A method of estimation on a curve of a relevant point for detecting an anomaly of a motor. The method includes selecting a profile including a binary code, each component of which codes a direction of variation between two consecutive characteristic points of at least one learning curve, a model making it possible to estimate a relevant point based on a set of characteristic points of a curve and a filter. The method also includes applying the filter of the profile selected to the curve, determining a set of characteristic points of the filtered curve and of a binary code, comparing the determined code and the code of the profile selected, and estimating, as a function of the comparison, the relevant point on the curve based on the characteristic points of the filtered curve and the model of the profile selected.

A method for monitoring an actuator in a physical system, including: providing a computer model that describes the actuator, the behavior of the actuator being represented by a computer model function and by one or more parameters of the computer model function; determining or adapting the values of the parameters of the computer model with the aid of one or more particular system quantities; determining an error when a specified error condition is fulfilled, the error condition defining when at least one of the parameters, and/or at least one quantity determined from a plurality of the parameters, lies outside a corresponding specified target deviation range for the relevant parameter or the relevant quantity.

Systems and methods for monitoring an operational system. An initial set of sensor data is accumulated from a system over a substantially shorter time than is required to collect data to characterize a regression model for an operating parameter of the system. An initial regression model is created based on the initial set of sensor data. A subsequent set of sensor data is received from the at least one sensor after creating the initial regression model. An expected dependent value for the subsequent independent value is determined using the initial regression model. An operator is prompted to update the initial regression model based on a difference between a subsequent dependent value and the expected dependent value. The initial regression model is updated to incorporate the subsequent set of sensor data. A notification is provided based on a difference between presently received sensor data and the updated regression model.

A method and system for localizing faults in an industrial process is proposed. The industrial process includes a plurality of components. The method includes receiving structural plant data from an industrial plant. A structured model of the process is generated from the structural plant data. Sensor data measuring characteristics of the plurality of components is also received. Parameters of the structured model are identified from the received sensor data and stored. Faults are detected during operation of the industrial plant utilizing the identified parameters and detecting changes in the parameters by comparing current parameters to stored parameters. The fault information is then displayed via a display to an operator.

An apparatus and method for predicting distress on a physical component. The method can include obtaining distress data. The distress data can be used to determine a distress rank. The distress rank can be compared to a distress output provided by a kernel that use parameters related to the physical component. The comparison can result in a prediction model for the physical component.

A smart exception handler system for safety-critical real-time systems is provided. The system is configured to: receive a plurality of parameters at a plurality of nodal points in a real-time execution path; analyze the received parameters using a trained exception handling model, wherein the trained exception handling model has been trained using machine learning techniques to learn the critical path of execution and/or critical range of parameters at critical nodes, wherein the critical range of parameters comprises a learned threshold at a node; compute, using the trained exception handling model, a probability of fault at the critical nodes; compare the probability of fault at a critical node against a learned threshold at the node; and take proactive action in real-time to avoid the occurrence of a fault when the probability of fault at the node is higher than the learned threshold at the node.

According to one embodiment, a computer-implemented method for prognostic for flow sensor is provided. The method includes receiving a first input, the first input related to an input power of a motor for driving a compressor, and receiving a second input, the second input related to a temperature differential of the compressor. The method also includes calculating an estimated airflow based on the first input and the second input, and exporting data associated with the first input, the second input, and the estimated airflow.

Disclosed is a method for improving the measuring performance of automation field devices, wherein each of the field devices determines a process variable using a measuring algorithm and is exposed to measurable environmental influences. The method includes capturing the calibration data of the field devices and capturing an item of environmental information of the field devices at defined time intervals; storing the environmental information, the calibration data, and a time stamp in a database; selecting a group of field devices which determine a process variable using the same measuring algorithm and which are exposed to the same environmental influences; correlating the environmental information and calibration data captured over time; creating a mathematical model relating the calibration data and the environmental information; adapting the measuring algorithm on the basis of the model; and transmitting the adapted measuring algorithm to all field devices in the group.

Disclosed are devices, systems and methods for the operational testing on autonomous vehicles. One exemplary method includes configuring a primary vehicular model with an algorithm, calculating one or more trajectories for each of one or more secondary vehicular models that exclude the algorithm, configuring the one or more secondary vehicular models with a corresponding trajectory of the one or more trajectories, generating an updated algorithm based on running a simulation of the primary vehicular model interacting with the one or more secondary vehicular models that conform to the corresponding trajectory in the simulation, and integrating the updated algorithm into an algorithmic unit of the autonomous vehicle.

Example implementations described herein involve a new data-driven analytical redundancy relationship (ARR) generation for fault detection and isolation. The proposed solution uses historical data during normal operation to extract the data-driven ARRs among sensor measurements, and then uses them for fault detection and isolation. The proposed solution thereby does not need to rely on the system model, can detect and isolate more faults than traditional data-driven methods, can work when the system is not fully observable, and does not rely on a vast amount of historical fault data, which can save on memory storage or database storage. The proposed solution can thereby be practical in many real cases where there are data limitations.