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.

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.

A method for predicting an operating anomaly comprises steps of (i) taking an assembly comprising at least a first and a second equipment item, each equipment item comprising a first operating parameter, (ii) recording and storing measurements over time of the first parameters for the first and the second equipment items, (iii) collecting the measurements during or after the completion of at least one part of an operating cycle, (iv) processing the collected measurements to detect a possible malfunction of the first and second equipment items by establishing a coefficient of determination, (v) emitting a first notification indicating the possible malfunction and/or triggering additional steps if the first coefficient of determination is less than a first threshold, and (vi) emitting a second notification and/or adjusting the first threshold if the first coefficient of determination is greater than or equal to the first threshold.

Environmental control system diagnostics and optimizations using intelligent lighting networks are provided. One or more intelligent lighting modules (ILMs) can be deployed in intelligent lighting fixtures, intelligent lighting zone controllers, and other intelligent lighting network devices to collect ambient environmental data (e.g., temperature, pressure, and humidity) in addition to occupancy and ambient light sensing used for lighting control. In this manner, embodiments of the present disclosure address diagnostics and improve performance of environmental control systems (e.g., heating ventilation and air conditioning (HVAC) systems) by offering a secondary set of sensors for HVAC systems at a lower cost than traditional approaches. In particular, the ILMs or other processing circuitry in communication with the ILMs analyze the collected ambient environmental data to diagnose the health and function of the environmental control system, and communicate the diagnoses to users and/or the HVAC system.

Real-time quality control of a culture for bioproduction is facilitated using machine learning. In this approach, real-time process data for a set of parameters for a current production run is received. Based on this process data, a prediction is made using an instance of a machine learning model that has been trained on process data from past production or development runs. The instance is uniquely associated to a particular culture day and thus independent of any other instance of the machine learning model (for other culture days). Based on the prediction, a quality control recommendation for the current production run is then made. Several different types of predictions are enabled, and various different recommendations are provided based on the predictions.

A method for automating system identification includes performing a system identification experiment, and performing a system identifying processing by fitting a model to data from the system identification experiment. The method also includes performing model reduction to generate a model numerically suitable for controller synthesis by removing inconsequential states that cause controller optimization methods to fail. The method further includes performing control synthesis using the generated model or reduced models, including disturbance spectrum estimates, to generate a candidate controller design to be used during system operation. The method also includes checking for controller robustness using the identified model to ensure stability of the system while maximizing closed-loop bandwidth and performance.

This disclosure relates generally to a method and system for real time monitoring and forecasting of fouling of an air preheater (APH) in a thermal power plant. The system is deploying a digital replica or digital twin that works in tandem with the real APH of the thermal power plant. The system receives real-time data from one or more sources and provides real-time soft sensing of intrinsic parameters as well as that of health, fouling related parameters of APH. The system is also configured to diagnose the current class of fouling regime and the reasons behind a specific class of fouling regime of the APH. The system is also configured to be used as advisory system that alerts and recommends corrective actions in terms of either APH parameters or parameters controlled through other equipment such as selective catalytic reduction or boiler or changes in operation or design.

A method is disclosed herein of detecting at least one frozen period in at least one sensor dataset associated with at least one sensor in a technical system. The method includes receiving the at least one sensor dataset in time series and computing run-lengths for the at least one sensor dataset, wherein each of the run-lengths is length of consecutive repetitions of a sensor value in the at least one sensor dataset. The method includes clustering the run-lengths into one of two clusters based on a run frequency, wherein the run frequency is a number of times the run-lengths are repeated in the at least one sensor dataset. Further, the method includes identifying a cluster from the two clusters with lower run frequency and detecting the at least one frozen period in the at least one sensor dataset based on the identified cluster.

A vehicle fault detection system including at least one sensor configured for coupling with a vehicle system, a vehicle control module coupled to the at least one sensor, and being configured to receive at least one time series of numerical sensor data from the at least one sensor, at least one of the at least one time series of numerical sensor data corresponds to a respective system parameter of the vehicle system being monitored, generate a graphical representation for the at least one time series of numerical sensor data to form an analysis image of at least one system parameter, and detect anomalous behavior of a component of the vehicle system based on the analysis image, and a user interface coupled to the vehicle control module, the user interface being configured to present to an operator an indication of the anomalous behavior for the component of the vehicle system.

The present invention discloses a method for detecting abnormity in an unsupervised industrial system based on deep transfer learning. Labeled machine sensor sequence data from a source domain and unlabeled sensor sequence data from a target domain are used in the present invention to train an industrial system abnormal detection model with good generalization ability, and the industrial system abnormal detection model is trained and tested to finally generate a trained industrial system abnormity discrimination model. Using the model, received machine sensor sequence data can be analyzed and whether a machine is abnormal is discriminated.