Fatigue represents a critical issue in many structural applications, and wind turbines are not an exception. Their dynamic response over the years determines the turbine's lifespan, meaning that fatigue loads have a clear impact on the Cost of Energy. Since the direct experimental determination of the loading state is complex or expensive, estimations arising from general operational signals can be explored as an indirect way to acquire knowledge of fatigue loading levels.A case study based on 10-minute aeroelastic simulations of a wind turbine dynamics is used to develop a Damage Equivalent Load estimation model using operational signals (typically recorded by SCADA systems) as inputs. The focus is on both the input selection and the model configuration, seeking the combination which reaches the lowest error. Three filters and two innovative wrappers (exploration and optimization) were considered within the selection. Linear and Artificial Neural Network models were implemented and compared. Results showed performances in Damage Equivalent Load estimation below 4% in terms of Normalized Root Mean Squared Error, which is promising as compared with related work. Additional conclusions were obtained concerning appropriate Artificial Neural Network configurations (net type, architecture and training algorithm), likewise the potential contribution of a proposed genetic algorithm.
Purpose: Airline strategy relies on the competitive environment analysis and the management of resources. Artificial Intelligence (AI) algorithms are being increasingly deployed throughout several industries. COVID-19 has further stressed a sector where firms have historically struggled to sustain profitability.The purpose is to explore the potential of AI applications regarding strategic decision-making in airlines in times of crisis and to depict a roadmap to encourage scholars and practitioners to jointly implement these tools within corporations.Design/methodology/approach: This study firstly reviews the state-of-the-art regarding transport organization trends with focus on airline strategy and finance as well as AI tools, supported by the collaboration of a former airline digitalization strategist. Secondly, the potential of the latter to be applied in those functions is analyzed, considering different Machine Learning (ML) methods and algorithms.Findings: Some applications or pathways are identified as of particular interest for the airlines’ strategic decision-making process. Most of them are based on ML algorithms and training methods that are currently underused or disregarded in certain business areas, such as Neural Network models for unsupervised market analysis or supervised cost estimation.Research limitations/implications: Focus is on airline strategy and finance, keeping engineering or operational applications out of the scope.Practical implications: Proposed guidance may promote the deployment of AI tools which currently lack practical implementation in certain business areas.Social implications: Showcased guidance may revert into a closer collaboration between business and academia.Originality/value: Comprehensive review of current airlines’ strategic levers and identification of promising AI pathways to be further explored.
Aviation CO2 emissions are growing along with traffic growth and expected technological efficiency improvements are not enough to reduce this continuous increase. International organizations are concerned and are implementing incentive rules in order to reduce them. IATA has stated a carbon neutral growth of emissions from 2020 onward within its roadmap. This paper aims to analyze suitable measures that could help to reach this target and focuses on their impact on the finances of 15 varied Spanish airlines. With these goals, an estimation model is designed in order to carry out a forecast of the 2017–2025 Spanish air market. This is comprised by three submodels: (i) the traffic model estimates the annual performance for Spanish carriers in each of their routes, (ii) the biofuel model is in charge of estimating the biofuel prices, emissions and regulations (with special attention to mandatory blending percentage), and (iii) the operating cost model estimates the carrier’s expenses structure. Data from several sources (regarding 2016 traffic statistics and forecasts of growth and fuel prices to name but two) is gathered and merged in order to feed the model. Aggregated results show that an average 3% per year increase of mandatory blending percentage should be applied for a 2020 CNG in the base scenario. Regarding the different biofuel feedstocks investigated, Camelina’s performance presents a good compromise in respect to price, emissions, and production issues. A further study on the airline’s cost structure shows that differences in the operating model (legacy, low cost, etc.) and route configurations can lead to big differences in terms of impact of biofuels introduction on the total airline costs. This could indicate that perhaps the design of distance-specific financial schemes would be desirable. In addition, high sensitivity to changes in common fuel price and traffic growth is observed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.