Soft start control method for intelligent temperature control of glue injection mold

Abstract

The invention discloses a soft start control method for intelligent temperature control of a glue injection mold, and particularly relates to the technical field of glue injection molds. Initial temperatures of a plurality of heating areas of the mold are collected, and a temperature distribution model is constructed; calculating a thermal inertia score value based on the thermal response characteristic and the thermal capacity parameter of each region; predicting temperature rise rates of different areas by using the thermal inertia score value, the thermal coupling degree abnormal value and the historical control deviation frequency, and setting differentiated soft start amplitude limiting parameters; temperature feedback is collected in real time in the heating process, a temperature rise rate error sequence is constructed, and the future deviation risk is predicted through the dynamic Bayesian network; when the risk value exceeds the limit, the PWM duty ratio or the conduction angle of the heating area is dynamically corrected, and power output self-adaptive adjustment is achieved; the method has the advantages of being high in predictability, accurate in response and intelligent in control, and is suitable for high-precision heating control application of the complex glue injection mold.

Description

Technical Field

[0001] The present invention relates to the technical field of glue injection molds, and in particular to a soft start control method for intelligent temperature control of glue injection molds. Background Art

[0002] Soft start control for intelligent temperature control of injection molds involves regulating the temperature of the mold's heating elements during the injection molding process through the intelligent temperature control system. A "soft start" approach is used during the initial heating phase to gradually increase the temperature. This prevents sudden current surges from impacting the equipment, extends the life of the heating elements, and ensures a uniform rise in mold temperature, improving molding quality and production stability. This control method combines temperature feedback with program settings to achieve precise and safe heating management.

[0003] The existing technology has the following shortcomings: In large or multi-cavity complex molds, due to the lag in heat conduction and significant differences in thermal inertia, existing temperature control systems mostly rely on single-point temperature sensors. This may cause the controller to misjudge that the temperature rise process is too slow and release the soft start limit prematurely, thereby causing a sudden local temperature rise that exceeds the material's tolerance limit, resulting in stress concentration and microcracks inside the mold, and even damage to the sealing structure, ultimately affecting the dimensional accuracy and appearance quality of the product. The risk is particularly prominent in high-cavity pressure molds such as automotive lamp housings or optical lenses. Summary of the Invention

[0004] The purpose of the present invention is to provide a soft start control method for intelligent temperature control of a glue injection mold to solve the shortcomings of the background technology.

[0005] In order to achieve the above object, the present invention provides the following technical solution: a soft start control method for intelligent temperature control of a glue injection mold, comprising: Acquire initial temperature data for multiple regions of the mold, including the mold cavity, nozzle, and material channel, and construct a temperature distribution model; Based on the temperature distribution model and the preset thermal inertia score, the temperature rise rate of different areas is predicted, and areas where thermal hysteresis may exist are identified; During the soft start phase, differentiated current or power limit parameters are set for each heating zone to form a dynamic soft start strategy at the zone level. Real-time collection of temperature feedback data from each area, combined with the predicted temperature rise trajectory and actual temperature rise rate, to dynamically correct the power output; After reaching the target temperature threshold, the limit is released and switched to PID closed-loop control to achieve uniform and stable control of the mold temperature.

[0006] Preferably, the calculation of the thermal inertia score includes: Collect historical temperature rise curves of each heating area of ​​the mold; Calculate the temperature rise response time per unit power in each area as the thermal response delay indicator; Calculate the thermal inertia score based on the thermal response delay index and regional heat capacity parameters; If the thermal inertia score of the heating area is higher than a preset threshold, it is marked as a thermal hysteresis area and the limiting strategy is adapted in the soft start control.

[0007] Preferably, predicting the temperature rise rate in different regions includes: inputting the current initial temperature and the target set temperature into a prediction model; the prediction model adopts a multi-factor weighted method, and the weighted factors include the thermal inertia score value, the regional thermal coupling abnormality value and the historical control deviation frequency to calculate the expected temperature rise time and rate.

[0008] Preferably, the method for obtaining the regional thermal coupling anomaly value is: synchronously collecting temperature change data in multiple preset heating areas to construct a temperature time series matrix for multiple time periods; calculating the temperature covariance between any two areas based on the temperature sequence, and solving the total thermal coupling degree of each area accordingly; calculating the global average value of the thermal coupling degrees of all areas, and calculating the thermal coupling degree deviation value of each area as the regional thermal coupling anomaly value.

[0009] Preferably, the method for obtaining the historical control deviation frequency is: recording the instantaneous deviation value between the actual temperature and the target temperature of each heating area in multiple historical soft start cycles; setting a deviation tolerance threshold, and counting the proportion of time points in each soft start cycle when the deviation exceeds the threshold, which is defined as the regional deviation frequency; summarizing the deviation frequencies of multiple cycles and taking their average to form the historical control deviation frequency.

[0010] Preferably, the dynamically corrected power output includes: Collect the temperature feedback value of each heating area in real time and calculate its temperature change rate per unit time as the actual temperature rise rate; The temperature rise trajectory output by the prediction model is called, and the error between the temperature rise trajectory and the actual temperature rise rate is calculated at each time step to construct a temperature rise rate error sequence. Based on the temperature rise rate error sequence, a probability model is performed on the difference between the predicted and actual temperatures to estimate the risk value of future temperature control deviation; If the temperature control deviation risk value exceeds the risk threshold, the PWM duty cycle or conduction angle of the heating area will be dynamically corrected to achieve real-time optimization of power output.

[0011] Preferably, estimating the future temperature control deviation risk value includes: The predicted temperature rise rate and the actual temperature rise rate of each heating area are collected in multiple time steps, and the difference between the two is calculated to form a temperature rise rate error sequence; Taking the error value as an observable variable, a dynamic Bayesian network model is constructed, defining the hidden state of each time step as the control deviation state, setting it to depend only on the hidden state at the previous moment, and establishing the state transition probability relationship; Based on historical control data or real-time observation sequences, estimate state transition probabilities and observation probability distributions using expectation maximization algorithms or Bayesian filtering methods; At any current moment, based on the known error sequence, the probability that the system will be in a high deviation state in the future period of time is inferred as the future temperature control deviation risk value.

[0012] Preferably, the dynamically correcting the PWM duty cycle or conduction angle of the heating area includes: Determine the adjustment priority of each heating area based on the predicted deviation risk value, and give priority to adjusting areas where the risk probability is higher than the threshold; If the heating area uses PWM control, the adjustment increment is calculated based on the current error direction and magnitude, and the PWM duty cycle is increased or decreased to refine the power output. The duty cycle change is limited to the preset maximum adjustment step size. If the heating area adopts thyristor or SCR control, the conduction angle is adjusted through phase control to shorten or extend the conduction time period, thereby changing the average electric power within a single cycle.

[0013] In the above technical solution, the technical effects and advantages provided by the present invention are: 1. By introducing multi-dimensional analysis parameters such as thermal inertia scoring, thermal coupling anomaly identification, and historical control deviation frequency, the present invention realizes differentiated limiting control and predictive temperature rise strategy in the heating area, effectively overcoming the problems of thermal lag misjudgment, local overheating, and large temperature fluctuations existing in traditional mold temperature control systems, and significantly improving the response accuracy and system safety of the heating process.

[0014] 2. The present invention integrates a dynamic Bayesian network algorithm to predict the risk of future temperature control deviations, and dynamically corrects the PWM duty cycle or conduction angle in combination with real-time feedback. After reaching the target temperature, it automatically switches to PID closed-loop control, constructing an integrated intelligent temperature control system with prediction, decision-making, and adaptive adjustment capabilities. This not only improves the uniformity of mold temperature rise and the consistency of molding quality, but also has good scalability and industrial applicability. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments described in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0016] Figure 1 This is a mind map of the method of the present invention. DETAILED DESCRIPTION

[0017] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0018] For examples, see Figure 1 As shown, the soft start control method for intelligent temperature control of the injection mold described in this embodiment includes: Acquire initial temperature data for multiple regions of the mold, including the mold cavity, nozzle, and material channel, and construct a temperature distribution model; Based on the temperature distribution model and the preset thermal inertia score, the temperature rise rate of different areas is predicted, and areas where thermal hysteresis may exist are identified; During the soft start phase, differentiated current or power limit parameters are set for each heating zone to form a dynamic soft start strategy at the zone level. Real-time collection of temperature feedback data from each area, combined with the predicted temperature rise trajectory and actual temperature rise rate, to dynamically correct the power output; After reaching the target temperature threshold, the limit is released and switched to PID closed-loop control to achieve uniform and stable control of the mold temperature.

[0019] Obtaining initial temperature data for multiple areas of the mold, including the mold cavity, nozzle, and material channel, and building a temperature distribution model can be broken down into the following technical steps and key points: Area division and sensor layout: Mold cavity: Place thermocouples or PT100 temperature sensors close to the molding cavity, cooling channels or stress concentration areas; Nozzle area: A sensor is installed at the nozzle root or flow channel interface to reflect the temperature of the initial injection point of the material; Channel area: sensors are installed near the main channel, branch channel and end gate to cover the heat conduction path; The goal is to achieve multi-point coverage of the main thermal control areas within the mold to ensure that the temperature control strategy takes local differences into account.

[0020] Initial temperature data collection: After the control system is turned on, real-time temperature data of all sensors are collected; If it is a cold start (long shutdown), the temperature of each area will be different after natural cooling; The data records are associated with timestamps to form a temperature initial state matrix; Constructing a temperature distribution model: Based on the collected data, the mold thermal distribution map is constructed through interpolation or thermal field simulation; Finite element modeling and spatial thermal network methods can be used to quantify the thermal inertia and heat capacity of each area; The system establishes a "mold area-temperature response relationship" for subsequent temperature rise prediction and control of differentiated current limiting; Integrating historical operating data or model training (such as machine learning) can further enhance model accuracy and responsiveness.

[0021] To achieve uniform temperature control and equipment protection during the initial heating phase of the injection mold, this paper proposes a soft-start control method for intelligent temperature control of the injection mold. This method specifically models and analyzes the thermal response characteristics of each heating zone. By collecting historical temperature data, building a thermal response model, and evaluating thermal coupling characteristics and control deviation risks, this method optimizes the power allocation strategy during the soft-start process, improving temperature control accuracy and system stability.

[0022] In a heating control system, each heating zone has significantly different temperature rise responses due to differences in structure, material, heat dissipation environment, and other factors. To model and quantify these differences, this paper proposes the concept of a "thermal inertia score."

[0023] First, during multiple typical heating cycles, the system collects temperature rise curves for each heating zone of the mold—the temperature trajectory of each zone per unit time. This data is used to analyze the time required for each zone to rise from the initial temperature to the target temperature.

[0024] Subsequently, under the premise of known heating power input, the temperature rise response time under unit power is calculated. Even if the heating power is 1 watt, the time required for each heating area to rise from the starting temperature to the set temperature is used as the "thermal response delay index" of the area.

[0025] Next, we introduce the regional heat capacity parameter. This parameter, calculated from the volume, material specific heat capacity, and density of the heated area, represents the region's heat storage capacity. Combining the thermal response delay metric with the heat capacity parameter creates a thermal inertia score. A higher score indicates a slower response and greater inertia.

[0026] To further identify potential control risks, this method sets a thermal inertia score threshold. If a region's score exceeds this threshold, it is considered to have a thermal hysteresis risk and is marked as a "thermal hysteresis region." In subsequent soft-start control, more conservative power limiting parameters are set for this region to prevent premature heating to excessive temperatures due to hysteresis, thereby avoiding local overheating and control errors.

[0027] In order to improve the predictive ability of the temperature control strategy, the present invention proposes to input the current initial temperature and the target set temperature into the prediction model, and realize the prediction of the temperature rise trend in different regions through weighted analysis.

[0028] The prediction model is a multi-factor weighted model, and its weighting factors include: Thermal inertia score: used to reflect the thermal response speed of each area; Regional thermal coupling anomaly value: used to indicate the intensity of thermal interference between the region and other regions; Historical control deviation frequency: used to measure the deviation stability of the area in past controls.

[0029] In practice, the model weights these factors and evolves the temperature difference between the initial and target temperatures, predicting the time and rate of temperature rise. This prediction is used to generate a temperature rise trend curve, which is compared with the target temperature rise curve. If the deviation exceeds the allowable range, the system proactively adjusts the soft-start current ratio or the slope of the heating curve to correct the temperature rise trend.

[0030] Heat conduction paths often exist between different heating zones in a mold, meaning that heating in one area can affect temperature fluctuations in adjacent areas. This paper proposes a computational method to identify this "thermal coupling" relationship and, through its fluctuation anomalies, identify potential system interference or structural coupling risks.

[0031] The specific method is as follows: First, temperature sensors are installed in multiple pre-set heating zones of the mold to collect real-time temperature change data during the heating process, forming a temperature time series for multiple time periods. For example, the temperature value of each zone is recorded every second, and continuous sampling is carried out for several minutes to obtain a detailed temperature change curve.

[0032] Then, we select any two regions and analyze whether there is any synchronization between the changing trends of their temperature series. We use a covariance calculation method, which observes the degree to which the temperatures of two regions rise or fall simultaneously over a certain period of time and calculates their covariance value as a measure of the strength of thermal coupling.

[0033] For each region, the absolute value of the covariance between it and all other regions is summed to obtain its "total thermal coupling" metric. The average total thermal coupling of all regions is then calculated, and the deviation between each region's thermal coupling and the average is analyzed. If the deviation exceeds a set threshold, the region is considered to have thermal coupling anomaly and is marked as a "thermal coupling anomaly region."

[0034] This judgment method allows the system to identify sensitive areas that may be greatly affected by neighboring areas, and then focus on protecting them during soft start control.

[0035] In order to further improve the reliability of the control strategy, the present invention introduces a historical control deviation frequency parameter to evaluate the probability of a certain area having obvious deviations in multiple past controls.

[0036] The evaluation steps are as follows: During multiple historical soft start cycles, the difference between the actual temperature and the target temperature of each zone is recorded; Set the temperature deviation tolerance threshold, such as ±2 degrees Celsius; If the difference between the actual temperature and the target temperature exceeds the threshold, it is considered a "deviation event"; The proportion of time points occupied by deviation events in each cycle is counted and defined as the "regional deviation frequency" of the cycle; The deviation frequencies over multiple historical periods are averaged to arrive at the “historical control deviation frequency”.

[0037] The higher the frequency, the greater the error in the temperature control model for that area or the greater the impact of disturbances. In subsequent prediction models, this area can be weighted or feedback sensitivity can be increased to allow for early intervention and control, thereby improving temperature control stability.

[0038] By modeling these four core data points and integrating them into a judgment mechanism, this invention develops a soft-start control method with learning and adaptive adjustment capabilities. This method is particularly suitable for injection molding systems with complex mold structures and demanding high temperature control stability. Compared to existing control methods that rely on single-point temperature feedback, this method effectively identifies and suppresses thermal hysteresis and thermal coupling errors, improving mold heating consistency and product quality.

[0039] Traditional mold heating soft-start control typically uses a unified limiting strategy, setting the same current limit or power slope for all heating zones. However, in actual mold applications, each zone has different structures, materials, heat capacity, and heat dissipation environments, resulting in inconsistent thermal response characteristics.

[0040] For example, the mold cavity typically dissipates heat quickly and responds slowly, while the nozzle or material channel, due to its small size and rapid material heat transfer, heats up significantly faster than other areas. Using uniform limiting parameters will inevitably lead to uneven heating, localized overheating, or insufficient heating. In severe cases, this can cause mold damage or fluctuating molding quality.

[0041] Therefore, it is necessary to set differentiated soft-start parameters based on the thermal characteristics of each heating zone to achieve zone-level heating strategy optimization.

[0042] The specific implementation steps of the differentiated limiting strategy include: Get the thermal inertia score of each heating zone (indicating how slow the thermal response is); Obtain the abnormal value of regional thermal coupling (representing the strength of interference from neighboring areas); Obtain historical control deviation frequency (representing temperature rise stability and model fitting degree); For areas with slower response and higher inertia scores (such as mold cavities), set a higher initial power or current limit to compensate for thermal response hysteresis; For areas with fast response or significant thermal coupling effects (such as nozzles), set a lower limit to avoid rapid temperature increases; Set a slow-rise curve or multi-level limiting strategy for areas with high deviation frequency to improve the controllability of temperature rise; For example, when the total rated power of a system is 100%, the power limit will be allocated in the following proportions during the soft start phase: 60% in the cavity area, 30% in the channel area, and 10% in the nozzle area.

[0043] The limiting parameters are not statically set, but are dynamically adjusted based on real-time temperature feedback and predicted deviations; The controller monitors the difference between the current temperature change rate of each area and the output of the prediction model. If a certain area heats up too quickly, its limit is tightened appropriately. If the temperature rise in a certain area lags significantly and there is no risk of thermal coupling, the limit can be temporarily relaxed to increase the temperature rise rate.

[0044] Use a PID controller with an adjustable phase controller (such as SCR or Triac) to accurately control the heating power by dynamically adjusting the conduction angle; Or use PWM to control the heating circuit opening cycle to achieve high-resolution power limit regulation; All control parameters are controlled by the soft start control algorithm module deployed in the temperature control motherboard or industrial-grade PLC.

[0045] For example, in a system for injecting glue into an automotive headlight, the cavity area is large and has a slow thermal response, while the nozzle area is a small metal cone. The system employs the differentiated limiting strategy of our invention, gradually increasing the power in the cavity area from 50% to 90%, while the nozzle area never exceeds 30%. This rate of increase is adjusted in real time by a predictive model, ultimately achieving a temperature differential within ±1.5°C across the mold, significantly outperforming traditional uniform heating methods.

[0046] During the heating process, this method collects the temperature values ​​of each heating zone in real time and calculates the temperature change rate per unit time as the actual temperature rise rate. Simultaneously, the system uses a pre-established prediction model to generate a predicted temperature rise trajectory for each zone based on input parameters such as initial temperature, thermal inertia score, and historical deviation.

[0047] Then, at each time step, the actual temperature-rise rate is compared with the predicted temperature-rise rate, and the difference, known as the temperature-rise rate error, is calculated. This error not only reflects the prediction accuracy but also serves as immediate feedback on system stability. The collection of error data generated within consecutive time steps constitutes a "temperature-rise rate error sequence," which is used for subsequent modeling and control decisions.

[0048] This method innovatively uses the dynamic Bayesian network (DBN) algorithm to probabilistically model the temperature rise rate error sequence to determine whether there will be a high deviation risk in the future, thereby providing prior decisions for the control strategy.

[0049] The temperature rise rate error at each time point is recorded as an observed variable as Et, which is the difference between the current predicted value and the actual temperature rise rate.

[0050] At the same time, the "hidden state" St at each moment is defined to represent the deviation level of the system's current temperature control, which is divided into several levels such as "normal", "slight deviation", and "serious deviation".

[0051] Set St only to the previous moment Related, satisfying the Markov assumption. That is: The transition probability is , which can be learned from historical training data.

[0052] The observation model is used to describe the observation error Et that the system may produce under a certain hidden state St. It is usually modeled as a Gaussian distribution; that is, a certain state corresponds to an error mean and standard deviation range.

[0053] Using the prior probability of the state at the previous moment Based on the error Et observed at the current time t, Bayesian inference or particle filtering is used to calculate the probability that the system will enter a "high deviation state" at the next time t+k. This probability is recorded as the temperature control deviation risk value Rt+k. If this value is greater than 0.7 (i.e., a 70% risk probability), the system deems a significant deviation trend to exist.

[0054] Once the prediction module determines that there is a risk of deviation from the temperature rising trend in a certain area, this method achieves dynamic optimization of power output by making fine-grained adjustments to the heating control parameters.

[0055] The system first determines the regulation priority of each area based on the deviation risk value. Areas with higher risk values ​​are prioritized for regulation, concentrating resources on controlling critical temperature rise areas.

[0056] If the area uses PWM (pulse width modulation) to control the electric heating element, the system calculates the PWM duty cycle adjustment increment based on the direction and magnitude of the current error: if the actual temperature rise is slower than predicted, the duty cycle is increased; if the actual temperature rise is too fast, the duty cycle is reduced; the adjustment step is limited to the set maximum variation range (such as a maximum of ±10% / cycle) to prevent temperature control oscillation or unstable heating.

[0057] If the zone uses silicon-controlled rectifiers (SCRs) or thyristor phase control technology, power regulation is achieved by varying the conduction angle. A larger conduction angle increases the heating time and increases the average power; vice versa. Based on the predicted risk, the controller appropriately shortens or lengthens the conduction angle to ensure that the actual heating rate approaches the predicted target.

[0058] All PWM duty cycle or conduction angle adjustment operations are completed within the system control cycle, forming a closed-loop control circuit. This is linked with the DBN prediction module, enabling the entire temperature control system to implement the intelligent control logic of "real-time monitoring → dynamic prediction → rapid response".

[0059] During the soft-start phase, due to issues such as uneven thermal inertia and structural thermal coupling during the initial heating phase, the system typically uses power limiting (limiting the PWM duty cycle or conduction angle) to gradually increase the temperature to prevent local overheating or system current surges. However, maintaining limiting control after the mold temperature approaches the set target value can result in insufficient temperature rise and a slow temperature control response, affecting production efficiency and mold temperature uniformity.

[0060] Therefore, when the temperature reaches a specific "target threshold", the system needs to release the limit limit and rely on PID closed-loop control to stably maintain the set temperature and achieve more precise temperature control.

[0061] The system usually sets a "target temperature determination threshold" which can be any of the following: Absolute temperature difference judgment: the actual temperature reaches a certain percentage of the target set value (such as 95%, 98%, 100%); Temperature rise rate determination: When the temperature rise rate decreases significantly and approaches zero, it indicates that the system is close to steady state; Temperature stability determination: The temperature fluctuation range is less than the set range (such as ±0.5°C) within a period of time (such as 30 seconds); Comprehensive condition judgment: Combine the above conditions to form a stability judgment model to further avoid misjudgment.

[0062] Once the above conditions are met, the controller will trigger the "release limit" flag.

[0063] Releasing the limit includes: canceling the soft-start power limit parameters; allowing the PWM duty cycle or conduction angle to return to the normal adjustable range (such as 0–100%); and the system enters a dynamic output response state with full power regulation capability.

[0064] Start the PID controller, use the set temperature as the target value, the current temperature as the feedback value, and calculate the error. Based on the error, the proportional (P), integral (I), and differential (D) are calculated in real time to adjust the output. The output control signal drives the heating power adjustment so that the actual temperature accurately tracks the set value.

[0065] The system continuously runs PID regulation and dynamically responds to external disturbances. If the temperature in a certain area deviates from the target, the PID controller responds immediately and adjusts the power output to restore the temperature balance. The control goal is to maintain temperature stability with minimum energy consumption, and the temperature fluctuation range is controlled within ±0.3°C.

[0066] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0067] It should be understood that the term "and / or" herein is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent three situations: A exists alone, A and B exist at the same time, and B exists alone, where A and B may be singular or plural. In addition, the character " / " herein generally indicates that the objects associated with each other are in an "or" relationship, but it may also indicate an "and / or" relationship, which can be understood by referring to the context. A person of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0068] The above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the scope of protection of the present application.

Claims

1. A soft start control method for intelligent temperature control of a glue injection mold, characterized by: include: Acquire initial temperature data for multiple regions of the mold, including the mold cavity, nozzle, and material channel, and construct a temperature distribution model; Based on the temperature distribution model and the preset thermal inertia score, the temperature rise rate of different areas is predicted, and areas where thermal hysteresis may exist are identified; During the soft start phase, differentiated current or power limit parameters are set for each heating zone to form a dynamic soft start strategy at the zone level. Real-time collection of temperature feedback data from each area, combined with the predicted temperature rise trajectory and actual temperature rise rate, to dynamically correct the power output; After reaching the target temperature threshold, the limit is released and switched to PID closed-loop control to achieve uniform and stable control of the mold temperature.

2. The soft start control method for intelligent temperature control of a glue injection mold according to claim 1, characterized in that: The calculation of the thermal inertia score includes: Collect historical temperature rise curves of each heating area of ​​the mold; Calculate the temperature rise response time per unit power in each area as the thermal response delay indicator; Calculate the thermal inertia score based on the thermal response delay index and regional heat capacity parameters; If the thermal inertia score of the heating area is higher than a preset threshold, it is marked as a thermal hysteresis area and the limiting strategy is adapted in the soft start control.

3. The soft start control method for intelligent temperature control of a glue injection mold according to claim 2, characterized in that: Predicting the temperature rise rate in different regions includes: inputting the current initial temperature and the target set temperature into a prediction model; the prediction model uses a multi-factor weighted method, and the weighted factors include the thermal inertia score value, the regional thermal coupling abnormality value and the historical control deviation frequency to calculate the expected temperature rise time and rate.

4. The soft start control method for intelligent temperature control of a glue injection mold according to claim 3, characterized in that: The method for obtaining the regional thermal coupling degree anomaly value is as follows: synchronously collecting temperature change data in multiple preset heating areas and constructing a temperature time series matrix for multiple periods; Calculate the temperature covariance between any two regions based on the temperature series, and use it to solve the total thermal coupling degree of each region; The global average value of thermal coupling in all regions is calculated, and the thermal coupling deviation value of each region is calculated as the regional thermal coupling anomaly value.

5. The soft start control method for intelligent temperature control of a glue injection mold according to claim 4, characterized in that: The method for obtaining the historical control deviation frequency is as follows: recording the instantaneous deviation value between the actual temperature and the target temperature of each heating zone during multiple historical soft start cycles; Set a deviation tolerance threshold and count the percentage of time points in each soft start cycle where the deviation exceeds the threshold. This is defined as the regional deviation frequency. Summarize the deviation frequencies over multiple cycles and take the average to form the historical control deviation frequency.

6. The soft start control method for intelligent temperature control of a glue injection mold according to claim 1, characterized in that: The dynamically corrected power output includes: Collect the temperature feedback value of each heating area in real time and calculate its temperature change rate per unit time as the actual temperature rise rate; The temperature rise trajectory output by the prediction model is called, and the error between the temperature rise trajectory and the actual temperature rise rate is calculated at each time step to construct a temperature rise rate error sequence. Based on the temperature rise rate error sequence, a probability model is performed on the difference between the predicted and actual temperatures to estimate the risk value of future temperature control deviation; If the temperature control deviation risk value exceeds the risk threshold, the PWM duty cycle or conduction angle of the heating area will be dynamically corrected to achieve real-time optimization of power output.

7. The soft start control method for intelligent temperature control of a glue injection mold according to claim 6, characterized in that: Estimating the risk value of future temperature control deviation includes: The predicted temperature rise rate and the actual temperature rise rate of each heating area are collected in multiple time steps, and the difference between the two is calculated to form a temperature rise rate error sequence; Taking the error value as an observable variable, a dynamic Bayesian network model is constructed, defining the hidden state of each time step as the control deviation state, setting it to depend only on the hidden state at the previous moment, and establishing the state transition probability relationship; Based on historical control data or real-time observation sequences, estimate state transition probabilities and observation probability distributions using expectation maximization algorithms or Bayesian filtering methods; At any current moment, based on the known error sequence, the probability that the system will be in a high deviation state in the future period of time is inferred as the future temperature control deviation risk value.

8. The soft start control method for intelligent temperature control of a glue injection mold according to claim 7, characterized in that: The dynamic correction of the PWM duty cycle or conduction angle of the heating area includes: Determine the adjustment priority of each heating area based on the predicted deviation risk value, and give priority to adjusting areas where the risk probability is higher than the threshold; If the heating area uses PWM control, the adjustment increment is calculated based on the current error direction and magnitude, and the PWM duty cycle is increased or decreased to refine the power output. The duty cycle change is limited to the preset maximum adjustment step size. If the heating area adopts thyristor or SCR control, the conduction angle is adjusted through phase control to shorten or extend the conduction time period, thereby changing the average electric power within a single cycle.

Images