A testing system for monitoring a machine under test is disclosed and includes one or more high frequency sensors configured to generate a sensor signal that is representative of an operating parameter of the machine. The high frequency sensors have a required high frequency sampling rate. The testing system also includes a notification device configured to generate a notification indicating the operating parameter monitored by the high frequency sensors has exceeded a predefined threshold value and a data acquisition control module configured to monitor the high frequency sensors at a first sampling rate. The testing system also includes a monitoring control module in electronic communication with the notification device. The monitoring control module is configured to monitor the high frequency sensors at a second sampling rate that is greater than the first sampling rate and at least equal to the required high frequency sampling rate.

Apparatus and associated methods relate to a vibrational sensing system (VSS) including an accelerometer and a data processor, which determines an “operational state” of a mechanical drive unit, the processor further employing the “operational state” to gate learning of long-term vibrational data to exclude collection of non-operational data, the long-term data collected to calculate alarm thresholds. For example, vibrations from a target motor are sensed by a coupled accelerometer. Vibrational data from the accelerometer is fed into a data processor which determines the operational state of the motor. The operational state (e.g., on/off indication) may gate data collection such that data is only acquired during on-time, which may advantageously create accurate baselines from which alarm thresholds may be generated, and nuisance alarms may be avoided.

Rotating machine vibration monitoring process for detecting degradations within a rotating machine providing an output axle fitted with magnetic bearings, the magnetic bearings having at least a position sensor and at least a magnetic actuator, the process provides the following steps: 1) defining a set of excitations that does not destabilizes the rotating machine, 2) injecting the set of excitations in the rotating machine through the magnetic actuators and 3) measuring the response of the rotating machine checking whether the response verifies at least one predefined criterium, 4) if it is not the case, adjusting the properties of the set of excitations and resuming the process at the injection step, 5) if the response verifies the at least one criterium, determining at least one condition indicator based on the response measured, 6) determining if an alarm is to be triggered based on the condition indicator determined.

A one-dimensional (1D) and two-dimensional (2D) scan scheme for a tracking continuously scanning laser Doppler vibrometer (CSLDV) system to scan the whole surface of a rotating structure excited by a random force. A tracking CSLDV system tracks a rotating structure and sweep its laser spot on its surface. The measured response of the structure using the scan scheme of the tracking CSLDV system is considered as the response of the whole surface of the structure subject to random excitation. The measured response can be processed by operational modal analysis (OMA) methods (e.g., an improved lifting method, an improved demodulation method, an improved 2D demodulation method). Damped natural frequencies of the rotating structure are estimated from the fast Fourier transform of the measured response. Undamped full-field mode shapes are estimated by multiplying the measured response using sinusoids whose frequencies are estimated damped natural frequencies.

A method analyzing a machine having a rotating shaft includes generating an electric measurement signal dependent on mechanical vibrations from the shaft rotation; sampling the measurement signal to generate a digital measurement data signal; performing a decimation of the digital measurement data signal to achieve a digital signal having a reduced sampling frequency, where the decimation includes controlling the reduced sampling frequency such that the number of sample values per revolution of the shaft is kept at a substantially constant value, and receiving the digital signal at an enhancer input performing a correlation in the enhancer so as to produce an output signal sequence where repetitive signals amplitude components are amplified in relation to stochastic signal components, and performing a condition analysis for analyzing the condition of the machine dependent on the digital signal having a reduced sampling frequency.

Provided is a signal processing device capable of effectively reducing a work load of a parameter setting operator in response to an increase in parameters constituting complicated filter control. Therefore, in the signal processing device filters an output signal from a sensor mounted on a vehicle, setting is made with respect to a plurality of filters having different filter types or filter coefficients for setting a filter characteristic of a cutoff frequency or a pass band, an individual code is set for each of the plurality of filters, and the signal processing device includes a CPU that selects the individual code based on an engine operating state so that a corresponding filter is selected, and processes an output signal from the sensor using the filter that has been selected.

One embodiment of the present invention provides an apparatus and the like for improving the accuracy of deterioration estimation regarding a monitoring target. An information processing apparatus as one embodiment of the present invention includes a detector, a separator, a calculator, and an estimator. The detector detects a normal waveform pattern included in a waveform of time-series data of a target. The separator separates the waveform of the time-series data into components while removing the normal waveform pattern that is detected. The calculator calculates a feature of the time-series data based on at least one of the components. The estimator estimates deterioration of the target based on the feature.

A method of identifying a fault in a synchronous reluctance electric machine, the method including carrying out a first vibration measurement on a stator in a first radial direction of the stator; carrying out a second vibration measurement on the stator in a second radial direction of the stator; determining, on the basis of at least one of the first vibration measurement and the second vibration measurement, a first vibration frequency; determining, on the basis of the first vibration measurement and the second vibration measurement, a mode shape of the vibration at the first vibration frequency; and determining, on the basis that the first vibration frequency f.sub.b and the mode shape m fulfil the following barrier fault conditions:

f.sub.b=f.sub.r, and m=1

where f.sub.r is a rotation frequency of a rotor, that a flux barrier of the rotor is defect.

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.

Systems and methods are disclosed for identifying one or more vibration mechanisms or other mechanism associated with tool failure. In one example, a machine learning data system comprises a data pre-processing module, a machine learning training module, and a predictive module. The pre-processing module analyzes dynamic sensor input to identify one or more vibration mechanisms associated with a downhole tool. The machine learning training module identifies a correlation between dynamic sensor data and failure data for a plurality of downhole tools. The predictive module correlates the one or more vibration mechanism with tool failure or performance.