- October 07, 2020
Dataprophet PRESCRIBE uses advanced predictive and prescriptive machine learning capabilities to predict defects, faults and quality errors, and prescribe optimum control parameters to improve production. The solution, which is already in use in multiple Tier 1 US automotive suppliers, can be integrated into a manufacturer’s existing data environment in as little as four to eight weeks.
PRESCRIBE ingests and analyses process and quality control information from databases, spreadsheets, streaming sensors and PLC sources, and can record up to a thousand data points a second. State-of-the-art machine learning models are able to learn from this data to identify optimal control bounds.
To enable process change, PRESCRIBE provides operators with an easy-to-use web-interface. It helps operators to identify when operational parameters have exceeded the target control bounds and prioritises the changes required to optimize production and reduce scrap. Access to the web-interface can be strictly controlled, limiting features, reports, and parameter access accordingly; while client manufacturing and application data is housed in a fully isolated database for maximum security.
Additional features allow users to compare reports across different time periods to ascertain if process changes are being actioned correctly, as well as explore reports across different steps in the manufacturing process. Users are also able to filter uncontrollable and optimized parameters to focus on critical changes that need to be made and search for parameters crucial to a particular piece of equipment or process change.
Frans Cronje, CEO at Dataprophet, commented: “Traditionally, process control changes are reactive and rely on coordination across a changing team of process engineers, operators, plant managers and support staff. Involving so many stakeholders means this process can take weeks or months.
“However, real impact is only achieved with pre-emptive action because real-time is often too late," Cronje continued. "Our state-of-the-art machine learning models combine process data and quality control measurements from across many data sources to identify optimal control bounds which guide teams through every step of the process required to improve efficiency and cut defects. Using DataProphet PRESCRIBE, teams work faster, operationalizing processes changes, and diagnosing new ones.”