Many research efforts to advance human health and well-being involve interdisciplinary problem spaces and complex, poorly-understood systems. This thesis integrates both computational and experimental approaches to advance our understanding and control of complex systems at the interface of machine learning, materials science, and manufacturing. Specifically, I demonstrate the data-driven description of supervised machine learning for biomedical engineering tasks, the data-driven design of optimized soft granular biomaterials, and the proof-of-concept development of a transcatheter additive manufacturing platform. In Part 1, I develop custom software for high-resolution, multifactorial machine learning (ML) experiments. I iteratively apply this workflow to a set of diverse ML problems from the biomedical engineering (BME) domain to generate massive meta-datasets covering each phase of the hierarchical ML optimization and evaluation process. Then, I describe the underlying patterns and heterogeneity in these rich datasets and delineate empirical guidelines for the rigorous and reliable adoption of machine learning for BME problems. In Part 2, I leverage the insights from Part 1 to develop a flexible and robust data-driven modeling pipeline for complex soft materials. The pipeline can be applied after each round of experimentation to build predictive models, extract key design rules, and generate data-driven design frameworks. I use this integrated, stepwise approach to optimize the structures, properties, and performance profiles of soft granular biomaterials for injection- and extrusion-based biomedical applications. In Part 3, I leverage the optimized materials from Part 2 to develop a novel microgel-based transcatheter additive manufacturing technology. I obtain proof-of-concept data for the platform's critical features, including controlled transcatheter material delivery to distant target locations, rapid in situ structuration of arbitrary 3D constructs, and reliable scaffold stabilization to ensure long-term implant integrity. Together, this work paves the way for minimally-invasive, patient-specific, in situ biofabrication.

A textbook covering data-science and machine learning methods for modelling and control in engineering and science, with Python and MATLAB®.

As data is becoming more readily accessible from various systems, data-driven modeling and control approaches have gained increased popularity among both researchers and practitioners. Compared to its first-principle counterparts, data-driven approaches require minimal domain knowledge and calibration efforts, which is especially appealing to nonlinear and complex systems. In this thesis, two efficient data-driven frameworks, indirect and direct, for the control of nonlinear and complex systems are presented.The indirect method first involves an efficient online system identification approach with a composite local model structure. We introduce the concept of evolving Spatial Temporal Filters (eSTF) that dynamically transforms an incoming input-output data stream into a nonlinear combination of local models. Each local model is assigned with an ellipsoid-shaped cluster that is used to define its validity zone, and a distance metric that combines the Mahalanobis distance to the clusters and the scaled local model prediction error is exploited to compute the local model composition weights. The cluster and model parameters are efficiently updated online using input-output data stream, enabling adaptive system identification with efficient computations.With the identified eSTF model structure, we then develop an efficient quasi-linear parameter varying (qLPV) based stochastic model predictive controller (SMPC) for a class of nonlinear systems subject to chance constraints and additive disturbance. The qLPV form is established with the scheduling variable and a set of linear time-invariant models obtained from the eSTF system identification approach. To handle chance constraints, probabilistic reachable sets-the probabilistic analogy of robust reachable sets-are exploited to tighten the constraints to robustly guarantee constraint satisfaction despite model uncertainties and additive disturbances.A shifted scheduling variable strategy is designed such that the resultant MPC optimization can be efficiently solved by solving a series of quadratic programming problems. The indirect data-driven modeling and control pipeline is successfully applied to automotive powertrain systems with great system identification and control performance demonstrated.On the other hand, we further develop a direct data-driven control paradigm that leverages behavioural system theory, and directly generates control commands from input/output data without the need of a parametric model. We exploit singular value decomposition (SVD)-based order reduction to significantly reduce the online computation complexity without degrading the control performance. This control paradigm is successfully applied to battery fast charging, which has complex dynamics and is difficult to model. Furthermore, the direct data-driven approach heavily relies on the intensive collection and sharing of data, which raises serious privacy concerns, especially for systems with multiple agents. Therefore, we develop a privacy-preserving data-enabled predictive control scheme where we exploit affine-masking to protect the privacy of shared input/output data. It is then applied to the control of connected and automated vehicles (CAVs) in a mixed traffic environment with promising results demonstrated through comprehensive simulations.

Data-driven dynamical systems is a burgeoning field?it connects how measurements of nonlinear dynamical systems and/or complex systems can be used with well-established methods in dynamical systems theory. This is a critically important new direction because the governing equations of many problems under consideration by practitioners in various scientific fields are not typically known. Thus, using data alone to help derive, in an optimal sense, the best dynamical system representation of a given application allows for important new insights. The recently developed dynamic mode decomposition (DMD) is an innovative tool for integrating data with dynamical systems theory. The DMD has deep connections with traditional dynamical systems theory and many recent innovations in compressed sensing and machine learning. Dynamic Mode Decomposition: Data-Driven Modeling of Complex Systems, the first book to address the DMD algorithm, presents a pedagogical and comprehensive approach to all aspects of DMD currently developed or under development; blends theoretical development, example codes, and applications to showcase the theory and its many innovations and uses; highlights the numerous innovations around the DMD algorithm and demonstrates its efficacy using example problems from engineering and the physical and biological sciences; and provides extensive MATLAB code, data for intuitive examples of key methods, and graphical presentations.

This book belongs to the subject of control and systems theory. It studies a novel data-driven framework for the design and analysis of iterative learning control (ILC) for nonlinear discrete-time systems. A series of iterative dynamic linearization methods is discussed firstly to build a linear data mapping with respect of the system’s output and input between two consecutive iterations. On this basis, this work presents a series of data-driven ILC (DDILC) approaches with rigorous analysis. After that, this work also conducts significant extensions to the cases with incomplete data information, specified point tracking, higher order law, system constraint, nonrepetitive uncertainty, and event-triggered strategy to facilitate the real applications. The readers can learn the recent progress on DDILC for complex systems in practical applications. This book is intended for academic scholars, engineers, and graduate students who are interested in learning control, adaptive control, nonlinear systems, and related fields.