Objective:

• To improve the transfer efficiency of robot painting.

Desired Outcomes:

• To improve efficiency by 30% through optimisation of the robot programme and spray parameters using vision system based AI/ML logic:
• The vision system fitted on the robot scans the painting jig and captures the image of the parts to be painted.
• Robot path to be generated using AI/ML algorithm based on the image data captured by the vision system.

Current Limitations:

• Two-wheeler parts are painted using a robot painting process, with the parts moving on a conveyor.
• Robot programme and spray parameters are developed by trial and error process based on the shape of the parts to be painted.
• It is an iterative process of modifying robot parameters and checking the paint film built on the parts after baking.
• This results in lower paint transfer efficiency – paint transfer efficiency is the ratio of paint deposited on the part to the total paint sprayed.
• Transfer efficiency for parts is measured by weight method, i.e. weight of the paint on the component to the total paint sprayed from the robot gun.
• The above process is highly skill-oriented (a skilled robot programmer is needed)
• Wide variety of parts to be painted in a single paint plant.
• Robot programmes cannot be optimised for each type of part, as it is a manual process of creating the robot programme.
• Trials and verification are time-consuming as paint thickness can be checked only after parts are baked in the oven.
• High skill requirement for engineers carrying out robot teaching for the painting process.