A method and system for co-injection molding of two molten plastic materials that allows monitoring and utilization of injection pressure and optionally melt pressure and/or flow front pressure during an injection run. A controller alters the injection pressure so as to achieve and maintain optimal or desired ratios of injection pressure, and optionally melt pressure and/or flow front pressure, of the two molten plastic materials. This allows for more precise part manufacture, including reducing the thickness of a skin or shell layer compared to a core layer of a molded part.

An injection molding machine uses a native controller and a retrofit controller to effectively control its operation. The controllers may determine and/or receive information regarding the machine's maximum load capacity, and may also determine a current operational load value of the machine. The retrofit controller may cause the machine to operate at any number of combinations of settings of operational parameters which result in the machine operating at or below the maximum load value by adjusting any number of machine parameters associated with the injection molding machine based on feedback sensors measuring real-time operating conditions of the machine.

In order to reduce oscillations in process variables of an injection molding process, a variable-gain proportional-integral-derivative (PID) controller is utilized to control one or more of the process variables. The injection molding system may also include a tuning controller to automatically tune at least one of the proportional, integral, or derivative gains within a mold cycle. The tuning controller may obtain sensor data that monitors the operation of the injection molding machine to determine an adjustment to at least one of the proportional, integral, or derivative gains. The tuning controller may adjust the gains of the variable-gain PID controller in accordance with the determined adjustment to the at least one of the proportional, integral, or derivative gains.

In order to improve the consistency of molded products as viscosity shifts throughout a run, a controller of an injection molding machine executes a calibration cycle in accordance with a mold cycle. The controller analyzes a plurality of sensed melt pressure values during the calibration cycle to determine one or more calibration metrics. The controller then uses the calibration metrics when executing each mold cycle of the run. More particularly, during each mold cycle of the run, the controller detects a plurality of sensed melt pressures prior to and during a fill phase of the mold cycle and compares the plurality of sensed melt pressures to the one or more calibration metrics to predict cavity pressure for a pack and hold phase of the mold cycle. The controller then adjusts a set point pressure for the pack and hold phase based on the predicted cavity pressure.

A method for operating an injection-molding machine, including the steps: a) in a current injection-molding cycle, after an accepted-part reference injection-molding cycle learned in a learning phase: detecting a compound pressure change k.sub.1 relative to an accepted-part reference compound pressure p.sub.masse, ref during at least part of an injection phase of the current injection-molding cycle by measuring a current compound pressure p.sub.masse, act and comparing the current compound pressure p with the accepted-part reference compound pressure p.sub.masse, ref, b) determining a target mold internal pressure curve p.sub.wkz,soll (1) for a holding-pressure phase of the current injection-molding cycle, wherein for this purpose a mold internal pressure curve p.sub.wkz,ref (t) of the accepted-part reference injection-molding cycle is adjusted at least in dependence on the compound pressure change k.sub.1 detected in step a), and c) traveling the holding-pressure curve p.sub.masse, Hld, act (t) of the current injection-molding cycle in such a way that an actual mold internal pressure curve pwkz,act (0 of the current injection-molding cycle runs at least more closely along the target mold internal pressure curve p.sub.wkz,soll (t) than a mold internal pressure curve p.sub.wkz,ref(t) that is unchanged in comparison with the accepted-part reference cycle.

The present invention discloses a model-free optimization method of process parameters of injection molding to solve the problems of frequent tests required and performing adaptive adjustment on different parameters in the existing optimization method. The method need not build a surrogate model between a product quality index and a process parameter to render the process parameter to converge nearby the optimal solution by an on-line iteration method. The present invention calculates the gradient direction of a current point by an iterative gradient estimation method, and uses adaptive moment estimation algorithm to allocate an adaptive step for each parameter. The method can significantly reduce the cost and time required in the process parameter, which greatly helps improving the optimization efficiency of process parameters of injection molding.

There are provided a molding conditions determination assist device and a resin state estimation device including: a quality estimation unit which estimates quality of the mold products by a machine learning on the basis of a detection data; a quality transition storage unit which accumulates the estimated quality of the mold products and stores a quality transition with respect to the accumulated quality of the mold products; a tendency evaluation unit which evaluates a quality change tendency with respect to a prescribed standard quality on the basis of the quality transition; a relationship storage unit which stores a relationship between the quality change tendency and a modification amount of the molding conditions for returning the quality to the standard quality; and a modification conditions determination unit which determines the modification amount of the molding conditions on the basis of the quality change tendency and the relationship.

In order to improve the consistency of molded products as viscosity shifts throughout a run, a controller of an injection molding machine executes a calibration cycle in accordance with a mold cycle. The controller analyzes a plurality of sensed melt pressure values during the calibration cycle to determine one or more calibration metrics. The controller then uses the calibration metrics when executing each mold cycle of the run. More particularly, during each mold cycle of the run, the controller detects a plurality of sensed melt pressures prior to and during a fill phase of the mold cycle and compares the plurality of sensed melt pressures to the one or more calibration metrics to predict cavity pressure for a pack and hold phase of the mold cycle. The controller then adjusts a set point pressure for the pack and hold phase based on the predicted cavity pressure.

A method for operating a device to produce a product includes capturing at least one quality data record that includes measured values of one or more quality parameters that each correspond to one property of the product. The method captures at least one associated machine data record including actual values of several adjustable machine parameters of the device, chronologically assigns the quality data record to the machine data record, and generates a first data record comprising chronologically-correlated measured values and actual values. The preceding steps are repeated at least once to generate at least one second data record. A correlation is determined between the quality parameter(s) and the machine parameter(s). The method provides a corresponding target value for at least one of the adjustable machine parameters on the basis of the control model, proceeding from a target value of the quality parameter(s).

A state determination device acquires data on an industrial machine, extracts data used for processing related to machine learning from the acquired data, out of the acquired data, according to an extraction condition for extracting the data, and executes the processing related to the machine learning using the extracted data.