CN110501421A - A kind of track profiling method of detection based on mechanical arm - Google Patents
A kind of track profiling method of detection based on mechanical arm Download PDFInfo
- Publication number
- CN110501421A CN110501421A CN201910670771.4A CN201910670771A CN110501421A CN 110501421 A CN110501421 A CN 110501421A CN 201910670771 A CN201910670771 A CN 201910670771A CN 110501421 A CN110501421 A CN 110501421A
- Authority
- CN
- China
- Prior art keywords
- mechanical arm
- track
- failure detector
- flaw
- teaching
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/04—Analysing solids
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/22—Details, e.g. general constructional or apparatus details
- G01N29/26—Arrangements for orientation or scanning by relative movement of the head and the sensor
- G01N29/265—Arrangements for orientation or scanning by relative movement of the head and the sensor by moving the sensor relative to a stationary material
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B25/00—Models for purposes not provided for in G09B23/00, e.g. full-sized devices for demonstration purposes
- G09B25/02—Models for purposes not provided for in G09B23/00, e.g. full-sized devices for demonstration purposes of industrial processes; of machinery
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B9/00—Simulators for teaching or training purposes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2291/00—Indexing codes associated with group G01N29/00
- G01N2291/02—Indexing codes associated with the analysed material
- G01N2291/023—Solids
- G01N2291/0234—Metals, e.g. steel
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2291/00—Indexing codes associated with group G01N29/00
- G01N2291/26—Scanned objects
- G01N2291/262—Linear objects
- G01N2291/2623—Rails; Railroads
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Educational Technology (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Acoustics & Sound (AREA)
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
The track profiling method of detection based on mechanical arm that the present invention relates to a kind of, it include: step S1, artificial teaching cooperates with the profiling flaw detection operation completed to continuous welded rail track connector by people with mechanical arm, mechanical arm terminal position and speed data, teaching m times when being fulfiled assignment with certain frequency f record;Step S2, track generate, by m time repeat teaching generate data set using Gaussian process return establish mapping model, obtain the time to position Function Mapping relationship;Step S3, autonomous to detect a flaw, the track that mechanical arm is generated according to step S2 drives failure detector to detect a flaw continuous welded rail track connector, while using location-based impedance control strategy, guarantees the constant-force contact of failure detector and joint surface in detection process.To the adaptability of continuous welded rail track joints when present invention study is manually detected a flaw, the contact force of control failure detector docking head surface is constant, realizes mechanical arm and detects a flaw to the autonomous profiling of rail joint, improves detection quality.
Description
Technical field
The present invention relates to track inspection fields, more particularly, to a kind of track profiling method of detection based on learning from instruction.
Background technique
With continuing to increase for train speed raising, heavy duty and rate of traffic flow, sub-rail foundation equipment is proposed more acute
Test is itself compared to rail, bigger to the damage capability of gapless rail joint.Gapless rail joint can generate weld seam and split
It the defects of line, pit, will affect the stationarity and safety of train operation, while rail can be accelerated to fail, bring biggish warp
Ji loss just can guarantee the quality of track, reduce the generation of accident so needing to carry out periodic detection to gapless rail joint.
For the research of track flaw detection, China has developed some achievements in recent years.Patent of invention (CN109212038) is announced
A kind of rail detector car and its probe layout system, including be set on car body, for raceway surface emit ultrasonic wave into
Several monocrystalline ultrasonic probes of row carrying out flaw detection, twin crystal ultrasonic probe and with adjustable ultrasonic incident angle function
Phased-array ultrasonic probe, and each probe can rotate horizontally, to adapt to different types of track.Patent of invention
(CN105109518A) disclose a kind of novel track inspection car, including a flat evacuation bottom plate, width be less than two rails it
Between width, height be less than rail height, further include multiple transmission shafts, two transmission shafts of the outermost at two tracks
Outer end be respectively provided with a rail wheel, track failure detector, the axle sleeve between the transmission shaft are installed on the rail wheel
Lower section is fixed with vertically flexible dipper crowding gear.
Existing rail detector car, failure detector fastening are set on car body, i.e. the relative position of failure detector and track
Fixed, the contact force of failure detector and raceway surface is uncontrollable, and can only detect a flaw along track to rail itself, cannot be right
Gapless rail joint carries out complete profiling flaw detection.And the flaw detection to gapless rail joint, main there are two main points, one is to visit
The profiling for hurting device along joint surface is moved, the other is the constant force control that failure detector is contacted with joint surface.
Summary of the invention
The track profiling method of detection based on learning from instruction that the object of the present invention is to provide a kind of, is able to solve background technique
The problems in, it overcomes the deficiencies of existing technologies, improves detection quality.
In order to solve the above technical problems, the present invention provides a kind of track profiling method of detection based on learning from instruction, including
Following steps:
Step S1, artificial teaching cooperate with the profiling flaw detection operation completed to continuous welded rail track connector by people with mechanical arm.People
Driving machinery arm completes flaw detection operation, the terminal position and speed of itself when mechanical arm is fulfiled assignment with certain frequency f record
Data, teaching m times;
The purpose of teaching is to complete flaw detection work, intermediate as long as the process of teaching can achieve the purpose that complete flaw detection work
The motion profile process of mechanical arm will not uniquely not influence the result of flaw detection work.
Step S2, track generate, and repeat the data set that teaching generates for m times and establish mapping mould using Gaussian process recurrence
Type, obtain the time to position Function Mapping relationship;
Step S3, autonomous to detect a flaw, the track that mechanical arm is generated according to step S2 drives failure detector to continuous welded rail track connector
It detects a flaw, while impedance is utilized that is, while controlling mechanical arm tail end position using location-based impedance control strategy
The control of power is converted correction position control by model, guarantees the constant-force contact of failure detector and joint surface in detection process.
Preferably, in step S1, the interaction of people and mechanical arm are realized using admittance controller, so that mechanical arm can be
Flaw detection operation is completed under the guidance of manpower, while remaining that failure detector is adjacent to continuous welded rail track joint surface.With certain frequency
The position data in each joint of mechanical arm, teaching m times when rate f record fulfils assignment.
Preferably, in step sl, by teaching process, n data point is collected on every trackIts
Middle t=[t1,t2,…,tn]TFor time point, x=[x1,x2,…,xn]TFor flaw detection point, the Descartes under robot coordinate system is sat
Mark;The likelihood function of time point and coordinate is obtained according to prior distribution:
Linear regression function f (t) based on bayesian theory=tTω, wherein t ∈ Rd, ω=[ω1,ω2,…,ωn]T,
F (t) representative function value.
Assuming that ω: (0, Σp), the probability distribution of ω is found out by the definition of bayesian theory and Gaussian Profile:
The Posterior probability distribution of ω is found out by maximum posteriori probability:
Wherein, p (x | t) is edge similar density, unrelated with weight ω, then another representation of formula (3):
p(ω|t,x)∝p(x|t,ω)p(ω) (4)
Wherein, ∝ expression is proportional to.Formula (1) and formula (2) is brought into formula (4), obtains the posterior probability point of weight vector ω
Cloth form:
Wherein,It enablesThe posterior probability of weight vector ω meets Gauss point
Cloth:
When there is data t*When input, corresponding predicted value x*Probability distribution are as follows:
It can be seen that predicted value x*Distribution or Gaussian Profile, manner is the Posterior probability distribution of weight vector ω
Mean value and data t*Product, variance is data t*With the quadratic form of the variance of the Posterior probability distribution of weight vector ω.
Preferably, in step s3, when executing flaw detection task, location-based impedance control strategy is by actually connecing
The deviation of touch and expected force obtains position deviation amount through impedance controller, and then adjusts the position of mechanical arm tail end failure detector
It sets, realizes the constant-force contact of failure detector and continuous welded rail track joint surface.
The beneficial effects of the present invention are: 1. are applied to learning from instruction in track flaw detection, to seamless when learning manually to detect a flaw
The adaptability of rail joint shape, it is only necessary to artificial teaching can carry out autonomous profiling flaw detection operation to gapless rail joint,
Improve flaw detection efficiency;2. realizing failure detector and nothing in detection process by using location-based impedance control strategy
The constant-force contact for stitching rail joint surface, improves detection quality.
Detailed description of the invention
Fig. 1 is the method for the present invention flow chart.
Fig. 2 is the impedance control block diagram the present invention is based on position.
Specific embodiment
Below with reference to the embodiments and with reference to the accompanying drawing the technical solutions of the present invention will be further described.
Embodiment:
In the embodiment of the present invention, artificial teaching is carried out first.The interaction that people and mechanical arm are realized using admittance controller, from
And mechanical arm can complete flaw detection operation under the guidance of manpower, cooperate with completion to continuous welded rail track connector with mechanical arm by people
Profiling flaw detection operation, mechanical arm terminal position and speed data, teaching m times when being fulfiled assignment with certain frequency f record.
Then track generation is carried out.The data set that teaching generates is repeated by m times, and foundation mapping mould is returned using Gaussian process
Type, obtain the time to position Function Mapping relationship.By teaching process, n data point is collected on every trackWherein t=[t1,t2,…,tn]TFor time point, x=[x1,x2,…,xn]TIt is flaw detection point under robot coordinate system
Cartesian coordinate;The likelihood function of time point and coordinate is obtained according to prior distribution:
Linear regression function f (t) based on bayesian theory=tTω, wherein t ∈ Rd, ω=[ω1,ω2,…,ωn]T,
F (t) representative function value.
Assuming that ω: (0, Σp), the probability distribution of ω is found out by the definition of bayesian theory and Gaussian Profile:
The Posterior probability distribution of ω is found out by maximum posteriori probability:
Wherein, p (x | t) is edge similar density, unrelated with weight ω, then another representation of formula (3):
p(ω|t,x)∝p(x|t,ω)p(ω) (4)
Wherein, ∝ expression is proportional to.Formula (1) and formula (2) is brought into formula (4), obtains the posterior probability point of weight vector ω
Cloth form:
Wherein,It enablesThe posterior probability of weight vector ω meets Gauss point
Cloth:
When there is data t*When input, corresponding predicted value x*Probability distribution are as follows:
It can be seen that predicted value x*Distribution or Gaussian Profile, manner is the Posterior probability distribution of weight vector ω
Mean value and data t*Product, variance is data t*With the quadratic form of the variance of the Posterior probability distribution of weight vector ω.
It is finally independently detected a flaw, the track that tool arm is generated according to step S2 drives failure detector to continuous welded rail track connector
It detects a flaw, while impedance is utilized that is, while controlling mechanical arm tail end position using location-based impedance control strategy
The control of power is converted correction position control by model, guarantees the constant-force contact of failure detector and joint surface in detection process.
Although having shown and having described the embodiment of the present invention above, it is to be understood that above-described embodiment is example
Property, it is not considered as limiting the invention, those skilled in the art is in the feelings for not departing from the principle of the present invention and objective
It can make changes, modifications, alterations, and variations to the above described embodiments, should belong to of the invention within the scope of the invention under condition
Protection scope.
Claims (2)
1. a kind of track profiling method of detection based on mechanical arm, which comprises the following steps:
Step S1, artificial teaching cooperate with the profiling flaw detection operation completed to continuous welded rail track connector, people's dragging by people with mechanical arm
Mechanical arm completes flaw detection operation, the terminal position and speed data of itself when mechanical arm is fulfiled assignment with certain frequency f record,
Teaching m times;
Step S2, track generate, and repeat the data set that teaching generates for m times and establish mapping model using Gaussian process recurrence, obtain
The Function Mapping relationship set in place to the time, specifically:
By teaching process, n data point is collected on every trackWherein t=[t1,t2,…,tn]TFor the time
Point, x=[x1,x2,…,xn]TFor cartesian coordinate of the flaw detection point under robot coordinate system;The time is obtained according to prior distribution
The likelihood function of point and coordinate:
Linear regression function f (t) based on bayesian theory=tTω, wherein t ∈ Rd, ω=[ω1,ω2,…,ωn]T, f (t)
Representative function value;
Assuming that ω: (0, Σp), the probability distribution of ω is found out by the definition of bayesian theory and Gaussian Profile:
The Posterior probability distribution of ω is found out by maximum posteriori probability:
Wherein, p (x | t) is edge similar density, unrelated with weight ω, then another representation of formula (3):
p(ω|t,x)∝p(x|t,ω)p(ω)(4)
Wherein, ∝ expression is proportional to;Formula (1) and formula (2) is brought into formula (4), obtains the Posterior probability distribution shape of weight vector ω
Formula:
Wherein,It enablesThe posterior probability of weight vector ω meets Gaussian Profile:
When there is data t*When input, corresponding predicted value x*Probability distribution are as follows:
It can be seen that predicted value x*Distribution or Gaussian Profile, manner is the mean value of the Posterior probability distribution of weight vector ω
With data t*Product, variance is data t*With the quadratic form of the variance of the Posterior probability distribution of weight vector ω;
Step S3, autonomous to detect a flaw, the track that mechanical arm is generated according to step S2 drives failure detector to carry out continuous welded rail track connector
Flaw detection, while by using location-based impedance control strategy shown in Fig. 2, guarantee failure detector and connector table in detection process
The constant-force contact in face;Specifically: the contact force for first acquiring failure detector and continuous welded rail track joint surface, by input impedance controller
Output displacement correction amount afterwards obtains the mechanical arm target to be adjusted then in conjunction with mechanical arm tail end failure detector home position
Position, target position are converted into the angle in each joint through mechanical arm inverse kinematics, are input in position control ring, then through machine
Tool arm forward kinematics solution exports the position actually adjusted, and failure detector and rail joint surface can generate new contact force at this time,
To realize closed-loop control.
2. the track profiling method of detection according to claim 1 based on mechanical arm, which is characterized in that in step s3,
It is the deviation by practical contact force and expected force using location-based impedance control strategy, through hindering when executing flaw detection task
Anti- controller obtains position deviation amount, and then adjusts the position of mechanical arm tail end failure detector, realizes failure detector and seamless rail
The constant-force contact of road joint surface.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910670771.4A CN110501421A (en) | 2019-07-24 | 2019-07-24 | A kind of track profiling method of detection based on mechanical arm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910670771.4A CN110501421A (en) | 2019-07-24 | 2019-07-24 | A kind of track profiling method of detection based on mechanical arm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110501421A true CN110501421A (en) | 2019-11-26 |
Family
ID=68586698
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910670771.4A Withdrawn CN110501421A (en) | 2019-07-24 | 2019-07-24 | A kind of track profiling method of detection based on mechanical arm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110501421A (en) |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100274102A1 (en) * | 2009-04-22 | 2010-10-28 | Streamline Automation, Llc | Processing Physiological Sensor Data Using a Physiological Model Combined with a Probabilistic Processor |
US8635172B1 (en) * | 2011-10-07 | 2014-01-21 | Google Inc. | Dynamic techniques for evaluating quality of clustering or classification system aimed to minimize the number of manual reviews based on Bayesian inference and Markov Chain Monte Carlo (MCMC) techniques |
CN105539624A (en) * | 2015-12-30 | 2016-05-04 | 广东出入境检验检疫局检验检疫技术中心 | Metal surface climbing and detecting robot |
CN105765461A (en) * | 2013-10-02 | 2016-07-13 | Asml荷兰有限公司 | Methods and apparatus for obtaining diagnostic information relating to an industrial process |
CN105956601A (en) * | 2016-04-15 | 2016-09-21 | 北京工业大学 | Robot Chinese character writing learning method based on track imitation |
CN106312397A (en) * | 2016-10-12 | 2017-01-11 | 华南理工大学 | Laser vision guided automatic welding track tracking system and method |
CN108115705A (en) * | 2017-12-31 | 2018-06-05 | 芜湖哈特机器人产业技术研究院有限公司 | A kind of robot polishing control system and method |
CN109382828A (en) * | 2018-10-30 | 2019-02-26 | 武汉大学 | A kind of Robot Peg-in-Hole assembly system and method based on learning from instruction |
CN109434843A (en) * | 2018-12-10 | 2019-03-08 | 华中科技大学 | A kind of device and method of the Robot Force console keyboard mill blade based on dragging teaching |
CN109571528A (en) * | 2018-12-29 | 2019-04-05 | 南京工程学院 | Activation lacking mechanical finger and finger tips trajectory predictions method |
CN109848983A (en) * | 2018-12-10 | 2019-06-07 | 华中科技大学 | A kind of method of highly conforming properties people guided robot work compound |
-
2019
- 2019-07-24 CN CN201910670771.4A patent/CN110501421A/en not_active Withdrawn
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100274102A1 (en) * | 2009-04-22 | 2010-10-28 | Streamline Automation, Llc | Processing Physiological Sensor Data Using a Physiological Model Combined with a Probabilistic Processor |
US8635172B1 (en) * | 2011-10-07 | 2014-01-21 | Google Inc. | Dynamic techniques for evaluating quality of clustering or classification system aimed to minimize the number of manual reviews based on Bayesian inference and Markov Chain Monte Carlo (MCMC) techniques |
CN105765461A (en) * | 2013-10-02 | 2016-07-13 | Asml荷兰有限公司 | Methods and apparatus for obtaining diagnostic information relating to an industrial process |
CN105539624A (en) * | 2015-12-30 | 2016-05-04 | 广东出入境检验检疫局检验检疫技术中心 | Metal surface climbing and detecting robot |
CN105956601A (en) * | 2016-04-15 | 2016-09-21 | 北京工业大学 | Robot Chinese character writing learning method based on track imitation |
CN106312397A (en) * | 2016-10-12 | 2017-01-11 | 华南理工大学 | Laser vision guided automatic welding track tracking system and method |
CN108115705A (en) * | 2017-12-31 | 2018-06-05 | 芜湖哈特机器人产业技术研究院有限公司 | A kind of robot polishing control system and method |
CN109382828A (en) * | 2018-10-30 | 2019-02-26 | 武汉大学 | A kind of Robot Peg-in-Hole assembly system and method based on learning from instruction |
CN109434843A (en) * | 2018-12-10 | 2019-03-08 | 华中科技大学 | A kind of device and method of the Robot Force console keyboard mill blade based on dragging teaching |
CN109848983A (en) * | 2018-12-10 | 2019-06-07 | 华中科技大学 | A kind of method of highly conforming properties people guided robot work compound |
CN109571528A (en) * | 2018-12-29 | 2019-04-05 | 南京工程学院 | Activation lacking mechanical finger and finger tips trajectory predictions method |
Non-Patent Citations (3)
Title |
---|
KELIN LI 等: "Learning-based Adaptive Robust Control of Manipulated Pneumatic Artificial Muscle Driven by H2-based Metal Hydride", 《2018 IEEE 14TH INTERNATIONAL CONFERENCE ON AUTOMATION SCIENCE AND ENGINEERING》 * |
KELIN LI 等: "Sparse Bayesian Learning-Based Adaptive Impedance Control in Physical Human-Robot Interaction", 《2018 IEEE 14TH INTERNATIONAL CONFERENCE ON AUTOMATION SCIENCE AND ENGINEERING》 * |
王娟 等: "复杂环境下基于贝叶斯决策的机器人路径规划", 《计算机工程与应用》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103056759B (en) | Robot grinding system based on feedback of sensor | |
CN203838115U (en) | Ultrasonic flaw detection wheel driving robot | |
CN204788276U (en) | Mouth detecting system is pouted to longitudinal welded pipe welding seam based on laser scanning | |
CN106323192A (en) | Longitudinal welded pipe welding seam protrusion detecting system based on laser scanning | |
CN114161048B (en) | 3D vision-based parameterized welding method and device for tower legs of iron tower | |
CN112110220A (en) | Unmanned operation system for material stacking and taking of bucket wheel machine | |
CN105458483A (en) | Automatic correcting and ultrasonic impacting system of post-welding seam tracking robot | |
CN105983802B (en) | A kind of welding robot control system and method | |
CN207326260U (en) | Long-pending large-scale water conservancy equipment is melted based on electric arc and repairs platform online | |
CN110409262A (en) | A kind of automatic tile work equipment in municipal administration road face | |
CN107957234A (en) | A kind of method and device for measuring normal vector of arbitrary point of free-form surface | |
CN110501421A (en) | A kind of track profiling method of detection based on mechanical arm | |
CN103123338A (en) | Non-contact type automatic adjusting mechanism of pipeline nondestructive inspection ultrasonic probe | |
CN204234993U (en) | With weldering ultrasonic impact intelligent robot TT&C system | |
CN103769723B (en) | A kind of nuclear island primary Ioops main pipeline installation method | |
CN107552935A (en) | A kind of fixed steel rail Flash Butt Welding automatic centering and measurement apparatus | |
CN106202843B (en) | A kind of measurement point creation method based on line Measurement Technique | |
CN112539702A (en) | Automatic centering method and system for rail flaw detection vehicle | |
CN108103501A (en) | A kind of laser melting coating and detection device and operating method suitable for Hydropower Plant runner chamber surface | |
CN106353401A (en) | Automatic bend flaw detection system | |
CN207184410U (en) | A kind of photovoltaic clean robot | |
CN204842534U (en) | Wave transformation automatic straightening executor | |
CN111958115B (en) | Rapid hand-eye calibration method for laser weld seam tracking | |
CN206130439U (en) | Return bend automated inspection portal frame structure that detects a flaw | |
CN206288598U (en) | A kind of double positioning High-speed roller machines |
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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20191126 |
|
WW01 | Invention patent application withdrawn after publication |