March 2021
Company Spotlight
Pinnacle
For this Company Spotlight, we interviewed Pinnacle’s Vice President of Business Development, Nathanael Ince, about how the company is rethinking the measurement, reporting, and optimization of industrial reliability. Pinnacle is exclusively focused on helping industrial facilities in the oil and gas, chemical, mining, and water and wastewater industries better leverage their data to improve performance, resulting in increased production, optimized reliability and maintenance spend, and improvement in process safety and environmental impact. For more information on Pinnacle Reliability, please visit www.pinnaclereliability.com.
Background: Founded in 2006, Pinnacle helps complex industrial facilities, such as refineries and water treatment plants, manage their maintenance and repair initiatives to maximize reliability (i.e., the ability to operate when desired) and minimize costs. While the efforts to optimize maintenance and repair operations in these industries have made significant progress over the last few decades, there is still a wide disparity in reliability performance amongst the various companies operating these industrial facilities. For example, it is estimated that U.S. refiners spend over $10 billion per annum on reliability-related activities, but the reliability-related spend across publicly traded U.S. independent refiners ranges from $0.50 to $3.00 per barrel of throughput (600% difference). Pinnacle believes that the current methods of modeling risk are limited by the following shortfalls:
Focused on Individual System Components: Most traditional models and analyses only assess the reliability or risk of individual component of the broader system. While this is helpful in maximizing the reliability of that particular asset, it ignores the impacts (both positive and negative) to the reliability of the overall system, making it difficult for management to optimally determine and allocate their maintenance budgets across the system.
Hyper-Conservative Models: Highly simplified empirical formulas, industry standards, and “rules of thumb” that are incorporated into traditional risk models have resulted in substantial and immeasurable uncertainty. To account for this, models and approaches have been designed to be overconservative, resulting in projected failure rates that are often an order of magnitude higher than actual failure rates.
Static and Siloed Models: Traditional models are developed using a snapshot of data and are used to build a plan for a specified period of time. Further, they are typically implemented separately and by different teams/vendors. As a result, these programs and models do not benefit from the valuable insights associated with other programs and models, and the ways in which data changes over time is qualitative at best.
Overreliance on Machine Learning: Because there is not a large enough sample size of failure points at most industrial facilities, machine learning and artificial intelligence cannot be relied on as the sole technique to optimize reliability performance and spend.
Value Proposition: To improve upon traditional reliability models, Pinnacle has developed its own improved approach to reliability modeling called Quantitative Reliability Optimization (QRO), which offers the following features and benefits:
Links Every Failure Point in a System: QRO statistically relates all the components of a system into one analysis. QRO’s analysis can cover thousands of assets for a particular facility or many more if modeling an entire fleet or supply chain. This statistical relation of all the system components enables Pinnacle to understand how critical data and specific failure points relate to the overall production or reliability impact of the system.
Quantifies Uncertainty: Instead of only providing a single probability number, QRO applies an advanced model called the Lifetime Variability Curve (LVC). The LVC forecasts the distribution of failure probabilities given the current level of knowns and unknowns. As a result, any failure of the system can be accurately modeled given the anticipated point of failure and the uncertainty associated to that point on the failure curve, eliminating the need to be overconservative, which often results in overspending on maintenance.
Dynamic Reliability Model: The QRO model is continually updated by relevant data sources so that key changes in those data points, whether in process, operations, maintenance, inspection, or economics, update the LVC for each failure point. As a result, facility leadership can see how changes to their data affect system reliability as a whole. These dynamic updates and the ability to see how they impact the reliability of the system improves the overall confidence of facility leadership regarding their reliability decisions.
Supplemental Data Science Capabilities: Pinnacle can deploy the QRO approach across various customer operations through a combination of services and software. The software, Newton™, is a cloud-based software application proprietary to Pinnacle, and is the first software in the world to provide for the QRO modeling capability. Being at the intersection of the best of reliability engineering models and data science, the Newton™ powered QRO model enables reliability and operational leaders to drive a better reliability strategy than ever before, resulting in improved bottom line and process safety.
Closing Thoughts: In order to better serve customers and differentiate from the competition, service providers need to embrace software and technology as a method to enhance their offering and improve processes. We look forward to following Pinnacle as they continue to streamline how reliability is measured and managed in complex industrial facilities.