How SAS® Enables the Connected Factory
Connect disparate data sources in the era of Industry 4.0. Apply a combination of monitoring, diagnostics and predictive maintenance techniques to improve asset and product reliability, as well as lower the cost of unexpected downtime.
A holistic view of operations
- Remove barriers imposed by siloed operational systems and gain full visibility into what's happening on the shop floor and out in the field.
- Bring together the voices of the process, product and customer for a single, comprehensive view of both process and product quality.
- Integrate structured and unstructured operational data from sources across your business.
- Minimize unplanned downtime and increase the availability of key assets.
- Maximize overall equipment effectiveness (OEE).
- Increase return on assets (ROA) while reducing maintenance costs by shortening the mean time to repair (MTTR).
- Avoid rush parts deliveries, repair overtime payments and high buffer stocks.
Early warning of potential issues
- Apply quality-specific data models and patented analytics to drive early warning of emerging quality and reliability issues, data-driven root cause analysis and deeper process understanding.
- Help predict potentially catastrophic equipment and process incidents.
- Quickly identify design and production defects before they become widespread.
- Start small from one use case for a specific asset and grow in analytics maturity, number of use cases applied and scale of deployment for a smarter, more connected factory.
How does one of the world’s largest hard disk drive suppliers identify potential failures early in the production process and avoid yield excursions?
SAS helped Western Digital:
- Monitor equipment sensors and tag machine-to-machine data to identify hidden patterns that predict failures.
- Predict yield excursions and reduce losses caused by the production of defective devices.
- Lower the overall number of returned units, which in turn boosted customer loyalty and trust.
How does one of the world's leading companies in health care use analytics to improve uptime by automating laboratories?
SAS and partner mayato helped Siemens Healthineers:
- Develop a predictive service and maintenance solution based on the SAS Platform to increase system availability and reduce service costs.
- Optimize workflow and clinical performance by transporting samples along a bidirectional magnetic conveyer belt and tracking every sample with a multicamera vision system.
- Ensure that throughput is uninterrupted and productivity remains as high as possible.
How does the OEM of C-130 aircraft use machine learning to transform predictive maintenance for complex equipment?
SAS helped Lockheed Martin:
- Use artificial intelligence, IoT and advanced analytics to predict when parts will fail, keeping more aircraft airborne for vital missions worldwide.
- Reduce data cleanup times by 95%, allowing the company to quickly produce results that it believes will reduce downtime and cost for customers.
- Learn from its collective maintenance history to form a real-time best practice for aircraft maintenance.