Intellegens > Case Studies > Optimizing Tooling for Composite Drilling Using Deep Learning

Optimizing Tooling for Composite Drilling Using Deep Learning

Technology Category

Analytics & Modeling - Machine Learning

Applicable Industries

Aerospace
Equipment & Machinery

Applicable Functions

Maintenance
Product Research & Development

Use Cases

Additive Manufacturing
Time Sensitive Networking

Services

Testing & Certification
Training

The Customer

The University of Sheffield Advanced Manufacturing Research Centre (AMRC)

About The Customer

The University of Sheffield Advanced Manufacturing Research Centre (AMRC) is a network of world-leading research and innovation centres working with companies involved in manufacturing of all sizes from around the globe. The AMRC has undertaken a number of historic CFRP and CFRP/metallic stack drilling trials in order to help industry develop economic methods of controlling drilling-induced delamination. Intellegens provides a unique machine learning solution for real-world experimental and process data problems in industrial R&D and manufacturing. The Alchemite™ deep learning software, based on a methodology that originated in the University of Cambridge, can model sparse, noisy data, where other machine learning approaches fail.

The Challenge

Laminated fibre-reinforced polymer (FRP) matrix composites are increasingly used in industries such as aerospace due to their excellent mechanical properties and highly-tailorable design. However, this tailorability can negatively impact costs, productivity, and sustainability during manufacture, especially in machining where FRP part-specific defects occur. Process uncertainties resulting in large, unpredictable defect generation are a common cause for prescribing overly-conservative cutting tool use limits, based on part quality criteria. Due to the wide array of tool designs and workpiece material configurations available, an application-specific approach is required to identify the most effective cutting strategies. Optimal cutting parameters can be found using an exhaustive, wide-boundary, DoE-based approach, with slow and costly testing required to identify absolute tool life limits. The challenge was to establish a novel machine learning-based method to predict tool life from start-of-life performance data, reducing experimental time and cost. The project was particularly challenging, because the original dataset was sparse, with 82% of the target data missing.

The Solution

Alchemite™, Intellegens’ novel machine learning software, leverages the unique insights of deep learning to build comprehensive models from sparse and noisy data. In this study, tooling time series data on 55 drill/composite pairs, recording 23 machining responses, including hole quality metrics and in-process measurements, was provided by the AMRC. This data was easily uploaded into the Alchemite™ Analytics software using its intuitive drag-and-drop interface. A deep learning model was trained on the tooling dataset. Despite the missing 82% of data, Alchemite™ was able to train a model with a high coefficient of determination of 0.73. This high accuracy was accomplished using the core Alchemite™ algorithm in combination with a variety of data pre-processing steps to reduce the inherent noise. These steps included data grouping and then aggregation. Although data from over 1,000 holes was available (a typical testing dataset), analysis showed that, with the right aggregation, 200 data points were sufficient to provide deep insight into a tool’s future cutting performance.

Operational Impact

By gaining insight from sparse data to quantify underlying, complex nonlinear property/property relationships, Alchemite™ created a tool-composite model with good predictive power. The ability to accurately predict exit delamination for some future number of drilled holes enables tool life to be estimated, and the impact of factors such as tooling geometry and material selection on this tool life to be studied. This can inform the design stage of an experimental campaign, ensuring that unsuitable tools are not unnecessarily tested and that only the most promising candidates are taken forward for more comprehensive tooling trials. Making useful decisions based on only 20% of the typically-acquired performance data allows progress based on far fewer tests, resulting in up to 80% reductions in the direct costs associated with testing, such as material wastage, machining and technician time, as well those associated with equipment maintenance and overhaul. The use of explainable AI tools in Alchemite™, such as the importance chart, enabled identification of variables that were irrelevant to predicting tool life performance, allowing additional experimental streamlining.

Quantitative Benefit

Reduced experimental time by quantifying complicated nonlinear tool-composite relationships.
Delivered useful predictions of future tooling performance from sparse and noisy data based on 80% fewer experiments.
Identified irrelevant features for predicting tool performance, facilitating further experimental cost savings.