Casting tool identification method and equipment and storage medium

Abstract

The invention relates to the technical field of casting processes, in particular to a casting tool identification method and equipment and a storage medium, and aims to overcome the defects of high temperature and dust pollution in an existing casting process, the high temperature resistance of stainless steel is utilized, and array holes are formed in the stainless steel; holes in different permutation and combination are identified through a visual identification algorithm, so that identification and tracing of different tools are realized. And through binarization and opening and closing operation, the problem of misrecognition caused by light change of the environment where the tool is located and hole and color change of the stainless steel surface under the action of high-temperature recycling and dust is solved, so that process connection, tool recognition and tracing in the whole casting process flow are guaranteed on the whole, the working stability is guaranteed, and the production efficiency is improved. And the safety of the production environment is improved.

Description

Technical Field

[0001] The invention relates to the technical field of casting technology, in particular to a casting tool identification method, equipment and storage medium. Background Art

[0002] Casting is an indispensable and important link in the development of equipment manufacturing industry, and is widely used in machine tools, automobiles, instruments and meters, shipbuilding, aerospace and other fields. Casting is the process of pouring molten metal into a mold and cooling and solidifying it to obtain parts with the required shape and performance. Casting is a commonly used manufacturing method with low manufacturing cost and great process flexibility. It can obtain complex shapes and large castings, and occupies a large proportion in mechanical manufacturing.

[0003] like Figure 1 As shown, the casting process usually includes the steps of sand box out of the warehouse, upper and lower boxes, box assembling, sand mold storage and out of the warehouse, pouring and cooling out of the warehouse, and sand dropout. The process connection in each link relies on digital intelligence for unified scheduling and management. Even after the finished product, follow-up is required, which requires that each sand box can be identified and traced to ensure the one-to-one correspondence between different sand boxes and different processes without confusion. Generally, such requirements usually use RFID electronic tags or barcode unique identification as a means of identification and traceability, but this method is difficult to implement in the casting process flow in this field. The specific reasons are: First of all, the surface drying process of the tooling (sand boxes, molds, etc.) needs to stay in an environment of 200℃~300℃ for more than 5 minutes, while the operating temperature of the RFID tag electronic chip usually cannot exceed 85℃. Although there are high-temperature resistant RFID tags on the market, most of them are insulated by high-temperature resistant shells, and cannot withstand long-term continuous heating in the high-temperature casting environment.

[0004] Secondly, during the pouring process of the tooling (sand box, pouring base, etc.), after the molten steel (iron) at more than 1000℃ is poured into the sand box, the heat conduction effect causes the RFID tag to experience a higher temperature test, and even the molten iron leaks and the surface burns. At this time, both the RFID tag and the barcode tag will inevitably be fatally damaged. Even if the cooling warehouse is multi-layered, the sand mold will still reach a very high temperature after entering the cooling warehouse (usually 400℃~500℃). In addition, the heat from the lower layer rises upward, which is also the reason for the damage to the RFID chip.

[0005] In order to solve this problem, there is also a method of using laser to engrave QR codes and DotCode dot matrix code graphics on the stainless steel of the tooling to solve the problem of high temperature resistance. The use of stainless steel can solve the problem of high temperature resistance, but the environment in the foundry is extremely harsh, and the dust caused by sand as a raw material is very heavy, which is very easy to stain on any tooling surface and thus pollute the laser engraving. That is, long-term turnover and recycling in harsh environments will still cause surface stains and color changes. Therefore, it is impossible to achieve industrial-level reliability in actual operations.

[0006] It can be seen that the traditional method of adding RFID identification tags and laser engraving cannot adapt to the special working environment such as high temperature and high dust in the casting environment, which has caused great troubles for process connection identification and finished product traceability in the casting process. For the casting field, it is impossible to guarantee the smooth progress of the process and the quality of the finished product, which in turn pushes up the production cost and process complexity. In addition, manual intervention is bound to be required in the process to eliminate the above problems to ensure the smooth progress of the process, which also increases the occurrence of safety hazards to a certain extent.

[0007] Based on the above reasons, the present invention designs a casting tool identification method, equipment and storage medium. By arranging holes on the surface of the cast workpiece to form a BCD code, and then reading it through an image recognition method, the cast workpiece can be effectively identified and traced. In addition, since the stainless steel holes on the workpiece surface are resistant to high temperature and dust, the effectiveness and durability of the label are greatly improved, which helps the normal and orderly casting process, improves production efficiency to a certain extent, and reduces potential safety risks. Summary of the invention

[0008] The purpose of the present invention is to overcome the shortcomings of the prior art and provide a casting tool identification method, equipment and storage medium. By arranging holes on the surface of the cast workpiece to form a BCD code, and then reading it through an image recognition method, the cast workpiece can be effectively identified and traced. In addition, since the stainless steel holes on the surface of the workpiece are resistant to high temperature and dust, the effectiveness and durability of the label are greatly improved, which helps the normal and orderly casting process, improves production efficiency to a certain extent, and reduces potential safety risks.

[0009] The present invention provides a casting tool identification method, comprising the following steps: S1, installing a stainless steel sheet as an identification tag on a casting tool, setting a circular hole array on the sheet, the hole array consisting of n rows and m columns, forming a BCD code with the hole array and the non-hole area on the sheet, in which the area with holes on the sheet is set to 1, and the area without holes is set to 0; S2, digging three square holes around the hole array on the sheet for positioning before identifying the label information; S3, image recognition, including: S3-1, image acquisition: using a webcam to take a photo of the identification tag to obtain a digital image; S3-2, preset cropping range: crop the area to be identified from the original image collected in S1-1, which can reduce the amount of calculation after cropping. The identification label is within this preset cropping range; S3-3, grayscale: decolorize the image cropped in S3-2 to obtain a grayscale image; S3-4, noise reduction: using the Gaussian blur method to perform noise reduction on the black and white image obtained in S3-3 to obtain a smooth image; S3-5, Binarization: Use fixed threshold and adaptive threshold binarization to process black and white images under different lighting conditions; S3-6, opening and closing operation: performing corrosion and expansion operations on the black and white image processed by S3-5 to remove small black spots and white spots inside holes; S3-7, edge detection: extract the edges, positions and other information of the circular holes and square holes in the image obtained by S3-6; S3-7, positioning: filtering and identifying the three square holes to obtain the position of the central circular hole array; S3-8, recognition: determine whether each unit in the hole array has a circular hole, and obtain the final recognition result.

[0010] The specific steps of S3-5 include: using image histogram calculation and analysis, using 3 to 5 different thresholds combined with fixed thresholds and adaptive thresholds to make multiple attempts.

[0011] The diameter of the circular holes in the hole array is 4 mm to 6 mm.

[0012] The side lengths of the three square holes are 4 mm to 6 mm.

[0013] The parameters of all operators in S3 are configured in different combinations. Different configurations are preset during on-site debugging and the success rates are recorded and counted during operation, which are used to prioritize the configurations used according to the success rates.

[0014] An electronic device comprises a processor and a memory storing a program, wherein the program comprises instructions, and when the instructions are executed by the processor, the processor executes a method of step S3 in a casting tool identification method.

[0015] The electronic device includes an APP, which provides a visual interface to simulate the identification tag, and is used to judge and correct abnormal hole arrays by directly clicking on the holes on the visual interface.

[0016] A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute a method of step S3 in a casting tool identification method.

[0017] Compared with the prior art, the present invention is based on the shortcomings of the existing casting process in terms of high temperature and dust pollution, and utilizes the high temperature resistance of stainless steel, and sets array holes on stainless steel, and uses a visual recognition algorithm to identify holes of different arrangements and combinations, thereby achieving the problem of identification and tracing of different tooling. In the image binarization step, with the help of the calculation and analysis of the image histogram, the threshold can be adaptively adjusted according to different lighting conditions such as day and night, and a combination of multiple fixed thresholds and adaptive threshold calculation methods is used and multiple attempts are made. The robustness of the algorithm is greatly improved, which ensures the process connection, tooling identification and tracing in the entire casting process as a whole, ensures the stability of the work, and improves the safety of the production environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a schematic diagram of the process flow of existing tooling casting in the background technology of the present invention.

[0019] Figure 2 This is a physical schematic diagram of the identification label of the present invention.

[0020] Figure 3 This is a schematic diagram of the label of the present invention when the light is insufficient.

[0021] Figure 4 This is a schematic diagram of the label of the present invention under the influence of dust and high temperature.

[0022] Figure 5 It is a schematic diagram showing images of the identification steps of the present invention.

[0023] Figure 6 It is a schematic diagram of the system deployment architecture of the present invention.

[0024] Figure 7 It is a schematic diagram of the algorithm flow of the present invention.

[0025] Figure 8 It is a schematic diagram of the exception handling APP end of the present invention. DETAILED DESCRIPTION

[0026] The present invention will now be further described with reference to the accompanying drawings.

[0027] See also Figures 1 to 8 The present invention provides a casting tool identification method, which is controlled by a graphics workstation and controls multiple industrial cameras through a network switch to realize the system architecture of the present invention (such as Figure 6 As shown), the method comprises the following steps (as Figure 7 shown): S1, installing a stainless steel sheet as an identification tag on a casting tool, setting a circular hole array on the sheet, the hole array consisting of n rows and m columns, forming a BCD code with the hole array and the non-hole area on the sheet, in which the area with holes on the sheet is set to 1, and the area without holes is set to 0; For example Figure 2 As shown, on the left is a 3-row 4-column hole array that can represent 3×4 binary bits of information. If all the holes are dug, it represents the hexadecimal number FFF.

[0028] S2, digging three square holes around the hole array on the sheet for positioning before identifying the label information; S3, such as Figure 5 , Figure 7 The schematic diagram of each image in the recognition step shown includes: S3-1, image acquisition: use a network camera to take a photo of the identification tag to obtain a digital image, the image here is the original image; S3-2, preset cropping range: crop the area to be identified from the original image collected in S1-1, which can reduce the amount of calculation after cropping. The identification tag is within this preset cropping range to obtain the BCD code original image; S3-3, grayscale: decolorize the image cropped in S3-2 to obtain a BCD grayscale image; S3-4, noise reduction: using the Gaussian blur method to perform noise reduction on the black and white image obtained in S3-3, so as to obtain a smooth BCD code image after removing part of the noise; S3-5, Binarization: Figure 3 As shown in the figure, since the foundry operates 24 hours a day, the ambient light brightness is different during the day and at night, so the image recognition algorithm needs to automatically adapt to different light brightness. Therefore, fixed threshold and adaptive threshold binarization are used to process black and white images under different lighting conditions, extract black hole information and output black and white images; S3-6, opening and closing operation: Figure 4 As shown in the figure, due to the repeated use of identification tags in the harsh factory environment (high temperature, dust), the surface will change, requiring the recognition algorithm to be highly robust. Therefore, the black and white image processed by S3-5 is eroded and expanded to remove small black spots and white spots inside the holes. S3-7, edge detection: extract the edges, positions and other information of the circular holes and square holes in the image obtained by S3-6; S3-7, positioning: filter and identify the three square holes, obtain the position of the central circular hole array, and use it to make necessary affine transformation; S3-8, identification: determine whether each unit in the hole array has a circular hole to obtain a BCD code and obtain the final identification result.

[0029] The specific steps of S3-5 include: using image histogram calculation and analysis, using 3 to 5 different thresholds combined with fixed thresholds and adaptive thresholds to make multiple attempts.

[0030] The diameter of the circular holes in the hole array is 4 mm to 6 mm, so that the holes are not easily blocked by debris.

[0031] The side lengths of the three square holes are 4 mm to 6 mm. The square holes serve as positioning information coding elements, have the function of positioning, and enable the label to be accurately identified even after the tooling is turned upside down.

[0032] The parameters of all operators in S3 are configured in different combinations. Different configurations are preset during on-site debugging and the success rate is recorded and counted during operation. This is a self-learning method, that is, based on the histogram data statistics of the cropped image, the parameter combination and priority with the highest success rate are intelligently adopted, which is used to prioritize the configurations used according to the success rate in the future, thereby reducing the number of attempts, saving recognition time, and improving the recognition rate.

[0033] An electronic device comprises a processor and a memory storing a program, wherein the program comprises instructions, and when the instructions are executed by the processor, the processor executes a method of step S3 in a casting tool identification method.

[0034] like Figure 8 As shown, the electronic device includes an APP, which provides a visual interface to simulate the identification tag, and is used to judge and correct abnormal hole arrays by directly clicking on the holes on the visual interface.

[0035] A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute a method of step S3 in a casting tool identification method.

[0036] The above are only preferred embodiments of the present invention, which are only used to help understand the method and core ideas of the present application. The protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

[0037] The present invention solves the problems in the existing foundry industry that RFID cannot be used because the chip integrated circuit is not resistant to high temperatures, and the metal two-dimensional code is difficult to avoid surface stains in a high-dust environment, so that the recognition rate does not meet the industrial-grade requirements, which in turn affects production efficiency and potential safety hazards. The present invention forms a BCD code by arranging various holes on the surface of the cast workpiece, and then reads it through an image recognition method, so that the cast workpiece can be effectively identified and traced. The stainless steel perforated on the surface of the workpiece makes it more resistant to high temperatures and impacts. The introduction of binarization and opening and closing operations in the algorithm reduces the interference of dust and debris on the identified image, greatly improving the effectiveness and durability of the label. The present invention helps the normal and orderly casting process as a whole, and also improves production efficiency to a certain extent, and reduces potential safety risks.

Claims

1. A method for identifying casting tooling, characterized in that: The following steps are involved: S1, installing a stainless steel sheet as an identification tag on a casting tool, wherein a circular hole array is arranged on the sheet, wherein the hole array consists of n rows and m columns, and the hole array and the non-hole-dug area on the sheet are formed into a BCD code, wherein the area with holes on the sheet is set to 1, and the area without holes is set to 0; S2, digging three square holes around the hole array on the sheet for positioning before identifying the label information; S3, image recognition, including: S3-1, collecting images: using a network camera to take a photo of the identification tag to obtain a digital image; S3-2, preset cropping range: cropping the area to be identified from the original image collected in S1-1, so as to reduce the amount of calculation after cropping, and the identification label is within the preset cropping range; S3-3, grayscale: decolorize the image cropped in S3-2 to obtain a grayscale image; S3-4, noise reduction: using a Gaussian blur method to perform noise reduction on the black and white image obtained in S3-3 to obtain a smooth image; S3-5, Binarization: Use fixed threshold and adaptive threshold binarization to process black and white images under different lighting conditions; S3-6, opening and closing operation: performing corrosion and expansion operations on the black and white image processed by S3-5 to remove small black spots and white spots inside holes; S3-7, edge detection: extracting the edges, positions and other information of the circular holes and square holes in the image obtained in S3-6; S3-7, positioning: filtering and identifying the three square holes to obtain the position of the central circular hole array; S3-8, recognition: determine whether each unit in the hole array has a circular hole, and obtain the final recognition result.

2. The casting tool identification method according to claim 1, characterized in that: The specific steps of S3-5 include: using image histogram calculation and analysis, using 3 to 5 different thresholds combined with fixed thresholds and adaptive thresholds to make multiple attempts.

3. The casting tool identification method according to claim 1, characterized in that: The diameter of the circular holes in the hole array is 4 mm to 6 mm.

4. The casting tool identification method according to claim 1, characterized in that: The side lengths of the three square holes are 4 mm to 6 mm.

5. The casting tool identification method according to claim 1, characterized in that: The parameters of all operators in S3 are configured in different combinations. Different configurations are preset during on-site debugging and the success rates are recorded and counted during operation, which are used to prioritize the configurations used according to the success rates.

6. An electronic device, characterized in that: The method comprises a processor and a memory storing a program, wherein the program comprises instructions, and when the instructions are executed by the processor, the processor is caused to perform the method according to step S3 of claim 1.

7. The electronic device according to claim 6, characterized in that: The electronic device includes an APP, which provides a visual interface to simulate the identification tag, and is used to judge and correct abnormal hole arrays by directly clicking holes on the visual interface.

8. A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the method of step S3 in claim 1.

Images