Unsupervised Machine Learning for Advanced Tolerance Monitoring of Wire Electrical Discharge Machining of Disc Turbine Fir-Tree Slots

The Review of Current and Proposed Methods of Manufacturing Fir Tree Slots of Turbine Aero Engine Discs

This review article presents a summary of currently used and proposed methods of manufacturing fir tree slots of discs in turbine engines. The production of aircraft, including aircraft engines during times of overlapping global economic crises related to the COVID-19 pandemic or the war in Eastern Europe requires a quick response to the changing numbers of passengers and cargo. Similarly, the aviation industry must adapt to these conditions, and thus utilize flexible production methods allowing for a quick change in the design or type of a given part. Due to the constant adoption of new materials for the most critical aero engine parts and the necessity of complying with environmental regulations, it is necessary to search for new methods of manufacturing these parts, including fir tree slots. As an alternative to currently used expensive and energy-intensive broaching, many manufacturers try to implement creep feed grinding CFG or contour milling. However, other manufacturing methods, thus far rarely used for crucial machine parts such as WEDM, ECDM or AWJ, are gaining more and more popularity in the aviation industry. This article presents the advantages and shortcomings of these methods in the context of manufacturing fir tree slots.

Experimental and Numerical Study of Crater Volume in Wire Electrical Discharge Machining

Wire Electrical Discharge Machining (WEDM) is a popular non-conventional machining technology widely used in high-added value sectors such as aerospace, biomedicine, and the automotive industry. Even though the technology is now ready to meet the requirements of the most complex components, certain fundamental aspects related to the discharge process and gap conditions are not yet fully explained and understood. Combining single discharge experiments with numerical simulation represents a good approach for obtaining a deeper insight into the fundamentals of the process. In this paper, a fundamental study of the WEDM through single discharge experiments and numerical simulation is presented. WEDM single discharge experiments are described with the aim of identifying the relation between crater dimensions, discharge gap, and part surface roughness. A thermal transient numerical model of the WEDM process is presented, and correlation with actual industrial material removal rates (MRR) is analyzed. Results from single discharge WEDM experiments show that crater volume is as much as 40% lower when discharging on a rough surface than when the discharge occurs on a flat surface. The proposed thermal numerical model can predict actual removal rates of industrial machines with great accuracy for roughing cuts, deviations with experimental values being below 10%. However, lager deviations have been observed for other WEDM conditions, namely trim cuts, thus confirming the need for future research in this direction.

AI-Based Sensor Information Fusion for Supporting Deep Supervised Learning

In recent years, artificial intelligence (AI) and its subarea of deep learning have drawn the attention of many researchers. At the same time, advances in technologies enable the generation or collection of large amounts of valuable data (e.g., sensor data) from various sources in different applications, such as those for the Internet of Things (IoT), which in turn aims towards the development of smart cities. With the availability of sensor data from various sources, sensor information fusion is in demand for effective integration of big data. In this article, we present an AI-based sensor-information fusion system for supporting deep supervised learning of transportation data generated and collected from various types of sensors, including remote sensed imagery for the geographic information system (GIS), accelerometers, as well as sensors for the global navigation satellite system (GNSS) and global positioning system (GPS). The discovered knowledge and information returned from our system provides analysts with a clearer understanding of trajectories or mobility of citizens, which in turn helps to develop better transportation models to achieve the ultimate goal of smarter cities. Evaluation results show the effectiveness and practicality of our AI-based sensor information fusion system for supporting deep supervised learning of big transportation data.

Geometrical Defect Detection in the Wire Electrical Discharge Machining of Fir-Tree Slots Using Deep Learning Techniques

Traceability is a critical issue in the manufacturing of aerospace components. However, extracting understandable information from huge amounts of data from manufacturing processes may become a very difficult task. In this paper, a novel proposal for geometrical defect detection in the manufacturing of fir-tree slots for disk turbines using wire electrical discharge machining is presented. Useful data about the wire Electrical Discharge Machining (WEDM) process are collected every 5 ms and each single discharge is classified as a function of ignition delay time. Information from this large amount of data is extracted by using a deep neural network, which includes two hidden dense layers, each with 64 units and Relu activation, and it ends with a single unit with no activation. The average of the per-epoch absolute error (MAE) scores has been used to decide the optimum training situation for the deep learning network. Validation of the method has been carried out by machining a high-precision fir-tree slot for a disk turbine under industrial conditions. Results show that even though a strict tolerance band of ±5 µm has been applied, as many as 80% of the predictions from the network match the results of the conventional measuring method (coordinate measuring machine).