Diagnosis of Machines within Industry using Sensor Signals and Case-Based Reasoning

Abstract

Machines are not perfect; they sometimes fail to operate as intended. Such failures can be more or less severe depending on the kind of machine and the circumstances of the failure. E.g. the failure of an industrial robot can cause the hold-up of an entire assembly line costing the affected company large amounts of money each minute on hold. This kind of situation can be prevented by equipping machines with automatic condition-monitoring systems that continuously monitor their condition and instantly report the detection of a failure or an incipient failure. The nature of machine-monitoring and diagnosis lends itself naturally to Case-Based Reasoning. Case-Based Reasoning is a method in the discipline of Artificial Intelligence based on the idea of assembling experience from problems and their solutions as ”cases” for reuse in solving future problems. Cases are stored in a case library, available for retrieval and reuse at any time. By collecting such sensor data as sound and vibrations from a machine and representing this data as the problem part of a case and consequently representing the measured corrective action as the solution to this problem, a complete series of the events of a machine failure and its correction can be stored in a case for future use. This thesis describes an innovative approach to this concept by using a combination of Case-Based Reasoning and wavelet analysis as a means of condition-monitoring and diagnosis of primarily industrial machines. For evaluation purposes this novel approach is implemented as a prototype system for the diagnosis of the status of gearboxes in industrial robots.