A system that allows a contractor to remotely monitor and/or interact with its customers' building control systems, such as heating, ventilating and air conditioning (HVAC) systems, and analyze information obtained from the building control systems over time. Such a system may help the contractor monitor and diagnosis customer building control systems, setup service calls, achieve better customer relations, create more effective marketing opportunities, as well as other functions. In some cases, the disclosed system may help a contractor pro-actively identify possible issues with its customer's building control systems. A controller of the system may populate a display screen on a remote device to display a summary display screen with selectable features for obtaining detailed information related to the selected feature. The summary display screen may display a summary of business performance data, customer performance data, and/or HVAC performance data associated with a set of log-in credentials.

A self-aware machine platform is implemented through analyzing operational data of machining tools to achieve machine tool damage assessment, prediction and planning in manufacturing shop floor. Machining processes are first identified by matching similar processes through an ICP algorithm. Machining processes are further clustered by Hotelling's T-squared statistics. Degradation of the machining tool is detected through a trend of the operational data within a cluster of machining processes by a monotonicity test, and the remaining useful life of the machining tool is predicted through a particle filter by extrapolating the trend under a first-order Markov process. In addition, process anomalies across machines are detected through a combination of outlier detection methods including SOMs, multivariate regression, and robust Mahalanobis distance. Warnings and recommendations are flexibly provided to manufacturing shop floor based on policy choice.

A data processing apparatus includes an acquisition circuit that acquires time-series data comprising a plurality of values observed in a plurality of channels at a plurality of points in time; a change trend calculation circuit that calculates a change trend of the observed values at each of the points in time on a channel-by-channel basis; a memory that stores a plurality of judgment tables each indicating a change trend of previous values at each of the points in time within a predetermined time period up to the current point in time; a comparison circuit that compares change trend data comprising a set of change trends of the observed values for each of the channels within the predetermined time period with the judgment tables; and a notification output circuit that outputs a notification related to a temporal change in the observed values on the basis of a result of the comparison.

Herein provided are methods and systems for detecting failure of a sensor in a control system for a gas turbine engine. A signal is received from the sensor. A high-pass filter is applied to the signal to produce a high-frequency component signal. A rate of occurrence of signal spikes in the high-frequency component signal is determined. The high-frequency component signal is compared to a component signal threshold which is based on at least one known healthy component signal and at least one faulty component signal. The presence of intermittent open circuits caused by the sensor is detected based on the comparing and on the rate of occurrence of signal spikes.

A data processing device according to one aspect of the present invention includes an extractor configured to extract time-series data indicating observed values at points in time in an analysis range from a first point in time to a second point in time, and a first calculator configured to calculate a gradient of a linear function indicating a trend of change in the observed values in the analysis range to minimize an objective function. The objective function indicates a sum of multiplication values at the points in time within the analysis range, the multiplication value is a numerical value obtained by multiplying a square of a difference between a function value of the linear function and the observed value by a weighting coefficient, and the weighting coefficient is a numerical value that increases as an elapsed time from the first point in time to each point in time increases.

A machine learning apparatus which learns the predicted life of a NAND flash memory provided in a numerical control device includes a state observation unit which observes state variables obtained based on at least one of the rewrite count, the rewrite interval, the read count, the temperature in the use environment, the error rate, information concerning the manufacturer, and information concerning the manufacturing lot for the NAND flash memory, and information concerning the ECC (Error Correction Coding) performance, information concerning the manufacturer, and information concerning the manufacturing lot for a memory controller which performs ECC processing for the NAND flash memory, and a learning unit which learns the predicted life of the NAND flash memory based on teacher data, and training data generated from the output of the state observation unit and data associated with the life of the NAND flash memory.

Embodiments of the disclosure can relate to predicting valve performance in power plants. In one embodiment, a method for predicting valve performance in power plants can include receiving at least one signal from a valve associated with a power plant. The method may further include receiving operational data from one or more power plants. The method may further include determining a confidence value associated with operation of the valve, based at least in part on the at least one signal from the valve and the operational data from one or more power plants. The method can further include comparing the confidence value to a threshold level, and comparing a time during which the confidence value persists to a threshold duration. When the confidence value exceeds the threshold level, and when the time exceeds the threshold duration, the method may include generating an alert for a probability of misoperation of the valve. The method may further include identifying a repair or replacement recommendation for the valve.

To provide a numerical controller and a machine learning device that predict an abnormality, based on machine learning with perception of temporal change in data. The numerical controller includes the machine learning device provided with a learning unit that conducts machine learning of trends in operation of a machine on occasions of occurrence of abnormalities in the machine, based on time-series data acquired by a data logger device and relating to the operation of the machine and abnormality information relating to the abnormalities which have occurred in the machine and a prediction unit that predicts an abnormality which will occur in the machine, based on results of the machine learning in the learning unit and time-series data acquired by the data logger device and relating to current operation of the machine.

A system that allows a contractor to remotely monitor and/or interact with its customers' building control systems, such as heating, ventilating and air conditioning (HVAC) systems, and analyze information obtained from the building control systems over time. Such a system may help the contractor monitor and diagnosis customer building control systems, setup service calls, achieve better customer relations, create more effective marketing opportunities, as well as other functions. In some cases, the disclosed system may help a contractor pro-actively identify possible issues with its customer's building control systems, and only then schedule maintenance as required. In some cases, based on the analysis of information obtained from the building control systems over time, the system may output indications of abnormalities in the operation of the building control systems from which information may be received.

Herein provided are methods and systems for detecting failure of a sensor in a control system for a gas turbine engine. A filtered signal is received from the sensor. A high-pass filter is applied to the filtered signal to produce a high-frequency component signal. A rate of occurrence of signal spikes in the high-frequency component signal is determined. The high-frequency component signal is compared to a component signal threshold based on at least one known healthy component signal and at least one faulty component signal, wherein the faulty component signal is based on a known faulty signal caused by intermittent open circuits. The presence of intermittent open circuits caused by the sensor is detected based on the comparing and on the rate of occurrence of signal spikes.