arXiv subjects

Lai Wei

Publications and source records attributed to Lai Wei.

At least 91 records · Page 5Linked to original sources

arXiv2022

A Contraction-constrained Model Predictive Control for Nonlinear Processes using Disturbance Forecasts

Model predictive control (MPC) has become the most widely used advanced control method in process industry. In many cases, forecasts of the disturbances are available, e.g., predicted renewable power generation based on weather forecast. While the predictions of disturbances may not be accurate, utilizing the information can significantly improve the control performance in response to the disturbances. By exploiting process and disturbance models, future system behaviour can be predicted and used to optimise control actions via minimisation of an economical cost function which incorporates these predictions. However, stability guarantee of the resulting closed-loop system is often difficult in this approach when the processes are nonlinear. Proposed in the following article is a contraction-constrained predictive controller which optimises process economy whilst ensuring stabilisation to operating targets subject to disturbance measurements and forecasts.

eess.SY↗

arXiv2022

Contraction Analysis and Control Synthesis for Discrete-time Nonlinear Processes

Shifting away from the traditional mass production approach, the process industry is moving towards more agile, cost-effective and dynamic process operation (next-generation smart plants). This warrants the development of control systems for nonlinear chemical processes to be capable of tracking time-varying setpoints to produce products with different specifications as per market demand and deal with variations in the raw materials and utility (e.g., energy). This article presents a systematic approach to the implementation of contraction-based control for discrete-time nonlinear processes. Through the differential dynamic system framework, the contraction conditions to ensure the exponential convergence to feasible time-varying references are derived. The discrete-time differential dissipativity condition is further developed, which can be used for control designs for disturbance rejection. Computationally tractable equivalent conditions are then derived and additionally transformed into an SOS programming problem, such that a discrete-time control contraction metric and stabilising feedback controller can be jointly obtained. Synthesis and implementation details are provided and demonstrated through a numerical case study.

eess.SY↗

arXiv2022

Adaptive Contraction-based Control of Uncertain Nonlinear Processes using Neural Networks

Driven by the flexible manufacturing trend in the process control industry and the uncertain nature of chemical process models, this article aims to achieve offset-free tracking for a family of uncertain nonlinear systems (e.g., using process models with parametric uncertainties) with adaptable performance. The proposed adaptive control approach incorporates into the control loop an adaptive neural network embedded contraction-based controller (to ensure convergence to time-varying references) and an online parameter identification module coupled with reference generation (to ensure modelled parameters converge those of the physical system). The integrated learning and control approach involves training a state and parameter dependent neural network to learn a contraction metric parameterized by the uncertain parameter and a differential feedback gain. This neural network is then embedded in an adaptive contraction-based control law which is updated by parameter estimates online. As uncertain parameter estimates converge to the corresponding physical values, offset-free tracking, simultaneously with improved convergence rates, can be achieved, resulting in a flexible, efficient and less conservative approach to the reference tracking control of uncertain nonlinear processes. An illustrative example is included to demonstrate the overall approach. An illustrative example is included to demonstrate the overall approach.

eess.SY↗

arXiv2022

A Contraction-constrained Model Predictive Control for Multi-timescale Nonlinear Processes

Many chemical processes exhibit diverse timescale dynamics with a strong coupling between timescale sensitive variables. Model predictive control with a non-uniformly spaced optimisation horizon is an effective approach to multi-timescale control and offers opportunities for reduced computational complexity. In such an approach the fast, moderate and slow dynamics can be included in the optimisation problem by implementing smaller time intervals earlier in the prediction horizon and increasingly larger intervals towards the end of the prediction. In this paper, a reference-flexible condition is developed based on the contraction theory to provide a stability guarantee for a nonlinear system under non-uniform prediction horizons.

eess.SY↗

arXiv2022

Crystal Transformer: Self-learning neural language model for Generative and Tinkering Design of Materials

Self-supervised neural language models have recently achieved unprecedented success, from natural language processing to learning the languages of biological sequences and organic molecules. These models have demonstrated superior performance in the generation, structure classification, and functional predictions for proteins and molecules with learned representations. However, most of the masking-based pre-trained language models are not designed for generative design, and their black-box nature makes it difficult to interpret their design logic. Here we propose BLMM Crystal Transformer, a neural network based probabilistic generative model for generative and tinkering design of inorganic materials. Our model is built on the blank filling language model for text generation and has demonstrated unique advantages in learning the "materials grammars" together with high-quality generation, interpretability, and data efficiency. It can generate chemically valid materials compositions with as high as 89.7\% charge neutrality and 84.8\% balanced electronegativity, which are more than 4 and 8 times higher compared to a pseudo random sampling baseline. The probabilistic generation process of BLMM allows it to recommend tinkering operations based on learned materials chemistry and makes it useful for materials doping. Combined with the TCSP crysal structure prediction algorithm, We have applied our model to discover a set of new materials as validated using DFT calculations. Our work thus brings the unsupervised transformer language models based generative artificial intelligence to inorganic materials. A user-friendly web app has been developed for computational materials doping and can be accessed freely at \url{www.materialsatlas.org/blmtinker}.

cond-mat.mtrl-sci↗

arXiv2022

DeepXRD, a Deep Learning Model for Predicting of XRD spectrum from Materials Composition

One of the long-standing problems in materials science is how to predict a material's structure and then its properties given only its composition. Experimental characterization of crystal structures has been widely used for structure determination, which is however too expensive for high-throughput screening. At the same time, directly predicting crystal structures from compositions remains a challenging unsolved problem. Herein we propose a deep learning algorithm for predicting the XRD spectrum given only the composition of a material, which can then be used to infer key structural features for downstream structural analysis such as crystal system or space group classification or crystal lattice parameter determination or materials property predictions. Benchmark studies on two datasets show that our DeepXRD algorithm can achieve good performance for XRD prediction as evaluated over our test sets. It can thus be used in high-throughput screening in the huge materials composition space for new materials discovery.

cond-mat.mtrl-sci↗

arXiv2021

TCSP: a Template based crystal structure prediction algorithm and web server for materials discovery

Fast and accurate crystal structure prediction (CSP) algorithms and web servers are highly desirable for exploring and discovering new materials out of the infinite design space. However, currently, the computationally expensive first principle calculation based crystal structure prediction algorithms are applicable to relatively small systems and are out of reach of most materials researchers due to the requirement of high computing resources or the software cost related to ab initio code such as VASP. Several computational teams have used an element substitution approach for generating or predicting new structures, but usually in an ad hoc way. Here we develop a template based crystal structure prediction algorithm (TCSP) and its companion web server, which makes this tool to be accessible to all materials researchers. Our algorithm uses elemental/chemical similarity and oxidation states to guide the selection of template structures and then rank them based on the substitution compatibility and can return multiple predictions with ranking scores in a few minutes. Benchmark study on the ~98,290 formulas of the Materials Project database using leave-one-out evaluation shows that our algorithm can achieve high accuracy (for 13,145 target structures, TCSP predicted their structures with RMSD < 0.1) for a large portion of the formulas. We have also used TCSP to discover new materials of the Ga-B-N system showing its potential for high-throughput materials discovery. Our user-friendly web app TCSP can be accessed freely at \url{www.materialsatlas.org/crystalstructure} on our MaterialsAtlas.org web app platform.

cond-mat.mtrl-sci↗

arXiv2021

Predicting Lattice Phonon Vibrational Frequencies Using Deep Graph Neural Networks

Lattice vibration frequencies are related to many important materials properties such as thermal and electrical conductivity as well as superconductivity. However, computational calculation of vibration frequencies using density functional theory (DFT) methods is too computationally demanding for a large number of samples in materials screening. Here we propose a deep graph neural network-based algorithm for predicting crystal vibration frequencies from crystal structures with high accuracy. Our algorithm addresses the variable dimension of vibration frequency spectrum using the zero padding scheme. Benchmark studies on two data sets with 15,000 and 35,552 samples show that the aggregated $R^2$ scores of the prediction reaches 0.554 and 0.724 respectively. Our work demonstrates the capability of deep graph neural networks to learn to predict phonon spectrum properties of crystal structures in addition to phonon density of states (DOS) and electronic DOS in which the output dimension is constant.

cond-mat.mtrl-sci↗

arXiv2021

A Two-stage Pricing Strategy Considering Learning Effects and Word-of-Mouth

This paper proposes a two-stage pricing strategy for nondurable (such as typical electronics) products, where retail price is cut down at certain time points of the product lifecycle. We consider learning effect of electronic products that, with the accumulation of production, average production cost decreases over time as manufacturers get familiar with the production process. Moreover, word-of-mouth (WOM) of existing customers is used to analyze future demand, which is sensitive to the difference between the actual reliability and the perceived reliability of products. We theoretically prove the existence and uniqueness of the optimal switch time between the two stages and the optimal price in each stage. In addition, warranty as another important factor of electronic products is also considered, whose interaction with word-of-mouth as well as the corresponding influences on total profit are analyzed. Interestingly, our findings indicate that (1) the main reason for manufacturers to cut down prices for electronic products pertains to the learning effects; (2) even through both internal factors (e.g., the learning effects of manufacturers) and external factors (e.g., the price elasticity of customers) have impacts on product price, their influence on manufacturer's profit is widely divergent; (3) generally warranty weakens the influence of external advertising on the reliability estimate, because warranty price only partially reflects the actual reliability information of products; (4) and the optimal warranty price can increase the profits for the manufacturer by approximately 10%.

econ.GN↗

arXiv2021

Scalable deeper graph neural networks for high-performance materials property prediction

Machine learning (ML) based materials discovery has emerged as one of the most promising approaches for breakthroughs in materials science. While heuristic knowledge based descriptors have been combined with ML algorithms to achieve good performance, the complexity of the physicochemical mechanisms makes it urgently needed to exploit representation learning from either compositions or structures for building highly effective materials machine learning models. Among these methods, the graph neural networks have shown the best performance by its capability to learn high-level features from crystal structures. However, all these models suffer from their inability to scale up the models due to the over-smoothing issue of their message-passing GNN architecture. Here we propose a novel graph attention neural network model DeeperGATGNN with differentiable group normalization and skip-connections, which allows to train very deep graph neural network models (e.g. 30 layers compared to 3-9 layers in previous works). Through systematic benchmark studies over six benchmark datasets for energy and band gap predictions, we show that our scalable DeeperGATGNN model needs little costly hyper-parameter tuning for different datasets and achieves the state-of-the-art prediction performances over five properties out of six with up to 10\% improvement. Our work shows that to deal with the high complexity of mapping the crystal materials structures to their properties, large-scale very deep graph neural networks are needed to achieve robust performances.

cond-mat.mtrl-sci↗

arXiv2021

MHD analysis on the physical designs of CFETR and HFRC

The China Fusion Engineering Test Reactor (CFETR) and the Huazhong Field Reversed Configuration (HFRC), currently both under intensive physical and engineering designs in China, are the two major projects representative of the low-density steady-state and high-density pulsed pathways to fusion. One of the primary tasks of the physics designs for both CFETR and HFRC is the assessment and analysis of the magnetohydrodynamic (MHD) stability of the proposed design schemes. Comprehensive efforts on the assessment of MHD stability of CFETR and HFRC baseline scenarios have led to preliminary progresses that may further benefit engineering designs.

physics.plasm-ph↗

arXiv2021

Online Estimation and Coverage Control with Heterogeneous Sensing Information

Heterogeneous multi-robot sensing systems are able to characterize physical processes more comprehensively than homogeneous systems. Access to multiple modalities of sensory data allow such systems to fuse information between complementary sources and learn richer representations of a phenomenon of interest. Often, these data are correlated but vary in fidelity, i.e., accuracy (bias) and precision (noise). Low-fidelity data may be more plentiful, while high-fidelity data may be more trustworthy. In this paper, we address the problem of multi-robot online estimation and coverage control by combining low- and high-fidelity data to learn and cover a sensory function of interest. We propose two algorithms for this task of heterogeneous learning and coverage -- namely Stochastic Sequencing of Multi-fidelity Learning and Coverage (SMLC) and Deterministic Sequencing of Multi-fidelity Learning and Coverage (DMLC) -- and prove that they converge asymptotically. In addition, we demonstrate the empirical efficacy of SMLC and DMLC through numerical simulations.

cs.RO↗

arXiv2021

Multi-Robot Gaussian Process Estimation and Coverage: A Deterministic Sequencing Algorithm and Regret Analysis

We study the problem of distributed multi-robot coverage over an unknown, nonuniform sensory field. Modeling the sensory field as a realization of a Gaussian Process and using Bayesian techniques, we devise a policy which aims to balance the tradeoff between learning the sensory function and covering the environment. We propose an adaptive coverage algorithm called Deterministic Sequencing of Learning and Coverage (DSLC) that schedules learning and coverage epochs such that its emphasis gradually shifts from exploration to exploitation while never fully ceasing to learn. Using a novel definition of coverage regret which characterizes overall coverage performance of a multi-robot team over a time horizon $T$, we analyze DSLC to provide an upper bound on expected cumulative coverage regret. Finally, we illustrate the empirical performance of the algorithm through simulations of the coverage task over an unknown distribution of wildfires.

cs.RO↗

arXiv2021

Control Contraction Metric Synthesis for Discrete-time Nonlinear Systems

Flexible manufacturing has been the trend in the area of the modern chemical process nowadays. One of the essential characteristics of flexible manufacturing is to track time-varying target trajectories (e.g. diversity and quantity of products). A possible tool to achieve time-varying targets is contraction theory. However, the contraction theory was developed for continuous time systems and there lacks analysis and synthesis tools for discrete-time systems. This article develops a systematic approach to discrete-time contraction analysis and control synthesis using Discrete-time Control Contraction Metrics (DCCM) which can be implemented using Sum of Square (SOS) programming. The proposed approach is demonstrated by illustrative example.

eess.SY↗

arXiv2021

Nonstationary Stochastic Multiarmed Bandits: UCB Policies and Minimax Regret

We study the nonstationary stochastic Multi-Armed Bandit (MAB) problem in which the distribution of rewards associated with each arm are assumed to be time-varying and the total variation in the expected rewards is subject to a variation budget. The regret of a policy is defined by the difference in the expected cumulative rewards obtained using the policy and using an oracle that selects the arm with the maximum mean reward at each time. We characterize the performance of the proposed policies in terms of the worst-case regret, which is the supremum of the regret over the set of reward distribution sequences satisfying the variation budget. We extend Upper-Confidence Bound (UCB)-based policies with three different approaches, namely, periodic resetting, sliding observation window and discount factor and show that they are order-optimal with respect to the minimax regret, i.e., the minimum worst-case regret achieved by any policy. We also relax the sub-Gaussian assumption on reward distributions and develop robust versions the proposed polices that can handle heavy-tailed reward distributions and maintain their performance guarantees.

cs.LG↗

arXiv2020

Minimax Policy for Heavy-tailed Bandits

We study the stochastic Multi-Armed Bandit (MAB) problem under worst-case regret and heavy-tailed reward distribution. We modify the minimax policy MOSS for the sub-Gaussian reward distribution by using saturated empirical mean to design a new algorithm called Robust MOSS. We show that if the moment of order $1+ε$ for the reward distribution exists, then the refined strategy has a worst-case regret matching the lower bound while maintaining a distribution-dependent logarithm regret.

stat.ML↗

arXiv2020

Secure Performance Analysis and Optimization for FD-NOMA Vehicular Communications

Vehicle-to-vehicle (V2V) communication appeals to increasing research interest as a result of its applications to provide safety information as well as infotainment services. The increasing demand of transmit rates and various requirements of quality of services (QoS) in vehicular communication scenarios call for the integration of V2V communication systems and potential techniques in the future wireless communications, such as full duplex (FD) and non-orthogonal multiple access (NOMA) which enhance spectral efficiency and provide massive connectivity. However, the large amount of data transmission and user connectivity give rise to the concern of security issues and personal privacy. In order to analyze the security performance of V2V communications, we introduce a cooperative NOMA V2V system model with an FD relay. This paper focuses on the security performance of the FD-NOMA based V2V system on the physical layer perspective. We first derive several analytical results of the ergodic secrecy capacity. Then, we propose a secrecy sum rate optimization scheme utilizing the instantaneous channel state information (CSI), which is formulated as a non-convex optimization problem. Based on the differential structure of the non-convex constraints, the original problem is approximated and solved by a series of convex optimization problems. Simulation results validate the analytical results and the effectiveness of the secrecy sum rate optimization algorithm.

cs.IT↗

arXiv2020

When deep learning meets causal inference: a computational framework for drug repurposing from real-world data

Drug repurposing is an effective strategy to identify new uses for existing drugs, providing the quickest possible transition from bench to bedside. Existing methods for drug repurposing that mainly focus on pre-clinical information may exist translational issues when applied to human beings. Real world data (RWD), such as electronic health records and insurance claims, provide information on large cohorts of users for many drugs. Here we present an efficient and easily-customized framework for generating and testing multiple candidates for drug repurposing using a retrospective analysis of RWDs. Building upon well-established causal inference and deep learning methods, our framework emulates randomized clinical trials for drugs present in a large-scale medical claims database. We demonstrate our framework in a case study of coronary artery disease (CAD) by evaluating the effect of 55 repurposing drug candidates on various disease outcomes. We achieve 6 drug candidates that significantly improve the CAD outcomes but not have been indicated for treating CAD, paving the way for drug repurposing.

stat.AP↗