October 17, 2016

Industrial IOT + Machine Learning + Mech Eng + Elec Eng + Instrumentation Specialization + Maintenance Programs + Business Analysis = IIOT Success!

In working with clients across the Oil & Gas, Utility, Engineering, Manufacturing, Maritime and Chemical Processing spaces there is one thing in common. They’re all trying to find ways to better service their clients, reduce downtime, reduce maintenance cost, drive new revenue streams and increase profits.

Neither the customers or their current partners are gracefully marrying up Industrial IOT Data Sciences + Machine Learning + Mechanical Engineering + Electrical Engineering + Instrumentation Specialization + Maintenance Programs + Business Analysis.

There are few different areas where this is relevant for the market today. As example, predictive maintenance is vital in the Industrial IOT space. Making sure assets are running at optimal levels can greatly reduce operational expenditures which in turn can save companies tens of millions of dollars each year. There are a number of metrics that goes into using an Industrial IOT platform to enable better predictive maintenance programs. They might include industrial gateways, mini PC’s, sensors, cameras and other equipment that would plug into the systems being monitored. The end game is to understand when a piece of equipment might fail before it actually does. Some companies have a time based maintenance program but the problem with this is that the machine might be being abused and not being ran at optimal levels.

This could cause the machine to break down long before the maintenance intervals are being met. On the other hand the machines might be able to continue to operate at their optimal levels long after the recommended maintenance periods which could greatly reduce cost to maintain the machines. For example, oil and gas companies work on scheduled maintenance programs for their Top Drives, rotating equipment, turbines, compressors, etc. but if an Industrial IOT platform can provide deep insights on the actual condition of the machine then based on spare parts refurbishment via algorithms predicting when a failure will occur vs. timed events then the companies can most certainly reduce their maintenance cost. 

If a company is streaming data from sensors and industrial gateways they can with better accuracy access current machine conditions and even be able to get alerts to warnings via algorithmic signals which could tie into maintenance programs like SAP, Maximo or Oracle. By providing maintenance based programs with an Industrial IOT platform these companies can then trigger an appropriate maintenance event or process which would then make the entire process dynamic with a much better way to automate the maintenance process. 

Of course this would provide cost savings over a time based maintenance program. Other benefits of this type of program would allow for increased equipment life, increased productivity, reduce exposure to mechanical failure risks, reduced exposure to safety risks and of course reduced downtime. This methodology is pretty much the same across multiple industries including oil and gas, utilities, engineering, heavy equipment and heavy construction, chemical process plants and other industries. 

What is apparent is that a lot of companies and service providers have not figured this out yet. They are still working with aged condition based monitoring systems or have rolled out systems that only specialize in certain areas of their business. 
Business leaders would like to see an Industrial IOT system that can incorporate all these multiple data streams and give them a 360 degree view of their operations.

October 3, 2016

3 reasons why IOT digital intelligence matters for Microgrid


A real transformation is happening in the grid. With the digitization  and innovative energy technology catching up its now possible to economically generate power from Microgrid. Microgrids are beginning to emerge  in residential communities, office park, university, military base etc. This has been accelerated by a number of local and global factors converging together – government regulations/incentives, energy consumers are becoming more concerned about their local power quality and efficiency of system. Industries and businesses have been economically impacted by local brownouts which are a  nuisance  In this context IOT and digital intelligence plays a major role for solving some of these problems. In this whitepaper we cover 3 reasons why IOT digital intelligence matters for Microgrid.

Reason-1: Prosumer Intelligence

The foundational building block of a Microgrid is the prosumer. A prosumer consumers energy and contributes to the energy grid. If the prosumers behaviour is modelled at a fine level of granularity a lot of Microgrid risks are mitigated. For example in Cerebra while algorithmically scoring prosumers behaviour it takes into account 4 distinct factors

  •           Quantity of contribution
  •          Quality of contribution
  •          Predictable regularity of the contribution habits
  •          Quantity of consumption
All of this is modelled using instantaneous power, current and voltage parameters typically at 15 min intervals or lower collected by the MDM Systems. This algorithmic prosumer can drive surgical actions to stabilize Microgrid outcomes and impact the overall economics

Reason-2: Microgrid Assets

A Microgrid consists of a variety of assets which are configured and orchestrated to deliver localized power. This could Local low-voltage (LV) and even medium-voltage (MV) distribution systems Distributed energy resources (DERs, e.g. micro turbines, fuel cells, photovoltaic), Storage devices (flywheels, energy capacitors and batteries) in order to satisfy the demands of energy consumers. Each of these assets can be diagnosed from a health perspective by deeply examining the digital IOT sensor data which are collected in SCADA/Historian systems and traditionally the signals are unexamined. Cerebra’s signal detection algorithms can forensically surface asset signals which reduce down time and enhance asset life.

Reason-3: Economics

At Flutura we have a simple formula

Prosumer behaviour intelligence + DER Asset intelligence = Microgrid economics

By carefully examining grid contribution signals in the instantaneous parameters coming from MDM systems and the asset stability signals from SCADA/PLCE sensor streams, the operator can dramatically impact the economic viability of executing a Microgrid.

Closing thoughts

Microgrids is one of the models for an alternate energy future. The economic viability of Microgrid operator is directly correlated to the Digital intelligence maturity. This calls for a comprehensive IOT digital implementation strategy for microgrids which ingests sensor, meter and ambient weather data to dramatically impact and guarantee asset stability/contribution behaviour.  Flutura with its next generation IOT intelligence platform tuned to Microgrid use cases combined with its strategic relationship with Electric Power Research Institute (EPRI – Palo Alto & Orlando) is ideally positioned to intercept the future.