Gopal GopalKrishnan has held several roles at OSIsoft and has been working with the PI System since the mid-1990s in software development, technical and sales support, and field services. Attached to the Philadelphia office, he is currently a Solution Architect in the Partners & Strategic Alliances Group. Previously, he was a Product Manager with a focus on Enterprise and Asset Integration and PI Data Access.
Gopal has a master's degree in Engineering, continuing education in business administration, and is a registered professional engineer in Pennsylvania. He is also active in the MESA Technical Committee and the MESA Continuous Process Industry Special Interest Group, and active in topics such as data mining, data science & machine learning, energy efficiency, manufacturing intelligence, sustainability, including green initiatives in facilities and data centers.
With the explosion of data, it is no longer efficient or cost-effective to use conventional methods for accessing silos of data. It takes the PI System to connect disparate sources of sensor-based time-series data and deliver the right information to the right people at the right time in the right context.
Through a single infrastructure, companies can transform their business.
As businesses expand into sensor-enabled equipment, more assets are streaming more data – increasing the need for and value of the PI System.
OSIsoft has installations in 127 countries and is widely used across manufacturing, energy, utilities, pharmaceuticals, life sciences, data centers, facilities, and the process industries, as well as the public sector and the federal government. OSIsoft is headquartered in San Leandro, California, with offices around the world.
Industrial IoT time-series data engineering - a layered approach to data quality
Data quality is a foundational prerequisite for data engineering in your digital transformation and data science/machine learning initiatives. Join us in this session for a “how-to” on getting started and implementing a layered approach to data quality with the PI System, such as:
- PI System Monitoring
- Simple analytics to validate (individual) sensor data streams
- Simple analytics to validate at an equipment level (several related sensors)
- Advanced (multivariate/machine learning) analytics to validate at a functional equipment group (FEG) level - tens or hundreds of sensors
- Advanced (connectivity model based) analytics - data reconciliation with mass/energy balance (one or more process units)
Whether it is an individual sensor (pressure, temperature, flow, vibration etc.) an individual piece of equipment such as a pump (with a few sensors), a functional equipment group (FEG) i.e. a feed water system (made up of a group of equipment like motor/pump/valve/filter/pipe assembly), or an entire process unit or a plant – the scope of data quality requirement has to be understood in its usage context. And, with streaming industrial sensor/IoT time-series data, a layered approach to data quality gives you the flexibility to apply fit-for-purpose techniques mapped to use case requirements.
We will review the basic validation checks for missing data (I/O timeout), flat-line data (sensor malfunction), out-of-range data, etc., and issues in source instrumentation/control system, network connectivity, faulty data collection configuration (scan rate, unit-of-measure, exception/compression specs), etc. We will also cover advanced analytics, including machine learning and data reconciliation with illustrative use cases.
Thursday, October 22nd, 12:45 - 13:15 (UTC -5)