Intelligent mold temperature compensation control method and system based on image recognition

Abstract

The invention provides a mold temperature intelligent compensation control method and system based on image recognition, and the method comprises the steps: carrying out the real-time image collection of the surface of a mold based on an infrared thermal imager, obtaining an infrared thermal image of the surface of the mold, and carrying out the graying processing of the infrared thermal image, and obtaining a gray image; carrying out region segmentation on the grayscale image based on a grayscale value corresponding to a preset normal working temperature of the mold to obtain a temperature abnormal region; determining a mold temperature value of the temperature abnormal area, and comparing the mold temperature value with a preset standard working temperature value of the mold to obtain a temperature deviation value; and a compensation control instruction is generated based on the temperature deviation value, heating or cooling adjustment is conducted on the mold based on the compensation control instruction, and intelligent compensation control over the mold temperature of the mold is achieved. According to the invention, when the temperature of the mold fluctuates abnormally, a response can be made quickly, compensation control can be carried out timely and accurately, and the quality and production efficiency of a molded product of the mold are effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to an image recognition-based intelligent compensation control method for a mold temperature and a system thereof. Background Art

[0002] Existing mold temperature compensation control methods mostly rely on temperature sensors to collect data for feedback control. However, this approach has significant drawbacks: temperature sensors can only obtain temperature information at a local point and cannot fully reflect the temperature distribution on the mold surface. Furthermore, there is a certain delay in data collection and transmission, resulting in a delayed response to changes in the mold's overall temperature. This makes it difficult to provide timely and accurate compensation control when abnormal mold temperature fluctuations occur, thus affecting the quality and production efficiency of molded products. Summary of the Invention

[0003] The present invention provides a mold temperature intelligent compensation control method and system based on image recognition, which are used to improve the quality and production efficiency of molded products.

[0004] In a first aspect, the present invention provides a mold temperature intelligent compensation control method based on image recognition, comprising:

[0005] Performing real-time image acquisition of the mold surface using an infrared thermal imager to obtain an infrared thermal image of the mold surface, and gray-processing the infrared thermal image to obtain a grayscale image;

[0006] Segmenting the grayscale image based on grayscale values corresponding to a preset normal working temperature of the mold to obtain temperature abnormality areas;

[0007] Determining a mold temperature value of the mold in the temperature abnormality area, and obtaining a temperature deviation value based on comparing the mold temperature value with a preset standard operating temperature value of the mold;

[0008] A compensation control instruction is generated based on the temperature deviation value, and the mold is heated or cooled based on the compensation control instruction to achieve intelligent compensation control of the mold temperature.

[0009] In a second aspect, the present invention further provides an intelligent mold temperature compensation control system based on image recognition, which is applied to the intelligent mold temperature compensation control method based on image recognition as described in the first aspect; the intelligent mold temperature compensation control system based on image recognition includes:

[0010] An image acquisition module is used to acquire real-time images of the mold surface using an infrared thermal imager, obtain an infrared thermal image of the mold surface, and grayscale the infrared thermal image to obtain a grayscale image;

[0011] A region segmentation module is used to segment the grayscale image into regions based on grayscale values corresponding to a preset normal working temperature of the mold to obtain temperature abnormality regions;

[0012] a temperature comparison module, configured to determine a mold temperature value of the mold in the temperature abnormality area, and compare the mold temperature value with a preset standard operating temperature value of the mold to obtain a temperature deviation value;

[0013] The compensation control module is used to generate a compensation control instruction based on the temperature deviation value, and to heat or cool the mold based on the compensation control instruction to achieve intelligent compensation control of the mold temperature.

[0014] In a third aspect, the present invention further provides an electronic device comprising: a memory for storing a computer software program; and a processor for reading and executing the computer software program, thereby implementing any one of the above-described intelligent compensation control methods for mold temperature based on image recognition.

[0015] In a fourth aspect, the present invention further provides a non-transitory computer-readable storage medium, in which a computer software program is stored. When the computer software program is executed by a processor, it implements any of the above-mentioned intelligent compensation control methods for mold temperature based on image recognition.

[0016] In a fifth aspect, the present invention further provides a computer program product, comprising a computer program, which, when executed by a processor, implements any of the above-described intelligent mold temperature compensation control methods based on image recognition.

[0017] The intelligent compensation control method for mold temperature based on image recognition provided by the embodiment of the present invention can obtain the overall temperature distribution image of the mold surface through an infrared thermal imager, avoiding the limitation that the temperature sensor can only obtain local point temperature information. During the image analysis and processing process, it can quickly and accurately identify the temperature abnormal area and calculate the temperature deviation value, which greatly improves the response speed compared with the delay of data acquisition and transmission in traditional methods. It can generate and execute compensation control instructions in time according to the temperature deviation value calculated in real time to achieve precise adjustment of the mold temperature. Therefore, by continuously looping and executing each step, the mold temperature can be monitored and adjusted in real time, and a quick response can be made when the mold temperature fluctuates abnormally, and compensation control can be carried out in a timely and accurate manner, effectively improving the quality and production efficiency of molded products. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 1 is a flow chart of a method for intelligent compensation control of mold temperature based on image recognition provided by an embodiment of the present invention;

[0019] Figure 2Schematic diagram of the structure of the mold temperature intelligent compensation control system based on image recognition provided by an embodiment of the present invention;

[0020] Figure 3 An embodiment diagram of an electronic device provided by an embodiment of the present invention;

[0021] Figure 4 An embodiment diagram of a computer-readable storage medium provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0022] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only 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 those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0023] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the specified features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0024] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration, or illustration." Any embodiment of the present invention described as "for example" is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that one of ordinary skill in the art will recognize that the present invention can be implemented without using these specific details. In other instances, well-known structures and processes are not described in detail to avoid obscuring the description of the present invention with unnecessary detail.

[0025] Thus, the present invention is not intended to be limited to the embodiments shown but is to be accorded the widest scope consistent with the principles and features disclosed herein.

[0026] Optional, see Figure 1 , Figure 1 The figure is a flow chart of the intelligent compensation control method for mold temperature based on image recognition provided by the present invention. In the embodiment of the present invention, the execution subject of the intelligent compensation control method for mold temperature based on image recognition is the compensation control system. Therefore, the intelligent compensation control method for mold temperature based on image recognition includes:

[0027] Step 10: Real-time image acquisition of the mold surface is performed using an infrared thermal imager to obtain an infrared thermal image of the mold surface, and the infrared thermal image is grayscaled to obtain a grayscale image.

[0028] Optionally, during the mold production process, the compensation control system controls the infrared thermal imager to capture real-time images of the mold surface. The infrared thermal imager detects the infrared radiation energy on the surface of the object, converts it into an electrical signal, and then converts it into a visual infrared thermal image through a series of processing. The infrared thermal image reflects the temperature distribution at different positions on the mold surface.

[0029] Since infrared thermal images are usually color images, for the convenience and efficiency of subsequent processing, the compensation control system performs grayscale processing on the acquired infrared thermal images. Grayscale processing converts the RGB value of each pixel in the color image into a grayscale value so that the image only presents different grayscale levels from black to white, eliminating the interference of color information on subsequent temperature analysis, and thus obtaining a grayscale image.

[0030] In one embodiment, taking the production of automobile injection molds as an example, the compensation control system activates an infrared thermal imager installed above the mold, which captures images of the mold surface at a frequency of 10 frames per second. During a production process, the infrared thermal imager obtains a color infrared thermal image of the mold surface. In the image, the gate of the mold appears red (indicating a high-temperature area) and the parting surface appears blue (indicating a low-temperature area). The compensation control system grayscales the color infrared thermal image using a built-in image processing algorithm. For example, a weighted average method is used to calculate the RGB value of each pixel according to a certain weight (such as R: 0.299, G: 0.587, B: 0.114) to obtain the corresponding grayscale value, and finally converts the color image into a grayscale image. Different grayscale values in the grayscale image correspond to different temperature areas on the mold surface.

[0031] Step 20 : Segment the grayscale image into regions based on the grayscale value corresponding to the preset normal working temperature of the mold to obtain temperature abnormality regions.

[0032] Furthermore, the normal operating temperature range of the mold and the corresponding grayscale value range are pre-set. Therefore, after obtaining the grayscale image, the compensation control system traverses each pixel in the image and compares the grayscale value of each pixel with the grayscale value range corresponding to the preset normal operating temperature.

[0033] If the grayscale value of a pixel exceeds the preset range, the area where the pixel is located is determined to be a temperature abnormality area. Therefore, the compensation control system can divide the grayscale image into normal temperature areas and temperature abnormality areas, and accurately identify the areas on the mold surface where temperature abnormalities exist.

[0034] Continuing with the above embodiment, the normal operating temperature range of the mold is pre-set to 80°C-120°C, and the corresponding grayscale value range is 50-200. When processing the grayscale image, the grayscale value of each pixel is checked one by one. It was found that in an area on the left side of the mold, the grayscale value of multiple pixels was 30, which was significantly lower than the preset grayscale value lower limit of 50. Therefore, the compensation control system determined this area as a temperature abnormality area (low temperature area); at the same time, the grayscale value of the pixels in some areas on the right side of the mold reached 220, which was higher than the preset grayscale value upper limit of 200. This area was also determined to be a temperature abnormality area (high temperature area). Through such area segmentation, the compensation control system clearly determined the specific location and range of the abnormal temperature on the mold surface.

[0035] Step 30 : determining the mold temperature value of the temperature abnormality area, and comparing the mold temperature value with a preset standard operating temperature value of the mold to obtain a temperature deviation value.

[0036] Furthermore, the compensation control system determines the mold temperature value according to the position of the temperature abnormality region in the grayscale image and the grayscale value in the temperature abnormality region, as specifically described in steps 301 to 304 .

[0037] Furthermore, the compensation control system compares the mold temperature value with the standard operating temperature value preset for the mold, and subtracts the standard operating temperature value from the mold temperature value to obtain a temperature deviation value, wherein the temperature deviation value reflects the difference between the actual temperature of the mold and the ideal operating temperature. Continuing with the above embodiment, the compensation control system calculates the mold temperature value of the low-temperature abnormal area on the left to be 70°C. The lower limit of the standard operating temperature preset for the mold is 80°C. By calculating 70°C-80°C=-10°C, the temperature deviation value of the low-temperature area is obtained to be -10°C. For the high-temperature abnormal area on the right, its mold temperature is calculated to be 130°C. Compared with the upper limit of the standard operating temperature of 120°C, the temperature deviation value is obtained to be 130°C-120°C=10°C.

[0038] Step 40 : generating a compensation control instruction based on the temperature deviation value, and performing heating or cooling adjustment on the mold based on the compensation control instruction to implement intelligent compensation control of the mold temperature.

[0039] Furthermore, the compensation control system generates corresponding compensation control instructions based on the temperature deviation value and a preset control strategy. If the temperature deviation value is negative, meaning the actual mold temperature is lower than the standard operating temperature, a heating control instruction is generated to control the heating device (such as an electric heating rod or heating coil) to heat the mold. If the temperature deviation value is positive, meaning the actual mold temperature is higher than the standard operating temperature, a cooling control instruction is generated to control the cooling device (such as a water cooling system or air cooling system) to cool the mold. Furthermore, the compensation control system achieves intelligent regulation of the mold temperature by precisely controlling the operating intensity and duration of the heating or cooling device, gradually bringing the mold temperature closer to the standard operating temperature.

[0040] Continuing with the above embodiment, for the low-temperature area on the left, since the temperature deviation value is -10°C, the compensation control system generates a heating control instruction, controls the power of the electric heating rod installed inside the mold to increase to 80% of the maximum power, and continues heating for 10 minutes. At the same time, the temperature changes in this area are monitored in real time. When the temperature reaches 80°C, the power of the electric heating rod is reduced to a level that maintains temperature stability. For the high-temperature area on the right, because the temperature deviation value is 10°C, the compensation control system generates a cooling control instruction, starts the water cooling system of the mold, increases the flow rate of cooling water, and allows the cooling water to take away the heat of the mold at a faster rate. After a period of cooling, when the temperature in this area drops to 120°C, the flow rate of the water cooling system is adjusted to keep the mold temperature stable within the standard operating temperature range, thereby realizing intelligent compensation control of the mold temperature, ensuring that the mold works under normal temperature conditions, and improving product quality and production efficiency.

[0041] The embodiment of the present invention can obtain the overall temperature distribution image of the mold surface through the infrared thermal imager, avoiding the limitation of the temperature sensor that can only obtain local point temperature information. During the image analysis and processing process, it can quickly and accurately identify the temperature abnormal area and calculate the temperature deviation value, thereby improving the response speed. It can timely generate and execute compensation control instructions based on the temperature deviation value calculated in real time to achieve precise adjustment of the mold temperature. Therefore, by continuously looping through each step, the mold temperature can be monitored and adjusted in real time, and a rapid response can be made when the mold temperature fluctuates abnormally, and compensation control can be carried out in a timely and accurate manner, effectively improving the quality and production efficiency of molded products.

[0042] In one embodiment, the descriptions of steps 301 to 304 are as follows:

[0043] Step 301: divide the grayscale image into quadrants to obtain four quadrants and a central area. The four quadrants include a first quadrant, a second quadrant, a third quadrant, and a fourth quadrant. The first quadrant represents the upper left area, the second quadrant represents the upper right area, the third quadrant represents the lower left area, and the fourth quadrant represents the lower right area.

[0044] Optionally, the compensation control system uses the geometric center of the grayscale image as the coordinate origin and divides the grayscale image equally in the horizontal and vertical directions to form four quadrant areas and a central area. The first quadrant area is located in the upper left part of the image, the second quadrant area is in the upper right part, the third quadrant area is in the lower left part, and the fourth quadrant area is in the lower right part. The central area is the portion in the middle of the image that is not divided into quadrants.

[0045] Continuing with the example of a grayscale image of an automotive injection mold, the image size is 800*600 pixels. The image's center coordinates are calculated as (400, 300). Using these coordinates as a reference, the image is then divided horizontally from 0-400 pixels into the left half and 400-800 pixels into the right half. Vertically, the image is divided from 0-300 pixels into the upper half and 300-600 pixels into the lower half. This results in four quadrants: the first quadrant is the upper left region between pixel coordinates (0, 0) and (400, 300); the second quadrant is the upper right region between (400, 0) and (800, 300); the third quadrant is the lower left region between (0, 300) and (400, 600); and the fourth quadrant is the lower right region between (400, 300) and (800, 600). Meanwhile, the central area is an area centered at (400, 300) within a certain range (eg, 350-450 pixels, 250-350 pixels).

[0046] Step 302 : Based on position mapping of the temperature abnormality region in the grayscale image, a position region corresponding to the temperature abnormality region in the grayscale image is determined.

[0047] Furthermore, the compensation control system maps the determined temperature abnormality area to the grayscale image based on its actual position on the mold surface. Specifically, through the pre-established correspondence between the mold surface coordinates and the grayscale image pixel coordinates, the coordinate information of the temperature abnormality area on the mold surface is converted into the pixel coordinate range in the grayscale image, and the corresponding position area of the temperature abnormality area in the grayscale image is determined.

[0048] Continuing with the automobile injection mold embodiment, it is known that the coordinate range of the determined low-temperature abnormal area on the left side of the mold surface is (100mm, 150mm)-(200mm, 250mm). The compensation control system pre-establishes a mapping relationship between the mold surface size and the grayscale image pixels. For example, 1mm of the mold surface corresponds to 5 pixels of the grayscale image. Then, by calculation, the pixel coordinate range of the low-temperature abnormal area in the grayscale image is (500, 750)-(1000, 1250). Since the grayscale image size is 800*600 pixels, the excess part is intercepted, and it is finally determined that the position area corresponding to the low-temperature abnormal area in the grayscale image is the part that intersects with the grayscale image, that is, it is in the lower right area of the image (part of the fourth quadrant area); similarly, the high-temperature abnormal area on the right side is also determined by similar mapping to determine its position area in the grayscale image.

[0049] Step 303: Determine a target grayscale value for the temperature abnormality area based on the location area and the grayscale value within the location area.

[0050] Furthermore, the compensation control system determines the target grayscale value of the temperature abnormality area based on the position area and the grayscale value within the position area, as specifically described in steps 3031 to 30319 .

[0051] Step 304 : Perform temperature conversion based on the target grayscale value to obtain the mold temperature value.

[0052] Furthermore, the compensation control system utilizes a temperature-to-grayscale conversion model based on support vector regression (SVR) to convert the target grayscale value into the mold temperature. Support vector regression is a supervised learning algorithm that uses training data from a large number of samples of known temperatures and corresponding grayscale values to construct a regression model that accurately reflects the relationship between the two. When a target grayscale value is input, the model calculates the corresponding mold temperature value through a complex nonlinear mapping relationship.

[0053] In one embodiment, the compensation control system pre-collects a large amount of grayscale value data at different temperatures of the automobile injection mold as training samples to train a support vector regression model. For the target grayscale value 215 determined for the high temperature abnormal area on the right, it is input into the trained SVR model. The model uses an internal kernel function (such as the radial basis kernel function K(x i ,x j )=exp(-γ||x i -x j || 2 ), where γ is the kernel function parameter) and an optimization algorithm (such as the sequential minimum optimization algorithm (SMO) perform complex calculations, and ultimately output the mold temperature value corresponding to this area as 132°C. Similarly, the target grayscale value of the low-temperature abnormal area on the left is calculated by the model, and the mold temperature value is 68°C.

[0054] The embodiment of the present invention can accurately locate the position of the abnormal area in the image through quadrant division and position mapping. The temperature conversion model based on support vector regression uses complex nonlinear relationships to achieve high-precision conversion from grayscale values to mold temperature values, providing an accurate temperature data basis for subsequent mold heating or cooling adjustment based on temperature deviation values, thereby improving the accuracy and reliability of intelligent compensation control of mold temperature, thereby effectively improving the quality and production efficiency of molded products.

[0055] In one embodiment, steps 3031 to 3034 are described as follows:

[0056] Step 3031: If the location area is the first quadrant area, obtain the maximum grayscale value and the minimum grayscale value in the location area, as well as the first number of maximum grayscale values and the second number of minimum grayscale values.

[0057] Optionally, the compensation control system determines whether the position area corresponding to the temperature abnormality area in the grayscale image is the first quadrant area.

[0058] Furthermore, if the area is the first quadrant, the compensation control system traverses all pixels within the location area and records the grayscale value of each pixel. By comparing all grayscale values, the maximum grayscale value is found as the maximum grayscale value, and the minimum grayscale value is found as the minimum grayscale value. Simultaneously, the compensation control system counts the number of times the maximum grayscale value and the minimum grayscale value appear within the location area, recording these as the first number and the second number, respectively.

[0059] Continuing with the automotive injection mold embodiment, for example, the location corresponding to the temperature anomaly region determined in step 302 is located in the first quadrant of the grayscale image, which contains 100 pixels. The compensation control system traverses these 100 pixels, recording the grayscale value of each pixel. After comparison, it is found that the maximum grayscale value is 230 and the minimum grayscale value is 180. Further statistics show that there are 15 pixels with a grayscale value of 230, i.e., the first number is 15; there are 10 pixels with a grayscale value of 180, i.e., the second number is 10.

[0060] Step 3032: Acquire a first number of first target grayscale values between the first grayscale value and the maximum grayscale value. The first grayscale value is three quarters of the maximum grayscale value.

[0061] Furthermore, the compensation control system calculates the first grayscale value, which is three-quarters of the maximum grayscale value, and obtains a number of values equal to the first number as the first target grayscale value within the range formed by the first grayscale value and the maximum grayscale value through a specific value generation algorithm. In this embodiment of the present invention, a value generation method based on a chaotic map is used to generate uniformly distributed values within a specified interval by utilizing the randomness and ergodicity of the chaotic system. The chaotic map formula can adopt a Logistic map: n+1 =μx n (1-x n ), where μ is the control parameter (the range of value is between 3.5699456-4, 3.8 can be selected), x n The current iteration value, the initial value x0 can be randomly selected between (0, 1). By iteratively calculating the Logistic map, the result is mapped to the interval between the first grayscale value and the maximum grayscale value to obtain the first target grayscale value.

[0062] Continuing with the automotive injection mold example above, given a maximum grayscale value of 230, the first grayscale value is 230*(3 / 4)=172.5. The compensation control system uses logistic mapping to generate the first target grayscale value, setting the initial value x0=0.3. Through multiple iterative calculations, the calculated results are mapped to the interval [172.5, 230], ultimately obtaining 15 first target grayscale values, such as 185, 192, and 200.

[0063] Step 3033: Acquire a second number of second target grayscale values between the minimum grayscale value and the second grayscale value range. The second grayscale value is an average of the maximum grayscale value and the minimum grayscale value.

[0064] Furthermore, the compensation control system calculates the second grayscale value, i.e., the average of the maximum grayscale value and the minimum grayscale value, and within the range determined by the minimum grayscale value and the second grayscale value, also uses a value generation method based on chaotic mapping (such as Logistic mapping) to obtain a number of values equal to the second number as the second target grayscale value.

[0065] Continuing with the automotive injection mold example, the maximum grayscale value is 230 and the minimum grayscale value is 180, so the second grayscale value is (230 + 180) / 2 = 205. The compensation control system uses an initial value x0 = 0.5 (which can be randomly selected) and uses a logistic map to perform iterative calculations within the interval [180, 205]. The results are mapped to this interval, ultimately obtaining 10 second target grayscale values, such as 188, 195, and 200.

[0066] Step 3034 , performing mean calculation based on the first number of first target grayscale values and the second number of second target grayscale values to obtain the target grayscale value of the temperature abnormality area.

[0067] Furthermore, the compensation control system summarizes the first target grayscale values of the first quantity and the second target grayscale values of the second quantity obtained. Then, the arithmetic mean of all the summarized target grayscale values is calculated, that is, all the target grayscale values are added together, and then divided by the total number of target grayscale values (the sum of the first quantity and the second quantity). The result obtained is the target grayscale value of the temperature abnormality area. Continuing in the embodiment of the automobile injection mold, the first quantity is 15, and the corresponding first target grayscale values are such as 185, 192, 200, etc.; the second quantity is 10, and the corresponding second target grayscale values are such as 188, 195, 200, etc. These 25 target grayscale values are added together, that is, 185+192+200+...+188+195+200, and then divided by the total number 25. The average value obtained is the target grayscale value of the temperature abnormality area. For example, the calculated result is 193.

[0068] The embodiment of the present invention targets the temperature anomaly area in the first quadrant, and based on the maximum and minimum grayscale values and their occurrence numbers, uses chaotic mapping to generate random and representative target grayscale values in different grayscale intervals, and then obtains the final target grayscale value through mean calculation. Therefore, it fully considers the distribution characteristics of the grayscale values in the position area, and can more reasonably reflect the actual grayscale situation of the temperature anomaly area, thereby providing more accurate data for subsequent temperature conversion based on grayscale values, improving the accuracy and reliability of mold temperature determination, and making the intelligent compensation control of mold temperature more accurate and effective, thereby effectively improving the quality and production efficiency of molded products.

[0069] In one embodiment, steps 3035 to 3038 are described as follows:

[0070] Step 3035: If the location area is the second quadrant area, obtain the maximum grayscale value and the minimum grayscale value in the location area, as well as the first number of maximum grayscale values and the second number of minimum grayscale values.

[0071] Optionally, the compensation control system determines whether the location area corresponding to the temperature anomaly region in the grayscale image is in the second quadrant. If the location area is confirmed to be in the second quadrant, the grayscale values of all pixels in the location area are scanned. During the scanning process, the grayscale values of each pixel are compared in real time to determine the maximum and minimum grayscale values. Simultaneously, the number of occurrences of the maximum and minimum grayscale values in the location area is counted to obtain a first number and a second number.

[0072] Continuing with the automotive injection mold production scenario, step 302 locates a temperature anomaly region corresponding to the second quadrant of the grayscale image, which contains 120 pixels. The compensation control system reads the grayscale values of these 120 pixels one by one, and during comparison, finds that the maximum grayscale value is 220 and the minimum grayscale value is 170. Further statistics show that the pixel with a grayscale value of 220 appears 18 times, or the first number is 18; the pixel with a grayscale value of 170 appears 12 times, or the second number is 12.

[0073] Step 3036: If the number of first grayscale values is less than the first number, then the center grayscale values of the corresponding number are obtained based on the difference between the number of first grayscale values and the first number, and the first grayscale values and the center grayscale values of the corresponding number are summed to obtain a third grayscale value. If the number of first grayscale values is greater than or equal to the first number, then the first grayscale values of the first number are summed to obtain a third grayscale value. The first grayscale value is three-quarters of the maximum grayscale value.

[0074] Furthermore, the compensation control system first calculates the first grayscale value, which is three-quarters of the maximum grayscale value. Then, the actual number of occurrences of the first grayscale value in the position area is counted and compared with the first number obtained in step 3035. When the actual number is less than the first number, the compensation control system calculates the difference between the two and obtains the center grayscale value of the corresponding number using an interpolation algorithm based on the Fibonacci sequence. The Fibonacci sequence formula is F n =F n-1 +F n-2 , where F0 = 0 and F1 = 1. By transforming and mapping the Fibonacci sequence so that the generated values fall within a reasonable grayscale range, the desired center grayscale value is obtained. Finally, the existing first grayscale value is added to the newly obtained center grayscale value to obtain the third grayscale value.

[0075] Furthermore, if the actual number of the first grayscale values is greater than or equal to the first number, the compensation control system directly sums the first number of first grayscale values to obtain the third grayscale value.

[0076] Continuing with the above embodiment, it is known that the maximum grayscale value in step 3035 is 220, then the first grayscale value is 220*(3 / 4)=165. In the position area of the second quadrant, the actual number of occurrences of the first grayscale value 165 is 10 according to statistics, which is less than the first number 18. The difference in number is 18-10=8. Using the Fibonacci sequence for transformation, the numerical values generated by the sequence are mapped to the grayscale value interval to obtain 8 center grayscale values, such as 175, 180, etc. The existing 10 first grayscale values are added to the newly obtained 8 center grayscale values to obtain the third grayscale value. For example, the sum result is 165*10+175+180+...=2000 (the specific calculation process in the middle is omitted here).

[0077] In step 3037, if the number of second grayscale values is less than the second number, the center grayscale values of the corresponding number are obtained based on the difference between the number of second grayscale values and the second number, and the second grayscale values and the center grayscale values of the corresponding number are summed to obtain a fourth grayscale value. If the number of second grayscale values is greater than or equal to the second number, the second grayscale values of the second number are summed to obtain a fourth grayscale value. The second grayscale value is the average of the maximum grayscale value and the minimum grayscale value.

[0078] Furthermore, the compensation control system calculates a second grayscale value, which is the average of the maximum grayscale value and the minimum grayscale value. Subsequently, the actual number of occurrences of the second grayscale value within the position area is counted and compared with the second number obtained in step 3035. When the actual number is less than the second number, the difference between the two is calculated, and a random interpolation algorithm based on fractal Brownian motion is used to obtain the corresponding number of center grayscale values. Fractal Brownian motion generates random values with fractal characteristics within the grayscale value range by controlling parameters such as the Hurst exponent. Finally, the existing second grayscale value is added to the newly obtained center grayscale value to obtain a fourth grayscale value.

[0079] Furthermore, if the actual number of the second grayscale values is greater than or equal to the second number, the compensation control system directly sums the second number of second grayscale values to obtain the fourth grayscale value.

[0080] Continuing with the above embodiment, it is known that the maximum grayscale value is 220 and the minimum grayscale value is 170, so the second grayscale value is (220+170) / 2=195. In this position area, the actual number of occurrences of the second grayscale value 195 is 8, which is less than the second number 12. The quantity difference is 12-8=4. Using the fractal Brownian motion algorithm, a suitable Hurst exponent is set to generate 4 center grayscale values within the grayscale value interval, such as 190, 200, etc. The existing 8 second grayscale values are added to the newly acquired 4 center grayscale values to obtain the fourth grayscale value. For example, the sum is 195*8+190+200+...=1800 (the specific calculation process in the middle is omitted here).

[0081] Step 3038: Calculate the average value based on the third grayscale value and the fourth grayscale value to obtain the target grayscale value of the temperature abnormality area.

[0082] Furthermore, the compensation control system summarizes the third grayscale value obtained in step 3036 and the fourth grayscale value obtained in step 3037, and obtains the target grayscale value of the temperature abnormality area through a simple arithmetic average calculation, that is, the sum of the two is divided by 2. The target grayscale value comprehensively considers the distribution and quantity differences of different grayscale values in the location area, and can more accurately reflect the temperature characteristics of the area.

[0083] The embodiment of the present invention targets the temperature abnormality area in the second quadrant. Based on the maximum and minimum grayscale values and their number, combined with complex algorithms such as Fibonacci series interpolation and fractal Brownian motion random interpolation, the number and weights of different grayscale values are dynamically adjusted, and the target grayscale value is finally obtained through mean calculation. Therefore, it can effectively deal with problems such as uneven distribution and quantity differences of grayscale values in the position area, and can more accurately capture the grayscale characteristics of the temperature abnormality area, provide reliable data for subsequent temperature conversion based on grayscale values, improve the overall accuracy of the intelligent compensation control of the mold temperature, and improve the quality and production efficiency of molded products.

[0084] In one embodiment, steps 3039 to 30312 are described as follows:

[0085] Step 3039: If the location area is the third quadrant area, obtain the maximum grayscale value, minimum grayscale value and center grayscale value in the location area, as well as the first number of maximum grayscale values and the second number of minimum grayscale values.

[0086] Optionally, the compensation control system determines whether the location area corresponding to the temperature anomaly area in the grayscale image is the third quadrant area. Once it is determined to be in the third quadrant area, a comprehensive scan of the grayscale values of all pixels in the location area is performed. During the scanning process, the maximum and minimum grayscale values are determined through continuous comparison. At the same time, the arithmetic mean of the grayscale values of all pixels in the location area is calculated and used as the central grayscale value. In addition, the compensation control system records the number of times the maximum grayscale value and the minimum grayscale value appear in the location area, i.e., the first number and the second number.

[0087] Continuing in the production process of automobile injection molds, after step 302 positioning, a certain temperature abnormality area corresponds to the third quadrant area of the grayscale image, which contains 150 pixels. The compensation control system reads the grayscale values of these 150 pixels one by one, and determines in the comparison process that the maximum grayscale value is 240 and the minimum grayscale value is 160. By calculating the sum of the grayscale values of all pixels and dividing it by the number of pixels 150, the center grayscale value is obtained. (g i represents the grayscale value of the i-th pixel). Further statistics show that the pixel with a grayscale value of 240 appears 20 times, that is, the first number is 20; the pixel with a grayscale value of 160 appears 15 times, that is, the second number is 15.

[0088] Step 30310: Determine a first grayscale difference based on the maximum grayscale value and the center grayscale value, and determine a second grayscale difference based on the minimum grayscale value and the center grayscale value.

[0089] Furthermore, the compensation control system calculates the difference between the maximum grayscale value and the center grayscale value to obtain a first grayscale difference; and calculates the difference between the minimum grayscale value and the center grayscale value to obtain a second grayscale difference.

[0090] In one embodiment, the maximum grayscale value is 240, the center grayscale value is 190, the first grayscale difference is 240-190=50; the minimum grayscale value is 160, and the second grayscale difference is 190-160=30.

[0091] Step 30311: Acquire a first number of fifth grayscale values between the first grayscale difference value and the maximum grayscale value range, and acquire a second number of sixth grayscale values between the minimum grayscale value and the second grayscale difference value range.

[0092] Furthermore, the compensation control system adopts the Kolmogorov entropy optimization algorithm based on chaos theory to generate a first number of fifth grayscale values within the range interval formed by the first grayscale difference and the maximum grayscale value; and to generate a second number of sixth grayscale values within the range interval formed by the minimum grayscale value and the second grayscale difference. Kolmogorov entropy is used to measure the degree of chaos in the system. By optimizing the entropy value, the generated grayscale value has better randomness and representativeness within the corresponding interval. The specific calculation formula is: Kolmogorov entropy K = -∑ i p i log2 p i , where p i is the probability that the system is in state i. By adjusting the algorithm parameters, the distribution characteristics of the generated grayscale values are controlled to make it more in line with actual needs.

[0093] Continuing with the above-mentioned automobile injection mold embodiment, the first grayscale difference is 50 and the maximum grayscale value is 240. Therefore, in the interval [50, 240], the compensation control system uses the Kolmogorov entropy optimization algorithm to generate 20 fifth grayscale values according to the first quantity 20, such as 180, 200, 220, etc.; the minimum grayscale value is 160, and the second grayscale difference is 30. In the interval [160, 30], 15 sixth grayscale values are generated according to the second quantity 15, such as 170, 185, 195, etc.

[0094] Step 30312: Calculate the average value based on the first number of fifth grayscale values and the second number of sixth grayscale values to obtain the target grayscale value of the temperature abnormality area.

[0095] Furthermore, the compensation control system summarizes the first number of fifth grayscale values and the second number of sixth grayscale values obtained in step 30311, and obtains the target grayscale value of the temperature abnormality area by calculating the arithmetic mean of these grayscale values, wherein the target grayscale value comprehensively considers the distribution of different grayscale values in the position area and the relationship with the center grayscale value, and can more accurately reflect the temperature characteristics of the area.

[0096] In one embodiment, a first number of fifth grayscale values (such as 20 values such as 180, 200, 220) and a second number of sixth grayscale values (such as 15 values such as 170, 185, 195) are known. The compensation control system adds these 35 grayscale values, i.e., 180+200+220+...+170+185+195, and then divides the sum by the total number 35. The obtained average value is the target grayscale value of the temperature abnormality area, for example, the calculated result is 192.

[0097] The embodiment of the present invention targets the temperature anomaly area in the third quadrant. Based on the maximum grayscale value, the minimum grayscale value, the center grayscale value and their number, the Kolmogorov entropy optimization algorithm is used to generate random and representative grayscale values within a specific grayscale range, and then the target grayscale value is obtained by mean calculation. Therefore, the relationship between the grayscale value in the position area and the center grayscale value is fully considered, which can more comprehensively and accurately reflect the grayscale characteristics of the temperature anomaly area and improve the accuracy of the intelligent compensation control of the mold temperature.

[0098] In one embodiment, steps 30313 to 30316 are described as follows:

[0099] Step 30313: If the location area is the fourth quadrant area, obtain the maximum grayscale value, minimum grayscale value and center grayscale value in the location area, as well as the first number of maximum grayscale values and the second number of minimum grayscale values.

[0100] Optionally, the compensation control system determines whether the location of the abnormal temperature region in the grayscale image is in the fourth quadrant. If so, a comprehensive scan of the grayscale values of all pixels in the region is performed. During the scan, the maximum and minimum grayscale values are continuously compared to determine the maximum and minimum grayscale values. Simultaneously, the arithmetic mean of the grayscale values of all pixels in the region is calculated as the central grayscale value.

[0101] Furthermore, the compensation control system counts the number of times the maximum grayscale value and the minimum grayscale value appear in the region, ie, the first number and the second number.

[0102] Continuing with the automotive injection mold production scenario, after step 302 positioning, a temperature abnormality area corresponds to the fourth quadrant of the grayscale image, which contains 160 pixels. The compensation control system reads the grayscale values of these 160 pixels one by one, and after comparison, determines that the maximum grayscale value is 250 and the minimum grayscale value is 150. By calculating the sum of the grayscale values of all pixels and dividing it by the number of pixels, the center grayscale value is obtained. (g i represents the grayscale value of the i-th pixel). Further statistics show that the pixel with a grayscale value of 250 appears 22 times, that is, the first number is 22; the pixel with a grayscale value of 150 appears 18 times, that is, the second number is 18.

[0103] Step 30314, calculate the mean based on the maximum grayscale value, the minimum grayscale value and the center grayscale value to obtain the average grayscale value.

[0104] Furthermore, the compensation control system adds the maximum grayscale value, the minimum grayscale value and the center grayscale value, and then divides them by 3 to obtain the average grayscale value by arithmetic averaging. The average grayscale value comprehensively reflects the overall level of grayscale values in the area and is used to subsequently determine the range of grayscale values.

[0105] In one embodiment, it is known that the maximum grayscale value is 250, the minimum grayscale value is 150, and the center grayscale value is 195, and the compensation control system calculates the average grayscale value as (250+150+195) / 3≈198.33.

[0106] Step 30315: Obtain a first number of seventh grayscale values between the average grayscale value and the maximum grayscale value range, and obtain a second number of eighth grayscale values between the minimum grayscale value and the average grayscale value range.

[0107] Furthermore, the compensation control system adopts a random search algorithm based on Levy flight to generate a first number of seventh grayscale values within the range interval formed by the average grayscale value and the maximum grayscale value; and generates a second number of eighth grayscale values within the range interval formed by the minimum grayscale value and the average grayscale value. Levy flight is a random walk pattern with a heavy-tailed distribution characteristic, and its formula is Among them, X t is the current position, α is the step size control parameter, Represents the Hadamard product, L(β) is the step size of the stable distribution, and β is the stability index (generally in the range of (0<β≤2). By adjusting the algorithm parameters, the generated grayscale values have good randomness and ergodicity within the corresponding interval.

[0108] Continuing with the above-mentioned automobile injection mold embodiment, the average grayscale value is approximately 198.33, the maximum grayscale value is 250, and in the interval [198.33, 250], the Levy flight random search algorithm is used to generate 22 seventh grayscale values such as 205, 220, 235, etc. according to the first number 22; the minimum grayscale value is 150, and in the interval [150, 198.33], 18 eighth grayscale values are generated according to the second number 18, such as 160, 175, 190, etc.

[0109] Step 30316: Perform mean calculation based on the first number of seventh grayscale values and the second number of eighth grayscale values to obtain a target grayscale value for the temperature abnormality area.

[0110] Furthermore, the compensation control system summarizes the first number of seventh grayscale values and the second number of eighth grayscale values obtained in step 30315, and obtains the target grayscale value of the temperature abnormality area by calculating the arithmetic mean of these grayscale values, wherein the target grayscale value comprehensively considers the distribution of different grayscale values in the area, and can more accurately reflect the grayscale characteristics of the temperature abnormality area.

[0111] Continuing with the above embodiment, a first number of seventh grayscale values (such as 22 values such as 205, 220, 235) and a second number of eighth grayscale values (such as 18 values such as 160, 175, 190) are known. The compensation control system adds these 40 grayscale values, i.e., 205+220+235+...+160+175+190, and then divides it by the total number 40. The average value obtained is the target grayscale value of the temperature abnormality area, for example, the calculated result is 200.

[0112] The embodiment of the present invention targets the temperature abnormality area in the fourth quadrant, and based on the maximum grayscale value, the minimum grayscale value, the center grayscale value and their number, uses the Levy flight random search algorithm to generate random and ergodic grayscale values within a specific grayscale range, and then obtains the target grayscale value through mean calculation. Therefore, the grayscale value distribution in the area is comprehensively considered from multiple dimensions, which can more accurately and comprehensively reflect the grayscale characteristics of the temperature abnormality area, provide more reliable data support for the subsequent temperature conversion based on grayscale values, improve the accuracy of the intelligent compensation control of the mold temperature, and improve the quality and production efficiency of the molded products.

[0113] In one embodiment, steps 30317 to 30319 are described as follows:

[0114] Step 30317: If the location area is the central area, obtain the maximum grayscale value, the minimum grayscale value, and the central grayscale value in the location area, as well as a third total number of the maximum grayscale value and the minimum grayscale value.

[0115] Optionally, the compensation control system determines whether the location corresponding to the abnormal temperature region in the grayscale image is the central region. If the central region is determined, the grayscale values of all pixels within the region are traversed. During the traversal process, the grayscale values of each pixel are compared in real time to determine the maximum and minimum grayscale values. Simultaneously, the arithmetic mean of the grayscale values of all pixels in the region is calculated as the central grayscale value. Furthermore, the total number of occurrences of the maximum and minimum grayscale values is counted and recorded as a third quantity.

[0116] Continuing in the automobile injection mold production process, after step 302 positioning, a certain temperature abnormal area corresponds to the center area of the grayscale image, which contains 80 pixels. The grayscale values of these 80 pixels are read one by one, and the maximum grayscale value is determined to be 235 and the minimum grayscale value is 165 during the comparison process. By calculating the sum of the grayscale values of all pixels and dividing it by the number of pixels, the center grayscale value is obtained. (g i (represents the grayscale value of the i-th pixel) Statistics show that the pixel with a grayscale value of 235 appears 12 times, and the pixel with a grayscale value of 165 appears 8 times, so the third number is 12+8=20.

[0117] Step 30318: Determine a first grayscale difference based on the maximum grayscale value and the center grayscale value, and determine a second grayscale difference based on the minimum grayscale value and the center grayscale value.

[0118] Furthermore, the compensation control system calculates the difference between the maximum grayscale value and the center grayscale value to obtain a first grayscale difference; and calculates the difference between the minimum grayscale value and the center grayscale value to obtain a second grayscale difference.

[0119] Continuing with the above embodiment, it is known that in step 30317, the maximum grayscale value is 235 and the center grayscale value is 200, so the first grayscale difference is 235-200=35; the minimum grayscale value is 165 and the center grayscale value is 200, so the second grayscale difference is 200-165=35.

[0120] Step 30319: Obtain a third number of ninth grayscale values between the first grayscale difference and the second grayscale difference range, and calculate the mean of the third number of ninth grayscale values to obtain a target grayscale value for the temperature abnormality area.

[0121] Furthermore, the compensation control system adopts a numerical generation method based on a quantum genetic algorithm to generate a third number of ninth grayscale values within a range interval formed by the first grayscale difference and the second grayscale difference.

[0122] The quantum genetic algorithm combines quantum computing principles with genetic algorithms, using the superposition state of quantum bits to represent individuals and achieving individual evolution through quantum gate operations. Its core operation includes quantum rotation gates to update the probability amplitude of quantum bits, and the formula is:

[0123]

[0124] Among them, α i and β i is the quantum bit probability amplitude, θ i The rotation angle is adjusted to achieve individual evolution. After generating the ninth grayscale value, the compensation control system adds these grayscale values, divides them by the third number, and calculates the target grayscale value of the temperature abnormality area through arithmetic mean.

[0125] Continuing with the above-mentioned automotive injection mold embodiment, the first grayscale difference and the second grayscale difference are both 35. Within the range [35, 35] (actually a small fluctuation range including this value, which can be set as [35-δ, 35+δ]), where δ is a minimum value, such as 0.01), the compensation control system uses a quantum genetic algorithm to generate 20 ninth grayscale values, such as 34.98, 35.02, and 35.01, based on the third quantity 20. These 20 ninth grayscale values are added together (i.e., 34.98 + 35.02 + 35.01 + ...), and then divided by 20. The resulting average is the target grayscale value for the temperature anomaly region, for example, 35.

[0126] This embodiment of the present invention targets temperature anomalies in the central region. Based on the maximum grayscale value, minimum grayscale value, and central grayscale value, as well as their number, the algorithm utilizes a quantum genetic algorithm to generate grayscale values within a specific grayscale range with efficient search capabilities and global optimization characteristics. The target grayscale value is then calculated through mean value calculation. This fully considers the distribution characteristics of the grayscale values in the central region, enabling more accurate capture of the grayscale characteristics within the region and effectively avoiding the problem of local optimal solutions. This provides more reliable and representative data for subsequent grayscale-based temperature conversion, improving the accuracy of intelligent compensation control of mold temperature in the central region, thereby effectively improving the quality and production efficiency of molded products.

[0127] Furthermore, the mold temperature intelligent compensation control system based on image recognition provided by the present invention is described below. The mold temperature intelligent compensation control system based on image recognition described below and the mold temperature intelligent compensation control method based on image recognition described above can be referenced to each other.

[0128] Optional, see Figure 2 , Figure 2It is a structural diagram of the mold temperature intelligent compensation control system based on image recognition provided by the present invention. The mold temperature intelligent compensation control system based on image recognition includes.

[0129] The image acquisition module 210 is used to acquire real-time images of the mold surface using an infrared thermal imager, obtain an infrared thermal image of the mold surface, and grayscale the infrared thermal image to obtain a grayscale image;

[0130] The region segmentation module 220 is used to segment the grayscale image into regions based on the grayscale value corresponding to the preset normal working temperature of the mold to obtain temperature abnormality regions;

[0131] The temperature comparison module 230 is used to determine the mold temperature value of the temperature abnormal area and compare the mold temperature value with the preset standard operating temperature value of the mold to obtain a temperature deviation value;

[0132] The compensation control module 240 is used to generate a compensation control instruction based on the temperature deviation value, and to heat or cool the mold based on the compensation control instruction to achieve intelligent compensation control of the mold temperature.

[0133] The embodiment of the present invention can obtain the overall temperature distribution image of the mold surface through the infrared thermal imager, avoiding the limitation of the temperature sensor that can only obtain local point temperature information. During the image analysis and processing process, it can quickly and accurately identify the temperature abnormal area and calculate the temperature deviation value, thereby improving the response speed. It can timely generate and execute compensation control instructions based on the temperature deviation value calculated in real time to achieve precise adjustment of the mold temperature. Therefore, by continuously looping through each step, the mold temperature can be monitored and adjusted in real time, and a rapid response can be made when the mold temperature fluctuates abnormally, and compensation control can be carried out in a timely and accurate manner, effectively improving the quality and production efficiency of molded products.

[0134] See also Figure 3 , Figure 3 This is a diagram of an embodiment of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, an embodiment of the present invention provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor 320. When the processor 320 executes the computer program 311, the following steps are implemented:

[0135] The infrared thermal imager is used to collect real-time images of the mold surface, obtain an infrared thermal image of the mold surface, and grayscale the infrared thermal image to obtain a grayscale image;

[0136] The grayscale image is segmented based on the grayscale value corresponding to the preset normal working temperature of the mold to obtain the temperature abnormality area;

[0137] Determine the mold temperature value of the temperature abnormal area, and compare the mold temperature value with the preset standard operating temperature value of the mold to obtain the temperature deviation value;

[0138] Compensation control instructions are generated based on the temperature deviation value, and the mold is heated or cooled based on the compensation control instructions to achieve intelligent compensation control of the mold temperature.

[0139] See also Figure 4 , Figure 4 Detailed description of an embodiment of a computer-readable storage medium provided by an embodiment of the present invention. Figure 4 As shown, this embodiment provides a computer-readable storage medium 400 on which a computer program 311 is stored. When the computer program 311 is executed by a processor, the following steps are implemented:

[0140] The infrared thermal imager is used to collect real-time images of the mold surface, obtain an infrared thermal image of the mold surface, and grayscale the infrared thermal image to obtain a grayscale image;

[0141] The grayscale image is segmented based on the grayscale value corresponding to the preset normal working temperature of the mold to obtain the temperature abnormality area;

[0142] Determine the mold temperature value of the temperature abnormal area, and compare the mold temperature value with the preset standard operating temperature value of the mold to obtain the temperature deviation value;

[0143] Compensation control instructions are generated based on the temperature deviation value, and the mold is heated or cooled based on the compensation control instructions to achieve intelligent compensation control of the mold temperature.

[0144] On the other hand, the present invention further provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the mold temperature intelligent compensation control method based on image recognition provided by the above methods, which includes:

[0145] The infrared thermal imager is used to collect real-time images of the mold surface, obtain an infrared thermal image of the mold surface, and grayscale the infrared thermal image to obtain a grayscale image;

[0146] The grayscale image is segmented based on the grayscale value corresponding to the preset normal working temperature of the mold to obtain the temperature abnormality area;

[0147] Determine the mold temperature value of the temperature abnormal area, and compare the mold temperature value with the preset standard operating temperature value of the mold to obtain the temperature deviation value;

[0148] Compensation control instructions are generated based on the temperature deviation value, and the mold is heated or cooled based on the compensation control instructions to achieve intelligent compensation control of the mold temperature.

[0149] The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0150] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0151] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. 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 replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A mold temperature intelligent compensation control method based on image recognition, characterized in that: include: Performing real-time image acquisition of the mold surface using an infrared thermal imager to obtain an infrared thermal image of the mold surface, and gray-processing the infrared thermal image to obtain a grayscale image; Segmenting the grayscale image based on grayscale values corresponding to a preset normal working temperature of the mold to obtain temperature abnormality areas; Determining a mold temperature value of the mold in the temperature abnormality area, and obtaining a temperature deviation value based on comparing the mold temperature value with a preset standard operating temperature value of the mold; A compensation control instruction is generated based on the temperature deviation value, and the mold is heated or cooled based on the compensation control instruction to achieve intelligent compensation control of the mold temperature.

2. The mold temperature intelligent compensation control method based on image recognition according to claim 1 is characterized in that: Determining the mold temperature value of the abnormal temperature area includes: Dividing the grayscale image into quadrants to obtain four quadrant areas and a central area; the four quadrant areas include a first quadrant area, a second quadrant area, a third quadrant area, and a fourth quadrant area, the first quadrant area representing an upper left area, the second quadrant area representing an upper right area, the third quadrant area representing a lower left area, and the fourth quadrant area representing a lower right area; Determining a location area corresponding to the temperature abnormality area in the grayscale image based on position mapping of the temperature abnormality area in the grayscale image; Determining a target grayscale value for the temperature abnormality area based on the location area and the grayscale value within the location area; Temperature conversion is performed based on the target grayscale value to obtain the mold temperature value.

3. The mold temperature intelligent compensation control method based on image recognition according to claim 2 is characterized in that: The determining, based on the location area and the grayscale value within the location area, a target grayscale value of the temperature abnormality area includes: If the location area is the first quadrant area, obtaining a maximum grayscale value and a minimum grayscale value in the location area, as well as a first number of maximum grayscale values and a second number of minimum grayscale values; Acquire a first number of first target grayscale values between the first grayscale value and the maximum grayscale value; the first grayscale value is three quarters of the maximum grayscale value; Acquire a second number of second target grayscale values between the minimum grayscale value and a second grayscale value range; the second grayscale value is an average of the maximum grayscale value and the minimum grayscale value; An average is calculated based on the first number of first target grayscale values and the second number of second target grayscale values to obtain a target grayscale value of the temperature abnormality area.

4. The mold temperature intelligent compensation control method based on image recognition according to claim 2 is characterized in that: The determining, based on the location area and the grayscale value within the location area, a target grayscale value of the temperature abnormality area includes: If the location area is the second quadrant area, obtaining a maximum grayscale value and a minimum grayscale value in the location area, as well as a first number of maximum grayscale values and a second number of minimum grayscale values; If the number of first grayscale values is less than the first number, obtaining a corresponding number of center grayscale values based on the difference between the number of first grayscale values and the first number, and summing the first grayscale value and the corresponding number of center grayscale values to obtain a third grayscale value; if the number of first grayscale values is greater than or equal to the first number, summing the first grayscale values of the first number to obtain the third grayscale value; the first grayscale value is three quarters of the maximum grayscale value; If the number of the second grayscale values is less than the second number, obtaining the corresponding number of center grayscale values based on the difference between the number of the second grayscale values and the second number, and summing the second grayscale values and the corresponding number of center grayscale values to obtain a fourth grayscale value; if the number of the second grayscale values is greater than or equal to the second number, summing the second number of second grayscale values to obtain the fourth grayscale value; the second grayscale value is the average of the maximum grayscale value and the minimum grayscale value; An average value is calculated based on the third grayscale value and the fourth grayscale value to obtain a target grayscale value of the temperature abnormality area.

5. The mold temperature intelligent compensation control method based on image recognition according to claim 2 is characterized in that: The determining, based on the location area and the grayscale value within the location area, a target grayscale value of the temperature abnormality area includes: If the position area is the third quadrant area, obtaining the maximum grayscale value, the minimum grayscale value, and the center grayscale value in the position area, as well as a first number of maximum grayscale values and a second number of minimum grayscale values; Determining a first grayscale difference value based on the maximum grayscale value and the center grayscale value, and determining a second grayscale difference value based on the minimum grayscale value and the center grayscale value; Acquire the first number of fifth grayscale values between the first grayscale difference value and the maximum grayscale value range, and acquire the second number of sixth grayscale values between the minimum grayscale value and the second grayscale difference value range; An average is calculated based on the first number of fifth grayscale values and the second number of sixth grayscale values to obtain a target grayscale value of the temperature abnormality area.

6. The mold temperature intelligent compensation control method based on image recognition according to claim 2 is characterized in that: The determining, based on the location area and the grayscale value within the location area, a target grayscale value of the temperature abnormality area includes: If the position area is the fourth quadrant area, obtaining a maximum grayscale value, a minimum grayscale value, and a center grayscale value within the position area, as well as a first number of maximum grayscale values and a second number of minimum grayscale values; Perform mean calculation based on the maximum grayscale value, the minimum grayscale value, and the center grayscale value to obtain an average grayscale value; Acquire the first number of seventh grayscale values between the average grayscale value and the maximum grayscale value range, and acquire the second number of eighth grayscale values between the minimum grayscale value and the average grayscale value range; An average is calculated based on the first number of seventh grayscale values and the second number of eighth grayscale values to obtain a target grayscale value of the temperature abnormality area.

7. The mold temperature intelligent compensation control method based on image recognition according to claim 2 is characterized in that: The determining, based on the location area and the grayscale value within the location area, a target grayscale value of the temperature abnormality area includes: If the location area is a central area, obtaining a maximum grayscale value, a minimum grayscale value, and a central grayscale value within the location area, as well as a third total number of the maximum grayscale value and the minimum grayscale value; Determining a first grayscale difference value based on the maximum grayscale value and the center grayscale value, and determining a second grayscale difference value based on the minimum grayscale value and the center grayscale value; The third number of ninth grayscale values are obtained between the first grayscale difference value range and the second grayscale difference value range, and the third number of ninth grayscale values are averaged to obtain a target grayscale value of the temperature abnormality area.

8. A mold temperature intelligent compensation control system based on image recognition, characterized in that: The method for intelligent mold temperature compensation control based on image recognition according to any one of claims 1 to 7 is applied; the intelligent mold temperature compensation control system based on image recognition comprises: An image acquisition module is used to acquire real-time images of the mold surface using an infrared thermal imager, obtain an infrared thermal image of the mold surface, and grayscale the infrared thermal image to obtain a grayscale image; A region segmentation module is used to segment the grayscale image into regions based on grayscale values corresponding to a preset normal working temperature of the mold to obtain temperature abnormality regions; a temperature comparison module, configured to determine a mold temperature value of the mold in the temperature abnormality area, and compare the mold temperature value with a preset standard operating temperature value of the mold to obtain a temperature deviation value; The compensation control module is used to generate a compensation control instruction based on the temperature deviation value, and to heat or cool the mold based on the compensation control instruction to achieve intelligent compensation control of the mold temperature.

9. An electronic device comprising: Memory for storing computer software programs; A processor for reading and executing the computer software program, wherein when the processor executes the computer software program, it implements the mold temperature intelligent compensation control method based on image recognition as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing a computer software program, wherein: When the computer software program is executed by a processor, the mold temperature intelligent compensation control method based on image recognition as claimed in any one of claims 1 to 7 is implemented.

Images