Acoustic Quality Assurance during End of Line Engine Test Approval

Abstract

<div class="section abstract"><div class="htmlview paragraph">Liebherr Machines Bulle SA (LMB) designs and produces High-quality diesel engines, injection systems as well as hydraulic components. Liebherr has an Acoustic End of Line (AEOL) system on serial test benches. All engines are measured, and noises are evaluated by operators. This subjective evaluation leads to dispersion on the evaluations, particularly for whining noise. To ensure customer satisfaction, Liebherr wishes to define a new methodology to find a quantitative and objective criterion to set a robust engine noise compliance standard. This new methodology is based on near field microphone measurement of an engine run-down. First, whining noise signatures are extracted from the raw signal. Secondly, psychoacoustic indicators are calculated on the extracted signatures. Thresholds are then established to validate engine deliveries. Finally, this process combining advanced signal processing and psychoacoustics is automated using the Ansys Sound Python library in mass production. All engines are now automatically sorted thanks to robust objective thresholds defined by experts. This process improves and automates the global End-of-Line (EOL) protocol. It reduces reaction and decision time to overcome an eventual assembly deviation or non-conformity of parts. It also helps adapting the tolerance intervals on the technical drawing plans of certain parts. In the future, this methodology will be further developed to identify additional characteristics such as slapping noise, whistling noise, and deployed to more Liebherr products. Machine Learning (ML) and Artificial Intelligence will also be investigated as solutions for further diagnostic automation.</div></div>