A method includes receiving data characterizing a first acoustic signal reflected by a first defect in a target object, and a first depth of the first defect relative to a surface of the target object. The first acoustic signal is detected by a detector located at a first location on the surface of the target object. The method also includes assigning a defect color to the received data based on an amplitude value associated with the first acoustic signal and one or more of a first predetermined threshold value and a second predetermined threshold value associated with the first depth. The method further includes rendering, in a graphical user interface display space, a first visual representation of the first acoustic signal in a graph including a first axis indicative of target object defect depth and a second axis indicative of amplitudes of acoustic signals detected by the detector. The first visual representation of the first acoustic signal includes the assigned defect color.

An apparatus and method for detecting an initial lubrication of a moving component including an ultrasonic sensor for detecting an ultrasonic output signal from the moving component and a processor for operating on the output signal. The processor determines if there has been an initiation of a lubrication operation. After identifying the initiation of the lubrication operation, the processor monitors the ultrasonic output signal received from the ultrasonic sensor to detect a momentary increase in the amplitude of the ultrasonic output signal above a level that indicates a need for lubrication, and which is indicative of an initial interaction between a lubricant and the moving component. Upon detecting the momentary increase in the amplitude, the processor tracks a progress of the lubrication operation by detecting for a sustained decrease in the amplitude of the ultrasonic output signal received from the ultrasonic sensor.

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.

There is provided a method for evaluating the cleanliness of a steel material by an ultrasonic flaw detection method enabling rapid acquisition of highly reliable data. Ultrasonic flaw detection is performed to detect a flaw in at least one part in the range of 90% or more and 100% or less of a steel material (for example, round bar 2) at a radial position where the center of the steel material is set as 0% and the surface is set as 100%, and then the cleanliness is evaluated based on the dimension and the number of inclusions in the steel material obtained by the ultrasonic flaw detection.

A detection device includes a vibration sensor configured to detect vibration of a machine, a calculation unit configured to perform FFT analysis on detection data of the vibration sensor, divide a specific frequency range into a plurality of frequency ranges, and calculate a partial overall value for each of the plurality of frequency ranges, and a wireless communication device configured to transmit the partial overall value.

According to the method of the invention, a lubricant is supplied incrementally to a rotary bearing while the bearing is in operation rotating at a rotational speed. The lubricant is supplied in consecutive steps so that at each step a portion of a prescribed amount of lubricant is supplied, followed each time by an ultrasound measurement. A first ultrasound measurement is performed before the first supply step, and starting from the second supply step, each measurement result is compared at least to the previous result, in order to evaluate the bearing condition and decide on that basis whether to continue the sequence or not. Stopping the sequence is decided when the lubrication of the bearing is assessed as successful, a lubrication failure or over-lubrication. The invention is equally related to a system for lubricating one or more bearings, applying the method of the invention to each of said bearings.

The invention relates to a slewing bearing that includes an inner ring, an outer ring, at least one row of rolling elements arranged between the rings in order to form an axial thrust that transmits axial forces, and at least one row of rolling elements arranged between the rings in order to form a radial thrust which can transmit radial forces. The slewing bearing further includes a sensing probe for detecting a relative displacement between the inner ring and outer ring and/or cracks, the inner ring having a through hole in which the sensing probe arranged. The through hole has a probe positioning element provided with a positioning portion and a support portion on which the sensing probe is supported so as to face the outer ring.

There is provided an abnormality diagnosis device, a bearing, a rotation device, an industrial machine, and a vehicle, which are able to discover abnormality early and also set a diagnosis threshold relatively easily. A differential value between an initial frequency component and an actual measurement frequency component is calculated, the differential value is compared to the diagnosis threshold, and abnormality diagnosis for an abnormality diagnosis target is carried out based on the comparison result, where the initial frequency component is a feature frequency component of abnormality of the abnormality diagnosis target in the rotation device, which is extracted from an initial vibration value measured at initial measurement timing while the axle is rotating at setting rotation speed during an operation of the rotation device, and the actual measurement frequency component is a feature frequency component extracted from an actual measurement vibration value measured at actual measurement timing that is the initial measurement timing or later while the axle is rotating at the setting rotation speed during the operation of the rotation device.

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.

Monitoring of a machine is performed by an acoustic monitor which acquires, through an acoustic sensor, acoustic signals from a vicinity of a machine, while the machine is operative. A processor calculates a frequency spectrum of a segment of the acquired acoustic signals, determines boundaries of a frequency band to be analyzed and extracts, from the calculated frequency spectrum, a base frequency window in the determined boundaries, and one or more harmonics windows of harmonics of the determined boundaries. For each of the base and harmonic windows a weight based on a distribution of values of frequencies in the windows is determined and a parameter of operation of the machine is calculated as a function of a weighted sum of the base and harmonic windows. The operation of the machine is evaluated responsive to the calculated parameter.