Our Process Data Miner™ product is a powerful new way of detecting trends in your data that are early warning signs of process or equipment problems. Left un-checked, efficiency losses, unplanned shutdowns and potential safety and regulatory issues will occur. Using a patented artificial intelligence algorithm, Process Data Miner automatically scans your data in real time and organizes it into a knowledge base consisting of  “data signatures” or patterns that characterize operating behavior of the system.   Process Data Miner automatically learns the patterns in your data and organizes them for easy knowledge discovery. 

Each pattern in the data represents a signature that can be correlated with the health of the process or a specific piece of equipment in the plant. These signatures are stored in a library for later analysis by reliability and or maintenance specialists. The power of  process data mining comes from learning directly from the plant’s own data. When an equipment problem develops, the early warning signs are difficult to detect in real time. Until now there was no easy way of capturing the patterns in the data that can be used as an early indicator of equipment or process problems. Process Data Miner not only learns these patterns in your data, but also recognizes them the next time they occur so that corrective actions can be taken before the problem escalates. Plant personnel are alerted to time sensitive issues through e-mail and pagers.  Statistics including; the number of times the pattern has been observed, the last occurrence and the “closeness” of the current condition to other patterns stored in a database can be viewed on the Remote Manager™ web site.

For a conceptual demonstration of the power of Process Data Miner, please view the Flash demo, then contact us for a complete demonstration and an evaluation of how this powerful technology can be applied at your plant.

Read about this excited new technology and applications in the power industry at the link below:

Predictive Condition Monitoring and Knowledge Management in Power Systems