We recently attended the 2022 API Inspection and Mechanical Integrity Summit!
We recently attended the 2022 API Inspection and Mechanical Integrity Summit in San Antonio, TX and it was so great to be back in person. The event was a huge success with attendees from all over the globe. We saw a few major themes over the three days of the conference: CML optimization, managing big data, and the introduction of data science into reliability. If you missed the conference or attended and want more information on our presentations, please check out the videos and eBooks below.
Big Data in Mechanical Integrity: The Next Generation of Corrosion Models
Andrew Waters, PhD & Fred Addington
Recent advances in technology have transformed the way the world uses data. “Big Data” has the potential to improve how we evolve our MI programs. Pinnacle recently completed a study comparing the accuracy of asset degradation rates predicted by a machine learning model to the rates predicted by human SMEs applying current industry standards. The study found that the machine learning model was able to predict degradation rates and associated variability with a higher level of accuracy and reduced the mean absolute error by 38% compared to the subject matter expert estimation. In this presentation, presenters discuss the details of the study, how large data sets can be used to better predict asset degradation, and the challenges of making “Big Data” actually work.
Case Study: Increasing the Effectiveness of CML Optimization Through Condition Monitoring Optimization
Andrew Waters, PhD & Ryan Myers
While many facilities approach traditional CML Optimization with the elimination of CMLs in mind, the focus should first and foremost be on effective risk management and risk reduction. Condition Monitoring Optimization, a new, data-driven methodology by which inspection scope, techniques, and intervals are determined and dynamically updated as new information is available, enables facilities to confidently prioritize CMLs and determine when additional data is required, inspection adds little or no value, or corrective maintenance is needed. In this presentation, the presenters walk through a case study where an energy company increased monitoring for select CMLs to reduce risk to prioritize inspection scope and intervals while also reducing near-term monitoring by about 50% on the rest of the population.
The Economics of Reliability: Leveraging Reliability as a Competitive Strategy in Refining, Mining, and Chemicals
Jeff Krimmel, PhD
While processing facilities spend $500 billion annually on reliability, many facilities struggle to measure the impact of reliability at their facility. Allocating more of your budget to reliability initiatives doesn’t necessarily result in more profitable operations, and the key to leveraging reliability as a competitive strategy is knowing where to strategically optimize your costs and mitigate risk. In this presentation, Jeff Krimmel, PhD, Chief Strategy Officer, analyzes insights from Pinnacle’s Economics of Reliability Reports, a series of reports that explore the impact of reliability on global industries. The presentation provides an understanding of the operational and financial realities that shape the reliability of major global industries and how they can leverage reliability as a core competitive strategy at their facility.
In general, the oil and gas industry is risk averse. Given the serious economic, environmental, and societal consequences that can result from an incident, facility management is typically conservative in how they calculate risk and in how they make risk management decisions. However, facilities must accept some level of risk in order to operate; capturing this accurately is key if facility management is to understand their true risks as well as how to deploy limited resources most effectively. Learn how to overcome these challenges by focusing on quality data, analyses, and decision-making processes.
Many industrial facilities have design, operations, process, asset condition, and risk model data stored in variety of different repositories, creating data silos. Regardless of whether the data is a hardcopy, stored in spreadsheets, or software, the solution is not simply integrating everything into one software. The key to successfully leveraging your data is bringing your data together and properly contextualizing it to feed into the right models to drive better and faster mechanical integrity and reliability decisions. In this presentation, Lewis Makin, Partner, discusses the typical data challenges and how to approach solving them.
There are an array of Inspection Data Management, Risk-Based Inspection, and other reliability function software packages in the industry. This discussion focuses on common pitfalls themes, including which software packages are used, how they are implemented, and then maintained. Additionally, this presentation includes examples of what not to do, what to look out for, and ultimately, how to make the right software work for you in attaining your reliability and mechanical integrity goals.
The Risk-Based Inspection (RBI) methodology presented in API RP 581 was developed as a method for using risk as a basis for prioritizing and managing the efforts of an inspection program. RBI programs help facilities increase operating times and run lengths while decreasing risk by shifting inspection and maintenance resources to focus on high-risk equipment while maintaining a lower level of activity on low-risk equipment. Watch the presentation for a discussion about how facilities can recognize greater benefits from their RBI program and demonstrates how comparing risk results between facilities can provide insight into the effectiveness of an inspection program. Learn how to use equipment to identify high-risk operations, compare risk across facilities and plants, and identify improved risk reduction activities.
Reducing Lifecycle Spend by Leveraging Advanced Image Analytics in Asset Integrity Programs
Austin Laskey & Siddharth Sanghavi
The total cost of corrosion in the oil and gas production industry is estimated to be greater than $1 billion annually. A recent NACE study stated implementing proactive and comprehensive corrosion management practices can result in 15-35% savings of the cost of the damage. With current advances in digital modeling and machine learning technologies, we can effectively reduce safety risk by optimizing our field personnel and resources. Such technological advancement can help proactively monitor for damage, screen for anomalies, and detect additional defects. Learn how to effectively integrate digitization and advanced image analytics into a mechanical integrity program to lower safety risk, reduce lifecycle cost, and more proactively manage your facility.