Computed Tomography
Assembly Line
Nikon’s AI Reconstruction draws on Deep Learning to deliver faster, clearer CT scans
Nikon IMBU has released AI Reconstruction, an innovative 3D computed tomography (CT) reconstruction software solution powered by artificial intelligence that lifts the traditional trade-off between scan speed and image quality.
By applying Deep Learning techniques to enhance image quality, Nikon’s breakthrough technology enables rapid results and superior analysis. Traditionally, CT users have had to pick between fast, lower-quality scans or slow, higher-quality scans. If scans are quick, important details can be missed. If scans are slow, fewer items can be scanned.
AI Reconstruction lifts these limits through AI enhancement tailored to individual customer needs by Nikon’s Applications Engineering team. The Deep Learning modeling underpinning AI Reconstruction is trained to distinguish relevant information from the scan artifacts to effectively filter noise and improve clarity.
How CT Data Analysis is helping TE Connectivity Reach Their Ultimate Goal of End-to-End Quality Inspection
As impressive as interconnected digital-platform benefits are for traditional CAD/CAE/CAM disciplines, Computed Tomography (CT)-data analysis for quality inspection has greatly expanded its reach and purpose within today’s growing digital landscape. Its new influence on the central tools of design, simulation and manufacturing are significant; CT data analysis software is making these tools, normally used well upstream of it, even better in their roles.
“We are on target for a ten-day turnaround for design, simulation, scanning and producing a digital metrology report,” says Stokowski. “So much is now going on upfront. We want as much done as possible before we hold a physical part.” Volume Graphics has helped TE Connectivity in this frontloading and looping of data with their Adaptive Measurement Templates. The templates can classify, localize and segment defects using AI and Machine Learning. They also automate much of the scan analysis and then capture information for metrology reports. The goal at TE Connectivity is to lower analysis time from 10 days to five.
Large-Format Multitasking Simplifies Tube Manufacturing
For decades, the shop relied on two three-axis machines to produce the necks and threads for its tubes, but the machines relied on manual programming for each part, a time-consuming process that also required a wealth of experience for smooth operation. Loading and part flipping also proved difficult for these machines — after all, the tubes can range from seven to 42 feet long — with both operations requiring the use of a large crane. The difficulty of finding people to operate its machines and the lengthy downtime waiting for the crane became bottlenecks for FIBA. Amid increasing demand from companies in the space exploration, alternative fuels and electronics industries, the shop decided to invest in an additional machine that could bypass some of these issues. It found a suitable solution in the Soraluce FLP 14000 multitasking machine.