Systems, methods, and other embodiments associated with autonomous discrimination of operation vibration signals are described herein. In one embodiment, a method includes partitioning a frequency spectrum of output into a plurality of discrete bins, wherein the output is collected from vibration sensors monitoring a reference device; generating a representative time series signal for each bin while the device is operated in a deterministic stress load; generating a PSD for each bin by converting each signal from the time domain to the frequency domain; determining a maximum power spectral density value and a peak frequency value for each bin; selecting a subset of the bins that have maximum PSD values exceeding a threshold; assigning the representative time series signals from the selected subset of bins as operation vibration signals indicative of operational load on the reference device; and configuring a machine learning model based on at least the operation vibration signals.

A power module for producing structure-borne sound. The power module includes: a control unit and a first substrate, the control unit being situated on the first substrate; at least one first power semiconductor and at least one second power semiconductor, the first substrate being situated on the at least one first power semiconductor and on the at least one second power semiconductor; a first metal connection, a second substrate, and a second metal connection, the first metal connection electrically connecting the first substrate and the second substrate, and the second metal connection being situated below the second substrate, wherein the second substrate has a piezoelectric material and the control unit is set up to excite the piezoelectric material of the second substrate so that a structure-borne sound signal is produced.

A method for estimating structural vibration in real time includes steps described below. A to-be-estimated measuring point of a to-be-measured structure is acquired, and at least one target measuring point associated with the to-be-estimated measuring point is determined; coordinates corresponding to each target measuring point of the at least one target measuring point, a target mode corresponding to the each target measuring point and a target vibration parameter corresponding to the each target measuring point are determined; a mode vibration parameter of the to-be-estimated measuring point and an interpolation vibration parameter of the to-be-estimated measuring point are determined based on the to-be-estimated measuring point and in combination with the target mode, the target vibration parameter and the coordinates of the each target measuring point; and an estimated vibration parameter of the to-be-estimated measuring point is determined according to the mode vibration parameter and the interpolation vibration parameter.

Disclosed are methods, apparatuses, and computer implemented methods to improve the reliability and safety of the autonomous vehicles. In one aspect, a method for determining an environmental exposure of an autonomous vehicle is disclosed. The method includes obtaining sensor data from one or more shock or vibration sensors mounted to the autonomous vehicle and determining a level of vibrations or a level of shock at the autonomous vehicle based on the obtained sensor data. The method further includes adding the level of vibrations of the autonomous vehicle to an accumulated level of vibrations of the autonomous vehicle and determining whether the accumulated level of vibrations of the autonomous vehicle exceeds a predetermined threshold value for the accumulated level of vibrations of the autonomous vehicle.

A smart device input method based on facial vibration includes: collecting a facial vibration signal generated when a user performs voice input; extracting a Mel-frequency cepstral coefficient from the facial vibration signal; and taking the Mel-frequency cepstral coefficient as an observation sequence to obtain text input corresponding to the facial vibration signal by using a trained hidden Markov model. The facial vibration signal is collected by a vibration sensor arranged on glasses. The vibration signal is processed by: amplifying the collected facial vibration signal; transmitting the amplified facial vibration signal to the smart device via a wireless module; and intercepting a section from the received facial vibration signal as an effective portion and extracting the Mel-frequency cepstral coefficient from the effective portion by the smart device.

An identification device according to an embodiment includes: a sensor that measures a grasping state of a grasped object as an identification target; a position information acquisition unit that acquires position information of a sensor wearer who is wearing the sensor; and an identification unit that identifies the grasped object that is grasped by the sensor wearer based on the grasping state measured by the sensor and the position information acquired by the position information acquisition unit.

A moving part control system for a vehicle configured to cause a movement of a mechanical part for loosening the mechanical part from a stuck state to a loose state. The moving part control system includes an electrically controlled actuator device configured to cause a movement of the mechanical part, a processing circuitry configured to be operatively connected to the electrically controlled actuator device and configured to determine an amplitude and/or a frequency of an oscillating movement of the electrically controlled actuator device to determine if the mechanical part is in a stuck state or a loose state.

A system for monitoring and identifying states of a semiconductor device, the system including at least one acoustic sensor for sensing acoustic emission emitted by at least one semiconductor device operating at a voltage of less than or equal to 220 V. the at least one acoustic sensor outputting at least one acoustic emission signal and a signal processing unit for receiving the at least one acoustic emission signal from the at least one acoustic sensor and for analyzing the at least one acoustic emission signal, the signal processing unit providing an output based on the analyzing, the output being indicative at least of whether the at least one semiconductor device is in an abnormal operating state with respect to a normal operating state of the semiconductor device.

A system for monitoring and identifying states of a semiconductor device, the system including at least one acoustic sensor for sensing acoustic emission emitted by at least one semiconductor device operating at a voltage of less than or equal to 220 V. the at least one acoustic sensor outputting at least one acoustic emission signal and a signal processing unit for receiving the at least one acoustic emission signal from the at least one acoustic sensor and for analyzing the at least one acoustic emission signal, the signal processing unit providing an output based on the analyzing, the output being indicative at least of whether the at least one semiconductor device is in an abnormal operating state with respect to a normal operating state of the semiconductor device.

An inertial measurement system includes three acceleration sensors detecting along three orthogonal axes, a display having several display areas, and a processor programed to perform a process. The processor calculates frequencies and spectral intensities of vibrations based on detected time series accelerations by three acceleration sensors and obtains relationship values between the calculated frequencies and the calculated spectral intensities. The processor causes the display to successively display an N-th value, intermediate values, and an (N+1)-th value of the relationship values at one display area in time series.