Analyzing the condition of a road surface by using a frequency-of-interest or a resonance sound in a tire. A training audio signal is sent to a learning unit, a label generator and a frequency selection model that does not complete learning. The training audio signal is obtained by collecting driving noise generated when a vehicle travels on a road. The label generator generates a label audio-of-interest signal by attenuating a band other than a frequency-of-interest band in the training audio signal. The frequency selection model derives a training imitated audio-of-interest signal imitating an audio-of-interest signal by performing a plurality of operations in which an unlearned weight is applied to the training audio signal. The learning unit calculates a generation loss that is a difference between the training imitated audio-of-interest signal and the label audio-of-interest signal, and performs optimization of updating the weight of the frequency selection model.

A motor noise detecting device according to an embodiment of the present disclosure includes a signal sensing part for sensing an acoustic signal generated from an object to be tested, a data acquisition part for receiving the acoustic signal sensed by the signal sensing part and converting it into an acoustic digital signal, and a data analysis part for receiving and analyzing the acoustic digital signal to perform a detection on whether the object to be tested is abnormal. In addition, the signal sensing part includes an AE (Acoustic Emission) sensor for sensing an elastic wave included in the acoustic signal, and the data analysis part generates result data of analyzing the acoustic digital signal, analyzes the generated result data through a pre-learned model, and detects whether the object to be tested is abnormal.

A machine learning device which learns fault prediction of one of a main shaft of a machine tool and a motor driving the main shaft, including a state observation unit observing a state variable including at least one of data output from a motor controller controlling the motor, data output from a detector detecting a state of the motor, and data output from a measuring device measuring a state of the one of the main shaft and the motor; a determination data obtaining unit obtaining determination data upon determining one of whether a fault has occurred in the one of the main shaft and the motor and a degree of fault; and a learning unit learning the fault prediction of the one of the main shaft and the motor in accordance with a data set generated based on a combination of the state variable and the determination data.

Methods and systems for solving inverse problems arising in systems described by a physics-based forward propagation model use a Bayesian approach to model the uncertainty in the realization of model parameters. A Generative Adversarial Network (“GAN”) architecture along with heuristics and statistical learning is used. This results in a more reliable point estimate of the desired model parameters. In some embodiments, the disclosed methodology may be applied to automatic inversion of physics-based modeling of pipelines.

There is provided a system for monitoring a screening machine, comprising a vibration sensor configured to record a vibration response of a screen fabric of the screening machine; and a signal processing device for digitally processing and evaluating the vibration response. In this connection, the signal processing device comprises an adaptive algorithm which is based on the methods of artificial intelligence, is related to vibration responses of one or several comparative screen fabrics and is adapted to characterize the vibration response recorded by the vibration sensor. Furthermore, a method for monitoring a screening machine is presented.

A downhole fluid analysis device includes a piezoelectric helm resonator, a spectroscopy sensor positioned symmetrically with respect to the piezoelectric helm resonator in at least one direction, and a circuit comprising a first terminal and a second terminal electrically coupled to a power supply. The piezoelectric helm resonator and the spectroscopy sensor are electrically coupled in parallel between the first and second terminals. The power supply drives the piezoelectric helm resonator with a voltage of a first polarity and the spectroscopy sensor with a voltage of a second polarity. The circuit includes at least one current flow control device in the circuit configured to prevent both the piezoelectric helm resonator and the spectroscopy sensor from being powered simultaneously.

A sensor device is coupled to a mechanical machine. The sensor device detects vibrations of the mechanical machine and transmits the vibration data to a remote processing device. The vibration data may be compressed prior to transmission. The remote processing device receives the data and generates a reconstructed version of the vibration data. The remote processing device includes a machine learning model trained to examine vibration data and to identify a motion pattern associated with an error condition. The machine learning model is applied to the reconstructed vibration data and detects an occurrence of an error condition in the mechanical machine. An alert indicating that an error condition has been detected is transmitted to a human operator. The human operator verifies the status of the mechanical machine and confirms that an error condition has occurred. In response to receipt of the confirmation, the machine learning model is further trained on training data updated to include the vibration data generated by the mechanical machine.

A system for testing properties of a sample, the system including a test cell. The test cell includes a cell casing having a first end piece, a second end piece, and at least one wall extending between the first end piece and the second end piece. The cell casing defines a pressure boundary enclosing an interior region of the cell. The test cell further includes a sample chamber, a first reservoir, and a second reservoir disposed within the pressure boundary. The sample chamber defines an interior region. The first reservoir fluidly connects to the interior region of the sample chamber. The second reservoir fluidly connects to the interior region of the sample chamber. The test cell also has a piston assembly having a piston fluid chamber and a piston with a stem extending into the piston fluid chamber. The piston partially defines the sample chamber.

A method and an apparatus for monitoring battery state are provided. A method of monitoring battery state involves collecting vibration information based on a signal from an acceleration sensor, calculating a cumulative impact based on the vibration information, and estimating a degree of damage to a battery based on the cumulative impact.

An ultrasonic inspection system, method, and software. In one embodiment, the ultrasonic inspection system includes an ultrasonic probe that directs ultrasound waves into a structure from a front wall, and receives reflected waves to generate a response signal. The system further includes a processor that rectifies the response signal to generate a rectified signal, integrates a portion of the rectified signal within a detection time window to determine an energy sum, and generates output based on the energy sum. The detection time window is restricted to a front wall reflection and at least a portion of a near-surface dead zone following the front wall reflection.