In some implementations, a control system may obtain historical data associated with usage of a distillation column during a historical time period. The control system may configure a prediction model to monitor the distillation column for a hazardous condition. The prediction model may be trained based on training data that is associated with occurrences of the hazardous condition. The control system may monitor, using the prediction model, the distillation column to determine a probability that the distillation column experiences the hazardous condition within a threshold time period. The prediction model may be configured to determine the probability based on measurements from a set of sensors of the distillation column. The control system may perform, based on the probability satisfying a probability threshold, an action associated with the distillation column to reduce a likelihood that the distillation column experiences the hazardous condition within the threshold time period.

The subject application relates to monitoring of drive by wire sensors in vehicles. Systems, methods and apparatuses of predictive maintenance of drive by wire systems of vehicles are provided. For example, a data storage device is configured in a vehicle to receive and store sensor data from at least one drive by wire system of the vehicle. During a period in which the vehicle is assumed to be operating normally, the sensor data stored in the data storage device is used to train an artificial neural network to recognize the normal patterns in the sensor data. Subsequently, using the trained artificial neural network, the data storage device determines whether operations of the at least one drive by wire system are abnormal based on the sensor data. A maintenance alert can be generated for the vehicle in response to a determination that the operations of the at least one drive by wire system are abnormal according to the artificial neural network.

A method of monitoring one or more manufacturing components includes clustering vibration data associated with the one or more manufacturing components to generate a plurality of clusters, determining a vibration characteristic of the one or more manufacturing components based on the plurality of clusters, comparing auxiliary data associated with the one or more manufacturing components and an auxiliary data prediction model associated with the one or more manufacturing components, and determining an auxiliary characteristic of the one or more manufacturing components based on a comparison of the auxiliary data associated and the auxiliary data prediction model. The method includes determining a state of the one or more manufacturing components based on the vibration characteristic and the auxiliary characteristic and broadcasting a notification based on the state.

The present invention relates to non-thermal renewable energy turbines (20,24,34, 38,40), in particular to the monitoring of turbine performance to identify a loss of performance indicative of faults or component degradation. The method involves comparison of measured power from a target turbine (20) with a predicted value for same turbine. The predicted value is calculated using the output from a plurality of other turbines (24,34,38,40) from an array and a predictive model including weightings for the other turbines (24, 34,38,40) based on the strength of correlation of their historical with historical data from the target turbine (20).

A machine learning apparatus that learns an alarm factor in a motor drive device includes a state observation unit that obtains a feature amount as a state variable from the motor drive device and an alarm factor as label data, the alarm factor corresponding to the feature amount, and a learning unit that generates a learning model for inferring a new alarm factor corresponding to a new feature amount, from a dataset created on a basis of a combination of the state variable and the label data. The feature amount includes at least one of a detected current value detected from the motor, a speed command value specifying a rotational speed of the motor, an output voltage value output to the motor, an estimated speed value of the motor, and a detected speed value of the motor.

Provided are an abnormality detection system and an abnormality detection method capable of performing more stable abnormality detection. An abnormality detection system that detects an abnormality of the target machine by a computer includes a communication unit configured to acquire first data from a first sensor attached to the target machine and second data from a second sensor attached to the target machine, an arithmetic unit, and a memory unit. The arithmetic unit includes an encoding unit trained to generate latent expressions including a predetermined latent expression that estimates the second data on the basis of the first data, a decoding unit trained to restore the first data from the latent expressions, and an abnormality detection unit configured to detect the abnormality of the target machine on the basis of a restoration error between the first data and the first data restored by the decoding unit.

Methods and apparatus for determining a subset of a plurality of relationships between a plurality of parameters describing operation of a lithographic apparatus, the method comprising: determining a first set of data describing first relationships between a plurality of parameters of a reference apparatus; based on one or more measurements, determining a second set of data describing second relationships between the plurality of parameters of the reference or a further apparatus; comparing the first set of data and the second set of data; and selecting from the second set of data a subset of the second relationships based on differences between the first set of data and the second set of data.

An abnormality determination system includes a state quantity obtaining circuit and an abnormality determination circuit. The state quantity obtaining circuit is configured to obtain a state quantity associated with a mechanical system. The abnormality determination circuit is configured to, according to a learning content obtained in a machine learning process and based on the state quantity, determine as to at least one of an occurrence of an abnormality in the mechanical system, an occurrence position of the abnormality, and a cause of the abnormality.

A failure detection system detects a failure of a sensor that detects a state of a semiconductor manufacturing apparatus. The failure detection system includes a generation unit configured to generate times-series data of information on a detection value of the sensor during a determination period, a calculation unit configured to calculate a regression line of the times-series data, and a failure determination unit configured to determine whether the sensor has failed based on a slope of the regression line.

The present invention is directed to a device capable of implementing a machine learning algorithm to identify states of operation, performance, and health of a piece of machinery based on vibration and sound patterns. The present invention features a small electronic device consisting of one or more sensors with a computing device, that collects patterns of vibration and/or acoustic measurement from machinery to generate one or more representative signals. The device uses a simple algorithm to characterize the representative signals, and uses a simple algorithm to compare future signals to the characterized signals.