A cooling adaptive control method and system for an injection mold, an electronic device, and a storage medium

Abstract

The application provides a cooling adaptive control method and system of an injection mold, an electronic device and a storage medium, and relates to the technical field of temperature control. The method comprises the following steps: acquiring a real-time temperature, cooling parameters and a target temperature of the mold; dynamically estimating the real-time temperature to obtain an optimal value, a change rate and a prediction result; inputting the change rate, the cooling parameters and the target temperature into an adaptive compensation model to obtain control parameters; executing cooling after correcting the cooling parameters according to the control parameters; in the cooling process, acquiring a real-time temperature value of the injection mold, updating the temperature prediction result based on the newly acquired real-time temperature value, judging whether the updated temperature prediction result meets a preset demolding condition, and executing a corresponding cooling strategy based on the judgment result. The application solves the problem that the existing injection cooling parameters need to be controlled independently and cannot be optimized cooperatively, which leads to a long cooling time and low injection production efficiency, and has the effect of improving the production efficiency of the injection mold.

Description

Technical Field

[0001] This invention relates to the field of temperature control technology, and in particular to an adaptive cooling control method, system, electronic device, and storage medium for injection molds. Background Technology

[0002] Injection molding is a core manufacturing process that involves injecting molten plastic into a mold cavity under high pressure, followed by cooling and solidification to obtain the finished product. It is widely used in the manufacturing of automotive parts, consumer electronics, medical devices, and everyday consumer goods. In the entire injection molding cycle, the cooling stage typically occupies a significant amount of time, and its efficiency and uniformity directly determine the surface quality, dimensional accuracy, internal stress distribution, and final production efficiency of the finished product. With the increasing demands for precision molding in the manufacturing industry, achieving a rapid, uniform, and controllable cooling process has become a pressing issue.

[0003] Existing injection molding cooling control methods typically treat mold temperature, cooling water flow rate, and cooling time as three independent process parameters, manually set or simply controlled in an open-loop manner. Operators set a fixed cooling water flow rate and a conservative cooling time based on experience or process instructions, keeping them constant throughout the production cycle to ensure basic cooling requirements. Building upon this, to further improve control accuracy, some solutions introduce PID control technology for closed-loop regulation of the mold temperature, using a linear combination of proportional, integral, and derivative components to suppress temperature deviations.

[0004] However, the aforementioned existing technical solutions have the following drawbacks: First, there is a strong coupling relationship between mold temperature, cooling water flow rate, and cooling time. Setting these three independently makes it impossible to adjust them in conjunction with the real-time process status, resulting in difficulty in accurately matching cooling parameters with actual heat exchange requirements. Second, PID control struggles to cope with the large thermal inertia, nonlinearity, and strong hysteresis characteristics inherent in injection molds. Temperature fluctuations can reach ±5℃ or more, and operators often set the cooling time much higher than the theoretical minimum to ensure product quality, resulting in a large amount of ineffective conservative margin. Therefore, these problems prevent the cooling stage of injection molds from achieving the shortest cycle time while ensuring product quality, thus leading to low production efficiency for injection molds. Summary of the Invention

[0005] In view of the above-mentioned shortcomings in the existing technology, the purpose of this invention is to provide an adaptive cooling control method for injection molds, which has the characteristic of improving the production efficiency of injection molds.

[0006] The above-mentioned objective of this invention is achieved through the following technical solution: An adaptive cooling control method for injection molds, comprising: Obtain the real-time temperature value, cooling process parameters, and target temperature value of the injection mold; The real-time temperature value is dynamically processed to obtain the optimal temperature value, the rate of temperature change, and the temperature prediction result. The temperature change rate, the cooling process parameters, and the target temperature value are input into a preset adaptive compensation model to obtain cooling control parameters. The cooling process parameters are corrected based on the cooling control parameters, and cooling is performed based on the corrected cooling process parameters. During the cooling process, the real-time temperature value of the injection mold is acquired, and the temperature prediction result is updated based on the newly acquired real-time temperature value to obtain the updated temperature prediction result. Determine whether the updated temperature prediction results meet the preset demolding conditions, and execute the corresponding cooling strategy based on the determination results.

[0007] By adopting the above technical solution, adaptive linkage adjustment of cooling water flow and cooling time is realized, and temperature is continuously predicted and demolding endpoint is intelligently determined during the cooling process. This effectively shortens the cooling cycle and improves injection molding production efficiency while ensuring product quality.

[0008] Preferably, the step of dynamically processing the real-time temperature value to obtain the optimal temperature value, the rate of temperature change, and the temperature prediction result includes: An extended Kalman filter is used to filter noise from the real-time temperature value to obtain the optimal temperature value. The temperature change rate is obtained by calculating the temperature change per unit time based on the optimal temperature value. The optimal temperature value is input into a preset mold heat conduction model to predict the mold temperature change trend within a preset time window, thus obtaining the temperature prediction result.

[0009] By adopting the above technical solution, the extended Kalman filter is used to filter out temperature acquisition noise, and the mold heat conduction model is combined to predict future temperature change trends, thereby improving the accuracy of temperature data and the reliability of prediction results.

[0010] Preferably, the preset adaptive compensation model includes a fuzzification layer, a fuzzy inference layer, a defuzzification layer, and an output layer connected in sequence; the step of inputting the temperature change rate, the cooling process parameters, and the target temperature value into the preset adaptive compensation model to obtain cooling control parameters includes: The temperature change rate, the cooling process parameters, and the target temperature value are fuzzified using the fuzzification layer to obtain fuzzy linguistic variables. The fuzzy inference layer performs fuzzy inference on the fuzzy linguistic variables based on a preset three-parameter coupling control rule base to obtain fuzzy output variables; The fuzzy output variable is defuzzified through the defuzzification layer to obtain a precise control quantity; The cooling water flow rate setpoint and cooling time correction coefficient in the precise control quantity are output through the output layer as the cooling control parameters.

[0011] By adopting the above technical solution, the adaptive compensation model is used to perform fuzzy reasoning on the temperature change rate, cooling process parameters and target temperature value, decouple the strong coupling relationship between mold temperature, cooling water flow rate and cooling time, and output the coordinated matching flow rate set value and time correction coefficient, thus realizing the adaptive linkage adjustment of the three parameters.

[0012] Preferably, the cooling process parameters include the current cooling water flow rate; the step of correcting the cooling process parameters based on the cooling control parameters and performing cooling based on the corrected cooling process parameters includes: Based on the cooling water flow rate setting value in the cooling control parameters, the current cooling water flow rate is corrected to obtain the updated cooling water flow rate. A preset cooling time algorithm is used to calculate the cooling time for the updated cooling water flow rate and the optimal temperature value to obtain the basic cooling time; The target cooling time is obtained by combining the cooling time correction factor with the base cooling time. Based on the target cooling time and the updated cooling water flow rate, the flow of cooling water in the cooling circuit of the injection mold is controlled.

[0013] By adopting the above technical solution, the current flow rate is dynamically corrected based on the flow rate setpoint, and the cooling time is recalculated based on the updated flow rate and optimal temperature values. This allows the cooling water flow rate and cooling time to be adjusted in tandem with real-time operating conditions, avoiding over-cooling or under-cooling caused by fixed parameters.

[0014] Preferably, determining whether the updated temperature prediction result meets the preset demolding conditions includes: Extract the predicted temperature value from the updated temperature prediction results; Determine whether the highest value among the predicted temperature values ​​is lower than a preset demolding temperature safety threshold, and whether the difference between the highest and lowest values ​​among the predicted temperature values ​​is lower than a preset uniformity requirement threshold. When the highest value is lower than the demolding temperature safety threshold and the difference is lower than the uniformity requirement threshold, it is determined that the preset demolding condition is met. Otherwise, it is determined that the preset demolding conditions are not met.

[0015] By adopting the above technical solution, based on the temperature prediction results, it is determined whether the highest temperature is lower than the demolding safety threshold and whether the temperature difference at each point meets the uniformity requirements, ensuring that the product is fully cured and the temperature is uniform during demolding, thus avoiding quality defects caused by local overheating or excessive temperature difference.

[0016] Preferably, the step of executing the corresponding cooling strategy based on the judgment result includes: When the judgment result is that the preset demolding conditions are met, the demolding execution strategy is executed. The demolding execution strategy is to generate a demolding command and stop supplying cooling water to the cooling circuit of the injection mold. When the judgment result is that the preset demolding condition is not met, a cyclic cooling strategy is executed. The cyclic cooling strategy is to jump to the step of obtaining the real-time temperature value of the injection mold, the cooling process parameters and the target temperature value until the preset demolding condition is met or the target cooling time is reached.

[0017] By adopting the above technical solution, cooling is stopped and demolding is performed immediately when the demolding conditions are met; if the conditions are not met, the process is iteratively optimized until the conditions are met, thus achieving the shortest cycle control of cooling as soon as the temperature reaches the target, effectively avoiding ineffective cooling time.

[0018] Preferably, when the determination result indicates that the preset demolding condition is not met, a cyclic cooling strategy is executed. This cyclic cooling strategy involves reverting to the step of obtaining the real-time temperature value of the injection mold, cooling process parameters, and target temperature value until the preset demolding condition is met or the target cooling time is reached. This includes: Obtain the current cumulative cooldown time and determine whether the current cumulative cooldown time has reached the target cooldown time; If the current cumulative cooling time has not reached the target cooling time, then proceed to the step of obtaining the real-time temperature value of the injection mold, the cooling process parameters, and the target temperature value; If the current cumulative cooling time reaches the target cooling time, a timeout alarm signal is generated, and a safe shutdown strategy is executed.

[0019] By adopting the above technical solution, cumulative cooling time monitoring is introduced during the cyclic cooling process. Under normal conditions, continuous iterative optimization is carried out until the demolding condition is met. If the timeout is exceeded, an alarm is triggered and a safe shutdown is executed. This not only ensures the timeliness of control but also provides safety assurance for abnormal working conditions.

[0020] The second objective of this invention is to provide an adaptive cooling control system for injection molds, which improves the production efficiency of injection molds.

[0021] The second objective of this invention is achieved through the following technical solution: An adaptive cooling control system for injection molds includes: a data acquisition module for acquiring real-time temperature values, cooling process parameters, and target temperature values ​​of the injection mold; The dynamic processing module is used to dynamically process the real-time temperature value to obtain the optimal temperature value, the rate of temperature change, and the temperature prediction result. The parameter calculation module is used to input the temperature change rate, the cooling process parameters, and the target temperature value into a preset adaptive compensation model to obtain cooling control parameters. A cooling execution module is used to correct the cooling process parameters based on the cooling control parameters, and to perform cooling based on the corrected cooling process parameters; The prediction update module is used to acquire the real-time temperature value of the injection mold during the cooling process, and update the temperature prediction result based on the newly acquired real-time temperature value to obtain the updated temperature prediction result. The strategy judgment module is used to determine whether the updated temperature prediction results meet the preset demolding conditions, and to execute the corresponding cooling strategy based on the judgment results.

[0022] By adopting the above technical solutions, the modules work together to achieve dynamic processing of temperature data, adaptive correction of cooling parameters, real-time updating of prediction results, and intelligent judgment of demolding conditions, effectively improving the automation level and production efficiency of the injection molding cooling process.

[0023] The third objective of this invention is to provide an electronic device that improves the production efficiency of injection molds.

[0024] The above-mentioned third objective of this invention is achieved through the following technical solution: An electronic device includes a memory and a processor, wherein the memory stores a computer program capable of being loaded by the processor and executing the adaptive cooling control method for injection molds described in any of the preceding claims.

[0025] The fourth objective of this invention is to provide a computer-readable storage medium capable of storing corresponding programs, which facilitates the improvement of injection mold production efficiency.

[0026] The fourth objective of this invention is achieved through the following technical solution: A computer-readable storage medium storing a computer program capable of being loaded by a processor and executing the adaptive cooling control method for injection molds described in any of the preceding claims.

[0027] In summary, the present invention has at least one of the following beneficial technical effects: 1. This invention integrates real-time temperature values, cooling process parameters, and target temperature values, solving the problem of conservative time settings in existing methods, which not only shortens the molding cycle but also improves production efficiency; 2. This invention continuously updates the temperature prediction results during the cooling process and simultaneously determines whether the demolding conditions are met based on the highest predicted temperature value and the temperature difference. If the conditions are met, cooling is stopped immediately; if not, iterative optimization is performed until the conditions are met. It also introduces a cumulative cooling time monitoring and overtime safety shutdown mechanism, realizing the shortest cycle control of cooling as soon as the temperature reaches the target. This effectively shortens the cooling cycle and improves injection molding production efficiency while ensuring product quality. Attached Figure Description

[0028] Figure 1 This is a flowchart illustrating the steps of an adaptive cooling control method for injection molds provided in Embodiment 1 of the present invention.

[0029] Figure 2 This is a structural block diagram of a cooling adaptive control system for injection molds provided in Embodiment 2 of the present invention. Detailed Implementation

[0030] This invention provides an adaptive cooling control method and system for injection molds, addressing the technical problem that existing injection molding cooling parameters require independent control and cannot be optimized collaboratively, resulting in long cooling times and low injection molding production efficiency. It effectively improves the production efficiency of injection molds.

[0031] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0032] It should be noted that in this embodiment of the invention, all content involving object data must be obtained with the object's authorization and consent, and must comply with current laws and standards. If the embodiment involves personal information, it must ensure that the individual's consent has been obtained; if it involves sensitive information, the separate consent of the information subject must be obtained. The implementation of the entire embodiment should also be based on the object's authorization and consent.

[0033] It should be noted that the terms "first," "second," etc., used in this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The implementations described in the following exemplary embodiments do not represent all implementations consistent with this disclosure.

[0034] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship. Example 1

[0035] Please see Figure 1 The present invention provides an adaptive cooling control method for injection molds, comprising: It should be noted that the adaptive cooling control method for injection molds provided by this invention is applied to a platform, which includes: an injection mold, a temperature sensing unit, a cooling water circulation unit, and a control unit. The injection mold is made of metal and has a cavity and a cooling circuit inside. The cavity is used to contain molten plastic and shape it. The cooling circuit consists of several interconnected channels, with a cooling water inlet and a cooling water outlet at each end of the channel, which are used to guide the cooling medium to flow through the mold to achieve heat exchange.

[0036] The temperature sensing unit includes multiple thermocouple sensors, which are pre-embedded in key locations inside the injection mold (including the cavity surface, near the cooling circuit, and the mold core). Their signal output terminals are electrically connected to the analog input interface of the control unit via a data acquisition line, which is used to collect temperature data at various points in the mold in real time and upload it to the control unit.

[0037] The cooling water circulation unit is set up independently of the injection mold and includes a water pump, a water tank, a flow regulating valve, and external connecting pipes. Its outlet is sealed and connected to the cooling water inlet of the injection mold through a pipe, and its return outlet is sealed and connected to the cooling water outlet of the injection mold through a pipe. The control terminal of the flow regulating valve or the variable frequency pump of the cooling water circulation unit is electrically connected to the analog or digital output interface of the control unit to receive the flow regulation command issued by the control unit and change the flow rate of the cooling water flowing through the internal cooling circuit of the mold accordingly.

[0038] The control unit is an industrial computer, programmable logic controller (PLC) or microcontroller, which integrates a data acquisition module, a timer or real-time clock module, a storage module and a processing module. The input terminal of the control unit is electrically connected to the temperature sensing unit to receive real-time temperature data, and the output terminal of the control unit is electrically connected to the flow regulation actuator of the cooling water circulation unit to send control commands.

[0039] Step 101: Obtain the real-time temperature value, cooling process parameters, and target temperature value of the injection mold.

[0040] Real-time temperature value refers to the temperature data of each temperature measurement point at the current moment, which is collected in real time by thermocouple sensors that are pre-embedded in key positions inside the injection mold at a preset sampling frequency (e.g., 10Hz).

[0041] Cooling process parameters refer to the adjustable operating parameters that control the cooling process, including but not limited to the current cooling water flow rate and the current cooling time. The current cooling water flow rate is the volume of water flowing through the mold cooling circuit per unit time, usually in liters per minute (L / min), and is controlled by the flow regulating valve or frequency converter pump in the cooling water circulation unit. The current cooling time is the length of time elapsed from the start of this cooling stage to the current time, usually in seconds (s), and is recorded by the real-time clock module inside the control unit.

[0042] The target temperature value refers to the reference temperature threshold that the mold should reach, which is preset according to the heat distortion temperature of the plastic material used, the demolding safety requirements of the product, and the quality consistency requirements. It is usually lower than the heat distortion temperature of the material and a certain safety margin is reserved. For example, for ABS material, its heat distortion temperature is about 95℃-100℃, and the target temperature value can be set between 75℃-85℃ to ensure that the product is fully cured and to avoid demolding deformation due to excessive temperature.

[0043] In this embodiment of the invention, instantaneous temperature data of each temperature measurement point is collected in real time at a preset sampling frequency as the real-time temperature value, while the current cooling process parameters and target temperature value are read.

[0044] Step 102: Dynamically process the real-time temperature value to obtain the optimal temperature value, the rate of temperature change, and the temperature prediction result.

[0045] Preferably, step 102 may include the following sub-steps: S11. An extended Kalman filter is used to filter noise from the real-time temperature value to obtain the optimal temperature value.

[0046] The Extended Kalman Filter (EPF) is a recursive filtering algorithm used for state estimation of nonlinear systems. It uses a system state model and observation data to make the optimal estimate of noisy measurements through two steps: prediction and update, in order to filter out random interference and approximate the true state value.

[0047] First, based on the thermal conductivity characteristics of the injection mold, a state transition relationship for mold temperature and a sensor observation mapping relationship are established. Within each sampling period (e.g., 0.1 seconds), the extended Kalman filter performs a prediction step: predicting the prior temperature estimate for the current moment based on the optimal temperature estimate from the previous moment. Then, an update step is performed: the real-time acquired raw temperature measurements and the predicted values ​​are weighted and fused to calculate the optimal temperature estimate for the current moment. Through this recursive iteration, the extended Kalman filter gradually converges, outputting the optimal temperature value after noise filtering.

[0048] For example, suppose that at a certain sampling moment, the original temperature measurement is 82.3℃, while the actual mold temperature is approximately 80.5℃. The extended Kalman filter predicts the current prior estimate of 80.6℃ based on the optimal temperature value estimated at the previous moment (80.2℃). Then, the original measurement of 82.3℃ is used as the observation input, and after weighted fusion, the optimal temperature estimate of 81.2℃ is output.

[0049] In this embodiment of the invention, an extended Kalman filter is used to filter noise from the real-time temperature value to obtain the optimal temperature value, which is closer to the true temperature than the original measurement value, effectively suppressing the influence of measurement noise.

[0050] S12. Calculate the temperature change per unit time based on the optimal temperature value to obtain the temperature change rate.

[0051] The preset temperature change per unit time refers to the range of change of the optimal mold temperature from the start to the end of a predetermined fixed time period (e.g., 1 second, 2 seconds, or 0.5 seconds). The calculation method is: Temperature change = Optimal temperature at the end - Optimal temperature at the start. This value can be positive (temperature increases) or negative (temperature decreases).

[0052] The rate of temperature change refers to the amount of temperature change in the mold per unit time, reflecting how quickly the mold cools down during the cooling process.

[0053] In this embodiment of the invention, whenever the extended Kalman filter outputs a new optimal temperature value, the optimal temperature value and its corresponding timestamp are stored in a buffer. When the optimal temperature values ​​of the first and last moments within a preset unit time (e.g., 1 second) are accumulated in the buffer, the temperature change within that time period is calculated. That is, the optimal temperature value at the end of the time period is subtracted from the optimal temperature value at the beginning of the time period, and then the temperature change is divided by the preset unit time to obtain the current temperature change rate. It is worth mentioning that, in order to suppress the influence of instantaneous fluctuations on the calculation results, a moving average method can also be used to calculate the average value of the temperature change rate over multiple consecutive unit time periods as the final output temperature change rate.

[0054] S13. Input the optimal temperature value into the preset mold heat conduction model, predict the mold temperature change trend within the preset time window, and obtain the temperature prediction result.

[0055] A mold heat conduction model refers to a mathematical relationship established based on the physical laws of heat conduction. It is used to describe the evolution of heat transfer and temperature distribution inside the mold over time. Its inputs include the current temperature state and cooling conditions, and its output is a prediction of the temperature distribution at future times.

[0056] A preset time window refers to a fixed duration extending into the future from the current moment, such as 3 seconds, 5 seconds, or 10 seconds, used to limit the time range for temperature prediction.

[0057] Temperature prediction results refer to the sequence of predicted temperature values ​​for each temperature measuring point of the mold at various future times within the preset time window.

[0058] A heat conduction model for the injection mold is established in advance based on the mold's geometry, material thermophysical parameters (including density ρ, specific heat capacity c, and thermal conductivity λ), and the arrangement of the cooling circuit. This model is based on Fourier's law of heat conduction, and its three-dimensional partial differential equation for heat conduction is as follows:

[0059] In the formula, T is temperature, t is time, x, y, z are spatial coordinates, and Q is the internal heat source term.

[0060] The boundary conditions are determined by the convective heat transfer between the mold surface and the cooling water, and the expression is:

[0061] In the formula, h is the convective heat transfer coefficient. Both are fixed parameters preset according to mold design and cooling process requirements, representing the cooling water temperature.

[0062] The finite difference method is used to discretize the above partial differential equation in space and time. In the prediction process, the optimal temperature value of the current moment output by the extended Kalman filter is used as the initial condition, and the preset convective heat transfer coefficient and cooling water temperature are used as the boundary conditions. The temperature distribution at each future moment is calculated recursively according to a set small time step (e.g., 0.1 seconds). Each recursive step yields the predicted temperature value of each temperature measurement point at that moment. The above recursive process is repeated until the end of the preset time window is reached, thereby generating a set of temperature prediction values ​​arranged in chronological order.

[0063] In this embodiment of the invention, the optimal temperature value at the current moment is used as the initial condition. The model of mold heat conduction based on Fourier's law of heat conduction is substituted into the model. Combined with the preset boundary conditions, the finite difference method is used to calculate the temperature step by step until the preset time window is reached, thereby generating a sequence of predicted temperature values ​​for each future moment.

[0064] Step 103: Input the temperature change rate, cooling process parameters, and target temperature value into the preset adaptive compensation model to obtain the cooling control parameters.

[0065] The preset adaptive compensation model includes a fuzzification layer, a fuzzy inference layer, a defuzzification layer, and an output layer connected in sequence.

[0066] The preset adaptive compensation model refers to a fuzzy neural network model pre-built and stored in the control unit. It is used to dynamically calculate and output cooling control parameters based on the mold temperature change rate, cooling process parameters, and target temperature value. The model includes a fuzzification layer, a fuzzy inference layer, a defuzzification layer, and an output layer connected in sequence. It can decouple the strong coupling relationship between mold temperature, cooling water flow rate, and cooling time, and realize adaptive linkage adjustment of the three parameters.

[0067] The adaptive compensation model is constructed by combining offline training and online adaptation. In the offline stage, based on historical process data and expert experience, input and output samples under typical working conditions are extracted. The error backpropagation algorithm is used to pre-train the membership function parameters and network connection weights in the fuzzy neural network, so that the model initially has the ability to map parameters. In the online application stage, the model parameters are fine-tuned using an adaptive learning algorithm according to the temperature response and control effect in the actual injection molding process, so as to continuously match the changes in mold thermal state and process fluctuations, and ensure control accuracy and robustness.

[0068] Preferably, step 103 may include the following sub-steps: S21. The temperature change rate, cooling process parameters and target temperature value are fuzzified by a fuzzification layer to obtain fuzzy linguistic variables.

[0069] The fuzzification layer refers to the processing unit that maps precise numerical input quantities to qualitative descriptions of fuzzy sets through membership functions. It is the first functional layer in the adaptive compensation model.

[0070] Fuzzy linguistic variables refer to a form of variable that uses qualitative terms from natural language to represent the value of a variable. Essentially, they transform precise numerical values ​​into the membership degree of a fuzzy set through a membership function, thereby facilitating logical judgments by fuzzy inference rules.

[0071] For the temperature change rate, cooling water flow rate and target temperature value, three fuzzy subsets of small, medium and large are pre-defined, and a triangular membership function is used to describe the numerical distribution range of each subset. The triangular membership function is determined by three parameters: the left base point, the vertex and the right base point. The membership degree of the input value is 1 at the vertex, gradually decreases to 0 at the boundary, and is 0 when it exceeds the boundary.

[0072] It is understandable that, since the rate of temperature change, cooling water flow rate, and target temperature value have different physical meanings and numerical ranges, the triangular membership function parameters (i.e., the values ​​of the left base point, vertex, and right base point) used for the corresponding "small," "medium," and "large" fuzzy subsets of the three are independently set according to the actual working conditions and process requirements, and are different from each other. For example, the "small" rate of temperature change can correspond to the range of 0-2℃ / s, the "small" cooling water flow rate can correspond to the range of 0-10L / min, and the "small" target temperature value can correspond to the range below 75℃, and so on.

[0073] In this embodiment of the invention, the temperature change rate, cooling water flow rate and target temperature value are input into the fuzzification layer for fuzzification processing to obtain each input quantity and its corresponding membership value combination, which serves as a fuzzy linguistic variable.

[0074] S22. Fuzzy inference is performed on fuzzy linguistic variables through a fuzzy inference layer based on a preset three-parameter coupling control rule base to obtain fuzzy output variables.

[0075] The fuzzy inference layer refers to the core logic processing unit in the adaptive compensation model that connects the fuzzification layer and the defuzzification layer. Its function is to perform fuzzy logic inference on the input fuzzy linguistic variables based on a preset three-parameter coupled control rule base, and generate fuzzy output variables that reflect the control strategy.

[0076] The three-parameter coupled control rule library refers to a set of predefined fuzzy rules used to describe the relationship between the mold temperature change rate, cooling water flow rate, target temperature value and cooling control parameters. This rule library reflects the coupling characteristics between the three parameters and can output coordinated and matched control strategies according to different combinations of process states.

[0077] Fuzzy output variables refer to the control results obtained after processing by the fuzzy inference layer and represented in the form of fuzzy sets, including but not limited to cooling water flow rate setpoints and cooling time correction coefficients.

[0078] It should be noted that the fuzzy inference layer does not involve precise numerical calculations. Instead, it calculates the activation strength of each rule by matching multiple fuzzy rules in the form of "if-then" in parallel, and synthesizes the fuzzy sets of the consequents of all activated rules, and finally outputs fuzzy output variables in the form of membership degree distribution.

[0079] Understandably, based on a pre-defined three-parameter coupled control rule base, logical reasoning is performed on the input fuzzy linguistic variables to generate fuzzy output variables that reflect the control strategy. This rule base consists of several fuzzy rules in the form of "if-then", and each rule corresponds to a typical mapping relationship between process state and control action.

[0080] For example, a rule can be stated as follows: if the rate of temperature change is medium, the cooling water flow rate is medium, and the target temperature value is medium, then the cooling water flow rate setting value is medium, and the cooling time correction factor is small.

[0081] The fuzzy inference layer will simultaneously activate multiple rules that match the current input, and synthesize the outputs of each rule through a fuzzy inference mechanism (such as the Mamdani inference method) to finally obtain one or a set of fuzzy set output variables, i.e. fuzzy output variables.

[0082] In this embodiment of the invention, based on the fuzzy language variables output by the fuzzification layer at the current moment, all fuzzy rules in the three-parameter coupled control rule base are matched in parallel, and the output fuzzy sets of each rule's "rule" part are combined by taking the largest (or summing) of the fuzzy sets through the fuzzy inference mechanism to generate fuzzy output variables.

[0083] S23. The fuzzy output variables are defuzzified by the defuzzification layer to obtain the precise control quantity.

[0084] The defuzzification layer refers to the layer in an adaptive compensation model that converts fuzzy output variables into precise numerical values.

[0085] Precise control quantity refers to a single numerical instruction that can be directly recognized by downstream actuators after defuzzification.

[0086] For the two output variables, the cooling water flow rate setpoint and the cooling time correction coefficient, each corresponds to a membership distribution function in the output universe of discourse. The defuzzification layer calculates the centroid position of the region enclosed by the curve of each membership function and the horizontal axis. The horizontal coordinate value corresponding to the centroid point is taken as the final accurate output value. The formula for the centroid method is as follows:

[0087] In the formula, u is the value of the output variable. The integration is performed over the entire output universe to determine the membership degree corresponding to this value.

[0088] In practical discretization implementations, since membership functions are usually stored in the form of discrete sampling points, the integral can be approximated as a summation:

[0089] In the formula, N is the number of discrete sampling points on the output universe of discourse.

[0090] In this embodiment of the invention, after the defuzzification layer receives the fuzzy output variable from the fuzzy inference layer, it uses the center of gravity (COG) method to convert it into a precise control quantity.

[0091] S24. The cooling water flow rate setpoint and cooling time correction coefficient in the precise control quantities are output through the output layer as cooling control parameters.

[0092] The output layer, which is the last layer in the adaptive compensation model, is used to output the precise control quantity obtained from the defuzzification layer in a specified data format.

[0093] The cooling water flow rate setpoint refers to the target flow rate value output by the adaptive compensation model to guide the actuator of the cooling water circulation unit to adjust the flow rate. The unit is liters per minute (L / min). This setpoint is part of the precise control quantity and reflects the amount of cooling water flow required to achieve the optimal cooling effect under the current process conditions.

[0094] The cooling time correction factor is a dimensionless scaling factor output by the adaptive compensation model used to adjust the base cooling time. It typically ranges from 0.5 to 1.5. This correction factor reflects the degree of deviation between the current process state and the standard state. A factor less than 1 indicates that the cooling time can be shortened from the base cooling time, while a factor greater than 1 indicates that the cooling time needs to be extended, thus achieving dynamic adaptive adjustment of the cooling duration.

[0095] Cooling control parameters refer to a set of parameters obtained by the adaptive compensation model after fuzzification, fuzzy inference, defuzzification, and output layer processing, which are used to guide the execution of the cooling process.

[0096] In this embodiment of the invention, after the output layer receives the precise control quantity from the defuzzification layer, it extracts two specific values: the cooling water flow rate setpoint and the cooling time correction coefficient, and transmits them downstream as cooling control parameters.

[0097] To clearly explain the specific implementation of step 103, an example is provided: Assuming the current injection mold is in the middle of the cooling stage, the following input data is obtained after collection and dynamic processing: temperature change rate: −2.5°C / s, current cooling water flow rate: 15L / min, and target temperature value: 80°C.

[0098] The three precise values ​​mentioned above are input into the fuzzification layer: For the rate of temperature change, the preset range of the rate of temperature change for small is 0-2°C / s (peak at 1°C / s), for medium it is 1-4°C / s (peak at 2.5°C / s), and for large it is 3-6°C / s (peak at 4.5°C / s). After calculating the membership function of −2.5°C / s, the membership degree of small is 0.2, that of medium is 0.8, and that of large is 0.

[0099] For the current cooling water flow rate of 15L / min, the preset values ​​are: small 0-10L / min (peak 5L / min), medium 8-20L / min (peak 14L / min), and large 15-30L / min (peak 22L / min). The membership degree of 15L / min is 0 for small, 0.9 for medium, and 0.1 for large.

[0100] For the target temperature value of 80°C, the preset ranges are: small 70-78°C (peak 74°C), medium 75-85°C (peak 80°C), and large 82-95°C (peak 88°C). The membership degree of 80°C is 0 for small, 1.0 for medium, and 0 for large.

[0101] The fuzzy linguistic variables output by the fuzzification layer are: temperature change rate: {small: 0.2, medium: 0.8, large: 0}; cooling water flow rate: {small: 0, medium: 0.9, large: 0.1}; target temperature value: {small: 0, medium: 1.0, large: 0}.

[0102] After receiving the aforementioned fuzzy linguistic variables, the fuzzy inference layer performs parallel matching of the rules in the three-parameter coupled control rule base. The rule base contains the following typical rules (taking three of them as examples): Rule R1: IF temperature change rate is medium AND cooling water flow rate is medium AND target temperature value is medium, THEN cooling water flow rate setting value is medium, cooling time correction coefficient is small; Rule R2: IF temperature change rate is small AND cooling water flow rate is medium AND target temperature value is medium, THEN cooling water flow rate setting value is small, cooling time correction coefficient is large; Rule R3: IF temperature change rate is medium AND cooling water flow rate is large AND target temperature value is medium, THEN cooling water flow rate setting value is large, cooling time correction coefficient is medium.

[0103] For rule R1, the membership degrees of the first three conditions are 0.8, 0.9, and 1.0, respectively. The minimum value is taken as the activation strength of 0.8. The activation strength of rule R2 is min(0.2,0.9,1.0)=0.2. The activation strength of rule R3 is min(0.8,0.1,1.0)=0.1. The activation strengths of other rules are all 0 or close to 0.

[0104] The fuzzy inference layer truncates (min) the suggested output fuzzy set after each rule (such as the membership distribution curve corresponding to the flow rate set value) according to the activation intensity. Then, it synthesizes the output fuzzy sets of all activated rules by taking the maximum value (max) to obtain the fuzzy output variables: the membership distribution of the cooling water flow rate set value in the output universe of discourse 0-30L / min is mainly concentrated in the 10-18L / min range (peak value about 0.8), and the cooling time correction coefficient in the 0-1.5 range is mainly concentrated in the 0.7-1.0 range (peak value about 0.8).

[0105] The defuzzification layer uses the centroid method to transform the two fuzzy output variables: for the cooling water flow rate setpoint, the centroid of the region enclosed by its membership distribution curve and the horizontal axis is calculated, yielding an accurate value of 15.3 L / min. For the cooling time correction coefficient, the centroid of its membership distribution is calculated, yielding an accurate value of 0.85.

[0106] The output layer extracts the two precise values ​​mentioned above and uses the cooling water flow rate setpoint of 15.3 L / min and the cooling time correction factor of 0.85 as the cooling control parameters.

[0107] Step 104: Correct the cooling process parameters based on the cooling control parameters, and perform cooling based on the corrected cooling process parameters.

[0108] Cooling process parameters include the current cooling water flow rate.

[0109] Preferably, step 104 may include the following sub-steps: S31. Based on the cooling water flow rate setting value in the cooling control parameters, the current cooling water flow rate is corrected to obtain the updated cooling water flow rate.

[0110] In this embodiment of the invention, the cooling water flow rate setpoint is first parsed from the cooling control parameters, and the currently executed cooling water flow rate is obtained. The deviation between the two is calculated. If the setpoint is greater than the current flow rate, the cooling water flow rate is increased; if the setpoint is less than the current flow rate, the cooling water flow rate is decreased; if the deviation is within the preset dead zone range (e.g., ±0.5L / min), the current flow rate is kept unchanged. After the adjustment is completed, the adjusted actual flow rate is used as the updated cooling water flow rate.

[0111] S32. The cooling time is calculated by using a preset cooling time algorithm to calculate the cooling time for the updated optimal values ​​of cooling water flow and temperature, and the basic cooling time is obtained.

[0112] The preset cooling time algorithm refers to the calculation formula stored in the control unit in advance to calculate the theoretical cooling time based on the current mold temperature and cooling water flow rate. The algorithm is based on the basic principles of heat transfer and takes into account factors such as mold volume, mold material thermal properties, heat transfer area, total heat transfer coefficient and logarithmic mean temperature difference. It can quantitatively describe the functional relationship between cooling water flow rate, mold temperature and required cooling time.

[0113] The basic cooling time refers to the theoretical shortest time required to cool the mold from its current temperature to the preset demolding temperature, calculated using a preset cooling time algorithm, under the current cooling water flow rate and mold temperature conditions. The unit is seconds (s).

[0114] The specific calculation formula for the preset cooldown time algorithm is as follows:

[0115] In the formula, Based on the cooldown time, For mold volume, For the density of the mold material, The specific heat capacity of the mold material. The average temperature difference between the plastic melt and the cooling water is calculated from the optimal temperature and the cooling water temperature. U is the overall heat transfer coefficient, which is obtained by looking up the corresponding relationship through experimental calibration based on the updated cooling water flow rate. A is the heat exchange area, and is the logarithmic mean temperature difference.

[0116] It should be noted that there is a non-linear positive correlation between the overall heat transfer coefficient U and the cooling water flow rate. This relationship is determined through prior experimental calibration: under stable mold conditions, the overall heat transfer coefficient corresponding to different cooling water flow rates is measured to form a flow rate-heat transfer coefficient comparison table or a fitting function curve. When actually calculating the basic cooling time, the updated cooling water flow rate is linearly interpolated in the comparison table to obtain the U value corresponding to the current flow rate.

[0117] The specific formula for calculating the logarithmic mean temperature difference is:

[0118] In the formula, The initial temperature of the plastic melt (characterized by the optimal temperature value). and These are the inlet and outlet temperatures of the cooling water, respectively.

[0119] The average temperature difference between the plastic melt and the cooling water can be expressed as the arithmetic mean temperature difference. Approximate calculations are performed to simplify the operation.

[0120] It should be noted that the mold volume is directly determined by the mold design dimensions and can be a fixed constant. The mold material density and specific heat capacity are determined by the materials used in the mold and can be fixed constants. The heat exchange area is determined by the structural design of the mold cooling circuit and can be a fixed constant. The logarithmic mean temperature difference can be a preset typical value or collected in real time by a temperature sensor.

[0121] In this embodiment of the invention, the above parameters are substituted into a preset cooling time algorithm for calculation to obtain the theoretical shortest time required to cool the mold from the current temperature to the demolding temperature under the current cooling water flow rate and mold temperature conditions, which is the basic cooling time.

[0122] S33. Combine the cooling time correction factor with the base cooling time to calculate the target cooling time.

[0123] The target cooling time refers to the final cooling duration used to actually control the cooling process after the cooling time correction factor is calculated together with the base cooling time.

[0124] Fusion computing uses multiplication operations, and the calculation formula is as follows:

[0125] In the formula, For the target cooldown time, This is a correction factor for cooling time.

[0126] when When <1, it means that the cooling time can be appropriately shortened under the current process conditions; A value >1 indicates that the cooling time needs to be extended to ensure the product is fully cured; when When =1, the base cooldown time is directly used as the target cooldown time.

[0127] In this embodiment of the invention, after the control unit obtains the base cooling time and the cooling time correction coefficient, it multiplies the two to obtain the target cooling time.

[0128] S34. Based on the target cooling time and the updated cooling water flow rate, control the flow of cooling water in the cooling circuit of the injection mold.

[0129] In this embodiment of the invention, the updated cooling water flow rate is used as the execution flow rate for the current cooling stage. By adjusting the opening of the flow regulating valve or the speed of the variable frequency water pump in the cooling water circulation unit, the actual flow rate is maintained near the set value. At the same time, the timer is started with the target cooling time as the planned duration of this cooling stage.

[0130] Step 105: During the cooling process, obtain the real-time temperature value of the injection mold, and update the temperature prediction result based on the newly obtained real-time temperature value to obtain the updated temperature prediction result.

[0131] In this embodiment of the invention, after cooling begins, the real-time temperature value of the injection mold is continuously acquired from each temperature measurement point according to a preset sampling period (e.g., 0.5 seconds). After acquiring a new set of real-time temperature values, they are input into the dynamic processing flow adopted in step 102, that is, the extended Kalman filter is re-executed to obtain a new optimal temperature value, and the optimal temperature value is substituted into the mold heat conduction model. Taking the current moment as a new starting point, the mold temperature change trend within the preset time window is re-predicted, thereby obtaining an updated temperature prediction result. This update process is repeated in each sampling period, so that the temperature prediction result can be continuously corrected with the real-time temperature change.

[0132] To improve the cooling uniformity control of multi-cavity molds, the temperature distribution of each cavity can be monitored in real time during the cooling process, and the cooling non-uniformity of each cavity can be calculated. In the formula, Let represent the measured temperature values ​​of the i cavities, where i = 1, 2, ..., n, and n is the total number of cavities in the mold. The average measured temperature of all cavities is given when any cavity... When the temperature exceeds the preset threshold, the flow rate of the corresponding cooling circuit of the cavity is adjusted individually according to the direction of the deviation: if the temperature is too high, the flow rate is increased to enhance cooling; if the temperature is too low, the flow rate is decreased to slow down cooling. In this way, the temperature of each cavity is balanced through flow rate adjustment, thereby improving the consistency of product quality of each cavity in a multi-cavity mold.

[0133] Step 106: Determine whether the updated temperature prediction result meets the preset demolding conditions, and execute the corresponding cooling strategy based on the determination result.

[0134] Preferably, step 106 may include the following sub-steps: S41. Extract the predicted temperature value from the updated temperature prediction results.

[0135] Predicted temperature values ​​refer to the values ​​obtained by using a mold heat conduction model to estimate the temperature at various temperature measurement points inside the injection mold at a certain future moment or within a future time window.

[0136] In this embodiment of the invention, the updated temperature prediction result includes the predicted temperature data of multiple temperature measuring points inside the mold at several discrete time steps in the future. The predicted temperature value corresponding to each temperature measuring point is extracted to form a set of predicted temperature values. This set includes the current predicted temperature of each temperature measuring point, the predicted temperature at each future time, and the highest and lowest values ​​therein.

[0137] S42. Determine whether the highest value in the predicted temperature is lower than the preset demolding temperature safety threshold, and whether the difference between the highest and lowest values ​​in the predicted temperature is lower than the preset uniformity requirement threshold.

[0138] The preset demolding temperature safety threshold refers to the upper limit of the mold temperature set in advance based on the heat distortion temperature of the plastic material and the demolding safety requirements of the product. It is usually the heat distortion temperature minus a certain safety margin to ensure that the product is fully cured when demolded and will not deform due to excessive temperature.

[0139] The preset uniformity threshold refers to the maximum allowable temperature difference limit between various temperature measurement points of the mold, which is set in advance to ensure the consistency of product quality. It is used to judge the uniformity of the temperature field of the mold and avoid quality problems such as uneven product shrinkage and uneven internal stress distribution caused by excessive local temperature difference.

[0140] In this embodiment of the invention, the highest and lowest values ​​are found from the predicted temperature values, and two judgments are performed: the first judgment is to compare the highest value in the predicted temperature values ​​with a preset demolding temperature safety threshold to confirm whether the highest value is lower than the threshold; the second judgment is to calculate the difference between the highest and lowest values ​​in the predicted temperature values ​​and compare the difference with a preset uniformity requirement threshold to confirm whether the difference is lower than the threshold.

[0141] S43. When the highest value is lower than the safe threshold for demolding temperature and the difference is lower than the threshold for uniformity requirement, the preset demolding conditions are met.

[0142] Preset demolding conditions refer to pre-set criteria for determining whether an injection mold is qualified for safe demolding. These criteria include at least two parallel conditions: First, the highest predicted temperature at each temperature measuring point inside the mold is lower than the preset safe demolding temperature threshold, ensuring that the product has been fully cured and will not deform due to excessive temperature during demolding. Second, the difference between the highest and lowest predicted temperatures at each temperature measuring point is lower than the preset uniformity requirement threshold, ensuring that the temperature distribution of the mold is uniform.

[0143] In this embodiment of the invention, when the control unit determines that the highest value among the predicted temperature values ​​is lower than the preset demolding temperature safety threshold, and at the same time the difference between the highest and lowest predicted temperature values ​​is lower than the preset uniformity requirement threshold, it is determined that the current mold state meets the preset demolding conditions. This determination result indicates that within the prediction time window, the temperature of each temperature measuring point of the mold has dropped below the demolding safety temperature, and the internal temperature distribution of the mold is uniform. The product has been fully cured and has a uniform quality state, and can be safely demolded without causing quality defects such as deformation, warping, or excessive internal stress.

[0144] S44. Otherwise, it is determined that the preset demolding conditions are not met.

[0145] In this embodiment of the invention, when the highest value of the predicted temperature is not lower than the preset demolding temperature safety threshold, or when the difference between the highest and lowest values ​​of the predicted temperature is not lower than the preset uniformity requirement threshold, it is determined that the current mold state does not meet the preset demolding conditions. This determination result indicates that the mold has not yet reached the temperature requirement or temperature uniformity requirement required for safe demolding. If demolding is forced at this time, it may lead to defects such as product deformation, insufficient curing, or inconsistent quality.

[0146] Preferably, step 106 may further include the following sub-steps: S51. When the judgment result is that the preset demolding conditions are met, the demolding execution strategy is executed. The demolding execution strategy is to generate a demolding command and stop supplying cooling water to the cooling circuit of the injection mold.

[0147] In this embodiment of the invention, when the preset demolding conditions are met, a demolding command is immediately generated and sent to the injection molding machine's execution system to initiate the demolding action. Simultaneously, a stop cooling command is issued to shut off the cooling water supply and cut off the flow of cooling water in the mold cooling circuit. Through the above operations, the cooling stage ends as soon as the demolding conditions are met, avoiding unnecessary continued cooling and achieving the shortest cycle control of cooling as soon as the temperature reaches the target. It is worth mentioning that the demolding command generation and cooling stop are executed synchronously, ensuring that the product enters the demolding stage immediately after reaching a safe demolding state, thereby effectively shortening the molding cycle and improving production efficiency.

[0148] S52. When the judgment result is that the preset demolding conditions are not met, the cyclic cooling strategy is executed. The cyclic cooling strategy is to jump to the step of obtaining the real-time temperature value of the injection mold, the cooling process parameters and the target temperature value until the preset demolding conditions are met or the target cooling time is reached.

[0149] Preferably, S52 may include the following sub-steps: S1. Obtain the current cumulative cooldown time and determine whether the current cumulative cooldown time has reached the target cooldown time.

[0150] The current cumulative cooling time refers to the total time elapsed from the start of the cooling phase of this injection molding cycle to the present moment.

[0151] In this embodiment of the invention, during the execution of the cyclic cooling strategy, the time elapsed from the start of the current cooling phase to the current time is recorded in real time as the current cumulative cooling time. During each cyclic iteration, the current cumulative cooling time is compared with the calculated target cooling time to determine whether the current cumulative cooling time has reached or exceeded the target cooling time.

[0152] S2. If the current cumulative cooling time has not reached the target cooling time, then proceed to the step of obtaining the real-time temperature value of the injection mold, cooling process parameters, and target temperature value.

[0153] In this embodiment of the invention, when it is determined that the current cumulative cooling time has not reached the target cooling time, it indicates that the cooling process is still within the allowable time range and has not exceeded the planned duration. At this time, the cooling is not stopped, but the process jumps back to step 101 to reacquire the real-time temperature value of the injection mold, the cooling process parameters, and the target temperature value. Then, steps 102 to 106 are executed sequentially, including dynamically processing the real-time temperature value to obtain the updated optimal temperature value, temperature change rate, and temperature prediction result, re-calling the adaptive compensation model to obtain the cooling control parameters, and correcting the cooling process parameters again if necessary. Through the above iterative cycle, the temperature status and prediction results are continuously updated in each sampling period until the preset demolding conditions are met or the cumulative cooling time reaches the target cooling time, thereby realizing continuous monitoring and adaptive control of demolding conditions within the safe time boundary.

[0154] S3. If the current cumulative cooldown time reaches the target cooldown time, a timeout alarm signal will be generated and a safe shutdown policy will be executed.

[0155] The timeout alarm signal is an automatically generated notification signal that indicates an abnormality in the cooling process when the current cumulative cooling time reaches or exceeds the target cooling time. This signal can be output through audible and visual alarms, display screen prompts, remote communication reporting, etc., to remind operators that the cooling stage has exceeded the preset planned time but the mold has not yet met the demolding conditions, and intervention is required to check possible abnormal causes (such as abnormal cooling water temperature, insufficient flow, sensor failure, etc.).

[0156] The safety shutdown strategy refers to a set of protective operations that the control unit automatically executes when the cooling process exceeds the time limit or other abnormal situations occur. These operations include at least stopping the supply of cooling water to the cooling circuit and prohibiting the execution of demolding commands. This strategy aims to prevent quality defects or equipment damage caused by forcibly demolding products that have not been fully cured, and to ensure that the system enters a safe state under abnormal operating conditions, waiting for operators to troubleshoot the fault and manually reset it.

[0157] In this embodiment of the invention, when the control unit determines that the current cumulative cooling time has reached or exceeded the target cooling time, it indicates that the cooling process has exceeded the preset planned duration, but the mold still does not meet the preset demolding conditions. At this time, an overtime alarm signal is immediately generated, and a safe shutdown strategy is executed. After the safe shutdown, the operator is waited to intervene and check to find out the possible causes of the overtime. After the problem is solved, the machine is manually reset and production is restarted. Example 2

[0158] Please see Figure 2The present invention provides a cooling adaptive control system for injection molds, comprising: The data acquisition module 201 is used to acquire the real-time temperature value, cooling process parameters, and target temperature value of the injection mold.

[0159] The dynamic processing module 202 is used to dynamically process the real-time temperature value to obtain the optimal temperature value, the rate of temperature change, and the temperature prediction result.

[0160] The parameter calculation module 203 is used to input the temperature change rate, cooling process parameters and target temperature value into a preset adaptive compensation model to obtain cooling control parameters.

[0161] The cooling execution module 204 is used to correct the cooling process parameters based on the cooling control parameters, and to perform cooling based on the corrected cooling process parameters.

[0162] The prediction update module 205 is used to acquire the real-time temperature value of the injection mold during the cooling process, and update the temperature prediction result based on the newly acquired real-time temperature value to obtain the updated temperature prediction result.

[0163] The strategy judgment module 206 is used to determine whether the updated temperature prediction result meets the preset demolding conditions, and to execute the corresponding cooling strategy based on the judgment result.

[0164] Since the above is a system corresponding to a cooling adaptive control method for injection molds, and its implementation principle is the same as that of a cooling adaptive control method for injection molds, for the sake of convenience and brevity, those skilled in the art can clearly understand that the specific working process of the system and modules described above can be referred to the corresponding process in the aforementioned method embodiments, and will not be repeated here. Example 3

[0165] An electronic device according to an embodiment of the present invention includes: a memory and a processor, wherein the memory stores a computer program; when the computer program is executed by the processor, the processor performs an adaptive cooling control method for injection molds as described in any of the above embodiments.

[0166] The memory can be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. The memory has storage space for program code used to perform any of the method steps described above. For example, the storage space for program code may include individual program codes for implementing the various steps in the methods described above. This program code can be read from or written to one or more computer program products. These computer program products include program code carriers such as hard disks, compact discs (CDs), memory cards, or floppy disks. The program code may be compressed, for example, in a suitable form. When run by a computing processing device, this code causes the computing processing device to perform the various steps in the methods described above. Example 4

[0167] This invention provides a computer-readable storage medium storing a computer program thereon, which, when executed, implements the adaptive cooling control method for injection molds according to any of the above embodiments.

[0168] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0169] In the embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0170] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0171] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0172] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0173] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A cooling adaptive control method for injection molds, characterized in that, include: Obtain the real-time temperature value, cooling process parameters, and target temperature value of the injection mold; The real-time temperature value is dynamically processed to obtain the optimal temperature value, the rate of temperature change, and the temperature prediction result. The temperature change rate, the cooling process parameters, and the target temperature value are input into a preset adaptive compensation model to obtain cooling control parameters. The cooling process parameters are corrected based on the cooling control parameters, and cooling is performed based on the corrected cooling process parameters. During the cooling process, the real-time temperature value of the injection mold is acquired, and the temperature prediction result is updated based on the newly acquired real-time temperature value to obtain the updated temperature prediction result. Determine whether the updated temperature prediction results meet the preset demolding conditions, and execute the corresponding cooling strategy based on the determination results.

2. The adaptive cooling control method for injection molds according to claim 1, characterized in that, The dynamic processing of the real-time temperature value to obtain the optimal temperature value, the rate of temperature change, and the temperature prediction result includes: An extended Kalman filter is used to filter noise from the real-time temperature value to obtain the optimal temperature value. The temperature change rate is obtained by calculating the temperature change per unit time based on the optimal temperature value. The optimal temperature value is input into a preset mold heat conduction model to predict the mold temperature change trend within a preset time window, thus obtaining the temperature prediction result.

3. The adaptive cooling control method for injection molds according to claim 1, characterized in that, The preset adaptive compensation model includes a fuzzification layer, a fuzzy inference layer, a defuzzification layer, and an output layer connected in sequence; the step of inputting the temperature change rate, the cooling process parameters, and the target temperature value into the preset adaptive compensation model to obtain cooling control parameters includes: The temperature change rate, the cooling process parameters, and the target temperature value are fuzzified using the fuzzification layer to obtain fuzzy linguistic variables. The fuzzy inference layer performs fuzzy inference on the fuzzy linguistic variables based on a preset three-parameter coupling control rule base to obtain fuzzy output variables; The fuzzy output variable is defuzzified through the defuzzification layer to obtain a precise control quantity; The cooling water flow rate setpoint and cooling time correction coefficient in the precise control quantity are output through the output layer as the cooling control parameters.

4. The adaptive cooling control method for injection molds according to claim 1, characterized in that, The cooling process parameters include the current cooling water flow rate; The step of correcting the cooling process parameters based on the cooling control parameters and performing cooling based on the corrected cooling process parameters includes: Based on the cooling water flow rate setting value in the cooling control parameters, the current cooling water flow rate is corrected to obtain the updated cooling water flow rate. A preset cooling time algorithm is used to calculate the cooling time for the updated cooling water flow rate and the optimal temperature value to obtain the basic cooling time; The target cooling time is obtained by combining the cooling time correction factor with the base cooling time. Based on the target cooling time and the updated cooling water flow rate, the flow of cooling water in the cooling circuit of the injection mold is controlled.

5. The adaptive cooling control method for injection molds according to claim 1, characterized in that, The step of determining whether the updated temperature prediction result meets the preset demolding conditions includes: Extract the predicted temperature value from the updated temperature prediction results; Determine whether the highest value among the predicted temperature values ​​is lower than a preset demolding temperature safety threshold, and whether the difference between the highest and lowest values ​​among the predicted temperature values ​​is lower than a preset uniformity requirement threshold. When the highest value is lower than the demolding temperature safety threshold and the difference is lower than the uniformity requirement threshold, it is determined that the preset demolding condition is met. Otherwise, it is determined that the preset demolding conditions are not met.

6. The adaptive cooling control method for injection molds according to claim 1, characterized in that, The execution of the corresponding cooling strategy based on the judgment result includes: When the judgment result is that the preset demolding conditions are met, the demolding execution strategy is executed. The demolding execution strategy is to generate a demolding command and stop supplying cooling water to the cooling circuit of the injection mold. When the judgment result is that the preset demolding condition is not met, a cyclic cooling strategy is executed. The cyclic cooling strategy is to jump to the step of obtaining the real-time temperature value of the injection mold, the cooling process parameters and the target temperature value until the preset demolding condition is met or the target cooling time is reached.

7. The adaptive cooling control method for injection molds according to claim 6, characterized in that, When the determination result indicates that the preset demolding condition is not met, a cyclic cooling strategy is executed. This cyclic cooling strategy involves reverting to the step of obtaining the real-time temperature value of the injection mold, cooling process parameters, and target temperature value until the preset demolding condition is met or the target cooling time is reached. This includes: Obtain the current cumulative cooldown time and determine whether the current cumulative cooldown time has reached the target cooldown time; If the current cumulative cooling time has not reached the target cooling time, then proceed to the step of obtaining the real-time temperature value of the injection mold, the cooling process parameters, and the target temperature value; If the current cumulative cooling time reaches the target cooling time, a timeout alarm signal is generated, and a safe shutdown strategy is executed.

8. A cooling adaptive control system for injection molds, characterized in that, include: The data acquisition module is used to acquire the real-time temperature value, cooling process parameters, and target temperature value of the injection mold; The dynamic processing module is used to dynamically process the real-time temperature value to obtain the optimal temperature value, the rate of temperature change, and the temperature prediction result. The parameter calculation module is used to input the temperature change rate, the cooling process parameters, and the target temperature value into a preset adaptive compensation model to obtain cooling control parameters. A cooling execution module is used to correct the cooling process parameters based on the cooling control parameters, and to perform cooling based on the corrected cooling process parameters; The prediction update module is used to acquire the real-time temperature value of the injection mold during the cooling process, and update the temperature prediction result based on the newly acquired real-time temperature value to obtain the updated temperature prediction result. The strategy judgment module is used to determine whether the updated temperature prediction results meet the preset demolding conditions, and to execute the corresponding cooling strategy based on the judgment results.

9. An electronic device, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program capable of being loaded by the processor and executing the adaptive cooling control method for the injection mold as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer program stores a method for adaptive cooling control of an injection mold as described in any one of claims 1 to 7, which can be loaded by a processor and executed.

Images