Superior quality batteries for your professional devices
For all your battery needs please contact H-squared on: Telephone: 01462 851 155 Email:
sales@h-squared.co.uk
addresses this by generating simulated data using techniques like Generative Adversarial Networks (GAN) and Convolutional Neural Networks (CNN). This simulated data enhances the training process, allowing manufacturers to develop stronger inspection programs that ensure quality, even with limited real-world data.
Another significant AI application is process optimisation through
machine-to-machine communication. Traditionally, the SPI machine would inspect solder paste deposits and provide a simple pass/fail result, which an engineer would manually review to adjust the screen printer. Over time, the process evolved to include real-time data collection and analysis, enabling engineers to make informed adjustments. Now, the SPI and printer communicate directly, with the SPI analysing solder paste deposits and automatically adjusting printer settings such as speed, pressure and offset. This continuous optimisation ensures peak performance without operator intervention, a concept known as the Koh Young Process Optimizer (KPO). This capability also extends to mounter-to-AOI communication, further enhancing process efficiency.
“
The most substantial benefits will come from the first 90 percent of automation, with the final 10 percent being the most challenging and resource-intensive. Over the next decade, AI will continue transforming manufacturing.
The Future of AI in Manufacturing Looking ahead, one AI application with significant potential is mounter diagnosis. This capability is especially valuable for manufacturers deploying pre-reflow AOI systems, despite the associated costs. Mounters are complex machines with numerous variables that can cause faults, from the head and nozzle to the feeder and reel. Manually diagnosing these issues can be time-consuming and error-prone. However, applying AI to real-time production data
”
allows manufacturers to quickly pinpoint the root cause of a problem. For example, AI can identify that a specific nozzle needs replacing or a particular feeder requires maintenance, allowing rapid intervention and minimising downtime.
This predictive maintenance approach improves efficiency and reduces the likelihood of costly breakdowns. As AI evolves, we can expect even more sophisticated diagnostic and optimisation tools to become available, further enhancing smart factory capabilities.
Implementing AI in Manufacturing AI is no longer a passing trend; it is a reality already making a tangible difference in the electronics manufacturing industry. While the journey to a fully autonomous factory may be long, the advancements we have seen are promising. AI offers unprecedented opportunities to enhance productivity, reduce errors and streamline processes. Just as we would not revert to calculators from abacuses or CAD from paper and pen, we should not fear AI. Instead, we should embrace its potential to alleviate the most manual, skilled and time-consuming tasks in manufacturing, allowing us to focus on innovation and growth.
OCTOBER 2024 | ELECTRONICS FOR ENGINEERS
21
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54
