The invention relates to a method for monitoring a milling process of a printed circuit board, having the steps of: (a) detecting (S1) the rotational speed of a milling head (2) of a milling machine (1) and at least one other operating parameter of the milling machine (1) during the milling process, wherein the other operating parameter is an electric supply current for operating the milling machine, and (b) analyzing (S2) the detected rotational speed and the detected operating parameter using a trained adaptive algorithm for detecting anomalies during the milling process.

A self-aware machine platform is implemented through analyzing operational data of machining tools to achieve machine tool damage assessment, prediction and planning in manufacturing shop floor. Machining processes are first identified by matching similar processes through an ICP algorithm. Machining processes are further clustered by Hotelling's T-squared statistics. Degradation of the machining tool is detected through a trend of the operational data within a cluster of machining processes by a monotonicity test, and the remaining useful life of the machining tool is predicted through a particle filter by extrapolating the trend under a first-order Markov process. In addition, process anomalies across machines are detected through a combination of outlier detection methods including SOMs, multivariate regression, and robust Mahalanobis distance. Warnings and recommendations are flexibly provided to manufacturing shop floor based on policy choice.

An actuator of a machine is controlled by a control device with a controller structure in a normal operating mode and a special operating mode. The control device determines from a position setpoint value and a position actual value a control signal for the actuator. In the normal operating mode, the setpoint values are determined using a utility program, and in the special operating mode by a system program that is different from the normal operating program. In the special operating mode, a frequency characteristic for the actuator is determined on the basis of the sequence of setpoint values and associated actual values, and an evaluation for the actuator and/or of the controller structure is performed using the frequency characteristic and parameters of the controller structure. Depending on the evaluation, a message is transmitted to an operator of the machine or to a computing device over a network.

A control apparatus includes a controller. The controller is configured to obtain a measurement value of a state of mechanical equipment corresponding to a period in which the mechanical equipment reaches a second state from a first state, extract at least one predetermined feature value by using the measurement value, and extract data for machine learning from data of the at least one predetermined feature value on a basis of a separation degree for distinguishing the first state and the second state from each other.

The invention relates to a container treatment machine for treating containers, in particular in the beverage-processing industry, medical technology, or the cosmetics industry, the container treatment machine comprising a control unit for controlling the function of the container treatment machine and at least one treatment unit for treating the containers; the container treatment machine is designed to treat the containers in exactly one way; the container treatment machine comprises at least one component which can output data relating to its operating state and/or the operating state of the container treatment machine to the control unit; and the control unit comprises a neural network which is configured and trained to use the data to determine whether a deviation of the operating state of the container treatment machine from a normal state is present and/or imminent.

A fault prediction system includes a machine learning device that learns conditions associated with a fault of an industrial machine. The machine learning device includes a state observation unit that, while the industrial machine is in operation or at rest, observes a state variable including, e.g., data output from a sensor, internal data of control software, or computational data obtained based on these data, a determination data obtaining unit that obtains determination data used to determine whether a fault has occurred in the industrial machine or the degree of fault, and a learning unit that learns the conditions associated with the fault of the industrial machine in accordance with a training data set generated based on a combination of the state variable and the determination data.

A system and a method for detecting tool status of a machine tool equipped with a controller and cutting tools are provided. The method includes the steps of: receiving a plurality of manufacturing signals; processing data from the manufacturing signals to organized information; selecting target features characterizing less noise, high effectiveness, and low multicollinearity from the organized information; fitting a classification model using tool status information with the organized information and the target features; obtaining tool status levels by using the classification model; and outputting tool treatments corresponding to the tool status levels.

Systems, methods, and apparatus for prediction of maintenance service for machines. In one example, one or more sensors are configured to generate a sensor data stream during operation of a machine. An artificial neural network (ANN) is configured to receive the sensor data stream and predict a maintenance service for the machine based on the sensor data stream. For example, the ANN can be trained using the sensor data stream collected within a predetermined time period of a machine being newly-installed in an assembly line or other industrial automation facility. The machine can be considered to be operating in a normal condition during the predetermined time period such that the ANN can be trained to detect anomaly that deviates from the normal patterns of the sensor data stream. For example, the ANN can be a spiking neural network (SNN).

A method for detecting a fault includes: receiving a plurality of time-series sensor data obtained in one or more manufacturing processes of an electronic device; arranging the plurality of time-series sensor data in a two-dimensional (2D) data array; providing the 2D data array to a convolutional neural network model; identifying a pattern in the 2D data array that correlates to a fault condition using the convolutional neural network model; providing a fault indicator of the fault condition in the one or more manufacturing processes of the electronic device; and determining that the electronic device includes a fault based on the fault indicator. The 2D data array has a dimension of an input data to the convolutional neural network model.

An aggregation layer subsystem, and method of operation thereof, for use with an architect subsystem and a plurality of edge processing devices in a distributed analytics system, wherein each edge processing device is adapted to monitor and control the operation of at least one monitored system according to a first analytic model, the aggregation layer subsystem comprising: a processor and memory, the memory containing instructions which, when executed by the processor, enables the aggregation layer subsystem to: receive a second analytic model from the architect subsystem, the second analytic model based on characteristics of at least one monitored system associated with at least one of the plurality of edge processing devices; receive monitored system information from each of the plurality of edge processing devices; and, provide control signals to the at least one monitored system, via one of the edge processing devices, according to the second analytic model in response to the monitored system information.