An intelligent toy injection molding process optimization method

Abstract

The application provides an intelligent toy injection molding process optimization method, comprising the following steps: for a key temperature control area, calculating an optimized cooling time value and a cooling water temperature setting value through an association model of toy material thermodynamic attribute parameters, cooling time and cooling water temperature, and issuing the optimized cooling time value and the cooling water temperature setting value to an injection molding machine control system; meanwhile, according to the temperature fluctuation amplitude of the key area, the molding pressure value is fine-tuned to reduce the temperature fluctuation of the key area; in the injection molding process, temperature data of multiple positions on the mold surface are collected in real time and transmitted to a central processor; after the collected temperature data are filtered and denoised by the central processor, it is judged whether the temperature data exceed the optimized temperature control range; if the temperature data exceed the optimized temperature control range, an alarm mechanism is triggered, and the injection molding machine operating parameters are automatically adjusted to shorten the time deviating from the temperature control range to the minimum.

Description

Technical Field

[0001] The present invention relates to the field of information technology, in particular to injection molding, and specifically to an intelligent toy injection molding process optimization method. Background Art

[0002] During the toy injection molding process, how can we precisely control the mold temperature distribution based on the toy's structural characteristics and material properties to ensure product quality? First, we need to obtain information such as the toy's structural complexity and wall thickness distribution, as well as material parameters such as heat deformation temperature and thermal conductivity. Using pre-established correlation models, we can initially determine the set ranges for heating temperature, cooling time, and molding pressure. However, in actual production, mold temperature distribution is often uneven, which can lead to product defects. Therefore, we need to perform numerical simulations of the mold temperature field and analyze the temperature distribution using image processing algorithms. If abnormal temperature areas are found, we need to determine whether they are located in areas with complex toy structures or large variations in wall thickness. For these critical temperature control areas, we need to optimize the cooling time and cooling water temperature, while also fine-tuning the molding pressure. During this process, we also need to monitor the mold surface temperature in real time and dynamically adjust the injection molding machine parameters based on the actual situation. Finally, through quality testing and feedback on the finished product, we can continuously optimize the process parameter model to improve production accuracy and efficiency. Summary of the Invention

[0003] The present invention provides an intelligent toy injection molding process optimization method, which mainly includes:

[0004] Obtain information such as the structural complexity, wall thickness distribution, size, and shape characteristics of the toy in the current production task, as well as thermodynamic property parameters such as thermal deformation temperature, thermal conductivity, specific heat capacity, and melting temperature of the toy material. Through the pre-established correlation model between the toy structural characteristics and the material thermodynamic properties and process parameters, determine the initial setting ranges for the heating temperature, cooling time, and molding pressure values ​​in the injection molding process;

[0005] Based on the number of mold cavities and the layout of the cooling water channels, the finite element analysis method is used to numerically simulate the mold temperature field during the injection molding process. A temperature distribution map reflecting the temperature distribution state of the mold surface is obtained. Based on the temperature distribution map, the image processing algorithm is used to determine the uniformity of the temperature distribution. If there is a temperature fluctuation exceeding a preset threshold or the temperature distribution is uneven beyond a preset ratio, the position coordinates of the temperature abnormality area and the temperature fluctuation amplitude value are automatically extracted;

[0006] Based on the coordinates of the temperature anomaly area, determine whether it is located in a part of the toy with complex structure or large wall thickness variations. If so, mark the area as a critical temperature control area. At the same time, based on the temperature fluctuation amplitude and the duration of the temperature anomaly, determine whether the temperature anomaly is caused by the mold surface coating material or uneven heater power. If so, generate corresponding mold repair or heater replacement instructions;

[0007] For key temperature control areas, the system calculates optimized cooling time and cooling water temperature settings using a correlation model between toy material thermodynamic properties and cooling time and cooling water temperature. These values ​​are then sent to the injection molding machine control system. Furthermore, the molding pressure is fine-tuned based on the temperature fluctuations in key areas to minimize these fluctuations.

[0008] During the injection molding process, temperature data from multiple locations on the mold surface is collected in real time and transmitted to the central processing unit. The central processing unit filters and removes noise from the collected temperature data and determines whether it exceeds the optimized temperature control range. If so, an alarm mechanism is triggered and the injection molding machine operating parameters are automatically adjusted to minimize the time that the temperature deviates from the control range.

[0009] After injection molding is completed, the size, shape and surface quality of the finished toy are automatically inspected to obtain the actual structural characteristic parameters of the finished toy, compare the actual structural characteristic parameters with the design parameters, and calculate the structural deviation value. If the deviation value exceeds the preset threshold, the deviation data is fed back to the process parameter optimization model to dynamically correct the initial setting range of the process parameters for the next production task.

[0010] The technical solution provided by the embodiment of the present invention may have the following beneficial effects:

[0011] The present invention establishes a process parameter correlation model by acquiring the structural characteristics of the toy and the thermodynamic properties of the material, and determines the initial process parameter range. Finite element analysis is used to simulate the mold temperature field, and image processing is used to identify temperature anomaly areas. For key temperature control areas, the cooling time and water temperature are optimized, and the molding pressure is adjusted. During the injection molding process, the temperature is monitored in real time, and the parameters are automatically adjusted to control temperature deviations. After molding, the toy is inspected, and the structural deviation is fed back to the parameter optimization model. The present invention achieves precise temperature control in the toy injection molding process, effectively improves product quality and production efficiency, reduces the defective product rate, and provides an intelligent and automated production solution for the toy manufacturing industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 This is a flow chart of an intelligent toy injection molding process optimization method of the present invention. DETAILED DESCRIPTION

[0013] To further understand the content of the present invention, the present invention is described in detail with reference to the accompanying drawings and examples. The present invention will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are intended only to illustrate the relevant invention and are not intended to limit the invention. It should also be noted that, for ease of description, only portions relevant to the invention are shown in the accompanying drawings.

[0014] like Figure 1 In this embodiment, a method for optimizing the injection molding process of an intelligent toy may specifically include:

[0015] Step S101: Obtain information such as the structural complexity, wall thickness distribution, size, and shape characteristics of the toy in the current production task, and simultaneously obtain thermodynamic property parameters such as the thermal deformation temperature, thermal conductivity, specific heat capacity, and melting temperature of the toy material. Determine the initial setting ranges of the heating temperature value, cooling time value, and molding pressure value in the injection molding process through a pre-established correlation model between the toy structural characteristics and the material thermodynamic properties and the process parameters.

[0016] Obtain data on the toy's structural complexity, wall thickness distribution, dimensional characteristics, and shape characteristics for the current production task to form a toy structural feature set. Obtain data on the toy material's thermal deformation temperature, thermal conductivity, specific heat capacity, and melting temperature to form a material thermodynamic property set. Input the toy structural feature set and the material thermodynamic property set into a pre-established correlation model to obtain the initial values ​​of the process parameters. If the initial values ​​of the process parameters exceed the preset threshold, adjust the weight coefficients in the correlation model and recalculate the initial values ​​of the process parameters. Based on the adjusted initial values ​​of the process parameters, determine the setting ranges for the heating temperature, cooling time, and molding pressure. Use a regression algorithm to optimize the setting ranges to obtain the optimal combination of process parameters. Input the optimal combination of process parameters into the injection molding control system to complete the process parameter configuration.

[0017] Specifically, the key to toy injection molding lies in understanding the relationship between structural characteristics and process parameters. For example, a children's building block toy has uneven wall thickness distribution: the outer wall is 3 mm thick, while the inner support ribs are 2 mm thick. This structural characteristic can lead to uneven shrinkage during injection molding. Regarding shape characteristics, the building block has a subtle surface texture and measures 50 x 50 x 20 mm, making it a medium-complexity structure. The material used is polypropylene, which has a heat deflection temperature of 145°C, a thermal conductivity of 0.22 watts per meter Kelvin, a specific heat capacity of 1920 joules per kilogram Kelvin, and a melting point of 165°C. These thermodynamic properties determine the material's flowability and cooling characteristics during the molding process. There is a close correlation between material properties and structural characteristics. For example, wall thickness distribution affects heat transfer efficiency, which in turn affects molding quality. The correlation model uses a neural network architecture, with the input layer containing nodes for structural characteristics and material properties. For the building block toy example, the initial calculations yielded a heating temperature of 220°C, a cooling time of 20 seconds, and a molding pressure of 80 MPa. When the temperature exceeded the threshold (200°C), the model's structural feature weights were adjusted to reduce the influence of wall thickness, and the temperature was recalculated to 195°C. The process parameter setting range must consider both product quality and production efficiency. A temperature range of 185 to 195°C prevents material degradation while ensuring sufficient melting. A cooling time range of 18 to 22 seconds balances the molding cycle and product warpage control. A molding pressure range of 75 to 85 MPa ensures complete filling without flashing. Regression optimization employed the response surface methodology, with product appearance quality, dimensional accuracy, and production efficiency as optimization objectives. Sample data was obtained through multiple experiments, and a mathematical model linking process parameters and product performance was established. The optimal parameters were ultimately determined: a temperature of 190°C, a cooling time of 20 seconds, and a pressure of 80 MPa. This set of parameters ensures both stable product quality and high production efficiency. The optimized parameters are input into the injection molding machine control system, which performs closed-loop control based on the actual processing process. Temperature and pressure sensors monitor the process parameters in real time to ensure they remain within the set range. This precise control can ensure product consistency during mass production, reduce defective rates and improve production efficiency.

[0018] Step S102: Based on the number of mold cavities and the layout of the cooling channels, finite element analysis is used to numerically simulate the mold temperature field during the injection molding process, generating a temperature distribution map reflecting the mold surface temperature distribution. An image processing algorithm is used to determine the uniformity of the temperature distribution map. If temperature fluctuations exceed a preset threshold or the temperature distribution is uneven beyond a preset ratio, the coordinates of the abnormal temperature area and the temperature fluctuation amplitude are automatically extracted.

[0019] The geometric data of the number of mold cavities and the layout of the cooling water channels are obtained as input conditions for finite element analysis. The mold temperature field is numerically simulated using finite element analysis methods to obtain a temperature distribution map of the mold surface. Based on the temperature distribution map, the temperature uniformity value is calculated using an image processing algorithm to determine whether the temperature fluctuation exceeds the preset threshold. If the temperature fluctuation exceeds the preset threshold, further analysis is performed to determine whether the temperature distribution ratio exceeds the preset ratio. When the uneven temperature distribution exceeds the preset ratio, the position coordinates of the temperature anomaly area are automatically extracted. Combining the position coordinates with the temperature distribution map, the fluctuation amplitude value of the temperature anomaly area is calculated. Based on the fluctuation amplitude value and the position coordinates, an analysis report of the temperature anomaly area is generated.

[0020] Specifically, the number of mold cavities is often directly related to production efficiency. For example, a dual-cavity mold can simultaneously produce two identical plastic toy parts, improving production efficiency. Cooling water channel layout is key to mold temperature control. For example, a baby toy mold uses a combination of linear and spiral cooling channels, with channel spacing maintained at approximately 25 mm. This layout ensures uniform cooling across all mold areas. Finite element analysis can be performed by dividing the mesh into cells. For example, the mold surface can be divided into 5,000 quadrilateral elements, each approximately 0.5 mm in size. The temperature field distribution is then calculated by solving the heat transfer equation. Temperature distribution graphs typically use different colors to represent different temperature zones, such as red indicating high temperatures, potentially reaching 180°C, and blue indicating low temperatures, perhaps 60°C. Temperature uniformity is calculated using the standard deviation method, statistically analyzing mold surface temperature data. The preset temperature fluctuation threshold is typically ±5°C; if a region's temperature exceeds this range, it warrants attention. The temperature distribution ratio refers to the percentage of the total area occupied by the abnormal temperature region, with a typical preset threshold of 10%. Abnormal temperature areas are located using a region growing algorithm, starting from the highest temperature point and expanding outward until the temperature difference falls below a set threshold. For example, in a toy wheel mold, a temperature anomaly was detected at a corner. This area was located 100 mm to the left of the mold center, and the temperature was eight degrees Celsius higher than the surrounding area. The fluctuation amplitude was calculated by calculating the difference between the highest temperature in the abnormal area and the average temperature of the surrounding area. The analysis report includes information such as the location of the abnormal area, the temperature value, and the fluctuation range. For example, if the temperature fluctuation in the right cavity of the mold reaches ten degrees Celsius, the cooling water circuit design in this area needs to be optimized. This analysis helps improve the design rationality of the mold cooling system and ensure stable product quality. Problems discovered through temperature field analysis can directly guide mold improvements. For example, analysis of a building block mold revealed that corners were prone to overheating, with temperatures seven to nine degrees Celsius higher than the surrounding area. Adding cooling water circuits or adjusting the water circuit layout in this area can achieve a more uniform temperature distribution. The uniformity of the mold surface temperature field directly affects the internal stress distribution and dimensional stability of the product, and is crucial for improving product qualification rates.

[0021] Step S103: Based on the coordinates of the abnormal temperature area, the system determines whether it is located in a complex toy structure or one with significant wall thickness variation. If so, the area is marked as a critical temperature control zone. Furthermore, based on the temperature fluctuation amplitude and the duration of the abnormal temperature, the system determines whether the abnormal temperature is caused by uneven mold surface coating material or heater power. If so, the system generates instructions for mold repair or heater replacement.

[0022] The coordinates of the temperature anomaly area are obtained and matched against a pre-established database of coordinates for complex toy structures and areas with varying wall thickness. If a match is found, the area is marked as a critical temperature control area. For each critical temperature control area, the temperature fluctuation amplitude and duration data are extracted and compared with preset temperature fluctuation and duration thresholds. If the thresholds are exceeded, the cause determination phase begins. Based on the specific values ​​of the temperature fluctuation amplitude and duration, a pre-established model for determining defects in the mold surface coating material is used for analysis. If the model output indicates a coating material issue, a mold repair instruction is generated. A pre-established model for determining heater power unevenness is used, combined with the specific values ​​of the temperature fluctuation amplitude and duration. If the model output indicates a heater power unevenness issue, a heater replacement instruction is generated. For each marked critical temperature control area, historical temperature data is obtained and time series analysis is used to predict future temperature trends, generating a temperature change forecast. This forecast is combined with a pre-established optimization strategy model for the critical temperature control area to generate a temperature control optimization plan. This temperature control optimization plan is integrated with the mold repair or heater replacement instructions to generate a complete temperature anomaly handling plan and output it.

[0023] Specifically, in toy injection molding production, locating and controlling abnormal temperature areas is a critical step. For example, in a multi-cavity building block mold, coordinate matching revealed that the location of abnormal temperature at the joints closely matched pre-determined complex structural areas. These areas often occur at locations with varying wall thicknesses, such as buckles and bosses, requiring particular attention to temperature control. In a real-world application, suppose a building block exhibits temperature fluctuations at the buckle area. Monitoring data indicates that the temperature fluctuations in this area during the molding process reach ±8°C and last for more than 20 seconds, significantly exceeding the preset thresholds of ±5°C and 15 seconds. In this case, further analysis of the root cause of the temperature anomaly is necessary. Analysis using a coating material defect detection model reveals that large and prolonged temperature fluctuations are likely due to localized wear of the mold surface coating. For example, a toy mold using nickel-based alloy coatings may develop microcracks in localized areas after long-term operation under high temperature and high pressure, leading to reduced thermal conductivity and, in turn, temperature anomalies. In this case, mold repair instructions are required to repair or replace the damaged coating. Uneven heater power is also a significant factor contributing to temperature anomalies. For example, a toy mold heating system utilizes multiple heater groups working together. When the power output of one heater group is unstable, it can cause temperature fluctuations in a localized area. By using an established judgment model and combining temperature fluctuation characteristics, faulty heaters can be accurately identified and replacement instructions can be generated promptly. For identified critical temperature control areas, temperature trend prediction is required. For a toy mold, for example, recent temperature change data for this area was collected, and time series analysis was used to predict the temperature trend over the next four hours. The prediction results showed a trend of increasing temperature fluctuations, necessitating timely optimization and adjustment. Developing a temperature control optimization plan requires comprehensive consideration of multiple factors. For example, the optimization plan for a toy mold included adjusting cooling water flow, optimizing heater power distribution, and improving the mold surface treatment process. These optimization measures, combined with equipment maintenance instructions, form a comprehensive temperature anomaly handling plan, ensuring the stability of the mold temperature field distribution and improving product quality.

[0024] Step S104: For key temperature control areas, the optimized cooling time and cooling water temperature settings are calculated using a correlation model between the toy material's thermodynamic properties and cooling time and water temperature. These values ​​are then sent to the injection molding machine control system. Simultaneously, the molding pressure is fine-tuned based on the temperature fluctuations in the key areas to minimize these fluctuations.

[0025] Obtain the thermodynamic property parameters of the toy material and calculate the optimized values ​​for cooling time and cooling water temperature based on a preset correlation model. Transmit the optimized cooling time and cooling water temperature setpoints to the injection molding machine control system to complete parameter configuration. Monitor the temperature fluctuation amplitude in key areas to determine whether it exceeds the preset fluctuation threshold. If the temperature fluctuation amplitude exceeds the threshold, calculate the molding pressure adjustment value based on the fluctuation amplitude. Send the molding pressure adjustment value to the injection molding machine control system to update the molding pressure parameters. Continuously monitor the temperature in key areas to determine whether the temperature fluctuation is stabilizing. If the temperature fluctuation is stabilizing, terminate the adjustment process; otherwise, repeat the calculation and adjustment steps.

[0026] Step S105: During the injection molding process, real-time temperature data from multiple locations on the mold surface is collected and transmitted to the central processing unit (CPU). The CPU filters and de-noises the collected temperature data and determines whether it exceeds the optimized temperature control range. If so, an alarm is triggered and the injection molding machine operating parameters are automatically adjusted to minimize the time spent outside the temperature control range.

[0027] Temperature values ​​are acquired at preset collection points on the mold surface and transmitted to the central processing unit. The central processing unit uses a preset filter to denoise the temperature values, generating filtered values. Based on pre-established control limits, the CPU determines whether the filtered temperature value exceeds the control limits. If the filtered temperature value exceeds the control limits, an alarm is triggered to issue an alarm signal. Based on the temperature deviation, adjustments to the injection molding machine's operating parameters are calculated. The machine's operating parameters are automatically adjusted based on the calculated adjustments. Optimization methods are used to iteratively update the temperature control process, shortening the time that the temperature value deviates from the control limits.

[0028] Specifically, thermocouples or infrared sensors are typically used to collect temperature data on the mold surface. Thermocouples offer fast response and high reliability, allowing multiple collection points to be placed at key locations within the mold, such as the cavity surface and near cooling channels. The collected temperature data is transmitted to the central processing unit (CPU) via a data acquisition module. The sampling frequency is typically set at ten times per second to ensure continuous monitoring of temperature changes. To eliminate interference and noise during the sensor acquisition process, the CPU uses digital filters for signal processing. Common filtering methods include mean filtering and Kalman filtering, which can be selected based on actual operating conditions. For example, mean filtering, which takes a moving average of ten consecutively collected temperature values, can effectively eliminate random fluctuations and produce a smoother temperature curve. Control limits are set based on product quality requirements and process experience. For example, when injection molding toy shells, the mold surface temperature is controlled between 80°C and 90°C. Exceeding this range can result in product warping or poor surface quality. When the temperature exceeds the control limit, the system issues an audible and visual alarm to alert the operator. Temperature deviation refers to the difference between the actual temperature and the target temperature. When the system detects elevated temperatures, it automatically increases the cooling time or decreases the cooling water temperature. For example, if the temperature exceeds the upper limit by five degrees, the cooling time is extended by two seconds and the cooling water temperature is lowered by three degrees. This automatic adjustment mechanism quickly responds to temperature anomalies and reduces defective products. Adjustments to injection molding machine operating parameters include mold temperature, pressure, and speed. For example, when a localized area is found to be overheated, the cooling water flow rate near that area can be adjusted to improve the temperature distribution. Increasing the flow rate by 20 percent can reduce the local temperature by three to five degrees. The temperature control process is optimized iteratively. The system records the temperature trend after each adjustment and analyzes the effectiveness of the adjustment. If the temperature returns to the control limit longer than expected, the adjustment amount is increased in the next round of adjustments. Through continuous optimization, the time it takes for the temperature to return to the normal range has been reduced from 30 seconds to approximately 15 seconds. More precise control is achieved by establishing a correlation model between temperature and injection molding parameters. This model considers factors such as material thermal conductivity and mold structural characteristics to predict the impact of parameter adjustments on temperature. For example, when producing polycarbonate toy shells, the system can automatically calculate the optimal cooling time and water temperature combination based on the material properties, thereby improving the product's dimensional accuracy by 20 percent.

[0029] Step S106: After injection molding is complete, the finished toy's size, shape, and surface quality are automatically inspected to obtain its actual structural characteristic parameters. These parameters are compared with the design parameters to calculate structural deviations. If the deviation exceeds a preset threshold, the deviation data is fed back to the process parameter optimization model to dynamically adjust the initial setting range of process parameters for the next production task.

[0030] An image acquisition device is used to perform a full-scale scan of the finished injection-molded toy, capturing surface image data. Dimensional measurements and shape profile data are then extracted from the surface image data. These dimensional measurements and shape profile data are then fed into a pre-established surface quality analysis module to analyze surface defect distribution, calculate surface smoothness and texture consistency indicators, and generate a set of actual structural characteristic parameters. Standard design parameters for the finished toy are retrieved from the product design database. A parameter comparison model is then constructed to compare the actual structural characteristic parameter set against the standard design parameters item by item, calculating the deviation for each parameter. Based on the preset deviation thresholds, each deviation is determined to determine whether it exceeds the allowable range. Any out-of-limit deviation is flagged as an abnormal parameter, and a deviation data set is generated for each abnormal parameter and its corresponding deviation value. This deviation data set is then fed into a process parameter optimization model to analyze the causes of the deviations, determine the types of injection molding process parameters that require adjustment, and calculate the corrections for each process parameter. The injection molding machine's process parameter settings are adjusted based on the corrections, updating the initial setting ranges for the next batch of production tasks and generating a new process parameter configuration file. The new process parameter configuration file is transferred to the injection molding machine control system to complete the process parameter optimization and update, start the next batch of production tasks, and realize closed-loop optimization control of the injection molding process.

[0031] Specifically, image acquisition equipment at the end of the injection molding line uses a multi-angle scanning head to capture real-time surface information about the toy. For example, a high-resolution camera and a structured light scanner scan a plastic car model, simultaneously capturing the exterior dimensions, color distribution, and surface texture characteristics. The surface quality analysis module first processes the scanned data. For a car model, the system calculates metrics such as length, width, and height, surface roughness, and seam smoothness. For example, surface smoothness can be measured by the uniformity of laser reflection intensity, while texture consistency is quantified by the standard deviation of the image's grayscale values. During the parameter comparison phase, the system compares measured data with the design standard. For example, if the design requires a car model length of 150 mm and the measured value is 152 mm, exceeding the preset tolerance of plus or minus one mm, the system will flag this deviation as an anomaly. A significant dent defect is also detected on the right side of the car body, and the surface roughness reaches 0.5 microns, far exceeding the design standard requirement of 0.2 microns. The process parameter optimization model analyzes the causes of these anomalies. For oversize issues, which may be caused by excessive mold temperature, resulting in reduced plastic shrinkage, the system recommends lowering the mold temperature by five degrees Celsius. For surface sinking and excessive roughness, which may be caused by insufficient injection pressure or a short hold time, the system will increase the injection pressure and extend the hold time accordingly. These correction parameters are incorporated into a new process parameter profile to guide the next batch of production. Within closed-loop control, the system continuously monitors the effects of these adjustments. For example, if the body dimensions of the first batch of products are reduced to 151 mm and the surface roughness improves to 0.3 microns after adjustments, but still falls short of the target, the system will further fine-tune the process parameters, such as lowering the mold temperature by two degrees Celsius and increasing the injection pressure. Through this continuous parameter optimization and dynamic adjustment, the production process gradually approaches its optimal state, ensuring continuous improvement in product quality. This automated quality control system significantly improves production efficiency, reduces the need for manual intervention, and ensures more stable and reliable product quality. In practical applications, the system can also establish a signature database for different defect types to help quickly identify the cause of the problem and provide more precise process parameter correction recommendations.

[0032] The dimensional measurement values ​​and shape contour data are obtained based on the surface image data. The actual structural characteristic parameter set is compared with the standard design parameters item by item through the parameter comparison model to obtain the deviation value of each parameter. The process parameter optimization model is used to analyze the cause of the deviation, determine the type of injection molding process parameters that need to be adjusted, and obtain the correction amount of each process parameter.

[0033] Use an image acquisition device to scan the finished toy, obtain surface image data, and extract dimensional measurements and shape contour data. Input the extracted data into the surface quality analysis module to calculate the surface smoothness and texture consistency indicators and generate a set of actual structural characteristic parameters. Retrieve standard design parameters from the product design database, build a parameter comparison model, compare the actual parameters with the standard parameters item by item, and calculate the deviation values ​​for each item. Based on the preset deviation threshold range, determine whether the deviation value exceeds the limit. If it exceeds the limit, mark it as an abnormal parameter and generate a deviation data set. Input the deviation data set into the process parameter optimization model, analyze the cause of the deviation, determine the type of process parameter that needs to be adjusted, and calculate the correction amount for each process parameter. Adjust the process parameter setting value of the injection molding machine according to the correction amount and generate a new process parameter configuration file. Transfer the configuration file to the injection molding machine control system, update the process parameter setting range, and start the next batch of production tasks.

[0034] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A method for optimizing the injection molding process of intelligent toys, characterized in that: The method comprises: Step S101: Acquire information such as the structural complexity, wall thickness distribution, size, and shape characteristics of the toy in the current production task. Simultaneously, obtain thermodynamic property parameters such as the thermal deformation temperature, thermal conductivity, specific heat capacity, and melting temperature of the toy material. Using a pre-established correlation model between the toy's structural characteristics, the material's thermodynamic properties, and the process parameters, determine the initial setting ranges for the heating temperature, cooling time, and molding pressure during the injection molding process. Step S102: Based on the number of mold cavities and the layout of the cooling water channels, a finite element analysis method is used to numerically simulate the mold temperature field during the injection molding process to obtain a temperature distribution map reflecting the temperature distribution state of the mold surface. The uniformity of the temperature distribution is determined using an image processing algorithm based on the temperature distribution map. If there is a temperature fluctuation exceeding a preset threshold or the temperature distribution is uneven exceeding a preset ratio, the position coordinates of the temperature abnormality area and the temperature fluctuation amplitude value are automatically extracted; Step S103: Based on the coordinates of the temperature anomaly area, determine whether it is located in a complex toy structure or a location with large wall thickness variations. If so, mark the area as a critical temperature control area. Based on the temperature fluctuation amplitude and the duration of the temperature anomaly, determine whether the temperature anomaly is caused by uneven mold surface coating material or heater power. If so, generate corresponding mold repair or heater replacement instructions. Step S104: For the key temperature control areas, the optimized cooling time and cooling water temperature settings are calculated using a correlation model between the thermodynamic properties of the toy material and the cooling time and cooling water temperature. These values ​​are then sent to the injection molding machine control system. Simultaneously, the molding pressure is fine-tuned based on the temperature fluctuations in the key areas to minimize temperature fluctuations in the key areas. Step S105: During the injection molding process, temperature data from multiple locations on the mold surface is collected in real time and transmitted to the central processing unit. The central processing unit filters and de-noises the collected temperature data and determines whether it exceeds the optimized temperature control range. If so, an alarm mechanism is triggered and the operating parameters of the injection molding machine are automatically adjusted to minimize the time the temperature deviates from the temperature control range. Step S106: After the injection molding is completed, the size, shape and surface quality of the finished toy are automatically detected to obtain the actual structural characteristic parameters of the finished toy. The actual structural characteristic parameters are compared with the design parameters to calculate the structural deviation value. If the deviation value exceeds the preset threshold, the deviation data is fed back to the process parameter optimization model to dynamically correct the initial setting range of the process parameters for the next production task.

2. The method according to claim 1, characterized in that The step S101 includes: Obtaining data on the structural complexity, wall thickness distribution, size characteristics, and shape characteristics of the toy of the current production task to form a toy structural feature set; Obtain the thermal deformation temperature, thermal conductivity, specific heat capacity and melting temperature data of toy materials to form a set of material thermodynamic properties; Input the toy structural feature set and the material thermodynamic property set into the pre-established correlation model to obtain the initial values ​​of the process parameters; If the initial value of the process parameter exceeds the preset threshold, the weight coefficient in the correlation model is adjusted and the initial value of the process parameter is recalculated; Determine the setting range of heating temperature, cooling time and molding pressure according to the adjusted initial values ​​of process parameters; The regression algorithm is used to optimize the setting range to obtain the optimal process parameter combination; Input the optimal process parameter combination into the injection molding control system to complete the process parameter configuration.

3. The method according to claim 1, characterized in that The step S102 includes: Obtain geometric data of the number of mold cavities and cooling water channel layout as input conditions for finite element analysis; Finite element analysis method is used to numerically simulate the mold temperature field and obtain the mold surface temperature distribution map; Based on the temperature distribution graph, the temperature uniformity value is calculated through image processing algorithm to determine whether the temperature fluctuation exceeds the preset threshold; If the temperature fluctuation exceeds the preset threshold, further analysis is performed to determine whether the temperature distribution ratio exceeds the preset ratio; When the uneven temperature distribution exceeds the preset ratio, the coordinates of the abnormal temperature area are automatically extracted; Combine the location coordinates and temperature distribution map to calculate the fluctuation amplitude of the temperature anomaly area; Generate an analysis report of the temperature anomaly area based on the fluctuation amplitude value and location coordinates.

4. The method according to claim 1, wherein The step S103 includes: Obtain the location coordinates of the temperature anomaly area and match them with the pre-established coordinate database of complex toy structural areas and areas with varying wall thickness. If the match is successful, the area is marked as a critical temperature control area. For key temperature control areas, extract the temperature fluctuation amplitude and abnormal duration data, and conduct comparative analysis based on the preset temperature fluctuation threshold and duration threshold. If the threshold is exceeded, enter the judgment phase; Based on the specific values ​​of the temperature fluctuation amplitude and abnormal duration, a pre-established mold surface coating material defect judgment model is used for analysis. If the model output indicates a coating material problem, a mold repair instruction is generated; A pre-established heater power unevenness judgment model is used to make a judgment based on the specific values ​​of the temperature fluctuation amplitude and the abnormal duration. If the model output indicates a heater power unevenness problem, a heater replacement instruction is generated. For the marked key temperature control areas, obtain their historical temperature data, use time series analysis methods to predict future temperature change trends, and obtain temperature change prediction results; Based on the temperature change prediction results and combined with the pre-established key temperature control area optimization strategy model, a temperature control optimization plan is obtained; Integrate the temperature control optimization plan with the mold repair instructions or heater replacement instructions to generate and output a complete temperature anomaly handling plan.

5. The method according to claim 1, wherein The step S104 includes: Obtain the thermodynamic property parameters of the toy material and calculate the optimized values ​​of cooling time and cooling water temperature based on the preset correlation model; The optimized cooling time and cooling water temperature setting values ​​are transmitted to the injection molding machine control system to complete the parameter configuration; Monitor the temperature fluctuation range in key areas to determine whether it exceeds the preset fluctuation threshold; If the temperature fluctuation amplitude exceeds the threshold, the molding pressure adjustment value is calculated based on the fluctuation amplitude; Send the molding pressure adjustment value to the injection molding machine control system to update the molding pressure parameters; Continuously monitor the temperature in key areas to determine whether temperature fluctuations are stabilizing; If the temperature fluctuation tends to be stable, the adjustment process is ended, otherwise the calculation and adjustment are repeated.

6. The method according to claim 1, characterized in that The step S105 includes: Acquire temperature values ​​at preset collection points on the mold surface and transmit the collected temperature values ​​to the central processing unit; The central processing unit uses a preset filter to perform denoising on the temperature value to obtain a filtered temperature value; According to the pre-established control limits, determine whether the filtered temperature value exceeds the control limit range; If the filtered temperature value exceeds the control limit, the alarm will be triggered to send out an alarm signal; Calculate the adjustment amount of the injection molding machine operating parameters according to the deviation of the temperature value; Automatically adjust the operating parameters of the injection molding machine according to the calculated adjustment amount; The optimization method is used to iteratively update the temperature control process to shorten the time when the temperature value deviates from the control limit range.

7. The method according to claim 1, characterized in that The step S106 includes: Use image acquisition equipment to perform full-scale scanning of injection-molded finished toys, obtain surface image data of the finished toys, and extract dimension measurements and shape profile data from the surface image data; Input the dimension measurement values ​​and shape profile data into the pre-established surface quality analysis module to analyze the surface defect distribution, calculate the surface smoothness and texture consistency index, and generate a set of actual structural characteristic parameters; Retrieve the standard design parameters of finished toys from the product design database, build a parameter comparison model, compare the actual structural characteristic parameter set with the standard design parameters item by item, and calculate the deviation value of each parameter; According to the preset deviation threshold range, determine whether the deviation values ​​exceed the allowable range. If there is an out-of-limit deviation, mark it as an abnormal parameter, and generate a deviation data set with the abnormal parameters and their corresponding deviation values; Input the deviation data set into the process parameter optimization model, analyze the generation of deviations, determine the type of injection molding process parameters that need to be adjusted, and calculate the correction amount of each process parameter; Adjust the process parameter setting value of the injection molding machine according to the correction amount, update the initial setting range of the process parameters for the next batch of production tasks, and generate a new process parameter configuration file; The new process parameter configuration file is transferred to the injection molding machine control system to complete the process parameter optimization and update, start the next batch of production tasks, and realize the closed-loop optimization control of the injection molding process; The dimensional measurement values ​​and shape contour data are obtained based on the surface image data. The actual structural characteristic parameter set is compared with the standard design parameters item by item through the parameter comparison model to obtain the deviation value of each parameter. The process parameter optimization model is used to analyze the deviation, determine the type of injection molding process parameters that need to be adjusted, and obtain the correction amount of each process parameter.

8. The method according to claim 7, characterized in that Said include: Use image acquisition equipment to scan finished toys, obtain surface image data, and extract dimensional measurements and shape contour data; The extracted data is input into the surface quality analysis module to calculate the surface smoothness and texture consistency index and generate a set of actual structural characteristic parameters; Retrieve standard design parameters from the product design database, build a parameter comparison model, compare actual parameters with standard parameters item by item, and calculate the deviation values ​​of each item; According to the preset deviation threshold range, determine whether the deviation value exceeds the limit. If it exceeds the limit, mark it as an abnormal parameter and generate a deviation data set; Input the deviation data set into the process parameter optimization model, analyze the deviation, determine the type of process parameters that need to be adjusted, and calculate the correction amount for each process parameter; Adjust the process parameter setting value of the injection molding machine according to the correction amount and generate a new process parameter configuration file; Transfer the configuration file to the injection molding machine control system, update the process parameter setting range, and start the next batch of production tasks.

Images