SBIR-STTR Award

The energy transport and refining sectors are challenged with reliably delivering safer and cleaner energy to US consumers while meeting an ever-growing global demand. The energy infrastructure of US refineries and pipelines is aging, and corrosion and damage mechanisms are constant threats to mechanical integrity and safety. However, governments and industry stakeholders are reluctant to replace or upgrade the existing infrastructure due to the immense cost. To better understand and mitigate the risks of aging infrastructure, strong technical analysis capabilities, combined with the optimization of monitoring and decision making, is critical. Today, this is accomplished via complex simulations and data analysis. However, what is often lacking in this is the decision and optimization support to save money and ensure safe operation. To this end, advanced life cycle management software will be developed that leverages state-of-the-art Bayesian Artificial Intelligence and High- Performance Computing paradigms. This will result in field engineers and plant managers to make more data-driven solutions that also grasp the underlying cause-effect relationships and maintain corporate memory. In Phase I, the main infrastructure for the Bayesian ENGine for Insights (Bengi) will be built out and enhanced with the infusion of Department of Energy High Performance Computing libraries. The project consists of 4 main modules that will lay the foundation for the industrial decision engine. The conditional probabilities libraries that relate probabilities of cause-effect events will be developed as the “Nuts & Bolts” for the engine. Then, a series of Tensor- based algorithms will be implemented with the infusion of HPC libraries. This is the primary challenge: bringing extreme-scale Bayesian Decision Network technology to the heavy industry sectors. Industrial scale Bayesian Networks will enable fast and efficient decision-making processes and allow engineers to maximize their prior knowledge. Finally, a user interface will be developed in parallel to enable end-users of various expertise to have access to the underlying R&D code base. The Bayesian AI technology developed here will be directly applicable to all aging equipment affected by pitting, weld defects, crack-like flaws, environmentally accelerated crack growth and various other damage mechanisms. These damage mechanisms also occur in many non-energy industries as well, and this engineering-based AI framework can help each of them reduce risk and make smarter life-cycle decisions. The direct cost of corrosion to the US is estimated to be approximately 3% of GDP and the indirect cost may well be above 6% of GDP. All industrial operations need to be able to effectively monitor, inspect and manage aging equipment. Further, the demand for petrochemicals and supply stocks in the midwestern United States are rapidly increasing, making well placed to deliver a regional impact. There is a large market for the engineering-based intelligent framework developed in this project to help operators safely extend the lives of their equipment. The commercial impact is not only in the unlocking of the data in heavy industries, but also enabling end-users to make Bayesian AI supported decisions to optimize workflows and drive down costs.

In the aging energy industries, pressurized fixed equipment and piping systems are exposed to harsh environments and operating conditions that promote a whirlwind of undesirable damage mechanisms. This damage may eventually result in catastrophic failure (leak or rupture) if left unchecked, with potentially significant consequences, especially if there is an environmental release of toxic or flammable fluids. Failure can also lead to loss of production, damage to nearby equipment, personnel injury, loss of life, and repair, replacement, and legal costs. To minimize the likelihood of unexpected failures, proactive inspection and maintenance plans are required. These plans require complex decision-making platforms to assist in integrating data and experience that ultimately end up in a series of decisions. From the foundational work accomplished in Phase I, we have developed an explainable AI engine for making such large-scale complex decisions. The core technology was made possible by leveraging DOE funded tensor engine libraries. This engine, called Bayesian ENGine for Insights (Bengi), is based on probabilistic cause-and-effect diagrams known as Bayesian Decision Networks. By using these networks, decisions under uncertainty are optimized in even the most complex scenarios to minimize cost, maximize profitability, and increase safety. Bayesian Networks properly blend data from various sources, such as human knowledge, mathematical models, numerical simulations, and field observations. In Phase I of this project: (1) We explored more advanced tensor contraction algorithms and data structures. In the end, we were able to integrate DOE HPC libraries into Bengi’s core tensor engine. Bengi now supports multiple backends.; (2) We built networks efficiently with a CPT library and thematic network generator. Now we can quickly generate networks on-the-fly without the use of a user-interface for systems level networks.; (3) Implemented the graph theoretic infrastructure to compute complex decision hierarchies. These algorithms were then used to implement the optimal decisions algorithm leveraging tensor solvers.; and (4) Incorporated these innovations into a user-interface, with a coherent user-experience in mind, to enable a wide array of users to have access to DOE-funded HPC software and resources. In Phase II of this project, the goal is to combine the modules that were developed in Phase I and extend, refine, verify, and commercialize those efforts as part of a complete decision-making solution for the next level of Life Cycle Management. To circumvent the limitations of traditional of Life Cycle Management and address the industry need for a financial-based automated decision support tool, we propose leveraging Bengi to develop Risk-Based Inspection Plus, a probabilistic cost-benefit analysis extension to traditional risk-based inspection that recommends optimal lifecycle decision strategies. During Phase II we will develop a market-ready the Risk-Based Inspection Plus software into a solution centered around facility-wide, financial-based inspection optimization with integrated fitness-for- service capabilities. The project is the fusion of tensor based HPC libraries and asset integrity management