Special Issue "Machine Learning-Guided Intelligent Modeling with Its Industrial Applications"

Submission Deadline: 01 October 2022
Submit to Special Issue
Guest Editors
Prof. Xiong Luo, University of Science and Technology Beijing, China.
Dr. Yongqiang Cheng, University of Hull, UK.
Prof. Zhifang Liao, Central South University, China.


The industrial system is the nerve center widely used in the fields of critical infrastructure such as power, petroleum and petrochemical, water conservancy, transportation, and nuclear facilities. With the increasing demand for intelligent manufacturing, the essence of the modern industrial system has been transformed into human-cyber-physical systems. Therefore, the industrial system has become a complex system with many factors, and the modeling and design guided by machine learning (ML) are gradually applied to large-scale production with higher accuracy.

In recent years, industrial production has reached an unprecedented level. In the complex industrial system operation process, huge amounts of production, operation, control, and other kinds of data are generated, which can be generally characterized by massiveness, multi-source, heterogeneity, and high-dimension. The accumulation of big data not only promotes the development of production technology but also brings great challenges. Due to its limited representation ability, the traditional modeling method cannot fully extract the information contained in the big data of the industrial system, thus, intelligent modeling intends to fully explore the useful information in big data by constructing an appropriate intelligent modeling structure. Accordingly, ML-guided directed evolution has become a new paradigm for industrial design that enables the optimization of complex functions. Both structured and unstructured data from industrial systems can be applied to ML intelligent modeling use to predict how sequence maps function without requiring a detailed model of the underlying physics pathways. Then it can help the system to make more accurate intelligent decisions and promote the concept of digital twins.


The focus of this Special Issue is on the development of ML-guided intelligent modeling for solving problems in the fields of industrial. Articles submitted to this Special Issue can also be concerned with the intelligence algorithms for systematic modeling, simulation, and optimization of complex industrial systems. We invite researchers to contribute original research articles, as well as review articles, that will stimulate the continuing research effort on applications of data-enabled intelligence about complex industrial systems and computing techniques to assess/solve engineering problems.

Topics of interest include but are not restricted to:

-Industrial applications of complex system theory

-Machine learning and deep learning for complex system modeling

-Filter-aided methods for industrial processes

-Data-driven control of industrial systems

-Artificial intelligence for system optimization

-Neurodynamic analysis for industrial process

-Detection classification for complex industrial systems

-Distributed multi-agent modeling algorithms and its industrial applications

-Robust modeling methods for industrial process

-the other related topics

Machine learning; Deep learning; Intelligent models; Data analysis; Industrial applications

Published Papers
  • LF-CNN: Deep Learning-Guided Small Sample Target Detection for Remote Sensing Classification
  • Abstract Target detection of small samples with a complex background is always difficult in the classification of remote sensing images. We propose a new small sample target detection method combining local features and a convolutional neural network (LF-CNN) with the aim of detecting small numbers of unevenly distributed ground object targets in remote sensing images. The k-nearest neighbor method is used to construct the local neighborhood of each point and the local neighborhoods of the features are extracted one by one from the convolution layer. All the local features are aggregated by maximum pooling to obtain global feature representation. The classification… More
  •   Views:47       Downloads:39        Download PDF

  • Machine Learning Enhanced Boundary Element Method: Prediction of Gaussian Quadrature Points
  • Abstract This paper applies a machine learning technique to find a general and efficient numerical integration scheme for boundary element methods. A model based on the neural network multi-classification algorithm is constructed to find the minimum number of Gaussian quadrature points satisfying the given accuracy. The constructed model is trained by using a large amount of data calculated in the traditional boundary element method and the optimal network architecture is selected. The two-dimensional potential problem of a circular structure is tested and analyzed based on the determined model, and the accuracy of the model is about 90%. Finally, by incorporating the… More
  •   Views:47       Downloads:48        Download PDF

  • Transferable Features from 1D-Convolutional Network for Industrial Malware Classification
  • Abstract With the development of information technology, malware threats to the industrial system have become an emergent issue, since various industrial infrastructures have been deeply integrated into our modern works and lives. To identify and classify new malware variants, different types of deep learning models have been widely explored recently. Generally, sufficient data is usually required to achieve a well-trained deep learning classifier with satisfactory generalization ability. However, in current practical applications, an ample supply of data is absent in most specific industrial malware detection scenarios. Transfer learning as an effective approach can be used to alleviate the influence of the… More
  •   Views:228       Downloads:172        Download PDF