Using Multiple-Model Adaptive Estimation and System Identification for Fault Detection in Nuclear Power Plants

2018 ◽  
Author(s):  
Jacob A. Farber ◽  
Daniel G. Cole
Keyword(s):  
System Identification ◽  
Nuclear Power ◽  
Power Plants ◽  
Nuclear Power Plants ◽  
Adaptive Estimation ◽  
Operating Conditions ◽  
Data Driven ◽  
Multiple Model ◽  
System Models ◽  
Multiple Model Adaptive Estimation

One challenge in nuclear power plant operation is the detection and identification of system faults and plant transients. Timely and accurate identification will reduce operational costs and increase plant safety. This paper describes a combined model-based and data-driven approach to identifying faults in nuclear power plants. Faults are detected for a GSES Generic Pressurized Water Reactor simulator using the multiple-model adaptive estimation (MMAE) technique. In this technique, multiple input-output system models are used that represent different operating conditions. The models predict sensor measurements for both normal and faulted operating conditions simultaneously. The predicted measurements are then compared to the sensor measurements to determine the most likely operating condition. The system models are obtained using system identification techniques for a specific set of faulted conditions. This technique uses sensor measurements from the simulation to identify appropriate parameters for the system models. The MMAE technique is then used to detect similar faults using the identified model. This combination of model-based and data-driven techniques can ultimately be used to create robust fault models that take advantage of both the models created during the design and validation process and real plant data.

Diagnosis of Corrosion Processes in Nuclear Power Plants Secondary Piping Structures

2020 ◽  
Author(s):  
Koushik A. Manjunatha ◽  
Andrea Mack ◽  
Vivek Agarwal ◽  
David Koester ◽  
Douglas Adams
Keyword(s):  
Experimental Test ◽  
Classification Accuracy ◽  
Nuclear Power ◽  
Power Plants ◽  
Nuclear Power Plants ◽  
Operating Conditions ◽  
Condition Based Maintenance ◽  
Support Vector ◽  
Maintenance Strategy ◽  
Test Bed

Abstract The current aging management plans of passive structures in nuclear power plants (NPPs) are based on preventative maintenance strategies. These strategies involve periodic, manual inspection of passive structures using nondestructive examination (NDE) techniques. This manual approach is prone to errors and contributes to high operation and maintenance costs, making it cost prohibitive. To address these concerns, a transition from the current preventive maintenance strategy to a condition-based maintenance strategy is needed. The research presented in this paper develops a condition-based maintenance capability to detect corrosion in secondary piping structures in NPPs. To achieve this, a data-driven methodology is developed and validated for detecting surrogate corrosion processes in piping structures. A scaled-down experimental test bed is developed to evaluate the corrosion process in secondary piping in NPPs. The experimental test bed is instrumented with tri-axial accelerometers. The data collected under different operating conditions is processed using the Hilbert-Huang Transformation. Distributional features of phase information among the accelerometers were used as features in support vector machine (SVM) and least absolute shrinkage and selection operator (LASSO) logistic regression methodologies to detect changes in the pipe condition from its baseline state. SVM classification accuracy averaged 99% for all models. LASSO classification accuracy averaged 99% for all models using the accelerometer data from the X-direction.

scholarly journals Prognostics and Health Management in Nuclear Power Plants: An Updated Method-Centric Review With Special Focus on Data-Driven Methods

2021 ◽  
Vol 9 ◽  
Author(s):  
Xingang Zhao ◽  
Junyung Kim ◽  
Kyle Warns ◽  
Xinyan Wang ◽  
Pradeep Ramuhalli ◽  
...  
Keyword(s):  
Nuclear Power ◽  
Power Plants ◽  
Nuclear Power Plants ◽  
Health Management ◽  
Nuclear Industry ◽  
Data Availability ◽  
Data Driven ◽  
Special Focus ◽  
Prognostics And Health Management ◽  
Term Operation

In a carbon-constrained world, future uses of nuclear power technologies can contribute to climate change mitigation as the installed electricity generating capacity and range of applications could be much greater and more diverse than with the current plants. To preserve the nuclear industry competitiveness in the global energy market, prognostics and health management (PHM) of plant assets is expected to be important for supporting and sustaining improvements in the economics associated with operating nuclear power plants (NPPs) while maintaining their high availability. Of interest are long-term operation of the legacy fleet to 80 years through subsequent license renewals and economic operation of new builds of either light water reactors or advanced reactor designs. Recent advances in data-driven analysis methods—largely represented by those in artificial intelligence and machine learning—have enhanced applications ranging from robust anomaly detection to automated control and autonomous operation of complex systems. The NPP equipment PHM is one area where the application of these algorithmic advances can significantly improve the ability to perform asset management. This paper provides an updated method-centric review of the full PHM suite in NPPs focusing on data-driven methods and advances since the last major survey article was published in 2015. The main approaches and the state of practice are described, including those for the tasks of data acquisition, condition monitoring, diagnostics, prognostics, and planning and decision-making. Research advances in non-nuclear power applications are also included to assess findings that may be applicable to the nuclear industry, along with the opportunities and challenges when adapting these developments to NPPs. Finally, this paper identifies key research needs in regard to data availability and quality, verification and validation, and uncertainty quantification.

On-Site Evaluation of Bending Stresses at the Root of Small Bore Pipes by Accelerometric Measurements

2003 ◽  
Author(s):  
J. Guillou ◽  
L. Paulhiac
Keyword(s):  
Nuclear Power ◽  
Power Plants ◽  
Nuclear Power Plants ◽  
Numerical Models ◽  
Operating Conditions ◽  
Strain Gauges ◽  
Bending Stress ◽  
Piping Systems ◽  
Bending Stresses ◽  
Site Evaluation

Several vibration-induced failures at the root of small bore piping systems occurred in French nuclear power plants in past years. The evaluation of the failure risk of the small bore pipes requires a fair estimation of the bending stress under operating conditions. As the use of strain gauges is too time-consuming in the environmental conditions of nuclear power plants, on-site acceleration measurements combined with numerical models are easier to handle. It still requires yet a large amount of updating work to estimate the stress in multi-span pipes with elbows and supports. The aim of the present study is to propose an alternate approach using two accelerometers to measure the local nozzle deflection, and an analytical expression of the bending stiffness of the nozzle on the main pipe. A first formulation is based on a static deformation assumption, thus allowing the use of a simple analog converter to get an estimation of the RMS value of the bending stress. To get more accurate results, a second method is based on an Euler Bernoulli deformation assumption: a spectral analyzer is then required to get an estimation of the spectrum of the bending stress. A better estimation of its RMS value is then obtained. An experimental validation of the methods based on strain gauges has been successfully performed.

Robustness Analysis and Improvement of Fault Diagnosis Model for Nuclear Power Plants Based on Random Forest

2021 ◽  
Author(s):  
Jiangkuan Li ◽  
Meng Lin
Keyword(s):  
Fault Diagnosis ◽  
Random Forest ◽  
Nuclear Power ◽  
Power Plants ◽  
Nuclear Power Plants ◽  
Robustness Analysis ◽  
Noisy Data ◽  
Data Driven ◽  
Model Based ◽  
Diagnosis Model

Abstract With the development of artificial intelligence technology, data-driven methods have become the core of fault diagnosis models in nuclear power plants. Despite the advantages of high flexibility and practicability, data-driven methods may be sensitive to the noise in measurement data, which is inevitable in the process of data measurement in nuclear power plants, especially under fault conditions. In this paper, a fault diagnosis model based on Random Forest (RF) is established. Firstly, its diagnostic performance on noiseless data and noisy data set containing 13 operating conditions (one steady state condition and 12 fault conditions) is analyzed, which shows that the model based on RF has poor robustness under noisy data. In order to improve the robustness of the model under noisy data, a method named ‘Train with Noisy Data’ (TWND) is proposed, the results show that TWND method can effectively improve the robustness of the model based on RF under noisy data, and the degree of improvement is related to the noise levels of added noisy data. This paper can provide reference for robustness analysis and robustness improvement of nuclear power plants fault diagnosis models based on other data-driven methods.

Wear Scar Progression of Impact-Fretting at Elevated Temperature for Steam Generator Tubes in Nuclear Power Plants

2006 ◽  
Vol 326-328 ◽  
pp. 1251-1254 ◽  
Author(s):  
Chi Yong Park ◽  
Jeong Keun Lee
Keyword(s):  
Steam Generator ◽  
Nuclear Power ◽  
Power Plants ◽  
Nuclear Power Plants ◽  
Operating Conditions ◽  
Wear Scar ◽  
Fretting Wear ◽  
Test Material ◽  
The Impact ◽  
Steam Generator Tubes

Fretting wear generated by flow induced vibration is one of the important degradation mechanisms of steam generator tubes in the nuclear power plants. Understanding of tube wear characteristics is very important to keep the integrity of the steam generator tubes to secure the safety of the nuclear power plants. Experimental examination has been performed for the purpose of investigating the impact fretting. Test material is alloy 690 tube and 409 stainless steel tube supports. From the results of experiments, wear scar progression is investigated in the case of impact-fretting wear test of steam generator tubes under plant operating conditions such as pressure of 15MPa, high temperature of 290C and low dissolved oxygen. Hammer imprint that is actual damaged wear pattern, has been observed on the worn surface. From investigation of wear scar pattern, wear mechanism was initially the delamination wear due to cracking the hard oxide film and finally transferred to the stable impact-fretting pattern.

Crack Initiation Factor by Impact Fretting Wear at INCONEL Alloy for Steam Generator Tube in Nuclear Power Plants

2007 ◽  
Vol 26-28 ◽  
pp. 1269-1272
Author(s):  
Chi Yong Park ◽  
Jeong Kun Kim ◽  
Tae Ryong Kim ◽  
Sun Young Cho ◽  
Hyun Ik Jeon
Keyword(s):  
Steam Generator ◽  
Wear Mechanism ◽  
Nuclear Power ◽  
Power Plants ◽  
Nuclear Power Plants ◽  
Operating Conditions ◽  
Fretting Wear ◽  
Steam Generator Tube ◽  
Inconel Alloy ◽  
The Impact

Inconel alloy such as alloy 600 and alloy 690 is widely used as the steam generator tube materials in the nuclear power plants. The impact fretting wear tests were performed to investigate wear mechanism between tube alloy and 409 stainless steel tube support plates in the simulated steam generator operating conditions, pressure of 15MPa, high temperature water of 290°C and low dissolved oxygen(<10 ppb). From investigation of wear test specimens by the SEM and EDS analysis, hammer imprint, which is known to be an actual damaged wear pattern, has been observed on the worn surface, and fretting wear mechanism was investigated. Wear progression of impact-fretting wear also has been examined. It was observed that titanium rich phase contributes to the formation of voids and cracks in sub-layer of fretting wear damage by impact fretting wear.

scholarly journals Belarus Power Engineering System Modeling Taking into Account the Nuclear Power Plant Commissioning

2021 ◽  
Vol 64 (1) ◽  
pp. 5-14
Author(s):  
A. A. Mikhalevic ◽  
U. A. Rak
Keyword(s):  
Nuclear Power ◽  
Power Plants ◽  
Nuclear Power Plants ◽  
Energy Systems ◽  
Operating Conditions ◽  
Power Engineering ◽  
Power Balance ◽  
Engineering System ◽  
Large Share ◽  
Load Duration

The article presents the analysis of the specific features of modeling the operation of energy systems with a large share of nuclear power plants (NPP). The study of operating conditions and characteristics of different power units showed that a power engineering system with a large share of NPP and CHPP requires more detailed modeling of operating modes of generating equipment. Besides, with an increase in the share of installations using renewable energy sources, these requirements are becoming tougher. A review of the literature revealed that most often the curve of the load duration and its distribution between blocks are used for modeling energy systems. However, since this method does not reflect a chronological sequence, it can only be used if there are no difficulties with ensuring power balance. Along with this, when the share of CHP and nuclear power plants is high, to maintain a balance of power one must know the parameters and a set of powered equipment not only currently but, also, in the previous period. But this is impossible if a curve of load duration is used. For modeling, it is necessary to use an hourly load curve and to calculate the state of the energy system for each subsequent hour in chronological order. In the course of a comparative analysis of available computer programs, it was not possible to identify a suitable model among the existing ones. The article presents a mathematical model developed by the authors, which makes us possible to simulate the operation of a power engineering system with a large share of NPP and CHPP while maintaining the power balance for each hour of the forecast period. Verification of the proposed model showed good accuracy of the methods used.

Sign in / Sign up

Export Citation Format

Share Document