Manufacturing settings are one of the most promising openings for Hadoop big data analytics, as a flood of sensor data and inputs from other automated processes can help provide insights on everything from potential fabrication errors to assembly line inefficiencies. A recent EE Times article profiled some of the ways manufacturers such as AMD and Samsung have implemented Hadoop platforms to create workflow improvements.
"In the past, raw manufacturing data from sensors was merely streamed to a passive data warehouse, which was only consulted by employees when problems arose – to determine what caused the problem – or to produce off-line reports about the efficiency of past manufacturing runs," EE Times contributor R. Colin Johnson explained.
Using a Hadoop implementation, AMD has been able to cut the work of employees checking semiconductor wafer quality data by 90 percent by catching faulty product batches earlier in production. Similarly, Samsung's use of a Hadoop file system for handling its data warehouse made analytics processing 10 times faster on 75 percent as much computing power, even as data sets grew 10 times larger.
Each of these users deployed Hadoop in conjunction with existing Microsoft tools. Hadoop-Microsoft integration is set to improve further with the introduction of the Hortonworks Data Platform, which offers Hadoop to Windows users. As accessing big data analytics functions becomes simpler due as user-friendly tools become available, businesses can tap into the same types of efficiencies Samsung and AMD found in their manufacturing environments.