An asset management method for a substation generates a unique reliability model by each element of the substation by comparing reliability by a reference reliability model by each substation type with health index by the each element thereof generated based on state data and real-time monitoring data by the each element of the substation and compensating the reference reliability model by the each element of the substation; assessing system reliability index and economic feasibility by each maintenance scenario based on a reference system reliability model for each candidate element subject to maintenance among the elements of the substation; selecting a maintenance scenario as a result of the health index and the unique reliability model by the each element of the substation, the system reliability index, and the economic feasibility and updating the unique reliability model by the each element of the substation by executing maintenance.

An apparatus/method for extracting multiple features from time series data collected from a plurality of sensors and for performing transfer learning on them. There is provided an apparatus including: a multi-feature extraction unit for extracting multiple features from a data stream for each sensor inputted from the plurality of sensors; a transfer-learning model generation unit for extracting useful multi-feature information from a learning model which has finished pre-learning, for the multiple features for forwarding the extracted multi-feature information to a multi-feature learning unit to generate a learning model that performs transfer learning on the multiple features; and the multi-feature learning unit for receiving learning variables from the learning model for each of the multiple features and for performing parallel learning for the multiple features, to calculate and output a loss. In addition, there is provided an apparatus for detecting leaks in plant pipelines.

An apparatus can include a fan including a control pin. The fan may receive a pulse width modulated (PWM) signal at the control pin. The fan may further control a speed of the fan based on a duty cycle of the PWM signal when the PWM signal is in a first range and, responsive to the duty cycle of the PWM signal being in a second range, transmit information corresponding to the fan to an external controller.

An abnormality detection method of an encoder includes an output step, a control step, an information acquisition step, and an abnormality determination step. The abnormality determination step compares command position information with detection position information of a motor calculated based on an output signal, and determines that the encoder is abnormal in a case where a difference between the command position information and the detection position information of the motor is equal to or more than a predetermined value.

Systems and methods are provided for detecting anomaly precursor events. The methods include organizing time series data into an input data structure that maintains an association between instances identified in the time series data and respective sensors. Additionally, the methods include calculating an instance attention value for each instance of at least one instance; calculating a sensor attention value for each sensor of the respective sensors; and identifying correlations between multiple sensors of the respective sensors based on the instance attention value and sensor attention value to identify a precursor event candidate based on a relationship between the instances and the respective sensors. Also, the method includes identifying an impending anomaly candidate from a database of historical anomalies based on the precursor event candidate. Further, the method includes generating an alert indicating an impending anomaly event identifying a type of impending anomaly event based on the database of historical anomalies.

An electrical discharge machine includes: a machining power supply having a plurality of different circuit states, and configured to be capable of being set to one circuit state of the plurality of circuit states by switching at least one of electrical connection and electrical setting; a state determining unit configured to, when each of the plurality of circuit states is set as the circuit state of the machining power supply, determine whether or not the set circuit state is normal; a failure portion specifying unit configured to specify a failure portion of the machining power supply based on a determination result with respect to each of the plurality of circuit states obtained by the state determining unit; and a reporting unit (a display unit or the like) configured to report the failure portion specified by the failure portion specifying unit to an operator.

A diagnostic system is provided for diagnosing a process of a plant, using a computing device. A detection unit automatically detects a faulty condition of the process based on a plurality of readings of parameters or measurements associated with the faulty condition for alerting an operator. An analysis unit determines an operating status of the plant based on the plurality of readings of parameters or measurements. A display device graphically links the faulty condition with the plurality of readings of parameters or measurements. A visualization unit displays the operating status of the plant with the readings of parameters or measurements using an alert dashboard grouping related data based on a source of the data for meaningfully illustrating relationships of the displayed data. An alert unit automatically generates a warning message based on the plurality of readings of parameters or measurements to inform the operator of the faulty condition.

A product testing system and an auxiliary testing method are provided. The product testing system includes a computer and a test fixture. The computer has a machine learning model. The auxiliary testing method includes the following steps. Firstly, the test fixture tests the plural under-test products sequentially, and generates corresponding test data to the computer. Then, the computer generates plural trend line graphs corresponding to the test data. Then, the operator determines corresponding human judging results according to the trend line graphs. The test data, the trend line graphs and the human judging results are inputted into the machine learning model, and a learning process is performed. If the number of samples reaches a predetermined threshold value, the machine learning model generates auxiliary judging results according to the corresponding test data and the corresponding trend line graphs.

Apparatus, device, methods and system relating to a vehicular telemetry environment for the for identifying in real time unpredictable network communication faults based upon pre-processed raw telematics big data logs that may include GPS data and an indication of vehicle status data, and supplemental data that may further include location data and network data.

The present disclosure relates to a system and method for actively detecting an ingress of a medical probe. In accordance with certain embodiments, a method includes monitoring, with a sensor within a medical probe, an internal environment of the medical probe, detecting, with the sensor, at least one of a temperature, pressure, humidity, or concentration of a gas within the medical probe, determining, with a processor that is in communication with the sensor, whether a seal that hermetically seals the medical probe has failed as a function of at least one of the temperature, pressure, humidity, or concentration of the gas, and outputting, with the processor, a notification that indicates whether the seal has failed.