SITUATION / Business REQUIREMENT / CHALLENGE

Impact to the “zero waste” ambition articulated by the Operational Excellence Oversight Group (OEOG) implies that no process should fail due to data defects – without high quality data, automated processes fall over, require rework or lead to wrong outcome. This is directly applicable to the Proactive Technical monitoring process being executed efficiently so that we realize our fit for the future ambition. Missing data leads to gaps in our surveillance process globally and in the assets.

OUR STRATEGY

• In-house Data is modelled in a hierarchy based on criticality, units/production area and in which surveillance work processes PI Tag is used.
• Running the PI tags against deviation detection algorithms specifically curated to adhere to following five key Business rules checks. – Bad Data, Stale Data, Flatline Data, Out of Range Data and No UOM Data
• PI DQ is the incorporation of people and technology with processes and workflows to limit loss of data availability and data completeness events
• It encompasses getting the data from its source, executing data quality checks based on business rules and converting it to a form where we can understand it (Dashboard) and ensuring it is used in our decision-making process.

RESULTS DELIVERED

• Efficiently replicate value adding technology solution based on a master data that contains all identified critical data elements at the assets
• Prominently visualize calculated data quality status in standard data platform.
• Identify and remediate data quality issues well before embarking on digitalization opportunities (e.g., advanced analytics, exception-based surveillance, technical monitoring) to make informed business decisions and create value out of asset data

Estimated Value Generation in USD: 18M USD savings in terms of Process improvement and people’s productivity
Business Feedback : Product has been flexible in adding new functionalities and improvisation in UI