AI-powered 5S boarD

5S tool boards empowered with machine vision AI neural network to control tool availability, such that no item can be check-out or missed from its place in a workshop. The software solution is spun to other industries requiring object recognition on-a-fly.

A manufacturing company formulated a rather innate problem, suffered by any workshop or a lab: missed tools problem. In LEAN manufacturing approach, such problem is circumvented by using 5s visualisation boards. However, in spaces with access to multiple users 5s boards typically fail to keep tools in its place.

EnCata’s AI team suggested to move further and add machine vision (MV) to 5S boards, helping to control the presence of tools on its place. EnCata’s developers created an artificial neural network (NN), which was able to capture the live image from the camera, hanging above the 5s board, and compare the ‘missing tool image’ to the fully equipped board. The NN went thru supervised learning routine of image recognition, taking into account camera lens distortions.

Now any user, taking a tool from the 5s board had to either check in the taken item (via QR code scanning). In case when any tool is taken from the board without checking it in, an ‘Andon’ signal makes a sound+visual alarm. The neural network recognised all the objects/tools on the 5s board and understands which tool is missing, enabling dual control of the items displacement.

The client in particular, received a very powerful solution for their workshop, tremendously reducing time for items searching. Developed AI-based solution enables a plethora of other applications involving object recognition. The manufacturer further plans to couple the MV software with its inventory management system by using the NN to recognise inventory Kanban stock and create an automated alert for component procurement.