A method for controlling the filling of at least one cavity in a device for producing an object, in particular in an injection molding machine, wherein a melt is inserted into the cavity through an opening, and the width thereof is altered, wherein the width of the opening is also to be changed and adjusted, that is, fixed, in a position between a closed position and a maximal open position.

A production machine in the plastics processing industry includes multiple cavities and multiple piezoelectric pressure transducers. At least one piezoelectric pressure transducer is arranged at each cavity and captures an internal tool pressure inside the cavity and returns an electrical charge signal for each internal tool pressure detected. A cabling interface conducts the electrical charge signal away from piezoelectric pressure transducer via an inner cable. Each of the inner cables can be connected electrically to the cabling interface via at least two different connection standards.

A foaming process and a method for operation of the foaming process are provided. The method includes flowing a molten polymeric material into a mold from an upstream device, receiving the molten polymeric material in a cavity of the mold, and maintaining a repeatable, uniform pressure profile as the molten polymeric material is delivered into the mold.

A method for monitoring a cyclic manufacturing process in which at least one piece good is manufactured in each cycle includes in a first process step for at least one cycle, at least one temporal sequence of sensor data of the manufacturing process, wherein the sensor data are in an effective relationship with a stability and an anomaly of the manufacturing process. In a second process step, the sensor data are marked as stable sensor data once the manufacturing process is determined to attain stability. In a third process step, the stable sensor data are reduced dimensionally to point data. In a fourth process step, a density distribution of the point data is formed with at least one stability area of the point data and at least one anomaly area of the point data that corresponds to an anomaly of the manufacturing process.

A molding device for producing a molded module. The molding device has one tool part and one further tool part, which together enclose a cavity. At least one of the tool parts has at least one dividing web arranged and configured to subdivide the cavity into at least a low-pressure sub-cavity and a high-pressure sub-cavity. The tool part has at least two feed channels, of which a low-pressure feed channel opens into the low-pressure sub-cavity and has a smaller cross-section at least over a longitudinal portion than a high-pressure feed channel opening into the high-pressure sub-cavity. The low-pressure feed channel is configured to become pressure-resistantly blocked through hardening of the molding compound once a predetermined time interval has elapsed or during the interval. The high-pressure feed channel is configured to conduct a molding pressure into the cavity for a longer time interval than the low-pressure feed channel.

A method and device is provided for operating an injection molding machine. The method uses the device, which is configured for determining the viscosity index of a melt in a cavity of an injection molding tool. The device includes pressure sensor member that measures an internal mold pressure of the melt in the cavity. The device includes an evaluation member configured for evaluating sensor data generated by the pressure sensor member. The evaluation member is configured to determine the viscosity index of the melt from the evaluated sensor data. The evaluation member is configured to compare the viscosity index to a target viscosity index and accordingly adjust operation of the machine's operating parameters so that the viscosity index of the melt conforms to the target viscosity index indicative of production of an acceptable part by the injection molding machine.

An injection molding machine includes a plasticizing unit having a plasticizing cylinder and a material-conveying device that is movable in the plasticizing cylinder and powered by a material-conveying drive, a material-conveying drive control, which is coupled with the material-conveying drive and is designed to control operating parameters of the material-conveying drive, a closing unit having an injection molding tool that is connected with an outlet nozzle of the plasticizing cylinder, as well as a closing unit control, which is coupled with a closing unit drive of the closing unit and is designed to control operating parameters of the closing unit drive. The injection molding machine further includes one or more dieletric or acoustic sensors which are disposed in the cavity of the injection molding tool or close to the cavity of the injection molding tool and are designed to determine the dielectric polarizability, mobility of free load carriers and/or acoustic material responses of a molding material in the cavity of the injection molding tool. A sensor control is coupled with the dielectric or acoustic sensor(s) and is designed to ascertain a time-dependent degree of crystallization and a time-dependent median temperature of the molding material in the cavity of the injection molding tool from the dielectric polarizability, mobility of free load carriers and/or acoustic material responses determined by the dielectric sensor(s) and, depending on the ascertained degree of crystallization and the ascertained median temperature, to actuate the material-conveying drive control and/or the closing unit control to adjust the operating parameters of the material-conveying drive and/or of the closing unit drive.

The present invention provides a method for predicting multiple qualities of finished products using feature encoding with machine learning, applicable for monitoring the manufacturing process in a production equipment. The method includes an experimental step, a data preprocessing step, a feature learning step, and a model calibration step. In experimental step, the production equipment produces a finished product under at least one process condition and obtains a detection data stream. In data preprocessing step, an autoencoder encodes the detection data stream to obtain a feature data stream, from which a quality index can be calculated. In feature learning step, a prediction module learns from the feature data stream and the quality index. In model calibration step, the prediction module is trained to learn the quality of the finished product to enhance the accuracy of the predictions made by the prediction module.