End-to-end data engineering process, including data quality audits and error remediation, integrations across disconnected data systems, and automated pipelines.
Analytics and ML layers built on top, enabling real-time KPI monitoring, deep-dive diagnostics, root cause analyses, and machine learning forecasts embedded into existing systems.
- Built on sheet-metal fabrication shop's data records (ERP, MES, QMS, Materials, HR)
- Cleans production, inspection, and material data records, integrates data source systems, and builds automated data pipeline flow
- Analytics diagnostic report details operating conditions that drive elevated defect rates
- KPI dashboard provides real-time view of defects and scrap costs
Downtime, OEE & Machine Health
- Built on precision machining shop's data records (MES, IIoT sensors, CMMS, ERP, HR)
- Cleans production, machine, and maintenance record data, integrates data source systems, and builds automated data pipeline flow
- KPI dashboard provides real-time monitoring of OEE and downtime, across the fleet and by machine
- Analytics diagnostic report details drivers of lost OEE by machine
- ML model forecasts machine health indicators, embedded into CMMS system
- Built on precision machining shop's data records (ERP and machine-monitoring sensors)
- Cleans ERP data records, integrates data systems, and builds automated data pipeline flow
- Job costing and margin analytics embedded into ERP system
- Analytics diagnostic report details job margin distributions, job cost overruns vs. estimates, and jobs that lost money
Brian Davis. Data engineering and applied analytics/ML for manufacturers. Other work: github.com/bmdvs.