A method of generating training spectra for training of a neural network includes measuring a first plurality of training spectra from one or more sample substrates, measuring a characterizing value for each training spectra of the plurality of training spectra to generate a plurality of characterizing values with each training spectrum having an associated characterizing value, measuring a plurality of dummy spectra during processing of one or more dummy substrates, and generating a second plurality of training spectra by combining the first plurality of training spectra and the plurality of dummy spectra, there being a greater number of spectra in the second plurality of training spectra than in the first plurality of training spectra. Each training spectrum of the second plurality of training spectra having an associated characterizing value.

A cover for an automated robot includes elastic sheets that are adhered to each other in a geometry. The geometry is configured to allow the elastic sheets to expand and contract while the automated robot moves within its range of motion. The elastic sheets are attached to the automated robot by elasticity of the elastic sheets. A first group of the elastic sheets forms an elastic collar configured to grip the automated robot at a distal end and a proximal end of the cover in a non-breakable manner such that during operation of the robot, the elastic sheets hold their elasticity and integrity without breaking.

Example embodiments of the present disclosure provide for an example method for controlling the activity of a production facility, such as a production facility having one or more automation environments. The example method includes receiving data indicative of a current production environment. The data can include data of a sensor representing a time since last unit or fill level at one or more processing stations in a production facility. The example method can include determining an impact probability of a downtime event based at least in part on data indicative of the current production environment. The example method can include determining the impact probability of a downtime event and performing a control action associated with the production facility in response to determining the impact probability of the downtime event.

A method determines state information relating to a belt grinder. The belt grinder has at least one abrasive belt for grinding a workpiece. The method includes providing measurement data relating to the belt grinder, and determining the state information from the measurement data using a machine learning system. The machine learning system is configured to determine the state information based on the provided measurement data.

A machine learning device, which detects an operator, communicates with a database registering information concerning the operator, and learns display of an operation menu based on the information concerning the operator, includes a state observation unit which observes an operation history of the operation menu; and a learning unit which learns the display of the operation menu on the basis of the operation history of the operation menu observed by the state observation unit.

An artificial intelligence server for controlling a plurality of robots using artificial intelligence includes a communication unit configured to receive a captured image of each of a plurality of zones and a processor configured to acquire situation information of each zone based on the received image, acquire degrees of guidance urgency respectively corresponding to the plurality of zones based on the acquired situation information of each zone, determine whether there is a degree of guidance urgency greater than a predetermined value in the acquired degrees of guidance urgency, and, when there is a degree of guidance urgency greater than the predetermined value, transmit a first control command for moving one or more robots to a zone corresponding to the degree of guidance urgency.

A method for automatically determining an optimized process configuration of a process for manufacturing or processing products that can be executed using a technical system and can be configured using a number of different process configuration parameters comprises: determining a process configuration of the process that is optimized with regard to a defined metric and is defined by respective target values of process configuration parameters using an optimization method that is adapted to the process and is at least partially based on machine learning, using input data that include production data and features that are given by historical process configuration data and status data of the system or process or are derived therefrom; and outputting target process configuration data representing the determined optimized process configuration by means of the target values of the process configuration parameters.

One or more first parameters associated with an electronic device manufacturing process are monitored. An artificial neural network associated with the one or more first parameters is determined. One or more second parameters are determined using the artificial neural network. The one or more first parameters are adjusted using the one or more second parameters.

Techniques are presented for the application of neural networks to the fabrication of integrated circuits and electronic devices, where example are given for the fabrication of non-volatile memory circuits and the mounting of circuit components on the printed circuit board of a solid state drive (SSD). The techniques include the generation of high precision masks suitable for analyzing electron microscope images of feature of integrated circuits and of handling the training of the neural network when the available training data set is sparse through use of a generative adversary network (GAN).

A method for configuring a semiconductor manufacturing process, the method including: providing an initial prediction model including a plurality of model parameters to one or more remote locations; receiving at least one updated model parameter from the one or more remote locations, the at least one model parameter is updated by training the initial prediction model with local data at the one or more remote locations; determining aggregated model parameters based on the at least one updated model parameter received from the one or more remote locations; and adjusting the initial prediction model based on the aggregated model parameters, the adjusted prediction model being operable to configure the semiconductor manufacturing process.