A. James Clark School of Engineering
Permanent URI for this communityhttp://hdl.handle.net/1903/1654
The collections in this community comprise faculty research works, as well as graduate theses and dissertations.
Browse
4 results
Search Results
Item INTERPRETABLE AND SPEED ADAPTIVE CONVOLUTIONAL NEURAL NETWORK FOR PROGNOSTICS AND HEALTH MANAGEMENT OF ROTATING MACHINERY(2023) Lee, Nam Kyoung; Pecht, Michael; Azarian, Michael H; Mechanical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Faulty rotating machines exhibit vibrational characteristics that can be distinguished from healthy machines using prognostics and health management methods. These characteristics can be extracted using signal processing techniques. However, these techniques require certain inputs, or parameters, before the desired characteristics can be extracted. Setting the parameters requires skill and knowledge, as they should reflect the component geometries and the operational conditions. Using convolutional neural networks for diagnosing faults on a rotating machine eliminates the need for parameter setting by replacing signal processing with mathematical operations in the networks. The parameters that affect the outcomes of the operations are learned from data during the training of the neural networks. The networks can capture characteristics that are related to the health state of a machine, but their operations are not interpretable. Unlike signal processing, the internal operations of the networks have no constraints that guide the networks to transform vibrations into certain information, that is, vibrational characteristics. Without the constraints, there is no basis for understanding the characteristics in terms that can be associated with the physics of failure. The lack of interpretability impedes the physical validation of vibrational characteristics captured by the networks.This dissertation presents a method for changing the internal operations of a convolutional neural network to emulate a specific type of signal processing known as envelope analysis. Envelope analysis demodulates vibrations to extract vibrational signatures associated with mechanical impact on a defective rolling component. An understanding of envelope analysis, along with knowledge of the geometries of machine components and operational speeds, allows for a physical interpretation of the signatures. The dissertation develops speed adaptive convolutional layers and a rotational speed estimation algorithm to identify defect signatures whose frequency components change as the speed changes. The characteristics that are captured by the developed convolutional neural network are verified through a feature selection process that is designed to filter out physically implausible features. Case studies on three different systems demonstrate the feasibility of using the developed convolutional neural network for the diagnosis.Item A PHYSICS-INFORMED NEURAL NETWORK FRAMEWORK FOR BIG MACHINERY DATA IN PROGNOSTICS AND HEALTH MANAGEMENT FOR COMPLEX ENGINEERING SYSTEMS(2022) Cofre Martel, Sergio Manuel Ignacio; Modarres, Mohammad; Lopez Droguett, Enrique; Mechanical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Big data analysis and data-driven models (DDMs) have become essential tools in prognostics and health management (PHM). Despite this, several challenges remain to successfully apply these techniques to complex engineering systems (CESs). Indeed, current state-of-the-art applications are treated as black-box algorithms, where research efforts have focused on developing complex DDMs, overlooking or neglecting the importance of the data preprocessing stages prior to training these models. Guidelines to adequately prepare data sets collected from CESs to train DDMs in PHM are frequently unclear or inexistent. Furthermore, these DDMs do not consider prior knowledge on the system’s physics of degradation, which gives little-to-no control over the data interpretation in reliability applications such as maintenance planning.In this context, this dissertation presents a physics-informed neural network (PINN) architecture for remaining useful life (RUL) estimation based on big machinery data (BMD) collected from sensor monitoring networks (SMNs) in CESs. The main outcomes of this work are twofold. First, a systematic guide to preprocess BMD for diagnostics and prognostics tasks is developed based on expert knowledge and data science techniques. Second, a PINN-inspired PHM framework is proposed for RUL estimation through an open-box approach by exploring the system’s physics of degradation through partial differential equations (PDEs). The PINN-RUL framework aims to discover the system’s underlying physics-related behaviors, which could provide valuable information to create more trustworthy PHM models. The data preprocessing and RUL estimation frameworks are validated through three case studies, including the C-MAPSS benchmark data set and two data sets corresponding to real CESs. Results show that the proposed preprocessing methodology can effectively generate data sets for supervised PHM models for CESs. Furthermore, the proposed PINN-RUL framework provides an interpretable latent variable that can capture the system’s degradation dynamics. This is a step forward to increase interpretability of prognostic models by mapping the RUL estimation to the latent space and its implementation as a state of health classifier. The PINN-RUL framework is flexible as it allows incorporating available physics-based models to its architecture. As such, this framework takes a step forward in bridging the gap between statistic-based PHM and physics-based PHM methods.Item Data Requirements to Enable PHM for Liquid Hydrogen Storage Systems from a Risk Assessment Perspective(2021) Correa Jullian, Camila Asuncion; Groth, Katrina M; Reliability Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Quantitative Risk Assessment (QRA) aids the development of risk-informed safety codes and standards which are employed to reduce risk in a variety of complex technologies, such as hydrogen systems. Currently, the lack of reliability data limits the use of QRAs for fueling stations equipped with bulk liquid hydrogen storage systems. In turn, this hinders the ability to develop the necessary rigorous safety codes and standards to allow worldwide deployment of these stations. Prognostics and Health Management (PHM) and the analysis of condition-monitoring data emerge as an alternative to support risk assessment methods. Through the QRA-based analysis of a liquid hydrogen storage system, the core elements for the design of a data-driven PHM framework are addressed from a risk perspective. This work focuses on identifying the data collection requirements to strengthen current risk analyses and enable data-driven approaches to improve the safety and risk assessment of a liquid hydrogen fueling infrastructure.Item A COMPARISON BETWEEN DATA-DRIVEN AND PHYSICS OF FAILURE PHM APPROACHES FOR SOLDER JOINT FATIGUE(2010) Jaai, Rubyca; Pecht, Michael G; Mechanical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Prognostics and systems health management technology is an enabling discipline of technologies and methods with the potential of solving reliability problems that have been manifested due to complexities in design, manufacturing, environmental and operational use conditions, and maintenance. Over the past decade, research has been conducted in PHM to provide benefits such as advance warning of failures, enable forecasted maintenance, improve system qualification, extend system life, and diagnose intermittent failures that can lead to field failure returns exhibiting no-fault-found symptoms. While there are various methods to perform prognostics, including model-based and data-driven methods, these methods have some key disadvantages. This thesis presents a fusion prognostics approach, which combines or ―fuses together‖ the model based and data-driven approaches, to enable increasingly better estimates of remaining useful life. A case study using an electronics system to illustrate a step by step implementation of the fusion approach is also presented. The various benefits of the fusion approach and suggestions for future work are included.