Researchers from IIT Kharagpur have developed a low-cost AI-based solution for real-time metrological inspection. The model consists of a low-cost imaging device and an AI-enabled software which can be deployed in the production line to check the quality of the jobs.
With this innovation, carried out by the Center of Excellence in Advanced Manufacturing Technology Department, the team hopes to make AI and ML-based solutions affordable to the industrial sector, especially the MSMEs.
What Does This Model Do?
The developed model is an innovative system that consists of a low-cost imaging device and supporting AI-enabled software that helps in getting instant results on the production line inspection. Notably, the AI software helps in enhancing the image quality taken by the low-cost camera and bringing it on par with a high-quality image. This image is then processed in real-time to give results. It also automates the acceptance or rejection of production jobs and delivers the outcome for real-time managerial insights.
Along with measuring the dimensional features of the production job, it can also inspect the presence of scratches, dents, etc. The total time taken for carrying out any such analysis by the model takes up to 12 seconds. The accuracy of the model is 98 percent, which has been guaranteed by testing it on different types of jobs. Next, the team is working on reducing the time taken for processing and analysis.
Explaining the benefit of this model, the lead of Centre of Excellence in Advanced Manufacturing Technology, Prof. Surjya K Pal said, “The MSMEs mostly rely on manual inspection of the jobs produced in a batch where a few samples are randomly selected and checked manually. Accordingly, the entire batch is either rejected or accepted, which lacks effectiveness and increases the cost of production. The potential of the developed solution can be leveraged to the inspection of each job in a batch, in real-time, and at a very minimum cost.”
The research group included Prof. Surjya K Pal, Prof. Debashish Chakravarty, research scholar Debasish Mishra, technical staff Pravanjan Nayak, and intern Ayan Banerjee. The team has filed a patent for the system and made it available for MSMEs to license the technology.
