An objective of the present invention is to provide a system which can infer the cause of a recipe error and present a correction candidate for the recipe error. A recipe information presentation system or recipe error inference system according to the present invention: causes a learner to learn a correspondence between a recipe and an error originating from the recipe; and acquires from the learner an inference result as to whether the error occurs when a new recipe is used (refer to FIG. 1).

Systems and method are provided for detecting an anomaly of a sensor of a vehicle. In one embodiment, a method includes: storing a plurality of sensor correlation groups based on vehicle dynamics; processing a subset of signals based on the sensor correlation groups to determine when an anomaly exists; processing the subset of signals based on the sensor correlation group to determine which sensor of the sensor correlation group is anomalous; and generating notification data based on the sensor of the correlation group that is anomalous.

A computer implemented method for the maintenance optimization of a fleet or group of turbomachinery assets is disclosed. The method comprises the step of model training and setup, aiming at setting configurations parameters, that can be executed offline, and the step of online calculation on new input data, which is based on detected data and extracted statistical features. An anomaly identification and classification follow, thus calculating a risk assessment, for estimating the risk that an anomaly might cause any event that requires a maintenance task to be executed on one or more assets of the fleet.

A robotic fleet management platform includes a resources data store that maintains a fleet resource inventory indicating fleet resources that can be assigned to a robotic fleet and, for each fleet resource, maintenance history, predicted maintenance need, and a preventive maintenance schedule. The platform includes a maintenance management library of fleet resource maintenance requirements for determining maintenance workflows, service actions, and service parts for at least one fleet resource in the fleet resource inventory. The platform calculates predicted maintenance need of a fleet resource based on anticipated component wear and anticipated component failure of the at least one fleet resource according to machine learning-based analysis of the maintenance status data. The platform monitors a health state of the fleet resource based on sensor data. The platform initiates a service action of the at least one item of maintenance for the fleet resource based on the fleet resource maintenance requirements.

A distributed computing system for product defect analysis is disclosed. The distributed computing system for product defect analysis includes a computing cluster for processing product manufacturing messages, a computing cluster for identifying product defect, a product image database, and a client device.

A computer implemented method of administering a complex system includes receiving multivariate data from a plurality of sensors of the system in an ambient state. Event sequences in the received multivariate data are identified. The multivariate event sequences are projected to a lower stochastic latent embedding. A temporal structure of the sequences is learned in a lower latent space. A probabilistic prediction in the lower latent space is provided. The probabilistic prediction in the lower stochastic latent space is decoded to an event prediction in the ambient state.

A method for monitoring of industrial devices includes: receiving sensor signal data of one or more industrial devices and one or more events associated with the operation of the one or more industrial devices. The method further includes: identifying, (e.g., using a first autoencoder), an abnormal behavior of the one or more industrial devices based on the sensor signal data; creating or updating an additional autoencoder based on the sensor signal data associated with a time window relating to the abnormal behavior; and associating events located within the time window with the additional autoencoder.

A method for diagnostics and monitoring of anomalies in a cyber-physical system (CPS) includes obtaining information related to anomalies identified in the CPS. The obtained information includes at least one value of one or more CPS variables. One or more classifying features of the identified anomalies in the CPS are generated based on the obtained information. Classification of the identified anomalies in the CPS into two or more anomaly classes is performed based on the generated classifying features. Each of the two or more anomaly classes is associated with one or more anomaly characteristics. Diagnostics of anomalies are performed in each of the two or more anomaly classes by calculating values of the anomaly characteristics associated with each of the two or more anomaly classes. Anomalies of each of the two or more anomaly classes are monitored based on the calculated values of the anomaly characteristics associated with each of the two or more anomaly classes.

A system processes historical facility data that relate to facility states and modes of operation. The historical facility data are clustered into groups representing the facility states and the modes of operation. The groups are used to determine a current state and mode of the facility. When the facility is in a normal state, the system determines whether an event in the facility is an abnormality. If an abnormality is identified, the system transmits a signal indicating the abnormality.

A method and system for detecting and characterizing weak signals of risk exposure in an industrial system based on industrial system data collected over a given time period. The system is configured for implementing: a module (36) for computing a risk predictive signature, from collected data relating to the industrial system, using a first term obtained by summing elementary signatures associated with elementary initiating events, dependent on parameters comprising a severity value, a characteristic function and a weighting function of the elementary initiating event, at least a part of said parameters being determined by using a neural network, a module (38) for detecting the presence of a weak signal of risk exposure by comparing the computed risk predictive signature with predetermined reference risk signatures.