CN113624225B - Pose resolving method for mounting engine positioning pins - Google Patents
Pose resolving method for mounting engine positioning pins Download PDFInfo
- Publication number
- CN113624225B CN113624225B CN202111078883.4A CN202111078883A CN113624225B CN 113624225 B CN113624225 B CN 113624225B CN 202111078883 A CN202111078883 A CN 202111078883A CN 113624225 B CN113624225 B CN 113624225B
- Authority
- CN
- China
- Prior art keywords
- pin mounting
- mounting hole
- locating pin
- laser ranging
- aircraft engine
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
- G01S17/06—Systems determining position data of a target
- G01S17/08—Systems determining position data of a target for measuring distance only
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Abstract
The invention discloses a pose resolving method for mounting an engine positioning pin, and relates to the field of aircraft security. According to the method, a visual sensor arranged on the outer space of the installation hole of the locating pin on one side of the aircraft engine cabin is reasonably utilized to acquire a target image, the installation hole features recognized in real time by a processor are removed, a non-target circle is removed, and two-dimensional relative pose information of the locating object in image coordinates is calculated; obtaining the engine cabin coordinates through coordinate conversion, and guiding the single-side alignment of the installation of the aircraft engine; and finally, distance information is obtained through a laser ranging sensor arranged on the other side and fed back to the processor, so that deflection angle and depth information of the engine are calculated, and double-side autonomous alignment of installation of the aircraft engine positioning pin is realized. Compared with the prior art, the invention has the advantages of intelligence, the installation accuracy is not influenced by the technology and emotion of operators, the installation efficiency is improved, and the manpower is liberated.
Description
Technical Field
The invention relates to a pose resolving method for mounting an engine locating pin, and belongs to the technical field of robots.
Background
At present, the engine is installed in a visual ranging and manual adjustment mode, so that the accuracy is low and the speed is low. The method for resolving the pose for mounting the engine locating pin is designed by adopting a computer vision image processing technology to identify the geometric shape of the object, calculating the shape, the size and the position coordinates of the object according to the geometric characteristics of the object and the proportion relation of pixels and combining a laser ranging technology, can remarkably improve the accuracy and the efficiency of mounting the engine, is convenient to use and has the intelligent characteristic.
Disclosure of Invention
The purpose of the invention is that: aiming at the problems of difficult observation, inconvenient position adjustment, lower efficiency, complex operation and the like in the engine installation process, the invention provides a pose resolving method for engine locating pin installation by combining visual image recognition and laser ranging technology.
The technical scheme of the invention is as follows:
the pose resolving method for mounting the engine positioning pins is realized by a system which comprises a positioning pin mounting hole A5 and a positioning pin mounting hole B6 respectively fixed on the outer surfaces of an aircraft engine cabin 3 and an aircraft engine 4, a laser ranging sensor 2 and a vision sensor 1 respectively positioned on the outer two sides of the positioning pin mounting hole A5 and the positioning pin mounting hole B6, and a processor connected with the vision sensor 1 and the laser ranging sensor 2; the laser ranging sensor 2 comprises a laser ranging sensor A2-1, a laser ranging sensor B2-2 and a laser ranging sensor C2-3;
the vision sensor 1 acquires image information of a locating pin mounting hole A5 and a locating pin mounting hole B6 on an aircraft engine cabin 3 and an aircraft engine 4;
the laser ranging sensors 2 collect distance information from the positions of the three laser ranging sensors to the bottom of the locating pin mounting hole B6 on the aircraft engine 4;
the processor calculates the relative pose of the aircraft engine compartment 3 and the locating pin mounting holes A5 and B6 on the aircraft engine 4 through an intelligent alignment algorithm, the intelligent alignment algorithm comprises a vision processing algorithm and a laser ranging signal processing algorithm, the vision processing algorithm comprises feature recognition, miscellaneous circle removal and coordinate conversion, plane information of the installation alignment of the locating pin mounting holes B6 on the aircraft engine compartment 3 and the aircraft engine 4 is obtained, the laser ranging processing algorithm comprises angle calculation and depth measurement, and angle information and depth information of the installation alignment of the locating pin mounting holes B6 are obtained.
As shown in FIG. 3, the radius R of the locating pin mounting hole B6 is smaller than the radius R of the locating pin mounting hole A5, and the mounting distance d between the laser ranging sensor A2-1 and the laser ranging sensor B2-2 is smaller than the mounting distance d 1,2 The installation distance d between the laser ranging sensor C2-3 and the centers of the laser ranging sensor A2-1 and the laser ranging sensor B2-2 3 All are required to be greater than
And is less than->
The alignment algorithm of the invention comprises the following steps:
the intelligent alignment algorithm detects all circular positioning object features in an image through feature recognition in a visual processing algorithm, edge detection, line segment fitting, arc detection, circle and ellipse detection according to the image information of the positioning pin mounting hole A5 and the positioning pin mounting hole B6 acquired by the visual sensor 1;
further, edge detection consists of gaussian filtering, image gradient calculation, anchor point extraction and anchor point connection steps. The algorithm converts the input color image to a gray scale image and uses the gaussian kernel of 5*5 for gaussian filtering. And calculating a pixel gradient value according to the Sobel operator, and eliminating weak pixels through a low threshold value to obtain an image of an edge region. When determining whether the pixels in the 'edge area' image are edge pixels, extracting anchor points according to the pixel gradient values and the amplitude values of neighbor gradient values, and finally obtaining a high-quality edge map and a group of edge segments formed by vector forms of pixel chains by a heuristic intelligent routing algorithm connected with the edge direction guiding anchor points.
Further, line segment fitting comprises two steps of extracting line segments and removing pseudo line segments, the least square method is adopted to fit edges, and the line segments are extracted from the generated pixel chains. Pseudowire segments are removed using the Helmholtz principle. The formula is as follows:
wherein N is 4 For the possible presence of N in a set of N x N images 4 The line segment, n is the length of the line segment, k is the probability that at least k points are consistent with the direction of the line segment, and p is the direction of the line segment.
Further, after the edge segments are fitted into line segments through an algorithm, the line segments meeting the conditions are synthesized into arcs by an arc detection method. The arc detection steps are as follows: and calculating the included angle and the direction between two adjacent line segments in sequence, and forming an arc if the directions of at least three line segments are the same and the included angle threshold condition (6-60 degrees) is met.
After the steps, firstly, fitting the longest arc and the arcs meeting the corresponding conditions into a circle; then sequentially performing circle fitting according to the arc length sequence; finally, the remaining arcs are fitted to ellipses. The judgment criterion of arc fitting into a circle is as follows: the radius difference is within 25%, the distance between the centers of circles cannot exceed 25% of the longest arc radius, and the sum of arc angles meeting the two conditions is required to be larger than pi. The ellipse fitting method is the same as the circle fitting, except that the radius difference and center distance limit of the ellipse are both 50%. The fitting of the circle and the ellipse is carried out by adopting a least square circle fitting algorithm.
Step two, after detecting all the circular positioning object features in the image, removing non-target circles according to the upper limit constraint and the lower limit constraint of the radius of the target circles so as to reduce noise interference, judging whether the positioning pin mounting holes B6 on the aircraft engine 4 are positioned in the identifiable region, and if not, continuing to advance the aircraft engine 4 until the positioning pin mounting holes B6 are positioned in the identifiable region; if yes, turning to a step three;
further, the process of removing the target circle radius upper and lower limit constraint hybrid circle comprises the following steps:
according to the actual radius R of the locating pin mounting hole A5, the distance D from the locating pin mounting hole A5 to the vision sensor 1 and the variation distance D of the locating pin mounting hole A5 change Calculating the upper limit R of the radius of the locating pin mounting hole A5 under the coordinate system of the visual sensor by the Focus size Focus and the Pixel point size Pixel of the visual sensor 1 max And a lower limit R min 。
According to the actual radius r of the locating pin installation hole B6, the distance d from the locating pin installation hole B6 to the vision sensor 1 and the change distance d of the locating pin installation hole B6 change Determining the upper limit r of the locating pin mounting hole B6 max Lower limit r min 。
All the circular positioning object features in the image are detected according to feature recognition, and non-target circles are removed through upper and lower limit constraint of the positioning pin mounting holes A5 and the positioning pin mounting holes B6 on the aircraft engine cabin 3 and the aircraft engine 4 so as to reduce noise interference.
When the locating pin mounting hole B6 of the aircraft engine 4 is positioned in the identifiable region, the intelligent alignment algorithm calculates two-dimensional relative coordinates of two circle centers under a visual sensor coordinate system according to the identified locating pin mounting hole A5 and the locating pin mounting hole B6, and obtains relative coordinates of the horizontal direction and the height direction of the circle centers of the locating pin mounting hole A5 and the locating pin mounting hole B6 under the aircraft engine cabin coordinate system through coordinate transformation by combining the geometric dimensions of the locating pin mounting hole A5 and the locating pin mounting hole B6;
further, the coordinate transformation process is as follows:
wherein D is level The two circle centers of the locating pin mounting hole A5 and the locating pin mounting hole B6 are horizontally opposite distances in the engine compartment coordinate system; d (D) vertical The relative distance between the two circle centers of the locating pin mounting hole A5 and the locating pin mounting hole B6 in the height direction of the engine compartment coordinate system; d, d level The relative distance between two circle centers in the horizontal direction under the coordinate system of the vision sensor; d, d vertical The relative distance between the two circle centers in the height direction under the visual sensor coordinate system is set; r is R camera Radius of the positioning pin hole 5 of the aircraft engine compartment in the visual sensor coordinate system; step four, after the center of the positioning pin mounting holes A5 and B6 on the aircraft engine cabin 3 and the aircraft engine 4 are aligned, the alignment algorithm detects whether the 3 laser ranging sensors are all irradiated to the bottom of the positioning pin mounting hole B6 on the aircraft engine 4 according to the difference value of the distance information obtained by the 3 laser ranging sensors, if not, the aircraft engine 4 is adjusted in the horizontal direction and the high-low direction, so that the 3 laser ranging sensors are all irradiated to the bottom of the positioning pin mounting hole B6 on the aircraft engine 4, and if yes, the step five is shifted;
fifthly, when the three laser ranging sensors are all irradiated to the bottom of the locating pin mounting hole B6 on the aircraft engine 4, calculating a horizontal direction deflection angle according to the measured values of the laser ranging sensors A2-1 and B2-2, and calculating a high-low direction deflection angle and depth information by combining the measured values of the laser ranging sensors C2-3;
further, the horizontal deflection angle is:
the deflection angle in the high-low direction is as follows:
the depth adjustment distance of the locating pin mounting hole B6 is as follows:
wherein l 1 For the measurement value l of the laser distance measuring sensor A2-1 2 For the measurement value l of the laser distance measuring sensor B2-2 3 Is a measurement value of the laser ranging sensor C2-3.
And step six, repeating the step one, the step two and the step three after the deflection angle and the depth direction are adjusted, so as to ensure the three-dimensional space alignment of the locating pin mounting holes A5 and the locating pin mounting holes B6 on the aircraft engine compartment 3 and the aircraft engine 4.
The error resolving precision of the intelligent alignment algorithm is 0.5mm.
The beneficial effects of the invention are as follows:
1. the precision is high. Aiming at the problem of inaccurate deflection angle measurement and calculation in the traditional binocular vision method, the invention adopts an intelligent alignment algorithm to calculate the gesture of the aircraft engine positioning pin based on the vision sensor and the laser ranging sensor, and has high precision and stability.
2. And the method is efficient in real time. According to the invention, the measuring frequency of the visual sensor reaches 30Hz, and the measuring frequency of the laser ranging sensor reaches more than 50 Hz.
3. And running across platforms. The alignment program in the invention can run in a plurality of different operating systems such as windows, linux and has stronger universality.
4. The cost is low. The invention has lower price than the three-dimensional dynamic tracking and capturing measuring instrument of similar products.
5. The structure is simple. The installation and the disassembly are convenient.
The invention has the characteristics of small volume and light weight, and is easy to integrate into other systems and exist as a functional unit.
Drawings
Fig. 1 is a schematic view of a locating pin installation pose resolving structure of the present invention.
FIG. 2 is a schematic view of the engine mounting pose resolving scene of the present invention
Fig. 3 is a schematic layout diagram of a laser ranging sensor according to the present invention.
FIG. 4 is a flow chart of the feature recognition workflow of the vision processing algorithm of the present invention.
Fig. 5 is a schematic diagram illustrating a horizontal direction angle calculation plan view of the laser ranging signal processing algorithm according to the present invention.
Fig. 6 is a schematic diagram of a left view of the calculation of the high-low direction angle of the laser ranging signal processing algorithm according to the present invention.
The reference numerals in the drawings: 1-visual sensor, 2-laser ranging sensor, 3-aircraft engine cabin, 4-aircraft engine, 5-locating pin mounting hole A, 6-locating pin mounting hole B, 2-1-laser ranging sensor A, 2-2-laser ranging sensor B, 2-3-laser ranging sensor C.
Detailed Description
The invention is further explained below with reference to the drawings.
Example 1: as shown in fig. 1, a pose resolving method for mounting an engine positioning pin comprises an aircraft engine cabin 3, an aircraft engine 4, a vision sensor 1 and a laser ranging sensor 2 fixed on the outer two sides of a positioning pin mounting hole A5, and a processor connected with the vision sensor 1 and the laser ranging sensor 2.
The vision sensor 1 acquires image information of a locating pin mounting hole A5 and a locating pin mounting hole B6 on an aircraft engine cabin 3 and an aircraft engine 4;
the laser ranging sensor 2 collects distance information from three positions to the bottom of a locating pin mounting hole B6 on the aircraft engine 4;
the processor calculates the relative pose of the positioning pin mounting hole A5 and the positioning pin mounting hole B6 on the aircraft engine 3 and the aircraft engine 4 through an intelligent alignment algorithm, the intelligent alignment algorithm comprises a visual processing algorithm and a laser ranging signal processing algorithm, the visual processing algorithm is composed of feature recognition, miscellaneous circle removal and coordinate conversion, the positioning pin mounting hole A5 and the positioning pin mounting hole B6 are selected as positioning object features, all circular features in a feature recognition detection image are selected, the miscellaneous circle removal discriminates a non-target circle in a complex background, the coordinate conversion maps the circle center information of an alignment object to an aircraft engine cabin coordinate system from a visual sensor coordinate system, the plane information of the alignment of the positioning pin mounting hole A5 and the positioning pin mounting hole B6 on the aircraft engine 4 is obtained, the laser ranging signal processing algorithm is composed of angle calculation and depth calculation, the distance information from three positions to the bottom of the positioning pin mounting hole B6 on the aircraft engine 4 is acquired through the laser ranging sensor 2, and the angle information and the depth information of the alignment object are calculated.
The invention discloses an intelligent alignment method, which comprises the following steps:
step one, the intelligent alignment algorithm is used for detecting all circular object features in an image through feature identification in a visual processing algorithm according to image information of a locating pin mounting hole A5 and a locating pin mounting hole B6 obtained by a visual sensor 1, and detecting all circular locating object features in the image through edge detection, line segment fitting, arc detection and circle and ellipse detection;
the edge detection comprises Gaussian filtering, image gradient calculation, anchor point extraction and anchor point connection. The algorithm converts the input color image to a gray scale image and uses the gaussian kernel of 5*5 for gaussian filtering. And calculating a pixel gradient value according to the Sobel operator, and eliminating weak pixels through a low threshold value, thereby obtaining an 'edge region' image. And when determining whether the pixels in the 'edge area' image are edge pixels, extracting an anchor point according to the amplitude values of the pixel gradient values and the neighbor gradient values, and guiding a heuristic intelligent routing algorithm connected with the anchor point by the edge direction. A high quality edge map and a set of edge segments consisting of vector forms of pixel chains are thus obtained.
The line segment fitting comprises two steps of extracting line segments and removing pseudo line segments, the least square method is adopted to fit edges, and the line segments are extracted from the generated pixel chains. Pseudowire segments are removed using the Helmholtz principle. The formula is as follows:
wherein N is 4 For the possible presence of N in a set of N x N images 4 The line segment, n is the length of the line segment, k is the probability that at least k points are consistent with the direction of the line segment, and p is the direction of the line segment.
After the edge segments are fitted into line segments through an algorithm, the line segments meeting the conditions are synthesized into arcs by an arc detection method. The arc detection step comprises the following steps of sequentially calculating the included angle and the direction between two adjacent line segments, and forming one arc if the directions of at least three line segments are the same and the included angle threshold condition (6-60 degrees) is met.
After the steps, firstly, fitting the longest arc and the arcs meeting the corresponding conditions into a circle; then sequentially performing circle fitting according to the arc length sequence; finally, the remaining arcs are fitted to ellipses. The arc fitting circle judging criterion is that the radius difference is within 25 percent, the circle center distance cannot exceed 25 percent of the longest arc radius, and the sum of arc angles meeting the conditions is more than pi. The ellipse fitting method is similar to circle fitting, except that the radius difference and center distance limit of the ellipse are both 50%. The fitting of the circle and the ellipse is carried out by adopting a least square circle fitting algorithm.
Step two, after the feature recognition detects all the circular positioning object features in the image, removing the mixed circle according to the actual radius R of the positioning pin mounting hole A5, the distance D between the positioning pin mounting hole A5 and the vision sensor 1 and the variation distance D of the positioning pin mounting hole A5 change Calculating the upper limit R of the radius of the locating pin mounting hole A5 under the coordinate system of the visual sensor by the Focus size Focus and the Pixel point size Pixel of the visual sensor 1 max And a lower limit R min 。
According to the actual radius r of the locating pin installation hole B6, the distance d from the locating pin installation hole B6 to the vision sensor 1 and the change distance d of the locating pin installation hole B6 change Determining the upper limit r of the locating pin mounting hole B6 max Lower limit r min 。
All the circular positioning object features in the image are detected according to feature recognition, and non-target circles are removed through upper and lower limit constraint of the positioning pin mounting holes A5 and the positioning pin mounting holes B6 on the aircraft engine cabin 3 and the aircraft engine 4 so as to reduce noise interference.
When the locating pin mounting holes B6 on the aircraft engine 4 are not identified, the aircraft engine 4 is guided to continue to advance until the processor identifies the characteristic contours of the locating pin mounting holes A5 and B6;
step three, when the locating pin mounting hole B6 is positioned in the identifiable region, the alignment algorithm calculates the radius R of the locating pin mounting hole A5 under the coordinate system of the visual sensor according to the identified locating pin mounting hole A5 and the locating pin mounting hole B6 camera And obtain the relative distance d between two centers of circles in the horizontal direction under the coordinate system of the vision sensor level Distance d relative to the height direction vertical The relative distance D between two circle centers in the horizontal direction under the engine compartment coordinate system is obtained through coordinate transformation by combining the radiuses of the locating pin mounting holes A5 and B6 level Opposite to the height directionDistance D vertical Guiding the aircraft engine 4 to align the circle centers of the positioning pin mounting holes A5 and the positioning pin mounting holes B6;
step four, after the center of the positioning pin mounting hole A5 and the center of the positioning pin mounting hole B6 on the engine cabin and the engine of the aircraft are aligned, detecting whether the 3 laser ranging sensors 2 irradiate the bottom of the positioning pin mounting hole B6 on the engine or not according to the difference value of distance information obtained by the 3 laser ranging sensors 2 by the alignment algorithm, if not, adjusting the engine in the horizontal direction and the height direction so that the 3 laser ranging sensors 2 irradiate the bottom of the positioning pin mounting hole B6, and if yes, turning to step five;
step five, as shown in FIG. 3, when all of the 3 laser ranging sensors 2 irradiate the bottom of the locating pin mounting hole B6, according to the measured value l of the laser ranging sensor A2-1 1 Measured value l of laser distance measuring sensor B2-2 2 And the installation distance d of the two 1,2 The horizontal deflection angle α is calculated.
When the deflection angle alpha in the horizontal direction meets the precision error, the measured value l of the laser ranging sensor C2-3 is combined 3 And a mounting distance d 3 The deflection angle beta in the height direction is calculated.
When the direction of height is deflected by an angle betaAfter the accuracy error is satisfied, calculating an ideal depth distance D when the aircraft engine 4 is centered in the aircraft engine compartment 3 according to the model parameters of the aircraft engine compartment 3 and the aircraft engine 4 DEPTH The depth of the positioning pin mounting hole B6 is adjusted by a distance D depth 。
And step six, repeating the step one, the step two and the step three after the deflection angle and the depth direction are adjusted, so as to ensure the three-dimensional space alignment of the locating pin mounting holes A5 and the locating pin mounting holes B6 on the engine compartment 3 and the engine 4 of the aircraft.
The foregoing is merely a preferred embodiment of the present invention and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present invention, which are intended to be comprehended within the scope of the present invention.
Claims (8)
1. The pose resolving method for mounting the engine positioning pins is characterized by comprising a positioning pin mounting hole A (5) and a positioning pin mounting hole B (6) which are respectively fixed on the outer surfaces of an aircraft engine cabin (3) and an aircraft engine (4), a laser ranging sensor (2) and a vision sensor (1) which are respectively positioned on the outer two side spaces of the positioning pin mounting hole A (5) and the positioning pin mounting hole B (6), and a processor connected with the vision sensor (1) and the laser ranging sensor (2); the laser ranging sensor (2) comprises a laser ranging sensor A (2-1), a laser ranging sensor B (2-2) and a laser ranging sensor C (2-3);
the visual sensor (1) acquires image information of a positioning pin mounting hole A (5) and a positioning pin mounting hole B (6) on an aircraft engine cabin (3) and an aircraft engine (4);
the laser ranging sensors (2) collect distance information from the positions of the three laser ranging sensors to the bottom of the locating pin mounting hole B (6) on the aircraft engine (4);
the processor calculates the relative pose of a positioning pin mounting hole A (5) and a positioning pin mounting hole B (6) on an aircraft engine (4) through an intelligent alignment algorithm, the intelligent alignment algorithm comprises a vision processing algorithm and a laser ranging signal processing algorithm, the vision processing algorithm comprises feature recognition, miscellaneous circle removal and coordinate conversion, plane information of the positioning pin mounting hole B (6) on the aircraft engine (4) and the aircraft engine (3) in mounting alignment is obtained, the laser ranging processing algorithm comprises angle calculation and depth measurement and calculation, and angle information and depth information of the positioning pin mounting hole B (6) in mounting alignment are obtained;
the radius R of the locating pin mounting hole B (6) is smaller than the radius R of the locating pin mounting hole A (5), and the mounting distance d between the laser ranging sensor A (2-1) and the laser ranging sensor B (2-2) is smaller than the mounting distance d 1，2 The installation distance d between the laser ranging sensor C (2-3) and the centers of the laser ranging sensor A (2-1) and the laser ranging sensor B (2-2) 3 All are required to be greater than
And is less than->
The specific method comprises the following steps:
the method comprises the steps that firstly, an intelligent alignment algorithm detects all round positioning object features in an image through feature recognition in a visual processing algorithm, edge detection, line segment fitting, arc detection, circle and ellipse detection according to image information of a positioning pin mounting hole A (5) and a positioning pin mounting hole B (6) acquired by a visual sensor (1);
step two, after detecting all the circular positioning object features in the image, removing non-target circles according to the upper limit constraint and the lower limit constraint of the radius of the target circles so as to reduce noise interference, judging whether the positioning pin mounting holes B (6) on the aircraft engine (4) are positioned in the identifiable region, if not, continuing to move the aircraft engine (4) until the positioning pin mounting holes B (6) are positioned in the identifiable region; if yes, turning to a step three;
when the locating pin mounting hole B (6) of the aircraft engine (4) is positioned in the identifiable area, the intelligent alignment algorithm calculates two-dimensional relative coordinates of two circle centers under a visual sensor coordinate system according to the identified locating pin mounting hole A (5) and the identified locating pin mounting hole B (6), and obtains the horizontal and high-low relative coordinates of the circle centers of the locating pin mounting hole A (5) and the locating pin mounting hole B (6) under the aircraft engine cabin coordinate system through coordinate transformation by combining the geometric dimensions of the locating pin mounting hole A (5) and the locating pin mounting hole B (6);
step four, after aligning the centers of the positioning pin mounting holes A (5) and the positioning pin mounting holes B (6) on the aircraft engine room (3) and the aircraft engine (4), detecting whether the 3 laser ranging sensors irradiate the bottoms of the positioning pin mounting holes B (6) on the aircraft engine (4) according to the difference value of the distance information obtained by the 3 laser ranging sensors, if not, adjusting the aircraft engine (4) in the horizontal direction and the height direction so that the 3 laser ranging sensors irradiate the bottoms of the positioning pin mounting holes B (6) on the aircraft engine (4), and if yes, turning to step five;
fifthly, when the three laser ranging sensors are all irradiated to the bottom of a locating pin mounting hole B (6) on an aircraft engine (4), calculating a horizontal direction deflection angle according to the measured values of a laser ranging sensor A (2-1) and a laser ranging sensor B (2-2), and calculating a high-low direction deflection angle and depth information by combining the measured values of a laser ranging sensor C (2-3);
and step six, repeating the step one, the step two and the step three after the deflection angle and the depth direction are adjusted, so as to ensure the three-dimensional space alignment of the locating pin mounting holes A (5) and the locating pin mounting holes B (6) on the aircraft engine cabin (3) and the aircraft engine (4).
2. The pose solving method for engine positioning pin installation according to claim 1, wherein in the first step, edge detection comprises gaussian filtering, image gradient calculation, anchor point extraction and anchor point connection steps; the algorithm converts the input color image into a gray image and uses the Gaussian kernel of 5*5 to carry out Gaussian filtering; calculating a pixel gradient value according to a Sobel operator, and eliminating weak pixels through a low threshold value to obtain an image of an edge region; when determining whether the pixels in the 'edge area' image are edge pixels, extracting anchor points according to the pixel gradient values and the amplitude values of neighbor gradient values, and finally obtaining a high-quality edge map and a group of edge segments formed by vector forms of pixel chains by a heuristic intelligent routing algorithm connected with the edge direction guiding anchor points.
3. The pose solving method for mounting engine positioning pins according to claim 1, wherein in the first step, line segment fitting comprises two steps of extracting line segments and removing pseudo line segments, a least square method is adopted to fit edges, and line segments are extracted from a generated pixel chain; removing pseudo line segments by using a Helmholtz principle; the formula is as follows:
wherein N is 4 For the possible presence of N in a set of N x N images 4 The line segment, n is the length of the line segment, k is the probability that at least k points are consistent with the direction of the line segment, and p is the direction of the line segment.
4. The pose resolving method for installing engine positioning pins according to claim 1, wherein in the first step, after the edge segments are fitted into line segments by algorithm, the line segments meeting the conditions are combined into arcs by an arc detection method; the arc detection steps are as follows: sequentially calculating the included angle and the direction between two adjacent line segments, and forming an arc if the directions of at least three line segments are the same and the included angle threshold condition (6-60 degrees) is met; firstly, fitting the longest arc and the arcs meeting the corresponding conditions into a circle; then sequentially performing circle fitting according to the arc length sequence; finally, fitting the rest arcs into ellipses; the judgment criterion of arc fitting into a circle is as follows: the distance between the circle centers within 25% of the radius difference cannot exceed 25% of the longest arc radius, and the sum of arc angles meeting the two conditions is required to be larger than pi; the ellipse fitting method is the same as the circle fitting, and the difference is that the radius difference and the circle center distance limit of the ellipse are 50%; the fitting of the circle and the ellipse is carried out by adopting a least square circle fitting algorithm.
5. The pose solving method for mounting engine positioning pins according to claim 1, wherein in the second step, the process of removing the constraint mixed circle of the upper limit and the lower limit of the radius of the target circle is as follows:
according to the actual radius R of the locating pin mounting hole A (5), the distance D from the locating pin mounting hole A (5) to the vision sensor (1) and the variation distance D of the locating pin mounting hole A (5) change Calculating the upper limit R of the radius of the locating pin mounting hole A (5) under the coordinate system of the visual sensor by the Focus size Focus and the Pixel point size Pixel of the visual sensor (1) max And a lower limit R min ；
According to the actual radius r of the locating pin mounting hole B (6), the distance d from the locating pin mounting hole B (6) to the vision sensor (1) and the fluctuation distance d of the locating pin mounting hole B (6) change Determining the upper limit r of the locating pin mounting hole B (6) max Lower limit r min ；
All circular positioning object features in the image are detected according to feature recognition, and non-target circles are removed through upper and lower limit constraint of positioning pin mounting holes A (5) and positioning pin mounting holes B (6) on an aircraft engine cabin (3) and an aircraft engine (4) so as to reduce noise interference.
6. The pose solving method for mounting engine positioning pins according to claim 1, wherein in the third step, the coordinate transformation process is as follows:
wherein D is level The two circle centers of the locating pin mounting hole A (5) and the locating pin mounting hole B (6) are horizontally opposite distances under the engine compartment coordinate system; d (D) vertical The distance between the two circle centers of the locating pin mounting hole A (5) and the locating pin mounting hole B (6) in the height direction under the engine compartment coordinate system is the relative distance; d, d level The relative distance between two circle centers in the horizontal direction under the coordinate system of the vision sensor; d, d vertical The relative distance between the two circle centers in the height direction under the visual sensor coordinate system is set; r is R camera The radius of the locating pin mounting hole A (5) of the aircraft engine compartment is in the coordinate system of the visual sensor.
7. The method for resolving a position and orientation of an engine positioning pin according to claim 1, wherein in the fifth step, the horizontal direction deflection angle is:
the deflection angle in the high-low direction is as follows:
the depth adjustment distance of the locating pin mounting hole B (6) is as follows:
wherein l 1 For the measurement value l of the laser distance measuring sensor A (2-1) 2 For the measurement value l of the laser distance measuring sensor B (2-2) 3 Is a measurement value of the laser ranging sensor C (2-3).
8. The pose solving method for engine positioning pin installation according to any of claims 1-7, wherein the intelligent alignment algorithm error solving precision is 0.5mm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111078883.4A CN113624225B (en) | 2021-09-15 | 2021-09-15 | Pose resolving method for mounting engine positioning pins |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111078883.4A CN113624225B (en) | 2021-09-15 | 2021-09-15 | Pose resolving method for mounting engine positioning pins |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113624225A CN113624225A (en) | 2021-11-09 |
| CN113624225B true CN113624225B (en) | 2023-07-04 |
Family
ID=78389973
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111078883.4A Active CN113624225B (en) | 2021-09-15 | 2021-09-15 | Pose resolving method for mounting engine positioning pins |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113624225B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114963894A (en) * | 2022-05-31 | 2022-08-30 | 大连四达高技术发展有限公司 | Full-elastic assembly intelligent sensing system |
| CN115156949B (en) * | 2022-07-22 | 2023-07-11 | 浙江威罗德汽配股份有限公司 | Positioning tool clamp for stamping part |
| CN115451882B (en) * | 2022-11-10 | 2023-03-24 | 通用技术集团沈阳机床有限责任公司 | Method for calculating normal vector of axis of skin bottom hole based on space pose of floating pin |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2186211A1 (en) * | 1996-09-23 | 1998-03-24 | Charles Hersom | Satellite attitude sensor using thermal imaging |
| CN110332887A (en) * | 2019-06-27 | 2019-10-15 | 中国地质大学（武汉） | A kind of monocular vision pose measurement system and method based on characteristic light punctuate |
| CN110793512A (en) * | 2019-09-11 | 2020-02-14 | 上海宾通智能科技有限公司 | Pose recognition method and device, electronic equipment and storage medium |
| CN112122917A (en) * | 2020-07-23 | 2020-12-25 | 南京优登科技有限公司 | Accurate matching method for engine assembly |
-
2021
- 2021-09-15 CN CN202111078883.4A patent/CN113624225B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2186211A1 (en) * | 1996-09-23 | 1998-03-24 | Charles Hersom | Satellite attitude sensor using thermal imaging |
| CN110332887A (en) * | 2019-06-27 | 2019-10-15 | 中国地质大学（武汉） | A kind of monocular vision pose measurement system and method based on characteristic light punctuate |
| CN110793512A (en) * | 2019-09-11 | 2020-02-14 | 上海宾通智能科技有限公司 | Pose recognition method and device, electronic equipment and storage medium |
| CN112122917A (en) * | 2020-07-23 | 2020-12-25 | 南京优登科技有限公司 | Accurate matching method for engine assembly |
Non-Patent Citations (1)
| Title |
|---|
| 发动机缸体试制加工策略(下);吴国君;周立民;黄洪浪;穆腾飞;;汽车工艺师(第04期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113624225A (en) | 2021-11-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113624225B (en) | Pose resolving method for mounting engine positioning pins | |
| US20210264176A1 (en) | Hazard detection from a camera in a scene with moving shadows | |
| CN107798330B (en) | Weld image feature information extraction method | |
| CN101839692B (en) | Method for measuring three-dimensional position and stance of object with single camera | |
| CN104916163B (en) | Parking space detection method | |
| CN112418103B (en) | Bridge crane hoisting safety anti-collision system and method based on dynamic binocular vision | |
| US8340400B2 (en) | Systems and methods for extracting planar features, matching the planar features, and estimating motion from the planar features | |
| CN101887586B (en) | Self-adaptive angular-point detection method based on image contour sharpness | |
| CN103714541B (en) | Method for identifying and positioning building through mountain body contour area constraint | |
| CN101609504B (en) | Method for detecting, distinguishing and locating infrared imagery sea-surface target | |
| CN103697855B (en) | A kind of hull horizontal attitude measuring method detected based on sea horizon | |
| CN108007388A (en) | A kind of turntable angle high precision online measuring method based on machine vision | |
| CN111598952B (en) | Multi-scale cooperative target design and online detection identification method and system | |
| CN110334678A (en) | A kind of pedestrian detection method of view-based access control model fusion | |
| CN105956619B (en) | A kind of container lockhole coarse positioning and tracking | |
| CN105865344A (en) | Workpiece dimension measuring method and device based on machine vision | |
| CN110675341B (en) | Monocular-vision-guided underwater robot and seabed platform butt joint method | |
| KR20080024776A (en) | Method and apparatus for recognizing parking slot marking by using hough transformation and parking assist system using same | |
| EP3239926A1 (en) | Position measuring equipment | |
| CN110147748A (en) | A kind of mobile robot obstacle recognition method based on road-edge detection | |
| CN105283750B (en) | Method for handling the digital picture of surface of tyre to detect abnormal | |
| CN109002800A (en) | The real-time identification mechanism of objective and recognition methods based on Multi-sensor Fusion | |
| JP5501084B2 (en) | Planar area detection apparatus and stereo camera system | |
| CN107767366B (en) | A kind of transmission line of electricity approximating method and device | |
| CN107506739A (en) | To vehicle detection and distance-finding method before a kind of night |
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 |