Due to ageing populations and a shortage of skilled labour, automatic machine condition monitoring is a powerful tool to ensure smooth operation of production systems with reduced manpower. Automatic condition monitoring enables early detection of machine faults, greatly increasing uptime, reliability, and safety. However, conventional fault detection methods based on vibration require installation of additional sensors, thus bringing up implementation effort and initial costs. The linear feed axis is a machine component whose failure can bring an entire production line to a standstill. Therefore, this study presents a sensorless approach, which uses a linear axis' motor current for the detection of misalignment. Motor current time series data was encoded as images and then fed to a CNN, more precisely a revised residual neural network (ResNet). A random search hyper-parameter tuning technique was used to optimise the structure of the CNN. Then, transfer learning was used to apply the current signal features already learned to other scenarios. The results showed that both horizontal and vertical misalignments of linear feed axes can be well detected by a revised ResNet using motor current signals, with an accuracy of 99.76%. Using transfer learning, misalignments were detected with an accuracy of 92.67% -even under the in uence of external forces.

Due to ageing populations and a shortage of skilled labour, automatic machine condition monitoring is a powerful tool to ensure smooth operation of production systems with reduced manpower. Automatic condition monitoring enables early detection of machine faults, greatly increasing uptime, reliability, and safety. However, conventional fault detection methods based on vibration require installation of additional sensors, thus bringing up implementation effort and initial costs. The linear feed axis is a machine component whose failure can bring an entire production line to a standstill. Therefore, this study presents a sensorless approach, which uses a linear axis’ motor current for the detection of misalignment. Motor current time series data was encoded as images and then fed to a CNN, more precisely a revised residual neural network (ResNet). A random search hyper-parameter tuning technique was used to optimise the structure of the CNN. Then, transfer learning was used to apply the current signal features already learned to other scenarios. The results showed that both horizontal and vertical misalignments of linear feed axes can be well detected by a revised ResNet using motor current signals, with an accuracy of 99.76%. Using transfer learning, misalignments were detected with an accuracy of 92.67% – even under the influence of external forces.

No abstract

Während sich Anwendungen der künstlichen Intelligenz (KI) bereits in vielen Technologiefeldern etabliert haben und die Verfügbarkeit sowie der Support der ihnen zugrunde liegenden KI-Frameworks hoch ist, verbleiben bei der Nutzung im produktionstechnischen Bereich noch offene Potenziale. Von der initialen Entwicklung, dem nutzerorientierten Einsatz im Feld bis hin zur langfristigen Unterstützung einer KI-Anwendung ist eine Vielzahl an Arbeitsschritten notwendig, wodurch der Einsatz insbesondere für KMUs mit Einstiegshürden verbunden ist.   While artificial intelligence (AI) applications are well-established in many technology sectors and the availability and support of the underlying frameworks is high, there remain untapped potentials for their use in manufacturing systems. From the initial development of an AI application and the user-centered deployment to the shop floor unto its long-term support numerous steps are necessary, which especially for SMEs, represent entry barriers.