A fault state detection apparatus includes an input unit and a processing unit. The input unit receives condition monitoring data. The processing unit implements a trained machine learning algorithm to analyze the received condition monitoring data to determine if the received condition monitoring data is associated with a fault state. The trained machine learning algorithm was trained on the basis of a plurality of non-fault state condition monitoring data and associated ground truth information and on the basis of a plurality of fault state condition monitoring data and associated ground truth information. A subset of the plurality of fault state condition monitoring data was generated from one or more non-fault state condition monitoring data. Generation of fault state conditioning monitoring data in the subset of the plurality of fault state condition monitoring data comprises a transformation of non-fault state condition monitoring data to fault state condition monitoring data.

Disclosed is a hydrocyclone monitoring system. The hydrocyclone monitoring system comprises a hydrocyclone comprising a separation chamber having an inlet for feeding an input mixture into the separation chamber and first and second outlets for ejecting flows of 5 respective first and second components of the mixture from the separation chamber. The hydrocyclone monitoring system further comprises a conduit and a sensor assembly. The conduit is connected to the first outlet and defines a channel for conducting the flow of the first component ejected from the separation chamber. The sensor assembly is configured to detect characteristics of the flow of the first component in the channel. The hydrocyclone 10 monitoring system further comprises a processing system configured to receive from the sensor assembly measurement data indicative of the characteristics of the flow of the first component, and to determine a mode of operation of the hydrocyclone based on the measurement data. Also disclosed is a method of monitoring a hydrocyclone.

Disclosed is a hydrocyclone monitoring system. The hydrocyclone monitoring system comprises a hydrocyclone comprising a separation chamber having an inlet for feeding an input mixture into the separation chamber and first and second outlets for ejecting flows of 5 respective first and second components of the mixture from the separation chamber. The hydrocyclone monitoring system further comprises a conduit and a sensor assembly. The conduit is connected to the first outlet and defines a channel for conducting the flow of the first component ejected from the separation chamber. The sensor assembly is configured to detect characteristics of the flow of the first component in the channel. The hydrocyclone 10 monitoring system further comprises a processing system configured to receive from the sensor assembly measurement data indicative of the characteristics of the flow of the first component, and to determine a mode of operation of the hydrocyclone based on the measurement data. Also disclosed is a method of monitoring a hydrocyclone.

An abnormal sound identification device includes an arithmetic device and an output device. The arithmetic device is configured to identify frequency-time data recorded in a vehicle, specify a first time range and a second time range in the frequency-time data, input the frequency-time data to the trained model to cause the trained model to identify an abnormal sound generated in the first time range as a first abnormal sound based on the input frequency-time data and cause the trained model to identify an abnormal sound generated in the second time range as a second abnormal sound, and cause the output device to output a kind of the first abnormal sound with the kind not matching a kind of the second abnormal sound among the first abnormal sounds.

An abnormal sound identification device includes an arithmetic device and an output device. The arithmetic device is configured to identify frequency-time data recorded in a vehicle, specify a first time range and a second time range in the frequency-time data, input the frequency-time data to the trained model to cause the trained model to identify an abnormal sound generated in the first time range as a first abnormal sound based on the input frequency-time data and cause the trained model to identify an abnormal sound generated in the second time range as a second abnormal sound, and cause the output device to output a kind of the first abnormal sound with the kind not matching a kind of the second abnormal sound among the first abnormal sounds.

A method for controlling at least two mechanical oscillators, more particularly in a motor vehicle, where each oscillator oscillates at a frequency during operation and where the frequency can be controlled by the power applied to the oscillators, includes arranging a single sound transducer at a distance from the oscillators and capturing an electrical signal, where the electrical signal is subjected to a Fourier transform and thus a Fourier spectrum is determined. The frequency of each oscillator is determined from extreme values of the Fourier spectrum.

A method for controlling at least two mechanical oscillators, more particularly in a motor vehicle, where each oscillator oscillates at a frequency during operation and where the frequency can be controlled by the power applied to the oscillators, includes arranging a single sound transducer at a distance from the oscillators and capturing an electrical signal, where the electrical signal is subjected to a Fourier transform and thus a Fourier spectrum is determined. The frequency of each oscillator is determined from extreme values of the Fourier spectrum.

Systems, methods, and apparatus for corona detection using audio data are provided. In one example embodiment, the method includes obtaining, by one or more computing devices, audio data indicative of audio associated with an electrical system for at least one time interval. The method includes partitioning, by the one or more computing devices, the audio data for the time interval into a plurality of time windows. The method includes determining, by the one or more computing devices, a signal indicative of a presence of corona based at least in part on audio data collected within an identified time window of the plurality of time windows relative to audio data collected for a remainder of the time interval.

Systems, methods, and apparatus for corona detection using audio data are provided. In one example embodiment, the method includes obtaining, by one or more computing devices, audio data indicative of audio associated with an electrical system for at least one time interval. The method includes partitioning, by the one or more computing devices, the audio data for the time interval into a plurality of time windows. The method includes determining, by the one or more computing devices, a signal indicative of a presence of corona based at least in part on audio data collected within an identified time window of the plurality of time windows relative to audio data collected for a remainder of the time interval.

The Emergency Automatic Gunshot Lockdown (EAGL) System detects gunshots and executes at least one predetermined adaptive response action, such as notifying law enforcement of an active shooter, providing access control measures such as locking down soft target areas, and alerting building occupants of an active shooter situation. A gunshot is detected and verified using a triple validation system. Once a firearm is discharged, the EAGL system sends “real time” data to building officials, law enforcement, and building occupants notifying them of an active shooter situation. Simultaneously, predetermined commands are sent to access control devices for perimeter, office, classroom, and other soft target areas to lockdown and stay secure, to keep the shooter from entering these soft target areas, and to prevent shooter from entering other buildings.