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.

A method, medium, and system to receive an indication of an assembly including a plurality of different components to produce by additive manufacturing (AM), determine based on a forward search process that starts with individual components of the plurality of components and iteratively adds other components of the plurality of components thereto in combinations until an entirety of the assembly is accounted for, determine based on a reverse search process that starts with the entirety of the assembly and iteratively removes components of the plurality of components therefrom in combinations until a two-component set is reached, automatically select an optimal combination of the plurality of components from the combinations determined by the forward search and reverse search processes; and transmit the selection of the optimal combination of the plurality of components to an AM controller.

A method, medium, and system to receive an indication of an assembly including a plurality of different components to produce by additive manufacturing (AM), determine based on a forward search process that starts with individual components of the plurality of components and iteratively adds other components of the plurality of components thereto in combinations until an entirety of the assembly is accounted for, determine based on a reverse search process that starts with the entirety of the assembly and iteratively removes components of the plurality of components therefrom in combinations until a two-component set is reached, automatically select an optimal combination of the plurality of components from the combinations determined by the forward search and reverse search processes; and transmit the selection of the optimal combination of the plurality of components to an AM controller.

A state determination device acquires data on an industrial machine, creates a plurality of pieces of partial time-series data obtained by sliding time-series data on physical quantities out of the data on the industrial machine in the direction of a time axis, based on the acquired data, extracts a plurality of pieces of data for learning including the plurality of pieces of partial time-series data, and performs machine learning using the extracted learning data, thereby generating a learning model.

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.

A manufacturing method of a mold, the mold having at its surface a plurality of recessed portions whose two-dimensional size is not less than 10 nm and less than 500 nm when viewed in a direction normal to the surface, the method comprising: (a) providing a mold base (10); (b) partially anodizing the aluminum alloy layer (18), thereby forming a porous alumina layer (14) which has a plurality of minute recessed portions (14p); (c) bringing the porous alumina layer into contact with an etching solution, thereby enlarging the plurality of minute recessed portions; (d) detecting a protrusion (210) formed at a surface of the porous alumina layer or the mold base; (e) determining whether or not a height of the detected protrusion is greater than a predetermined height; and (f) if it is determined at step (e) that the height of the protrusion is greater, irradiating the protrusion with laser light such that the height of the protrusion becomes smaller than the predetermined height.

A failure cause diagnostic device of the present invention receives input of internal and external state data on injection molding machines and diagnoses failure cause of the injection molding machines by means of a machine learning device. An internal parameter of the machine learning device is obtained by performing machine learning using the state data obtained from the injection molding machines subject to failure cause and the state data obtained from the injection molding machines free of failure cause.

A method comprises switching on a first radiation source of a plurality of radiation sources. The plurality of radiation sources are for delivering radiation towards a print area of a printing apparatus. Each of the plurality of radiation sources may be connected to control circuitry via one of a plurality of circuit terminals. The method may further comprise detecting, using a detector, a change resulting from radiation from the first radiation source. The method may further comprise determining, using a processor, based on the detected change, connection information indicative of the circuit terminal to which the first radiation source is connected.

The present invention is a method to start-up a process to make expandable vinyl aromatic polymer pellets comprising, a) providing a pelletizer (S) containing means to introduce the molten vinyl aromatic polymer comprising the expandable agent and optionally additives, a die plate having a plurality of holes of small diameter, typically in the range 0.8 to 1.6 mm and cutting means to make pellets, b) providing a pelletizer (L) containing means to introduce the molten vinyl aromatic polymer comprising the expandable agent and optionally additives, a die plate having a plurality of holes of large diameter, typically in the range 3 to 5 mm and cutting means to make pellets, c) sending the expandable vinyl aromatic polymer pellets comprising an expandable agent and optionally additives to the pelletizer (L) until the polymer flow rate is in the operating range of the pelletizer (S) and provided the proportion of expandable agent and optional additives are in the specifications, d) switching the molten vinyl aromatic polymer stream comprising the expandable agent and optionally additives to the pelletizer (S) and operating said pelletizer (S) at conditions effective to produce expandable vinyl aromatic polymer pellets, e) recovering from pelletizer (S) the expandable vinyl aromatic polymer pellets, f) recovering the pellets produced at step c) for optional subsequent recycling in the molten state at step d). In another embodiment while the pelletizer (S) is in production and troubles happen in the introduction of the expanding agent and/or the optional additives or in any equipment or even an equipment needs maintenance the production is switched from the pelletizer (S) to one or more pelletizers (L). When the troubles are over, the production is switched from the pelletizer (L) to the pelletizer (S). In an embodiment while the pelletizer (S) is in production the die plate of the pelletizer (L) having a plurality of holes of large diameter is removed and replaced by a die plate having a plurality of holes of small diameter to convert said pelletizer (L) into a pelletizer (S) capable to produce expandable vinyl aromatic polymer pellets. By way of example said established pelletizer (S) is used during maintenance of the other pelletizer (S).

A manufacturing method of a mold, the mold having at its surface a plurality of recessed portions whose two-dimensional size is not less than 10 nm and less than 500 nm when viewed in a direction normal to the surface, the method comprising: (a) providing a mold base (10); (b) partially anodizing the aluminum alloy layer (18), thereby forming a porous alumina layer (14) which has a plurality of minute recessed portions (14p); (c) bringing the porous alumina layer into contact with an etching solution, thereby enlarging the plurality of minute recessed portions; (d) detecting a protrusion (210) formed at a surface of the porous alumina layer or the mold base; (e) determining whether or not a height of the detected protrusion is greater than a predetermined height; and (f) if it is determined at step (e) that the height of the protrusion is greater, irradiating the protrusion with laser light such that the height of the protrusion becomes smaller than the predetermined height.