http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
INCORPORATING PRIOR BELIEF IN THE GENERAL PATH MODEL: A COMPARISON OF INFORMATION SOURCES
Coble, Jamie,Hines, J. W esley Korean Nuclear Society 2014 Nuclear Engineering and Technology Vol.46 No.6
The general path model (GPM) is one approach for performing degradation-based, or Type III, prognostics. The GPM fits a parametric function to the collected observations of a prognostic parameter and extrapolates the fit to a failure threshold. This approach has been successfully applied to a variety of systems when a sufficient number of prognostic parameter observations are available. However, the parametric fit can suffer significantly when few data are available or the data are very noisy. In these instances, it is beneficial to include additional information to influence the fit to conform to a prior belief about the evolution of system degradation. Bayesian statistical approaches have been proposed to include prior information in the form of distributions of expected model parameters. This requires a number of run-to-failure cases with tracked prognostic parameters; these data may not be readily available for many systems. Reliability information and stressor-based (Type I and Type II, respectively) prognostic estimates can provide the necessary prior belief for the GPM. This article presents the Bayesian updating framework to include prior information in the GPM and compares the efficacy of including different information sources on two data sets.
Incorporating Prior Belief in the General Path Model: A Comparison of Information Sources
Jamie Coble,WESLEY HINES 한국원자력학회 2014 Nuclear Engineering and Technology Vol.46 No.6
The general path model (GPM) is one approach for performing degradation-based, or Type III, prognostics. TheGPM fits a parametric function to the collected observations of a prognostic parameter and extrapolates the fit to a failurethreshold. This approach has been successfully applied to a variety of systems when a sufficient number of prognosticparameter observations are available. However, the parametric fit can suffer significantly when few data are available orthe data are very noisy. In these instances, it is beneficial to include additional information to influence the fit to conformto a prior belief about the evolution of system degradation. Bayesian statistical approaches have been proposed to includeprior information in the form of distributions of expected model parameters. This requires a number of run-to-failure caseswith tracked prognostic parameters; these data may not be readily available for many systems. Reliability information andstressor-based (Type I and Type II, respectively) prognostic estimates can provide the necessary prior belief for the GPM. This article presents the Bayesian updating framework to include prior information in the GPM and compares the efficacyof including different information sources on two data sets.
Maintenance-based prognostics of nuclear plant equipment for long-term operation
Zachary Welz,Jamie Coble,Belle Upadhyaya,Wes Hines 한국원자력학회 2017 Nuclear Engineering and Technology Vol.49 No.5
While industry understands the importance of keeping equipment operational and well maintained, theimportance of tracking maintenance information in reliability models is often overlooked. Prognosticmodels can be used to predict the failure times of critical equipment, but more often than not, thesemodels assume that all maintenance actions are the same or do not consider maintenance at all. Thisstudy investigates the influence of integrating maintenance information on prognostic model predictionaccuracy. By incorporating maintenance information to develop maintenance-dependent prognosticmodels, prediction accuracy was improved by more than 40% compared with traditional maintenanceindependent models. This study acts as a proof of concept, showing the importance of utilizing maintenance information in modern prognostics for industrial equipment.
Plutonium mass estimation utilizing the ( α ,n) signature in mixed electrochemical samples
Stephen N. Gilliam,Jamie B. Coble,Braden Goddard 한국원자력학회 2022 Nuclear Engineering and Technology Vol.54 No.6
Quantification of sensitive material is of vital importance when it comes to the movement of nuclear fuelthroughout its life cycle. Within the electrorefiner vessel of electrochemical separation facilities, the taskof quantifying plutonium by neutron analysis is especially challenging due to it being in a constantmixture with curium. It is for this reason that current neutron multiplicity methods would prove ineffective as a safeguards measure. An alternative means of plutonium verification is investigated thatutilizes the (a,n) signature that comes as a result of the eutectic salt within the electrorefiner. This is doneby utilizing the multiplicity variable a and breaking it down into its constituent components: spontaneous fission neutrons and (a,n) yield. From there, the (a,n) signature is related to the plutonium contentof the fuel
Gursel Ezgi,Reddy Bhavya,Khojandi Anahita,Madadi Mahboubeh,Coble Jamie Baalis,Agarwal Vivek,Yadav Vaibhav,Boring Ronald L. 한국원자력학회 2023 Nuclear Engineering and Technology Vol.55 No.2
Human error (HE) is an important concern in safety-critical systems such as nuclear power plants (NPPs). HE has played a role in many accidents and outage incidents in NPPs. Despite the increased automation in NPPs, HE remains unavoidable. Hence, the need for HE detection is as important as HE prevention efforts. In NPPs, HE is rather rare. Hence, anomaly detection, a widely used machine learning technique for detecting rare anomalous instances, can be repurposed to detect potential HE. In this study, we develop an unsupervised anomaly detection technique based on generative adversarial networks (GANs) to detect anomalies in manually collected surveillance data in NPPs. More specifically, our GAN is trained to detect mismatches between automatically recorded sensor data and manually collected surveillance data, and hence, identify anomalous instances that can be attributed to HE. We test our GAN on both a real-world dataset and an external dataset obtained from a testbed, and we benchmark our results against state-of-the-art unsupervised anomaly detection algorithms, including one-class support vector machine and isolation forest. Our results show that the proposed GAN provides improved anomaly detection performance. Our study is promising for the future development of artificial intelligence based HE detection systems.