The objective of this research was to work with industrial partners to develop and apply innovative and intelligent improvement to their production processes in order to achieve a higher level of productivity and quality while lowering cost.
Two projects were completed and are discussed in this work. The first project was focused on improving tooling in a milling process of high value parts by varying coatings and geometries of the tooling. The second project involved implementing statistical process control (SPC) using control charts and process capability metrics through customized software.
In the first project, the industrial partner was experiencing rapid wear of tools when milling NiCrMoV steel. A detailed material characterisation study revealed the likely cause was the presence of un-tempered martensite having high hardness. Cutting tools were then chosen to compare the performance of tools with varying rake angle and coating; where all other geometry/features were identical. It was found that the best performing tooling had a relatively more aggressive rake angle at 16°, and a PVD coating consisting of TiAlN + Al₂O₃ + ZrN; showing a tool life 300% greater than the baseline tooling. Inspection of the worn tools by SEM, EDX, and Raman spectroscopy revealed that the Al₂O₃ and ZrN coating layers detached long before the failure.
In the second project, software was developed collaboratively with an industrial partner for a CNC turning process. The process was semi-automated, and used 100% inspection of parts. Part measurement data was recorded by the software, allowing for SPC to be applied to identify common-cause sources of variation. The software was then able to make offset recommendations in real-time to correct for variation. Providing process history for quality assurance (QA) also allowed for identifying of several areas for improvement in the process which were corrected, considerably reducing variability.