A mold temperature detection and mold foreign body detection method, system, device and medium

Abstract

The present invention belongs to the field of die-casting machines, and specifically relates to a method, system, device and medium for detecting mold temperature and mold foreign matter. Among them, a method for detecting mold temperature and mold foreign matter includes the following steps: obtaining a first temperature of a first preset observation point based on a first temperature image obtained when the mold is opened; judging whether the temperature of the die-casting process is abnormal based on the first temperature and the first preset temperature range; obtaining a first foreign matter-free template image based on a conditional diffusion model and the average temperature obtained by the first temperature; and obtaining a foreign matter detection image by marking foreign matter on the first temperature image based on the first foreign matter-free template image and the first temperature image. The present invention can detect the mold temperature and mold foreign matter when the mold is opened, ensuring that the mold works at a qualified temperature and without foreign matter, and has the advantages of improving product qualification rate, reducing costs and improving safety.

Description

Technical Field

[0001] The present invention belongs to the field of automobile manufacturing, and in particular relates to a mold temperature detection and mold foreign body detection method, system, device and medium. Background Art

[0002] In the modern automobile manufacturing industry, especially in the die-casting process of automobile parts, precise control of mold temperature and effective detection of foreign matter on the mold are crucial. This is because mold temperature plays a decisive role in the die-casting process. It directly affects the flow characteristics of molten metal, filling speed, cooling rate, crystallization process, and the dimensional accuracy, shape stability, internal structure and surface quality of the final parts. Too high or too low mold temperature will lead to product defects such as pores, shrinkage, warping, etc. At the same time, even tiny foreign matter in the die-casting mold may cause serious problems; foreign matter may cause local overheating of the mold, increased wear, and even block the gate and damage the sealing surface, further affecting the quality of the casting and the service life of the mold. In addition, foreign matter embedded in the casting will directly lead to unqualified products, increase scrap rate and production costs.

[0003] Mold temperature monitoring usually adopts time analysis method and handheld thermal imaging monitoring. The time analysis method mainly relies on manual experience to judge the temperature change trend of the die-casting machine in an operation process, and then adjust the operation process and time. Manual judgment is easily affected by the environment and is subjective, and it is difficult to achieve standardization of production control; handheld thermal imaging temperature measurement is used. Since the die-casting machine is dangerous when working, the die-casting machine will be completely closed on all sides. It is necessary to enter the die-casting machine after an operation cycle to measure the mold temperature, which seriously affects the operation efficiency and the accuracy of handheld infrared temperature measurement is easily affected by distance.

[0004] Foreign body detection is usually based on post-testing, that is, the mold is checked after product abnormalities occur. Delayed detection can easily lead to an increase in the scrap rate.

[0005] In view of this, the present invention is proposed. Summary of the invention

[0006] In order to solve the technical problems existing in the prior art, the present invention provides a mold temperature detection and mold foreign body detection method, system, device and medium.

[0007] The present invention includes the following technical solutions:

[0008] A first aspect of the present invention provides a method for detecting mold temperature and mold foreign matter, the method comprising the following steps:

[0009] Obtaining a first temperature of a first preset observation point based on a first temperature image acquired when the mold is opened;

[0010] Based on the first temperature and the first preset temperature range, determining whether the temperature of the die-casting process is abnormal;

[0011] Obtaining a first foreign-matter-free template image based on the conditional diffusion model and the average temperature obtained by the first temperature;

[0012] A foreign object detection image is obtained based on the first foreign object-free template image and the first temperature image.

[0013] Furthermore, the method further comprises the following steps:

[0014] Obtaining a second temperature of a second preset observation point based on a second temperature image acquired after spraying;

[0015] Based on the second temperature and the first preset temperature, it is determined whether the temperature of the spraying process is abnormal.

[0016] Further, based on the second temperature and the first preset temperature, determining whether the temperature of the spraying process is abnormal includes the following steps:

[0017] If the absolute value of the difference between the second temperature and the first preset temperature is within the first preset range, it indicates that the temperature of the spraying process is normal;

[0018] If the absolute value of the difference between the second temperature and the first preset temperature is not within the first preset range, it indicates that the spraying process is abnormal, and an early warning is issued.

[0019] Further, based on the first temperature and the first preset temperature range, determining whether the temperature of the die-casting process is abnormal includes the following steps:

[0020] If the first temperature is within the first preset temperature range, it indicates that the temperature of the die-casting process is normal;

[0021] If the first temperature is not within the first preset temperature range, it indicates that the temperature of the die-casting process is abnormal, and an early warning is issued.

[0022] Furthermore, the method for establishing the conditional diffusion model comprises the following steps:

[0023] A conditional diffusion model is constructed based on an unlabeled mold opening temperature image dataset and a preset average temperature.

[0024] Further, obtaining a foreign body detection image based on the first foreign body-free template image and the first temperature image comprises the following steps:

[0025] The first temperature image is differentially compared with the first foreign body-free template image to extract a temperature difference image; then the temperature difference image is thresholded, binarized, morphologically processed, connected domain analyzed, and the foreign body area contour is extracted to obtain a foreign body detection image with foreign body markings.

[0026] A second aspect of the present invention provides a mold temperature detection and foreign matter detection system, comprising: a mold temperature detection module: obtaining a first temperature of a first preset observation point based on a first temperature image acquired when the mold is opened; judging whether the die-casting process temperature is abnormal based on the first temperature and a first preset temperature range;

[0027] Foreign body detection module: obtains a first foreign body-free template image based on a conditional diffusion model and an average temperature obtained from the first temperature; and obtains a foreign body detection image based on the first foreign body-free template image and the first temperature image.

[0028] Furthermore, the mold temperature detection module is also used to obtain a second temperature of a second preset observation point based on a second temperature image obtained after spraying; and to determine whether the temperature of the spraying process is abnormal based on the second temperature and the first preset temperature.

[0029] A third aspect of the present invention provides a mold temperature detection and foreign matter detection device, comprising:

[0030] Dual-light camera: used to obtain the first temperature image when the mold is opened and the second temperature image after spraying;

[0031] Terminal: including a timing control circuit and an algorithm processing unit; the algorithm processing unit includes a mold temperature detection module and a foreign matter detection module;

[0032] Mold temperature detection module: obtains a first temperature of a first preset observation point based on a first temperature image obtained by a dual-light camera when the mold is opened; determines whether the temperature of the die-casting process is abnormal based on the first temperature and the first preset temperature range;

[0033] Foreign body detection module: obtain a first foreign body-free template image based on the conditional diffusion model and the average temperature obtained by the first temperature; obtain a foreign body detection image based on the first foreign body-free template image and the first temperature image

[0034] A fourth aspect of the present invention provides a computer storage medium having executable instructions stored thereon, which, when executed by a processor, enables the processor to implement the above-mentioned mold temperature detection and mold foreign body detection method.

[0035] By adopting the above technical solution, the present invention has the following advantages:

[0036] 1. The present invention can detect the mold temperature and mold foreign matter when the mold is opened, ensuring that the mold works at a qualified temperature and without foreign matter, and has the advantages of improving product qualification rate, reducing costs and improving safety.

[0037] 2. The present invention can also detect the temperature of the mold after die-casting, which has the advantages of further improving product qualification rate, reducing costs and improving safety.

[0038] 3. The present invention can realize the status monitoring of die-casting, spraying and other process flows of die-casting machines, and automatically warn of abnormal production environments (temperature anomalies). At the same time, a foreign body template generation model guided by the temperature mean is designed, which effectively solves the false alarm problem of the existing foreign body detection algorithm based on comparison under complex working conditions such as frequent temperature fluctuations.

[0039] 4. The method of the present invention realizes the online detection of mold temperature and foreign matter, and the die-casting machine linkage can be realized based on the online detection.

[0040] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures pointed out in the description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0042] Figure 1 This is a flow chart of mold temperature detection in an embodiment of the present invention;

[0043] Figure 2 This is a flow chart of mold foreign matter detection in an embodiment of the present invention;

[0044] Figure 3 A schematic diagram of the structure of a mold temperature detection and foreign matter detection device in an embodiment of the present invention Figure 1 ;

[0045] Figure 4 A schematic diagram of the structure of a mold temperature detection and foreign matter detection device in an embodiment of the present invention Figure 2 ;

[0046] Figure 5 Schematic diagram of the arrangement of a mold temperature detection and foreign matter detection device in an embodiment of the present invention.

[0047] In the figure, 10-dual light camera, 101-electric actuator, 102-light source, 103-visible light lens, 104-visible light sensor, 105-infrared lens, 106-infrared sensor, 107-indicator laser, 108-main control board, 20-terminal, 201-algorithm processing unit, 202-timing control circuit, 30-die casting machine, 301-mold. DETAILED DESCRIPTION

[0048] The following description provides many different embodiments or examples for implementing different features of the present invention. The components and arrangements described in the following specific examples are only used to simplify the present invention and are only used as examples, not to limit the present invention.

[0049] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] This embodiment provides a method for detecting mold temperature and mold foreign matter, the method comprising the following steps:

[0051] Based on the first temperature image obtained when the mold is opened, the first temperature of the first preset observation point is obtained; based on the first temperature and the first preset temperature range, it is judged whether the temperature of the die-casting process is abnormal: if the absolute value of the difference between the second temperature and the first preset temperature is within the first preset range, it indicates that the temperature of the spraying process is normal; if the absolute value of the difference between the second temperature and the first preset temperature is not within the first preset range, it indicates that the spraying process is abnormal, and an early warning is issued.

[0052] Based on the second temperature image obtained after spraying, the second temperature of the second preset observation point is obtained; based on the second temperature and the first preset temperature, it is determined whether the temperature of the spraying process is abnormal: if the first temperature is within the first preset temperature range, it indicates that the temperature of the die-casting process is normal; if the first temperature is not within the first preset temperature range, it indicates that the temperature of the die-casting process is abnormal, and an early warning is issued.

[0053] More detailed, such as Figure 1 As shown, firstly, temperature calibration and temperature measurement point preset are performed, specifically, the first preset temperature range and the first preset temperature calibration, and the setting of the first preset observation point and the second preset observation point; then, a first temperature image is obtained when the die-casting machine opens the mold, and the first temperature located at the first preset observation point is obtained from the first temperature image; finally, a second temperature image is obtained after the die-casting machine is sprayed, and the second temperature located at the second preset observation point is obtained from the second temperature image.

[0054] Among them, the first preset observation point can be one or more. If multiple first preset observation points are set, multiple first temperatures will be obtained accordingly. Setting multiple first observation points has the effect of improving the accuracy of mold temperature detection; similarly, the second preset observation point can also be one or more. If multiple second preset observation points are set, multiple second temperatures will be obtained accordingly. Setting multiple second preset observation points improves the accuracy of mold temperature detection.

[0055] It should be understood that in order to detect the mold temperature, the temperature when the mold is opened can be detected when the mold is opened; or both the temperature when the mold is opened and the temperature after spraying can be detected, which can further improve the product qualification rate and improve safety.

[0056] It should be noted that the first temperature image and the second temperature image can be obtained by a dual-light camera. The dual-light camera is an existing product, and the image taken is a temperature map, and each pixel value of the temperature map is temperature information. As for the method of obtaining the temperature value from the temperature map, it can be obtained by using the existing technology for those skilled in the art, and it will not be described in detail here.

[0057] like Figure 2 As shown, a conditional diffusion model is first constructed, and the method for establishing the conditional diffusion model includes the following steps:

[0058] A conditional diffusion model is constructed based on an unlabeled mold opening temperature image dataset and a preset average temperature.

[0059] Exemplarily, (1) obtaining an unlabeled open mold temperature image dataset;

[0060] (2) Based on the mold opening temperature image data set, a conditional diffusion model is constructed to generate a foreign body-free template image with controllable mean;

[0061] First, a score model is constructed to generate a foreign body-free template map. The model training objectives are:

[0062]

[0063] in, The convolutional network constructed is used to simulate the inverse denoising process of stochastic differential equations; Indicates the data status at time t The probability density function of The logarithm of , which is the score function; are the convolutional network parameters to be optimized; is the time step in the diffusion process, Represents the data state at time step t, which is given by As time steps gradually diffuse, is the first temperature image when the mold is opened, is the gradient of the probability density function with respect to x(t).

[0064] Then, a conditional diffusion model is constructed, and by inputting a preset average temperature, the fractional model is guided to generate a foreign-matter-free template image whose temperature mean is also the preset average temperature.

[0065] A first foreign body-free template image is obtained based on the conditional diffusion model and the average temperature obtained by the first temperature; a foreign body detection image is obtained based on the first foreign body-free template image and the first temperature image. Specifically, the first foreign body-free template image with the temperature of the average temperature is generated by inputting the average temperature into the conditional diffusion model; based on the first foreign body-free template image and the first temperature image, a foreign body detection image is obtained by marking foreign bodies on the first temperature image; specifically, the foreign body detection image can be obtained by comparing the first foreign body-free template image with the first temperature image and marking foreign bodies on the first temperature image.

[0066] The generated first foreign body-free template image is obtained by acquiring the average temperature, thereby eliminating the influence of temperature on the generated first foreign body-free template image and improving the accuracy of foreign body detection.

[0067] In some embodiments, obtaining a foreign body detection image based on the first foreign body-free template image and the first temperature image may include the following steps:

[0068] The first temperature image is differentially compared with the first foreign body-free template image to extract a temperature difference image; then the temperature difference image is thresholded, binarized, morphologically processed, connected domain analyzed, and the foreign body area contour is extracted to obtain a foreign body detection image with foreign body markings.

[0069] In some embodiments, the acquired first temperature image and second temperature image may be preprocessed and enhanced first. By means of preprocessing steps such as noise removal, grayscale, and histogram equalization, the contrast and signal-to-noise ratio of the image may be improved, thereby highlighting the difference between the foreign matter in the first temperature image and the surface of the mold 301.

[0070] This embodiment also provides a mold temperature detection and foreign matter detection system, including:

[0071] Mold temperature detection module: obtains a first temperature of a first preset observation point based on a first temperature image obtained when the mold is opened; determines whether the temperature of the die-casting process is abnormal based on the first temperature and a first preset temperature range;

[0072] Foreign body detection module: obtains a first foreign body-free template image based on a conditional diffusion model and an average temperature obtained from the first temperature; and obtains a foreign body detection image based on the first foreign body-free template image and the first temperature image.

[0073] In some embodiments, the mold temperature detection module is also used to obtain a second temperature of a second preset observation point based on a second temperature image obtained after spraying; and determine whether the spraying process temperature is abnormal based on the second temperature and the first preset temperature.

[0074] This embodiment also provides a mold temperature detection and foreign matter detection device, such as Figure 3, Figure 4 As shown, including:

[0075] Dual-light camera 10: used to obtain a first temperature image when the mold is opened and a second temperature image after spraying;

[0076] Terminal 20: includes a timing control circuit 202 and an algorithm processing unit 201; the algorithm processing unit 201 includes a mold temperature detection module and a foreign matter detection module;

[0077] Mold temperature detection module: obtains a first temperature of a first preset observation point based on a first temperature image when the mold is opened acquired by the dual-light camera 10; determines whether the die-casting process temperature is abnormal based on the first temperature and the first preset temperature range;

[0078] Foreign body detection module: obtains a first foreign body-free template image based on a conditional diffusion model and an average temperature obtained from the first temperature; and obtains a foreign body detection image based on the first foreign body-free template image and the first temperature image.

[0079] Figure 4 In the figure, the dual-light camera 10 may include an electric actuator 101, a light source 102, a visible light lens 103, a visible light sensor 104, an infrared lens 105, an infrared sensor 106, an indication laser 107 and a main control board 108, and the first temperature image and the second temperature image are captured by the dual-light camera 10. The algorithm processing unit 201 of the dual-light camera 10 is connected through a timing control circuit 202, and the timing circuit controls the acquisition timing of the dual-light camera 10, and can transmit the first temperature image and the second temperature image acquired in the timing to the algorithm processing unit 201. It should be noted that the above only provides the specific structure of the dual-light camera 10, and the control program for the first temperature image and the second temperature image obtained by it is set in the main control board 108. Since it is a mature existing product and can be directly purchased and used, its control program will not be described in detail.

[0080] Figure 1 In the embodiment, the first temperature image and the second temperature image are captured cyclically, that is, the die-casting machine 30 is captured each time it works; the terminal 20 can also obtain the mold opening signal and the spraying signal of the die-casting machine 30, and control the dual-light camera 10 to capture the first temperature image and the second temperature image through the signal.

[0081] Figure 5 , a schematic diagram of the position of the foreign matter detection device when used on the die-casting machine 30 is shown. In the figure, dual-light cameras 10 are arranged at the four corners of the die 301 of the die-casting machine 30 to achieve comprehensive acquisition of the image of the die 301 (including the movable die and the fixed die) of the die-casting machine 30, avoiding local occlusion caused by the concave and convex surface of the die 301 of the die-casting machine 30.

[0082] This embodiment also provides a computer storage medium on which executable instructions are stored. When the instructions are executed by a processor, the processor implements the above-mentioned method.

[0083] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0084] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installation", "connection", and "connection" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, an electrical connection, or mutual communication; it can be a direct connection, or an indirect connection through an intermediate medium, it can be the internal connection of multiple components or the interaction relationship of multiple components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0085] In the description of the present invention, it should be understood that all terms used to indicate orientation or positional relationships are based on the orientation or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and should not be understood as a limitation on the present invention.

[0086] Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent substitutions for some of the technical features therein; and these modifications or substitutions do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for detecting mold temperature and mold foreign matter, characterized in that: The method comprises the following steps: Obtaining a first temperature of a first preset observation point based on a first temperature image acquired when the mold is opened; Based on the first temperature and the first preset temperature range, determining whether the temperature of the die-casting process is abnormal; A conditional diffusion model is constructed based on an unlabeled mold opening temperature image dataset and a preset average temperature; Obtaining a first foreign-matter-free template image based on the conditional diffusion model and the average temperature obtained by the first temperature; Based on the first foreign-matter-free template image and the first temperature image, foreign matter is marked on the first temperature image to obtain a foreign matter detection image.

2. A mold temperature detection and mold foreign body detection method according to claim 1, characterized in that: The method further comprises the steps of: Obtaining a second temperature of a second preset observation point based on a second temperature image acquired after spraying; Based on the second temperature and the first preset temperature, it is determined whether the temperature of the spraying process is abnormal.

3. A mold temperature detection and mold foreign body detection method according to claim 2, characterized in that: Based on the second temperature and the first preset temperature, determining whether the temperature of the spraying process is abnormal includes the following steps: If the absolute value of the difference between the second temperature and the first preset temperature is within the first preset range, it indicates that the temperature of the spraying process is normal; If the absolute value of the difference between the second temperature and the first preset temperature is not within the first preset range, it indicates that the spraying process is abnormal, and an early warning is issued.

4. A mold temperature detection and mold foreign body detection method according to any one of claims 1 to 3, characterized in that: Based on the first temperature and the first preset temperature range, determining whether the temperature of the die-casting process is abnormal includes the following steps: If the first temperature is within the first preset temperature range, it indicates that the temperature of the die-casting process is normal; If the first temperature is not within the first preset temperature range, it indicates that the temperature of the die-casting process is abnormal, and an early warning is issued.

5. The method for detecting mold temperature and mold foreign matter according to claim 1, characterized in that: Based on the first foreign-matter-free template image and the first temperature image, marking the foreign matter on the first temperature image to obtain the foreign matter detection image comprises the following steps: The first temperature image is differentially compared with the first foreign body-free template image to extract a temperature difference image; then the temperature difference image is thresholded, binarized, morphologically processed, connected domain analyzed, and the foreign body area contour is extracted to obtain a foreign body detection image with foreign body markings.

6. A mold temperature detection and foreign matter detection system, characterized in that: include: Mold temperature detection module: obtains a first temperature of a first preset observation point based on a first temperature image acquired when the mold is opened; Based on the first temperature and the first preset temperature range, determining whether the temperature of the die-casting process is abnormal; Conditional diffusion model building module: builds a conditional diffusion model based on an unlabeled mold opening temperature image dataset and a preset average temperature; Foreign body detection module: obtain a first foreign body-free template image based on the conditional diffusion model and the average temperature obtained by the first temperature; based on the first foreign body-free template image and the first temperature image, mark foreign bodies on the first temperature image to obtain a foreign body detection image.

7. A mold temperature detection and foreign matter detection system according to claim 6, characterized in that: Mold temperature detection module: also used to obtain the second temperature of the second preset observation point based on the second temperature image obtained after spraying; based on the second temperature and the first preset temperature, determine whether the temperature of the spraying process is abnormal.

8. A mold temperature detection and foreign matter detection device, characterized in that: include: Dual-light camera: used to obtain the first temperature image when the mold is opened and the second temperature image after spraying; Terminal: including a timing control circuit and an algorithm processing unit; the algorithm processing unit includes a mold temperature detection module and a foreign matter detection module; Mold temperature detection module: obtains a first temperature of a first preset observation point based on a first temperature image obtained by a dual-light camera when the mold is opened; determines whether the temperature of the die-casting process is abnormal based on the first temperature and the first preset temperature range; Conditional diffusion model building module: builds a conditional diffusion model based on an unlabeled mold opening temperature image dataset and a preset average temperature; Foreign body detection module: obtain a first foreign body-free template image based on the conditional diffusion model and the average temperature obtained by the first temperature; based on the first foreign body-free template image and the first temperature image, mark foreign bodies on the first temperature image to obtain a foreign body detection image.

9. A computer storage medium, characterized in that Executable instructions are stored thereon, and when the instructions are executed by the processor, the processor implements the mold temperature detection and mold foreign body detection method according to any one of claims 1 to 5.

Images