Injection mold hot runner temperature regulation and control system and method based on machine learning

Abstract

The invention relates to the technical field of temperature regulation and control, and discloses an injection mold hot runner temperature regulation and control system and method based on machine learning, the system comprises a data acquisition module, a temperature threshold setting module and a hot runner temperature regulation and control module; the temperature threshold setting module is used for determining the optimal temperature range of the hot runner based on the injection molding material type, the mold design parameters and the injection molding environment data, and determining the optimal temperature thresholds at different positions in the hot runner in combination with an optimization algorithm; and the hot runner temperature regulation and control module is used for accurately regulating and controlling the temperature in the hot runner according to a comparison result of the real-time temperature data at different positions in the hot runner and the optimal temperature threshold. The precision and the stability of temperature control of the hot runner of the injection mold can be improved, personal errors are reduced, the production efficiency and the product quality can be improved, the rejection rate is reduced, and wide application prospects and economic benefits are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature control, and in particular to a system and method for controlling a hot runner temperature of an injection mold based on machine learning. Background Art

[0002] At present, in the process of injection mold manufacturing, the temperature control of the hot runner is the core link to ensure product quality and production efficiency. The hot runner is the channel in the injection mold responsible for transmitting the molten plastic. The precise control of its temperature is crucial to the flow characteristics and curing process of the molten plastic. In the traditional injection mold manufacturing process, the temperature control of the hot runner mainly depends on the operator's experience and manual adjustment. Although this method can meet production needs to a certain extent, its stability and accuracy are often difficult to guarantee in the face of complex and changing production environments. Different experience and skill levels of operators may lead to inconsistency in temperature control, thus affecting the stability of product quality.

[0003] With the advancement of science and technology, machine learning and automation technologies have been widely used in the field of injection mold manufacturing. The introduction of these technologies makes it possible to intelligently control the temperature of the hot runner. Especially in the production of immunoassay system consumables-reaction cups, the importance of temperature control is particularly prominent. The reaction cup is a key component in the immunoassay system, and its quality directly affects the accuracy and reliability of immunoassays. The injection temperature control of the reaction cup is crucial to ensure product quality. Accurately controlling the injection temperature of the reaction cup can ensure the dimensional accuracy and surface quality of the reaction cup, thereby improving the accuracy of immunoassays. At the same time, by intelligently controlling the hot runner temperature, the scrap rate can be reduced, production costs can be reduced, and production efficiency can be improved.

[0004] Therefore, accurately controlling the temperature of the reaction cup in the hot runner of the injection mold during the injection molding process is crucial to ensuring product quality. Therefore, the present invention proposes a system and method for controlling the temperature of the hot runner of the injection mold based on machine learning. Summary of the invention

[0005] In response to the problems in the related art, the present invention proposes a hot runner temperature control system and method for injection molds based on machine learning to overcome the above-mentioned technical problems existing in the existing related technology.

[0006] To this end, the specific technical solution adopted by the present invention is as follows: According to one aspect of the present invention, there is provided an injection mold hot runner temperature control system based on machine learning, comprising a data acquisition module, a temperature threshold setting module and a hot runner temperature control module; The data acquisition module is used to collect control parameters related to the injection molding process, and the control parameters include temperature data in the hot runner, type of injection molding material, design parameters of the injection mold, injection molding environment data and injection molding product quality; The temperature threshold setting module is used to determine the optimal temperature range of the hot runner based on the injection material type, mold design parameters and injection environment data, and to determine the optimal temperature thresholds at different positions in the hot runner in combination with the optimization algorithm; The hot runner temperature control module is used to accurately control the temperature in the hot runner based on the comparison results of real-time temperature data at different positions in the hot runner and the optimal temperature threshold.

[0007] Most preferably, the data acquisition module includes a temperature data acquisition module, a material type data acquisition module, a mold design parameter acquisition module, an injection molding environment data acquisition module and an injection molding product quality acquisition module; Among them, the temperature data acquisition module is used to collect historical temperature data and real-time temperature data at different positions in the hot runner; Material type data collection module, used to collect the melting point, thermal stability and fluidity data of injection molding materials; Mold design parameter collection module, used to collect the flow channel type, size and shape data of the injection mold; Injection molding environment data collection module, used to collect ambient temperature and humidity data during the injection molding process; The injection molding product quality collection module is used to collect the dimensional accuracy and surface quality data of injection molding products.

[0008] Most preferably, the temperature threshold setting module includes an optimal temperature range setting module and an optimal temperature threshold setting module; Among them, the optimal temperature range setting module is used to determine the optimal temperature range of the hot runner according to the injection material type, mold design parameters and injection environment data; The optimal temperature threshold setting module is used to determine the optimal temperature thresholds at different positions in the hot runner based on the optimal temperature range of the hot runner in combination with the optimization algorithm.

[0009] Most preferably, the optimal temperature range setting module includes a first temperature range setting module, a second temperature range setting module, a third temperature range setting module and a comprehensive analysis setting module; Among them, the first temperature range setting module is used to set the first temperature range of the hot runner based on the reference data and industry standards of the material supplier and in combination with the melting point, thermal stability and fluidity data of the injection molding material; A second temperature range setting module, used to set a second temperature range of the hot runner by using simulation technology combined with the runner type, size and shape data of the injection mold; A third temperature range setting module, used to set a third temperature range of the hot runner by using a neural network model combined with ambient temperature and humidity data during the injection molding process; The comprehensive analysis setting module is used to determine the optimal temperature range of the hot runner by combining the first temperature range, the second temperature range and the third temperature range.

[0010] Most preferably, the third temperature range setting module includes: Acquire historical injection molding production data, and clean and normalize the acquired historical injection molding production data, wherein the injection molding production data includes ambient temperature, humidity, and corresponding hot runner temperature settings and product quality data; Construct a neural network model, and use the normalized injection molding production data to train and test the model to obtain a trained neural network model; The real-time ambient temperature and humidity data during the injection molding process are obtained, and the trained neural network model is used to output the hot runner temperature range corresponding to the real-time ambient temperature and humidity data to obtain the third temperature range.

[0011] Most preferably, the comprehensive analysis setting module includes: Respectively obtain data of a first temperature range, a second temperature range, and a third temperature range, and set a priority for each temperature range, wherein the priorities of the first temperature range, the second temperature range, and the third temperature range gradually decrease; Analyze the conflicts among the first temperature range, the second temperature range, and the third temperature range, and adjust the temperature ranges according to a preset priority order when conflicts exist among the three; The first temperature range is compared with the second temperature range, and a temperature range that satisfies both material properties and mold design parameters is obtained by analysis, and the temperature range obtained by comparison is adjusted according to the third temperature range to obtain an initial optimal temperature range; Determine whether the initial optimal temperature range meets the preset accuracy requirements. If so, use the initial optimal temperature range as the optimal temperature range of the hot runner. If not, use the optimization algorithm to optimize and adjust the initial optimal temperature range to obtain the final optimal temperature range.

[0012] Most preferably, the initial optimal temperature range is optimized and adjusted using an optimization algorithm, and the final optimal temperature range includes: Taking maximizing product quality as the optimization goal and the temperature parameters of the hot runner as the decision variable; designing the chromosome structure and encoding the temperature parameters into a gene sequence; Randomly generate an initial population, where each individual in the population represents a potential temperature range solution; define a fitness function for evaluating the performance of each individual; Select excellent individuals for breeding the next generation based on fitness, randomly select two individuals for crossover, and perform random mutations on the individuals; Repeat the selection, crossover and mutation operations to generate a new generation of population, where the individuals in each generation of population represent new temperature range solutions; Determine whether the maximum number of iterations or fitness threshold is reached. If not, iterate. If so, select the optimal solution from the final population as the final optimal temperature range.

[0013] Most preferably, the optimal temperature threshold setting module includes, when determining the optimal temperature thresholds at different positions in the hot runner based on the optimal temperature range of the hot runner in combination with the optimization algorithm: The optimization goal is to maximize product quality, and the temperature thresholds at different locations in the hot runner are used as decision variables. A group of particles are randomly initialized within the optimal temperature range of the hot runner, and each particle represents a set of potential temperature threshold combinations. Define a fitness function for evaluating the performance of each particle; calculate the fitness of each particle, determine its individual optimal position, and find the global optimal position among all particles; update the speed and position of each particle based on the current speed, individual optimal position, and global optimal position; Repeat the speed and position update steps to generate a new generation of particles, where each generation of particles represents a new temperature threshold combination; determine whether the maximum number of iterations or the fitness threshold is reached, if not, iterate, and if so, obtain the optimal temperature thresholds at different positions in the hot runner based on the best particles.

[0014] Most preferably, the hot runner temperature control module includes a temperature analysis and comparison module and a hot runner temperature control module; Among them, the temperature analysis and comparison module is used to compare the real-time temperature data at different positions in the hot runner with the optimal temperature threshold, and generate a control instruction when there is a difference between the real-time temperature data and the optimal temperature threshold; The hot runner temperature control module is used to accurately control the temperature at different positions in the hot runner according to the generated control instructions.

[0015] According to another aspect of the present invention, a method for controlling the temperature of a hot runner of an injection mold based on machine learning is provided. The method for controlling the temperature of a hot runner of an injection mold based on machine learning comprises the following steps: S1. Collecting control parameters related to the injection molding process, wherein the control parameters include temperature data in the hot runner, type of injection molding material, design parameters of the injection mold, injection molding environment data and injection molding product quality; S2. Determine the optimal temperature range of the hot runner based on the injection material type, mold design parameters and injection environment data, and determine the optimal temperature thresholds at different positions in the hot runner in combination with the optimization algorithm; S3. Accurately control the temperature in the hot runner based on the comparison results of the real-time temperature data at different positions in the hot runner with the optimal temperature threshold.

[0016] The beneficial effects of the present invention are: 1) The present invention determines the optimal temperature range of the hot runner based on the type of injection material, mold design parameters and injection environment data, and determines the optimal temperature thresholds at different positions in the hot runner in combination with an optimization algorithm, thereby being able to accurately control the temperature at different positions in the hot runner based on the comparison results of real-time temperature data and the optimal temperature thresholds. Compared with traditional manual control methods, the present invention can not only improve the accuracy and stability of injection mold hot runner temperature control and reduce human errors, but also improve production efficiency and product quality and reduce scrap rate. It has broad application prospects and economic benefits and can better meet the use needs of enterprises.

[0017] 2) The present invention determines the first temperature range by the type of injection molding material, which helps to ensure that the material is within a safe operating temperature range and avoid degradation of material performance due to overheating or insufficient cooling; determines the second temperature range by mold design parameters, which helps to consider the impact of mold design on hot runner temperature distribution, thereby controlling the temperature more accurately; determines the third temperature range by injection molding environment data, which helps to consider the impact of external environmental factors on hot runner temperature and achieve more intelligent temperature control.

[0018] 3) The present invention combines the first, second and third temperature ranges, analyzes the conflict situation and makes adjustments using the priority order to obtain the optimal temperature range of the hot runner, which helps to comprehensively consider various factors and achieve more comprehensive and accurate temperature control; in addition, the present invention can also determine the optimal temperature thresholds at different positions in the hot runner based on the optimal temperature range of the hot runner in combination with the optimization algorithm, thereby achieving fine control of the temperature at different positions in the hot runner and improving product quality and production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1is a structural block diagram of a hot runner temperature control system for an injection mold based on machine learning according to an embodiment of the present invention; Figure 2 It is a flow chart of a method for controlling the temperature of a hot runner of an injection mold based on machine learning according to an embodiment of the present invention.

[0021] In the figure: 1. Data acquisition module; 2. Temperature threshold setting module; 3. Hot runner temperature control module. DETAILED DESCRIPTION

[0022] To further illustrate each embodiment, the present invention provides drawings, which are part of the disclosure of the present invention and are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, ordinary technicians in the field should be able to understand other possible implementations and advantages of the present invention. The components in the figures are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0023] According to an embodiment of the present invention, a system and method for controlling the temperature of a hot runner of an injection mold based on machine learning are provided.

[0024] The present invention will now be further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to one embodiment of the present invention, a hot runner temperature control system for an injection mold based on machine learning is provided, comprising a data acquisition module 1, a temperature threshold setting module 2 and a hot runner temperature control module 3; The data acquisition module 1 is used to collect the control parameters related to the injection molding process, and the control parameters include the temperature data in the hot runner, the type of injection molding material, the design parameters of the injection mold, the injection molding environment data and the quality of the injection molding product; Specifically, the data acquisition module 1 includes a temperature data acquisition module, a material type data acquisition module, a mold design parameter acquisition module, an injection molding environment data acquisition module, and an injection molding product quality acquisition module; Among them, the temperature data acquisition module is used to collect historical temperature data and real-time temperature data at different positions in the hot runner; Collecting historical temperature data and real-time temperature data at different locations in the hot runner helps monitor the temperature changes of the hot runner and provide an accurate data basis for subsequent temperature control and optimization. The collection of real-time temperature data can detect temperature anomalies in a timely manner, thereby making timely adjustments to ensure the stability of the injection molding process and product quality.

[0025] Material type data collection module, used to collect the melting point, thermal stability and fluidity data of injection molding materials; Collect the melting point, thermal stability and fluidity data of the injection molding material. These data are crucial to determine the temperature range of the hot runner, because different materials have different thermal properties; by collecting these data, you can ensure that the material works at an appropriate temperature to avoid material performance degradation or damage caused by improper temperature.

[0026] Mold design parameter collection module, used to collect the flow channel type, size and shape data of the injection mold; Collect the runner type, size and shape data of the injection mold. The mold design parameters directly affect the temperature distribution of the hot runner, so the collection of this data is crucial for accurately controlling the hot runner temperature; by collecting this data, the temperature distribution of the hot runner can be more accurately simulated and predicted, thereby achieving more precise temperature control.

[0027] Injection molding environment data collection module, used to collect ambient temperature and humidity data during the injection molding process; Collect ambient temperature and humidity data during the injection molding process. Environmental factors have a significant impact on the temperature of the hot runner, especially in an open production environment; by collecting this data, the temperature setting of the hot runner can be adjusted in time to adapt to environmental changes and ensure the stability of the injection molding process and product quality.

[0028] The injection molding product quality collection module is used to collect the dimensional accuracy and surface quality data of injection molding products.

[0029] Collect the dimensional accuracy and surface quality data of injection molded products. These data are important indicators for evaluating the quality of injection molded products, and are also important bases for feedback and optimization of hot runner temperature control; by collecting these data, the effect of hot runner temperature control can be evaluated and optimized, thereby improving product quality and production efficiency.

[0030] The temperature threshold setting module 2 is used to determine the optimal temperature range of the hot runner based on the injection material type, mold design parameters and injection environment data, and determine the optimal temperature thresholds at different positions in the hot runner in combination with the optimization algorithm; Specifically, the temperature threshold setting module 2 includes an optimal temperature range setting module and an optimal temperature threshold setting module; Among them, the optimal temperature range setting module is used to determine the optimal temperature range of the hot runner according to the injection material type, mold design parameters and injection environment data; The optimal temperature range setting module includes a first temperature range setting module, a second temperature range setting module, a third temperature range setting module and a comprehensive analysis setting module; Among them, the first temperature range setting module is used to set the first temperature range of the hot runner based on the reference data and industry standards of the material supplier and in combination with the melting point, thermal stability and fluidity data of the injection molding material; Based on the reference data of the material supplier and industry standards, the steps for setting the first temperature range of the hot runner in combination with the melting point, thermal stability and fluidity data of the injection molding material are as follows: Collect reference data: Obtain detailed technical data of injection molding materials from material suppliers, including key parameters such as melting point, thermal stability, fluidity, etc. Consult relevant industry standards to understand the general temperature range requirements for injection molding of such materials.

[0031] Analyze material properties: Analyze the melting point of the injection molding material to determine the temperature at which the material begins to melt. Consider the thermal stability of the material to determine the stable working range of the material at high temperatures. Evaluate the fluidity of the material to determine at what temperature the material can maintain good fluidity and filling capacity.

[0032] Determine the preliminary temperature range: Based on the melting point and thermal stability of the material, preliminarily determine the lower and upper temperature limits of the hot runner. Ensure that the temperature range allows the material to fully melt without causing material degradation or performance degradation.

[0033] Consider fluidity requirements: Combine the material's fluidity data and adjust the temperature range to ensure that the material can fully fill every corner of the mold during the injection molding process.

[0034] Reference to industry standards: Compare to industry standards to ensure that the set temperature range meets industry regulations and best practices.

[0035] Safety factor adjustment: Taking into account the uncertainties in actual production, appropriately lower the upper limit of the temperature range or increase the lower limit to introduce a certain safety factor.

[0036] Experimental verification: In a laboratory environment, use different temperature settings to perform injection molding tests to verify the rationality of the temperature range. Adjust the temperature range based on the experimental results to optimize the injection molding effect.

[0037] Record and standardize: Record the final hot runner temperature range and form a standard operating procedure to ensure that the temperature range is consistently applied in subsequent production.

[0038] Through the above steps, the first temperature range of the hot runner can be scientifically set to provide a reliable temperature control basis for the subsequent injection molding process, thereby ensuring product quality and production efficiency.

[0039] A second temperature range setting module, used to set a second temperature range of the hot runner by using simulation technology combined with the runner type, size and shape data of the injection mold; The steps for setting the second temperature range of the hot runner by using simulation technology combined with the runner type, size and shape data of the injection mold are as follows: Collect mold design data: Obtain detailed design drawings of the injection mold, including the type (such as straight-through, annular, etc.), size (such as diameter, length, etc.) and shape (such as straight line, curved, etc.) of the runner.

[0040] Select simulation software: Choose appropriate simulation software, such as Moldflow, Ansys, etc. These software can simulate the hot runner temperature distribution during the injection molding process.

[0041] Build a simulation model: Build a 3D model of the injection mold, including the hot runner system, in the simulation software. Ensure that the runner type, size, and shape in the model are consistent with the actual mold design.

[0042] Set simulation parameters: Input the thermophysical performance parameters of the injection molding material, such as thermal conductivity, specific heat capacity, etc. Set the process parameters during the injection molding process, such as injection speed, pressure, cooling time, etc.

[0043] Run simulation: Run simulation software to simulate the temperature distribution of the hot runner during the injection molding process. Analyze the simulation results, especially the temperature changes of various parts of the hot runner.

[0044] Evaluate temperature distribution: Evaluate whether the temperature distribution in the simulation results is uniform and whether there are overheated or undercooled areas. Determine whether the temperature of each part of the flow channel is within a safe operating range.

[0045] Adjust the temperature range: According to the simulation results, adjust the temperature range of the hot runner to ensure that the temperature of each part of the runner is within the appropriate range. Pay special attention to the key parts of the runner, such as turns and branches, as temperature control in these areas is particularly important.

[0046] Verify simulation results: In actual production, adjust the temperature settings of the hot runner according to the simulation results. Observe the actual products in production to verify the accuracy of the simulation results.

[0047] Record and standardize: Record the final hot runner temperature range and form a standard operating procedure to ensure that the temperature range is consistently applied in subsequent production.

[0048] Through the above steps, the second temperature range of the hot runner can be set by using simulation technology combined with the runner type, size and shape data of the injection mold, thereby achieving more accurate and efficient hot runner temperature control.

[0049] The third temperature range setting module is used to set the third temperature range of the hot runner by using a neural network model combined with ambient temperature and humidity data during the injection molding process, specifically including: Acquire historical injection molding production data, and clean and normalize the acquired historical injection molding production data, wherein the injection molding production data includes ambient temperature, humidity, and corresponding hot runner temperature settings and product quality data; Construct a neural network model, and use the normalized injection molding production data to train and test the model to obtain a trained neural network model; The real-time ambient temperature and humidity data during the injection molding process are obtained, and the trained neural network model is used to output the hot runner temperature range corresponding to the real-time ambient temperature and humidity data to obtain the third temperature range.

[0050] The comprehensive analysis setting module is used to determine the optimal temperature range of the hot runner by combining the first temperature range, the second temperature range and the third temperature range, specifically including: Respectively obtain data of a first temperature range, a second temperature range, and a third temperature range, and set a priority for each temperature range, wherein the priorities of the first temperature range, the second temperature range, and the third temperature range gradually decrease; Analyze the conflicts among the first temperature range, the second temperature range, and the third temperature range (i.e., compare the three temperature ranges to find out the conflicting areas), and if there is a conflict among the three, adjust the temperature ranges according to the pre-set priority order. For example, if the first temperature range conflicts with the second temperature range, and the first temperature range has a higher priority, the adjustment should be based on the first temperature range; The first temperature range is compared with the second temperature range, and the intersection between the two is analyzed, that is, a temperature range that satisfies both material properties and mold design parameters is obtained, and the temperature range obtained by comparison is adjusted according to the third temperature range. For example, if there is a conflict between the third temperature range and the intersection temperature range, the adjustment is made according to the actual influence of environmental factors, that is, the intersection temperature range is expanded or reduced to ensure that the stability of the injection molding process can be maintained under changing environmental conditions, and the initial optimal temperature range is obtained; Determine whether the initial optimal temperature range meets the preset accuracy requirements (according to industry standards, product quality requirements and production experience, set the accuracy requirements of hot runner temperature control, including the temperature fluctuation range). If so, use the initial optimal temperature range as the optimal temperature range of the hot runner. If not, use the optimization algorithm to optimize the initial optimal temperature range to obtain the final optimal temperature range.

[0051] Specifically, the initial optimal temperature range is optimized and adjusted using the optimization algorithm, and the final optimal temperature range includes: The optimization goal is to maximize product quality and the temperature parameters of the hot runner are used as decision variables. The chromosome structure is designed and the temperature parameters are encoded into gene sequences. Each gene represents a dimension of the temperature range or a temperature value at a specific position. Randomly generate the initial population to ensure population diversity, where each individual in the population represents a potential temperature range solution; define a fitness function for evaluating the performance of each individual, and the fitness function should reflect the optimization goal, such as product quality; In this embodiment, product quality is represented by a comprehensive index. For example, product quality is measured by the weighted sum of multiple indicators such as product weight, dimensional accuracy, and surface quality. A comprehensive quality scoring function Q(T) is defined to represent product quality, where T represents the temperature range solution. The fitness function F(T) is:

[0052] In the formula, Q ( T ) is the product quality score corresponding to the temperature range solution T, which reflects the comprehensive performance of multiple indicators such as product weight, dimensional accuracy, and surface quality; S ( T ) is a penalty term that takes into account the feasibility and practicality of the temperature range solution T. For example, if the temperature range exceeds the operating range of the device or causes excessive energy consumption, S(T) will decrease, thereby reducing the fitness; α is a weight factor that determines the relative importance of product quality Q(T) and penalty term S(T) in the fitness function. α The value of is usually between 0 and 1, and can be adjusted according to actual needs and goals. In this embodiment, it is preferably 0.6.

[0053] Select excellent individuals for breeding the next generation based on fitness (roulette, tournament selection or other selection strategies can be used), randomly select two individuals for crossover, exchange some genes to produce new offspring, and randomly mutate individuals to change gene values ​​to increase population diversity; Repeat the selection, crossover and mutation operations to generate a new generation of population, where the individuals in each generation of population represent new temperature range solutions; Determine whether the maximum number of iterations or fitness threshold is reached. If not, iterate. If so, select the optimal solution from the final population as the final optimal temperature range.

[0054] The optimal temperature threshold setting module is used to determine the optimal temperature thresholds at different positions in the hot runner based on the optimal temperature range of the hot runner in combination with the optimization algorithm.

[0055] Specifically, the optimal temperature threshold setting module includes: The optimization goal is to maximize product quality, and the temperature thresholds at different locations in the hot runner are used as decision variables. A group of particles are randomly initialized within the optimal temperature range of the hot runner, and each particle represents a set of potential temperature threshold combinations. Define a fitness function for evaluating the performance of each particle. The fitness function should reflect the optimization goal, such as product quality. Calculate the fitness of each particle, determine its individual optimal position, and find the global optimal position among all particles. Update the speed and position of each particle based on the current speed, individual optimal position, and global optimal position. The fitness function is:

[0056] In the formula, F ( x ) is the fitness function used to evaluate the particle x performance; Q ( x ) is a particle x The corresponding product quality score; P ( x ) is the penalty term, which reflects the particle x Certain unfavorable factors, such as exceeding the optimal temperature range, may cause the risk of excessive energy consumption or equipment damage. P ( x ) The lower it is, the less punishment it will receive; β 1 is the weight factor, which is used to adjust the importance of product quality score in the fitness function; β 2 is the weight factor used to adjust the importance of the penalty term in the fitness function.

[0057] During the particle swarm optimization process, the velocity and position of each particle are updated according to the following formula: v i+1 = w ⋅ v i + c 1 ⋅ r 1 ⋅( pbest i − x i )+ c 2 ⋅ r 2 ⋅( gbest − x i ) x i+1 = x i + v i+1 In the formula, v i+1 The particle is i+ The speed of 1 generation, v i The particle is i The speed of generation; w is the inertia weight, which controls the continuity of the particle velocity; c 1 and c 2 is the acceleration constant, which controls the strength of the particle moving toward the individual optimal position and the global optimal position; r 1 and r 2 is a random number in the interval [0,1], used to increase the randomness of the search; x i+1 The particle is i+ The current position of the 1st generation, x i The particle is i The current position of the generation; pbest i It is i The individual optimal position of each particle is gbest is the global optimal position, that is, the optimal position found by all particles during the iteration process.

[0058] Repeat the speed and position update steps to generate a new generation of particles, where each generation of particles represents a new temperature threshold combination; determine whether the maximum number of iterations or the fitness threshold is reached, if not, iterate, and if so, obtain the optimal temperature thresholds at different positions in the hot runner based on the best particles.

[0059] The hot runner temperature control module 3 is used to accurately control the temperature in the hot runner according to the comparison result of the real-time temperature data at different positions in the hot runner and the optimal temperature threshold.

[0060] Specifically, the hot runner temperature control module 3 includes a temperature analysis and comparison module and a hot runner temperature control module; Among them, the temperature analysis and comparison module is used to compare the real-time temperature data at different positions in the hot runner with the optimal temperature threshold, and generate control instructions when there is a difference between the real-time temperature data and the optimal temperature threshold; specifically including: comparing the real-time collected temperature data with the optimal temperature threshold, comparing the temperature data at each position with the corresponding optimal temperature threshold; identifying the difference between the real-time temperature data and the optimal temperature threshold, and analyzing the reasons for the difference, such as environmental changes, equipment aging, operating errors, etc.; when there is a difference between the real-time temperature data and the optimal temperature threshold, generating control instructions, the control instructions include adjusting the heater power, changing the cooling water flow, adjusting the injection speed, etc.; sending the control instructions to the corresponding execution equipment, such as heaters, cooling systems, etc., to ensure that the control instructions can be executed quickly and accurately.

[0061] The hot runner temperature control module is used to accurately control the temperature at different positions in the hot runner according to the generated control instructions.

[0062] The steps to accurately control the temperature at different positions in the hot runner according to the generated control instructions are as follows: Instruction analysis: Receive and analyze the generated control instructions to determine the temperature position and target temperature value that need to be adjusted. Ensure the accuracy and completeness of the instructions.

[0063] Execution equipment preparation: Confirm that the equipment that executes the regulation (such as heaters, cooling systems, etc.) is in normal working condition. Check whether the response time and control accuracy of the equipment meet the requirements.

[0064] Temperature adjustment: According to the control instructions, the temperature at different positions in the hot runner is accurately adjusted. During the adjustment process, the temperature changes are closely monitored to ensure that the temperature changes are stable and in line with expectations.

[0065] Real-time monitoring: Use temperature sensors to continuously monitor the actual temperature at each location in the hot runner. Provide real-time feedback of temperature data to adjust the control strategy in a timely manner.

[0066] Closed-loop control: Implement closed-loop control to dynamically adjust control instructions based on the difference between real-time temperature data and target temperature, ensuring the stability and response speed of the temperature control system.

[0067] Abnormal handling: When abnormal temperature changes or equipment failures are detected, corresponding emergency measures are taken immediately, including adjusting control strategies, switching to backup equipment, or manual intervention.

[0068] Recording and reporting: Record key data and events during the control process, including temperature changes, equipment status, etc. Generate reports regularly to analyze control effects and system performance.

[0069] Continuous optimization: Based on long-term operation data, we continuously optimize control strategies and parameter settings to improve the accuracy and efficiency of temperature control.

[0070] Through the above steps, the temperature at different positions in the hot runner can be accurately controlled, thereby ensuring the consistency of injection molded product quality and the stability of the production process.

[0071] According to another embodiment of the present invention, Figure 2 As shown, a method for controlling the temperature of a hot runner of an injection mold based on machine learning is provided, and the method for controlling the temperature of a hot runner of an injection mold based on machine learning comprises the following steps: S1. Collecting control parameters related to the injection molding process, wherein the control parameters include temperature data in the hot runner, type of injection molding material, design parameters of the injection mold, injection molding environment data and injection molding product quality; S2. Determine the optimal temperature range of the hot runner based on the injection material type, mold design parameters and injection environment data, and determine the optimal temperature thresholds at different positions in the hot runner in combination with the optimization algorithm; S3. Accurately control the temperature in the hot runner based on the comparison results of the real-time temperature data at different positions in the hot runner with the optimal temperature threshold.

[0072] To sum up, with the help of the above-mentioned technical scheme of the present invention, the present invention determines the optimal temperature range of the hot runner based on the type of injection material, mold design parameters and injection molding environment data, and determines the optimal temperature threshold at different positions in the hot runner in combination with the optimization algorithm, so that the temperature at different positions in the hot runner can be accurately controlled according to the comparison result of real-time temperature data and the optimal temperature threshold. Compared with the traditional manual control method, the present invention can not only improve the accuracy and stability of the temperature control of the hot runner of the injection mold, reduce human errors, but also improve production efficiency and product quality, reduce scrap rate, has broad application prospects and economic benefits, and can better meet the use needs of enterprises.

[0073] At the same time, the present invention determines the first temperature range by the type of injection molding material, which helps to ensure that the material is within a safe operating temperature range and avoid degradation of material performance due to overheating or insufficient cooling; determines the second temperature range by mold design parameters, which helps to consider the impact of mold design on hot runner temperature distribution, thereby controlling the temperature more accurately; determines the third temperature range by injection molding environment data, which helps to consider the impact of external environmental factors on the hot runner temperature and achieve more intelligent temperature control.

[0074] At the same time, the present invention combines the first, second and third temperature ranges, analyzes the conflict situation and adjusts them according to the priority order to obtain the optimal temperature range of the hot runner, which helps to comprehensively consider various factors and achieve more comprehensive and accurate temperature control; in addition, the present invention can also determine the optimal temperature thresholds at different positions in the hot runner based on the optimal temperature range of the hot runner in combination with the optimization algorithm, thereby achieving fine control of the temperature at different positions in the hot runner and improving product quality and production efficiency.

[0075] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A hot runner temperature control system for injection molds based on machine learning, characterized in that: It includes a data acquisition module, a temperature threshold setting module and a hot runner temperature control module; Wherein, the data acquisition module is used to collect control parameters related to the injection molding process; The data acquisition module includes a temperature data acquisition module, a material type data acquisition module, a mold design parameter acquisition module, an injection molding environment data acquisition module and an injection molding product quality acquisition module; Temperature data acquisition module, used to collect historical temperature data and real-time temperature data at different positions in the hot runner; Material type data collection module, used to collect the melting point, thermal stability and fluidity data of injection molding materials; Mold design parameter collection module, used to collect the flow channel type, size and shape data of the injection mold; Injection molding environment data collection module, used to collect ambient temperature and humidity data during the injection molding process; Injection molding product quality collection module, used to collect the dimensional accuracy and surface quality data of injection molding products; The temperature threshold setting module is used to determine the optimal temperature range of the hot runner based on the injection material type, mold design parameters and injection environment data, and determine the optimal temperature thresholds at different positions in the hot runner in combination with the optimization algorithm; The hot runner temperature control module is used to accurately control the temperature in the hot runner according to the comparison result of the real-time temperature data at different positions in the hot runner and the optimal temperature threshold.

2. The injection mold hot runner temperature control system based on machine learning according to claim 1, characterized in that: The temperature threshold setting module includes an optimal temperature range setting module and an optimal temperature threshold setting module; The optimal temperature range setting module is used to determine the optimal temperature range of the hot runner according to the injection material type, mold design parameters and injection environment data; The optimal temperature threshold setting module is used to determine the optimal temperature thresholds at different positions in the hot runner based on the optimal temperature range of the hot runner in combination with the optimization algorithm.

3. The injection mold hot runner temperature control system based on machine learning according to claim 2, characterized in that: The optimal temperature range setting module includes a first temperature range setting module, a second temperature range setting module, a third temperature range setting module and a comprehensive analysis setting module; Wherein, the first temperature range setting module is used to set the first temperature range of the hot runner based on the reference data and industry standards of the material supplier, combined with the melting point, thermal stability and fluidity data of the injection molding material; The second temperature range setting module is used to set the second temperature range of the hot runner by using simulation technology combined with the runner type, size and shape data of the injection mold; The third temperature range setting module is used to set the third temperature range of the hot runner by using a neural network model in combination with ambient temperature and humidity data during the injection molding process; The comprehensive analysis setting module is used to determine the optimal temperature range of the hot runner by combining the first temperature range, the second temperature range and the third temperature range.

4. The injection mold hot runner temperature control system based on machine learning according to claim 3, characterized in that: The third temperature range setting module sets the third temperature range of the hot runner by using the neural network model in combination with the ambient temperature and humidity data during the injection molding process, including: Acquire historical injection molding production data, and clean and normalize the acquired historical injection molding production data, wherein the injection molding production data includes ambient temperature, humidity, and corresponding hot runner temperature settings and product quality data; Construct a neural network model, and use the normalized injection molding production data to train and test the model to obtain a trained neural network model; The real-time ambient temperature and humidity data during the injection molding process are obtained, and the trained neural network model is used to output the hot runner temperature range corresponding to the real-time ambient temperature and humidity data to obtain the third temperature range.

5. The injection mold hot runner temperature control system based on machine learning according to claim 3, characterized in that: The comprehensive analysis setting module determines the optimal temperature range of the hot runner by combining the first temperature range, the second temperature range and the third temperature range, including: Respectively obtain data of a first temperature range, a second temperature range, and a third temperature range, and set a priority for each temperature range, wherein the priorities of the first temperature range, the second temperature range, and the third temperature range gradually decrease; Analyze the conflicts among the first temperature range, the second temperature range, and the third temperature range, and adjust the temperature ranges according to a preset priority order when conflicts exist among the three; The first temperature range is compared with the second temperature range, and a temperature range that satisfies both material properties and mold design parameters is obtained by analysis, and the temperature range obtained by comparison is adjusted according to the third temperature range to obtain an initial optimal temperature range; Determine whether the initial optimal temperature range meets the preset accuracy requirements. If so, use the initial optimal temperature range as the optimal temperature range of the hot runner. If not, use the optimization algorithm to optimize and adjust the initial optimal temperature range to obtain the final optimal temperature range.

6. The injection mold hot runner temperature control system based on machine learning according to claim 5, characterized in that: The optimization algorithm is used to optimize and adjust the initial optimal temperature range to obtain the final optimal temperature range including: Taking maximizing product quality as the optimization goal and the temperature parameters of the hot runner as the decision variable; designing the chromosome structure and encoding the temperature parameters into a gene sequence; Randomly generate an initial population, where each individual in the population represents a potential temperature range solution; define a fitness function for evaluating the performance of each individual; Select excellent individuals for breeding the next generation based on fitness, randomly select two individuals for crossover, and perform random mutations on the individuals; Repeat the selection, crossover and mutation operations to generate a new generation of population, where the individuals in each generation of population represent new temperature range solutions; Determine whether the maximum number of iterations or fitness threshold is reached. If not, iterate. If so, select the optimal solution from the final population as the final optimal temperature range.

7. The injection mold hot runner temperature control system based on machine learning according to claim 2, characterized in that: The optimal temperature threshold setting module includes: determining the optimal temperature thresholds at different positions in the hot runner based on the optimal temperature range of the hot runner in combination with the optimization algorithm; The optimization goal is to maximize product quality, and the temperature thresholds at different locations in the hot runner are used as decision variables. A group of particles are randomly initialized within the optimal temperature range of the hot runner, and each particle represents a set of potential temperature threshold combinations. Define a fitness function for evaluating the performance of each particle; calculate the fitness of each particle, determine its individual optimal position, and find the global optimal position among all particles; update the speed and position of each particle based on the current speed, individual optimal position, and global optimal position; Repeat the speed and position update steps to generate a new generation of particles, where each generation of particles represents a new temperature threshold combination; determine whether the maximum number of iterations or the fitness threshold is reached, if not, iterate, and if so, obtain the optimal temperature thresholds at different positions in the hot runner based on the best particles.

8. The injection mold hot runner temperature control system based on machine learning according to claim 1, characterized in that: The hot runner temperature control module includes a temperature analysis and comparison module and a hot runner temperature control module; The temperature analysis and comparison module is used to compare the real-time temperature data at different positions in the hot runner with the optimal temperature threshold, and generate a control instruction when there is a difference between the real-time temperature data and the optimal temperature threshold; The hot runner temperature control module is used to accurately control the temperature at different positions in the hot runner according to the generated control instructions.

9. A method for controlling the temperature of a hot runner of an injection mold based on machine learning, which is implemented based on the system for controlling the temperature of a hot runner of an injection mold based on machine learning as described in any one of claims 1 to 8, characterized in that: The method for controlling the temperature of the hot runner of an injection mold based on machine learning comprises the following steps: S1. Collecting control parameters related to the injection molding process, wherein the control parameters include temperature data in the hot runner, type of injection molding material, design parameters of the injection mold, injection molding environment data and injection molding product quality; S2. Determine the optimal temperature range of the hot runner based on the injection material type, mold design parameters and injection environment data, and determine the optimal temperature thresholds at different positions in the hot runner in combination with the optimization algorithm; S3. Accurately control the temperature in the hot runner based on the comparison results of the real-time temperature data at different positions in the hot runner with the optimal temperature threshold.

Images