A mold temperature detection method and system

Abstract

This invention provides a mold temperature detection method and system, relating to the field of mold temperature detection technology. The method includes: dividing the mold into multiple regions and acquiring infrared images of each region at multiple moments during the current detection cycle; determining the average temperature data of the mold at multiple moments during the current detection cycle based on the infrared images; acquiring injection molding machine feed rate data, injection pressure data, and nozzle temperature data at multiple moments during the current detection cycle; processing the feed rate data, injection pressure data, and nozzle temperature data using a trained temperature prediction model to obtain predicted temperature data at multiple moments during the current detection cycle; determining a temperature detection error score based on the predicted temperature data and the average temperature data; and determining whether the mold temperature detection is qualified based on the temperature detection error score and a temperature detection error score threshold. According to this invention, abnormal changes in mold temperature can be detected in a timely manner during the material injection process.

Description

Technical Field

[0001] This invention relates to the field of mold temperature detection technology, and in particular to a mold temperature detection method and system. Background Technology

[0002] In related technologies, CN115673295A provides a mold baking preheating device and method. The mold baking preheating device includes an air delivery module, a natural gas delivery module, a mixer, a surface burner, a temperature sensor, and a controller. Both the air delivery module and the natural gas delivery module are connected to the mixer, which mixes air and natural gas in a certain proportion and then delivers the mixture to the surface burner. The air delivery module, the natural gas delivery module, and the temperature sensor are all communicatively connected to the controller. The temperature sensor monitors the surface temperature of the mold and transmits the temperature information to the controller, which controls the operating status of the air delivery module and the natural gas delivery module based on the temperature information. This device can automatically monitor the surface temperature of the mold, with high accuracy and timely feedback. The temperature information is fed back to the controller, which automatically controls the flame temperature based on the temperature information, improving the quality of mold baking preheating, resulting in high mold heating quality and a long service life.

[0003] CN116275005A relates to a mold temperature detection method and system, belonging to the field of mold temperature control technology. The method includes acquiring an infrared image of the mold after initial heating; dividing the mold in the infrared image into different regions and determining the temperature difference between each region and a standard temperature; determining the heating rate and temperature decay rate corresponding to each region of the mold; and determining the required heating time for each region based on the temperature difference, heating rate, and temperature decay rate, so as to heat the mold according to the heating time. This solution solves the problem of inconsistent heating during existing mold preheating processes.

[0004] Therefore, although the mold can be preheated in the relevant technology, the temperature of the mold is not detected during the material injection process. It is impossible to detect abnormal changes in the mold temperature in time during the material injection process, which leads to a decline in material performance.

[0005] The information disclosed in the background section of this application is intended only to enhance the understanding of the general background of this application and should not be construed as an admission or in any way implying that the information constitutes prior art known to those skilled in the art. Summary of the Invention

[0006] This invention provides a mold temperature detection method and system, which can solve the technical problem of not being able to detect abnormal changes in mold temperature in a timely manner during the material injection process.

[0007] According to a first aspect of the present invention, a mold temperature detection method is provided, comprising: dividing the mold into multiple regions and acquiring infrared images of each region at multiple moments in a current detection cycle; determining average temperature data of the mold at multiple moments in the current detection cycle based on the infrared images; acquiring feed rate data, injection pressure data, and nozzle temperature data of an injection molding machine at multiple moments in the current detection cycle; processing the feed rate data, injection pressure data, and nozzle temperature data using a trained temperature prediction model to obtain predicted temperature data at multiple moments in the current detection cycle; determining a temperature detection error score based on the predicted temperature data and the average temperature data; and determining whether the mold temperature detection is qualified based on the temperature detection error score and a temperature detection error score threshold.

[0008] According to the present invention, determining the average temperature data of the mold at multiple moments in the current detection cycle based on the infrared image includes: obtaining the average region temperature data of each region at multiple moments in the current detection cycle based on the pixel values ​​of the pixels in the infrared image; averaging the average region temperature data to determine the average temperature data of the mold at multiple moments in the current detection cycle.

[0009] According to the present invention, the training steps of the temperature prediction model include: acquiring historical average temperature data of the mold at multiple moments in multiple historical detection cycles, wherein the previous historical detection cycle of the current detection cycle is the first historical detection cycle; acquiring historical feed rate data, historical injection pressure data, and historical nozzle temperature data of the injection molding machine at multiple moments in multiple historical detection cycles; processing the historical feed rate data, historical injection pressure data, and historical nozzle temperature data through the temperature prediction model to obtain historical predicted temperature data at multiple moments in multiple historical detection cycles; determining the loss function of the temperature prediction model based on the historical average temperature data, the historical feed rate data, the historical injection pressure data, the historical nozzle temperature data, and the historical predicted temperature data; and training the temperature prediction model according to the training loss function to obtain the trained temperature prediction model.

[0010] According to the present invention, determining the loss function of the temperature prediction model based on the historical average temperature data, the historical feed rate data, the historical injection pressure data, the historical nozzle temperature data, and the historical predicted temperature data includes: determining the loss function of the temperature prediction model according to the formula... Determine the loss function Loss for the temperature prediction model, where M s，k M represents the historical feed rate data at time k in the s-th historical detection cycle. s，1 For the historical feed rate data at the first moment of the s-th historical detection cycle, P s，kFor the historical injection pressure data at time k in the s-th historical detection cycle, P s，1 T represents the historical injection pressure data at time 1 of the s-th historical detection cycle. s，k T represents the historical nozzle temperature data at time k in the s-th historical detection cycle. s，1 This refers to the historical nozzle temperature data at the first moment of the s-th historical detection cycle. This refers to the historical average temperature data at time k in the s-th historical detection period. The temperature prediction model outputs historical predicted temperature data at time k in the s-th historical detection period, where m is the number of historical detection periods, n is the number of times within a detection period, k≤n, s≤m, and k, n, s, and m are all positive integers; the temperature prediction model is trained according to the training loss function to obtain the trained temperature prediction model.

[0011] According to the present invention, determining a temperature detection error score based on the predicted temperature data and the average temperature data includes: fitting the predicted temperature data to a time point in the current detection cycle to determine a predicted temperature function in the current detection cycle; determining a predicted temperature derivative function based on the predicted temperature function; determining a predicted temperature change rate at multiple times in the current detection cycle based on the predicted temperature derivative function; fitting the average temperature data to a time point in the current detection cycle to determine an average temperature function in the current detection cycle; determining an average temperature derivative function based on the average temperature function; determining an average temperature change rate at multiple times in the current detection cycle based on the average temperature derivative function; obtaining a predicted temperature state vector based on the predicted temperature data and predicted temperature change rate of the mold at multiple times in the current detection cycle; obtaining an average temperature state vector based on the average temperature data and average temperature change rate of the mold at multiple times in the current detection cycle; and determining a temperature detection error score based on the predicted temperature state vector and the average temperature state vector.

[0012] According to the present invention, determining a temperature detection error score based on the predicted temperature state vector and the average temperature state vector includes: according to the formula Determine the temperature detection error score D, where, This is the average temperature data at the k-th moment of the current detection cycle. This represents the average temperature change rate at time k in the current detection cycle. This is the predicted temperature data at the k-th moment of the current detection cycle. This represents the predicted temperature change rate at time k in the current detection cycle. This represents the average temperature state vector at the k-th moment of the current detection cycle. Let be the predicted temperature state vector at the k-th moment of the current detection cycle, n be the number of moments in the detection cycle, k ≤ n, and both k and n are positive integers, and min is the minimum value function.

[0013] According to the present invention, determining whether the mold temperature detection is qualified based on the temperature detection error score and the temperature detection error score threshold includes: according to the formula Obtain the first condition C1 and the second condition C2, where D is the temperature detection error score. p The temperature detection error scoring threshold is set; if the first condition C1 is met, the mold temperature detection is determined to be unqualified; if the second condition C2 is met, the mold temperature detection is determined to be qualified.

[0014] According to a second aspect of the present invention, a mold temperature detection system is provided, comprising: an infrared image module for dividing the mold into multiple regions and acquiring infrared images of each region at multiple moments in the current detection cycle; an average temperature data module for determining average temperature data of the mold at multiple moments in the current detection cycle based on the infrared images; an injection molding machine data module for acquiring feed rate data, injection pressure data, and nozzle temperature data of the injection molding machine at multiple moments in the current detection cycle; a predicted temperature data module for processing the feed rate data, injection pressure data, and nozzle temperature data using a trained temperature prediction model to obtain predicted temperature data at multiple moments in the current detection cycle; a temperature detection error scoring module for determining a temperature detection error score based on the predicted temperature data and the average temperature data; and a pass / fail judgment module for determining whether the mold temperature detection is qualified based on the temperature detection error score and a temperature detection error score threshold.

[0015] Technical effects: According to the present invention, by using the trained temperature prediction model and combining the feeding speed data, injection pressure data, and nozzle temperature data during the injection molding process, the mold temperature when injecting materials into the mold can be predicted, which can improve the accuracy of mold temperature prediction. Comparing the predicted temperature data output by the temperature prediction model with the measured average temperature data of the mold can promptly detect abnormal changes in the mold temperature, thereby reducing the finished product quality problems caused by temperature, improving the material performance and molding quality. When training the temperature prediction model, the influence of the feeding speed data, injection pressure data, and nozzle temperature data on the mold temperature can be used to determine the influence of the above data on the error of the predicted temperature data. Based on this influence, as well as the relative error of the historical predicted temperature data, and considering the characteristic that the longer the time interval and the shorter the cycle interval, the lower the prediction accuracy, weights are set to train the loss function, so as to enhance the objectivity and accuracy of the loss function, thereby reducing the training loss function during the training process, improving the training intensity and training efficiency, and increasing the accuracy of the temperature prediction model. When determining the temperature detection error score, the temperature detection error score can be determined through the predicted temperature state vector and the average temperature state vector, which can achieve real-time monitoring and abnormal detection of the mold temperature during the material injection process, enabling the material to be processed under suitable temperature conditions, improving the material performance and molding quality. When determining whether the mold temperature detection is qualified, it can be determined whether the mold temperature detection is qualified by comparing the temperature detection error score with the temperature detection error score threshold. If the mold temperature detection is qualified, it can be judged that the temperature of the mold during the material injection process remains within a reasonable range, thereby improving the consistency of the material performance.

[0016] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and do not limit the present invention. According to the following detailed description of the exemplary embodiments with reference to the accompanying drawings, other features and aspects of the present invention will be clearer. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other embodiments can be obtained based on these drawings;

[0018] Figure 1 Exemplarily shows a flowchart of a mold temperature detection method according to an embodiment of the present invention;

[0019] Figure 2 Exemplarily shows a block diagram of a mold temperature detection system according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] The technical solution of the present invention will be described in detail below with reference to specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0022] Figure 1 An exemplary flowchart of a mold temperature detection method according to an embodiment of the present invention is shown. The method includes: step S101, dividing the mold into multiple regions and acquiring infrared images of each region at multiple moments in the current detection cycle; step S102, determining the average temperature data of the mold at multiple moments in the current detection cycle based on the infrared images; step S103, acquiring the feed rate data, injection pressure data, and nozzle temperature data of the injection molding machine at multiple moments in the current detection cycle; step S104, processing the feed rate data, injection pressure data, and nozzle temperature data using a trained temperature prediction model to obtain predicted temperature data at multiple moments in the current detection cycle; step S105, determining a temperature detection error score based on the predicted temperature data and the average temperature data; and step S106, determining whether the mold temperature detection is qualified based on the temperature detection error score and a temperature detection error score threshold.

[0023] According to an embodiment of the present invention, the mold temperature detection method uses a trained temperature prediction model to predict the mold temperature when material is injected into the mold, by combining the feed rate data, injection pressure data and nozzle temperature data of the injection process. This improves the accuracy of mold temperature prediction. By comparing the predicted temperature data output by the temperature prediction model with the average temperature data measured in the mold, abnormal changes in mold temperature can be detected in a timely manner, thereby reducing finished product quality problems caused by temperature and improving material performance and molding quality.

[0024] According to one embodiment of the present invention, in step S101, each detection cycle can be set to 1 minute, 2 minutes, etc., and the interval between adjacent moments can be set to 1 second, 2 seconds, etc., and the present invention does not limit this. The mold is divided into multiple different regions. These regions can be divided according to the shape, size, or function of the mold to enable more accurate temperature monitoring. At multiple moments in the current detection cycle, an infrared imaging device is used to photograph each region and record the temperature distribution information of that region.

[0025] According to an embodiment of the present invention, in step S102, the average temperature data of the mold at multiple moments in the current detection cycle is determined based on the infrared image.

[0026] According to an embodiment of the present invention, step S102 includes: obtaining average regional temperature data of each region at multiple moments in the current detection cycle based on the pixel values ​​of the pixels in the infrared image; averaging the average regional temperature data to determine the average temperature data of the mold at multiple moments in the current detection cycle.

[0027] According to one embodiment of the present invention, each infrared image is analyzed to extract the pixel value of each pixel in the image. Each pixel value represents the temperature value at that location. The temperature values ​​are summed and divided by the number of pixels in the region to calculate the average regional temperature data of the region. The average regional temperature data of each region at multiple moments within the current detection cycle are summed and then divided by the number of regions to obtain the average temperature data of the mold at multiple moments within the current detection cycle. This average temperature data is used as the measured temperature of the mold.

[0028] According to one embodiment of the present invention, in step S103, the feeding speed refers to the rate at which the injection molding machine injects material into the mold. The injection pressure refers to the pressure applied when the material is injected into the mold during the injection molding process, and the nozzle temperature is the temperature of the material before injection into the mold. This data is automatically collected by sensors connected to the injection molding machine, improving the accuracy and real-time performance of the data.

[0029] According to one embodiment of the present invention, in step S104, the feed rate data, injection pressure data, and nozzle temperature data of the injection molding machine have a significant impact on the mold temperature. For example, a faster feed rate causes the material to flow rapidly in the mold, generating higher shear heat and raising the mold temperature. Higher injection pressure causes the material to contact the mold surface more closely, accelerating heat transfer and leading to an increase in mold temperature. Higher nozzle temperature causes the material to overheat before entering the mold, resulting in an excessively rapid increase in mold temperature. The temperature prediction model is a deep learning neural network model, which can process the feed rate data, injection pressure data, and nozzle temperature data to obtain predicted temperature data for multiple moments in the current detection cycle.

[0030] According to an embodiment of the present invention, the training steps of the temperature prediction model include: acquiring historical average temperature data of the mold at multiple moments in multiple historical detection cycles, wherein the previous historical detection cycle of the current detection cycle is the first historical detection cycle; acquiring historical feed rate data, historical injection pressure data, and historical nozzle temperature data of the injection molding machine at multiple moments in multiple historical detection cycles; processing the historical feed rate data, historical injection pressure data, and historical nozzle temperature data through the temperature prediction model to obtain historical predicted temperature data at multiple moments in multiple historical detection cycles; determining the loss function of the temperature prediction model based on the historical average temperature data, the historical feed rate data, the historical injection pressure data, the historical nozzle temperature data, and the historical predicted temperature data; and training the temperature prediction model according to the training loss function to obtain the trained temperature prediction model.

[0031] According to one embodiment of the present invention, the loss function of the temperature prediction model is used to measure the difference between the model's prediction results and the actual situation, and is a key indicator for training the model. During the training process, by backpropagating the loss function, the model parameters are adjusted to minimize the loss function, thereby improving the accuracy of the temperature prediction model and obtaining the trained temperature prediction model.

[0032] According to one embodiment of the present invention, determining the loss function of the temperature prediction model based on the historical average temperature data, the historical feed rate data, the historical injection pressure data, the historical nozzle temperature data, and the historical predicted temperature data includes: determining the loss function Loss of the temperature prediction model according to formula (1).

[0033]

[0034] Among them, M s，k M represents the historical feed rate data at time k in the s-th historical detection cycle. s，1 For the historical feed rate data at the first moment of the s-th historical detection cycle, P s，k For the historical injection pressure data at time k in the s-th historical detection cycle, P s，1 T represents the historical injection pressure data at time 1 of the s-th historical detection cycle. s，k T represents the historical nozzle temperature data at time k in the s-th historical detection cycle. s，1 This refers to the historical nozzle temperature data at the first moment of the s-th historical detection cycle. This refers to the historical average temperature data at time k in the s-th historical detection period. The temperature prediction model outputs historical predicted temperature data at time k in the s-th historical detection period, where m is the number of historical detection periods, n is the number of times within a detection period, k≤n, s≤m, and k, n, s, and m are all positive integers; the temperature prediction model is trained according to the training loss function to obtain the trained temperature prediction model.

[0035] According to one embodiment of the present invention, the prediction error at the first moment of any detection cycle is smaller, the prediction result is more accurate, and the magnitude of the error is positively correlated with the moment within the detection cycle. In formula (1), The ratio of the historical feed rate data at time k in the s-th historical detection cycle to the historical feed rate data at time 1 is the ratio of the historical feed rate data at time k. The closer this ratio is to 1, the smaller the impact of the historical feed rate data change on the mold temperature. Therefore, the smaller the impact of the historical feed rate data change on the error of the predicted temperature data. The ratio of the historical injection pressure data at time k in the s-th historical detection cycle to the historical injection pressure data at time 1 is given. The closer this ratio is to 1, the smaller the impact of changes in historical injection pressure data on mold temperature. Consequently, the smaller the impact of changes in historical injection pressure data on the error of predicted temperature data is. This represents the ratio of the historical nozzle temperature data at time k in the s-th historical detection cycle to the historical nozzle temperature data at time 1. The closer this ratio is to 1, the smaller the impact of changes in historical nozzle temperature data on mold temperature, and thus the smaller the impact of changes in historical nozzle temperature data on the error of predicted temperature data. The product of the above three terms indicates a positive correlation between the feed rate data, injection pressure data, and nozzle temperature data and mold temperature. For example, a faster feed rate causes the material to flow rapidly in the mold, generating higher shear heat, thus raising the mold temperature. Higher injection pressure causes the material to contact the mold surface more tightly, accelerating heat transfer and leading to a rise in mold temperature. A higher nozzle temperature means the material is already overheated before entering the mold, causing the mold temperature to rise too quickly. Therefore, the larger the feed rate data, injection pressure data, and nozzle temperature data at time k in the s-th historical detection cycle are relative to the data at time 1, the greater the correlation between these values. and The larger the value, the higher the mold temperature, and the greater the impact on the error of the predicted temperature data. The relative error between the historical average temperature data at time k in the s-th historical detection period and the historical predicted temperature data at time k in the s-th historical detection period output by the temperature prediction model. The weight at time k is used to reasonably weight the relative errors at different times in the loss function. For the s-th historical detection period, the accuracy of the historical predicted temperature data at time k is usually higher than that at time k+1. That is, the longer the time interval between a certain time and time 1 in a certain historical detection period, the less accurate the prediction result is, and therefore the lower its weight is. Conversely, the more accurate the prediction result is, the higher its weight is. This represents a weighted summation of the relative errors at each moment within the s-th historical detection period. Let be the weight of the s-th historical detection cycle. The previous historical detection cycle is the first historical detection cycle. Longer mold usage time has various impacts on temperature measurement, such as heat exchanger blockage and cooling water channel obstruction. Therefore, the longer the time interval between a historical detection cycle and the current detection cycle, the more accurate the prediction result, and thus the higher its weight. Conversely, the shorter the time interval, the less accurate the prediction result, and thus the lower its weight. Using the weights of the historical detection cycles, the weighted sum of the relative errors at each moment within the s-th historical detection cycle is calculated to obtain the loss function of the temperature prediction model. During training, the model parameters are adjusted by backpropagating the loss function to reduce its value, thereby improving the accuracy of the temperature prediction model and obtaining the final temperature prediction model.

[0036] In this way, the influence of feed rate data, injection pressure data, and nozzle temperature data on mold temperature can be used to determine the error of the predicted temperature data. Based on this influence, as well as the relative error of historical predicted temperature data, and by setting weights according to the characteristic that the longer the time interval and the shorter the cycle interval, the lower the prediction accuracy, the loss function is trained to improve the objectivity and accuracy of the loss function. This reduces the training loss function during the training process, thereby improving the training intensity and efficiency, and increasing the accuracy of the temperature prediction model.

[0037] According to an embodiment of the present invention, in step S105, a temperature detection error score is determined based on the predicted temperature data and the average temperature data.

[0038] According to an embodiment of the present invention, step S105 includes: fitting the predicted temperature data and the time in the current detection cycle to determine the predicted temperature function in the current detection cycle; determining the predicted temperature derivative function based on the predicted temperature function; determining the predicted temperature change rate at multiple times in the current detection cycle based on the predicted temperature derivative function; fitting the average temperature data and the time in the current detection cycle to determine the average temperature function in the current detection cycle; determining the average temperature derivative function based on the average temperature function; determining the average temperature change rate at multiple times in the current detection cycle based on the average temperature derivative function; obtaining a predicted temperature state vector based on the predicted temperature data and predicted temperature change rate of the mold at multiple times in the current detection cycle; obtaining an average temperature state vector based on the average temperature data and average temperature change rate of the mold at multiple times in the current detection cycle; and determining a temperature detection error score based on the predicted temperature state vector and the average temperature state vector.

[0039] According to one embodiment of the present invention, the predicted temperature data is fitted to multiple moments in the current detection period to obtain a predicted temperature function describing the change of the predicted temperature data over time in the current detection period. The derivative of the predicted temperature function is determined, and the predicted temperature derivative function is substituted into the predicted temperature derivative function to determine the predicted temperature change rate for the multiple moments in the current detection period. Similarly, the average temperature data is fitted to multiple moments in the current detection period to obtain an average temperature function describing the change of the average temperature data over time in the current detection period. The derivative of the average temperature function is determined, and the average temperature change rate for the multiple moments in the current detection period is substituted into the average temperature derivative function to determine the average temperature change rate for the multiple moments in the current detection period. The predicted temperature data and the predicted temperature change rate are combined into a vector to obtain a predicted temperature state vector. Finally, the average temperature data and the average temperature change rate are combined into a vector to obtain an average temperature state vector.

[0040] According to one embodiment of the present invention, determining a temperature detection error score based on the predicted temperature state vector and the average temperature state vector includes: determining a temperature detection error score D according to formula (2).

[0041]

[0042] in, This is the average temperature data at the k-th moment of the current detection cycle. This represents the average temperature change rate at time k in the current detection cycle. This is the predicted temperature data at the k-th moment of the current detection cycle. This represents the predicted temperature change rate at time k in the current detection cycle. This represents the average temperature state vector at the k-th moment of the current detection cycle. Let be the predicted temperature state vector at the k-th moment of the current detection cycle, n be the number of moments in the detection cycle, k ≤ n, and both k and n are positive integers, and min is the minimum value function.

[0043] According to an embodiment of the present invention, in formula (2), The cosine similarity between the average temperature state vector at time k in the current detection cycle and the predicted temperature state vector at time k in the current detection cycle is calculated. The closer this cosine similarity is to 0, the greater the difference between the actual measured average temperature and the rate of change of the average temperature at time k, and the difference between the predicted temperature and the rate of change of the predicted temperature. In other words, it indicates that the mold temperature is abnormal and deviates significantly from the predicted reasonable value. For example, after the mold has been used for a long time, the heat exchange tube may experience a decrease in heat exchange efficiency due to impurity accumulation, causing abnormal mold temperature. Alternatively, excessively high external ambient temperatures may also cause abnormal mold temperature. The minimum cosine similarity between the average temperature state vector and the predicted temperature state vector at multiple times in the current detection cycle is taken as the temperature detection error score. That is, the maximum difference between the actual measured temperature and the predicted temperature of the mold is taken as the temperature detection error score of the mold. The larger this temperature detection error score, the greater the degree of abnormality in the mold temperature during material injection.

[0044] In this way, the temperature detection error score can be determined by predicting the temperature state vector and the average temperature state vector, enabling real-time monitoring and anomaly detection of the mold temperature during the material injection process. This allows the material to be processed under suitable temperature conditions, improving material performance and molding quality.

[0045] According to one embodiment of the present invention, in step S106, the mold temperature detection is determined to be qualified by comparing the temperature detection error score with the temperature detection error score threshold.

[0046] According to one embodiment of the present invention, determining whether the mold temperature detection is qualified based on the temperature detection error score and the temperature detection error score threshold includes: obtaining the first condition C1 and the second condition C2 according to formula (3).

[0047]

[0048] Where D is the temperature detection error score, D p The temperature detection error scoring threshold is set; if the first condition C1 is met, the mold temperature detection is determined to be unqualified; if the second condition C2 is met, the mold temperature detection is determined to be qualified.

[0049] According to an embodiment of the present invention, in formula (3), the first condition C1 indicates that the temperature detection error score is greater than or equal to the temperature detection error score threshold, the mold temperature is detected as abnormal, and the mold temperature detection is unqualified. The second condition C2 indicates that the temperature detection error score is less than the temperature detection error score threshold, the mold temperature is not detected as abnormal, and the mold temperature detection is qualified.

[0050] In this way, it is possible to determine whether the mold temperature detection is qualified through the temperature detection error score and the temperature detection error score threshold. If the mold temperature detection is qualified, it can be judged that the temperature of the mold during the material injection process remains within a reasonable range, thereby improving the consistency of the material properties.

[0051] According to the mold temperature detection method of the embodiment of the present invention, through the trained temperature prediction model, combined with the feeding speed data, injection pressure data and nozzle temperature data during the injection molding process, the mold temperature when injecting materials into the mold is predicted, which can improve the accuracy of mold temperature prediction. By comparing the predicted temperature data output by the temperature prediction model with the average temperature data actually measured by the mold, abnormal changes in the mold temperature can be detected in a timely manner, thereby reducing the quality problems of the finished products caused by temperature and improving the material properties and molding quality. When training the temperature prediction model, the influence of the feeding speed data, injection pressure data and nozzle temperature data on the mold temperature can be used to determine the influence of the above data on the error of the predicted temperature data. Based on this influence, the relative error of the historical predicted temperature data, and the characteristic that the longer the time interval and the shorter the cycle interval, the lower the prediction accuracy, weights are set to train the loss function to improve the objectivity and accuracy of the loss function. Thus, during the training process, the training loss function is reduced, the training intensity and training efficiency can be improved, and the accuracy of the temperature prediction model can be increased. When determining the temperature detection error score, the temperature detection error score can be determined through the predicted temperature state vector and the average temperature state vector, which can achieve real-time monitoring and abnormal detection of the mold temperature during the material injection process, so that the material can be processed under suitable temperature conditions, improving the material properties and molding quality. When determining whether the mold temperature detection is qualified, it is possible to determine whether the mold temperature detection is qualified through the temperature detection error score and the temperature detection error score threshold. If the mold temperature detection is qualified, it can be judged that the temperature of the mold during the material injection process remains within a reasonable range, thereby improving the consistency of the material properties.

[0052] Figure 2An exemplary block diagram of a mold temperature detection system according to an embodiment of the present invention is shown. The system includes: an infrared image module for dividing the mold into multiple regions and acquiring infrared images of each region at multiple moments in the current detection cycle; an average temperature data module for determining the average temperature data of the mold at multiple moments in the current detection cycle based on the infrared images; an injection molding machine data module for acquiring injection molding machine feed rate data, injection pressure data, and nozzle temperature data at multiple moments in the current detection cycle; a predicted temperature data module for processing the feed rate data, injection pressure data, and nozzle temperature data using a trained temperature prediction model to obtain predicted temperature data at multiple moments in the current detection cycle; a temperature detection error scoring module for determining a temperature detection error score based on the predicted temperature data and the average temperature data; and a pass / fail judgment module for determining whether the mold temperature detection is qualified based on the temperature detection error score and a temperature detection error score threshold.

[0053] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are merely examples and do not limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functions and structural principles of the present invention have been demonstrated and explained in the embodiments, and any variations or modifications may be made to the implementation of the present invention without departing from the stated principles.

Claims

1. A method for detecting mold temperature, characterized in that, include: The mold is divided into multiple regions, and infrared images of each region are obtained at multiple moments in the current detection cycle. Based on the infrared image, determine the average temperature data of the mold at multiple moments in the current detection cycle; At multiple moments in the current detection cycle, the feed rate data, injection pressure data, and nozzle temperature data of the injection molding machine are acquired; the feed rate data, injection pressure data, and nozzle temperature data are processed using a trained temperature prediction model to obtain predicted temperature data at multiple moments in the current detection cycle; and a temperature detection error score is determined based on the predicted temperature data and the average temperature data. Based on the temperature detection error score and the temperature detection error score threshold, determine whether the mold temperature detection is qualified; the training steps of the temperature prediction model include: acquiring the historical average temperature data of the mold at multiple moments in multiple historical detection cycles, wherein the previous historical detection cycle is the first historical detection cycle; acquiring the historical feed rate data, historical injection pressure data, and historical nozzle temperature data of the injection molding machine at multiple moments in multiple historical detection cycles; processing the historical feed rate data, historical injection pressure data, and historical nozzle temperature data through the temperature prediction model to obtain historical predicted temperature data at multiple moments in multiple historical detection cycles; determining the loss function of the temperature prediction model based on the historical average temperature data, historical feed rate data, historical injection pressure data, historical nozzle temperature data, and historical predicted temperature data; training the temperature prediction model based on the training loss function to obtain the trained temperature prediction model; determining the loss function of the temperature prediction model based on the historical average temperature data, historical feed rate data, historical injection pressure data, historical nozzle temperature data, and historical predicted temperature data, including: according to the formula Determine the loss function Loss for the temperature prediction model, where M s，k M represents the historical feed rate data at time k in the s-th historical detection cycle. s，1 T represents the historical feed rate data at the first moment of the s-th historical detection cycle. s，k For the historical injection pressure data at time k in the s-th historical detection cycle, P s，1 T represents the historical injection pressure data at time 1 of the s-th historical detection cycle. s，k T represents the historical nozzle temperature data at time k in the s-th historical detection cycle. s，1 This refers to the historical nozzle temperature data at the first moment of the s-th historical detection cycle. This refers to the historical average temperature data at time k in the s-th historical detection period. The temperature prediction model outputs historical predicted temperature data at time k in the s-th historical detection period, where m is the number of historical detection periods, n is the number of times within a detection period, k ≤ n, s ≤ m, and k, n, s, and m are all positive integers. The temperature prediction model is trained according to the training loss function to obtain the trained temperature prediction model. A temperature detection error score is determined based on the predicted temperature data and the average temperature data, including: fitting the predicted temperature data to the times in the current detection period to determine the predicted temperature function in the current detection period; determining the predicted temperature derivative function based on the predicted temperature function; determining the predicted temperature change rate at multiple times in the current detection period based on the predicted temperature derivative function; and applying the average temperature data... The temperature data is fitted to the time points in the current detection cycle to determine the average temperature function for the current detection cycle; based on the average temperature function, the average temperature derivative function is determined; based on the average temperature derivative function, the average temperature change rate at multiple times in the current detection cycle is determined; based on the predicted temperature data and predicted temperature change rate of the mold at multiple times in the current detection cycle, a predicted temperature state vector is obtained; based on the average temperature data and average temperature change rate of the mold at multiple times in the current detection cycle, an average temperature state vector is obtained; based on the predicted temperature state vector and the average temperature state vector, a temperature detection error score is determined; the temperature detection error score is determined based on the predicted temperature state vector and the average temperature state vector, including: according to the formula... Determine the temperature detection error score D, where, This is the average temperature data at the k-th moment of the current detection cycle. This represents the average temperature change rate at time k in the current detection cycle. This is the predicted temperature data at the k-th moment of the current detection cycle. This represents the predicted temperature change rate at time k in the current detection cycle. This represents the average temperature state vector at the k-th moment of the current detection cycle. Let be the predicted temperature state vector at the k-th moment of the current detection cycle, n be the number of moments in the detection cycle, k ≤ n, and both k and n are positive integers, and min is the minimum value function.

2. The mold temperature detection method according to claim 1, characterized in that, Determining the average temperature data of the mold at multiple moments in the current detection cycle based on the infrared image includes: obtaining the average regional temperature data of each region at multiple moments in the current detection cycle based on the pixel values ​​of the pixels in the infrared image; averaging the average regional temperature data to determine the average temperature data of the mold at multiple moments in the current detection cycle.

3. The mold temperature detection method according to claim 1, characterized in that, Based on the temperature detection error score and the temperature detection error score threshold, determine whether the mold temperature detection is qualified, including: according to the formula Obtain the first condition C1 and the second condition C2, where D is the temperature detection error score. p The temperature detection error scoring threshold is set; if the first condition C1 is met, the mold temperature detection is determined to be unqualified; if the second condition C2 is met, the mold temperature detection is determined to be qualified.

4. A mold temperature detection system for performing the mold temperature detection method as described in any one of claims 1-3, characterized in that, include: The infrared imaging module is used to divide the mold into multiple regions and acquire infrared images of each region at multiple moments in the current detection cycle. The average temperature data module is used to determine the average temperature data of the mold at multiple moments in the current detection cycle based on the infrared image. The injection molding machine data module is used to acquire data on the injection molding machine's feed rate, injection pressure, and nozzle temperature at multiple points in the current testing cycle. The predicted temperature data module is used to process the feed rate data, the injection pressure data and the nozzle temperature data through a trained temperature prediction model to obtain predicted temperature data for multiple moments in the current detection cycle. The temperature detection error scoring module is used to determine the temperature detection error score based on the predicted temperature data and the average temperature data. The qualification module is used to determine whether the mold temperature detection is qualified based on the temperature detection error score and the temperature detection error score threshold.

Images