pushing the boundaries of minds and machines GE
In machine-intensive industries, for instance in the utility sector (industries such as oil and gas, power, aviation, mining, or transportation)the operational assets are machines like generators, aircrafts, turbines, and locomotives, which require continuous data collection and monitoring for intelligent decision-making. In an era of automation, these industries that utilize mission-critical systems require highly accurate, real-time data management and monitoring applications to guide their day-to-day operations. As they collectively represent a sizable chunk of the global economy, one cannot ignore the impact of these industries on our daily lives.
How different is industrial data analytics?
Industrial data analytics differs from traditional data analytics in the sense that it needs to be deployed on running machines (both fixed and mobile) which are often at remote locations. Large volumes of data have to be collected, stored and analyzed at high speeds to make mission-critical decisions. Generally, cloud-based platforms work very well for these types of industrial analytics environments.
The new industrial big data technology wave has brought forth new ways of collecting and analyzing the industrial data load that leads to actionable insights. In most cases, data and analytics are synchronized in real time; so these systems require machines, sensors, software, data scientists, and engineers to work at tandem to get quick, actionable insights. This new information-based service has just set the stage for a new dawn in industrial revolution.
The big data platform comes at a time when hardware, sensor, and storage technologies have become affordable to businesses; so the new cost-benefit matrix is further driving the big data analytics wave across all industry sectors. Furthermore, employees stretching from the COO to the field technician are extremely mobile today, and are looking forward to an era of digitized operations in their work environment.
Role of GE in industrial data analytics
GE, the giant US conglomerate is at the forefront of this revolution, and has invested a big chunk of its research resources on creating software systems that are targeted to the industrial big data analytics market.
Lets take a look at an actual example of industrial analytics with big data in the transportation industry; where aircrafts or locomotives have to remain in motion for the majority of their operational lives. Here, the industrial big data platform must be able to transfer large volumes of data during a reloading or refueling interval.
In these cases, the communication between an operator and the analytics platform can occur only when the operator (mobile asset) has arrived at a certain destination. Where real-time, in-transit requirements apply for successful communication. Furthermore, a high degree of reliability is imperative when a critical event is detected during motion. In the case of an aircraft engine, the onboard intelligence must be able to immediately respond or react to a detected situation without any human interaction! Undoubtedly, critical events must be handled in real time; meaning that data communications must be managed efficiently to optimize the use of in-motion network bandwidths.
Industrial data analytics in the airlines
An in-flight aircraft engine can generate hundreds of tags every ten milliseconds, which may easily amount to 1TB of sensor data per flight. What generally happens is that an onboard analytics system for mobile assets transmits the essential tags to the operations center via satellite. So, the industrial big data platform has to be highly responsive to the real time, in-transit requirements of a mobile asset.
At an airlines analytics center, the data downloads may only take place a couple times a day. So, the analytics system at the airlines flight operations center or at an OEMs remote monitoring center should be capable of detecting and flagging anomalous information while it is being downloaded for further analysis. This real-time monitoring capability enables the airline to manage its maintenance functionskeeping its fleet on operational status as per plan.
Aircrafts are subjected to differing climatic environments during a flight, which results in mobile asset degradation in varying rates. For example, while flying through hot, sandy desertsthe fan blades of an aircrafts engine may degrade at a quicker pace than while flying through milder climates. Contrary to fixed assets, mobile assets have to be transported to a maintenance center before undergoing maintenance and reparations, which can complicate scheduling, inventory, and other requirements.
If youre interested in learning more about GEs role in tackling the airline industrys big data challenge, then click this link to review the publication that inspired this post:
The Case for an Industrial Big Data Platform Laying the Groundwork for the New Industrial Age