MICROSCOPIC DEFECTS: 99% ACCURACY WITH AI AND ROBOTICS

Orthopedic implants manufacturer

Our client is a multinational company specializing in the design, production and marketing of a wide range of orthopedic implants. They also manufacture devices designed to guide doctors during semi-robotic surgery.

Orthopedic implants manufacturer

Industry

Health

Service

ARTIFICIAL INTELLIGENCE (AI)

CHALLENGE

As is it usually the case with the pharmaceutical and medical industries, the products are subjected to rigorous quality standards and numerous audits and must therefore be free of defects that could compromise medical procedures.

However, these defects are often very difficult to spot because they are microscopic (sometimes less than one square millimetre) and vary greatly in appearance. Scratches, stains or black spots, for example, are never identical from one product to the next and require exhaustive verification to avoid recalls or incidents.

The company previously performed their quality control manually, an inefficient method that allowed for a high error rate.

SOLUTION

Vooban's main task was to develop an artificial intelligence model for defect recognition. This is a supervised model, which detects and categorizes all possible anomalies on a given product.

Meanwhile, we also developed the user interface and the web app where all the product images are listed. This interface allows the company to monitor the quality assurance process and adjust their tolerance thresholds for anomaly detection.

Vooban also helped the company with the cobotics for factory handling. In a sterile room, the UR5 robot inspects the parts by itself, classifying them according to their quality level. To do so, it uses a vacuum gripping tool to move the parts without damaging them, thus providing a complete handling and defect detection solution.

RESULTS

99%

As of today, our detection model exceeds FDA standards and performs at more than 99%. This mean less than 3% of false rejects, an incredible result for an industry where the detection of anomalies is so vital. A project of the like is perfect for the medical industry, where there is a lot of compliance required for product distribution and where defects are often minuscule.