Wei Chen

Northwestern University | NU · Department of Mechanical Engineering

Metamaterials with functional responses can exhibit varying properties under different conditions (e.g., wave‐based responses or deformation‐induced property variation). This work addresses rapid inverse design of such metamaterials to meet target qualitative functional behaviors, a challenge due to its intractability and nonunique solutions. Unlik...

System design has been facing the challenges of incorporating complex dependencies between individual entities into design formulations. For example, while the decision-based design framework successfully integrated customer preference modeling into optimal design, the problem was formulated from a single entity's perspective, and the competition b...

Network-based analyses have shown their effectiveness in understanding customer preferences through interactions and relationships between customers and products, particularly for tailored product design. There is limited research on applying this analysis to diverse customers with varied preferences. This paper introduces a market-segmented networ...

Graph neural networks (GNNs) have excelled in predictive modeling for both crystals and molecules, owing to the expressiveness of graph representations. High-entropy alloys (HEAs), however, lack chemical long-range order, limiting the applicability of current graph representations. To overcome this challenge, we propose a representation of HEAs as...

Artificial intelligence and machine learning frameworks have served as computationally efficient mapping between inputs and outputs for engineering problems. These mappings have enabled optimization and analysis routines that have warranted superior designs, ingenious material systems and optimized manufacturing processes. A common occurrence in su...

Recent advances in machine learning (ML) are expediting materials discovery and design. One significant challenge facing ML for materials is the expansive combinatorial space of potential materials formed by diverse constituents and their flexible configurations. This complexity is particularly evident in molecular mixtures, a frequently explored s...

A representative volume element (RVE) is a reasonably small unit of microstructure that can be simulated to obtain the same effective properties as the entire microstructure sample. Finite element (FE) simulation of RVEs, as opposed to much larger samples, saves computational expenses, especially in multiscale modeling. Therefore, it is desirable t...

Materials in crystalline form possess translational symmetry (TS) when the unit cell is repeated in real space with long‐ and short‐range orders. The periodic potential in the crystal regulates the electron wave function and results in unique band structures, which further define the physical properties of the materials. Amorphous materials lack TS...

High-performance catalysts are crucial for sustainable energy conversion and human health. However, the discovery of catalysts faces challenges due to the absence of efficient approaches to navigating vast and high-dimensional structure and composition spaces. In this study, we propose a high-throughput computational catalyst screening approach int...

Customer preferences are found to evolve over time and correlate with geographical locations. Studying spatiotemporal heterogeneity of customer preferences is crucial to engineering design as it provides a dynamic perspective for understanding the trend of customer preferences. However, existing choice models for demand modeling do not take the spa...

Gaining a deep insight into the factors that influence product competition is essential for a company to maintain its competitiveness in the market. While many studies have been conducted on competition analysis of various products, existing work often has oversight of market heterogeneity. This makes the analysis of product competition less accura...

Network-based analyses have been shown to be effective in understanding customer preferences by modeling the interactions and relationships between customers and products as a complex network system. Certain network representations, such as bipartite networks, can capture customers’ two-stage (consideration-then-choice) decision-making processes by...

Liquid phase exfoliation (LPE) of graphene is a potentially scalable method to produce conductive graphene inks for printed electronic applications. Among LPE methods, wet jet milling (WJM) is an emerging approach that uses high‐speed, turbulent flow to exfoliate graphene nanoplatelets from graphite in a continuous flow manner. Unlike prior WJM wor...

Multifunctional metamaterials (MMM) bear promise as next‐generation material platforms supporting miniaturization and customization. Despite many proof‐of‐concept demonstrations and the proliferation of deep learning assisted design, grand challenges of inverse design for MMM, especially those involving heterogeneous fields possibly subject to eith...

This paper presents the data collection method and introduces the dataset about consumers’ consider-then-choose behaviors in the household vacuum cleaner market. First, we designed a questionnaire that collected participants’ consideration and choice data, social network data, demographic information, and preferences for product features. In additi...

Multi-fidelity (MF) methods are gaining popularity for enhancing surrogate modeling and design optimization by incorporating data from both high- and various low-fidelity (LF) models. While most existing MF methods assume a fixed training set, adaptive sampling methods that dynamically allocate resources among models with different fidelities can a...

Recent advances in machine learning (ML) have expedited materials discovery and design. One significant challenge faced in ML for materials is the expansive combinatorial space of potential materials formed by diverse constituents and their flexible configurations. This complexity is particularly evident in molecular mixtures, a frequently explored...

Shape morphing that transforms morphologies in response to stimuli is crucial for future multifunctional systems. While kirigami holds great promise in enhancing shape-morphing, existing designs primarily focus on kinematics and overlook the underlying physics. This study introduces a differentiable inverse design framework that considers the physi...

Multifunctional metamaterials (MMM) bear promise as next-generation material platforms supporting miniaturization and customization. Despite many proof-of-concept demonstrations and the proliferation of deep learning assisted design, grand challenges of inverse design for MMM, especially those involving heterogeneous fields possibly subject to eith...

Metamaterials with functional responses, such as wave-based responses or deformation-induced property variation under external stimuli, can exhibit varying properties or functionalities under different conditions. Herein, we aim at rapid inverse design of these metamaterials to meet target qualitative functional behaviors. This inverse problem is c...

Metamaterials are artificial materials designed to exhibit effective material parameters that go beyond those found in nature. Composed of unit cells with rich designability that are assembled into multiscale systems, they hold great promise for realizing next‐generation devices with exceptional, often exotic, functionalities. However, the vast des...

A bottleneck in high-throughput nanomaterials discovery is the pace at which new materials can be structurally characterized. Although current machine learning (ML) methods show promise for the automated processing of electron diffraction patterns (DPs), they fail in high-throughput experiments where DPs are collected from crystals with random orie...

It has been widely recognized that structural materials are better designed simultaneously with the target component so that their properties can be tailored to the service loading conditions to meet component performance. This concurrent approach helps avoid over-strengthening the materials and components through unnecessary reinforcements, leadin...

Data-driven materials design often encounters challenges where systems possess qualitative (categorical) information. Specifically, representing Metal-organic frameworks (MOFs) through different building blocks poses a challenge for designers to incorporate qualitative information into design optimization, and leads to a combinatorial challenge, wi...

The localized stress and strain field simulation results are critical for understanding the mechanical properties of materials, such as strength and toughness. However, applying off-the-shelf machine learning or deep learning methods to a digitized microstructure restricts the image samples to be of a fixed size and also lacks interpretability. Add...

Polymer nanodielectrics present a particularly challenging materials design problem for capacitive energy storage applications like polymer film capacitors. High permittivity and breakdown strength are needed to achieve high energy density and loss must be low. Strategies that increase permittivity tend to decrease the breakdown strength and increa...

Researchers have developed a uniform grating DFB with an integrated active optical feedback waveguide (UG-AFDFB) to enhance the modulation speed of direct modulation lasers (DMLs) while reducing costs based on identical active layer designations. However, this design has difficulties in obtaining high single mode yield (SMY) and low relative intens...

Metamaterials are artificial materials designed to exhibit effective material parameters that go beyond those found in nature. Composed of unit cells with rich designability that are assembled into multiscale systems, they hold great promise for realizing next-generation devices with exceptional, often exotic, functionalities. However, the vast des...

While most calibration methods focus on inferring a set of model parameters that are unknown but assumed to be constant, many models have parameters that have a functional relation with the controllable input variables. Formulating a low-dimensional approximation of these calibration functions allows modelers to use low-fidelity models to explore p...

Growing materials data and data-driven informatics drastically promote the discovery and design of materials. While there are significant advancements in data-driven models, the quality of data resources is less studied despite its huge impact on model performance. In this work, we focus on data bias arising from uneven coverage of materials famili...

A bottleneck in high-throughput nanomaterials discovery is the pace at which new materials can be structurally characterized. Although current machine learning (ML) methods show promise for the automated processing of electron diffraction patterns (DPs), they fail in high-throughput experiments where DPs are collected from crystals with random orie...

Data-driven methods have gained increasing attention in computational mechanics and design. This study investigates a two-scale data-driven design for thermal metamaterials with various functionalities. To address the complexity of multiscale design, the design variables are chosen as the components of the homogenized thermal conductivity matrix or...

Customer preference modelling has been widely used to aid engineering design decisions on the selection and configuration of design attributes. Recently, network analysis approaches, such as the exponential random graph model (ERGM), have been increasingly used in this field. While the ERGM-based approach has the new capability of modelling the eff...

Cracks that form during fatigue offer critical information regarding the fracture process of the associated material, such as the crack speed, energy dissipation, and material stiffness. Characterization of the surfaces formed after these cracks have propagated through the material can provide important information complementary to other in-depth a...

The design and operation of systems are conventionally viewed as a sequential decision-making process that is informed by data from physical experiments and simulations. However, the integration of these high-dimensional and heterogeneous data sources requires the consideration of the impact of a decision on a system’s remaining life cycle. Consequ...

Additive Manufacturing (AM) simulations offer an alternative to expensive AM experiments to study the effects of processing conditions on granular microstructures. Existing AM simulations lack support from reliable validation techniques. The stochastic nature and spatial heterogeneity of microstructures make it difficult to validate the simulated m...

Data-driven design shows the promise of accelerating materials discovery but is challenging due to the prohibitive cost of searching the vast design space of chemistry, structure, and synthesis methods. Bayesian optimization (BO) employs uncertainty-aware machine learning models to select promising designs to evaluate, hence reducing the cost. Howe...

Growing materials data and data-centric informatics tools drastically promote the discovery and design of materials. While data-driven models, such as machine learning, have drawn much attention and observed significant progress, the quality of data resources is equally important but less studied. In this work, we focus on bias mitigation, an impor...

Inspired by the recent achievements of machine learning in diverse domains, data-driven metamaterials design has emerged as a compelling paradigm that can unlock the potential of the multiscale architectures. The model-centric research trend, however, lacks principled frameworks dedicated to data acquisition, whose quality propagates into the downs...

Engineering design often involves qualitative and quantitative design variables, which requires systematic methods for the exploration of these mixed-variable design spaces. Expensive simulation techniques, such as those encountered in materials design, underline the need for efficient search strategies — Bayesian optimization being one of the most...

Deep generative models have demonstrated effectiveness in learning compact and expressive design representations that significantly improve geometric design optimization. However, these models do not consider the uncertainty introduced by manufacturing or fabrication. Past work that quantifies such uncertainty often makes simplifying assumptions on...

The design and operation of systems are conventionally viewed as a sequential decision-making process that is informed by data from physical experiments and simulations. However, the integration of these high-dimensional and heterogeneous data sources requires the consideration of the impact of a decision on a system's remaining life cycle. Consequ...

Real engineering and scientific applications often involve one or more qualitative inputs. Standard Gaussian processes (GPs), however, cannot directly accommodate qualitative inputs. The recently introduced latent variable Gaussian process (LVGP) overcomes this issue by first mapping each qualitative factor to underlying latent variables (LVs), and...

Engineering design often involves qualitative and quantitative design variables, which requires systematic methods for the exploration of these mixed-variable design spaces. Expensive simulation techniques, such as those required to evaluate optimization objectives in materials design applications, constitute the main portion of the cost of the des...

I Inspired by the recent achievements of machine learning in diverse domains, data-driven metamaterials design has emerged as a compelling paradigm that can unlock the potential of multiscale architectures. The model-centric research trend, however, lacks principled frameworks dedicated to data acquisition, whose quality propagates into the downstr...

Deep generative models have demonstrated effectiveness in learning compact and expressive design representations that significantly improve geometric design optimization. However, these models do not consider the uncertainty introduced by manufacturing or fabrication. Past work that quantifies such uncertainty often makes simplifying assumptions on...

Based on standard stiffness (compliance) and stress designs in structural topology optimization (TO), this work proposes a simple strategy to tailor fracture properties of brittle architected materials. Material distribution in the design domain is customized through a stress‐constrained strain‐energy maximization TO framework. Structures consistin...

Data-driven design shows the promise of accelerating materials discovery but is challenging due to the prohibitive cost of searching the vast design space of chemistry, structure, and synthesis methods. Bayesian Optimization (BO) employs uncertainty-aware machine learning models to select promising designs to evaluate, hence reducing the cost. Howe...

Molecular dynamics simulations have shown substantial promise in the design of organic photovoltaic cells (OPVC). Despite their potential, the utility of molecular dynamics simulations when designing an OPVC is often limited due to their considerable computational cost and their limited prediction accuracy. To address these challenges, we introduce...

Data-driven design shows the promise of accelerating materials discovery but is challenging due to the prohibitive cost of searching the vast design space of chemistry, structure, and synthesis methods. Bayesian Optimization (BO) employs uncertainty-aware machine learning models to select promising designs to evaluate, hence reducing the cost. Howe...

Polymer Nanodielectrics are class of materials with intriguing combinations of properties. Predicting and designing the properties, however, is complex due to the number of parameters controlling the properties. This makes it difficult to compare results across groups, validate models, and develop a design methodology. This presentation will share...

Plaques will be awarded to each of the authors of the Editors' Choice Award and certificates will be awarded to the authors of the paper with an Honorable Mention. We would like to congratulate all the award recipients and look forward to continuing to work with the entire ASME community of editors, authors, reviewers, and staff to bring the Journa...

Tread compounding has always been faced with the simultaneous optimization of multiple performance properties, most of which have tradeoffs between the properties. The search for overcoming these conflicting tradeoffs have led many companies in the tire industry to discover and develop material physics-based platforms. This report describes some of...

Predicting and designing the properties of polymer nanodielectrics is challenging due to the number of parameters controlling properties and the breadth of scale (from electronic to mm). This paper summarizes a preliminary study using elongated semiconducting nanoparticles with an extrinsic interface that enhanced carrier trapping to attempt to fin...

Understanding relationships between different products in a market system and predicting how changes in design impact their market position can be instrumental for companies to create better products. We propose a graph neural network-based method for modeling relationships between products, where nodes in a network represent products and edges rep...

To create heterogeneous, multiscale structures with unprecedented functionalities, recent topology optimization approaches design either fully aperiodic systems or functionally graded structures, which compete in terms of design freedom and efficiency. We propose to inherit the advantages of both through a data-driven framework for multiclass funct...

De-homogenization is becoming an effective method to significantly expedite the design of high-resolution multiscale structures, but existing methods have thus far been confined to simple static compliance minimization problems. There are two critical issues in accommodating general design cases: enabling the design of unit-cell orientation and usi...

Significance An invisibility cloak to conceal objects from an outside observer has long been a subject of interest in metamaterial design. While cloaks have been manufactured for optical, thermal, and electric fields, limited progress has been made for mechanical cloaks. Most existing designs rely on mapping-based methods, which have so far been li...

Deep generative models have demonstrated effectiveness in learning compact and expressive design representations that significantly improve geometric design optimization. However, these models do not consider the uncertainty introduced by manufacturing or fabrication. Past work that quantifies such uncertainty often makes simplifying assumptions on...

Inspired by the recent success of deep learning in diverse domains, data-driven metamaterials design has emerged as a compelling design paradigm to unlock the potential of multiscale architecture. However, existing model-centric approaches lack principled methodologies dedicated to high-quality data generation. Resorting to space-filling design in...

Prognosis health management is an effective way to improve the operational safety and economy of industrial equipment. The development of an accurate and quick response model to monitor equipment health status, predict performance, and diagnose faults is key to its implementation. However, the inevitable performance degradation of industrial equipm...

Building processing, structure, and property (PSP) relations for computational materials design is at the heart of the Materials Genome Initiative in the era of high-throughput computational materials science. Recent technological advancements in data acquisition and storage, microstructure characterization and reconstruction (MCR), machine learnin...

Statistical network models have been used to study the competition among different products and how product attributes influence customer decisions. However, in existing research using network-based approaches, product competition has been viewed as binary (i.e., whether a relationship exists or not), while in reality, the competition strength may...

We present a systematic inverse design approach to achieve digitally addressable plasmonic metasurfaces. Beyond existing literature, we adopt a variety of input phase profiles to control the local optical field distribution on the metasurface. Our inverse design approach relies on three building blocks. First, we model the spatial phase distributio...