4Common Plant Historian -- OSIsoft PI 29 PI Servers203 interfaces to various systems1000+ process displays & reports350K tags (real-time data points)
5OSIsoft PI took care of history and current value but not what the value should be…. We selected SmartSignal to leverage our existing OSI PI infrastructure and predict…
6SmartSignal Predictive Maintenance Tool SS takes data from our PI infrastructure (like vibration, temperature, pressure, etc.) and inputs it into a software model. This model shows how a a typical piece of equipment is supposed to operate over various loads and ambient temperatures.If the data goes outside of the predictive model, an alarm is sent to the station for further investigation.Basically, we are making the computer do the work of scanning all of the sensors and instruments in the plant for changes in known equipment behavior.
7Defining WatchList Graphing Terms: Actual, Estimate, Residual, Alert, Incident Actual (blue) from OSI PIEstimate (green) generated by SSC modelsResidual = Actual - EstAlerts (red X) Statistically significant residual valueIncident (diamond) multiple samples or sensors showing alerts; drives the WatchList
8Typical Results & Additional Terms VSG (green diamond) Virtual Signal Generation was enabledMissing Value (blue X) Signal gave NaN value
9Smart Signal – Site WatchList ModelsCan see incidents by clicking the arrow button.
10SmartSignal – Site Model Detail Site that you are on.Incident List – This is a list of incidents on the models.Chart View –The Blue line is the actual PI data and the Green line is the model data.
11SmartSignal-Reliant Scope 67 coal & natural gas power units across U.S.Total 13,450 MW powerRotating & non-rotating balance-of-plant assets monitored411 assets, 1174 modelsTurn 30K+ sensors to exception-based monitoringGoals includeEarly warning of equipment faults & process problemsMaximize availabilityMinimize forced outagesImprovement of unit heat rates
12Reliant’s “Virtual” M&D Center Staff of three working 5*8 at their own cubes:Review WatchListplants when equipment issues are detectedTuneBuild new modelsTeach WatchList classesDocument issues and model changes.Plant championsLook at the WatchListUse logDeal with the easy ones
14Typical Plant Response The Plant Champion will commonly use Pi Processbook or Datalink to confirm the item and issue a work order
15Example of Full Cycle of a Catch From:Sent: Thursday, November 30, :34 PMThis is a pretty significant movement on FD Fan Motor outboard bearing (about 17 deg above expected currently).The oil levels are all good and the filters have been changed. The filters were dirty and the temps are dropping on the motor after the change out.
18Truth Table (Logic) SS Catch SS Catch False Catch True Catch SS no CatchSS no CatchNo Machine issueMachine issue
19What is a Good Model So Far? Modeling elementsIt has catches (detects changes)It has no misses (or few)It uses as-found dataHuman elementsIt has engaged users
20MetricsTrue CatchesLook at the tracking log-equipment/instrumentation catchesMissed CatchesLong term – Use Power GADS to review major eventsWas the system modeled? If not, should it be? Build it.If modeled, review and improve the model.No Catches & No Machine ProblemsCould be a sign of a good programCould mean just waitFalse CatchTrack issuesUse log statistics and target problematic models
21Catches The table shows true catches and false catches *2006 catches not a full year
22False CatchSmartSignal alerts indicate a change from the model data set (State matrix)-A repair could cause a changeA new seasonAn operational mode changeAn abnormal configurationOr bad modeling data
23Model with False Alerts Detailed review of this modeldata set found that it had twomodes. A and B with the sameInlet temperature and A downstream of B
24Model with False Alerts Detailed review of this modeldata set found that it had twospikes that were included in themodel.
25Human Factors How can acceptance be measured? Is the user engaged? What are good KPIs?How can it be made “fair” for peaking and base load unit?
26Levels of SmartSignal Utilization basic level is where the WatchList Team (WLT) serves as an M&D center. Plant responds to WLT questions about their units and WatchList items.the engaged user logs into the WatchList at least once a week (on average).The committed user logs in several times a week (on average). They also add information to the log and clear alerts from the WatchList.The power user exceeds the committed user level by pressing model issues and providing a dialogue about known plant repairs and changes.
28KPI IssuesTerms like basic, power user work well for a full-year but they did not track seasonal units wellWe moved to a new metric that is much closer to the desired outcome– If you are running- login
29“Average number of service hours between logins” SS Login Ratio“Average number of service hours between logins”
30Log Entries 2007 50% of plants had no log entries 78% of log entries were at one plant “C”2008Only 10% have no log entries for 2008Log entries more evenly spread across fleet119% increase in total log entries
31LessonsThe knowledge of how the plant should run comes from how it has run (PI data)Keeping the messenger alive is part of the task (instruments)Eliminate variables (do not add them)Model to detect changesException-basedStatistics-based technologies are not common in plant environments.Tools are not complete solutions – People still have to act