A method for diagnosing faults includes receiving a system description of a thermal hydraulic system, the system description indicating a plurality of components and sensors. The method also includes constructing, based on physical conservations laws and using the system description, a plurality of physics-based models for the plurality of components, each of the plurality of physics-based models including unknown parameters. The method further includes receiving historical measurements and calibrating the physics-based models by calculating the unknown parameters of each of the physics-based models using the historical measurements to produce calibrated models. The method also includes receiving sensor measurements of the sensors, and calculating residuals corresponding to differences between measurements predicted by the plurality of calibrated models and the sensor measurements. The method also includes determining, based on the calculated residuals, a fault of a component or a sensor, and generating an alert indicating the fault.

A method for diagnosing faults includes receiving a system description of a thermal hydraulic system, the system description indicating a plurality of components and sensors. The method also includes constructing, based on physical conservations laws and using the system description, a plurality of physics-based models for the plurality of components, each of the plurality of physics-based models including unknown parameters. The method further includes receiving historical measurements and calibrating the physics-based models by calculating the unknown parameters of each of the physics-based models using the historical measurements to produce calibrated models. The method also includes receiving sensor measurements of the sensors, and calculating residuals corresponding to differences between measurements predicted by the plurality of calibrated models and the sensor measurements. The method also includes determining, based on the calculated residuals, a fault of a component or a sensor, and generating an alert indicating the fault.

A method may include providing a first pulse width modulation (PWM) signal to a microcontroller unit (MCU) included at a cooling fan. The method may further include receiving information from the MCU identifying a duty cycle of a second PWM signal generated by the MCU, the duty cycle of the second PWM signal determined by the MCU based on a duty cycle of the first PWM signal and based on a tachometer signal received from a rotor included at the cooling fan. The present current consumption of the cooling fan may be determined based on the duty cycle of the second PWM signal.

A method may include providing a first pulse width modulation (PWM) signal to a microcontroller unit (MCU) included at a cooling fan. The method may further include receiving information from the MCU identifying a duty cycle of a second PWM signal generated by the MCU, the duty cycle of the second PWM signal determined by the MCU based on a duty cycle of the first PWM signal and based on a tachometer signal received from a rotor included at the cooling fan. The present current consumption of the cooling fan may be determined based on the duty cycle of the second PWM signal.

A method for predicting a remaining life of a tool of a computer numerical control machine is provided. In the method, indirect measurement indicators of the tool are selected based on monitoring and analyzing a current state of the tool, a prediction model for the remaining life of the tool is established based on data de-noising, feature extraction and a multi-kernel W-LSSVM algorithm. Thereby, a method for predicting a remaining life of a tool of a computer numerical control machine is provided.

A method for predicting a remaining life of a tool of a computer numerical control machine is provided. In the method, indirect measurement indicators of the tool are selected based on monitoring and analyzing a current state of the tool, a prediction model for the remaining life of the tool is established based on data de-noising, feature extraction and a multi-kernel W-LSSVM algorithm. Thereby, a method for predicting a remaining life of a tool of a computer numerical control machine is provided.

Systems and methods are presented for monitoring shipping containers. A system comprises a shipping container, a sensing component, and a transmission device. The shipping container defines an interior compartment. The sensing component is positioned within the interior compartment and comprises one or more sensors, a sensing component battery, a sensing component microcontroller, and a communication chip. The one or more sensors sense atmospheric data. The sensing component microcontroller has a memory and receives the atmospheric data sensed by the one or more sensors at a predetermined interval and stores the atmospheric data in the memory. The transmission device is external to the interior compartment and comprises a receiver and a transmitter. The receiver receives data transmitted by the sensing component. The transmitter transmits the received data to a storage location. The transmission device is paired with the sensing component or an interior component contained within the interior compartment.

A system may comprise a device. The device may be configured to receive, from one or more sensor devices of the machine, sensor data associated with wear of one or more components of an undercarriage of the machine; and predict, using a machine learning model and the sensor data, an amount wear of the one or more components based on a wear rate of the one or more components. The machine learning model is trained, using training data, to predict the wear rate of the one or more components. The training data includes two or more of: historical sensor data, historical inspection data, or simulation data, of a simulation model, from one or more third devices. The device may perform an action based on the amount of wear.

The present disclosure provides a method of multi-objective and multi-dimensional online joint monitoring for a nuclear turbine. The method includes: obtaining first temperature monitoring data of the nuclear turbine by performing online thermal monitoring on a rotor, a valve cage and a cylinder of the nuclear turbine under quick starting-up; obtaining second temperature monitoring data of tightness of a flange association plane of the cylinder of the nuclear turbine by performing online thermal monitoring on the tightness of the flange association plane; obtaining operation monitoring data of a shafting vibration of a rotor and bearing system of the nuclear turbine by performing online safety monitoring on the shafting vibration of the rotor and bearing system; and optimizing operation and maintenance control of the nuclear turbine according to at least one type of monitoring data among the first temperature monitoring data, the second temperature monitoring data and the operation monitoring data.

Techniques are described for testing whether an end effector, or component thereof, is correctly or incorrectly installed to a manipulation system. In an example, a manipulation system can include a manipulator arm configured to receive an end effector having a first moveable jaw, a transducer configured to provide first effort information of the end effector as the end effector moves, and a processor configured to provide a command signal to effect a first test move of the first moveable jaw, and to provide an installation status of the of the end effector using the first effort information of the first test move.