scholarly journals A Dynamic Bayesian Network Structure for Joint Diagnostics and Prognostics of Complex Engineering Systems

Algorithms ◽  
2020 ◽  
Vol 13 (3) ◽  
pp. 64
Author(s):  
Austin D. Lewis ◽  
Katrina M. Groth

Dynamic Bayesian networks (DBNs) represent complex time-dependent causal relationships through the use of conditional probabilities and directed acyclic graph models. DBNs enable the forward and backward inference of system states, diagnosing current system health, and forecasting future system prognosis within the same modeling framework. As a result, there has been growing interest in using DBNs for reliability engineering problems and applications in risk assessment. However, there are open questions about how they can be used to support diagnostics and prognostic health monitoring of a complex engineering system (CES), e.g., power plants, processing facilities and maritime vessels. These systems’ tightly integrated human, hardware, and software components and dynamic operational environments have previously been difficult to model. As part of the growing literature advancing the understanding of how DBNs can be used to improve the risk assessments and health monitoring of CESs, this paper shows the prognostic and diagnostic inference capabilities that are possible to encapsulate within a single DBN model. Using simulated accident sequence data from a model sodium fast nuclear reactor as a case study, a DBN is designed, quantified, and verified based on evidence associated with a transient overpower. The results indicate that a joint prognostic and diagnostic model that is responsive to new system evidence can be generated from operating data to represent CES health. Such a model can therefore serve as another training tool for CES operators to better prepare for accident scenarios.

Energies ◽  
2021 ◽  
Vol 14 (13) ◽  
pp. 3860
Author(s):  
Priyanka Shinde ◽  
Ioannis Boukas ◽  
David Radu ◽  
Miguel Manuel de Manuel de Villena ◽  
Mikael Amelin

In recent years, the vast penetration of renewable energy sources has introduced a large degree of uncertainty into the power system, thus leading to increased trading activity in the continuous intra-day electricity market. In this paper, we propose an agent-based modeling framework to analyze the behavior and the interactions between renewable energy sources, consumers and thermal power plants in the European Continuous Intra-day (CID) market. Additionally, we propose a novel adaptive trading strategy that can be used by the agents that participate in CID market. The agents learn how to adapt their behavior according to the arrival of new information and how to react to changing market conditions by updating their willingness to trade. A comparative analysis was performed to study the behavior of agents when they adopt the proposed strategy as opposed to other benchmark strategies. The effects of unexpected outages and information asymmetry on the market evolution and the market liquidity were also investigated.


Energies ◽  
2021 ◽  
Vol 14 (20) ◽  
pp. 6852
Author(s):  
Grant Buster ◽  
Paul Siratovich ◽  
Nicole Taverna ◽  
Michael Rossol ◽  
Jon Weers ◽  
...  

Geothermal power plants are excellent resources for providing low carbon electricity generation with high reliability. However, many geothermal power plants could realize significant improvements in operational efficiency from the application of improved modeling software. Increased integration of digital twins into geothermal operations will not only enable engineers to better understand the complex interplay of components in larger systems but will also enable enhanced exploration of the operational space with the recent advances in artificial intelligence (AI) and machine learning (ML) tools. Such innovations in geothermal operational analysis have been deterred by several challenges, most notably, the challenge in applying idealized thermodynamic models to imperfect as-built systems with constant degradation of nominal performance. This paper presents GOOML: a new framework for Geothermal Operational Optimization with Machine Learning. By taking a hybrid data-driven thermodynamics approach, GOOML is able to accurately model the real-world performance characteristics of as-built geothermal systems. Further, GOOML can be readily integrated into the larger AI and ML ecosystem for true state-of-the-art optimization. This modeling framework has already been applied to several geothermal power plants and has provided reasonably accurate results in all cases. Therefore, we expect that the GOOML framework can be applied to any geothermal power plant around the world.


Author(s):  
Jahau Lewis Chen ◽  
Chuan Hung

AbstractThis paper presents an eco-innovation method by revised the “Anticipatory Failure Determination (AFD)” method which is the failure analysis tools in TRIZ theory. Using the functional analysis to list the system process and make the functional analysis model. Based on the environmental efficiency factors and functional analysis model, Substance-Field inverse analysis can find a lot of failure modes in the system. In order to assess the priority of risk improvement, the designer can calculate the environmental risk priority number including controlling documents, public image and environmental consequences. Designer can quickly find out the potential failure mode in the complex engineering system with the systematic steps. The TRIZ methods are used for finding eco-innovation idea to solve failure problem. The capability of the whole eco-innovative design process was illustrated by the electrical motorcycle case.


2006 ◽  
Vol 321-323 ◽  
pp. 441-444
Author(s):  
Heung Seop Eom ◽  
Sa Hoe Lim ◽  
Jae Hee Kim ◽  
Young H. Kim ◽  
Hak Joon Kim ◽  
...  

This study was aimed at developing an effective method and a system for on-line health monitoring of pipes in nuclear power plants by using ultrasonic guided waves. For this purpose we developed a multi-channel ultrasonic guided wave system for a long-range inspection of pipes and a few techniques which can effectively find defects in pipes. To validate the developed system we performed a series of experiments and analyzed the results.


Author(s):  
Lukman Irshad ◽  
H. Onan Demirel ◽  
Irem Y. Tumer ◽  
Guillaume Brat

Abstract While a majority of system vulnerabilities such as performance losses and accidents are attributed to human errors, a closer inspection would reveal that often times the accumulation of unforeseen events that include both component failures and human errors contribute to such system failures. Human error and functional failure reasoning (HEFFR) is a framework to identify potential human errors, functional failures, and their propagation paths early in design so that systems can be designed to be less prone to vulnerabilities. In this paper, the application of HEFFR within the complex engineering system domain is demonstrated through the modeling of the Air France 447 crash. Then, the failure prediction algorithm is validated by comparing the outputs from HEFFR and what happened in the actual crash. Also, two additional fault scenarios are executed within HEFFR and in a commercially available flight simulator separately, and the outcomes are compared as a supplementary validation.


Author(s):  
John R. Fyffe ◽  
Stuart M. Cohen ◽  
Michael E. Webber

Coal-fired power plants are a source of inexpensive, reliable electricity for many countries. Unfortunately, their high carbon dioxide (CO2) emissions rates contribute significantly to global climate change. With the likelihood of future policies limiting CO2 emissions, CO2 capture and sequestration (CCS) could allow for the continued use of coal while low- and zero-emission generation sources are developed and implemented. This work compares the potential impact of flexibly operating CO2 capture systems on the economic viability of using CCS in gas- and coal-dominated electricity markets. The comparison is made using a previously developed modeling framework to analyze two different markets: 1) a natural-gas dominated market (the Electric Reliability Council of Texas, or ERCOT) and 2) a coal-dominated market (the National Electricity Market, or NEM in Australia). The model uses performance and economic parameters for each power plant to determine the annual generation, CO2 emissions, and operating profits for each plant for specified input fuel prices and CO2 emissions costs. Previous studies of ERCOT found that flexible CO2 capture operation could improve the economic viability of coal-fired power plants with CO2 capture when there are opportunities to reduce CO2 capture load and increase electrical output when electricity prices are high. The model was used to compare the implications of using CO2 capture systems in the two electricity systems under CO2 emissions penalties from 0–100 US dollars per metric ton of CO2. Half the coal-fired power plants in each grid were selected to be considered for a CO2 capture retrofit based on plant efficiency, whether or not SO2 scrubbers are already installed on the plant, and the plant’s proximity to viable sequestration sites. Plants considered for CO2 capture systems are compared with and without inflexible CO2 capture as well as with two different flexible operation strategies. With more coal-fired power plants being dispatched as the marginal generator and setting the electricity price in the NEM, electricity prices increase faster due to CO2 prices than in ERCOT where natural gas-plants typically set the electricity price. The model showed moderate CO2 emissions reductions in ERCOT with CO2 capture and no CO2 price because increased costs at coal-fired power plants led to reduced generation. Without CO2 prices, installing CO2 capture on coal-fired power plants resulted in moderately reduced CO2 emissions in ERCOT as the coal-fired power plants became more expensive and were replaced with less expensive natural gas-fired generators. Without changing the makeup of the plant fleet in NEM, a CO2 price would not currently promote significant replacement of coal-fired power plants because there is minimal excess capacity with low CO2 emissions rates that can displace existing coal-fired power plants. Additionally, retrofitting CO2 capture onto half of the coal-based fleet in NEM did not reduce CO2 emissions significantly without CO2 costs being implemented because the plants with capture become more expensive and were replaced by the coal-fired power plants without CO2 capture. Operating profits at NEM capture plants increased as CO2 price increased much faster than capture plants in ERCOT. The higher rate of increasing profits for plants in NEM is due to the marginal generators in NEM being coal-based facilities with higher CO2 emissions penalties than the natural gas-fired facilities that set electricity prices in ERCOT. Overall, coal-fired power plants were more profitable with CO2 capture systems than without in both ERCOT and NEM when CO2 prices were higher than USD25/ton.


Sign in / Sign up

Export Citation Format

Share Document