• Energy Research

The Houston-Dallas (I-45) corridor is the busiest route among 18 traffic corridors in Texas, USA. The expected population growth and the surge in passenger mobility may result in a significant impact on the regional environment. This study uses a life cycle framework to predict and evaluate the net changes of environmental impact associated with the potential development of a high-speed rail (HSR) System along the I-45 corridor through its life cycle. The environmental impact is estimated in terms of CO2 and greenhouse gas (GHG) emissions per vehicle/passenger-kilometers traveled (V/PKT) using life cycle assessment. The analyses are performed referring to the Ecoinvent 3.4 inventory database through the phases: material extraction and processing, infrastructure construction, vehicle manufacturing, system operation, and end of life. The environmental benefit is evaluated by comparing the potential development of the HSR system with those of the existing transportation systems. The vehicle component, especially operation and maintenance of vehicles, is the primary contributor to the total global warming potential with about 93% of the life cycle GHG emissions. For the infrastructure component, 56.76% of GHG emissions result from the material extraction and processing phase (23.75 kgCO2eq/VKT). Various life cycle emissions of HSR except PM are significantly lower than for passenger cars.

Abstract This paper proposes and tests a sequence-based modeling of deep learning (DL) for structural damage detection of floating offshore wind turbine (FOWT) blades using Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) neural networks. The complete framework was developed with four different designs of deep networks using unidirectional or bidirectional layers of LSTM and GRU networks. These neural networks, specifically developed to learn long-term and short-term dependencies within sequential information such as time-series data, are successfully trained with the sensor signals of damaged FOWT. The sensor data were simulated due to the limited availability of field data from damaged FOWTs using multiple computational methods previously validated with experimental tests. The simulations accounted for the damage scenarios with various intensities, locations, and damage shapes, totaling 1320 damage scenarios. Both the presence of damage and its location were detected up to an accuracy of 94.8% using the best performing model of the selected network when tested for independent signals. The K-fold cross-validation accuracy of the selected network is estimated to be 91.7%. The presence of damage itself was detected with an accuracy of 99.9% based on the cross-validation regardless of the damage location. Structural damage detection using deep learning is not restricted by the assumptions of the systems or the environmental conditions as the networks learn the system directly from the data. The framework can be applied to various types of civil and offshore structures. Furthermore, the sequence-based modeling enables engineers to harness the vast amounts of digital information to improve the safety of structures.