Accurately Predicting Equipment Breakdown With Digital Technology Creating Big Savings

Oil and gas pipeline ruptures are not only potentially costly events, but also occurrences that erode public confidence in pipeline safety, and therefore social licence to build and operate them. The breakdown of multimillion-dollar pieces of equipment used in the oil and gas industry can be similarly dangerous, and costly.

The ability to accurately predict such occurrences, and prevent them from occurring, while not taking pipelines or equipment offline prematurely to forestall such occurrences, represents a valuable capability, particularly in today’s low price environment. And it is something today’s digital oilfield can provide.

According to the Digital Oilfield Outlook Report: Optimizing operations to unlock the hidden barrels, the adoption of predictive maintenance technologies can allow companies to avoid the extraordinary costs associated with such occurrences while significantly reducing operating costs.

One case study documented in the report details the savings generated by the operator of one of the biggest natural gas fields in Europe, which was experiencing faulty sensor readings in compressor trains that formed part of the field’s processing and compression facilities.

The cores of the 31,000-horsepower compressors hover on six sets of magnetic bearings that are constantly monitored by 40 sensors. The operator found that faulty readings were misrepresenting the position of the compressor core, resulting in breakdowns costing millions of dollars in repairs and average deferred revenues of $5.2 million per upset. Resulting production losses were as high as $14 million per week, in addition to penalties applied for missed service. Over and above the costs, replacing a damaged core can also be hazardous, as the internal components of the compressor are contaminated with mercury.

The production assets of the massive gas field, developed with more than 300 wells in 29 well clusters, generate some six million records of operational data per second, and each record contains 90 fields, making it virtually impossible for human operators to sort through all the data and distinguish correlations between the data streams, according to the case study.

What human operators could not accomplish, however, was achievable using SAS Asset Performance Analytics (APA) predictive maintenance technology. SAS APA was able to show a complete picture of past events and the same view of the current condition of the operation, allowing exception-based surveillance. The data is used to generate a set of models that range from simple thresholds to engineering rules-based models and advanced predictive models, and together these allowed the operator to predict equipment malfunctions and determine the lifecycle of new equipment.

“The foresight gained through this analytical approach enables the operator to schedule preventative maintenance and make more confident production and operational decisions, resulting in a significant annual cost savings,” the case study found.

Alerts are now generated 10 weeks in advance of sensor failure, enabling the operator to manage and schedule sensor replacement, and the mean time to repair has been reduced from 38 days to 10 days for a savings of US$750,000 per replacement. The operator estimated annual savings of US$10 million when it had implemented the analytic models on 15 of its 29 clusters. All of its well clusters are now managed by analytics.

When applied to pipelines, predictive maintenance can create similar benefits. Current pipeline leak detection and maintenance technologies such as point sensors and periodic surveys provide only limited levels of monitoring and capacity for predictive maintenance, notes the report. Calgary-based Hifi Engineering developed a new technology using advanced fibre optic monitoring technology to provide the kind of predictive maintenance that could prevent issues like corrosion from leading to leaks and spills.

Its recently developed high fidelity dynamic sensing (HDS) system uses latest generation fibre optics that can double as high precision sensors—up to 200 times more sensitive than conventional technologies—able to detect vibration, strain, temperature and acoustic energy along every centimetre of their length. The sensing technology is coupled with advanced data processing and management, operating on GE’s Predix operating system, with the capability to decipher some 10 terabytes of data per day from a single cable (up to 100 kilometres long) and turn it into actionable intelligence.

By combining analysis for strain, acoustics and temperature, each of which has a distinctive signature, the HDS system is able to solve one of the main drawbacks of less sensitive technologies that rely on only one of those variables—their susceptibility to false alarms.

“Based on the statistical incidence of pipeline leaks alone—including average leak sizes, remediation costs, regulatory penalties and forgone revenue from operational downtime—Hifi determined in a business case study that operator payback on 100 kilometres of pipeline is less than one year. Additional value can be derived from the system’s ability to generate precise fluid-flow dynamics data to increase pipeline efficiencies. The reduced reputational damage and increased social licence to operate that could be gained by avoiding oil spills and natural gas ruptures offer further benefits,” concludes the case study.

Produced by JWN Energy with partners GE, SAS, Panoptic Automation Solutions and ABB Group, Digital Oilfield Outlook Report: Optimizing operations to unlock the hidden barrels focuses primarily on predictive maintenance and production asset optimization. Based on a comprehensive survey of oil and gas professionals in the Canadian oilpatch, it also includes recommendations for the uptake of digital oilfield technologies in challenging times. Free download of the report is available here: http://www2.jwnenergy.com/digitaloilfieldreport-November-2016.

Dear user, please be aware that we use cookies to help users navigate our website content and to help us understand how we can improve the user experience. If you have ideas for how we can improve our services, we’d love to hear from you. Click here to email us. By continuing to browse you agree to our use of cookies. Please see our Privacy & Cookie Usage Policy to learn more.