DICA Electronics Ltd is deploying AI decision-support tools to reduce manufacturing quality escapes and gather key data from manual processes to help speed root cause analysis. Pleora’s Visual Inspection System uniquely requires just one image to start using AI, with continuous and transparent training based on operator actions to improve and speed automated decision support.
DICA provides high quality electronic assembly services for industrial controls, telecom, security, and digital imaging applications. The manufacturer uses AI visual inspection to help operators detect errors, such as incorrect components and orientation, solder defects, and through hole issues, for unique component types, assembly steps, and custom low-run products where automated optical inspection (AOI) is too complex and expensive.
“Pleora’s Visual Inspection System provides a ‘second set of eyes’ for our human inspectors,” said Steve Vaughan, Vice President, Operations with DICA. “Human visual inspection is a key component of our manufacturing processes, and Pleora’s system helps our operators make consistent and reliable decisions to ensure we always deliver to the quality standards expected by our customers.
The Visual Inspection System is a camera-based solution with integrated Inspection and Tracking & Reporting apps that are easily trained on a manufacturer’s unique products and processes.
With just one good image, Inspection apps for incoming, in-process, and final quality control steps automatically compare products to a “golden reference” and visually highlight differences and deviations for an operator. As the operator accepts or rejects potential errors, the AI model is transparently trained based on their decisions.
After even just one inspection, the AI model will start automatically suggesting a decision for the operator. Over time, the speed and accuracy of automated decision-making will improve as the system continuously learns from operator preferences. In comparison, most AI inspection tools require numerous good and bad images plus time-consuming and expensive algorithm development before they can be deployed in production.
Integrated Tracking & Reporting apps include automated and customizable reporting tools to provide data and insight on manual tasks. Typically, collecting actionable data from manual processes is a challenge for manufacturers, making it difficult to ensure end-to-end quality and implement process improvements when errors do occur. With Pleora’s system, manufacturers can collect and save data on the number of suspected and confirmed defects, add operator notes on detected issues, and store product images for traceability, inventory & shipment management, and batch tracking.
“When something goes wrong, data from manual inspection processes helps speed investigation so we can prevent future mistakes,” said Mr. Vaughan. “Recording and saving images of visually inspected products has saved us considerable time when an in-field issue was reported. With Tracking & Reporting we could verify that a good product left our facility, and pinpoint a downstream issue that was impacting quality for the customer. Without data, resolving these types of issues can be a long and complicated process that costs both our company and the customer time and money.”