Figure 1 - uploaded by Menghui Zhu
Content may be subject to copyright.
Source publication
Adaptive drilling enables the optimisation of cutting parameters to suit the specific requirements of multi-material stacks, for example hybrid stacks comprising carbon fibre reinforced polymer (CFRP) and aluminium which are commonly used in the aerospace industry. This work proposed a deep learning approach to identify process incidences from diff...
Context in source publication
Context 1
... the drilling tool penetrates through a stacked structure comprising different layers, a series of process incidences occurs. In the case of CFRP/Al stacks, there are five distinct process incidences that take place in a specific temporal order, as shown in Figure 1. The first incidence is tool engagement, where the tool begins to enter the upper layer of the stack. ...
Similar publications
The stacked carbon fiber reinforced plastic (CFRP) laminate and metallic plate are widely used in the aerospace industry to improve structural performance and reliability. Abrasive waterjet (AWJ) machining is a promising technique for cutting hybrid metallic/CFRP stacks with high efficiency and versatility, while the machining defects including ker...
Citations
... Neugebauer et al. [147] utilized AE signals to identify the drill transition point in CFRP/Al stacks drilling, where a change of slope was used to locate the entry point to Al layer. However, the reliability of these approaches is significantly influenced by the process uncertainties, extent of tool wear and dependence on expert knowledge [166]. ...
... This model achieved material identification accuracy of 100%. Zhang et al.[166] deployed 1D CNN to extract and fuse the features from thrust force and torque signals for the recognition of 5 different stages in drilling (engagement, CFRP cutting, transition, Al cutting and disengagement). The prediction confusion matrices with thrust force and torque signals are presented inFig. ...
... Studies on material transition recognition in drilling of CFRP/metal stack using data-driven methods (a) Flow chart of a method based on multi-sensor data fusion and RF[46]; (b) Prediction confusion matrices of 1D CNN model with different signals (thrust force and torque)[166]; (c) Variation of prediction accuracy with sampling frequency and sampling time[167] ...
The global drive towards net-zero has accelerated the adoption of carbon fibre reinforced polymers (CFRP) for lightweight structures in various sectors such as aerospace, automotive, energy and biomedical. Mechanical machining of CFRP is often necessary to meet dimensional or assembly-related requirements. However, significant challenges including surface defects (delamination, burr, surface roughness), rapid tool wear and material transition issues in drilling CFRP/metal stack, underscore the need for effective, automated process prediction / optimization for improved machining performance. Conventional physics-based models often fall short due to their reliance on extensive computational resources and inability to capture CFRP’s complex machining dynamics arising from thermo-mechanical load coupling and process uncertainties. To address these limitations, recent advancements in artificial intelligence (AI) offer promising, data-driven solutions that reduce reliance on domain-specific knowledge while delivering fast, accurate predictions by uncovering patterns within dataset. This provides a promising solution towards intelligent CFRP machining process with improved quality and efficiency. To date, there is a lack of comprehensive, up-to-date review of data-driven methods in CFRP machining process prediction/optimization. This review fills this gap and provides a critical analysis of data-driven methods in four key application settings: (i) machining process characteristics and surface quality/defects prediction; (ii) tool wear prediction; (iii) material transition recognition in CFRP/metal stacks machining; (iv) vision-based surface defects recognition. By presenting a state-of-the-art overview of advances, challenges and future research directions, this review highlights the transformative potential of data-driven methods in advancing intelligent CFRP machining within the manufacturing value chain.
