Flexometal

The challenge

Flexometal is a leading company in steel tube manufacturing, with a 10-year track record in the market. During this time, they have consolidated a highly qualified team and are committed to meeting their customers' needs with efficiency and speed.

Despite their success in steel tube production, Flexometal faced difficulties in inventory counting. The manual process, which involved using plastic tubes, generated errors and delays in delivery times. Human errors were frequent, causing delays and the need to allocate more resources to ensure each order was delivered with the correct number of tubes within the stipulated time.

The solution

When iNBest approached Flexometal, we understood their needs and performed a thorough analysis of improvement opportunities. We proposed an artificial intelligence-based solution using Computer Vision and Machine Learning. This solution would overcome the inventory counting challenge, reducing errors and significantly accelerating delivery times.

For the development of this solution, the following Amazon Web Services (AWS) were used:

Amazon Rekognition: Used for recognition and analysis of steel tube images.

Amazon EC2: Used to host and run the Computer Vision application developed by iNBest on AWS infrastructure.

We developed a tool using Amazon Web Services (AWS) technologies. With this tool, simply by capturing an image or photograph of the tubes, whether for fulfillment or in the warehouse, it is possible to determine with 99.9999% accuracy the quantity of tubes in a matter of seconds.

Results

• 99.9999% accuracy in inventory counting
• Significantly reduced delivery times
• Better inventory control reflected in MRP system
• More reliable purchase planning and cost reduction