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

« July 2014 | Main | September 2014 »

August 28, 2014

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.

Predicting Asset Failure Using Similarity Based Modeling -Part II

 Similarity Based Modeling offers a more accurate checkpoint for deviations from recognized behavioral patterns as it considers a group of signals and compares the pattern of a signal relative to the pattern of all other related signals. SBM does not eliminate the human element of analytics or actions but it aids in scanning vast quantities of data quickly and making sense of it. Traditional alert limits can assist in protecting equipment but they don't substantially protect or improve availability and reliability. By using SBM the engineers can absolve themselves from direct data trending activities. Sufficient time to respond to aberrant or changing condition is available as data is monitored by the software and the engineers review the data when an exception is posted. Monitoring efforts are always efficient as only signals deviating from the normal expected pattern are highlighted. Searching for all visible signals for problems can thus be avoided. Near real time data can be obtained by performing SBM routinely on the equipment and the software application helps in identifying the pattern changes much earlier than the human eye can detect leading to a highly accurate analysis.

The advantages of using SBM are as follows:
1) Physically linked signal behaviors can be modeled together
2) No regression or other parametric analysis needs to be done.
3) The parameters all move relatively together in identifiable patterns of behavior which are recognizable using SBM and are superior to an engineer using monitoring disciplines and techniques.
4) Simple design, robust estimate of each signals behavior and easy interpretation of results.
5) Provides sufficient time for diagnosis and recommendation for the problem in hand and the maintenance activity can be done well in time to avoid shutdown.

The Similarity Based Model can be better understood with the help of an example. In steam turbine, sensors are placed to monitor the oil temperature, bearing temperature and vibrations. The empirical thresholds in normal operating conditions have been defined by the OEMs for the above operating parameters. The data from all the sensors are obtained in real time and compared with the historical data to identify a pattern in the behavior of the signals from the sensors. The pattern thus obtained is then used for comparison with the actual real time value. The software applies a predictive analytics model to the sensor data and returns the information on the behavior of individual sensors. In a case where under normal operating conditions the differential bearing temperature is above the empirical threshold defined by the OEMs, then SBM model in the software highlights only the signal deviating from the normal expected pattern. This is the Detection stage in the incident life-cycle.

 Predicting Asset Failure Pic 1.png

Fig.1 The top graph shows the differential bearing temperature in both normal operating condition and in alert condition while the bottom graph shows how the SBM generates the alert signal at an initial error stage.


As soon as the signal highlights an abnormal behavior in bearing temperature, the plant engineer can focus all his attention to identify the cause of the problem and make recommendations to rectify the problem before it causes the equipment failure. In this case of steam turbine, the temperature difference occurred between the two surfaces and the OEM recommendation has been exceeded. A shutdown of the turbine would have been necessitated had this small anomaly gone unnoticed.

 Predicting Asset Failure Pic 2.png

 Fig. 2     Incident Life Cycle of an asset

 The Diagnosis stage of the incident life cycle focuses on the causal analysis and the Communication stage focuses on the recommendations of the plant engineer to the maintenance personnel. The Action stage in the incident life cycle focusses on implementing the recommendations of the plant engineer and ensures the breakdown is averted by proper maintenance. The maintenance personnel will take actions to mitigate the temperature difference. The early detection using the Similarity Based Modeling allows maintenance department and plant engineers the time to devise and enact a mitigation plan.


How is Similarity Based Modeling using Predictive Analytics is a Smart Solution?
Predictive Analytics Solution helps asset intensive industries achieve and exceed asset performance, improve reliability and availability by providing prior warnings and notifications on upcoming failures, resulting in ample time for planning, scheduling and executing maintenance jobs. Overall SBM optimizes maintenance activities and reduce maintenance cost expenditures helping organizations in gaining competitive advantage .Organizations will be able to focus on proactive maintenance rather on reactive maintenance. Plant engineers need to ensure that the critical equipment maintain the required levels of reliability, availability and performance. This requires frequent and accurate assessment of the equipment operating conditions to minimize the operational risks of unscheduled interruptions. Effectively analyzing the realms of data collected gives an idea not only about the overall health of the plant but also about production system elements like turbine, compressor etc. The data comes from periodic and real time systems. Functional failure prone elements in critical equipment's can be identified using periodic methods, but it can be time consuming and intermittent. Model based solutions are being increasingly used to obtain real time understanding of the equipment health. Periodic inspection methods will be much more efficient if the actionable intelligence created from large amount of data helps in detecting the problems automatically and provide a basis for diagnosis and prioritizing the problems.

 Predicting Asset Failure Pic 3.png

Fig 3.       Few Benefits of Predictive Analytics Based Asset Management

 The foundation of next-generation asset management will be the ability to see, understand and respond to not just what is happening now in the asset base, but also to what will happen in the future. Similarity Based Modeling using Predictive analytics will provide utilities with the strong foundation and investment confidence they need to operate and excel with minimized risk. The imperative of using the wealth of asset data available in utilities' back offices and operations, along with expanding the future use and availability of real-time asset intelligence, will provide a means to planning and investing in a secure and dependable infrastructure while promoting efficient and effective operations.

August 26, 2014

Successful EAM Implementation - Prepare & Plan

In today's technology savvy world, most of the industries stumble upon this daunting question- Whether I really need a robust EAM software? If yes then what are the key elements it addresses? Some industries are forced to keep the EAM software just to comply with the statutory & regulatory requirements or sometimes it's purely for increasing their brand value in the competitive market. It is very important to ensure a proper pre selection & pre-planning exercises without which the EAM program could end up in a failure. There are few aspects which I believe needs to be considered here, let's see what they are

Some of the common which industries can experience are:

• Low system usage due to inability to track system usage effectiveness
• Low software license usage for which high license cost is being paid
• High customization to meet specific business requirement
• Data information flow is not streamlined due to non-synchronized data
• High usage of adhoc tools such as Excel etc. affecting data quality
• Limited reporting feature due to data sits across different system/tool
• System is made rigid with non-scalable solutions & incurring more cost on upgrade cost


Now a days Enterprise asset management software is being popularly used within the organization to manage their assets. Most of the EAM software does not cover the complete asset management cycle thus compelling the organizations to go for additional software(s) to mitigate those gaps in EAM software. On the other hand many organizations are found not utilizing the EAM package at the most due lack of proper due diligence in place. Some of key questions which each organization should have a definite answer(s) before going for an EAM software implementation program are:

• How EAM software will be beneficial for the company and their people?
• How can they derive full benefits from the EAM software?
• How much of their process and standards can comply (Fitness %) with the standard EAM software? Do they really need additional software's?
• What will be the long run cost incurred having an EAM software in place?
• Do we have proper governance model in place?
• Is the current business process harmonized? 
• Any communication plan in place? - People should be aware off of the happenings so that they can make up their mind for the upcoming changes.
• Are we proposed to use right people for EAM implementation? Users who has diversified/depth process knowledge from different business should be part of implementation team
• Do we have detailed plan of how many, how long, where, when & how to involve business team members during implementation as this will avoid project delays
• What all risk & opportunity will be encountered? Do we have mitigation plan for the identified risks.
• Do we have detailed change management program in place?


There are organizations who have successfully implemented EAM software by identifying & bridging the gaps between People > Process > Software. However, few organizations were not so successful in reaping the full benefits of EAM solution and are still in process. The suggestion which I would like to provide here is to carefully evaluate the challenges, identifying the pitfalls and introspect on the listed aspects, I am sure this would definitely yield results and will help to convert the pitfalls in to opportunities making a comfortable success zone to move on!

Subscribe to this blog's feed

Follow us on

Blogger Profiles

Infosys on Twitter


Categories