Naacam Show to offer a platform for machine learning specialist

1st March 2019 By: Mc'Kyla Nortje - Journalist

Naacam Show to offer a platform for machine learning specialist

ARTIFICIAL INTELLIGENCE AI is used to optimise processes in the automotive assembly process

Cape Town-based machine learning specialist DataProphet cofounder and CEO Frans Cronje says the association of automotive component and allied manufacturers (Naacam) Show will act as a platform to showcase its work.

DataProphet chief technology officer Dr Michael Grant will present at the event on the future of automotive manufacturing, followed by a technical demonstration of the company’s OMNI artificial intelligence (AI) solution on March 13. The event will be held in Durban, Kwazulu-Natal, at the Durban International Convention Centre, from March 12 to 14.

OMNI optimises control parameter settings and is aimed at achieving zero defects in the manufacturing process. Using advanced predictive and prescriptive machine learning capabilities, as well as state-of-the-art computer vision, OMNI can predict defects, faults and quality errors, and prescribe the ideal process variables to shift processes to higher yields.

Cronje tells Engineering News that two DataProphet solutions have successfully been implemented in the automotive assembly and manufacturing industry – OMNI – for optimised parameter control settings, and OMNI Vision – for quality inspection. The show will enable DataProphet to meet industry key players who are interested in this type of technology. “The show is a good platform to get our name out there; the exposure we can get out of such an event is key to our growth and expansion,” adds Cronje.

He points out that, currently, AI is used to optimise processes and make them more efficient, for example, robotic stud welding, spot welding and laser welding in the automotive assembly.

However, a challenge for DataProphet regarding AI is that manufacturers still struggle with interpreting AI correctly, “and is often confounded with business intelligence or other software tools”, adds Cronje.

Another challenge is that the fear of the unknown is prevalent, with companies remaining reluctant to adopt the technology.

But, Cronje says the automotive manufacturing industry is innovative and continuously striving for improvements in quality, using various machine learning techniques to prove the value of this novel application of AI with tangible results extends the field with great success from academia to practice.

“The application of deep learning to the automotive industry and manufacturing as a whole will improve the quality of products by modelling subtle dependencies between production parameters at different stages of the manufacturing process.”

Additionally, it will enable manufacturers to better understand the effects of controllable parameters on their various quality-control metrics, and to adjust their production processes in an informed and targeted manner to minimise scrap and defective products.

DataProphet helps to determine the extent to which these solutions will assist in understanding the many problems facing the industry.

DataProphet expects good attendance at the show, and that “Industry 4.0 will be one of the main topics of discussion”, says Cronje, adding that the DataProphet team is also “looking forward to having some great conversations around AI and how it will improve the automotive sector”, concludes Cronje.