Armin Wolfram

Component-based multi-model approach for fault detection and diagnosis of a centrifugal pump

A model-based approach for fault detection and diagnosis of nonlinear processes is presented. However, the supervision of nonlinear systems is often very difficult in view of the lack of accurate models. Neuro-fuzzy models may help to cope with this problem since they can be trained from measured data. In this paper the application of a multi-model approach for fault detection and diagnosis of centrifugal pumps is presented. For this purpose the process is decomposed in several sub-processes. The supervision scheme allows the detection of several faults both in the hydraulic and mechanical subsystems.

Semi-physical modelling of nonlinear processes by means of local model approaches

Abstract For many practical applications, a combination of theoretical and experimental modelling appears feasible. Qualitative knowledge about the most significant effects are often known or easily accessible. This contribution suggests a semi-physical modelling approach based on the special architecture of local models. Due to their inherent transparency, these models are very well suited for the incorporation of mainly qualitative process knowledge. The integration of prior knowledge is realised by an adaptation of the model structure to that one of the process. As a result, the final process-specific models are characterised by high generalisation performance also in situations with only few measurement data.

Component based tele-diagnosis approach to a textile machine

Abstract The detection and diagnosis of faults in technical systems is of great practical significance. With the help of recent data transfer techniques, service technicians must not necessarily be on site in order to diagnose the cause of failure. Therefore tele-diagnosis can be defined as a service making use of modern communication channels. However, further progress can be achieved by automating the supervision task. An early detection of faults may help to avoid product deterioration, performance degradation, major damage to the machinery itself and damage to human health or even loss of lives. Furthermore, by employing modern diagnostic systems, faults can even be detected before they lead to a partial or total failure of the plant. This information can be utilised to plan maintenance cycles and thus to minimise plant outages. Within this paper a component-based plant monitoring approach is proposed which relies on the idea that the supervision of complex plants can take place in the individual components.

On-Line Fault Detection of Inverter-Fed Induction Motors Using Advanced Signal Processing Techniques

Abstract Due to the increasing demands concerning reliability, safety and economy of technical processes, on-line fault detection of induction motors is an important topic in the engineering field. Approaches, based on the spectral analysis of motor currents have been frequently proposed. The main drawback of these approaches has been the restriction on induction machines fed by power supplies with constant frequency. Due to the progress in semiconductor technology and power electronics, inverter-fed induction motors providing a wide speed range are more and more employed. This paper proposes the basics of a nonlinear time-domain transformation which is capable of applying the same spectral analysis scheme for different speeds. Finally, experiments are shown for the detection of insulation failures in the stator windings.

Component Based Tele-Diagnosis Approach to a Textile Machine

Abstract The detection and diagnosis of faults in technical systems is of great practical significance. With the help of recent data transfer techniques, service technicians must not necessarily be on-site in order to diagnose the cause of failure. Therefore tele-diagnosis can be defined as a service making use of modern communication channels. However, further progress can be achieved by automating the supervision task. An early detection of faults may help to avoid product deterioration, performance degradation, major damage to the machinery itself and damage to human health or even loss of lives. Furthermore, by employing modern diagnostic systems, faults can even be detected before they lead to a partial or total failure of the plant. This information can be utilised to plan maintenance cycles and thus to minimise plant outages. Within this paper a component-based plant monitoring approach is proposed which relies on the idea that the supervision of complex plants can take place in the individual components.