Special Issue "Recent Trends in Artificial Intelligence for Automated Complex Industrial Systems"

Submission Deadline: 30 October 2020 (closed)
Guest Editors
Dr. S. Balamurugan, Intelligent Research Consultancy Services, India
Prof. Seifedine Kadry, Beirut Arab University, Lebanon
Dr. R.Lakshmana Kumar, Hindusthan College of Engineering and Technology, India
Prof. BalaAnand Muthu, College of Engineering and Technology, India

Summary

The development of Artificial Intelligence is speeding up rapidly and combination of Artificial Intelligence with automation has started to change the business landscape. As the technologies are becoming more complex, the demand of Artificial Intelligence is growing because of its ability to solve complex problems with limited human resources and expertise and within a limited time. AI adopts the abilities to equip the technical expertise and can amplify expertise to learn and deploy new methods and applications.


AI and complex systems techniques are of value for many different aspects of manufacturing management and control. Complex Systems constitute many elements that communicate with each other. It also refers to the study of relationships and the resulting behavior as well as how the system interacts and forms a relationship with the environment. Modeling of Complex System is typically difficult due to the behavior such as the dependencies, relationships or other interactions between the system and environment. Those behaviors include nonlinearity, emergence, and feedback loops. With the presence of such behaviors, the system is analytically untreatable. Hence, numerical methods are developed and used for both the linear and weakly nonlinear systems. Linearization and several approximation methods are used for nonlinear systems. It is essential to represent complex systems with a model and find effective tools to interpret and perceive them. The complexity involved should make model-based systems invaluable in supporting decision taking.

 

However, the main concern in regards to the modeling of complex systems is their nonlinearity and the need for representation of every detail. A complex system is difficult to be compressed with generic laws and definitely, cannot be subdivided due to its collective dependencies. With the recent growth in computer systems and the effectiveness of programming, the simulation has become an ideal form for representing, modeling and optimizing complex systems. Due to the recent trends in Computers, new nature-inspired metaheuristic algorithms are preferred, though the traditional method is still important for providing solutions. The main reason for the popularity of new metaheuristic algorithms is due to their simplicity and easy implementation while solving diverse and nonlinear problems.

 

In industrial scenarios, there is a continual need to monitor the performance of systems and processes to identify or predict faults or other situations likely to produce undesirable results. Using machine learning, models can be trained on available data to learn the internal, opaque state of complex systems. Due to the complexity of the problems involved, human planners and schedulers tend to resort to oversimplification and reduction. It is, therefore, believed that attempts aimed at tapping the potential of AI, are more likely to benefit from drawing upon work on planning and search than on expert systems.

 

This special issue will provide us a platform to stage various ideas and discussions related to modeling and simulating a complex system with the implications of the latest trends and advancements in the Industrial applications through Artificial Intelligence. This special issue also involves collection of several mathematical and soft computing models which may contribute to the analytic patterns of complex system. This special issue also provides an ample scope for creatively combining various complex systems techniques using Artificial Intelligence.


Keywords
• Automated complex systems governance
• Adaptive and automotive complex systems using AI
• Automated Industrial complex systems modeling, monitoring, and control
• Better planning and decision-making in Industrial AI
• Challenges in complex systems optimization
• Complex system modeling and simulation in Industrial Applications
• Cognitive computation for implementing an automated complex system
• Internet of things and sensor technologies based complex system model
• Industrial AI Use Case

Published Papers
  • Robust Speed Regulation of Induction Motor Subjected to Unknown Load Torque
  • Abstract Induction motors are still the most used in industrial applications due to the simplicity of installation and low maintenance cost, especially for the squirrel cage type. The significant development in power electronics in terms of high-speed technologies in power electronic switches, their availability in high ratings, and the considerable decrease in the cost of the power electronics components supports this increase in uses. However, changing the induction motor's speed with loading, load torque measurement devices, and speed sensors limit this increase in using such motors. This paper proposes a state feedback controller-based backstepping technique for robust speed regulators of induction… More
  •   Views:202       Downloads:60        Download PDF

  • Tyre Inspection through Multi-State Convolutional Neural Networks
  • Abstract Road accident is a potential risk to the lives of both drivers and passers-by. Many road accidents occur due to the improper condition of the vehicle tyres after long term usage. Thus, tyres need to be inspected and analyzed while manufacturing to avoid serious road problems. However, tyre wear is a multifaceted happening. It normally needs the non-linearly on many limitations, like tyre formation and plan, vehicle category, conditions of the road. Yet, tyre wear has numerous profitable and environmental inferences particularly due to maintenance costs and traffic safety implications. Thus, the risk to calculate tyre wear is therefore of… More
  •   Views:827       Downloads:760        Download PDF

  • Text Detection and Classification from Low Quality Natural Images
  • Abstract Detection of textual data from scene text images is a very thought-provoking issue in the field of computer graphics and visualization. This challenge is even more complicated when edge intelligent devices are involved in the process. The low-quality image having challenges such as blur, low resolution, and contrast make it more difficult for text detection and classification. Therefore, such exigent aspect is considered in the study. The technology proposed is comprised of three main contributions. (a) After synthetic blurring, the blurred image is preprocessed, and then the deblurring process is applied to recover the image. (b) Subsequently, the standard maximal… More
  •   Views:613       Downloads:525        Download PDF