The invention relates to an acoustic sensor system (1) for detecting a defect (2) of a pipeline wall (3), having: at least one transmitter unit (4) which is configured to emit ultrasound in the direction of a pipeline wall (3) and detect an ultrasound echo reflected by the pipeline wall (3); and a control unit (5) which is connected to the at least one transmitter unit (4) for signaling purposes and which is configured to detect a defect (2) of the pipeline wall (3) using a present change in he ultrasound echo. The invention additionally relates to an in-line inspection device comprising the sensor system (1), to a method for detecting a defect (2) in a pipeline wall (3), to a computer program, to a data carrier signal, and to a data storage unit.

A fault state detection apparatus includes an input unit and a processing unit. The input unit receives condition monitoring data. The processing unit implements a trained machine learning algorithm to analyze the received condition monitoring data to determine if the received condition monitoring data is associated with a fault state. The trained machine learning algorithm was trained on the basis of a plurality of non-fault state condition monitoring data and associated ground truth information and on the basis of a plurality of fault state condition monitoring data and associated ground truth information. A subset of the plurality of fault state condition monitoring data was generated from one or more non-fault state condition monitoring data. Generation of fault state conditioning monitoring data in the subset of the plurality of fault state condition monitoring data comprises a transformation of non-fault state condition monitoring data to fault state condition monitoring data.

A fault state detection apparatus includes an input unit and a processing unit. The input unit receives condition monitoring data. The processing unit implements a trained machine learning algorithm to analyze the received condition monitoring data to determine if the received condition monitoring data is associated with a fault state. The trained machine learning algorithm was trained on the basis of a plurality of non-fault state condition monitoring data and associated ground truth information and on the basis of a plurality of fault state condition monitoring data and associated ground truth information. A subset of the plurality of fault state condition monitoring data was generated from one or more non-fault state condition monitoring data. Generation of fault state conditioning monitoring data in the subset of the plurality of fault state condition monitoring data comprises a transformation of non-fault state condition monitoring data to fault state condition monitoring data.

A method of determining wear/degradation levels of a consumable assembly of a welding/plasma torch may utilize a controlled sound signal in order to determine an acoustic profile or full spectral audio analysis dataset of the consumable assembly that facilitate the identification of patterns that correlate to certain wear/degradation levels of the consumable assembly. The full spectral audio analysis dataset may be obtained by subjecting a given consumable assembly to a controlled sound signal between operations and as the consumable assembly degrades over time. The full spectral audio analysis may serve as a wear/degradation profile over the life of the given consumable assembly. With a full dataset known for a particular consumable assembly model, an acoustic profile of another consumable assembly of the same model may be obtained and compared to the full dataset in order to identify the wear/degradation level of the tested consumable assembly.

Aspects of the disclosure include systems, methods, and program products for evaluating the condition of a component using an acoustic sensor embedded within a lighting device. A system according to the present disclosure can include a first lighting device configured to illuminate an area of an industrial plant; a first acoustic sensor embedded within the first lighting device and configured to detect an acoustic signature of a component in the industrial plant; a computing device communicatively connected to the first acoustic sensor and configured to evaluate a condition of the component in the industrial plant based on the acoustic signature.

A system for determining one or more properties of one or more gases. The system comprises sensors configured to measure thermal conductivity and exothermic responses of a sample at multiple temperatures. Sensor responses to exposure to a gas sample at two or more temperatures are compensated and analyzed by a subsystem. The subsystem is configured to determine a thermal conductivity of the gas sample at each of the two or more temperatures and determine at least one component of the gas sample based at least in part on the thermal conductivity value of the sample at each of the two or more temperatures. Related systems and methods of determining one or more properties of a sample are also disclosed.

A non-destructive measurement apparatus and method for quantitatively measuring texture of a food snack is disclosed. The apparatus includes a laser generating tool, an ultrasound excitation device, an acoustic capturing device, an ultrasound capturing device and a data processing unit. The laser generating tool and the ultrasound excitation tool direct energy towards a food snack placed on a surface and produce an acoustic signal and an ultrasound signal. The data processing unit further comprises a digital signal processing module that processes the received acoustic signal and ultrasound signal. A statistical processing module further filters the acoustic signal from the data processing unit and generates a quantitative acoustic model for texture attributes such as hardness and fracturability. The quantitative model is correlated with a qualitative texture measurement from a descriptive expert panel. Texture of food snacks are quantitatively measured with the quantitative acoustic model.

According to one embodiment, a control method includes setting a transmission angle of an ultrasonic wave to a standard angle. The control method further includes transmitting an ultrasonic wave at the set transmission angle and detecting an intensity of a reflected wave from an object. The control method further includes calculating a tilt angle based on a gradient of the intensity. The tilt angle indicates a tilt of the object. The control method further includes resetting the transmission angle based on the tilt angle.

According to one embodiment, a control method includes setting a transmission angle of an ultrasonic wave to a standard angle. The control method further includes transmitting an ultrasonic wave at the set transmission angle and detecting an intensity of a reflected wave from an object. The control method further includes calculating a tilt angle based on a gradient of the intensity. The tilt angle indicates a tilt of the object. The control method further includes resetting the transmission angle based on the tilt angle.

In one example, a method performed by electronic circuitry comprises: causing a transducer to transmit a first signal; receiving a second signal from the transducer; computing distances responsive to a time between the first and second signals; determining a vibration characteristic based on the distances; reading reference vibration characteristics from data in a memory; comparing the input vibration characteristic to the reference vibration characteristics; and responsive to the comparing, performing at least one of: providing a signal representing a status of the comparing; or updating the data in the memory.