CN113686892A - Novel bearing surface defect intelligent detection system - Google Patents
Novel bearing surface defect intelligent detection system Download PDFInfo
- Publication number
- CN113686892A CN113686892A CN202110960356.XA CN202110960356A CN113686892A CN 113686892 A CN113686892 A CN 113686892A CN 202110960356 A CN202110960356 A CN 202110960356A CN 113686892 A CN113686892 A CN 113686892A
- Authority
- CN
- China
- Prior art keywords
- bearing
- motor
- stepping motor
- supporting plate
- light source
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8806—Specially adapted optical and illumination features
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
Abstract
The invention belongs to the technical field of bearing surface defect detection, and particularly discloses a novel bearing surface defect intelligent detection system, which comprises a bottom plate and a lower box body; a power supply module, an industrial personal computer, a PLC, a camera power supply controller, a light source power supply controller, a first stepping motor controller and a second stepping motor controller are fixed on the bottom plate; the lower box body is connected with a vertical base, a vertical rod connected with a bar-shaped light source and a line scanning vision sensor, a first motor supporting plate connected with a first stepping motor, a second motor supporting plate connected with a second stepping motor and a motor bearing seat supporting plate; the base is provided with a bearing guide groove, a bearing sliding groove, a first sliding bearing connected with a cam shaft and a second sliding bearing connected with a friction wheel shaft, and prism supports used for fixing the prism are arranged on two sides of the base. The invention integrates the optical imaging technology with the machine vision, realizes the information acquisition and the defect detection of the whole surface of the bearing through one station, and solves the problem of low bearing detection efficiency.
Description
Technical Field
The invention belongs to the technical field of bearing surface defect detection, and particularly discloses a novel intelligent bearing surface defect detection system.
Background
In rotating mechanical equipment, the quality of the bearings plays a crucial role in the stability of the operation of the mechanical equipment. Particularly in automotive wheel axles, both to carry loads from both the axial and radial directions and to provide precise guidance for rotation. If the bearing has a problem, the performance of the automobile is influenced if the bearing is in a light state, and serious accidents are caused if the bearing is in a heavy state. Bearing manufacturers should ensure that bearings with quality problems are detected before leaving factories as much as possible, and if the bearings are found after accidents happen in the using process of users, huge economic and reputation losses are brought. Therefore, the quality detection of the bearing becomes an important link for strict control in the bearing processing process of each bearing production enterprise.
At present, domestic bearing production enterprises mostly adopt an artificial mode for detecting the defects on the surface of a bearing. Usually, a worker looks for defects by visually observing the surface of the bearing on a stage irradiated with intense light. The efficiency and accuracy of the detection method are influenced by individual factors of workers, strict and uniform detection standards are difficult to guarantee, and the conditions of missed detection and false detection are easy to occur. Meanwhile, under the working environment of strong light, the eye injury is great, and the health of workers is seriously affected.
Disclosure of Invention
The invention aims to provide a novel bearing surface defect intelligent detection system to solve the problem of low bearing detection efficiency.
In order to achieve the purpose, the technical scheme of the invention is as follows: the novel bearing surface defect intelligent detection system comprises a bottom plate and a lower box body, wherein the lower box body is fixed above the bottom plate; a power module, an industrial personal computer, a PLC, a camera power controller, a light source power controller, a first stepping motor controller and a second stepping motor controller are fixed on one side of the bottom plate, which is close to the lower box body;
a power switch is arranged on one side of the outer part of the lower box body, which is vertical to the bottom plate; one end of the outer part of the lower box body, which is far away from the bottom plate, is provided with a vertical upright rod, one end of the upright rod, which is far away from the lower box body, is vertically connected with a camera support frame through a camera support frame adapter block, the camera support frame is connected with linear array camera support plates, and a linear scanning visual sensor is connected between the linear array camera support plates; the middle part of the upright rod is connected with a strip-shaped light source fixing frame parallel to the camera supporting frame through a light source support switching block, and a strip-shaped light source is fixed on the strip-shaped light source fixing frame;
a vertical hollow base is further arranged at one end, far away from the bottom plate, of the outer portion of the lower box body, a bearing guide groove is formed in the top end of the base, a bearing sliding groove is formed in the middle of the base, located below the bearing guide groove, of the base, a first sliding bearing and a second sliding bearing are arranged on the base, the first sliding bearing is connected with a cam shaft in a sliding mode, the second sliding bearing is connected with a friction wheel shaft in a sliding mode, synchronous belt wheels are fixed on the cam shaft and the friction wheel shaft, a synchronous belt is connected on the synchronous belt wheels in a sliding mode, and the normal line of the center line of the cam shaft and the center line of the friction wheel shaft is overlapped with the center line of the line scanning vision sensor; prism supports for fixing the prisms are arranged on two sides of the base, and rectangular planes corresponding to the right-angle sides of the prisms are parallel to the plane of the bearing side; a first proximity switch and a second proximity switch are also arranged in the base;
one end of the outer part of the lower box body, which is far away from the bottom plate, is provided with a first vertical motor supporting plate, a second vertical motor supporting plate and a motor bearing seat supporting plate, the first motor supporting plate and the second motor supporting plate are positioned on one side, which is close to the upright rod, of the base, the motor bearing seat supporting plate is positioned on one side, which is far away from the upright rod, of the base, and the first motor supporting plate and the motor bearing seat supporting plate are positioned on the same straight line; a first stepping motor is fixed at one side, close to the upright post, of the top end of the first motor supporting plate, a second motor bearing seat is arranged at one side, far away from the upright post, of the top end of the first motor supporting plate, and a motor coupler is arranged between the first stepping motor and the second motor bearing seat; the top end of the motor bearing seat supporting plate is provided with a first motor bearing seat, and a shifting wheel matched with the bearing guide groove is connected between the first motor bearing seat and the second motor bearing seat in a sliding manner.
The working principle of the technical scheme is as follows:
the utility model provides a novel bearing surface defect intelligent detection system, gathers bearing image through bearing image acquisition device's line scanning vision sensor, utilizes specific algorithm to handle and realizes bearing surface defect detection. In the bearing image acquisition device, the center line of the line scanning vision sensor is superposed with the normal of the center lines of the cam shaft and the friction wheel shaft, and the target surface line of the line scanning vision sensor is parallel to the center line of the bearing, so that the line scanning vision sensor is ensured to acquire a complete bearing surface image in rows; the rectangular plane that the prism right-angle side corresponds is parallel with bearing side plane, and when the bearing rotated, the image of every side upper half can reflect the upper surface to the prism through the rectangular plane that the prism hypotenuse corresponds, and with the cylinder top on the coplanar, line scanning vision sensor was in a station department, once gathered the whole surface visual information of bearing.
The beneficial effects of this technical scheme lie in:
(1) the utility model provides a novel bearing surface defect intelligent detection system, fuses optical imaging technique and machine vision mutually, and the rectangle plane that corresponds through prism right-angle side parallels with the bearing side plane, and when the bearing was rotatory, the image of every side first half can reflect near prism's upper surface through the rectangular surface that the prism hypotenuse corresponds, and a station is realized bearing whole surface information acquisition and defect detection, improves the detection efficiency of bearing greatly, improves workman's operational environment.
(2) The defect detection is realized by the acquisition of a line scanning vision sensor and the processing of a specific algorithm, the center line of the line scanning vision sensor is superposed with the normal line of the center lines of the cam shaft and the friction wheel shaft, the target line of the line scanning vision sensor is parallel to the center line of the bearing, the line scanning vision sensor is ensured to acquire a complete bearing surface image according to lines, the signal to noise ratio of the image is improved, in the acquired image, the cylindrical surface area of the bearing and the side surface areas of the two bearings are rectangular, which is equivalent to the expansion of the bearing around the radius of the bearing, and the extraction of the bearing surface area in the algorithm is facilitated.
Further, an imaging method of visual information of the outer surface of the bearing is used, and the imaging method is realized through a prism with a rectangular plane corresponding to a right-angle side and a plane parallel to the side plane of the bearing; the prism is an equilateral right-angle triangular prism made of quartz glass, and the surface of the triangular surface is frosted; two rectangular surfaces corresponding to the right-angle sides of the triangle are transparent surfaces, the rectangular surface corresponding to the hypotenuse of the triangle is a mirror surface, and the half parts of images on the two side surfaces of the bearing are respectively reflected to the same plane with the uppermost end of the cylindrical surface through the mirror surfaces of the two prisms. The prisms on the both sides of bearing can reflect the image information of bearing side to with two planes parallel on the cylinder, and line scanning vision sensor can gather the information of three faces simultaneously, and this structure has guaranteed that line scanning vision sensor is in a station department, once gathers the whole surface visual information of bearing and has solved traditional problem that needs three stations just can realize bearing surface defect and detect.
Furthermore, the upper end of the lower box body is also connected with an upper box body, and a display is arranged on one side, close to the power switch, of the outer part of the upper box body.
Furthermore, the power module is connected with a power switch, a display, a camera power controller, a line scanning vision sensor, an industrial personal computer, a light source power controller, a first stepping motor and a second stepping motor; the industrial personal computer is connected with the power module, the line scanning vision sensor, the PLC and the display; the PLC is connected with the power module, the industrial personal computer, the line scanning vision sensor, the bar-shaped light source, the first stepping motor controller, the first proximity switch and the second proximity switch; the camera power supply controller is connected with the power supply module and the line scanning visual sensor; the light source power supply controller is connected with the power supply module and the strip-shaped light source; the first stepping motor controller is connected with the power module, the PLC and the first stepping motor; the second stepping motor controller is connected with the power module, the PLC and the second stepping motor; the power switch is connected with the power module; the display is connected with the power module and the industrial personal computer.
Furthermore, the bearing guide groove is in a U-shaped long strip shape, and the width of the concave area of the bearing guide groove is equal to that of the bearing; the thumb wheel is ratchet-shaped, and has 6 notches, and each notch only allows one bearing to pass through. The bearing can only roll in along the strip direction, so that the precision of image acquisition is ensured, and the stability of system operation is improved.
Further, the intelligent detection of the bearing surface defects is realized by an algorithm, and the method comprises the following steps:
(1) collecting a large number of bearing images without defects by using a bearing image collecting device, building a bearing surface defect model based on a reconstructed network in an industrial personal computer, and carrying out network training;
(2) deploying a model with the capability of reconstructing a defect-free bearing image into an industrial personal computer;
(3) and an algorithm module in the industrial personal computer receives the bearing image, inputs different first and second algorithms respectively, and if any one of the first and second algorithms judges that the image has defects, the bearing is considered as a defective bearing.
Drawings
FIG. 1 is a schematic structural diagram of an embodiment of the novel intelligent detection system for bearing surface defects of the present invention;
FIG. 2 is a schematic structural diagram of an embodiment of the present invention;
FIG. 3 is an external structural view of an embodiment of the present invention;
FIG. 4 is a diagram of the hardware structure of an embodiment;
FIG. 5 is a principal schematic diagram of embodiment defect detection;
FIG. 6 is a schematic view of an embodiment thumb wheel and bearing guide channel configuration;
FIG. 7 is a schematic view of an embodiment prism installation;
FIG. 8 is a schematic view of an embodiment prism;
FIG. 9 is a schematic of an embodiment acquisition;
FIG. 10 is an image of information collected by the embodiment;
FIG. 11 is a schematic view of the structure of a detection region of an embodiment;
FIG. 12 is a flow chart of an embodiment algorithm;
FIG. 13 is a simplified diagram of an embodiment reconstruction algorithm;
FIG. 14 is a diagram of an embodiment restructured network structure;
FIG. 15 is a flowchart of the second embodiment algorithm.
Detailed Description
The following is further detailed by way of specific embodiments:
reference numerals in the drawings of the specification include: a power supply module 1, an industrial personal computer 2, a PLC3, a camera power supply controller 4, a line scanning vision sensor 5, a light source power supply controller 6, a bar-shaped light source 7, a first stepping motor controller 8, a first stepping motor 9, a second stepping motor controller 10, a second stepping motor 11, a first proximity switch 12, a second proximity switch 13, a display 14, a power switch 15, a dial wheel 16, a motor coupler 17, a linear camera support plate 18, a first motor bearing seat 19, a second motor bearing seat 20, a bearing guide groove 21, a first motor support plate 2, a bearing chute 23, a motor bearing seat support plate 24, a bar-shaped light source support adapter block 25, a friction wheel shaft 26, a cam shaft 27, a first sliding bearing 8, a synchronous pulley 29, a synchronous belt 30, a prism support 31, a base 32, a prism 33, a bar-shaped light source fixing frame 34, a camera support frame 35, an upper box 36, The device comprises a lower box body 37, a bottom plate 38, a second motor supporting plate 39, a second sliding bearing 40, a strip-shaped light source supporting frame 41, a vertical rod 42 and a camera support transfer block 43.
The embodiment is basically as shown in figure 1, and the novel bearing surface defect intelligent detection system, which is combined with figure 2, comprises a bottom plate 38 and a lower box body 37, wherein a power supply module 1, an industrial personal computer 2, a PLC3, a camera power supply controller 4, a light source power supply controller 6, a first stepping motor controller 8 and a second stepping motor controller 10 are fixed at the upper end of the bottom plate 38 through bolts; the lower box body 37 is fixed above the bottom plate 38 through bolts, and the power module 1, the industrial personal computer 2, the PLC3, the camera power controller 4, the light source power controller 6, the first stepping motor controller 8 and the second stepping motor controller 10 are positioned inside the lower box body 37;
as shown in fig. 3, the power switch 15 is connected to the front end of the outer part of the lower case 37 by bolts; the upper end of the lower box body 37 is connected with a vertical upright rod 42 through threads, the upper end of the upright rod 42 is vertically connected with a camera support frame 35 through a camera support frame transfer block 43, the camera support frame 35 is connected with linear array camera support plates 18, and a linear scanning vision sensor 5 is connected between the linear array camera support plates 18 through bolts; the middle part of the upright rod 42 is connected with a strip-shaped light source fixing frame 34 parallel to the camera supporting frame 35 through a light source support switching block, the strip-shaped light source fixing frame 34 is connected with a strip-shaped light source 7 through a bolt, and the length direction of the light emitting surface of the strip-shaped light source 7 is parallel to the central line of the bearing; a vertical hollow base 32 is arranged at the upper end of the lower box body 37, a bearing guide groove 21 is arranged at the top end of the base 32, a bearing sliding groove 23 is arranged below the bearing guide groove 21 in the middle of the base 32, and the bearing guide groove 21 and the bearing sliding groove 23 are fixed on two walls of the base 32 through bolts; the base 32 is provided with a first sliding bearing 28 and a second sliding bearing 40, the first sliding bearing 28 is connected with a cam shaft 27 in a sliding manner, the first sliding bearing 28 is connected with a friction wheel shaft 26 in a sliding manner, a synchronous pulley 29 is fixed on the cam shaft 27 and the friction wheel shaft 26, and a synchronous belt 30 is connected on the synchronous pulley 29 in a sliding manner; prism supports 31 for fixing the prisms 33 are respectively fixed on the front side and the rear side of the base 32 through bolts; the prism 33 is placed in the prism holder 31, the prism 33 is fixed by bolts at both sides, and the prism holder 31 is fixed at both sides of the base 32. The rectangular plane corresponding to the right-angle side of the prism 33 is parallel to the plane of the bearing side; a first proximity switch 12 and a second proximity switch 13 are fixed inside the base 32 through bolts; the upper end of the lower box body 37 is welded with a first vertical motor supporting plate 22, a second vertical motor supporting plate 39 and a motor bearing seat supporting plate 24, the first motor supporting plate 22 and the second motor supporting plate 39 are positioned at the front end of the base 32, the motor bearing seat supporting plate 24 is positioned at the rear end of the base 32, and the first motor supporting plate 22 and the motor bearing seat supporting plate 24 are positioned on the same straight line; a first stepping motor 9 is fixed at one side, close to the upright post, of the upper end of the first motor support plate 22 through bolts, a second motor bearing seat 20 is arranged at one side, far away from the upright post, of the upper end of the first motor support plate 22 through bolts, and a motor coupler 17 is connected between the first stepping motor 9 and the second motor bearing seat 20 in a sliding mode; the top end of the motor bearing seat support plate 24 is fixed with a first motor bearing seat 19 through a bolt, and a thumb wheel 16 matched with the bearing guide groove 21 is connected between the first motor bearing seat 19 and the second motor bearing seat 20 in a sliding manner.
A novel bearing surface defect intelligent detection system is shown in a hardware connection relation as figure 4, a power switch 15 is connected with a power module 1, a display 14 is connected with the power module 1, a camera power controller 4 is connected with the power module 1, a line scanning vision sensor 5 is connected with the camera power controller 4, an industrial personal computer 2 is connected with the line scanning vision sensor 5, the industrial personal computer 2 is connected with the display 14, the power module 1 is connected with the industrial personal computer 2, a light source power controller 6 is connected with the power module 1, a bar-shaped light source 7 is connected with the light source power controller 6, a PLC3 is connected with the power module 1, the industrial personal computer 2 is connected with a PLC3, a PLC3 is connected with the line scanning vision sensor 5, the PLC3 is connected with the bar-shaped light source 7, the PLC3 is connected with a first stepping motor controller 8, the first stepping motor controller 8 is connected with a first stepping motor 9, the second stepping motor controller 10 is connected with the second stepping motor 11, the power supply is connected with the first stepping motor controller 8, the power module 1 is connected with the second stepping motor controller 10, the first proximity switch 12 is connected with the PLC3, the second proximity switch 13 is connected with the PLC3, the power module 1 is connected with the first stepping motor 9, and the power module 1 is connected with the second stepping motor 11.
The specific implementation process is as follows:
when the power switch 15 is turned on, the PLC3 controls the first stepping motor 9 to rotate 30 degrees, so that the bearing to be detected is driven to enter a detection area between the cam shaft 27 and the friction wheel shaft 26 through the dial wheel 16, and the first proximity switch 12 is triggered at the moment; after receiving the trigger signal of the first proximity switch 12, the PLC3 controls the second stepper motor 11 to rotate for one circle, and simultaneously turns on the bar light source 7, the line scanning vision sensor 5 starts to collect the image of the surface of the bearing, and when the bearing rotates, the image of the upper half of each side surface of the bearing can be reflected to the upper surface of the prism 33 through the rectangular surface (vertical surface) corresponding to the oblique edge of the prism 33; after image acquisition is accomplished, carry out image processing in reaching industrial computer 2 automatically, the bearing passes through the notch whereabouts of cam simultaneously, trigger second proximity switch 13, accomplish and detect, begin the second bearing simultaneously and get into thumb wheel 16, first bearing receives the action of gravity, roll in the notch of thumb wheel 16, and blocked by the right side prong, when thumb wheel 16 anticlockwise rotation, the right side prong lifts up, the bearing receives the thrust of gravity and left side prong, roll into the detection area along bearing guide slot 21 rectangular direction, next bearing gets into the notch of thumb wheel 16 because of the action of gravity simultaneously, the defect detection leading principle is as shown in figure 5.
The intelligent detection of the bearing surface defects is realized through an algorithm, the bearing image acquisition device is firstly utilized to collect a large number of bearing images without defects, and meanwhile, a bearing surface defect model based on a reconstruction network is built in the industrial personal computer 2 for network training, so that the model has the capability of reconstructing the bearing images without defects. And further deploying the trained network model into the industrial personal computer 2 to complete preparation work, inputting image information into different algorithms I and II when an algorithm module in the industrial personal computer 2 receives a bearing image, and if any algorithm in the algorithms I and II judges that the image has a defect, determining that the bearing is a defective bearing.
In the embodiment, the strip-shaped light source 7 can rotate at 0-45 degrees, so that the optimal illumination angle can be conveniently adjusted. The prism 33 of the both sides of bearing can reflect the image information of bearing side to with two planes parallel on the cylinder, and line scanning vision sensor 5 can gather the information of three faces simultaneously, has solved the traditional problem that needs three stations just can realize bearing surface defect and detect.
In the embodiment, as shown in fig. 6, the bearing guide groove 21 and the thumb wheel 16 are in a U-shaped strip shape, and the width of the concave area is equal to the width of the bearing, so that the bearing can only roll in along the strip direction; the top of the end of the bearing guide groove 21 is provided with a thumb wheel 16, the thumb wheel 16 is in a ratchet shape and has 6 notches, and each notch only allows one bearing to pass through. When the detection is started, the first bearing rolls into the notch of the thumb wheel 16 under the action of gravity and is blocked by the right convex tip; when the thumb wheel 16 rotates anticlockwise, the right convex tip is lifted, the bearing rolls into the detection area along the long strip direction of the bearing guide groove 21 under the action of gravity and the thrust of the left convex tip, and meanwhile the next bearing enters the notch of the thumb wheel 16 under the action of gravity. The mechanism is simple and small, moves through the rotation of the bearing, does not need to provide kinetic energy additionally, and saves energy consumption.
In the embodiment, as shown in fig. 7, the prism 33 is an equilateral right-angle triangular prism, which is made of quartz glass, the surface of the triangular surface is frosted, two rectangular surfaces corresponding to right-angle sides of the triangle are transparent surfaces, a rectangular surface corresponding to a hypotenuse of the triangle is a mirror surface, and the prism 33 reflects the side surface of the bearing in the vertical direction to the direction of the cylindrical surface of the bearing; as shown in fig. 8, the prism 33 is placed in the prism holder 31, the prism 33 is fixed by bolts at both sides, and the prism holder 31 is fixed at both sides of the base 32. The rectangular plane corresponding to the right-angled side of the prism 33 remains parallel to the bearing-side plane. When the bearing rotates, the image of the upper half part of each side face of the bearing can be reflected to the upper surface of the prism 33 through the rectangular surface (vertical surface) corresponding to the bevel edge of the prism 33 and is positioned on the same plane with the uppermost end of the cylindrical surface, and the structure can ensure that the line scanning vision sensor 5 collects the vision information of the whole outer surface of the bearing at one time at one station.
In the embodiment, the strip-shaped light source 7 is a high-power blue strip-shaped light source, as shown in fig. 9, the illumination can be more uniform, and the influence caused by uneven illumination can be prevented, the length direction of the light emitting surface of the strip-shaped light source 7 is parallel to the central line of the bearing, the light emitting surface and the bottom plate 38 surface can be adjusted at 0-45 degrees, the strip-shaped light source 7 is connected with the strip-shaped light source support frame 41 through a bolt, the strip-shaped light source 7 can be ensured to rotate along the length direction of the strip-shaped light source 7, the angle between the light emitting surface and the bottom plate 38 surface is adjusted to be optimal, and the optimal illumination collection condition is obtained; the central line of the line scanning vision sensor 5 is superposed with the normal line of the central lines of the cam shaft 27 and the friction wheel shaft 26, and the imaging information (one pixel line) of the line scanning vision sensor 5 is parallel to the central line of the bearing, so that the line scanning vision sensor 5 can acquire complete bearing surface images in rows, and the signal-to-noise ratio of the images is improved. As shown in fig. 10, in the acquired image, the bearing cylindrical surface region and the two bearing side surface regions are both rectangular, which is equivalent to the fact that the bearings are spread around the radius of the bearings, and is beneficial to extracting the bearing surface region in the algorithm.
In the embodiment, the control flow of the line scanning vision sensor 5 for acquiring the bearing surface image in rows is as follows: setting a proper pulse frequency of the second stepping motor 11, initializing the pulse frequency of the line scanning vision sensor 5, and selecting a proper acquisition frequency of the line scanning vision sensor 5 through debugging. Referring to fig. 11, when the bearing passes through the first proximity switch 12, a trigger signal is sent, and after a certain time delay, the control line scanning vision sensor 5 collects the image and the first stepping motor 9 rotates at the same time.
In the embodiment, the flow of the first algorithm is as shown in fig. 12, the bearing in the image is positioned first, and the target area to be detected is selected; the defects are divided into five categories of deep and shallow pits, dust covers, inner rings, outer rings and corrosion because the types of the defects of the bearings are different greatly, the five categories of the defects are detected in parallel, and the defects of each part are detected; firstly, the five methods all adopt a method of blob analysis, difference and characteristics to remove irrelevant interference, wherein the deep and shallow pits adopt a mode of combining threshold segmentation with morphology and gray level co-occurrence matrix to extract pit defects; the dustproof cover part detects defects by adopting a mode of combining sub-pixels and features; detecting defects of the inner ring and the outer ring by using a difference + characteristic and gray level co-occurrence matrix method; after texture interference of the corrosion defect is removed, the corrosion defect is mainly extracted by a method of threshold segmentation + characteristics and gray level co-occurrence matrix.
In an embodiment, as shown in fig. 13 and 14, an algorithm two includes an input layer, an encoding layer, a semantic feature layer, a decoding layer, and an output layer, which are connected in sequence, where an output in the middle of the encoding layer is also connected to the decoding layer in a jumping manner; the encoder comprises 4 convolution modules, each convolution module comprises 1 convolution layer, 1 BN layer and a nonlinear activation layer, and the first three convolution modules also comprise a pooling layer capable of changing the image scale; relu is selected as an activation function in the activation layer; the decoder comprises 4 deconvolution modules, each deconvolution module comprises 1 deconvolution layer, one BN layer and a nonlinear activation layer, the first three deconvolution modules further comprise feature splicing layers, and the through size feature tensors are obtained from the corresponding layers of the encoder to be spliced. Referring to fig. 15, the image is input into the trained network model, the reconstructed bearing image without defect is output, the difference between the reconstructed image and the original image is obtained, the bearing surface defect is located and detected, and the precision of extracting the bearing surface defect is improved through dual-algorithm judgment.
The foregoing is merely an example of the present invention and common general knowledge of known specific structures and features of the embodiments is not described herein in any greater detail. It should be noted that, for those skilled in the art, without departing from the structure of the present invention, several changes and modifications can be made, which should also be regarded as the protection scope of the present invention, and these will not affect the effect of the implementation of the present invention and the practicability of the patent.
Claims (6)
1. The novel bearing surface defect intelligent detection system is characterized by comprising a bottom plate and a lower box body, wherein the lower box body is fixed above the bottom plate; a power module, an industrial personal computer, a PLC, a camera power controller, a light source power controller, a first stepping motor controller and a second stepping motor controller are fixed on one side of the bottom plate, which is close to the lower box body;
a power switch is arranged on one side of the outer part of the lower box body, which is vertical to the bottom plate; one end of the outer part of the lower box body, which is far away from the bottom plate, is provided with a vertical upright rod, one end of the upright rod, which is far away from the lower box body, is vertically connected with a camera support frame through a camera support frame adapter block, the camera support frame is connected with linear array camera support plates, and a linear scanning visual sensor is connected between the linear array camera support plates; the middle part of the upright rod is connected with a strip-shaped light source fixing frame parallel to the camera supporting frame through a light source support switching block, and a strip-shaped light source is fixed on the strip-shaped light source fixing frame;
a vertical hollow base is further arranged at one end, far away from the bottom plate, of the outer portion of the lower box body, a bearing guide groove is formed in the top end of the base, a bearing sliding groove is formed in the middle of the base, located below the bearing guide groove, of the base, a first sliding bearing and a second sliding bearing are arranged on the base, the first sliding bearing is connected with a cam shaft in a sliding mode, the second sliding bearing is connected with a friction wheel shaft in a sliding mode, synchronous belt wheels are fixed on the cam shaft and the friction wheel shaft, a synchronous belt is connected on the synchronous belt wheels in a sliding mode, and the normal line of the center line of the cam shaft and the center line of the friction wheel shaft is overlapped with the center line of the line scanning vision sensor; prism supports for fixing the prisms are arranged on two sides of the base, and rectangular planes corresponding to the right-angle sides of the prisms are parallel to the plane of the bearing side; a first proximity switch and a second proximity switch are also arranged in the base;
one end of the outer part of the lower box body, which is far away from the bottom plate, is provided with a first vertical motor supporting plate, a second vertical motor supporting plate and a motor bearing seat supporting plate, the first motor supporting plate and the second motor supporting plate are positioned on one side, which is close to the upright rod, of the base, the motor bearing seat supporting plate is positioned on one side, which is far away from the upright rod, of the base, and the first motor supporting plate and the motor bearing seat supporting plate are positioned on the same straight line; a first stepping motor is fixed at one side, close to the upright post, of the top end of the first motor supporting plate, a second motor bearing seat is arranged at one side, far away from the upright post, of the top end of the first motor supporting plate, and a motor coupler is arranged between the first stepping motor and the second motor bearing seat; the top end of the motor bearing seat supporting plate is provided with a first motor bearing seat, and a shifting wheel matched with the bearing guide groove is connected between the first motor bearing seat and the second motor bearing seat in a sliding manner.
2. The novel intelligent bearing surface defect detection system as claimed in claim 1, wherein an imaging method of visual information of the outer surface of the bearing is used, and is realized by a prism with right-angled sides corresponding to a rectangular plane and parallel to a bearing side plane; the prism is an equilateral right-angle triangular prism made of quartz glass, and the surface of the triangular surface is frosted; two rectangular surfaces corresponding to the right-angle sides of the triangle are transparent surfaces, the rectangular surface corresponding to the hypotenuse of the triangle is a mirror surface, and the half parts of images on the two side surfaces of the bearing are respectively reflected to the same plane with the uppermost end of the cylindrical surface through the mirror surfaces of the two prisms.
3. The system of claim 1, wherein the upper end of the lower housing is further connected to an upper housing, and a display is disposed outside the upper housing on a side thereof adjacent to the power switch.
4. The system for intelligently detecting the defects of the surface of the novel bearing as claimed in claim 1, wherein the power module is connected with a power switch, a display, a camera power controller, a line scanning vision sensor, an industrial personal computer, a light source power controller, a first stepping motor and a second stepping motor; the industrial personal computer is connected with the power module, the line scanning vision sensor, the PLC and the display; the PLC is connected with the power module, the industrial personal computer, the line scanning vision sensor, the bar-shaped light source, the first stepping motor controller, the first proximity switch and the second proximity switch; the camera power supply controller is connected with the power supply module and the line scanning visual sensor; the light source power supply controller is connected with the power supply module and the strip-shaped light source; the first stepping motor controller is connected with the power module, the PLC and the first stepping motor; the second stepping motor controller is connected with the power module, the PLC and the second stepping motor; the power switch is connected with the power module; the display is connected with the power module and the industrial personal computer.
5. The system for intelligently detecting the defects of the surface of the novel bearing as claimed in claim 1, wherein the bearing guide groove is in a U-shaped long strip shape, and the width of the concave area of the bearing guide groove is equal to the width of the bearing; the thumb wheel is ratchet-shaped, and has 6 notches, and each notch only allows one bearing to pass through.
6. The system of claim 1, wherein the intelligent detection of bearing surface defects is realized by an algorithm, comprising the following steps:
(1) collecting a large number of bearing images without defects by using a bearing image collecting device, building a bearing surface defect model based on a reconstructed network in an industrial personal computer, and carrying out network training;
(2) deploying a model with the capability of reconstructing a defect-free bearing image into an industrial personal computer;
(3) and an algorithm module in the industrial personal computer receives the bearing image, inputs different first and second algorithms respectively, and if any one of the first and second algorithms judges that the image has defects, the bearing is considered as a defective bearing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110960356.XA CN113686892B (en) | 2021-08-20 | 2021-08-20 | Novel bearing surface defect intelligent detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110960356.XA CN113686892B (en) | 2021-08-20 | 2021-08-20 | Novel bearing surface defect intelligent detection system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113686892A true CN113686892A (en) | 2021-11-23 |
| CN113686892B CN113686892B (en) | 2023-08-25 |
Family
ID=78581001
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110960356.XA Active CN113686892B (en) | 2021-08-20 | 2021-08-20 | Novel bearing surface defect intelligent detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113686892B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115753797A (en) * | 2022-11-23 | 2023-03-07 | 哈尔滨工程大学 | Three-dimensional rotating bearing appearance defect image acquisition device |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070279622A1 (en) * | 2004-02-27 | 2007-12-06 | Kazuhide Yamauchi | Multidirectional Simultaneous Observation Optical System, Image Reading Device, Image Reading Method, And Multidirectional Simultaneous Observation Combined Optical System |
| US20110018999A1 (en) * | 2007-12-19 | 2011-01-27 | Societe De Technologie Michelin | Device for Evaluating the Surface of a Tire |
| WO2016098872A1 (en) * | 2014-12-16 | 2016-06-23 | Canon Kabushiki Kaisha | Surface shape measuring apparatus and defect determining apparatus |
| US20170241773A1 (en) * | 2014-12-16 | 2017-08-24 | Canon Kabushiki Kaisha | Surface shape measuring apparatus and defect determining apparatus |
| CN107255911A (en) * | 2012-11-06 | 2017-10-17 | 株式会社尼康 | Exposure device |
| CN108548823A (en) * | 2018-05-15 | 2018-09-18 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of large scale plate side surface of workpiece detection device and method |
| CN109211934A (en) * | 2018-08-29 | 2019-01-15 | 南京理工大学 | Based on interference micro- microballoon planar defect detection device and its detection method |
| US20200182801A1 (en) * | 2016-03-16 | 2020-06-11 | Agency For Science, Technology And Research | Lighting device and inspection apparatus |
| CN111537488A (en) * | 2020-06-08 | 2020-08-14 | 山西中谱能源科技有限公司 | Device and method for eliminating mercury element measurement interference by utilizing Zeeman fluorescence |
| CN111965192A (en) * | 2020-09-18 | 2020-11-20 | 桂林电子科技大学 | Multi-surface imaging visual detection system and detection method |
| CN215678251U (en) * | 2021-05-18 | 2022-01-28 | 广东机电职业技术学院 | Acid-base neutralization automatic titration system based on color identification |
-
2021
- 2021-08-20 CN CN202110960356.XA patent/CN113686892B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070279622A1 (en) * | 2004-02-27 | 2007-12-06 | Kazuhide Yamauchi | Multidirectional Simultaneous Observation Optical System, Image Reading Device, Image Reading Method, And Multidirectional Simultaneous Observation Combined Optical System |
| US20110018999A1 (en) * | 2007-12-19 | 2011-01-27 | Societe De Technologie Michelin | Device for Evaluating the Surface of a Tire |
| CN107255911A (en) * | 2012-11-06 | 2017-10-17 | 株式会社尼康 | Exposure device |
| WO2016098872A1 (en) * | 2014-12-16 | 2016-06-23 | Canon Kabushiki Kaisha | Surface shape measuring apparatus and defect determining apparatus |
| US20170241773A1 (en) * | 2014-12-16 | 2017-08-24 | Canon Kabushiki Kaisha | Surface shape measuring apparatus and defect determining apparatus |
| US20200182801A1 (en) * | 2016-03-16 | 2020-06-11 | Agency For Science, Technology And Research | Lighting device and inspection apparatus |
| CN108548823A (en) * | 2018-05-15 | 2018-09-18 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of large scale plate side surface of workpiece detection device and method |
| CN109211934A (en) * | 2018-08-29 | 2019-01-15 | 南京理工大学 | Based on interference micro- microballoon planar defect detection device and its detection method |
| CN111537488A (en) * | 2020-06-08 | 2020-08-14 | 山西中谱能源科技有限公司 | Device and method for eliminating mercury element measurement interference by utilizing Zeeman fluorescence |
| CN111965192A (en) * | 2020-09-18 | 2020-11-20 | 桂林电子科技大学 | Multi-surface imaging visual detection system and detection method |
| CN215678251U (en) * | 2021-05-18 | 2022-01-28 | 广东机电职业技术学院 | Acid-base neutralization automatic titration system based on color identification |
Non-Patent Citations (2)
| Title |
|---|
| WEI SHAO ET AL: "Smooth Surface Visual Imaging Method for Eliminating High Reflection Disturbance", 《SENSOR》, pages 1 - 11 * |
| 刘凯斌: "高亮回转表面缺陷检测光照方法的研究及系统设计", 《中国硕士电子期刊》, pages 1 - 63 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115753797A (en) * | 2022-11-23 | 2023-03-07 | 哈尔滨工程大学 | Three-dimensional rotating bearing appearance defect image acquisition device |
| CN115753797B (en) * | 2022-11-23 | 2023-08-29 | 哈尔滨工程大学 | Three-dimensional rotating bearing appearance defect image acquisition device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113686892B (en) | 2023-08-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109084957B (en) | Defect detection and color sorting method and system for photovoltaic solar crystalline silicon cell | |
| CN103716620B (en) | Automatic function testing machine for camera modules | |
| WO2015055060A1 (en) | Online detecting method for continuous casting slab surface quality | |
| CN204064972U (en) | optical lens surface defect detecting system | |
| CN203695443U (en) | Screening and measuring device for precise hardware | |
| CN102284428A (en) | Corn real-time detection and grading machine vision system | |
| CN113686892A (en) | Novel bearing surface defect intelligent detection system | |
| CN102890093A (en) | Machine vision detecting device of surface quality of master cylinder piston of automobile brake | |
| CN202114018U (en) | Machine vision system for grain real-time detection and grading | |
| CN103175850A (en) | Detection method and system for material surface detects of wide-range high-speed production line | |
| CN105119571A (en) | Silicon solar cell defect on-line detection device | |
| CN110702699A (en) | Rolled glass defect detection device and method | |
| CN202166618U (en) | Detection device for solar cell piece of satellite solar wing | |
| CN106053485A (en) | Machine vision-based novel algorithm of intelligent circular inspection of steel ball surface defects | |
| CN219552297U (en) | Appearance detection system for coated square battery | |
| CN108489830A (en) | Crack propagation measuring system | |
| CN103091332B (en) | Detection method and detection system of U-shaped powder pipe based on machine vision | |
| CN219104760U (en) | Photovoltaic module outward appearance detecting system based on area array camera | |
| CN218995107U (en) | New energy automobile battery defect visual inspection device | |
| CN103439341B (en) | Photoelectric encoder defect detection system and its implementation | |
| CN109839387A (en) | The method of the surface contamination of express statistic optical elements of large caliber and damage | |
| CN202562857U (en) | End surface defect detection system for transparent capsules | |
| CN211825761U (en) | Rolled glass defect detection device | |
| CN210322833U (en) | Appearance detection device for solar cell | |
| CN114047201A (en) | AI intelligent technology-based multiple fabric flaw detection device and operation method |
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 |