Enterprise Asset Management is an emerging strategic tool enabling optimal utilization of assets contributing to business goals of an organization. Come join us as we uncover the hidden potential of Asset Management with our deep insights spanning industry domains and technology

« Predicting Asset Failure Using Similarity Based Modeling -Part II | Main | Risk based Asset Management »

Use of Smart Maintenance Model in Electric Utility Industry for Power Grids-Part I

Every utility industry, be it an electrical, water or gas has its own set of unique challenges.  Since the time Thomas Edison invented Light Bulb in 1879 till date, the industry has grown by leaps and bounds. There has also been a substantial growth in the demand of electricity as a huge chunk was dedicated to industries labelled as development. The population also contribute a great deal to the increase in consumption rate over the years, however, there exists a disequilibrium between the demand of electricity and its production. This apparently made the burden of excess demand fall on the existing power grids, making them vulnerable to breakdown. As it is said "squeaky wheel gets the grease", naturally the Asset which were most susceptible to breakdown, got all the attention. There have been many cases throughout the world where the power grid failures have caused major power outages. Major power outages such as the one in Turkey in  the year 2012 affecting 20 million people; the  Grid failure in India in  the year 2012 affecting 7 north Indian states leaving half of India without electricity or the one in Chile in the 2010 affecting 90% of its population surely leaves some serious messages for the Management . The management have always fretted over ensuring proper Asset maintenance to avoid unexpected and abrupt breakdowns. These breakdowns resulted in power outages and loss of revenue for the industry and ultimately a displeased customer. In this write-up, I would like to emphasize on my recent work on the Smart Maintenance model which for the Power grids can be seen as a probable solution to elude unforeseen grid failures and power outages.

Smart Maintenance model thrives on Predictive Maintenance principle and is a step to move from Reactive and Preventive maintenance towards Predictive maintenance.  The proposed model can leverage the historical data of assets breakdown along with the real time asset monitoring data. Both historical and real time data tied under a Statistical model can help us predict with fair accuracy, the probability of future asset breakdowns. This model will not only help electric companies to retain their existing customers, but also discontinue the probable loss of revenue due to power outages and asset breakdown costs.

The Smart Maintenance model entails 3 phases to predict future asset breakdowns. Procuring data is the very first step of this model. The data collected will be both real time and historical. EAM (Enterprise Asset Management) has been religiously used in the electric utility industry to manage asset information including asset location, hierarchies, asset condition, and work history. EAM facilitates access to historical data concerning the date and number of times assets have broken down in past and Corrective/Preventive maintenance taken place to counter it. It also high spots the cost of repairs accumulated till date. The real time data can be collected by way of SCADA (Supervisory Control & Data Acquisition) systems which gathers information as to where the fault occurred, transfers information back to central site along with ongoing real time monitoring of asset; RTU (Remote Terminal Unit)  a subsystem of SCADA which collects analog and telemetry data through field devices and sends it to the central database for processing and some of the Intelligent Electronic Devices (IEDs) like Digital Fault Recorder (DFR)  which gathers data with respect to power disturbances in terms of voltage fluctuations, frequency etc. Yet another IED used to gather data is Meter, assembling data in terms of system current, voltage, and power values. After the data is collected from these sources, the very next phase of the model is to analyze the data using a statistical technique. Once the analysis is complete, the last stride in Smart Maintenance model is to expect an apt management decision based on the analysis results.

In the next part of the blog I will talk about the methodology used to analyze the data using Regression Analysis technique and explore probable course of action thereafter.

Post a comment

(If you haven't left a comment here before, you may need to be approved by the site owner before your comment will appear. Until then, it won't appear on the entry. Thanks for waiting.)

Please key in the two words you see in the box to validate your identity as an authentic user and reduce spam.