Process Optimization with ML Closed Loop - Crosser Top 10 Smart Industry Use Cases

This video discusses process optimization by running optimization processes near data sources, crucial for enhancing machine or process efficiency in production environments. Using Modbus as an example for data acquisition, Crosser collects and preprocesses data streams, converting them into sliding windows. These windows are then input into a machine learning model within a Python environment, enabling the model to provide optimized settings. Outputs from the model are fed back into the machines using Modbus or other machine connectors, tailored for different industries like discrete manufacturing or process industries to optimize production yield, energy consumption, or resource use. This approach keeps data local, ensuring security and enabling low-latency operations, making it a widely adopted solution in recent years.
Watch the full video here to gain practical insights on implementations and benefits: info.crosser.io/webinar_Top-1...