SPECIAL ISSUE: Machine Intelligence for Engineering Under Uncertainties

Machine intelligence (MI) integrates computation, data, models, and algorithms to solve problems that are too complex for humans. During the last three decades, MI has been a highly researched topic and widely used for solving complex real-world engineering problems. The main theme of this Special Issue is dedicated to the development of MI methods that sheds a new light for solving problems deemed difficult in engineering sciences under uncertainties.

Many real-world engineering design problems can be formulated as optimization. Yet the curse of dimensionality with a large number of design variables, both discrete and continuous, makes the solution searching process difficult. Furthermore, interpretation of the large amount of simulation and experimental data needs advanced computation, data mining, Big Data analytics, and deep learning methodologies. The stochastic nature of real-world engineering systems makes these analyses even more challenging. Due to their complexity, real-world problems are difficult to solve using derivative-based local optimization algorithms. In the recent past, MI and its branches have been used to solve complex real-world engineering problems that cannot be solved using conventional methods.

This Special Issue strives to gather the latest developments of MI applications in real-world engineering systems, particularly the ones under uncertainty. On this basis, this Special Issue includes key applications of MI on different engineering disciplines such as engineering design, monitoring and maintenance, structural systems, applied
mechanics, etc. Theories, methodologies, tools, computational aspects for MI topics include (but are not limited to):

Topic Areas
• Mathematical foundation of machine learning under uncertainties
• Probabilistic methods and statistical tools for scientific machine learning
• Neural networks and deep learning with probabilistic reasoning
• Genetic programming and evolved systems with uncertainties
• Evolutionary and Swarm Intelligence with uncertainties for multi-objective problems
• Stochastic and robust optimization using intelligent search methods
• Randomized algorithms (stochastic gradient, compressed sensing, etc.)
• Stochastic surrogate/metamodels with model-form and parameter uncertainties
• Machine learning based on emerging computing hardware
• Data-driven statistical inverse problems
• Data mining, pattern recognition, and data clustering
• Fuzzy control, optimization, and decision making under uncertainties
• Applications of MI in product engineering such as engineering mechanics, system dynamics, reliability
• Applications of MI in process engineering such as scheduling, system monitoring, maintenance, optimal control

TABLE OF CONTENTS

EDITORIAL

Special Issue: Machine Intelligence for Engineering Under Uncertainties 

Amir H. Gandomi, Marc Mignolet, Christian Soize, Yan Wang, J. Comput. Inf. Sci. Eng. February 2023, 23(1): 010201. doi: https://doi.org/10.1115/1.4056396

RESEARCH PAPERS

Surrogate Modeling of Nonlinear Dynamic Systems: A Comparative Study 

Ying Zhao, Chen Jiang, Manuel A. Vega, Michael D. Todd, Zhen Hu, J. Comput. Inf. Sci. Eng. February 2023, 23(1): 011001. doi: https://doi.org/10.1115/1.4054039

A Framework for Inverse Prediction Using Functional Response Data 

Daniel Ries, Adah Zhang, J. Derek Tucker, Kurtis Shuler, Madeline Ausdemore, J. Comput. Inf. Sci. Eng. February 2023, 23(1): 011002. doi: https://doi.org/10.1115/1.4053752

A Probabilistic Learning Approach Applied to the Optimization of Wake Steering in Wind Farms 

Jeferson O. Almeida, Fernando A. Rochinha, J. Comput. Inf. Sci. Eng. February 2023, 23(1): 011003. doi: https://doi.org/10.1115/1.4054501

A Priori Denoising Strategies for Sparse Identification of Nonlinear Dynamical Systems: A Comparative Study 

Alexandre Cortiella, Kwang-Chun Park, Alireza Doostan, J. Comput. Inf. Sci. Eng. February 2023, 23(1): 011004. doi: https://doi.org/10.1115/1.4054573

Uncertainty Quantification and Optimal Robust Design for Machining Operations 

Jinming Wan, Yiming Che, Zimo Wang, Changqing Cheng, J. Comput. Inf. Sci. Eng. February 2023, 23(1): 011005. doi: https://doi.org/10.1115/1.4055039

Multi-Level Bayesian Calibration of a Multi-Component Dynamic System Model 

Berkcan Kapusuzoglu, Sankaran Mahadevan, Shunsaku Matsumoto, Yoshitomo Miyagi, Daigo Watanabe, J. Comput. Inf. Sci. Eng. February 2023, 23(1): 011006. doi: https://doi.org/10.1115/1.4055315

Characterizations and Optimization for Resilient Manufacturing Systems With Considerations of Process Uncertainties

Qiyang Ma, Yiming Che, Changqing Cheng, Zimo Wang, J. Comput. Inf. Sci. Eng. February 2023, 23(1): 011007. doi: https://doi.org/10.1115/1.4055425

A Multi-Fidelity Approach for Reliability Assessment Based on the Probability of Classification Inconsistency 

Bharath Pidaparthi, Samy Missoum, J. Comput. Inf. Sci. Eng. February 2023, 23(1): 011008. doi: https://doi.org/10.1115/1.4055508

Acceleration of a Physics-Based Machine Learning Approach for Modeling and Quantifying Model-Form Uncertainties and Performing Model Updating 

Marie-Jo Azzi, Chady Ghnatios, Philip Avery, Charbel Farhat, J. Comput. Inf. Sci. Eng. February 2023, 23(1): 011009. doi: https://doi.org/10.1115/1.4055546

Spatial Transform Depthwise Over-Parameterized Convolution Recurrent Neural Network for License Plate Recognition in Complex Environment 

Jiehang Deng, Haomin Wei, Zhenxiang Lai, Guosheng Gu, Zhiqiang Chen, Leo Chen, Lei Ding, J. Comput. Inf. Sci. Eng. February 2023, 23(1): 011010. doi: https://doi.org/10.1115/1.4055507

Monotonic Gaussian Process for Physics-Constrained Machine Learning With Materials Science Applications 

Anh Tran, Kathryn Maupin, Theron Rodgers, J. Comput. Inf. Sci. Eng. February 2023, 23(1): 011011. doi: https://doi.org/10.1115/1.4055852

Physics-Constrained Bayesian Neural Network for Bias and Variance Reduction 

Luka Malashkhia, Dehao Liu, Yanglong Lu, Yan Wang, J. Comput. Inf. Sci. Eng. February 2023, 23(1): 011012. doi: https://doi.org/10.1115/1.4055924

TECHNICAL BRIEFS

A Nested Weighted Tchebycheff Multi-Objective Bayesian Optimization Approach for Flexibility of Unknown Utopia Estimation in Expensive Black-Box Design Problems 

Arpan Biswas, Claudio Fuentes, Christopher Hoyle, J. Comput. Inf. Sci. Eng. February 2023, 23(1): 014501. doi: https://doi.org/10.1115/1.4054480

A Quantitative Insight Into the Role of Skip Connections in Deep Neural Networks of Low Complexity: A Case Study Directed at Fluid Flow Modeling 

Abouzar Choubineh, Jie Chen, Frans Coenen, Fei Ma, J. Comput. Inf. Sci. Eng. February 2023, 23(1): 014502. doi: https://doi.org/10.1115/1.4054868

GUEST EDITORS

Amir H. Gandomi, Professor, University of Technology Sydney, Australia, gandomi@uts.edu.au
Marc Mignolet, Professor, Arizona State University, USA, marc.mignolet@asu.edu
Christian Soize, Professor, Université Gustave Eiffel, France, christian.soize@univ-eiffel.fr
Yan Wang, Professor, Georgia Institute of Technology, USA, yan.wang@me.gatech.edu