Inspection in confined spaces and difficult-to-access machines is a challenging quality assurance task and particularly difficult to quantify and automate. Using the example of aero engine inspection, an approach for the high-precision inspection of movable turbine blades in confined spaces will be demonstrated. To assess the condition and damages of turbine blades, a borescopic inspection approach in which the pose of the turbine blades is estimated on the basis of measured point clouds is presented. By means of a feature extraction approach, film-cooling holes are identified and used to pre-align the measured point clouds to a reference geometry. Based on the segmented features of the measurement and reference geometry a RANSAC-based feature matching is applied, and a multi-stage registration process is performed. Subsequently, an initial damage assessment of the turbine blades is derived, and engine disassembly decisions can be assisted by metric geometry deviations. During engine disassembly, the blade root is exposed to high disassembly forces, which can damage the blade root and is crucial for possible repair. To check for dismantling damage, a fast inspection of the blade root is executed using the borescopic sensor.

The disassembly of complex capital goods is characterized by strong uncertainty regarding the product condition and possible damage patterns to be expected during a regeneration job. Due to the high value of complex capital goods, the disassembly process must be as gentle as possible and being adaptable to the varying und uncertain product's state. While methods based on data mining have already been successfully used to forecast capacity and material requirements, the determination of the product's or component's condition has become apparent in the recent past. Despite the rapid increase in sensor technology on capital goods such as aircraft engines and their use for condition monitoring due to countless interfering effects, it is only possible to react spontaneously to the product's condition. So far, we have concentrated on product condition-based prioritization of disassembly operations in a logistics-oriented sequencing strategy. In this article, we present an approach to predict disassembly process-planning parameters based on operational usage data using machine learning. With the prediction of disassembly forces and times, processes, tools and capacities can be efficiently planned. Thus, we can establish a componentfriendly disassembly process adaptable to varying product conditions. In this article, we show the successful validation on a replacement model of an aircraft engine.

No abstract

No abstract

No abstract