Improving Site-Dependent Wind Turbine Performance Prediction Accuracy Using Machine Learning

Data-driven wind turbine performance predictions, such as power and loads, are important for planning and operation. Current methods do not take site-specific conditions such as turbulence intensity and shear into account, which could result in errors of up to 10%. In this work, four different machine learning models (k-nearest neighbors regression, random forest regression, extreme gradient boosting regression and artificial neural networks (ANN) are trained and tested, firstly on a simulation dataset and then on a real dataset. It is found that machine learning methods that take site-specific conditions into account can improve prediction accuracy by a factor of two to three, depening on the error indicator chosen. Similar results are observed for multi-output ANNs for simulated in- and out-of-plane rotor blade tip deflection and root loads. Future work focuses on understanding transferability of results between different turbines within a wind farm and between different wind turbine types.

A Computational Framework for Human-centric Vehicular Crashworthiness Design and Decision-Making Under Uncertainty

Government agencies, globally, strive to minimize the likelihood and frequency of human death and severe injury on road transport systems. From an engineering design standpoint, the minimization of these road accident effects on occupants becomes a critical design goal. This necessitates the quantification and management of injury risks on the human body in response to several vehicular impact variables and their associated uncertainties for different crash scenarios. In this paper, we present a decision-based, robust design framework to quantify and manage the impact-based injury risks on occupants for different computational model-based car crash scenarios. The key functionality offered is the designer's capability to conduct robust concept exploration focused on managing the selected impact variables and associated uncertainties, such that injury risks are controlled within acceptable levels. The framework's efficacy is tested for near-side impact scenarios with impact velocity and angle of impact as the critical variables of interest. Two injury criteria, namely, Head Injury Criterion (HIC) and Lateral Neck Injury Criteria (Lateral Nij), are selected to quantitatively measure the head and neck injury risks in each crash simulation. Using the framework, a robust design problem is formulated to determine the combination of impact variables that best satisfice the injury goals defined. The framework and associated design constructs are generic and support the formulation and decision-based robust concept exploration of similar problems involving models under uncertainty. Our focus in this paper is on the framework rather than the results per se.

Prognostics and Health Management of Wind Energy Infrastructure Systems

The improvements in wind energy infrastructure have been a constant process throughout many decades. There are new advancements in technology that can further contribute towards the Prognostics and Health Management (PHM) in this industry. These advancements are driven by the need to fully explore the impact of uncertainty, quality and quantity of data, physics-based machine learning (PBML), and digital twin (DT). All these aspects need to be taken into consideration to perform an effective PHM of wind energy infrastructure. To address these aspects, four research questions were formulated. What is the role of uncertainty in machine learning (ML) in diagnostics and prognostics? What is the role of data augmentation and quality of data for ML? What is the role of PBML? What is the role of the DT in diagnostics and prognostics? The methodology used was Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA). A total of 143 records, from the last five years, were analyzed. Each of the four questions was answered by discussion of literature, definitions, critical aspects, benefits and challenges, the role of aspect in PHM of wind energy infrastructure systems, and conclusion.

Interpretable Machine Learning in Damage Detection Using Shapley Additive Explanations

In recent years, Machine Learning (ML) techniques have gained popularity in Structural Health Monitoring (SHM). These have been particularly used for damage detection in a wide range of engineering applications such as wind turbine blades. The outcomes of previous research studies in this area have demonstrated the capabilities of ML for robust damage detection. However, the primary challenge facing ML in SHM is the lack of interpretability of the prediction models hindering the broader implementation of these techniques. For this purpose, this study integrates the novel Shapley Additive exPlanations (SHAP) method into a ML-based damage detection process as a tool for introducing interpretability and, thus, build evidence for reliable decision-making in SHM applications. The SHAP method is based on coalitional game theory and adds global and local interpretability to ML-based models by computing the marginal contribution of each feature. The contribution is used to understand the nature of damage indices (DIs). The applicability of the SHAP method is first demonstrated on a simple lumped mass-spring-damper system with simulated temperature variabilities. Later, the SHAP method has been evaluated on data from an in-operation V27 wind turbine with artificially introduced damage in one of its blades. The results show the relationship between the environmental and operational variabilities (EOVs) and their direct influence on the damage indices. This ultimately helps to understand the difference between false positives caused by EOVs and true positives resulting from damage in the structure.

Survey Use to Validate Engineering Methodology and Enhance System Safety

Surveys and the resulting data provide powerful insights to an item or concept being assessed. Not only do they garner feedback that can be used to enhance the item, but, in the instance of this article, they can enhance the validity of positive change via novel concepts prior to spending the time and money in incorporating these concepts and running the risk of negligible meaningful return. In an effort to ensure the validity of proposed novel methods in a design engineering context, a survey was developed and administered to engineering subject matter experts. This was done to not only ensure that the proposed methods would be viable if implemented but gave confidence in the results of the research that drove the method development. This assessment activity served as a risk reduction activity to ensure smooth implementation of the methods from both an efficiency standpoint and, most importantly, as part of maximizing system safety. This paper discusses the composition and considerations of the survey administered in the research study, in addition to the survey results with the intention of providing a format for others in a similar context to glean from and, if practical, replicate the method.

Special Issue on Uncertainty Quantification and Management in Additive Manufacturing

N/A

Uncertainty Quantification for Additive Manufacturing Process Improvement: Recent Advances

This paper reviews the state of the art in applying uncertainty quantification (UQ) methods to additive manufacturing (AM). Physics-based as well as data-driven models are increasingly being developed and refined in order to support process optimization and control objectives in AM, in particular to maximize the quality and minimize the variability of the AM product. However, before using these models for decision-making, a fundamental question that needs to be answered is to what degree the models can be trusted, and consider the various uncertainty sources that affect their prediction. Uncertainty quantification (UQ) in AM is not trivial because of the complex multi-physics, multi-scale phenomena in the AM process. This article reviews the literature on UQ methodologies focusing on model uncertainty, discusses the corresponding activities of calibration, verification and validation, and examines their applications reported in the AM literature. The extension of current UQ methodologies to additive manufacturing needs to address multi-physics, multi-scale interactions, increasing presence of data-driven models, high cost of manufacturing, and complexity of measurements. The activities that need to be undertaken in order to implement verification, calibration, and validation for AM are discussed. Literature on using the results of UQ activities towards AM process optimization and control (thus supporting maximization of quality and minimization of variability) is also reviewed. Future research needs both in terms of UQ and decision-making in AM are outlined.

Multi-Objective Optimization Under Uncertainty of Part Quality in Fused Filament Fabrication

This work presents a data-driven methodology for multi-objective optimization under uncertainty of process parameters in the fused filament fabrication (FFF) process. The proposed approach optimizes the process parameters with the objectives of minimizing the geometric inaccuracy and maximizing the filament bond quality of the manufactured part. First, experiments are conducted to collect data pertaining to the part quality. Then, Bayesian neural network (BNN) models are constructed to predict the geometric inaccuracy and bond quality as functions of the process parameters. The BNN model captures the model uncertainty caused by the lack of knowledge about model parameters (neuron weights) and the input variability due to the intrinsic randomness in the input parameters. Using the stochastic predictions from these models, different robustness-based design optimization formulations are investigated, wherein process parameters such as nozzle temperature, nozzle speed, and layer thickness are optimized under uncertainty for different multi-objective scenarios. Epistemic uncertainty in the prediction model and the aleatory uncertainty in the input are considered in the optimization. Finally, Pareto surfaces are constructed to estimate the trade-offs between the objectives. Both the BNN models and the effectiveness of the proposed optimization methodology are validated using actual manufacturing of the parts.

Definition of a Basic Design for Conversion of an Offshore Fixed Platform on a Depleted Reservoir Into a Sustainable Plant

In the framework of energy transition, a focus is given to the study of the conversion of offshore Oil&Gas platforms at the end of their life due to depletion of the reservoirs on which they operate. Their modular and versatile structure allows the implementation of new processes and innovative sustainable technologies for reducing the environmental impact of a complete decommissioning, especially on the subsea ecosystem that has grown around the jacket, and for guaranteeing costsaving solutions. Among different conversion options, this paper focuses on the installation on the platform of a system for the production of photovoltaic (PV) energy to be used for seawater desalination and its delivery to other platforms operating in the same area. The project focuses on the definition of technical characteristics of the basic design, on the investigation of the technical feasibility of the conversion process, on qualitative safety and environmental impact studies. Moreover, the old platform equipment to be decommissioned (ie. the equipment necessary for hydrocarbons treatment) are identified and the installation of new equipment is optimized, eg. the number of PV panels and, therefore, the installed power are maximized. At the same time, decommissioning costs and impacts can be minimized. The basic design is completed with a preliminary structural verification to guarantee that critical situations do not rise, with an indication on the main maintenance activities for the preservation of plant good efficiency and with safety and environmental preliminary analyses for the identification of potential criticalities to be managed at different design levels.

Calibration and Validation of Multiscale Model for Ultimate Strength Prediction of Composite Laminates Under Uncertainty

A methodology to account for the effect of epistemic uncertainty (regarding model parameters) on the strength prediction of carbon fiber reinforced polymer (CFRP) composite laminates is presented. A three-dimensional concurrent multiscale physics modeling framework is considered. A continuum damage mechanics-based constitutive relation is used for multiscale analysis. The parameters for the constitutive model are unknown and need to be calibrated. A least squares-based approach is employed for the calibration of model parameters and a model discrepancy term. The calibrated constitutive model is validated quantitatively using experimental data for both unnotched and open-hole specimens with different composite layups. The quantitative validation results are used to indicate further steps for model improvement.