OWith the latest developments in artificial intelligence (AI) technology incorporated into modern cloud platforms, integrating AI into business processes is no longer an expensive or time-consuming process. Automotive industry leaders are showing a rapid approach to innovation, deploying an application of AI in the manufacturing production line.
“As an example of the efficiencies that AI can introduce, consider production line workers and engineers who manage reject rates in the pulley assembly process. Previously, this was a manual multi-step process,” confirms Paul Bouchier, Director of Sales at iOCO, at iOCO Software Distribution, an Infor Gold Partner.
“Now, thanks to AI-based anomaly detection, the process is radically changed, as machine learning actively checks every 10 minutes by processing millions of sensor data records from the Internet of Things. (IoT) on the pulley assembly production line for a potential increase in the reject rate. By suggesting the root cause of the failure, workers can quickly solve the problem in the production line. In practice, with the ‘IA, Automotive Leaders Record Lowest Levels of Rejection Rates Than Ever Before.”
The accuracy and speed of the AI models are based on two years of production line and machine sensor data fed into the Infor Data Lake and used to train the machine learning (ML) model to observe when the pulley tightening process falls outside the normal behavior, increasing the rejection rate.
“In practice, we have seen 99% faster fault detection and diagnosis (from one day to 10 minutes), lower rejection rates and improved overall equipment effectiveness (OEE) and use of assets. As a result, better products are delivered, and these pass quality checks on their first pass. This then leads to reduced scrap and rework of parts, allowing its customers to meet orders on time even more consistently,” adds Bouchier.
Creating industry agility, AI applications can scale quickly and easily, across multiple production lines and factories. Additionally, OEE is the gold standard for measuring manufacturing productivity. For example, an OEE score of 100% means that only the right parts are made as quickly as possible, with no downtime. In OEE parlance, this means 100% quality (only good parts), 100% performance (as fast as possible) and 100% uptime (no downtime).
“Measuring OEE and asset utilization is a manufacturing best practice for gaining important insights into the systematic improvement of the manufacturing process. Now, AI provides built-in business intelligence and reporting dashboards to track rejection rates, OEE, and other key performance indicators (KPIs) in real time. This reduces the manual burden, simplifying and automating the reporting and self-service process,” concludes Bouchier.