CN202029367U - Embedded plastic mould protecting device based on histogram matching - Google Patents

Abstract

An embedded plastic mould protecting device based on histogram matching is divided into four modules including an image acquisition module, a compute matching module, a man-machine interaction module and an action control module. The image acquisition module comprises two infrared cameras and a filament lamp, the compute matching module comprises an Arm development board, the man-machine interaction module is an upper computer of an injection molding machine controller, and the action control module is a lower computer of the injection molding machine controller. The image acquisition module, the compute matching module and the man-machine interaction module are controllably connected through Ethernet net wires of a network concentrator, and the man-machine interaction module and the action control module are controllably connected by Can/232 wires. The embedded plastic mould protecting device is capable of automatically judging whether products not falling off are left in plastic moulds or not, and thereby effectively protecting the plastic moulds. Further, the embedded plastic mould protecting device has the advantages of high efficiency and reliability, high safety coefficient, and the like.

Description

A kind of embedded plastic mould protective device based on the histogram coupling

Technical field

The utility model relates to a kind of mould of plastics protective device, especially a kind of embedded plastic mould protective device based on the histogram coupling belongs to computer vision field.

Background technology

Plastics are because its good processing and serviceability have obtained using widely in the every field of national economy, and China's plastic products total output has reached 3,000 ten thousand tons and with 8%～10% growth rate cumulative year after year at present.Injection moulding is good because of its Forming Quality, the efficient height, and low cost and other advantages, and become the particularly topmost means of production of high-performance plastic material products of plastics industry.According to statistics, injection molding goods account for 1/3rd of all moulded plastics articles total outputs, and injection molding accounts for the over half of mould for plastics quantity.

Injection molding is made up of dynamic model and cover half two parts, and dynamic model is installed on the moving die plate of injection machine, and cover half is installed on the fixed form of injection machine.The injection-moulding plastic process is a kind of cyclic process of intermittently operated, in each cycle period, at first, dynamic model and cover half closed formation running gate system and die cavity, then, the plastics of fusion are under the pressure that injection machine provides, flow into die cavity and cooling curing setting through running gate system, at last, dynamic model separates with cover half, ejects plastic products by ejecting mechanism.Yet, in actual production process, usually because the ejecting mechanism inefficacy, mould structure designs reasons such as unreasonable or plastic products quality fluctuation, cause plastic products to eject smoothly easily, and remain in (the particularly mould of a multi-cavity mold) in the mould, at this moment, if dynamic model and cover half closure, residual plastic products cause the damage of mould easily.For fear of this situation, a lot of enterprises adopt manual type to address this problem, and promptly a secondary mould is joined an employee, and the special monitoring production process is closed injection machine immediately when finding that plastic products eject failure, stop dynamic model and cover half closure.This manual type except the human cost height, simultaneously because normal person's reaction time is 0.1～0.5s, and energy time of concentration has only 20～30min, therefore, problem such as manual type exists response speed slow, and reliability is low.

In computer vision field, histogram can provide the statistical information of image, and it has reflected what and distribution situation thereof of the different tonal gradation number of pixels of piece image, and its abscissa is represented gray scale, and its ordinate is represented pixel quantity.Histogrammic generation does not need complicated conversion and computing, and image processing speed is fast.Histogrammic matching algorithm can detect the statistics variations of significant edge of different images and color, and the difference of quick identification video scene.

Summary of the invention

The purpose of this utility model is to overcome the deficiency of above-mentioned existence; a kind of embedded plastic mould protective device based on the histogram coupling is provided; this device can judge whether there are the plastic products that do not come off in the mould automatically, is a kind of application of computer vision technique in the injection-moulding plastic process.

The purpose of this utility model is finished by following technical solution, and this device is divided into four modules and is respectively: image capture module, calculate matching module, human-computer interaction module, action control module; Described image capture module comprises two infrared cameras and an incandescent lamp; Calculate matching module and comprise that one is used for the histogram of computed image and carries out the Arm development board that the histogram coupling is calculated; Human-computer interaction module is the controller of plastic injection molding host computer that is used to show the captured image of infrared camera and is responsible for man-machine interactive operation; Action control module is the controller of plastic injection molding slave computer that is used to control the mold closing action of injection machine dynamic model; Image capture module calculates between matching module and the human-computer interaction module and connects control by hub with the Ethernet netting twine, is connected control with the Can/232 line between human-computer interaction module and the action control module.

As preferably, described two infrared cameras are separately fixed on the fixed half and moving half by the magnetic force gauge stand, and infrared camera is toward the opening part of described fixed half and moving half and gather image; Described incandescent lamp is fixed on the cover half by the magnetic force gauge stand, and this socket is toward the opening part of described fixed half and moving half, and for providing infrared camera to gather the required light source of image.

As preferably, described hub is provided with four ports, wherein two ports respectively with image capture module in two infrared cameras with the control that links to each other of Ethernet netting twine; In addition two ports respectively with calculate matching module in Arm development board and human-computer interaction module in the controller of plastic injection molding host computer with the control that links to each other of Ethernet netting twine.

The beneficial effects of the utility model are: can judge whether there are the goods that do not come off in the mould of plastics automatically according to the difference of two image histograms,, then report to the police if exist, and the inaccurate mold closing of indication injection machine, thus effectively protect mould.

Description of drawings

Fig. 1 is an overall structure schematic diagram of the present utility model.

Fig. 2 is a workflow diagram of the present utility model.

The specific embodiment

Label in the utility model accompanying drawing is respectively: 1, infrared camera, 2, incandescent lamp, 3, magnetic force gauge stand, 4, the Ethernet netting twine, 5, hub, 6, controller of plastic injection molding host computer, 7, Arm development board, 8, the Can/232 line, 9, the controller of plastic injection molding slave computer, 10, cover half, 11, dynamic model.

Below in conjunction with accompanying drawing the utility model is done detailed introduction: as shown in Figure 1, this device is divided into four modules and is respectively: image capture module, calculate matching module, human-computer interaction module, action control module; Described image capture module comprises two infrared cameras 1 and an incandescent lamp 2; Calculate matching module and comprise that one is used for the histogram of computed image and carries out the Arm development board 7 that the histogram coupling is calculated; Human-computer interaction module is the controller of plastic injection molding host computer 6 that is used to show the captured image of infrared camera and is responsible for man-machine interactive operation; Action control module is the controller of plastic injection molding slave computer 9 that is used to control the mold closing action of injection machine dynamic model; Image capture module calculates between matching module and the human-computer interaction module and connects control by hub 5 with Ethernet netting twine 4, is connected control with Can/232 line 8 between human-computer interaction module and the action control module.

Described two infrared cameras 1 are separately fixed on cover half 10 and the dynamic model 11 by magnetic force gauge stand 3, and infrared camera 1 is toward the opening part of described cover half 10 and dynamic model 11 and gather image; Described incandescent lamp 2 is fixed on the cover half 10 by magnetic force gauge stand 3, and this socket is toward the opening part of described cover half 10 and dynamic model 11, and for providing infrared camera 1 to gather the required light source of image.

Described hub 5 is provided with four ports, wherein two ports respectively with image capture module in two infrared cameras 1 with Ethernet netting twine 4 control that links to each other; In addition two ports respectively with calculate matching module in Arm development board 7 and human-computer interaction module in controller of plastic injection molding host computer 6 with Ethernet netting twine 4 control that links to each other.

As shown in Figure 2, the course of work of the present utility model can be described as, at first, the pattern of injection machine is set to manually, the similarity threshold T of image is set, 0≤T≤1, and utilize the image capture module collection not have the dynamic model image and each one of the cover half image (following abbreviation respectively: dynamic model standard picture and cover half standard picture) of residual goods, dynamic model standard picture and cover half standard picture are kept at automatically and calculate in the matching module; Then, the pattern of injection machine is set to semi-automatic or full-automatic, put in place and in mold closing action also not before the action at the liftout attachment rollback, image capture module is gathered dynamic model and each one of cover half image (following abbreviation respectively: dynamic model contrast images and cover half contrast images) automatically, is saved in equally and calculates in the matching module; Then, calculate matching module and calculate dynamic model standard picture and the similarity value of dynamic model contrast images and the similarity value of cover half standard picture and cover half contrast images, if both similarity values are all greater than the similarity threshold of setting, then thinking does not all have residual goods in dynamic model and the cover half, action control module is carried out the mold closing action of dynamic model, begins next cycle period.If both similarity thresholds have one or two less than the similarity threshold of setting, think then to have residual goods in dynamic model or the cover half that action control module stops the mold closing action of dynamic model, and gives the alarm.

The computational methods of above-mentioned dynamic model standard picture and dynamic model contrast images similarity value and the computational methods of cover half standard picture and cover half contrast images are identical, and computational methods mainly may further comprise the steps:

(1) gray level image of taking according to infrared camera generates histogram.Histogrammic abscissa is a gray value, has the pixel quantity of this gray value in the ordinate presentation video.The gray value of gray level image is 0～255, with gray value be divided into n interval, i.e. 0～255/n, 255/n～2 * 255/n ...The value of n is unsuitable excessive also unsuitable too small, and too small meeting causes histogram too average and can't embody difference, excessively then can produce sharp-pointed and single effect.

(2) carry out histogrammic normalization operation, be about in the histogram pixel quantity between each gray area divided by the total number of pixels of image, like this, in the histogram between each gray area pairing ordinate and be 1.

(3), calculate two and treat the histogrammic similarity value of contrast images according to normalized histogram.Histogrammic matching algorithm has three kinds in the utility model, and suc as formula shown in (I), formula (II) and the formula (III), the user can select suitable matching algorithm to the computing formula of three kinds of algorithms as required in the actual production process respectively.

$d_2(H_1,H_2)=\underset{i}{\overset{n}{\mathrm{\Σ}}}\min (H_1\left(i\right),H_2\left(i\right))---\left(I\right)$

$d_1(H_1,H_2)=1-\frac{1}{2}\underset{i}{\overset{n}{\mathrm{\Σ}}}\frac{{(H_1\left(i\right)-H_2\left(i\right))}^2}{H_1\left(i\right)+H_2\left(i\right)}---\left(\mathrm{II}\right)$

$d_3(H_1,H_2)=1-\sqrt{1-\underset{i}{\overset{n}{\mathrm{\Σ}}}\frac{\sqrt{H_1\left(i\right)\·H_2\left(i\right)}}{\underset{i}{\overset{n}{\mathrm{\Σ}}}{H}_1\left(i\right)\·\underset{i}{\overset{n}{\mathrm{\Σ}}}{H}_2\left(i\right)}}---\left(\mathrm{III}\right)$

In the formula, i is between histogrammic i gray area, H ₁And H ₂For waiting to contrast the normalized value of two image histogram ordinates.

The present invention is described in further detail below by a production example, histogrammic in this embodiment matching algorithm selection algorithm 1, and the n value gets 37.

The first step: injection machine is set to manual work pattern, gathers each one of dynamic model standard picture and cover half standard picture, and it is 0.8 that similarity threshold T is set.

Second step: injection machine is set to the fully automatic working pattern, puts in place and in mold closing action also not before the action at the liftout attachment rollback, and image capture module is gathered each one of dynamic model and cover half contrast images automatically.

The 3rd step: calculate the histogram similarity between matching module calculating cover half standard picture and the cover half contrast images.At first generate the histogram of cover half standard picture, the sum of all pixels of cover half standard picture is 305398, wherein the pixel count of (gray value is 0～5) is 307 between first gray area, histogram with the cover half standard picture carries out the normalization operation then, and the pixel value of (gray value is 0～5) is 307/305398=0.00100525 between first gray area.Equally, generate the histogram of cover half contrast images earlier, carry out the normalization operation then.After the normalization operation, the histogram data of cover half standard picture and contrast images is as follows:

。Then, the histogram similarity value of calculating between cover half standard picture and the cover half contrast images according to formula (I) is 0.9936.

The 4th step: calculate the histogram similarity between matching module calculating dynamic model standard picture and the dynamic model contrast images.Calculation procedure is identical with the 4th step, and the normalization histogram data of dynamic model standard picture and contrast images are as follows:

, same, the histogram similarity value of calculating between dynamic model standard picture and the dynamic model contrast images according to formula (I) is 0.7574.

The 5th step: histogram similarity between cover half standard picture and the cover half contrast images is worth 0.9936 greater than similarity threshold 0.8, thinks not have residual goods in the cover half; Histogram similarity between dynamic model standard picture and dynamic model contrast images value 0.7574 is less than similarity threshold 0.8, then thinks to have residual goods in the dynamic model, stops the mold closing action and gives the alarm.

Claims (3)

1. embedded plastic mould protective device based on histogram coupling, this device is divided into four modules and is respectively: image capture module, calculate matching module, human-computer interaction module, action control module; It is characterized in that: described image capture module comprises two infrared cameras (1) and an incandescent lamp (2); Calculate matching module and comprise that one is used for the histogram of computed image and carries out the Arm development board (7) that the histogram coupling is calculated; Human-computer interaction module is the controller of plastic injection molding host computer (6) that is used to show the captured image of infrared camera and is responsible for man-machine interactive operation; Action control module is the controller of plastic injection molding slave computer (9) that is used to control the mold closing action of injection machine dynamic model; Image capture module calculates between matching module and the human-computer interaction module and connects control by hub (5) with Ethernet netting twine (4), is connected control with Can/232 line (8) between human-computer interaction module and the action control module.

2. the embedded plastic mould protective device based on the histogram coupling according to claim 1, it is characterized in that: described two infrared cameras (1) are separately fixed on cover half (10) and the dynamic model (11) by magnetic force gauge stand (3), and infrared camera (1) is toward the opening part of described cover half (10) and dynamic model (11) and gather image; Described incandescent lamp (2) is fixed on the cover half (10) by magnetic force gauge stand (3), and this socket is toward the opening part of described cover half (10) and dynamic model (11), and for providing infrared camera (1) to gather the required light source of image.

3. the embedded plastic mould protective device based on the histogram coupling according to claim 1 and 2, it is characterized in that: described hub (5) is provided with four ports, wherein two ports respectively with image capture module in two infrared cameras (1) with Ethernet netting twine (4) control that links to each other; In addition two ports respectively with calculate matching module in Arm development board (7) and the interior controller of plastic injection molding host computer (6) of human-computer interaction module with Ethernet netting twine (4) control that links to each other.

Images