Disclosure of Invention
The invention provides an intelligent toy injection molding process optimization method, which mainly comprises the following steps:
Obtaining information such as structural complexity, wall thickness distribution, size and shape characteristics of a toy in a current production task, simultaneously obtaining thermodynamic property parameters such as thermal deformation temperature, thermal conductivity coefficient, specific heat capacity, melting temperature and the like of a toy material, and determining an initial setting range of a heating temperature value, a cooling time value and a forming pressure value in an injection molding process through a pre-established association model of the structural property of the toy and the thermodynamic property of the material with the technological parameters;
according to the number of mold cavities and the layout of cooling waterways, performing numerical simulation on a mold temperature field in an injection molding process by adopting a finite element analysis method to obtain a temperature distribution diagram reflecting the temperature distribution state of the mold surface, judging the uniformity of the temperature distribution diagram by an image processing algorithm, and automatically extracting the position coordinates and the temperature fluctuation amplitude numerical value of a temperature abnormal region if the temperature fluctuation exceeds a preset threshold value or the temperature distribution unevenness exceeds a preset proportion;
judging whether the temperature abnormality region is positioned at a position with a complex structure or large wall thickness change according to the position coordinates of the temperature abnormality region, if so, marking the region as a key temperature control region, and judging whether the temperature abnormality is caused by uneven coating materials on the surface of the die or power of a heater according to the value of the temperature fluctuation amplitude and the duration of the temperature abnormality, if so, generating corresponding die repair or heater replacement instructions;
Aiming at a key temperature control area, calculating an optimized cooling time value and a cooling water temperature set value through a correlation model of thermodynamic property parameters of toy materials, cooling time and cooling water temperature, and sending the optimized cooling time value and the optimized cooling water temperature set value to an injection molding machine control system, and fine-tuning a molding pressure value according to the temperature fluctuation range of the key area so as to reduce the temperature fluctuation of the key area;
in the injection molding process, temperature data of a plurality of positions on the surface of the mold are acquired in real time and transmitted to a central processing unit, the central processing unit judges whether the acquired temperature data exceeds an optimized temperature control range after filtering and denoising, if so, an alarm mechanism is triggered, and meanwhile, the operation parameters of the injection molding machine are automatically adjusted, so that the time for deviating from the temperature control range is shortened to the minimum;
After injection molding is finished, the size, shape and surface quality of the toy finished product are automatically detected, the actual structural characteristic parameters of the toy finished product are obtained, the actual structural characteristic parameters are compared with the design parameters, the structural deviation value is calculated, if the deviation value exceeds a preset threshold value, deviation data are fed back to the process parameter optimization model, and the process parameter initial setting range of the next production task is dynamically corrected.
The technical scheme provided by the embodiment of the invention can have the following beneficial effects:
According to the invention, through obtaining the structural characteristics of the toy and the thermodynamic properties of the materials, a process parameter association model is established, and an initial process parameter range is determined. And simulating a mold temperature field by utilizing finite element analysis, and identifying a temperature anomaly region through image processing. And optimizing cooling time and water temperature aiming at a key temperature control area, and adjusting forming pressure. The temperature is monitored in real time in the injection molding process, and parameters are automatically adjusted to control temperature deviation. And detecting the toy after molding, and feeding back the structural deviation to the parameter optimization model. The invention realizes the accurate temperature control of the toy injection molding process, effectively improves the product quality and the production efficiency, reduces the defective rate, and provides an intelligent and automatic production solution for the toy manufacturing industry.
Detailed Description
For a further understanding of the present invention, the present invention will be described in detail with reference to the drawings and examples. The invention is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be noted that, for convenience of description, only the portions related to the invention are shown in the drawings.
As shown in fig. 1, the method for optimizing the injection molding process of the intelligent toy according to the embodiment specifically may include:
step S101, obtaining information such as structural complexity, wall thickness distribution, size and shape characteristics of a toy in a current production task, simultaneously obtaining thermodynamic property parameters such as thermal deformation temperature, heat conduction coefficient, specific heat capacity, melting temperature and the like of a toy material, and determining an initial setting range of a heating temperature value, a cooling time value and a molding pressure value in an injection molding process through a pre-established association model of the structural property of the toy and the thermodynamic property of the material with the technological parameters.
And acquiring the toy structure complexity, wall thickness distribution, size characteristics and shape characteristic data of the current production task to form a toy structure characteristic set. And acquiring data of the thermal deformation temperature, the thermal conductivity coefficient, the specific heat capacity and the melting temperature of the toy material to form a thermodynamic property set of the material. And inputting the toy structure feature set and the material thermodynamic property set into a pre-established association model to obtain an initial value of the technological parameter. If the initial value of the process parameter exceeds the preset threshold, adjusting the weight coefficient in the associated model, and recalculating the initial value of the process parameter. And determining the setting ranges of the heating temperature, the cooling time and the forming pressure according to the adjusted initial values of the process parameters. And optimizing the set range by adopting a regression algorithm to obtain the optimal technological parameter combination. Inputting the optimal technological parameter combination into an injection molding control system to complete technological parameter configuration.
In particular, the key to injection molding toys is the understanding of the relationship of structural features to process parameters. Taking a child building block toy as an example, the structure of the child building block toy has uneven wall thickness distribution, the wall thickness of the outer side is 3mm, the wall thickness of the inner side supporting rib is 2mm, and the structure characteristic can cause the problem of uneven shrinkage during injection molding. In terms of shape characteristics, the surface of the building block is provided with fine concave-convex textures, the size is 50 times 20mm, and the building block belongs to a medium-complexity structure. The material is polypropylene, the thermal deformation temperature is 145 ℃, the thermal conductivity is 0.22 watt per meter Kelvin, the specific heat capacity is 1920 joules per kilogram Kelvin, and the melting temperature is 165 degrees. These thermodynamic properties determine the flowability and cooling characteristics of the material during the forming process. There is a close correlation between material properties and structural features, such as wall thickness distribution, that can affect heat transfer efficiency and, in turn, molding quality. The association model adopts a neural network structure, and the input layer comprises structural characteristics and material attribute nodes. Taking a building block toy as an example, the heating temperature is 220 ℃ and the cooling time is 20 seconds, and the forming pressure is 80 megapascals. When the temperature is found to exceed the threshold value (200 degrees), the influence of the wall thickness factors is reduced by adjusting the weight of the structural characteristics in the model, and the temperature is calculated again to obtain 195 degrees. The determination of the process parameter setting range needs to consider the product quality and the production efficiency. The temperature range is 185 to 195 degrees, which can avoid material degradation and ensure sufficient melting. The cooling time ranges from 18 to 22 seconds, balancing the molding cycle and product warpage control. The forming pressure ranges from 75 to 85 megapascals, so that the filling is complete, and flash cannot be generated. The regression optimization adopts a response surface method, and takes the appearance quality, the dimensional accuracy and the production efficiency of the product as optimization targets. Sample data are obtained through multiple tests, and a mathematical model of technological parameters and product performance is established. Finally, the optimal parameters are obtained by optimizing the temperature to be 190 ℃, the cooling time to be 20 seconds and the pressure to be 80 megapascals. The set of parameters not only ensures stable product quality, but also realizes higher production efficiency. And inputting the optimized parameters into an injection molding machine control system, wherein the system needs to carry out closed-loop control according to the actual processing process. The process parameters are monitored in real time through the temperature sensor and the pressure sensor, so that the stability of the process parameters is ensured to be within the range of a set value. The accurate control can ensure the consistency of products in mass production, reduce the defective rate and improve the production benefit.
And step S102, carrying out numerical simulation on a mold temperature field in the injection molding process by adopting a finite element analysis method according to the number of mold cavities and the cooling water path layout, and obtaining a temperature distribution diagram reflecting the temperature distribution state of the mold surface. And judging the uniformity of the temperature distribution graph by an image processing algorithm, and automatically extracting the position coordinates and the temperature fluctuation amplitude values of the temperature abnormal region if the temperature fluctuation exceeds a preset threshold value or the temperature distribution is uneven by a preset proportion.
And obtaining the geometric data of the number of the die cavities and the layout of the cooling waterways, and taking the geometric data as input conditions of finite element analysis. And carrying out numerical simulation on the temperature field of the die by adopting a finite element analysis method to obtain a surface temperature distribution diagram of the die. And calculating a temperature uniformity value according to the temperature distribution diagram through an image processing algorithm, and judging whether the temperature fluctuation exceeds a preset threshold value. If the temperature fluctuation exceeds the preset threshold, further analyzing whether the temperature distribution proportion exceeds the preset proportion. And when the temperature distribution is uneven and exceeds the preset proportion, automatically extracting the position coordinates of the temperature abnormal region. And calculating the fluctuation amplitude value of the temperature abnormal region by combining the position coordinates and the temperature distribution map. And generating an analysis report of the temperature anomaly region according to the fluctuation amplitude value and the position coordinate.
In particular, the number of mold cavities is generally directly related to the production efficiency, for example, a dual cavity mold can simultaneously produce two identical plastic toy parts, thereby improving the production efficiency. The cooling waterway layout is the key of controlling the temperature of the mould, for example, a certain baby toy mould adopts a waterway layout combining a linear type with a spiral type, the waterway interval is kept at about twenty-five millimeters, and the layout can ensure that each region coo i ng of the mould is uniform. Finite element analysis may divide a grid of cells, such as dividing the mold surface into five thousand quadrilateral cells, each cell sized about five millimeters at zero, and obtain a temperature field distribution by solving a heat transfer equation. The temperature profile typically represents different temperature regions in different colors, e.g., red represents that a high temperature region may reach one hundred eighty degrees and blue represents that a low temperature region may be sixty degrees. And calculating the temperature uniformity by adopting a standard deviation method, and carrying out statistical analysis on the temperature data of the die surface. The preset temperature fluctuation threshold is usually plus or minus five degrees, and if the temperature of a certain area exceeds the range, important attention is required. The temperature distribution ratio refers to the percentage of the area of the abnormal temperature region to the total area, and the preset ratio threshold is generally ten percent. The abnormal temperature region is positioned by adopting a region growing algorithm, and the abnormal temperature region is expanded from the highest temperature point to the surrounding until the temperature difference is lower than a set threshold value. If in a toy wheel mold, temperature anomalies are found at the corners, the coordinates of the region are located one hundred millimeters to the left of the center of the mold, and the temperature is eight degrees higher than the surrounding. The fluctuation amplitude value is obtained by calculating the difference between the maximum temperature of the abnormal region and the surrounding average temperature. The analysis report contains information such as location description, temperature value, fluctuation range, and the like of the abnormal region. For example, the temperature fluctuation range of the cavity at the right side of the die reaches ten degrees, and the cooling water path of the area needs to be optimally designed. This analysis helps to improve the design rationality of the mold cooling system and ensures stable product quality. The problems found by temperature field analysis can direct the mold improvement directly. If analysis of a building block mould shows that the edge is easy to generate overheat, the temperature is seven to nine degrees higher than the surrounding temperature, and the temperature distribution can be more uniform by adding a cooling water path or adjusting the water path layout at the edge. The uniformity of the temperature field on the surface of the die directly influences the internal stress distribution and the dimensional stability of the product, and has important significance for improving the qualification rate of the product.
Step S103, judging whether the temperature abnormal region is positioned at a position with a complex toy structure or a large wall thickness change according to the position coordinates of the temperature abnormal region, and if so, marking the region as a key temperature control region. And judging whether the temperature abnormality is caused by uneven material of a coating on the surface of the die or power of the heater according to the temperature fluctuation amplitude value and the temperature abnormality duration, and if so, generating corresponding die repair or heater replacement instructions.
And acquiring position coordinate information of the temperature abnormal region, matching the position coordinate information with a coordinate database of a pre-established toy structure complex region and a wall thickness change region, and marking the region as a key temperature control region if the matching is successful. And extracting temperature fluctuation amplitude and abnormal duration data of the key temperature control region, carrying out comparison analysis by combining a preset temperature fluctuation threshold value and a preset duration threshold value, and entering a reason judging link if the threshold value is exceeded. And according to the specific values of the temperature fluctuation range and the abnormal duration, adopting a pre-established model for judging the defects of the coating material on the surface of the die to analyze, and generating a die repair instruction if the model output is the problem of the coating material. And judging by adopting a pre-established heater power non-uniformity judging model and combining specific values of the temperature fluctuation range and the abnormal duration, and generating a heater replacement instruction if the model output is the problem of the heater power non-uniformity. And aiming at the marked key temperature control area, acquiring historical temperature data of the marked key temperature control area, and predicting the future temperature change trend by adopting a time sequence analysis method to obtain a temperature change prediction result. And according to the temperature change prediction result, combining a pre-established key temperature control area optimization strategy model to obtain a temperature control optimization scheme. And integrating the temperature control optimization scheme with a die repair instruction or a heater replacement instruction, generating a complete temperature abnormality processing scheme and outputting the complete temperature abnormality processing scheme.
In particular, in toy injection molding production, the location and control of the temperature anomaly area is a key link. For example, aiming at a multi-cavity splicing toy mould, the abnormal temperature position of the connecting part can be found to be in high coincidence with a prestored complex-structure area through coordinate matching. Such areas often occur at abrupt wall thickness changes such as snaps, bosses, etc. of the toy parts, and the temperature control thereof needs to be focused. In practical application, provided that temperature fluctuation occurs at a buckling part of a certain spliced toy, monitoring data shows that the fluctuation amplitude of the temperature of the region reaches +/-8 ℃ in the forming process, and the duration exceeds 20 seconds and is obviously higher than preset +/-5 ℃ and 15 seconds thresholds. In this case, it is necessary to further analyze the root cause of the temperature abnormality. Through analysis of a coating material defect judging model, when the temperature fluctuation range is large and the duration time is long, the local loss of the coating material on the surface of the die is likely to occur. For example, when a toy mold is coated with a nickel-based alloy, after the toy mold is operated for a long time in a high-temperature and high-pressure environment, micro cracks appear in a local area, so that the heat conduction performance is reduced, and the temperature abnormality is caused. At this time, a mold repair instruction needs to be generated to repair or replace the damaged plating layer. The heater power non-uniformity is also an important factor causing temperature anomalies. If a toy mould heating system adopts a plurality of groups of heaters to work cooperatively, when the power output of a certain group of heaters is unstable, the temperature fluctuation of a local area can be caused. Through the established judgment model, the fault heater can be accurately identified by combining the temperature fluctuation characteristics, and a replacement instruction can be timely generated. For the determined critical temperature control area, a temperature change trend prediction is required. Taking a toy mould as an example, collecting recent temperature change data of the area, and predicting the temperature change trend within 4 hours in the future by a time sequence analysis method. The prediction result shows that the temperature fluctuation range has an expanding trend, and the optimization adjustment is needed in time. The formulation of the temperature control optimization scheme needs to comprehensively consider a plurality of factors. Such as optimization schemes for certain toy molds, including aspects of adjusting cooling water flow, optimizing heater power distribution, improving mold surface treatment processes, and the like. The optimization measures are combined with the equipment maintenance instructions to form a complete temperature anomaly processing scheme, so that the stability of the distribution of the temperature field of the die is ensured, and the product quality is improved.
Step S104, aiming at the key temperature control area, calculating an optimized cooling time value and a cooling water temperature set value through a correlation model of the thermodynamic property parameters of the toy materials, the cooling time and the cooling water temperature, and transmitting the optimized cooling time value and the optimized cooling water temperature set value to an injection molding machine control system. And meanwhile, the forming pressure value is finely adjusted according to the temperature fluctuation range of the key area so as to reduce the temperature fluctuation of the key area.
Thermodynamic property parameters of the toy materials are obtained, and optimized values of cooling time and cooling water temperature are calculated based on a preset association model. And transmitting the optimized cooling time and the optimized cooling water temperature set value to an injection molding machine control system to complete parameter configuration. And monitoring the temperature fluctuation amplitude of the key area, and judging whether the temperature fluctuation amplitude exceeds a preset fluctuation threshold value. If the temperature fluctuation range exceeds the threshold value, calculating a forming pressure adjustment value according to the fluctuation range. And sending the molding pressure adjustment value to an injection molding machine control system, and updating the molding pressure parameter. And continuously monitoring the temperature of the key area, and judging whether the temperature fluctuation tends to be stable or not. If the temperature fluctuation tends to be stable, ending the adjustment process, otherwise repeating the calculation and adjustment steps.
Step 105, in the injection molding process, temperature data of a plurality of positions on the surface of the mold are collected in real time and transmitted to the central processing unit. And after the central processing unit filters and denoises the collected temperature data, judging whether the temperature data exceeds an optimized temperature control range, triggering an alarm mechanism if the temperature data exceeds the optimized temperature control range, and simultaneously automatically adjusting the operation parameters of the injection molding machine to shorten the time for deviating from the temperature control range to the minimum.
Acquiring a temperature value at a preset acquisition point on the surface of the die, and transmitting the acquired temperature value to a central processing unit. The central processing unit adopts a preset filter to carry out denoising treatment on the temperature value, and a filtered temperature value is obtained. And judging whether the filtered temperature value exceeds the control limit range according to the pre-established control limit. And if the filtered temperature value exceeds the control limit range, triggering an alarm to send out an alarm signal. And calculating the adjustment quantity of the operation parameters of the injection molding machine according to the deviation degree of the temperature value. And automatically adjusting the operation parameters of the injection molding machine according to the calculated adjustment quantity. And the temperature control process is iteratively updated by adopting an optimization method, so that the time for deviating the temperature value from the control limit range is shortened.
Specifically, thermocouples or infrared sensors are typically employed when acquiring temperature values at the mold surface. The thermocouple has the characteristics of high response speed and high reliability, and a plurality of acquisition points such as the surface of a cavity, the vicinity of a cooling water channel and the like can be arranged at key positions of the die. The collected temperature data are transmitted to the central processing unit through the data collection module, the sampling frequency is generally set to be ten times per second, and continuous monitoring of temperature change is ensured. In order to eliminate interference and noise in the sensor acquisition process, a digital filter is adopted by the central processing unit for signal processing. Common filtering methods include mean filtering and Kalman filtering, and can be selected according to actual working conditions. Taking mean value filtering as an example, ten continuously acquired temperature values are subjected to moving average, so that random fluctuation can be effectively removed, and a more stable temperature curve is obtained. The control limits are set based on product quality requirements and process experience. For example, when producing toy shells by injection molding, the mold surface temperature is controlled between eighty degrees and ninety degrees, and exceeding this range may result in warping of the product or poor surface quality. The system sends out an audible and visual alarm signal when the temperature value exceeds the control limit, and reminds operators of paying attention. The temperature deviation means a difference between the actual temperature and the target temperature. When a higher temperature is detected, the system automatically increases the cooling time or decreases the cooling water temperature. For example, when the temperature exceeds the upper limit by five degrees, the cooling time is prolonged by two seconds, and the cooling water temperature is lowered by three degrees. The automatic regulating mechanism can quickly respond to abnormal temperature and reduce defective products. The adjustment of the operation parameters of the injection molding machine comprises the mold temperature, the pressure, the speed and the like. Taking the mold temperature control as an example, when the local area temperature is found to be too high, the temperature distribution can be improved by adjusting the flow rate of cooling water near the area. By increasing the water flow by twenty percent, the local temperature can be reduced by three to five degrees. The optimization of the temperature control process is performed in an iterative manner. The system records the temperature change trend after each adjustment, and analyzes the adjustment effect. If the time of the temperature regression control limit exceeds the expected time, the adjustment amount is increased in the next round of adjustment. By continuous optimization, the time for returning the temperature to the normal range can be shortened from the original thirty seconds to about fifteen seconds. By establishing a correlation model of temperature and injection molding parameters, more accurate control is realized. The model considers factors such as material thermal conductivity, mould structural characteristics, and the like, and predicts the influence of parameter adjustment on temperature. For example, in the production of polycarbonate toy shells, the system can automatically calculate the optimal combination of cooling time and water temperature according to the material characteristics, so that the dimensional accuracy of the product is improved by twenty percent.
And S106, after the injection molding is finished, automatically detecting the size, shape and surface quality of the finished toy product, and obtaining the actual structural characteristic parameters of the finished toy product. Comparing the actual structural characteristic parameter with the design parameter, calculating a structural deviation value, and if the deviation value exceeds a preset threshold value, feeding back deviation data to a process parameter optimization model to dynamically correct the process parameter initial setting range of the next production task.
And carrying out omnibearing scanning on the injection molded toy finished product by adopting image acquisition equipment to acquire surface image data of the toy finished product, and extracting size measurement value and shape contour data from the surface image data. Inputting the size measurement value and the shape profile data into a pre-established surface quality analysis module, analyzing the surface defect distribution condition, calculating the surface smoothness and texture consistency index, and generating an actual structure characteristic parameter set. And retrieving standard design parameters of the toy finished product from a product design database, constructing a parameter comparison model, comparing the actual structural characteristic parameter set with the standard design parameters item by item, and calculating deviation values of the parameters. Judging whether each deviation value exceeds an allowable range according to a preset deviation threshold range, marking the deviation value as an abnormal parameter if the deviation exceeds the allowable range, and generating a deviation data set from the abnormal parameter and the corresponding deviation value. Inputting the deviation data set into a process parameter optimization model, analyzing the reason for generating the deviation, determining the type of injection molding process parameters to be adjusted, and calculating the correction quantity of each process parameter. And (3) adjusting a technological parameter set value of the injection molding machine according to the correction quantity, updating a technological parameter initial set range of a next batch of production tasks, and generating a new technological parameter configuration file. And transmitting the new technological parameter configuration file to an injection molding machine control system, completing technological parameter optimization updating, starting a next batch of production tasks, and realizing closed-loop optimization control of an injection molding process.
Specifically, the image acquisition device acquires the toy surface information in real time at the end of the injection molding production line through the multi-angle scanning head, for example, a plastic automobile model is scanned by using a high-resolution camera and a structured light scanner, and the outline size, the color distribution and the surface texture characteristics of the outer surface of the automobile body can be acquired simultaneously. The surface quality analysis module firstly processes the scanning data, and for an automobile model, the system calculates indexes such as length, width, height, size, surface concave-convex degree, joint flatness and the like of the automobile body. For example, the smoothness of the surface of the vehicle body can be measured by the uniformity of the laser reflection intensity, and the texture uniformity can be quantified by the standard deviation of the gray value of the image. In the parameter comparison link, the system compares the measured data with the design standard. Taking an automobile model as an example, if the design requirement body length is one hundred fifty millimeters, the actual measurement value is one hundred fifty two millimeters, and the actual measurement value exceeds a preset tolerance range of plus or minus one millimeter, the system marks the deviation as abnormal. Meanwhile, the right side of the automobile body is detected to have obvious concave defects, and the surface roughness reaches five micrometers at zero and far exceeds the zero two-micrometer requirement of the design standard. The process parameter optimization model analyzes the cause of these anomalies. Aiming at the problem of bigger size, which is probably caused by the reduction of plastic shrinkage rate caused by the too high temperature of the mould, the system can recommend to reduce the temperature of the mould by five degrees, and for the surface dent and roughness exceeding, which is probably caused by insufficient injection pressure or too short dwell time, the system can correspondingly increase the injection pressure and prolong the dwell time. These correction parameters are integrated into a new process parameter profile for guiding the next batch production. In closed loop control, the system continuously monitors the effects after adjustment. Assuming that the body size in the adjusted first lot is reduced to one hundred fifty-one millimeter and the surface roughness is improved to zero three microns, but the target requirements are still not met, the system may further fine tune the process parameters, such as continuing to reduce the mold temperature by two degrees, increasing the injection pressure. Through the continuous parameter optimization and dynamic adjustment, the production process gradually tends to an optimal state, and the continuous improvement of the product quality is ensured. The automatic quality control system remarkably improves the production efficiency, reduces the manual intervention requirement and ensures that the product quality is more stable and reliable. In practical application, the system can also establish feature databases of different defect types, help to quickly locate the cause of the problem and provide more accurate technological parameter correction suggestions.
And obtaining a dimension measurement value and shape contour data according to the surface image data, comparing the actual structural characteristic parameter set with the standard design parameters item by item through a parameter comparison model to obtain deviation values of the parameters, analyzing a deviation generation reason by adopting a process parameter optimization model, determining the type of injection molding process parameters to be adjusted, and obtaining correction amounts of the process parameters.
And scanning the toy finished product by adopting image acquisition equipment, acquiring surface image data, and extracting size measurement values and shape contour data. Inputting the extracted data into a surface quality analysis module, calculating surface smoothness and texture consistency indexes, and generating an actual structure characteristic parameter set. And (3) retrieving standard design parameters from a product design database, constructing a parameter comparison model, comparing actual parameters with standard parameters item by item, and calculating various deviation values. And judging whether the deviation value exceeds the limit according to a preset deviation threshold range, and if so, marking the deviation value as an abnormal parameter to generate a deviation data set. Inputting the deviation data set into a process parameter optimization model, analyzing the deviation reason, determining the type of the process parameter to be adjusted, and calculating the correction quantity of each process parameter. And adjusting the technological parameter set value of the injection molding machine according to the correction quantity, and generating a new technological parameter configuration file. And transmitting the configuration file to an injection molding machine control system, updating the process parameter setting range, and starting the next batch of production tasks.
While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the invention.