Reducing greenhouse gas emission from pipeline compressor stations is a critical challenge for operators. Traditional approaches to emissions reduction often depend on hardware upgrades that require capital investment and downtime. When considering alternative methods for emissions reduction, such as varying the operations of existing equipment, the task is complicated by the diversity of gas turbine and compressor manufacturers and models in service, each with distinct operational characteristics and performance behaviors. Operators need practical tools to identify how to dispatch their existing stations to reduce full and part load greenhouse gas emission without downtime or capital-intensive modifications. This report describes a spreadsheet-based tool developed to meet this need. The tool evaluates station operating conditions and recommends station setpoints that minimize greenhouse gas emissions while meeting throughput requirements and respecting equipment operational constraints. It generates optimized dispatch schedules across available units, identifying how gas flow can be best allocated to minimize greenhouse gas emissions across the station's operational range. The report describes the development and validation of supporting models, the design of the optimization framework, and example case studies demonstrating its application to representative stations. The report aims to help pipeline engineers, planners, and operations personnel understand how to deploy the spreadsheet-based tool to reduce greenhouse gas emissions with existing assets. With the developed tool, they can evaluate station performance, develop dispatch schedules, and implement operational strategies that reduce greenhouse gas emission while maintaining station throughput. The zipped deliverable package, PR592-242009-Z01 GHG Reduction at Compressor Stations Using Optimization with Physics-Informed Models, contains the following files: - Final Report - PR592-242009-R01 GHG Reduction at Compressor Stations Using Optimization with Physics-Informed Models.pdf - Optimization Tool User Guide - PR592-242009-M01 GHG Reduction at Compressor Stations Using Optimization with Physics-Informed Models User Guide.pdf - Excel-based Spreadsheet Optimization Tool - PR592-242009-E01 GHG Reduction at Compressor Stations Using Optimization with Physics-Informed Models.xlsm - Alternate version of the Excel-based Spreadsheet Optimization Tool without compressor map plotting, for compatibility with older excel versions - PR592-242009-E04 GHG Reduction at Compressor Stations Using Optimization with Physics-Informed Models NO MAPS.xlsm

Optimizing gas turbine maintenance can reduce total operating costs but raises the risk of unit failures. A large pipeline fleet requires constant up time, but experiences variation in unit-to-unit reliability and availability. There is an ongoing desire to optimize maintenance budget to maximize fleet availability. This can be done using detailed maintenance records; however, analyzing these in-depth for the entire fleet can be cumbersome. In this study, a Bayesian reliability and availability analysis is used to predict failure risks for both the fleet and individual units using only high level summary information including MTBF, MTTR, and asset service factor. Bayesian statistics enable transformation of these summary metrics into predictive distributions for reliability and availability accounting for seasonal and annual variations. The study considers a fleet of gas turbines and compares individual units to the fleet to identify outliers. This provides the first step in prioritizing maintenance decisions.

Effective power plant dispatch relies on precise performance predictions, particularly for gas turbines operating in changing environmental and operational conditions. This work builds on prior efforts constructing tools for performance visualization in both simple and combined cycle systems. Previous work developed a refined digital twin modeling framework to enhance performance predictions under changing weather conditions. With a set of training data, the resulting model requires only three ambient conditions pressure, temperature, and humidity to predict plant heat rate and power output. The goal was to strike a balance between modeling accuracy and practical usability, which tends to be missing in traditional approaches. This project introduces several advancements in the digital twin model. Extrapolation techniques were enhanced to improve reliability in scenarios outside the original training data. Augmentation modeling was developed to account for auxiliary systems and their effects on plant performance. Additionally, dispatch optimization integrates the performance prediction models with cost and operational constraints, enabling 7-day-ahead dispatch scheduling. Improvements were tested via a case study on Chevron Pipeline and Power gas turbines the result is a tool, Optora, supporting better management of power plant performance. Optora offers operators a clear understanding of how plants perform across diverse scenarios while accommodating uncertainties inherent to real-world operations.

The energy industry is undergoing unprecedented changes as it pursues global trends towards decarbonization, decentralization, and digitalization. Rapid development and deployment of big data and artificial intelligence technology over the past few decades have transformed the power generation industry in turning into a smarter industry that can monitor and adjust the status of key assets in real time. Digital twins, which are currently in the spotlight, are a technology that reproduce real physical assets using physical and data-driven models to simulate or predict the state of a system. There is a wide range of assets suitable for digital twins in power generation. They aim to identify changes in the system to detect anomalies or make maintenance decisions. The need for digital twins for energy transformation continues to grow. This paper provides a review of digital twin technology specific to the power generation industry. Among the power generation systems, digital twin studies for the combined cycle gas turbine, wind turbine, solar, and nuclear power plant were classified according to the lifecycle, complexity, and type of digital twin model, and the specific features and limitations of each application were analyzed. The goal is to provide readers with a curated summary of use cases which they may find useful in applying to their own work. The paper also explores the challenges and potential future research directions for increasing efficiency, availability, reliability, and solving environmental problems.

The EPA previously proposed new CO2 standards for both new and existing stationary combustion turbines under Section 111 of the Clean Air Act. At the time of writing, these standards would have had a have significant implications on the operation, capacity factor, reliability, availability, and performance of the gas turbine fleet within the U.S. power grid. The standards would impact the costs of operating the fleet which will impact fleet owners and operators and the public. The proposed standards limit CO2 emissions from new and existing sources and are justified with associated Best System of Emission Reductions (BSER) using Hydrogen-blended fuels or Carbon Capture and Storage. The paper shows that the BSER used to justify the proposed limits are insufficient (i.e., levels of Hydrogen and CCS required for rule compliance are beyond what is stated as BSER justification). Analysis is presented to consider the impact of the rules on the existing gas turbine fleet as operated including assessments of the amount of hydrogen required, number of plants that would be impacted, and projections of the required renewable generation required to replace non-compliant or curtailed gas turbines. The authors also discuss potential unintended incentivized actions based on the rules, such as early retirement of critical generation capacity, and minimizing plant capacity factors at the expense of total CO2 emissions. The methodology to assess the economy-wide impact of technology depends on the analysis’s assumptions. Therefore, this analysis does not predict specific outcomes but offers insights into potential impacts under certain assumed conditions.

Many utility monitoring and diagnostic centers have adopted advanced pattern recognition software to aid in anomaly detection and diagnosis. Due to the wide variety of electricity generation methods and associated supporting hardware, utilities choose software that is applicable to the broad category of industrial hardware. As a result, these tools excel at detecting large deviations from normal operation but struggle to identify subtle shifts in performance that are indicative of the onset of degradation and failure. At worst, these tools can be oversensitive and raise false alarms when the deviations are explained by operation outside of what was observed in the tool's training data. Recent developments in physics-based modeling have resulted in models that are capable of accurately detecting faults in the DC collector field that, individually, results in a less than 5% power loss at the combiner box level. These new models are benchmarked against current state-of-the-art utilities tools, with models designed to match the physics-based approach as much as is feasible. The applied physics-based models improve fault detection capabilities over the standard utility tool, detecting approximately twice as many real faults for a given false positive rate.

This paper presents an integration readiness assessment for Thermal Energy Storage (TES) concepts. TES’s primary motivation is to store surplus energy and release it as needed to balance demand. Within the broader energy market, TES seeks to capture arbitrage opportunities and enable higher capacity factors for Variable Renewable Energy (VRE) sources like wind and solar. The paper explores how integrating energy storage with gas-turbine-based power plants can enhance value and capacity while reducing CO2 emissions. Both simple cycle and combined cycle plants are considered. The paper carries out an Integration and System Readiness Assessment (ISRA) for three specific TES technologies: Brenmiller Crushed Rock, Pintail Power Liquid Salt Combined Cycle (LSCC), and Redox Box Thermochemical storage. The ISRA’s objective is to systematically evaluate the system readiness level (SRL) to determine the current development status and potential risks. Early identification of these risks can guide targeted demonstrations to mitigate risk and validate the technology. ISRA has been carried out for other systems but is being applied to the problem of the integration of new storage technology with existing generating assets with a desire to derisk technology showstoppers earlier in the maturation process. This paper demonstrates how this process can be used to focus technology development efforts on derisking activities vs. demonstration for demonstration’s sake. Interviews were conducted with the technology developers to evaluate their current status, challenges, and successes. The focus is not solely on the score but on using the method to identify the technologies’ development stage. This paper specifically addresses readiness for integration into gas turbine power plants. Controls and balance of plant challenges when integrating into existing power plants were a common area for development.

Gas turbines are the lynchpin of a stable and prospering U.S. power grid and economy. As more forward growth emphasizes renewables, maintaining the existing gas turbine fleet will become even more critical. Gas turbines undergo regular maintenance cycles that inspect, repair, and replace life limited parts. The complexity and invasiveness of maintenance often leads to variability in the resulting performance recovery. For example, parts may not be installed correctly or controls may not be adjusted after the outage as needed. While engineers have a personal ‘expectation model’, this often is incorrect and few organizations rigorously benchmark outage recovery to identify lost performance and incorrect repairs. This paper applies the EPRI Gas Turbine Digital Twin to a historical set of outages for B class gas turbines. A methodology is presented to track outage recovery by comparing model performance to site data pre and post outage and accounting for model and measurement uncertainty through the use of machine learning. This provides a probabilistic estimate of outage recovery which is used to create a fleet outage recovery expectation model. The intent is to use this model to benchmark and score future outages’ effectiveness. The resulting expectation model is also presented here for others to use in their own benchmarking efforts.

String, combiner, and tracker faults comprise a significant reduction in PV plant capacity. A method is presented to detect these faults using data typically monitored at utility-scale plants. The detection algorithm has been validated using aerial infrared data and the accuracy is presented across a range of sites, conditions, and scenarios, including automated versus manual model configuration and satellite versus ground-based weather data.

This paper outlines a process for proactive mitigation measures for detecting and preventing threats through detection of exploited vulnerabilities in power generation assets. In many cases, these vulnerabilities are only known to deep domain experts who are familiar with the intricacies of how these systems work, and not to cybersecurity experts. While a focus on IT security. represents the first line of defense, successful attacks on the OT systems can go beyond disruption to business operations or service and can lead to catastrophic equipment failure. Recent advancements in monitoring and diagnostics technology have been used to protect OT equipment from normal wear and tear but have not been fully operationalized to assist in detecting intrusions. Monitoring and Diagnostic (M&D) centers typically collect significant sensor data with the aim of detecting faults and failures in operating equipment; however, collection and analysis of additional data including control system settings, verification of sensor signals, and verification of proper actuator function is typically not analyzed. These functions are almost certainly not analyzed from the specific perspective of cybersecurity OT attacks. To help aid in discussions between plant engineers, M&D, and IT/OT, a process and examples are presented for identifying potential attack vectors in the cyber-physical OT systems. This includes a systematic identification of potential systems, categorical attack mechanisms, and cataloguing of the resulting impact.

Most photovoltaic power generation sites schedule maintenance as a result of physical inspections and observations. For example, a site may use aerial infrared imaging to determine the fault status of individual combiner boxes and/or strings. However, the costs to perform aerial scans result in infrequent, typically annual, application. As a result, DC faults can often go unnoticed for months at a time. While this repetitive, expensive task is attractive for automation, the limited granularity of modern sensor suites makes it difficult. The authors' work has enabled continuous, real-time PV anomaly detection using existing, installed sensor suites. This relies on a detailed knowledge of the site layout to correctly predict expected performance. Previously this information was manually codified using available site drawings for each site. However, the manual review and codification of metadata is time-consuming, increasing the investment required for an M&D center to implement the code. This difficulty is exacerbated by the competitiveness of the PV market, which has led to leaner O&M investments. This work presents a new method to estimate the site architecture using performance data and a fraction of the metadata. The setup speed is accelerated by more than a factor of 15, while achieving similar anomaly detection quality to the previous work using manually codified site layouts.

As gas turbines are operated and maintained, it is key to understand engine firing temperatures at cyclical and variable load operations, and more specifically, the tradeoff between engine performance, repair costs and reliability. It is crucial to ensure performance is maintained without sacrificing the life of critical parts. OEMs traditionally have not provided much information about how tuning activities can impact performance. The current practice of tuning to meet emissions and combustion dynamics, or pulsations, can directly impact output, efficiency, and hot gas path (HGP) component life. A good understanding how and when this can happen can empower users to ensure they get the best performance and understand tradeoffs between performance, operability, and emissions. To better explain the concept of ‘tuning’, this paper discusses and provides basic tuning guidance common for all gas turbines regarding how tuning steps can impact gas turbine firing temperature, performance, and emissions tradeoffs. A three-step process is described for; 1) assessing if there is evidence of temperature control curve changes; 2) performing a cursory analysis using existing gas turbine instrumentation and operating data to see if there is potential impact on firing temperature / turbine inlet temperature; and 3) examining for evidence of temperature change, whereby a means to analyze time series data using a physics-based model (EPRI gas turbine digital twin) to estimate delta changes in firing temperature pre and post outage is discussed. This process uses software tools available to the authors but is applicable to any trusted analysis toolset. The paper aims to enhance industry understanding of what is completed during combustion tuning; it provides information about tuning activities impact on gas turbine performance to connect the dots between tuning and performance; and it describes how to conduct a simplified digital twin heat balance analysis to better quantify these impacts.

Gas Turbine operator M&D centers currently spend a disproportionate amount of time responding to false alarms. Often, these false alarms are caused by errors in the instrumentation acquisition and recording chain. Sensors may fail outright, drift, or data may be corrupted during transmission or archival storage. Any one of these issues can lead to erroneous data which may lead to false alarms at the M&D center. Many advanced algorithms used for M&D are particularly susceptible to errors in input signals. Erroneous or missing data can cause issues during the training process and during diagnostic use. This work has constructed a physics-informed AI model which calculates a health indicator for faulty, mis-calibrated, or mis- recorded sensor readings. The process uses auto associative neural networks coupled with Historian data to identify not just a good/bad flag, but a likelihood score which indicates the probability that the reading is indeed erroneous. In the event the signal is anomalous, a digital twin model can be executed to determine if the issue is indeed instrumentation, or if the issue is hardware related. The method works for any physical asset and can be deployed using standard libraries available to gas turbine owners and operators.

Characterizing the performance of gas fired combined cycle power plants is critical to economic dispatch decisions. Dispatch models rely on an accurate prediction of Gas Turbine and combined cycle power output and heat rate. Approaches for generating performance characteristics range from correction curves to detailed thermodynamic performance models. Unfortunately, most techniques are either too simplified, require significant expertise, or are manually labor intensive. Furthermore, these performance estimation techniques do not intrinsically capture uncertainty due to the inherent variability of the weather and state of the asset. This paper proposes a physics-enhanced Artificial Intelligence technique for automatically characterizing power plant performance including uncertainty due to weather effects. The model uses a layered sub-model approach to rapidly learn power plant performance without the need for extensive data preparation. The proposed technique is used to evaluate for accuracy, ease of use, and level of automation. The new technique is accurate to within 1% and provides a power and efficiency forecast one week out. The technique is also applicable to other power generation assets and scaling techniques, and challenges will be discussed. An overview of the automation framework is provided including discussion on modeling approaches, AI approaches used, modeling techniques, and use cases.

Maintenance at large-scale photovoltaic plants employs a mix of preventative and corrective maintenance practices. Large outages, such as an inverter tripping offline, are often easy to detect. More subtle sub-inverter faults and failures can accumulate and go unnoticed for months or years. A software-based fault detection method has been developed to analyze commonly measured data from large-scale PV plants for more timely detection of subtle underperformance. The method has been demonstrated on eight datasets from large-scale plants with high accuracy of detection. Results are validated using aerial infrared scanning. String outages are detected with a true positive rate of 73 percent and tracker issues are detected with a true positive rate of 88 percent. The developed method can be uniformly applied to photovoltaic plants across a range of scales and configurations to assess performance, quickly detect underperformance, and determine the source and location of failures. The results inform and improve operations and maintenance at PV plants, ultimately aiding in improved affordability, reliability, availability, and resiliency of solar electricity.

At the Turbo Expo 2018: Turbomachinery Conference & Expedition, in Oslo, Norway, an innovative approach for assessing operating and near real-time data from power generating assets with meaningful predictive analytics was presented and discussed. GT2018-75030, entitled; Energy Innovation: A Focus on Power Generation Data Capture & Analytics in a Competitive Market established a challenging objective for the industry: “To advance the notion that the fusion of total plant data, from three primary sources, with the ability to transform, analyze, and act based on integrating subject matter expertise is essential for effectively managing assets for optimum performance and profitability; executing and delivering on the promise of “Big Data” and advanced analytics.” Throughout 2019 and 2020, a team comprised of members from Strategic Power Systems, Inc. ® (SPS), Turbine Logic (TL), and two National Labs; National Energy Technology Laboratory (NETL) and Oak Ridge National Laboratory (ORNL), collaborated on the paper’s hypothesis. The team worked with the support of funding from DOE’s Fossil Energy Program through its HPC4 Materials Program, which provided access to the High-Performance Computing assets at both laboratories. The team brought unique skills, strengths, and capabilities that would serve as the basis for an effective, open, and challenging collaboration. The engineering and data science disciplines that converged on this project provided the back-bone for the unbiased analysis and model building that took place; relying on a unique and up-to-date source of plant operating and design data essential for performing the engineering scope of work. A key objective was to use the data and the modeling to be predictive; to characterize remaining life, expended life, and to determine the “next failure” for critical systems and components. Proof-of-concepts were tested for longer term, data-driven reliability prediction for fleets of power generating assets, near real-time prediction of power plant faults which could lead to imminent failure, and physics-based model prediction of life consumption of critical parts. Each of these pilot scale projects is summarized with key results presented.

EPRI has been developing a digital twin of simple and combined cycle gas turbines over the last 5+ years to provide owners and operators with improved capabilities that typically reside in the expert domain of OEMs and 3rd party service providers. The digital twin is a digital model, a physics-based representation of the actual asset. The model is thermodynamic and is created with the intent to support 5 M&D areas: • Integrate with existing M&D tools such as advanced pattern recognition (APR) • Power plant performance prediction and trending such as day, week, and month ahead performance prediction for capacity and generation planning • Health Monitoring and Fault Diagnostics to support asset management with additional health scores and virtual instrumentation enabled by the digital twin model • Monitoring and prediction of both base and part-load performance. Many gas turbine tools have been simplified to work only at full load conditions. To be useful and to improve utilization of collected data, part-load conditions should also be considered. • Outage and repair impacts, including “what-if” capability to understand and quantify potential root causes of less than expected performance improvement or recovery after outage and repairs. This paper presents current progress in creating an EPRI Digital Twin applicable to gas turbines. The formulation, methodology, and real-world use cases are presented. To date, digital twins have been created and tested for both E and F class frames. This paper describes the process of generating closed-form equations capable of transforming existing, measured historian data into the health parameters and virtual sensors needed to better track unit health and monitor faulted performance. These equations encapsulate the digital twin physical model and provide end-users with a methodology to calibrate to their specific unit and efficiently use their choice of monitoring software. Tests have been performed using operator data and have shown good accuracy at detecting anomalous operation and predicting week ahead performance with excellent accuracy. Post-outage impact analysis is also assessed. Real-world application cases for the digital twin are also presented. Examples include using the digital twin to identify causes of post-outage emissions and performance issues, expected impact of degradation and fault conditions, and simulating improvements to operation through part repair and upgrades.

A team of researchers from multiple universities are collaborating on the demonstration of a hybrid turboelectric regional jet for 2030 under the NASA ULI Program. The thermal management is one of the major challenges for the development of such an electric propulsion concept. Existing studies hardly modeled the thermal management systems with the propulsion systems nor integrated it to the aircraft for system- and mission-level analyses. Therefore, it is very difficult to verify whether a design of the thermal management system is feasible and optimal based on current literature. To fill this gap, this paper presents a design of the thermal management system for the hybrid turboelectric regional jet under the ULI program and integrates it to the aircraft. The TMS is tested against the cooling requirements, where the thermal loads from the electric propulsion system are quantified through the whole mission. Potential solutions for peak thermal loads during takeoff and climb are also proposed and analyzed, where additional coolant or phase change materials are used. Moreover, the impacts of the TMS on the system- and mission-level performance are investigated by the presented integration approach as well. It is discovered that a basic oil-air thermal management system cannot fully remove the heat during the early mission segments. Using additional coolant or phase change materials as heat absorption can handle such heating problem, but penalty due to additional weight is added. It is found that greater penalties in fuel burn and takeoff weight are added by additional coolant solution than the phase change material solution.

Under the NASA University Leadership Initiative (ULI) program, a team of universities are collaborating on the advancement of technologies a hybrid turboelectric regional jet, with an intent to enter service in the 2030 timeframe. In the previous studies of the ULI program, the in-service benefits of the technologies under development were analyzed by integrating the technologies of interest to a 2030 regional jet with a hybrid turbo-electric distributed propulsion system. As the program has progressed, the projected performances for each technology and subsystem have been updated. This paper presents an update in the sizing and performance analysis of the regional jet with the hybrid turbo-electric distributed propulsion system, by integrating the updated values of the technologies and subsystems to the vehicle. The updates in this paper include the DC/AC conversion links, efficiency of generator and cabling losses, weight of the wires, the battery cooling through the environmental control system, motor and inverter cooling by the thermal management system, and the redundancy strategy of the propulsion system. The updates of the results from the integrated model include the overall efficiency of the propulsion system, mission fuel savings, mission energy flow distribution, and the optimal hybridization rate in climb and cruise. The overall fuel saving benefit for the target 600-nmi mission is 19.9% compared to the baseline aircraft.

Hybrid-electric gas turbine generators are considered a promising technology for more efficient and sustainable air transportation. The Ohio State University is leading the NASA University Leadership Initiative (ULI) Electric Propulsion: Challenges and Opportunities, focused on the design and demonstration of advanced components and systems to enable high-efficiency hybrid turboelectric powertrains in regional aircraft to be deployed in 2030. Within this large effort, the team is optimizing the design of the battery energy storage system (ESS) and, concurrently, developing a supervisory energy management strategy for the hybrid system to reduce fuel burn while mitigating the impact on the ESS life. In this paper, an energy-based model was developed to predict the performance of a battery-hybrid turboelectric distributed-propulsion (BHTeDP) regional jet. A study was conducted to elucidate the effects of ESS sizing and cell selection on the optimal power split between the turbogenerators (TGs) and ESS. To this extent, the supervisory energy management strategy is formulated into a discrete time optimal control problem and solved via dynamic programming. The performance of BHTeDP was compared to a turboelectric distributed-propulsion (TeDP) next-gen aircraft that assumes improvements in weight, drag, and engine efficiency consistent with regional jet entering operation in 2035.