Predictive Analytics is Heart of Digital Transformation for Energy industry

Senthilkumar Pandi, a Digital Data Management Expert, explains how the Predictive Analytics enable Energy Industry to prevent costly unexpected downtime using Predictive Analytics and suggests how to choose right solution.

Digitising and Digitalization has always been part and parcel of galvanising process of business. However, breakthrough technologies will make a big difference in realizing the value of digitalization, Predictive Analytics is one such technologies making waves in the Energy Industry and it is becoming indispensable for energy industry to maintain their multibillion-dollar assets efficiently by preventing expensive unexpected failures of Equipments which are backbone for the operations.

Adoption of right Predictive Analytic System for Energy Industry

Predictive Analytics is useful in early warning detection from critical equipments, in particular the rotary equipments such as compressors, pumps, motors, Turbines, Fans, blowers, gearboxes of rotary equipments. Merely having the data in dashboard and allowing human to analyse the data and make decision will not make any difference. The data should be used to read and generate alerts, early warnings automatically to operators to take the equipment and systems for maintenance and avoid unexpected failures of equipments and its cascading effects on entire operation of plant which would result in huge loss. The predictive Analytics would not only help is avoiding the unexpected failures of equipment’s, but also could reduce unnecessary regular maintenances.

While, any organization before choosing the right solution for their Predictive Analytics, a broad level study is essential to implement a Predictive Analytic system successfully and leverage the Technological Advancements.

Here are the few key elements that determine the successful implementation of Predictive Analytics based maintenance system.

1. Compatibility to fetch the live data from historian and import of data from various sources such as   TAS/ DCS/SCADA/ PLC/ OPC/ Data base files etc.
2. Modern and user-friendly interface with heavy usage of application using desktop and mobile Apps with dashboards  
3. The system to commercially off- the -shelf (COTS) which should allow the users to configure the system and deploy on -premises with standard libraries and easy to modify the models
4. The system should generate notifications and alerts effectively based on data driven techniques like statistical model and advance analytics using Artificial Intelligence (AI) and Machine Learning (ML).
5. Compatible to your organizational Data Encryption/Data Protection policy to protect the Data to be used for predictive analytics. The data is your digital Asset.

Alerts are your Asset:

While the Predictive Analytics in intended to protect your assets, the Alerts and notifications are the real assets that one should expect from predictive Analytics system. If a system continues to generate to numerous alerts and false alerts, then the reliability of Predictive Analytics will be at a stake. Here comes the vital role of machine learning (ML) and Artificial Intelligence (AI) which would play an important role to recognize the pattern from data points and generate the reliable and actionable alerts. So, before you choose a system for predictive analytics, it is essential that you should evaluate the standard libraries for various types of equipments and the OOTB model available for various use cases and you can simulate with historian data to ascertain that the system function to it is purpose and then can deploy the system to work with live data coming from various sources. Open sources developments are limited and not proven, while there are Standard industry softwares such as AVEVA Predictive Analytics (earlier known as PRiSM), Hexagon EAM.Baker Hughes Advanced ESP Predictive Failure Analytics are some of globally adopted solutions, for energy industry predive analytics to protect the critical assets.                  

Hadwares and Softwares Selection

The success of the system you choose and deploy for predictive analytics is fully depending on the right combination of hardwares and softwares. Like any analytical software requires high processing capacity, Predictive Analytics when powered by machine learning, the system should be capable of recognizing the patterns generated by data points coming from sensors every day, week, and month in order identify the deviation, it really requires a robust hardware’s and supporting OS and other allied software applications for fetching, integrating, synthesizing the data to be used for analysing. Do not select the hardware’s that is nearing end of life and same as OS and other applications. Be conscious about compatibility and capability of the predictive analytics system to integrate with your existing systems from where the data to be fetched. Before you for implementation, through investigation on usability of existing data available in Historian shall be conducted to ascertain that the data available is rely upon data to build the models.

Image Courtesy: Aveva

An illustration where the predictive model developed using historian data for nearly normal operation of an asset, is compared with Actual data coming from an Asset through sensors. Leveraging pattern recognizing algorithms and AI and ML techniques Alarm/Alerts will be start generating when there is a deviation from the Predictive Model. Also, the traditional alarm which is set based on threshold value which is still far from the Actual and predicted model, it allows an operator to have a look at the root cause for this deviation well in advance, before it actually reaches the threshold level and prescribe the action to be performed on the asset being monitored and prevent the costly damage that might occur to the asset.

Deployment Methodology and KPI of System

More you go digital; more you are vulnerable to risk your assets. An idle Predive Analytics solution should be deployed on-premises if an organization would avert any incident pertaining to data security. The security testing for the system should be conducted using VAPT tool or through a CERT. The system performance should be linked to various KPI’s for its functionalities to realize the benefits.