Search NASA⌕ Search

SEARCH · Search NASA

Results for “prognostics”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,729 records · Page 96

A Multicenter Retrospective Analysis of Survival Outcome Following Postoperative Chemoradiotherapy in Non-Small-Cell Lung Cancer Patients With N2 Nodal Disease

Purpose: To retrospectively evaluate the role of postoperative chemoradiotherapy (POCRT) in patients with completely resected non-small-cell lung cancer (NSCLC) with N2 lymph node involvement. Methods and Materials: This study included 183 patients from four centers in southwest China who underwent radical section of Stage III-N2 NSCLC without any preoperative therapy. One hundred and four were treated with POCRT and 79 with postoperative chemotherapy (POCT) alone. The median radiation dose to clinical target volume (CTV) was 50 Gy (varying between 48 and 54 Gy), whereas the cycles of platinum-based chemotherapy ranged from two to six with a median of four. Results: The median duration of follow-up was 72 months. The 5-year overall survival rate (OS) was 30.5% in the POCRT group, and 14.4% in the POCT group (p = 0.007). The 5-year disease-free survival rate (DFS) was 22.2% in POCRT group and 9.3% in POCT group (p = 0.003). In a multivariate analysis, N1 nodal involvement (N1+/N2+) was associated with significantly worse OS (HR = 1.454, 95% CI, 1.012-2.087, p = 0.043) and DFS (HR = 1.685, 95% CI, 1.196-2.372, p = 0.003). Absence of radiotherapy and treatment with fewer than three cycles of chemotherapy both were poor prognostic factors for both OS and DFS. Conclusions: As compared with chemotherapy alone, adjuvant treatment with both radiotherapy and chemotherapy improves survival in patients with completely resected Stage III-N2 nodal disease in NSCLC. Future study of treatment modality with radiotherapy and chemotherapy is warranted, especially focusing on both N1 and N2 nodal status.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Is Elective Irradiation to the Lower Neck Necessary for N0 Nasopharyngeal Carcinoma?

Purpose: To summarize our experience and treatment results in lymph node-negative nasopharyngeal carcinoma treated in a single institution. Methods and Materials: From January 2000 to December 2003, 410 patients with lymph node-negative nasopharyngeal carcinoma were retrospectively analyzed. The T-stage distribution was 18.8% in T1, 54.6% in T2 (T2a, 41 patients; T2b, 183 patients), 13.2% in T3, and 13.4% in T4. All patients received radiotherapy to the nasopharynx, skull base, and upper neck drainage areas, including levels II, III, and VA. The dose was 64-74 Gy, 1. 8-2.0 Gy per fraction over 6.5-7.5 weeks to the primary tumor with {sup 60}Co or 6-MV X-rays, and 50-56 Gy to levels II, III, and VA. Residual disease was boosted with either {sup 192}Ir afterloading brachytherapy or small external beam fields. Results: The median follow-up time was 54 months (range, 3-90 months). Four patients developed neck recurrence, and only 1 patient (0.2%) experienced relapse outside the irradiation fields. The 5-year overall survival rate was 84.2%. The 5-year relapse-free survival rate, distant metastasis-free survival rate, and disease-free survival rate were 88.6%, 90.6% and 80.1%, respectively. Both univariate and multivariate analyses demonstrated that T classification was the only significant prognostic factor for predicting overall survival. The observed serious late toxicities were radiation-induced brain damage (7 cases), cranial nerve palsy (16 cases), and severe trismus (13 cases; the distance between the incisors was {<=}1 cm). Conclusion: Elective levels II, III, and VA irradiation is suitable for nasopharyngeal carcinoma without neck lymph node metastasis.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Application of Margin-Based Methods to Assess System Health

Health management of complex systems such as nuclear power plants is an essential task to guarantee system reliability. This task can be greatly enhanced by constantly monitoring asset status and performances and process such data (through anomaly detection, diagnostic, and prognostic computational algorithms) to identify asset degradation trends and faulty states. While such information and data are typically available for many of the assets, they are not propagated from the asset to the system level in order to identify the most critical assets and prioritize maintenance and surveillance activities. The main reason is driven by the fact that current reliability modeling techniques are inadequate to process such information/data. This is due to the nature of these techniques which are based on the concept of failure rate/probability that do not serve an operational context where quantitative asset health information is available. Simply stated, current reliability techniques serve a run-to-failure operational setting and not a predictive maintenance one where the goal is to perform maintenance and surveillance activities only when they are needed based on asset health. The risk informed asset management (RIAM) project is focusing on the development of a different kind of reliability modeling techniques designed to adequately serve a predictive operational setting. Such reliability techniques move aways from a failure rate/probability to a margin-based mindset where margin is here used as a metric to quantify asset health based only on current and past operational experience of the asset under consideration. In addition, margin-based reliability techniques are able to propagate asset health information from the component to system level and provide importance measure to each asset. This report summarizes a recent activity performed in collaboration with plant modernization pathway designed to integrate monitoring data into margin-based reliability models. Such activity focuses on a specific system of an existing nuclear power plant where large amount of historic monitoring data is used to monitor asset and system health.

97 MATHEMATICS AND COMPUTING↗

Russian-Norwegian Cooperation In Regulation of the Public Radiation Protection in the Northwest Russia - 12440

In 1960's, the large technical bases of the Northern Fleet were arranged on the Kola Peninsula. These bases were involved in support of nuclear submarines performing acceptance and storage of radioactive waste (RW) and spent nuclear fuel (SNF). Since 1985, the waste acceptance has been stopped and the technical bases changed their functions to serve as sites of temporary storage (STS). According to the RF Government Directive of 09 February 2000 No 220-r, the STS were put under Rosatom responsibility in order to conduct operations dealing with the SNF and RW management being accumulated during the naval activity and originated from dismantlement of nuclear submarines and surface ships equipped with nuclear powered installations, as well as to carry out environmental remediation of radiation hazardous facilities in this region. The international collaborative assistance is very important to increase effectiveness of such works. This paper includes the findings of cooperation between the Federal Medical Biological Agency (FMBA) and Norwegian Radiation Protection Authority (NRPA) in radiation protection of the public in the course of the STS remediation. Since 2004, the following works has been carried out in this direction: - radiation threat assessment and identification of the priority directions of radiation and hygienic studies; - radiation situation inspections on-site and within the coastal offshore waters at different stage of remediation; - development of the documents including the criteria for the STS remediation and guidelines for radiation monitoring to control the mentioned criteria compliance; - development of the radio-ecological geo-information system. The developed criteria consider four basic options of the STS remediation - renovation, conversion, conservation and liquidation. The main (dose) and derived remediation levels have been determined for each option. The resulted from monitoring radiation parameters - including contents of {sup 137}Cs, {sup 90}Sr and {sup 60}Co in samples of soil, vegetation, seawater, seaweeds, bottom sediments, invertebrates and vertebrates, gamma dose rate values - are integrated in the database, which is the component of the geo-information system. The developed regulative and methodical documents and the geo-information system have been introduced in Regional Management-120 under FMBA of Russia, which is responsible for the radiation safety supervision, Centre of Hygiene and Epidemiology-120 under FMBA of Russia, which carries out regulatory radiation control, and in the operating organization involved in the STS remediation and responsible for radiation protection of workers and public. The works completed have permitted to solve the majority of problems in enhancement of radiation and hygienic supervision of SevRAO operation. However, some relevant questions in this area need additional efforts. In particular, in the course of specification of the design solutions, obtaining additional data on the radiation situation parameters and clarification of the prognostic assessments, the necessity will certainly arise to amend the regulatory documents taking the adopted design solutions into account. We are on the way to real results. Much has been done for the first time, and although it is difficult to foresee all future problems and challenges, our knowledge, experience and close cooperation permit to assess the prospects confidently. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Environmental Radiation Monitoring at the Areas of the Former Military Technical Bases at the Russian Far East - 12445

After termination of operation at the serviced facilities of the nuclear fleet of the former Soviet Union, the Military Technical Base in Sysoeva Bay has been reorganized to the site for SNF and RW temporary storage (STS). The main activities of STS are receipt, storage and transmission to radioactive waste reprocessing. Establishment of the RW management regional centre in the Far-Eastern region at the STS in Sysoeva Bay implies intensification of SNF and RW management in this region that can result in increasing ecological load to the adjacent areas and settlements. Regulatory supervision of the radiation safety at the areas of the Former Military Technical Bases at the Russian Far East is one of the regulatory functions of the Federal Medical Biological Agency (FMBA of Russia). To regulate SNF an RW management and provide the effective response to changing radiation situation, the environmental radiation monitoring system is arranged. For this purpose, wide range of environmental media examinations at the Sysoeva Bay STS was performed by Burnasyan Federal Medical Biophysical Centre - a technical support organization of FMBA of Russia in collaboration with the Federal State Geological Enterprise 'Hydrospecgeology' (Federal Agency for Entrails). Regulation during the RW and SNF management is continuous process, which the FMBA of Russia implements in close cooperation with other Russian responsible authorities - the State Atomic Energy Corporation 'Rosatom' and Federal Agency for Entrails. The Environmental radiation monitoring findings served as a basis for the associated databank arrangement. The radio ecological monitoring system was arranged at the facilities under inspection for the purpose of the dynamic control of the radiation situation. It presupposes regular radiometry inspections in-situ, their analysis and assessment of the radiation situation forecast in the course of the STS remediation main stages. Some new data on the radiation situation at the facilities will appear in future and the prognostic assessment will become more precise. The mentioned natural, practical and theoretical works is a base for the development of the set of regulatory documents to assure radiation protection and safety of workers, public and environment, as well as development of documents to regulate SNF and RW management at the STS facilities. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Twenty Years and Counting—Where are they? Practical Recommendations for Commercializing AI/ML for Intrusion Detection in the Nuclear Industry

Research and development into applications for improving equipment condition monitoring programs at nuclear facilities has been around since the 1990s. However, while the field has moved from using data-driven machine learning (ML) algorithms for detection and prediction of equipment degradation and failure to prognostic capabilities, these applications are still not widely used in the U.S. nuclear industry. Additionally, there has been significant effort in designing both data-driven and physics-based artificial intelligence (AI) and ML models for many other potential applications in the nuclear industry, including cyber intrusion detection systems (IDS). However, as the last twenty years in condition-based maintenance research has shown us, there are significant hurdles that must be overcome for deployment of IDS on plant systems. This paper provides a discussion on the practical recommendations that researchers should consider for successful adoption of AI/ML IDS in the nuclear industry.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗

Panel Session 94: Nuclear and Industrial Robotics, Remote Systems and Emerging Technologies

This panel focused on the use and benefits of robotics in different nuclear environments. Examples of robotics deployed in nuclear environments that come from industry, academia, and the government were presented. It is through these varying perspectives that the panel participants will show the breath of nuclear robotics used across the world. Presentations proposed include: 1 - Robotics and Emerging Technologies at Assystem (Fanny Fouin, Assystem Energy and Infrastructure (United Kingdom)); 2 - An Undergraduate Perspective (Michael DiBono, Applied Research Center - FIU (USA)); 3 - US-ROK International Collaboration on Robotics and Remote Systems for D and D of NPPs (Young Soo Park, Argonne National Laboratory (USA)); 4 - EM's Historical Engagement with Robotics and Universities (Genia McKinley, US DOE (USA)); 5 - Robotic Systems for Environmental Remediation Applications (Leonel Lagos, Applied Research Center - FIU (USA)); 6 - Remote and Nuclear Challenges and Solutions at the Savannah River Site - SRS (Jean Plummer, Savannah River National Laboratory (USA)); 7 - Nuclear and Industrial Robotics, Remote Systems and Emerging Technologies Challenges, Opportunities and Prognostications (Kim 'KD' Auclair, KD Auclair and Associates LLC (USA))

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Assessment of dynamic PRA techniques with industry average component performance data - 208

In the nuclear industry, risk monitors are intended to provide a point-in-time estimate of the system risk given the current plant configuration. Current risk monitors are limited in that they do not properly take into account the deteriorating states of plant equipment, which are unit-specific. Current approaches to computing risk monitors use probabilistic risk assessment (PRA) techniques, but the assessment is typically a snapshot in time. Living PRA models attempt to address limitations of traditional PRA models in a limited sense by including temporary changes in plant and system configurations. However, information on plant component condition is not considered. This often leaves risk monitors using living PRA models incapable of conducting evaluations with dynamic degradation scenarios evolving over time. There is a need to develop enabling approaches to solidify risk monitors to provide time- and condition-dependent risk by integrating traditional PRA models with condition monitoring and prognostic techniques. This paper presents an estimation of system risk evolution over time by integrating plant risk monitoring data with dynamic PRA methods that incorporate aging and degradation. Several online, nondestructive approaches have been developed for diagnosing plant component conditions in the nuclear industry, i.e., using a condition indication index, vibration analysis, current signatures, and operational history . In this work, the component performance measures at U.S. commercial nuclear power plants are incorporated within the dynamic PRA methodologies to provide better estimates of the probability of failures. Aging and degradation are modeled within the Level 1 PRA framework, are applied to several failure modes of pumps, and can be extended to a range of components, namely, valves, generators, batteries, and pipes. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Identifying requisite changes to support modern maintenance practices - 294

Modern data science and processing require the use of modern maintenance records. With traditional record-keeping practices, the isolated nature of the data, as well as the presence of handwritten maintenance work orders and incomplete service logs, severely limit the amount of progress that can be made towards advanced condition-based maintenance. These condition-based methods of diagnostics, prognostics, and maintenance planning are a primary goal of next-generation plant operations and maintenance strategies, and are all dependent on the availability of quality plant data including maintenance data. By implementing changes to maintenance record-keeping practices, such as the use of a computerized maintenance management system, key data will become available to allow for implementation of state-of-the-art data analysis methods. This paper covers the benefits of utilizing digital record systems to increase maintenance data availability in terms of condition-based maintenance and asset management. The ability of these methods to enable state-of-the-art practices within industrial organizations is discussed to offer insight into ways that these improvements to operating strategy will contribute to improvements in world-class maintenance excellence. A discussion of the future of asset management in terms of data analytics, maintenance decision support, and data integration is provided to illustrate the changing landscape of plant management. The result is an examination of innovative maintenance strategies and discussion of challenges related to the future of asset management and implementing modern maintenance practices. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Behavior-based approach to misuse detection of a simulated SCADA system - 339

This paper presents the initial findings in applying a behavior-based approach for detection of unauthorized activities in a simulated Supervisory Control and Data Acquisition (SCADA) system. Misuse detection of this type utilizes fault-free system telemetry to develop empirical models that learn normal system behavior. Future monitored telemetry sources that show statistically significant deviations from this learned behavior may indicate an attack or other unwanted actions. The experimental test bed consists of a set of Linux based enterprise servers that were isolated from a larger university research cluster. All servers are connected to a private network and simulate several components and tasks seen in a typical SCADA system. Telemetry sources included kernel statistics, resource usages and internal system hardware measurements. For this study, the Auto Associative Kernel Regression (AAKR) and Auto Associative Multivariate State Estimation Technique (AAMSET) are employed to develop empirical models. Prognostic efficacy of these methods for computer security used several groups of signals taken from available telemetry classes. The Sequential Probability Ratio Test (SPRT) is used along with these models for intrusion detection purposes. The different intrusion types shown include host/network discovery, DoS, brute force login, privilege escalation and malicious exfiltration actions. For this study, all intrusion types tested displayed alterations in the residuals of much of the monitored telemetry and were able to be detected in all signal groups used by both model types. The methods presented can be extended and implemented to industries besides nuclear that use SCADA or business-critical networks. (authors)

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Automating Anomaly Detection for Target systems at Spallation Neutron Source

The Spallation Neutron Source (SNS) at Oak Ridge National Laboratory, produces the world’s most intense pulse neutrons beams. An accelerated proton beam is directed into a mercury target to generate neutrons via spallation. The target system accounted for over 40% of the overall downtime of the facility in 2022. Thus, early detection in anomalies in the target systems can enable taking corrective actions to avoid failures and reduce downtime. Fault prognostics and anomaly detection in accelerators, both at SNS and outside, has largely focused on the beam side. This paper presents one the first studies exploring leveraging machine learning to automate the detection of anomalies in the target system. The target system consists of over 30 different interconnected subsystems, and the present work focuses on the mercury process system as a use case. Analyzing data from 28 process variables from 2022 and 2023, tree-based and reconstruction-based algorithms are employed to detect anomalies in archived data. The algorithms detected previously unreported anomalies, several of which were deemed alert worthy by human experts, particularly those found by reconstruction-based algorithms. Using data from each production run in the accelerator increased the generalizability of the models in time. Efforts are now underway to implement a workflow for incorporating human feedback to update the models and evaluating performance on unseen data. The models will eventually be integrated into the existing System Tracking and Reliability system with a web interface for automated anomaly detection and reporting along with a pathway for incorporating human feedback for model updates.

Raj, Anant [ORNL] (ORCID:0000000306711244)↗

System Engineers and Decisions: It?s All about Knowledge

In order to guarantee that a system meets adequate levels of reliability and availability, system performances are continuously monitored and analyzed thanks to the technological advancements driving the Industry 4.0 revolution. An Industry 4.0 approach is typically based on advanced statistical, big data mining, machine learning, and internet-of-things methods designed to detect anomalies in the behavior of system, detect the most likely failure modes, and provide indications to system engineers on when maintenance activities should be performed before system performance are deemed unacceptable (which can be generated by diagnostic and prognostic methods). However, these analyses, which are designed to automatize and increase the efficacy of the system maintenance program, require large amount of data which can come in various forms: numeric, textual, images, sounds etc. Such data constitutes the historic knowledge benchmark to track system performances and support system engineer decisions. Here we claim that data is not sufficient to support this kind of analyses when applied to systems characterized by complex architectures and behaviors. Robust system engineer decisions require the ability to understand the system operational context that lies behind the observed data elements. In this respect, system models are in fact necessary to “put data in context” and capture relationships between data elements. Industry 4.0 methods require in fact contextual knowledge as a basis upon which hypotheses can be generated and assumptions tested. In our view, for complex systems, model-based system engineering (MBSE) models can afford this contextual knowledge, as they are typically used to describe systems architecture and dynamic behaviors. System knowledge is here intended as the blending of collected data and system architecture which takes the form of a “knowledge graph”. A knowledge graph is a database which consists of a large set of nodes (in our case an entity can be either a data or an MBSE element) which are linked to each other. The types of nodes and links follow a pre-defined topology, sometimes also refers as an ontology, that is designed to fit the actual decisions that needs to be performed. We show here how a knowledge graph can be defined to support system engineer maintenance decisions and how the same graph can be built based on system MBSE models and pre-processed data from numeric (through anomaly detections and diagnostic methods) and textual elements (through technical language processing TLP).

97 - MATHEMATICS AND COMPUTING↗

A Risk-Informed Approach to Trustworthiness Assessment in Digital Twins-Based Autonomous Control

In autonomous control systems, digital twins (DTs) are used to perform diagnostic and prognostic functions. The trustworthiness of these DTs is dependent on quality and coverage of the training data, model accuracy and integrity of sensor data. This work introduces a methodology to determine the trustworthiness of a DT system given faulty sensor data using a risk informed approach. Bayesian Belief Networks (BBNs) are used to propagate uncertainties and determine the probability of trustable recommendations. The decision to trust the control action provided by the DT is based on the DT output, expert opinion, and severity of problems. The performance of DTs is reliant on the data they are trained on. When they encounter out of distribution data, the trustworthiness of the recommendations decreases. To address this issue, we include an expert component that provides input on sensor degradation. For this, we utilize a generative artificial intelligence (AI) model, such as Generative Pretrained Transformer (GPT). The GPT functions as an expert with broad knowledge. The GPT is fine-tuned to understand and discriminate sensor degradation scenarios using manufactured data. This methodology is demonstrated through a case study on a Nearly Autonomous Management and Control System (NAMAC) during a steady state scenario. Various sensor degradation types with different severity levels are considered. Degraded sensor data is processed by the DT system and the fine-tuned GPT. Finally, using the BBN, we combine the GPT information and the DT output with its sources of uncertainty. This provides an output regarding the trustworthiness of the DT recommendation.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗

Nuclear Hybrid Energy Systems: Imperatives, Prospects, and Challenges

As global population reaches an expected 8 billion people by 2030, primary energy consumption is expected to increase by almost 40% from approximately 520 exajoules consumed today to almost 740 exajoules. Much of this increase is expected to come from non-Organization for Economic Cooperation and Development (OECD) nations, and Asia specifically. In these economies, energy used for transportation is expected to grow substantially, as is industrial, commercial and to a lesser degree residential energy use, creating considerable pressure on global and local energy markets. The magnitude and timing of growth in energy consumption likely will create a global imperative to deploy energy production technologies that balance the three pillars of energy security: • economic stability – related to the affordability of energy products, stability and predictability in their price, and the efficient and effective deployment of global capital resources in their development; • environmental sustainability – related to minimizing the negative impacts of energy production to air, land, and water systems and advancing the long-term viability of using a particular resource in a way that does not limit future generations ability to prosper; • resource security – related to the ability to access energy resources and products where and when necessary, in an affordable and predictable manner. One approach to meeting these objectives is hybrid energy systems (HES). Broadly described, HES are energy product production plants that take two or more energy resource inputs (typically includes both carbon and non-carbon based sources) and produce two or more energy products (e.g. electricity, liquid transportation fuels, industrial chemicals) in an integrated plant. Nuclear energy integration into HES offers intriguing potential, particularly if smaller (<300 MWe) reactors are available. Although the concept of using nuclear energy in a variety of non-electrical process applications is certainly not new, renewed interest in more tightly coupled energy product plants (such as HES) that meet the objectives outline above have gained additional interest recently, an interest likely sparked by sharpening energy security concerns. Studies have shown that non-nuclear integrated (hybrid) energy systems can have appealing attributes in terms of overall process efficiency, enhanced electric grid stability, renewable energy integration, and economic performance, and lifecycle greenhouse gas emissions. These attributes seem to be sufficiently compelling that several significant commercial investments in fossil-renewable HES are being made in the United States while the U.S. Defense Advanced Research Projects Agency (DARPA) has openly solicited information regarding nuclear energy integration schemes. The challenges of nuclear energy integration include myriad issues associated with the following RD&D areas, or “platforms”: • feedstock processing (e.g. bio-feedstock integration with coal, carbon feedstock extraction using nuclear energy); • heat / energy management (e.g. advanced heat exchangers, process design); • energy storage (e.g. H2 production, liquid fuels synthesis); • byproduct management (e.g. CO2 recycle approaches); • systems dynamics, integration and control (e.g. process dynamics analyses and optimization, advanced prognostics, diagnostics, variable time scale control and flow sheet optimization).

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Material Aging and Degradation Detection and Remaining Life Assessment for Plant Life Management

One of the major factors that may impact long term operations is structural material degradation, Detecting materials degradation, estimating the remaining useful life (RUL) of the component, and determining approaches to mitigating the degradation are important from the perspective of long term operations. In this study, multiple nondestructive measurement and monitoring methods were evaluated for their ability to assess the material degradation state. Metrics quantifying the level of damage from these measurements were defined, and evaluated for their ability to provide estimates of remaining life of the component. An example of estimating the RUL from nondestructive measurements of material degradation condition is provided.

Bayesian prognostics↗

Artificial intelligence to unlock real-world evidence in clinical oncology: A primer on recent advances

Purpose: Real world evidence is crucial to understanding the diffusion of new oncologic therapies, monitoring cancer outcomes, and detecting unexpected toxicities. In practice, real world evidence is challenging to collect rapidly and comprehensively, often requiring expensive and time-consuming manual case-finding and annotation of clinical text. In this Review, we summarise recent developments in the use of artificial intelligence to collect and analyze real world evidence in oncology. Methods: We performed a narrative review of the major current trends and recent literature in artificial intelligence applications in oncology. Results: Artificial intelligence (AI) approaches are increasingly used to efficiently phenotype patients and tumors at large scale. These tools also may provide novel biological insights and improve risk prediction through multimodal integration of radiographic, pathological, and genomic datasets. Custom language processing pipelines and large language models hold great promise for clinical prediction and phenotyping. Conclusions: Despite rapid advances, continued progress in computation, generalizability, interpretability, and reliability as well as prospective validation are needed to integrate AI approaches into routine clinical care and real-time monitoring of novel therapies.

60 APPLIED LIFE SCIENCES↗

Co-optimization of nuclear reactor flexible power operation and maintenance scheduling

As flexible power operation of nuclear power plants becomes more attractive due to the reduction in fossil-fueled dispatchable generation on energy grids, finding optimal power production strategies that balance revenue generation with operational concerns becomes more complex. This article presents a general framework to aid operators in designing economically optimal long term dispatch strategies for nuclear power plants. The principal novelty is the linking of estimated system remaining useable life (RUL) to strategic operational decisions. It is shown that, depending on the relationship between the fixed costs from maintenance and the associated lost revenue from an outage, it can be economically optimal in the long term to delay a maintenance outage and not perform this alongside refueling. For a given relationship between power ramping and degradation, optimal strategies were found that discouraged load following in some situations while minimizing unnecessary maintenance. It is shown that heavy load following can cause maintenance and refueling outages to diverge due to their inverse relationships with respect to load following, potentially leading to a significant loss in capacity factor. As a result, this general framework can be applied to specific reactor dispatch allowing operators to adapt operational strategies as future grid conditions change.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Rapid failure mode classification and quantification in batteries: A deep learning modeling framework

Unique, rapid identification and quantification of the dominant aging modes in lithium-ion batteries (LiBs) with early and non-specialized test data is a significant scientific challenge. Leveraging synthetic-data, deep-learning (DL) techniques have great potential to enable fast and robust classification and quantification of battery aging modes that produce different patterns of cell aging. This study, for the first time, presents a synthetic–data-based DL modeling framework for rapid and automatic classification and quantification of battery-aging modes and resultant aging with experimental validation. Availing synthetic dQ.dV -1 curves for ~26000 initial conditions and aging modes, the framework classified the dominant aging modes, for cells undergoing fast charge, in fewer than 100 cycles. Upon classification, the framework quantified the evolution of the aging modes, which were often nonuniform with cycling, for 22 gr/NMC532 pouch cells tested up to 600 cycles at different charging rates (1C–9C).

25 ENERGY STORAGE↗