Acoustic Recognition of Failures in Machines and Systems
A new sensor system developed by the Fraunhofer Institute for Nondestructive Testing IZFP can detect failures or imperfections in systems and machines quickly and reliably by means of an acoustic noise assessment. The sensor system has already been successfully deployed by John Deere to test combine harvester cutting units.
In cases in which large-scale machines or plants are already in operation, defects or improperly assembled components may result in machine malfunctions and consequently production shut-down and economic loss. Therefore, quality assurance prior to launch and after the final assembly of plants or machines is crucial. Fraunhofer IZFP researchers have developed an inspection solution that provides objective results, as well as the capacity for permanent quality monitoring and final assembly inspection of moving or rotating machines and plants.
Reliable failure detection without elaborate calibration
In operation, machines and plants generate characteristic vibrations and therefore noises, which provide information on quality since assembly errors or other defects often induce a change in the regular operating noises. Often, assembly staff have a good ear and several years of experience in detecting these changes. However human hearing has a subjective nature: it is subject to deterioration over time and can be adversely affected by environmental noise. Existing commercially-available solutions often require adaptation or extensive calibration.
Fraunhofer IZFP's AcoustiX sensor system exploits data of individually adjusted acoustic sensors which are directly attached to the machine. Alternatively, microphones are used for contactless recording of vibrations or noises of machines or plants. Failures or imperfections are then automatically analysed and subsequently logged. Based on the signal assessment, targeted analysis regarding the correct assembly and function of the plant or machine is produced within minutes.
Range of industrial applications
The system can be used in all areas in which final assembly inspection or permanent operation monitoring are crucial, e.g., to monitor huge autonomously operated machines and plants or to assess the quality of single assembly units which are operated, among other things, on test benches. "The development zeroes in on our analytical methods, the algorithms. They are suited to be integrated in existing inspection lines and can be adapted to fit the individual needs of the customer," explains Matthias Heinrich, scientist at Fraunhofer IZFP.
Currently, AcoustiX is successfully used at John Deere for the permanent quality monitoring of cutting units of combine harvesters in industrial application and is currently being validated for use in mass production. The medium-term goal of the researchers is precise failure localisation, as well as the detailed determination of the defect type by means of intelligent algorithms or analytical methods.