Big Data and Analytics is the science of examining raw data with the purpose of drawing conclusions about that data and transforming the conclusions to actionable information. Data analytics is used in many industries to allow companies and organizations to both verify or disprove existing models or theories and make better business decisions. Data analytics focuses on inference, the process of deriving a conclusion based solely on what is already known by the researcher.
The current technology advances in sensors and the ability to collect massive amounts of data have created huge opportunities. Our focus for Big Data and Analytics has been Engineering, Manufacturing, Services and Finance for Fortune 500 organizations. Our largest successes to date revolve around engineering field services for large complex high cost equipment sets. We are also working in the area of edge computing with a research organization.
The majority of the Big Data work we have been involved in revolves around equipment performance data. This data is collected either from machine data directly taken from sensors or from machine performance logs. Sensors take machine readings on flow, pressure and temperatures. Machine performance logs capture information such as unplanned outages and parts replacement information. These logs can have data intervals in the magnitude of seconds, resulting several million rows across the fleet for a given day. The data is extracted and cleansed to ensure data veracity. The data is placed in a repository where it is integrated with other machine data and aggregated to give a full picture of daily performance. The current Data Lake contains both structured and unstructured data. Statistical analysis and representation of the data occurs to search for patterns. Statistical models are developed and run against the data and the results are interpreted.
The asset performance management capabilities of Big Data and Analytics have basically eliminated the need for corrective and preventative maintenance and allowed organizations to move toward predictive maintenance. The ability to see products as they are used in the field are essential to the core concept of the “Internet of Things.” This has resulted in higher uptime, better coordination of equipment service and lower total cost of operations for large original equipment manufacturers and their customers.