel module, for detecting the travel distance of the robot.
Detecting robot of pipe of the invention is directed to 1016mm large-scale petroleum pipe design, to comply in made in China 2025
Key post robot substitution, intelligent and national oil and gas pipeline tend to the trend of enlargement, can carry a variety of detections
Module and sensor can accurately obtain environment sensing and robot itself perception in pipeline.
Detecting robot of pipe of the invention can realize Robot remote and autonomous operation double control mode, have open/stop,
Differential speed rotation control, defect information detection, robot monitoring running state, machine in pipeline in travelling control, robot pipeline
The functions such as people's automatic fault selftesting.As shown in figure 3, in the control system of inventive pipeline detection robot, in application layer part, on
Position machine (PC machine) can be communicated by the interface and robot of application layer, complete artificial monitoring and remote control operation.Sensing layer part by
Laser radar, encoder, diaphragm pressure sensor, gyroscope, mileage wheel, infrared distance sensor, Temperature Humidity Sensor, gas
Concentration sensor, camera are constituted, and realize tube environment perception, the perception of robot oneself state and robot fault pre-detection,
Multiple sensors information is handled by signal processing module and is merged, and to make up the erroneous detection of single-sensor, improves detection accuracy.Control
Preparative layer part multi-sensor information processing fusion and autonomous layering are realized by DSP module and the control module of Cortex_M kernel
Control, and communicated with host computer；Control layer part is first initialized after robot is opened, and then starts to advance, and is acquired
The sensing data of sensing layer sensor transmissions carries out inspection, runs corresponding program by event-driven, and carry out robot fault inspection
It surveys.Hardware bottom layer part is mainly made of direct current generator, driving (driving plate of direct current generator) and steering engine, is sent out by control module
The control information sent is overdrived to control direct current generator movement, camera is provided on steering engine, by the movement of steering engine come real
The existing multi-direction rotation of camera, encoder, the speed of pressure sensor feedback and crawler belt pressure information realize crawler belt and push rod fortune
Dynamic closed-loop control.
As shown in figure 4, the Multi-sensor Fusion detection method of inventive pipeline detection robot, comprising:
Step 1, main control module obtain the detection data of each sensor every preset time.
In the present embodiment, the preset time is set as 0.2s.In the present invention, each sensor detection obtained
Data all include two aspect content of data Layer information and characteristic layer information.
All detection datas that current time obtains are divided into robot oneself state data and tube environment by step 2
Data.
Specifically, the robot oneself state data include caterpillar drive status data, robot travel distance data,
Obstacle principle condition and robot and front obstacle range data in pipeline；
The tube environment data include pipeline detection image, inner wall of the pipe stray field signal, in pipeline environment temperature
Harmful gas concentration data in degree and humidity data and pipeline.
The caterpillar drive status data is by the positive pressure force data and crawler travel speed between crawler belt and inner wall of the pipe
Data, again by robot run acceleration information verify obtaining.In the present embodiment,
Positive pressure force data between the crawler belt and inner wall of the pipe is obtained by diaphragm pressure sensor；
The crawler travel speed data is obtained by encoder；
The robot operation acceleration information is obtained by gyroscope；
The robot travel distance data are obtained by mileage wheel module；
Obstacle principle condition is obtained by laser radar in the pipeline；
The robot is obtained with front obstacle range data by infrared distance sensor；
The pipeline detection image is obtained by camera；
The inner wall of the pipe stray field signal is obtained by leakage field module；
The temperature and humidity data of environment are obtained by Temperature Humidity Sensor in the pipeline；
Harmful gas concentration data are obtained by gas concentration sensor in the pipeline.
After the diaphragm pressure sensor of tripodia Athey wheel interlayer and the detection data of encoder are in parallel, the data Layer of output is believed
Breath and characteristic layer information are merged with the acceleration information of gyroscope, and the information of these three comprehensive sensors can accurate judgement tripodia shoe
The motion state of belt wheel prejudges robot in time and is likely to occur situation about being stuck in pipeline, stops driving robot motor in advance,
Carry out pose adjustment.Later, gyroscope, mileage wheel, laser radar, infrared distance sensor data parallel connection fusion, obtain machine
People's oneself state accurate data, such as specific location, travel speed, with bend pipe turning distance etc., camera, leakage field module, temperature
Humidity sensor and gas sensor data parallel connection fusion, obtain tube environment accurate data.
Step 3, respectively to current time obtain the robot oneself state data and the tube environment data into
Row feature extraction.
The feature extraction refers to time and spatial reference point for unified each sensor, all inspections to current time
Measured data carries out time calibration and space coordinate transformation, with unified time reference point and georeferencing needed for forming fusion calculation
Point.
Step 4, respectively to the robot oneself state data and tube environment data progress after feature extraction
Parameter Estimation obtains the subsequent time data estimation of the robot oneself state data and the tube environment data respectively；
Meanwhile to the robot oneself state data and tube environment data progress feature identification after feature extraction, respectively
Obtain the current time characteristic attribute of the robot oneself state data and the tube environment data.
The parameter Estimation is that the fusion of data Layer information is carried out to the detection data of each sensor, using Kalman
The data fusion mode of filtering.Specifically, by after feature extraction the robot oneself state data and the tube environment
Data are respectively formed the matrix measured value of row of N column, by the detection data value at current time and last moment to it is current when
The deviation of the data estimated value at quarter obtains the robot oneself state data and the tube environment data multiplied by weight number
The subsequent time data estimation.It should be noted that above-mentioned weight number changes always, the power in Kalman filtering
Weight and detection data value and last moment are related to the deviation of the data estimated value at current time.
The feature identification is that the fusion of characteristic layer information is carried out to the detection data of each sensor, specifically, according to spy
The observed result of the robot oneself state data and the tube environment data after sign extraction, is respectively formed a N-dimensional
Feature vector, wherein per an one-dimensional independent characteristic for representing detected data, as having zero defect, robot traveling shape in pipe
Condition quality etc., to obtain the current time characteristic attribute of the robot oneself state data and the tube environment data.
Step 5, respectively to the subsequent time number of the robot oneself state data and the tube environment data
Fusion calculation is carried out with the current time characteristic attribute according to estimates, obtains the comprehensive of robot operating status and tube environment situation
Close battle field situation.
The fusion calculation is the row of N column matrix measured value and N exported to the parameter Estimation and feature identification division
The dependent observation result of dimensional feature vector is verified, is analyzed, supplementing choice, modification and status tracking estimation, to uncorrelated sight
It surveys result and carries out analysis and synthesis, obtain and the comprehensive situation of robot operating status and tube environment situational awareness is estimated.
The final result obtained by Multi-sensor Fusion detection method provided by the invention, i.e. robot operating status
Estimate with the comprehensive situation of tube environment situational awareness, is sent to main control module and carries out decision, obtain corresponding counter-measure, it is main
The decision for carrying out corresponding That deal with the TBT will be changed for complex environment and target by controlling module, be controlled by machine main control module
Direct current generator, push rod etc. are adjusted, thus guarantee trouble-free operation of the robot in pipeline and to tube environment carry out compared with
Comprehensively and accurately to detect.For example, being estimated according to the comprehensive situation of robot operating status, feeds back robot out and be likely to occur
The situation blocked is taken by main control module decision and stops the measure that tripodia motor makes robot stop in time, to avoid robot
It blocks.
Detecting robot of pipe provided by the invention and its Multi-sensor Fusion detection method, and only use a kind of sensor
Robot compare, multiple-sensor integration can more fully obtain the information to detected object and increase the reliability of system,
Even if system may still operate normally in one or more sensors failure.The data processing side of Fusion
Formula has better fault-tolerance compared to the data processing method for only individually being judged sensor information or being simply added,
Because the noise of each sensor be it is incoherent, can obviously inhibit noise after fusion treatment, reduce uncertain.Meanwhile this
The fusion detection method of invention improves the complementarity between each sensor information, and certain sensors provide dense information, other
Sensor provides sparse information, these are complementary after fusion, can compensate for the uncertainty and measurement range of single-sensor
Limitation.Use Kalman filtering that can predict that NextState value is provided under statistical significance according to current time value for fuse information
Optimal estimation, and its recursion characteristic make system information processing do not need a large amount of information and storage operation.
In other embodiments, according to actual needs, caterpillar drive status data can also be by between crawler belt and inner wall of the pipe
Positive pressure force data and crawler travel speed data obtain, without further pass through robot operation acceleration information tested
Card, is also able to achieve the purpose of the present invention.
Obviously, the above embodiments are merely examples for clarifying the description, and does not limit the embodiments.It is right
For those of ordinary skill in the art, can also make on the basis of the above description it is other it is various forms of variation or
It changes.There is no necessity and possibility to exhaust all the enbodiments.And it is extended from this it is obvious variation or
It changes still within the protection scope of the invention.
Claims (10)
1. a kind of detecting robot of pipe, including main body rack (1) and the three group walkings circumferentially uniformly distributed around the main body rack (1)
Component, the walking component include the Athey wheel (4) of bottom bracket (3) and setting on the bottom bracket (3), the bottom
Bracket (3) is connect by connecting bracket (2) with the main body rack (1), it is characterised in that: is arranged on the main body rack (1)
There are laser radar, camera, gyroscope, Temperature Humidity Sensor and gas concentration sensor, is arranged on each Athey wheel (4)
There are diaphragm pressure sensor, leakage field module and encoder, the first extending bracket (5) and second on the outside of the main body rack (1)
Infrared distance sensor and mileage wheel module are respectively arranged on extending bracket (8).
2. detecting robot of pipe according to claim 1, it is characterised in that: the laser radar and the camera are set
The main body rack (1) is placed in towards the side of direction of travel, the gyroscope, the Temperature Humidity Sensor and the gas are dense
Degree sensor is set to the inside of the main body rack (1), and the diaphragm pressure sensor is set to the folder of the Athey wheel (4)
In layer, the leakage field module setting is uniformly distributed in the inside of the Athey wheel (4), and the encoder is set to the Athey wheel
(4) on motor gear (7) mounted.
3. a kind of Multi-sensor Fusion detection method of detecting robot of pipe as claimed in claim 1 or 2, which is characterized in that packet
It includes:
Step 1, main control module obtain the detection data of each sensor every preset time；
All detection datas that current time obtains are divided into robot oneself state data and tube environment number by step 2
According to；
Step 3, the robot oneself state data to current time acquisition and the tube environment data carry out special respectively
Sign is extracted；
Step 4, respectively to the robot oneself state data and tube environment data progress parameter after feature extraction
Estimation obtains the subsequent time data estimation of the robot oneself state data and the tube environment data respectively；Meanwhile
To the robot oneself state data and tube environment data progress feature identification after feature extraction, institute is obtained respectively
State the current time characteristic attribute of robot oneself state data and the tube environment data；
Step 5 respectively estimates the subsequent time data of the robot oneself state data and the tube environment data
Meter and the current time characteristic attribute carry out fusion calculation, obtain the synthesis state of robot operating status and tube environment situation
Gesture estimation.
4. Multi-sensor Fusion detection method according to claim 3, it is characterised in that: in the step 3, the spy
Sign, which is extracted, to be referred to all detection datas progress time calibration at current time and space coordinate transformation, to form fusion calculation institute
The unified time reference point and spatial reference point needed.
5. Multi-sensor Fusion detection method according to claim 4, it is characterised in that: in the step 4, the ginseng
It counts the robot oneself state data being estimated as by after feature extraction and the tube environment data is respectively formed one one
The matrix measured value of row N column, by the detection data value at current time and last moment to the inclined of the data estimated value at current time
Difference multiplied by weight number, estimate by the subsequent time data for obtaining the robot oneself state data and the tube environment data
Meter；
The feature is identified as according to the robot oneself state data and the tube environment data after feature extraction
Observed result is respectively formed the feature vector of a N-dimensional, wherein per an one-dimensional independent characteristic for representing detected data, from
And obtain the current time characteristic attribute of the robot oneself state data and the tube environment data.
6. Multi-sensor Fusion detection method according to claim 5, it is characterised in that:
The robot oneself state data include caterpillar drive status data, robot travel distance data, obstacle in pipeline
Principle condition and robot and front obstacle range data；
The tube environment data include pipeline detection image, inner wall of the pipe stray field signal, in pipeline the temperature of environment and
Harmful gas concentration data in humidity data and pipeline.
7. Multi-sensor Fusion detection method according to claim 6, it is characterised in that: the caterpillar drive status data
By between crawler belt and inner wall of the pipe positive pressure force data and crawler travel speed data obtain.
8. Multi-sensor Fusion detection method according to claim 7, it is characterised in that: the caterpillar drive status data
By between crawler belt and inner wall of the pipe positive pressure force data and crawler travel speed data, again pass through robot operation accelerate degree
It is obtained according to being verified.
9. Multi-sensor Fusion detection method according to claim 8, it is characterised in that:
Positive pressure force data between the crawler belt and inner wall of the pipe is obtained by diaphragm pressure sensor；
The crawler travel speed data is obtained by encoder；
The robot operation acceleration information is obtained by gyroscope；
The robot travel distance data are obtained by mileage wheel module；
Obstacle principle condition is obtained by laser radar in the pipeline；
The robot is obtained with front obstacle range data by infrared distance sensor；
The pipeline detection image is obtained by camera；
The inner wall of the pipe stray field signal is obtained by leakage field module；
The temperature and humidity data of environment are obtained by Temperature Humidity Sensor in the pipeline；
Harmful gas concentration data are obtained by gas concentration sensor in the pipeline.
10. Multi-sensor Fusion detection method according to claim 3, it is characterised in that: the robot operating status
Comprehensive situation estimation with tube environment situation is sent to main control module and carries out decision, obtains corresponding counter-measure；Institute
Stating preset time is 0.2s.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910417013.1A CN110159869B (en) | 2019-05-20 | 2019-05-20 | Pipeline detection robot and multi-sensor fusion detection method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910417013.1A CN110159869B (en) | 2019-05-20 | 2019-05-20 | Pipeline detection robot and multi-sensor fusion detection method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110159869A true CN110159869A (en) | 2019-08-23 |
| CN110159869B CN110159869B (en) | 2020-11-03 |
Family
ID=67631406
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910417013.1A Expired - Fee Related CN110159869B (en) | 2019-05-20 | 2019-05-20 | Pipeline detection robot and multi-sensor fusion detection method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110159869B (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110824524A (en) * | 2019-11-13 | 2020-02-21 | 西安通航装备科技开发有限公司 | Satellite video transmission system based on airborne Ka wave band |
| CN110861123A (en) * | 2019-11-14 | 2020-03-06 | 华南智能机器人创新研究院 | Method and device for visually monitoring and evaluating running state of robot |
| CN110954593A (en) * | 2019-12-18 | 2020-04-03 | 中北大学 | Pipeline defect in-service detection device and method based on rotating magnetic field array type probe |
| CN111007532A (en) * | 2019-12-27 | 2020-04-14 | 江苏恒澄交科信息科技股份有限公司 | Pipeline measuring method based on laser radar |
| CN111735491A (en) * | 2020-05-14 | 2020-10-02 | 国网浙江宁波市鄞州区供电有限公司 | Cable pipeline detection device with accurate measurement |
| CN112228697A (en) * | 2020-11-04 | 2021-01-15 | 杭州申昊科技股份有限公司 | Crawler-type pipeline robot |
| CN112228696A (en) * | 2020-11-04 | 2021-01-15 | 杭州申昊科技股份有限公司 | Air bag type pipeline robot |
| WO2021098342A1 (en) * | 2019-11-22 | 2021-05-27 | 长安大学 | In-situ detection robot for loess geological information |
| CN113273480A (en) * | 2021-05-20 | 2021-08-20 | 安徽师范大学皖江学院 | Intelligent underground infiltrating irrigation system and method based on soil humidity sensing |
| CN114135740A (en) * | 2021-12-01 | 2022-03-04 | 国网江苏省电力有限公司连云港供电分公司 | Pipeline inspection robot |
| CN114136670A (en) * | 2021-10-26 | 2022-03-04 | 中国石油化工股份有限公司 | Pipeline detection robot evaluation method based on pipeline detection robot test platform |
| CN114414571A (en) * | 2022-01-21 | 2022-04-29 | 付世艳 | Wireless toxic gas detection robot |
| CN114739303A (en) * | 2022-06-09 | 2022-07-12 | 国机传感科技有限公司 | Pipeline inner diameter sensing scanning device based on line laser |
| CN114791067A (en) * | 2021-01-25 | 2022-07-26 | 杭州申昊科技股份有限公司 | Pipeline robot with heat detection function, control method and control system |
| CN115081741A (en) * | 2022-07-21 | 2022-09-20 | 西南石油大学 | Natural gas metrological verification intelligent prediction method based on neural network |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103615663A (en) * | 2013-11-11 | 2014-03-05 | 江苏师范大学 | Robot for detecting inner condition of pipeline |
| CN104565675A (en) * | 2014-06-20 | 2015-04-29 | 北京石油化工学院 | Pipeline detection robot |
| CN106764245A (en) * | 2017-01-11 | 2017-05-31 | 福州川大软件科技有限公司 | A kind of crawler belt type pipeline robot |
| CN109114355A (en) * | 2018-10-25 | 2019-01-01 | 南京水动力信息科技有限公司 | A kind of pipe network Robot system |
| CN208595354U (en) * | 2018-06-08 | 2019-03-12 | 上海工程技术大学 | A kind of oil pipeline detection maintenance multi-foot robot |
| CN109611640A (en) * | 2018-12-04 | 2019-04-12 | 山东大学 | Pipe robot |
| CN109737267A (en) * | 2019-01-16 | 2019-05-10 | 青岛理工大学 | Pipeline detection robot and method based on multi-sensor information fusion |
-
2019
- 2019-05-20 CN CN201910417013.1A patent/CN110159869B/en not_active Expired - Fee Related
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103615663A (en) * | 2013-11-11 | 2014-03-05 | 江苏师范大学 | Robot for detecting inner condition of pipeline |
| CN104565675A (en) * | 2014-06-20 | 2015-04-29 | 北京石油化工学院 | Pipeline detection robot |
| CN106764245A (en) * | 2017-01-11 | 2017-05-31 | 福州川大软件科技有限公司 | A kind of crawler belt type pipeline robot |
| CN208595354U (en) * | 2018-06-08 | 2019-03-12 | 上海工程技术大学 | A kind of oil pipeline detection maintenance multi-foot robot |
| CN109114355A (en) * | 2018-10-25 | 2019-01-01 | 南京水动力信息科技有限公司 | A kind of pipe network Robot system |
| CN109611640A (en) * | 2018-12-04 | 2019-04-12 | 山东大学 | Pipe robot |
| CN109737267A (en) * | 2019-01-16 | 2019-05-10 | 青岛理工大学 | Pipeline detection robot and method based on multi-sensor information fusion |
Non-Patent Citations (1)
| Title |
|---|
| 王黎等: "基于多源信息融合的管道机器人定位技术研究", 《科技信息(学术研究)》 * |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110824524A (en) * | 2019-11-13 | 2020-02-21 | 西安通航装备科技开发有限公司 | Satellite video transmission system based on airborne Ka wave band |
| CN110824524B (en) * | 2019-11-13 | 2021-10-26 | 西安通航装备科技开发有限公司 | Satellite video transmission system based on airborne Ka wave band |
| CN110861123A (en) * | 2019-11-14 | 2020-03-06 | 华南智能机器人创新研究院 | Method and device for visually monitoring and evaluating running state of robot |
| WO2021098342A1 (en) * | 2019-11-22 | 2021-05-27 | 长安大学 | In-situ detection robot for loess geological information |
| CN110954593A (en) * | 2019-12-18 | 2020-04-03 | 中北大学 | Pipeline defect in-service detection device and method based on rotating magnetic field array type probe |
| CN111007532A (en) * | 2019-12-27 | 2020-04-14 | 江苏恒澄交科信息科技股份有限公司 | Pipeline measuring method based on laser radar |
| CN111735491A (en) * | 2020-05-14 | 2020-10-02 | 国网浙江宁波市鄞州区供电有限公司 | Cable pipeline detection device with accurate measurement |
| CN112228696A (en) * | 2020-11-04 | 2021-01-15 | 杭州申昊科技股份有限公司 | Air bag type pipeline robot |
| CN112228697A (en) * | 2020-11-04 | 2021-01-15 | 杭州申昊科技股份有限公司 | Crawler-type pipeline robot |
| CN114791067A (en) * | 2021-01-25 | 2022-07-26 | 杭州申昊科技股份有限公司 | Pipeline robot with heat detection function, control method and control system |
| CN114791067B (en) * | 2021-01-25 | 2024-02-06 | 杭州申昊科技股份有限公司 | Pipeline robot with heat detection function, control method and control system |
| CN113273480A (en) * | 2021-05-20 | 2021-08-20 | 安徽师范大学皖江学院 | Intelligent underground infiltrating irrigation system and method based on soil humidity sensing |
| CN113273480B (en) * | 2021-05-20 | 2022-11-11 | 安徽师范大学皖江学院 | Intelligent underground infiltrating irrigation system and method based on soil humidity sensing |
| CN114136670A (en) * | 2021-10-26 | 2022-03-04 | 中国石油化工股份有限公司 | Pipeline detection robot evaluation method based on pipeline detection robot test platform |
| CN114135740A (en) * | 2021-12-01 | 2022-03-04 | 国网江苏省电力有限公司连云港供电分公司 | Pipeline inspection robot |
| CN114135740B (en) * | 2021-12-01 | 2024-03-05 | 国网江苏省电力有限公司连云港供电分公司 | Pipeline detection robot |
| CN114414571B (en) * | 2022-01-21 | 2024-01-26 | 北京中电华劳科技有限公司 | Wireless poisonous gas detection robot |
| CN114414571A (en) * | 2022-01-21 | 2022-04-29 | 付世艳 | Wireless toxic gas detection robot |
| CN114739303A (en) * | 2022-06-09 | 2022-07-12 | 国机传感科技有限公司 | Pipeline inner diameter sensing scanning device based on line laser |
| CN115081741A (en) * | 2022-07-21 | 2022-09-20 | 西南石油大学 | Natural gas metrological verification intelligent prediction method based on neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110159869B (en) | 2020-11-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110159869A (en) | A kind of detecting robot of pipe and its Multi-sensor Fusion detection method | |
| CN110095061A (en) | Vehicle morpheme detection system and method based on profile scan | |
| CN108154084A (en) | For the farm environment cognitive method of the unpiloted Multi-sensor Fusion of agricultural machinery | |
| CN103776463B (en) | Manless working face coal-winning machine automatic Memory coal cutting freedom positioning device method of testing | |
| CN104713491B (en) | The method that the slope monitoring system of slope deforming three-dimensional data can be obtained and its obtain slope deforming three-dimensional data | |
| KR20200141422A (en) | Vehicle and sensing device of utilizing spatial information acquired using sensor, and server for the same | |
| CN101839721A (en) | Visual navigation method in autonomous rendezvous and docking | |
| CN110766785B (en) | Real-time positioning and three-dimensional reconstruction device and method for underground pipeline | |
| CN110455275A (en) | A kind of macrotype spherical storage tank climbing robot Position Fixing Navigation System and method | |
| CN205950750U (en) | Transformer station inspection robot control system that navigates based on inertial navigation | |
| Song et al. | Design of in-pipe robot based on inertial positioning and visual detection | |
| CN107014296A (en) | Comprehensive inspection car OCS inspecting system high speed orientation triggering method and device | |
| CN110454642A (en) | A kind of control method of detecting robot of pipe | |
| CN108388187A (en) | A kind of robot control system | |
| CN104005324A (en) | Pavement texture information detection system | |
| US20220111531A1 (en) | Robot globally optimal visual positioning method and device based on point-line features | |
| CN117150425B (en) | Segment erector motion state prediction method based on mechanism data fusion | |
| CN109668547A (en) | A kind of bridge intelligence inspection system | |
| CN116524116A (en) | Drainage pipeline three-dimensional model construction system with multi-sensor data fusion function | |
| Gao et al. | Multi-Sensor Fusion Perception System in Train | |
| Monteriù et al. | Real-time model-based fault detection and isolation for ugvs | |
| KR102660478B1 (en) | System and apparatus for crop automatic image acquisition and diagnosis method of acquired plant image | |
| CN109284753A (en) | A kind of localization method of liquid transmission line and application | |
| Tian et al. | A design of odometer-aided visual inertial integrated navigation algorithm based on multiple view geometry constraints | |
| Monteriu et al. | Experimental validation of a real-time model-based sensor fault detection and isolation system for unmanned ground vehicles |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20201103 |