Avoid unplanned downtime
Apart from reducing revenues and safety issues, unplanned downtime is typically accompanied by lots of waste: massive flaring in refineries, lots of unfinished / off spec products, along with start-up inefficiencies. And if that isn't enough, unplanned downtime results in a lot of unnecessary repair work, which equals unneeded activity at site leading to unavoidable emissions.
By collecting and analyzing the correct data from the equipment, we can apply the proper maintenance at the required time and thereby help avoid unplanned downtime, along with its negative consequences. We are ready to apply our structured 6-step process to put you back in control.
Identify data sources
Data can come from many sources: process instruments, periodic inspection reports, continuous monitoring systems, CMMS systems, manually entered (maintenance) logbooks, and many more. Knowing which data to collect is the first step to asset performance management.
Before modeling & analysis can start, data needs to be accessible. This can vary from digitizing manually filled out data logs, to collecting periodic data-dumps from hand-held inspection tools, to anomaly data transfer, to real-time full data transfer. Data can be transferred to cloud environments, but also kept decentralized (“fog computing”).
Despite its name, big data analytics isn't about throwing massive amounts of data into a computer program, expecting it to spit out novel correlations. Grouping data into models around failure mechanisms will greatly speed up analysis. This includes building algorithms that learn to detect anomalies and failure mechanisms based on historical failures (fingerprints).
In this next step, we actually look at what the gathered model tells us about asset performance. This is about determining the reliability of the models, preventing false positives and false negatives, drawing the right conclusions and building business cases to determine the best course of action.
Visualizing data on dashboards filled with graphs and tables can enhance insights and thereby provide important decision support. This can be a mix of historic data showing trends, real-time alerts and predictions on the health / chance of specific failures. Large automation suppliers like IBM, Emerson and OSIsoft provide the software, which subsequently needs to be configured and aligned with customer-specific KPIs.
Knowing that something will fail doesn’t immediately dictate what the remedial action will be. Options include applying some on-line maintenance techniques, taking the risk to wait for the next planned turnaround, or prematurely shutting down the plant. In the case of prescriptive maintenance, these decisions are automated, but otherwise humans need to decide.
Either way, decisions need to be converted into work orders that will get the right people dispatched with the right tools at the right time to take care of the situation.
How we make the difference!
Failure mechanism knowledge
We have a thorough understanding of failure mechanisms; an essential ingredient to predictive maintenance.
|Big data analytics||We understand how big data analytics supports predictive maintenance.|
Proven expertise in predictive maintenance
Predictive maintenance in six steps
Smart Condition Monitoring
Moving towards data-driven maintenance
Get in touch with us
Interested in learning more about our services? Let's have a talk!
Our Subject Matter Experts take the time to discuss your existing challenges and help you make smart decisions that best meet your needs.