Mould demoulding detection system based on distance measuring camera

Abstract

The invention discloses a mold demolding detection system based on a distance measuring camera. The system comprises an injection molding machine, an injection molding machine control unit, the distance measuring camera, a light supplementing device and an image processing unit, an injection molding part area is arranged in the middle of the injection molding machine; the injection molding machine control unit is used for controlling the injection molding machine to realize mold injection molding; the distance measuring camera is used for shooting color feature images of an injection molding part area and transmitting information to the image processing unit, and the image processing unit is used for judging the information transmitted in the distance measuring camera so as to achieve demolding detection. According to the invention, an image processing module is made based on a color and distance measuring industrial camera, whether a product with large color difference with a mold is demolded can be rapidly identified through RGB comparison, whether the mold is demolded is re-judged through secondary comparison of differentiated distance thresholds, the comparison success rate is enhanced, the error rate is low, the detection effect is high in intelligent degree, the man-machine interaction performance is high, and the detection efficiency is high. And an operator can autonomously set mold detection standards according to different types of injection molds, so that the use range is wide.

Description

Technical Field

[0001] The invention belongs to the technical field of numerical control moulds, and in particular relates to a mould demoulding detection system based on a range-finding camera. Background Art

[0002] Injection molding is a method of producing industrial products, and the products are usually made of rubber or plastic. In modern mold manufacturing, demoulding is a key step in the injection molding process. During the demoulding process, if the injection molded part fails to completely separate from the mold, it will cause product quality problems and even damage the mold. Therefore, real-time and accurate detection of mold demoulding is of great significance to ensure product quality and improve production efficiency.

[0003] At present, the detection of mold demolding mostly relies on manual observation or simple sensor detection, and operators are required to use specific testing equipment to perform quality inspection on the injection molded products after demolding.

[0004] However, traditional manual inspection methods have extremely high requirements for the environment. They cannot be used normally in dim, flickering, or reflective environments, which greatly consumes manpower and material resources. These methods have problems such as low detection accuracy, poor real-time performance, and susceptibility to human factors. They also bring many inconveniences to unmanned production on the assembly line, resulting in reduced injection molding production efficiency.

[0005] In order to solve these problems and improve the inspection efficiency and accuracy of injection molded parts, it is urgent to design an injection molded parts inspection equipment with a high degree of automation to replace manual inspection and improve the inspection efficiency of injection molded parts. Summary of the invention

[0006] The purpose of the present invention is to provide a mold demoulding detection system based on a rangefinder camera to solve the problems of poor detection accuracy and low detection efficiency of mold injection parts mentioned in the above background technology. The following technical solution is provided: a mold demoulding detection system based on a rangefinder camera, wherein the equipment includes:

[0007] An injection molding machine, an injection molding machine control unit, a ranging camera, a fill light device and an image processing unit; an injection molding area is arranged in the middle of the injection molding machine, and the injection molding machine control unit is used to control the injection molding machine to realize mold injection; the ranging camera is used to capture the color characteristic image of the injection molding area and transmit the information to the image processing unit, and the image processing unit is used to judge the information transmitted in the ranging camera to realize mold detection.

[0008] The rangefinder camera is arranged above the injection molding area, and an image processing module and a distance measurement module are arranged inside the rangefinder camera, which are used to obtain the color image characteristics of the injection molding area and the distance parameters from the rangefinder camera to the injection molding area. The rangefinder camera can automatically adjust the focal length for the injection molding in the injection molding area.

[0009] The image processing module is used to process the color feature image of the injection mold in the injection molded part area collected by the ranging camera;

[0010] Initially, the color feature image of the image processing module is divided into nine-square grids. Get the average value of the RGB three-color values ​​of all pixels in each area, recorded as [s1, s2, …s9];

[0011] The color feature image captured by the rangefinder camera is divided into nine-square grids. Get the average value of the sum of the RGB three-color values ​​of all pixels in each area as [r1, r2, …, r9];

[0012] The image processing module compares the difference between [s1, s2, …, s9] and [r1, r2, …, r9] one by one to obtain the average value of the differentiated RGB three-color values ​​of the injection molded parts, which is recorded as [d1, d2, …, d9].

[0013] Set the RGB threshold to △d. The RGB threshold △d is set according to the color of the injection molded product. The closer the color is to the metal color of the mold, the smaller the absolute value of the RGB threshold △d is, and vice versa.

[0014] During the detection process of the image processing module, if the absolute value of at least one value in [d1, d2, …, d9] exceeds △d, the color image feature of the injection molded part is judged as a failure, otherwise it is judged as a success.

[0015] The RGB threshold △d of the color feature image of the image processing module is initially in the range of (0-60).

[0016] In this technical solution, the RGB threshold △d of the initial color feature image is 15 by default.

[0017] The workflow of this system is as follows:

[0018] 1. When used for the first time, the ranging camera takes a photo of the mold and the initial distance from the camera to the mold in the mold cavity when the mold cavity is opened in the injection molding area; the area for mold comparison is framed on the image processing unit;

[0019] 2. During the formal operation, when the injection molding machine opens the mold cavity, the injection molding machine control unit detects that the injection molding machine mold cavity is opened and sends a signal to the image processing unit. After receiving the signal, the image processing unit commands the ranging camera to start taking pictures and measuring distance, and transmits the nearly two pictures and distance measurement information back to the image processing unit;

[0020] 3. After receiving the information, the image processing unit first calculates the RGB three-channel histogram matrix of the two pictures and compares the correlation between the two histogram matrices:

[0021] When it is greater than the threshold (default 15, configurable), the comparison passes. After passing, the image processing unit sends a signal to the injection molding machine control unit, and the injection molding machine control unit executes the injection molding machine closing. When it is less than the threshold (default 15, configurable) and the comparison fails, the image processing unit sends a signal to the injection molding machine control unit, and the injection molding machine control unit executes the injection molding machine to pause and stimulates the alarm device to sound an alarm.

[0022] The RGB comparison steps are:

[0023] 1. Calculate the RGB three-channel histogram matrix of the two pictures;

[0024] 2. Compare the correlation between the two histogram matrices;

[0025] 3. If the value is greater than the threshold (default 15, configurable), the comparison passes; otherwise, the comparison fails.

[0026] When inspecting injection molded parts, the operator can also configure the system to perform dual authentication and verification of photo information and ranging information, and the system will pass when one of the two meets the verification requirements.

[0027] It should be noted that the injection molding machine involved in this application can be a common injection molding machine equipment on the market and injection molding equipment with different mold models, and the comparison in this application is not specifically limited. For the same purpose, the RGB parameters of the demoulding injection molded parts can also be used in this solution to perform color image feature comparison, wherein the steps of color feature image comparison are:

[0028] 1. First, obtain two recent color comparison pictures;

[0029] 2. Process the color image into a black and white image (grayscale image);

[0030] 3. Thresholding the grayscale image will set the pixels with grayscale values ​​greater than the threshold (default 127, configurable) to 255 (white) and the others to 0 (black), thus obtaining a binary image.

[0031] 4. Dilate the binary image of the original image (the dilation value is configurable) to obtain the original Figure 2 Dilation graph of the value graph;

[0032] 5. Subtract the binary image matrix of the comparison image from the original Figure 2 The expansion map of the value map is used to obtain the difference matrix of the comparison and subtraction of the original map (the value of the result less than 0 in the subtraction algorithm will become 0);

[0033] 6. Perform an erosion operation on the difference matrix of the contrast minus the original image (the erosion matrix is ​​configurable) to filter out the noise;

[0034] 7. If the matrix after corrosion is 0, the original image coverage comparison image verification is passed;

[0035] 8. Carry out steps 3 to 5 in the same way to verify that the comparison image covers the original image;

[0036] 9. If both verifications pass, the image comparison passes.

[0037] In any of the above technical solutions, further, the initial distance parameter matrix between the calibration distance measurement module and the injection molded part area is divided into nine squares, by Get the average distance of each area [e1, e2, ... e9], and divide the distance parameter matrix between the injection molding area collected by the ranging camera and the ranging camera into nine squares. Get the average distance of each region [f1,f2,…,f9];

[0038] The distance threshold is set to △h. The distance threshold △h needs to be set according to the minimum wall thickness of the injection molded product. The thinner the wall thickness of the injection molded product, the smaller the absolute value of the distance threshold △h, and vice versa.

[0039] The distance measurement module obtains the distance difference [h1, h2, …, h9] of the injection molded part by comparing [e1, e2, …, e9] with [f1, f2, …, f9] one by one. If the absolute value of at least one value in [h1, h2, …, h9] exceeds the distance threshold △h, the distance feature judgment of the injection molded part fails, otherwise it succeeds.

[0040] In this technical solution, the step of comparing the distance values ​​is:

[0041] 1. Obtain the distance depth matrix of the last two comparisons from the binocular camera.

[0042] 2. Calculate the histogram matrix of the two matrices,

[0043] 3. Compare the correlation of the two histogram matrices. If the distance threshold △h is 0.95 by default and can be configured, the comparison passes, otherwise the comparison fails.

[0044] In any of the above technical solutions, further, the image processing unit includes a data processing module, an RGB threshold setting module and a distance threshold setting module;

[0045] The RGB threshold setting module is used to set the system allowable range of the differential RGB threshold △d of the injection molded parts in the injection molded parts area;

[0046] The distance threshold setting module is used to set the system allowable range of the differential distance threshold △h of the injection molded parts in the injection molded parts area;

[0047] The data processing module is used to compare the determination results of the image processing module with the distance measurement module to determine the detection result of the demoulding of the injection molded part. The fill light device uses LED to fill light to the injection molded part area.

[0048] In the present application, the fill light device may use different light sources, such as LED (light emitting diode), xenon lamp, etc., and may adopt different lighting modes such as stroboscopic, pulse or continuous lighting to achieve fill light for the injection molded parts.

[0049] In any of the above technical solutions, further, the injection molding machine control unit also includes an alarm device, which sends an alarm signal when determining that the demoulding is abnormal; the rangefinder camera can automatically adjust the focal length of the injection molded parts in the injection molded parts area; the fill light device uses LED to fill light to the injection molded parts area

[0050] In the technical solution, the alarm device is used to send out an alarm signal to notify the operator when the demoulding is abnormal. The storage module is used to store the color feature images, distance parameters and judgment results collected in succession, so as to facilitate subsequent data analysis and system optimization.

[0051] The beneficial effects of the present invention are as follows: the mold is made of steel and is gray. The RGB comparison can be used to quickly identify whether the product with a large color difference from the mold is demoulded. In addition, the RGB comparison makes up for the situation where the grayscale image edge algorithm fails to detect the edge of a flat product due to low edge detection. Furthermore, the distance value comparison makes up for the situation where the grayscale image edge algorithm fails to detect the edge of a product with similar color to the mold due to low edge detection.

[0052] This system is an image processing module based on a color and ranging industrial camera. It can solve the image comparison success rate in a changing environment. RGB comparison can quickly identify whether the product with large color difference from the mold is demolded. Through the secondary comparison of differentiated distance thresholds, it can judge whether the mold is demolded again to enhance the comparison success rate. The error rate is low, the detection effect is highly intelligent, and the human-computer interaction performance is high. The operator can independently set the mold detection standard according to different types of injection molds, and it has a wide range of uses. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 It is a schematic diagram of the appearance of the present invention;

[0054] Figure 2 is a comparative flow chart of the present invention;

[0055] Figure 3 It is a comparison flow chart after adding grayscale image comparison. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0057] In the description of the present application, it should be noted that the terms used herein are only for describing specific embodiments, and are not intended to limit the exemplary embodiments according to the present application. For ease of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship. The technology, methods and equipment known to ordinary technicians in the relevant field may not be discussed in detail, but in appropriate cases, the technology, methods and equipment should be regarded as part of the authorization specification. In all examples shown and discussed here, any specific value should be interpreted as merely exemplary, rather than as a limitation. Therefore, other examples of the exemplary embodiments may have different values. It should be noted that similar numbers and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0058] like Figure 1-3 As shown, this embodiment provides a mold demoulding detection system based on a ranging camera, wherein the device includes:

[0059] Injection molding machine 10, injection molding machine control unit 20, ranging camera 30, fill light device 40 and image processing unit 50;

[0060] An injection molding area 11 is provided in the middle of the injection molding machine 10, and an injection molding machine control unit 20 is used to control the injection molding machine 10 to realize mold injection; the ranging camera 30 is used to capture the color feature image of the injection molding area 11 and transmit the information to the image processing unit 50, and the image processing unit 50 is used to judge the information transmitted in the ranging camera 30 to realize mold detection.

[0061] The ranging camera 30 is disposed above the injection molding area 11. An image processing module 31 and a distance measurement module 32 are disposed inside the ranging camera 30. The image processing module 31 and the distance measurement module 32 are used to obtain the color image features of the injection molding area 11 and the distance parameters from the ranging camera 30 to the injection molding area 11. The ranging camera 30 can automatically adjust the focal length for the injection molding in the injection molding area 11.

[0062] The image processing module 31 is used to process the color characteristic image of the injection mold in the injection molded part area 11 acquired by the ranging camera 30;

[0063] Initially, the color feature image of the image processing module 31 is divided into nine-square grids. Get the average value of the RGB three-color values ​​of all pixels in each area, recorded as [s1, s2, …s9];

[0064] The color feature image captured by the ranging camera 30 is divided into nine-square grids. Get the average value of the sum of the RGB three-color values ​​of all pixels in each area as [r1, r2, …, r9];

[0065] The image processing module 31 compares the differences between [s1, s2, ..., s9] and [r1, r2, ..., r9] one by one to obtain the average value of the differentiated RGB three-color values ​​of the injection molded part, which is recorded as [d1, d2, ..., d9].

[0066] Set the RGB threshold to △d. The RGB threshold △d is set according to the color of the injection molded product. The closer the color is to the metal color of the mold, the smaller the absolute value of the RGB threshold △d is, and vice versa.

[0067] During the detection process of the image processing module 31 , if the absolute value of at least one value in [d1, d2, …, d9] exceeds Δd, the color image feature of the injection molded part is judged as a failure, otherwise it is judged as a success.

[0068] The RGB threshold Δd of the color feature image of the image processing module 31 is initially within the range of (0-60).

[0069] In this technical solution, the RGB threshold △d of the initial color feature image is 15 by default.

[0070] The workflow of this system is as follows:

[0071] 1. When used for the first time, the distance measuring camera 30 captures a mold photo and the initial distance from the camera to the mold in the mold cavity when the mold cavity is opened in the injection molding area 11; and frames the area for mold comparison on the image processing unit;

[0072] 2. During the formal operation, when the injection molding machine 10 opens the mold cavity, the injection molding machine control unit 20 detects that the injection molding machine mold cavity is opened, and sends a signal to the image processing unit 50. After receiving the signal, the image processing unit 50 instructs the ranging camera 30 to start taking pictures and measuring distance, and transmits the nearly two times of photographing information and ranging information back to the image processing unit 50;

[0073] 3. After receiving the information, the image processing unit 50 first calculates the RGB three-channel histogram matrix of the two images and compares the correlation between the two histogram matrices:

[0074] When the value is greater than a threshold value (default value is 15, which is configurable), the comparison passes. After passing, the image processing unit 50 sends a signal to the injection molding machine control unit 20, and the injection molding machine control unit 20 executes the injection molding machine 10 to close. When the value is less than a threshold value (default value is 15, which is configurable), the comparison fails. The image processing unit 50 sends a signal to the injection molding machine control unit 20, and the injection molding machine control unit 20 executes the injection molding machine 10 to pause and activates the alarm device 60 to sound an alarm.

[0075] The RGB comparison steps are:

[0076] 1. Calculate the RGB three-channel histogram matrix of the two pictures;

[0077] 2. Compare the correlation between the two histogram matrices;

[0078] 3. If the value is greater than the threshold (default 15, configurable), the comparison passes; otherwise, the comparison fails.

[0079] It should be noted that the injection molding machine involved in this application can adopt common injection molding machine equipment on the market and injection molding equipment with different mold models, and the comparison in this application is not specifically limited.

[0080] In the comparison process, the system may add a picture comparison process based on the subsequent comparison of color image features by RGB parameters. When inspecting injection molded parts, the operator may configure the system to perform multiple inspections and verifications with distance measurement information, RGB information, and photo information.

[0081] When adding a picture comparison process, the steps of picture comparison are:

[0082] 1. First, obtain two recent color comparison pictures;

[0083] 2. Process the color image into a black and white image (grayscale image);

[0084] 3. Thresholding the grayscale image will set the pixels with grayscale values ​​greater than the threshold (default 127, configurable) to 255 (white) and the others to 0 (black), thus obtaining a binary image.

[0085] 4. Dilate the binary image of the original image (the dilation value is configurable) to obtain the original Figure 2 Dilation graph of the value graph;

[0086] 5. Subtract the binary image matrix of the comparison image from the original Figure 2 The expansion map of the value map is used to obtain the difference matrix of the comparison and subtraction of the original map (the value of the result less than 0 in the subtraction algorithm will become 0);

[0087] 6. Perform an erosion operation on the difference matrix of the contrast minus the original image (the erosion matrix is ​​configurable) to filter out the noise;

[0088] 7. If the matrix after corrosion is 0, the original image coverage comparison image verification is passed;

[0089] 8. Carry out steps 3 to 5 in the same way to verify that the comparison image covers the original image;

[0090] 9. If both verifications pass, the image comparison passes.

[0091] In a preferred embodiment of the present invention:

[0092] like Figure 1-2 As shown, specifically, the initial distance parameter matrix between the calibration distance measurement module 32 and the injection molded part area 11 is divided into nine squares, through Get the average distance of each area [e1, e2, ... e9], and divide the distance parameter matrix between the injection molding area 11 and the ranging camera 30 collected by the ranging camera 30 into nine squares. Get the average distance of each region [f1,f2,…,f9];

[0093] The distance threshold is set to △h. The distance threshold △h needs to be set according to the minimum wall thickness of the injection molded product. The thinner the wall thickness of the injection molded product, the smaller the absolute value of the distance threshold △h, and vice versa.

[0094] The distance measurement module 32 obtains the distance difference [h1, h2, ..., h9] of the injection molded part by comparing [e1, e2, ..., e9] with [f1, f2, ..., f9] one by one. If the absolute value of at least one value in [h1, h2, ..., h9] exceeds the distance threshold △h, the distance feature judgment of the injection molded part fails, otherwise it succeeds.

[0095] In this technical solution, the step of comparing the distance values ​​is:

[0096] 1. Obtain the distance depth matrix of the last two comparisons from the binocular camera.

[0097] 2. Calculate the histogram matrix of the two matrices,

[0098] 3. Compare the correlation of the two histogram matrices. If the distance threshold △h is 0.95 by default and can be configured, the comparison passes, otherwise the comparison fails.

[0099] In a preferred embodiment of the present invention:

[0100] The image processing unit 50 includes a data processing module 51, an RGB threshold setting module 52 and a distance threshold setting module 53; the RGB threshold setting module 52 is used to set the system allowable range of the differentiated RGB threshold △d of the injection molded parts in the injection molded parts area 11;

[0101] The distance threshold setting module 53 is used to set the system allowable range of the differentiated distance threshold △h of the injection molded parts in the injection molded parts area 11;

[0102] The data processing module 51 is used to compare the determination results of the image processing module 31 and the distance measurement module 32 to determine the detection result of the demoulding of the injection molded part. The fill light device 40 uses LED to fill light to the injection molded part area 11.

[0103] In the present application, the fill light device 40 may use different light sources, such as LED (light emitting diode), xenon lamp, etc., and may adopt different lighting modes such as stroboscopic, pulse or continuous lighting to achieve fill light for the injection molded parts.

[0104] In a preferred embodiment of the present invention:

[0105] The injection molding machine control unit 20 also includes an alarm device 60, which sends an alarm signal when it determines that the demoulding is abnormal; the rangefinder camera 30 can automatically adjust the focal length of the injection molded parts in the injection molded parts area 11; the fill light device 40 uses LED to fill light to the injection molded parts area 11

[0106] In the present technical solution, the alarm device 60 is used to send out an alarm signal to notify the operator when the demoulding is abnormal. The storage module 54 is used to store the color feature images, distance parameters and determination results collected in succession, so as to facilitate subsequent data analysis and system optimization.

[0107] The embodiments of the present application are described above in conjunction with the accompanying drawings. In the absence of conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A mold demoulding detection system based on a rangefinder camera, characterized in that: include: An injection molding machine control unit (20), a distance measuring camera (30), a fill light device (40) and an image processing unit (50); The range-finding camera (30) is used to capture a color feature image of an injection molded part and transmit the information to an image processing unit (50); the image processing unit (50) is used to determine the image information in the range-finding camera (30) to complete demoulding detection of the injection molded part.

2. A mold demoulding detection system based on a range-finding camera according to claim 1, characterized in that: The invention also comprises an injection molding machine (10), wherein a molded part area (11) is arranged in the middle of the injection molding machine (10), and the injection molding machine control unit (20) is used to control the injection molding machine (10) to realize mold injection; the distance measuring camera (30) is arranged above the molded part area (11), and an image processing module (31) and a distance measuring module (32) are arranged inside the distance measuring camera (30).

3. A mold demoulding detection system based on a range-finding camera according to claim 2, characterized in that: The image processing module (31) is used to process the color characteristic image of the injection mold in the injection molded part area (11) collected by the range-finding camera (30); Initially, the color feature image of the image processing module (31) is divided into nine-square grids. Get the average value of the RGB three-color values ​​of all pixels in each area, recorded as [s1, s2, …s9]; The color feature image captured by the distance measuring camera (30) is divided into nine-square grids. Get the average value of the sum of the RGB three-color values ​​of all pixels in each area as [r1, r2, …, r9]; The image processing module (31) compares the difference between [s1, s2, ..., s9] and [r1, r2, ..., r9] one by one, and obtains the average value of the differentiated RGB three-color values ​​of the injection molded part, which is recorded as [d1, d2, ..., d9].

4. The mold demoulding detection system based on a range-finding camera according to claim 3, characterized in that: Set the RGB threshold to △d. The RGB threshold △d is set according to the color of the injection molded product. The closer the color is to the metal color of the mold, the smaller the absolute value of the RGB threshold △d is, and vice versa. During the detection process of the image processing module (31), if the absolute value of at least one value in [d1, d2, ..., d9] exceeds Δd, the color image feature of the injection molded part is judged as a failure, otherwise it is judged as a success.

5. The mold demoulding detection system based on a range-finding camera according to claim 4, characterized in that: The RGB threshold Δd of the color feature image of the image processing module (31) is initially within the range of (0-60).

6. The mold demoulding detection system based on a range-finding camera according to claim 5, characterized in that: The initial distance parameter matrix between the distance measurement module (32) and the injection molded part area (11) is calibrated and divided into nine squares, by The average distance values ​​[e1, e2, ... e9] of each area are obtained, and the distance parameter matrix between the injection molded part area (11) and the distance measuring camera (30) collected by the distance measuring camera (30) is divided into nine-square grids. Get the average distance of each region [f1,f2,…,f9].

7. A mold demoulding detection system based on a range-finding camera according to claim 6, characterized in that: The distance threshold is set to △h. The distance threshold △h needs to be set according to the minimum wall thickness of the injection molded product. The thinner the wall thickness of the injection molded product, the smaller the absolute value of the distance threshold △h, and vice versa. The distance measurement module (32) obtains the distance difference [h1, h2, ..., h9] of the injection molded part by comparing [e1, e2, ..., e9] with [f1, f2, ..., f9] one by one. If the absolute value of at least one value in [h1, h2, ..., h9] exceeds the distance threshold value △h, the distance feature determination of the injection molded part fails, otherwise it succeeds.

8. The mold demoulding detection system based on a range-finding camera according to claim 7, characterized in that: The image processing unit (50) comprises a data processing module (51), an RGB threshold setting module (52) and a distance threshold setting module (53); The RGB threshold setting module (52) is used to set a system-allowed range of a differentiated RGB threshold Δd of an injection molded part in the injection molded part area (11); The distance threshold setting module (53) is used to set a system-allowed range of a differential distance threshold Δh of injection molded parts in the injection molded parts area (11); The data processing module (51) is used to compare the determination results of the image processing module (31) and the distance measurement module (32) to determine the detection result of the demoulding of the injection molded part.

9. The mold demoulding detection system based on a range-finding camera according to claim 8, characterized in that: When the data processing module (51) determines that demoulding is abnormal, the injection molding machine control unit (20) automatically controls the injection molding machine (10) to stop running. The image processing unit (50) also includes a storage module (54), and the storage module (54) is used to store the collected RGB color feature image, distance parameters and injection molded part detection results.

10. The mold demoulding detection system based on a range-finding camera according to claim 2, characterized in that: The injection molding machine control unit (20) further comprises an alarm device (60), wherein the alarm device (60) issues an alarm signal when determining that the demoulding is abnormal; the distance measuring camera (30) can automatically adjust the focal length of the injection molded parts in the injection molded parts area (11); and the fill light device (40) uses an LED to fill light to the injection molded parts area (11).

Images