A building management system includes connected equipment configured to measure a plurality of monitored variables and a predictive diagnostics system configured to receive the monitored variables from the connected equipment; generate a probability distribution of the plurality of monitored variables; determine a boundary for the probability distribution using a supervised machine learning technique to separate normal conditions from faulty conditions indicated by the plurality of monitored variables; separate the faulty conditions into sub-patterns using an unsupervised machine learning technique to generate a fault prediction model, each sub-pattern corresponding with a fault, and each fault associated with a fault diagnosis; receive a current set of the monitored variables from the connected equipment; determine whether the current set of monitored variables correspond with one of the sub-patterns of the fault prediction model to facilitate predicting whether a corresponding fault will occur; and determining the fault diagnosis associated with the predicted fault.

Estimating Remaining Useful Life (RUL) from multi-sensor time series data is difficult through manual inspection. Current machine learning and data analytics methods, for RUL estimation require large number of failed instances for training, which are rarely available in practice, and these methods cannot use information from currently operational censored instances since their failure time is unknown. Embodiments of the present disclosure provide systems and methods for estimating RUL using time series data by implementing an LSTM-RNN based ordinal regression technique, wherein during training RUL value of failed instance(s) is encoded into a vector which is given as a target to the model. Unlike a failed instance, the exact RUL for a censored instance is unknown. For using the censored instances, target vectors are generated and the objective function is modified for training wherein the trained LSTM-RNN based ordinal regression is applied on an input test time series for RUL estimation.

Implementations described herein generally relate to a method for detecting anomalies in time-series traces received from sensors of manufacturing tools. A server feeds a set of training time-series traces to a neural network configured to derive a model of the training time-series traces that minimizes reconstruction error of the training time-series traces. The server extracts a set of input time-series traces from one or more sensors associated with one or more manufacturing tools configured to produce a silicon substrate. The server feeds the set of input time-series traces to the trained neural network to produce a set of output time series traces reconstructed based on the model. The server calculates a mean square error between a first input time series trace of the set of input time series traces and a corresponding first output time series trace of the set of output time-series traces. The server declares the sensor corresponding to the first input time-series trace as having an anomaly when the mean square error exceeds a pre-determined value.

Systems and methods described herein can involve management of a system having a plurality of sensors, the plurality of sensors observing a plurality of process steps, which can involve selecting a subset of the plurality of sensors for observation; executing anomaly detection from data provided from the subset of the plurality of sensors; for a detection of an anomaly from a sensor from the subset of sensors, selecting ones of the plurality of process steps based on the detected anomaly; estimating a probability of anomaly occurrence for the selected ones of the plurality of process steps; and for the estimated probability of anomaly occurrence meeting a predetermined criteria, selecting ones of the plurality of sensors associated with the selected ones of the plurality of process steps for observation.

A computer-implemented method for controlling and/or monitoring a production plant (110) is proposed. The production plant (110) comprises at least one process chain (112) comprising at least one batch process (114). The method comprises the following steps: a) at least one step of determining of input data (132), wherein the input data comprises at least one quality criterion and production plant layout data, wherein the step comprises retrieving the production plant layout data and receiving information relating to the quality criterion via at least one communication interface (158); b) at least one prediction step (134), wherein in the prediction step operating conditions for operating the production plant (110) are determined by applying at least one trained model (136) on the input data, wherein the trained model (136) is at least partially data-driven by being trained on sensor data from historical production runs; c) at least one control and/or monitoring step (140), wherein the operating conditions are provided.

An equipment state monitoring device includes: a feature amount extracting unit to extract a feature amount of operation data in which a state of equipment is measured; an operation pattern determining unit to determine whether an operation pattern of the equipment when the operation data is measured is a learned pattern in which a determination range of a state of the equipment is learned or an unlearned pattern; a feature amount correcting unit to correct the feature amount of the operation data corresponding to the operation pattern determined as the unlearned pattern to correspond to the learned pattern on a basis of a relationship between an operation pattern of the equipment and a feature amount of operation data; and an equipment state determining unit to determine a state of the equipment on a basis of the corrected feature amount and a determination range of a state of the equipment.

Provided are an abnormality diagnosis system and an abnormality diagnosis method that can prevent wrongly diagnosing equipment as having an abnormality when the equipment actually does not have an abnormality. An abnormality diagnosis system 20 comprises a sampler 21 and a calculator 24. The calculator 24 is configured to: perform first abnormality determination of whether there is an abnormality based on a result of first principal component analysis; in the case where a result of the first abnormality determination is that there is an abnormality, and perform second abnormality determination of whether there is an abnormality based on a result of second principal component analysis; and in the case where a result of the second abnormality determination is that there is an abnormality, diagnose the equipment as having an abnormality.

Disclosed is an apparatus for estimating disturbance flowing into a control system on the basis of input/output data. The apparatus includes an input unit, and an estimator configured to, when input data (u) is provided to the control system through the input unit and thus output data is acquired, estimate the input data (u) from the acquired output data, based on a system model matrix corresponding to an input/output relation model of the control system. Accordingly, efficiency of the apparatus may be improved.

Techniques are described for facilitating automation of a self-lifting forklift. According to one or more embodiments, a system is provided that can be located on or within a forklift. The system can comprise a lifting system that provides for vertically lifting or lowering the forklift, a power supply, a memory that stores computer readable and executable components, and a processor that executes the computer readable and executable components stored in the memory. The processor can be operably couple to: a plurality of sensors that sense conditions associated with the forklift, a context component that determines context of the forklift, an analysis component that analyzes information from the plurality of sensors and the context component, and a control component that controls the forklift based on an output from the analysis component, wherein the control includes automatically lifting or lowering of the forklift.

A system including an aircraft, and a computing system remote from the aircraft. The aircraft includes a sensor, an aircraft component associated with the sensor, a first transmitter, and a first receiver. The computing system includes a processor, a second transmitter, and a second receiver. The aircraft transmits sensor data sensed by the sensor to the computing system. The computing system is configured to process the received sensor data to generate status data indicative of an operational mode of the aircraft component, and to transmit, when the status data is indicative of an altered operational mode of the aircraft component, the status data to the aircraft via the second transmitter. The aircraft is configured to indicate, based at least partially on the status data received by the first receiver, the altered operational mode of the aircraft component.