How Can Predictive Analytics Reduce Unplanned Downtime in Oil and Gas Production?
With the recent recovery of oil prices, most oil and gas companies are starting to see light at the end of the tunnel and preparing to ramp up their investments to either maintain or grow output. Production can increase either by developing new fields or improving asset uptime in existing fields, but asset downtime due to facility maintenance – planned or unplanned - is costing producers millions of dollars in lost revenue every year. According to a recent ARC survey, companies have been losing between 3-5% of their production to unplanned downtime. In a hypothetical case of 10,000 barrels per day of oil production facility, a 1% gain in asset utilization can easily yield several millions of dollars in additional revenue. Therefore, addressing the challenges of unplanned downtime can reap huge rewards for companies.
Impact of Unplanned Downtime on Production1
Challenges in keeping assets running optimally in remote fields
As production assets in the oil and gas fields, whether offshore or onshore, are often situated in non-ideal environments and constantly exposed to harsh operational conditions, maintaining equipment to keep up with production goals can be challenging. Adding to that challenge are changes in asset loading profiles which can be due to declining production over time which make it harder for operators to detect equipment issues in a timely way using their current asset monitoring systems. This can, and often does, lead to failures which cause production outages. However, this situation can be avoided with an appropriate maintenance strategy based on the asset type, criticality, maintenance history, business purpose and overall company goals.
Can you read the asset health easily from this chart?
Is your current maintenance strategy outdated?
Today, preventive maintenance, based on time or usage statistics, is one of the most commonly adopted approaches by oil and gas producers to keep their operations running. In other words, maintenance is performed at regular intervals to reduce the probability of asset failure. However, in most cases, this strategy has often resulted in either over-maintenance or under-maintenance of assets due to differences in equipment ages, operating environment and unpredictable performance. Over-maintenance costs unnecessary production downtime while under-maintenance increases the risks of equipment failures that lead to the deployment of costly reactive maintenance. A more effective strategy is to optimise maintenance based on acceptable risk - a combination of preventive and predictive maintenance.
Optimising maintenance based on acceptable risk
Step Up to Predictive Analytics
In recent years, advancements in technology – cloud platform, analytics and computing power, and their focus on reliability problems - have accelerated the adoption of predictive analytics to improve asset reliability in the process industry. Predictive Analytics enables empirical multi-variate modelling of rotating equipment performance – such as pump, compressor and turbine - using advanced pattern recognition and machine learning algorithms to identify and diagnose any potential operating issues days or weeks before failures occur. Operating models, including past loading, ambient and operational conditions, are used to create a unique asset signature for each piece of equipment. Real-time operating data is then compared against these models to detect any subtle deviations from expected equipment behavior, allowing reliable and effective monitoring of different types of equipment. The early warning notification allows reliability and maintenance teams to assess, identify and resolve the problems, preventing a major breakdown that can cost companies millions of dollars in production slowdowns or even stoppages. Benefits of Predictive Analytics include:
• Improve asset ROI through early warning of asset failure before it happens,
• Reduce unplanned downtime and improve asset availability
• Reduce operations and maintenance costs
• Extend equipment life and increase asset utilization
Maintenance Management Transformation Is not only about Technology
Transforming maintenance management from a reactive to a proactive culture requires companies to embrace change management and create new business models to build the required capabilities. It is a journey to drive digital transformation through deployment of analytics, automation of work flows and work orders, and behavioral changes in workforce – changing when, where, which and how work is performed and evolved. Although this may seem like a daunting task, making the transition successfully can be profoundly rewarding for companies as even a slight improvement in asset utilization can result in huge gain in revenue and profits.
Are you ready to take the first steps to enable Predictive Analytics in your enterprise to reduce unplanned downtime? Register for our Webinar now.
Join Noel Philips for our “Improve Asset Reliability with Predictive Analytics for Oil and Gas Production” webinar on Jan 29 at 10am CST. In this webinar, Noel will outline the various maintenance strategies in oil and gas, highlight customer use cases and explain how you can maximize asset uptime in oil and gas fields leveraging a holistic Asset Performance Management platform, including predictive maintenance, mobility, augmented reality (AR) and virtual reality (VR).
1: ARC Survey of Senior Executives and Engineering, Operations and Maintenance Managers in Oil & Gas
Eddy currently manages Industry Solutions marketing at Aveva, driving awareness of new solutions that enable enterprises to stay ahead of the curve. Over the past 15 years, he has been involved with product management, marketing and sales management in the Industrial Automation space. He is a strong advocate for leveraging technology to improve operational processes to enable a profitable and sustainable future for every stakeholder, Eddy holds a MBA from National University of Singapore and a Bachelor in Engineering from Nanyang Technological University.