Smart companies are saving millions of dollars on their industrial assets using big data to predict and resolve problems before they even arise. That means lower maintenance costs, higher efficiency, more uptime and less unplanned outages. But to get the most out of big data, you have to look for it in the small places.Read more
Systems that were meant to keep the process in control and inform operators of deviations, at BP Refinery in Texas City (1) and Texaco Refinery in Milford Haven (2), were incapable of their basic task. As a result the operators in one case were given faulty alarm information whereas in the other case operators were flooded with too much alarm information not allowing timely response. It was very difficult for the operators to be aware of the situation that was developing. Read more
Why is Citizen Data Science a driver for better IOT and CEP solutions using Operational Intelligence?
It’s interesting to see how emerging technology has changed in just 5 years. Specifically the term ‘Citizen Data Scientist’, a person who creates or generates models that leverage predictive or prescriptive analytics but whose primary job function is outside of the field of statistics and analytics, has become an Innovation Trigger (more on this by Gartner and Forbes).
IIoT endeavors – Proof of Concept, Proof of Value – are often uncharted territory for organizations. This either because data is unlocked from assets where no-data has been before or because the organization is going to trial new methods of service/product delivery where no other organization has gone before. This all sounds a bit trekky, but deep down the innovative nature of many IIoT endeavors can also be havoc to its result.
An important, crucial, aspect in IIoT applications is the communication layer. This layer is responsible for relaying sensor values from the field to northbound processing of this data and the southbound control.
In my previous blog I concluded that IIoT is reality, but headaches are ahead choosing the right protocol and communications provider, especially when your IIoT solution requires long-range support, will be deployed in multiple countries and needs cross border coverage. Read more
Most of you have seen the term IoT – Internet of Things – presented at webinars, seminars and conferences. If not, you have probably read-up on one of the thousands of articles, market reports, blogs et cetera on the topic. Rest assured this post is not about IoT but covers its less known ‘brother’: the Industrial Internet of Things (IIoT). Read more
The purpose of Predictive Maintenance Programs (PMP) is to prevent/reduce unscheduled outage of equipment. The direct business benefits are in: reduced maintenance costs; reduction of breakdowns; and the reduction of maintenance time spent. Benefits that are tempting … but not all your equipment is ‘eligible’ for a PMP.
Predictive Maintenance is all about predicting failures, to critical assets, in a timely fashion to allow for repair/replacement without too much or no upset(s) to production/processes.
The business case for running a Predictive Maintenance Program (PMP) is clear to most clients/companies. For many we find it is often unclear as to how to run an effective PMP and what techniques to embrace.
This post is too short to dive into the finesses of asset, part selection and using available data and engineering resources such as FMEAs and FMECAs to create models that predict failure and degradation … but long enough to focus on one of the important aspects in PMP: use of event asset data to enhance predictive models and detect early failures. Read more
Event Stream Processing and Complex Event processing is computing on live event streams. Event streams can contain a wide variety of time based occurrences (events). These can range from work orders to alarms, warnings or events associated to process conditions, items in your workflows, events from your assets et cetera et cetera.
Very often event streams contain valuable information when events are occurring in a certain sequence of time or in a specific frequency. In certain cases it is also valuable to know when event streams do not follow a known pattern.
An example of an event pattern for a windmill is:
- An increase in wind speed;
- An stable rotor speed; and
- An increase in bearing temperature.
This may be indicative of a bearing failure. The example is very clear because it correlates only a few events in the time domain and none of the other data that is also contained within the data/event stream of the windmill is shown. Read more
One of the most popular applications of IoT and M2M is Predictive Maintenance. UREASON has vast experience in this field and recently organized two webinars about Predictive Maintenance. For those of who have missed these webinars, please watch the recordings:
Predictive Maintenance webinar part I
Predictive Maintenance webinar part II
UREASON NL Office
Fourth Floor, A4.004
3013 AK Rotterdam
UREASON UK Office
Central Working Reading
R+, Aldwych House
2, Blagrave Street
Reading, RG1 1AZ