Abstract: An apparatus for detecting a leak sound in plant equipment using time-frequency transformation includes a first microphone measuring an acoustic signal generated in the plant equipment, a second microphone measuring an acoustic signal generated in the plant equipment, and a leak sound detection module detecting a leak sound in the plant equipment using time-frequency transformation of the acoustic signal measured by the first microphone and the acoustic signal measured by the second microphone, wherein a leak sound may be detected even when a transient dispersive noise signal, as well as a periodic noise signal, is large.

Abstract: An apparatus for detecting leakage of a pipe by using a distance difference-frequency analysis includes: vibration detecting sensors, which are mounted at a predetermined distance in a longitudinal direction of a pipe and are configured to measure vibration signals of the pipe; and a control unit, which is configured to calculate a cross-correlation function by using the vibration signals, to reveal time delay information in the frequency domain by calculating time-delay frequency analysis diagram for the cross-correlation function, to calculate a distance difference-frequency analysis diagram by applying compensation conversion using frequency-dependent propagation speed information to the time-delay frequency analysis diagram, and to detect a leakage component of the pipe in the distance difference-frequency analysis diagram.

Abstract: 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.

Abstract: An apparatus for detecting leakage of a pipe by using a distance difference-frequency analysis includes: vibration detecting sensors, which are mounted at a predetermined distance in a longitudinal direction of a pipe and are configured to measure vibration signals of the pipe; and a control unit, which is configured to calculate a cross-correlation function by using the vibration signals, to reveal time delay information in the frequency domain by calculating time-delay frequency analysis diagram for the cross-correlation function, to calculate a distance difference-frequency analysis diagram by applying compensation conversion using frequency-dependent propagation speed information to the time-delay frequency analysis diagram, and to detect a leakage component of the pipe in the distance difference-frequency analysis diagram.

Abstract: Provided are an apparatus and method for detecting an anomaly in a plant pipe using multiple meta-learning. When a multi-sensor data stream about a plant pipe is received, each of a plurality of meta-learning modules for processing different packet section ranges, extracts one or more preset types of features from sensor data of packet section ranges set according to trend from an arbitrary reception time point, generates 2D image features of the features according to multi-sensor-specific times, generates 3D volume features by accumulating the 2D image features in a depth direction according to multiple sensors, and learns the 3D volume features in parallel through multi-sensor-specific learning modules. Results of the learning of the meta-learning modules are aggregated, and it is determined whether there is an anomaly in a plant pipe according to a learning result selected based on an optimal combination of multiple features, multiple sensors, and multiple packet sections.

Abstract: An apparatus for detecting leakage of a pipe by using a distance difference-frequency analysis includes: vibration detecting sensors, which are mounted at a predetermined distance in a longitudinal direction of a pipe and are configured to measure vibration signals of the pipe; and a control unit, which is configured to calculate a cross-correlation function by using the vibration signals, to reveal time delay information in the frequency domain by calculating time-delay frequency analysis diagram for the cross-correlation function, to calculate a distance difference-frequency analysis diagram by applying compensation conversion using frequency-dependent propagation speed information to the time-delay frequency analysis diagram, and to detect a leakage component of the pipe in the distance difference-frequency analysis diagram.

Abstract: An apparatus for detecting a leak sound in plant equipment using time-frequency transformation includes a first microphone measuring an acoustic signal generated in the plant equipment, a second microphone measuring an acoustic signal generated in the plant equipment, and a leak sound detection module detecting a leak sound in the plant equipment using time-frequency transformation of the acoustic signal measured by the first microphone and the acoustic signal measured by the second microphone, wherein a leak sound may be detected even when a transient dispersive noise signal, as well as a periodic noise signal, is large.

Abstract: Provided are an apparatus and method for detecting an anomaly in a plant pipe using multiple meta-learning. When a multi-sensor data stream about a plant pipe is received, each of a plurality of meta-learning modules for processing different packet section ranges, extracts one or more preset types of features from sensor data of packet section ranges set according to trend from an arbitrary reception time point, generates 2D image features of the features according to multi-sensor-specific times, generates 3D volume features by accumulating the 2D image features in a depth direction according to multiple sensors, and learns the 3D volume features in parallel through multi-sensor-specific learning modules. Results of the learning of the meta-learning modules are aggregated, and it is determined whether there is an anomaly in a plant pipe according to a learning result selected based on an optimal combination of multiple features, multiple sensors, and multiple packet sections.

Abstract: Provided are an apparatus and a method for measuring a nonlinearity parameter using laser, and more particularly, an apparatus and a method for measuring a nonlinearity parameter using laser for computing the nonlinearity parameter by irradiating laser of a toneburst signal on a surface of a sample by non-contact type laser so as to excite the sample, irradiating measurement laser beam on the surface of the sample so as to receive displacement information occurring on the surface of the sample over time, measuring the displacement in an interferometer principle, and performing a bandpass filtering for the measured signal so as to measure amplitude A1 of a component of a fundamental frequency and amplitude A2 of a component of a secondary harmonic wave.

Abstract: Disclosed are an apparatus for detecting pipe wall thinning, which measures a natural frequency of a pipe and determines a level of the pipe wall thinning, and a method thereof. The apparatus for detecting the pipe wall thinning includes a hitting member 10 for hitting the pipe T, a vibration measurement sensor 20 which measures a vibration signal generated when the pipe T is hit with the hitting member 10, and a control part 30 which compares the natural frequency calculated from the vibration signal measured from the vibration measurement sensor 20 with a natural frequency generated from a normal pipe in which wall thinning does not occur, and determines the level of the wall thinning of the pipe T.

Abstract: Provided are an apparatus and a method for measuring a nonlinearity parameter using laser, and more particularly, an apparatus and a method for measuring a nonlinearity parameter using laser for computing the nonlinearity parameter by irradiating laser of a toneburst signal on a surface of a sample by non-contact type laser so as to excite the sample, irradiating measurement laser beam on the surface of the sample so as to receive displacement information occurring on the surface of the sample over time, measuring the displacement in an interferometer principle, and performing a bandpass filtering for the measured signal so as to measure amplitude A1 of a component of a fundamental frequency and amplitude A2 of a component of a secondary harmonic wave.

Abstract: Disclosed are an apparatus for detecting pipe wall thinning, which measures a natural frequency of a pipe and determines a level of the pipe wall thinning, and a method thereof. The apparatus for detecting the pipe wall thinning includes a hitting member 10 for hitting the pipe T, a vibration measurement sensor 20 which measures a vibration signal generated when the pipe T is hit with the hitting member 10, and a control part 30 which compares the natural frequency calculated from the vibration signal measured from the vibration measurement sensor 20 with a natural frequency generated from a normal pipe in which wall thinning does not occur, and determines the level of the wall thinning of the pipe T.

Abstract: Provided is a method and device for low frequency vibration excitation, which may generate a low frequency using a plurality of ultrasonic generators for high frequency. The method generates ultrasonic waves using a plurality of ultrasonic generators attached to a target structure to induce a beat phenomenon, and extract a frequency lower than a frequency of each of the plurality of the ultrasonic generators to measure a property of the target structure, and thereby may be freely applied to a target structure, regardless of a shape of the target structure such as a plate, a curved pipe, and the like, using a relatively small-sized ultrasonic sensor for high frequency, and may excite a specific frequency of an acceleration range, so that the ultrasonic excitation method may be applicable in a relatively poor Signal-to-Noise Ratio (SNR) range.

Abstract: Provided is a method and device for low frequency vibration excitation, which may generate a low frequency using a plurality of ultrasonic generators for high frequency. The method generates ultrasonic waves using a plurality of ultrasonic generators attached to a target structure to induce a beat phenomenon, and extract a frequency lower than a frequency of each of the plurality of the ultrasonic generators to measure a property of the target structure, and thereby may be freely applied to a target structure, regardless of a shape of the target structure such as a plate, a curved pipe, and the like, using a relatively small-sized ultrasonic sensor for high frequency, and may excite a specific frequency of an acceleration range, so that the ultrasonic excitation method may be applicable in a relatively poor Signal-to-Noise Ratio (SNR) range.

Abstract: Provided is a leakage detection system and method using an image that may detect a leakage of high temperature high pressure steam using an image. The leakage detection method may include: obtaining an image of a target where a leakage of high temperature high pressure steam occurs; detecting, in the obtained image, an edge image before the leakage occurs and an edge image after the leakage occurs; detecting only a leakage edge image by comparing the edge image before the leakage occurs and the edge image after the leakage occurs; removing noise from the leakage edge image; and displaying the leakage edge image in which the noise is removed.

Abstract: A method and system for measuring structural vibration using curve fitting from a video signal, which can reduce an error in vibration measurement displacement, is provided. A method for measuring structural vibration using curve fitting from a video signal, the method includes the steps of: obtaining a video signal of the object; converting the video signal of the object into a gray video signal; adjusting the brightness of the converted video signal; separating an area to be measured from the brightness-adjusted video signal; selecting an edge area of the object from a video signal of the separated area; removing noises from the edge regions; and performing curve fitting with respect to the noise-removed video signal of the edge area. Accordingly, a displacement error is reduced, so that vibration can be more exactly measured.

Abstract: An integrated monitoring method and a system using the same which can monitor structural integrity or an operating state of a nuclear device are provided. One integrated analysis unit receives a plurality of signals in order to integrate, mutually exchange, and analyze from a plurality of heterogeneous sensors installed in the nuclear device. The integrated analysis unit may notify an operator with an alarm since an alarm unit may be adhered to the integrated analysis unit. Accordingly, the present invention may provide accurate, useful, and various information due to integration of the sensor signal while not increasing a number of installed sensors, manufacture a simulator by generating a database of the sensor signals, or use a past signal as data for an optimum design by researching and analyzing the past signal.