TPPC Cover.jpg

Production Planning and Control

Machine Learning Methods for Cloud Based IOT Applications for Manufacturing
Submission Deadline: 25th May 2022

SCOPE AND PURPOSE

Cloud computing is growing rapidly and it has become a necessity for businesses to have a competitive advantage and offer a superior quality of services. Cloud manufacturing provides a new way for upgrading the traditional manufacturing into a knowledge-based, collaborative, flexible and highly efficient one. The IoT is used to connect smart sensors and devices and to collect large amounts of data from the manufacturing shop floor. Machine learning can be leveraged to analyze the big data collected from IoT and transform it into actionable knowledge to support informed decision making. The IoT network connects physical objects with sensors or detectors via the Internet, which enables data collection and cloud-based computing. This has resulted in significant business opportunities in almost all areas, such as manufacturing. The Cloud, the Internet, and sophisticated sensors are all converging and revolutionizing manufacturing, in modern manufacturing environments, sensors and instruments are placed at different parts of the machinery to interpret information regarding environmental condition, operational condition and response on a millisecond basis. Sensor data can be used dynamically with machine learning algorithms to make timely decisions to achieve an efficient manufacturing process. Machine learning enables real-time analysis on various levels of current industrial production and manufacturing processes by applying self-learning algorithms to analyze sensory data in real time with minimal latency.

 

As sensor-enabled machinery and a host of end-user devices are connected to the cloud and generate efficient production of goods and services, the availability of data for the manufacturing industries presents new challenges and opportunities for business leaders. Cloud - based, data-driven approaches facilitate the development of new applications that have the potential to enhance productivity, maintenance logistics and support services beyond the traditional product portfolio. The vision is to enable a transition from reactive to predictive maintenance and eventually to autonomous repair, which would result in vast cost and energy savings. There is a need for models to predict when machines will break down, but also how to best utilize the resources, specifically due to increasing capacity requirements, especially if some assets are kept for longer duration than others, or have different costs associated with them.

 

This special issue aims to increase the innovative research on machine learning  methods for cloud based IoT assisted applications for manufacturing. It is focused on the challenges and opportunities of cloud-based IoT in manufacturing, the importance of the synergic use of machine learning and IoT in several industrial and manufacturing applications, how to select the proper machine learning method (e.g., clustering, classification, regression, or anomaly detection) for specific problems and tasks as well as to understand some practical issues related with performance improvement (complexity, scalability) when we deal with large data volumes originated from smart products/assets that mirror new business models.

 

TOPICS INCLUDE, BUT ARE NOT LIMITED TO:

 

  • Intelligent computing algorithms for next generation IoT assisted smart manufacturing

  • Role of machine learning based algorithm based algorithms in industrial production and management

  • Automation of industrial applications with machine learning and cloud assisted IoT systems

  • End-to-End machine learning algorithms for cloud based IoT applications in manufacturing

  • Advances in machine learning algorithms for industrial automation

  • Innovations in machine learning for cloud computing assisted smart industrial IoT systems

  • Emerging trends in machine learning and big data analytics for sustainable production

  • Intelligent big data analytics and machine learning approaches for smart manufacturing

  • Human-centered AI and machine learning approaches for sustainable production and manufacturing

  • Emerging advances in machine learning algorithms for next-generation digital manufacturing applications

  • Responsible and explainable artificial intelligence in industrial internet of things.

TENTATIVE DATES

  • Submission Deadline: 25th May 2022

  • Authors Notification: 05th July 2022

  • Revised Version Submission: 10th October 2022

  • Final Decision Notification: 12th December 2022

 

We are planning to promote the special issue among various research communities across the globe through the mail and other online sources.

GUEST EDITORS

Dr. Chi Lin

Senior member of IEEE, ACM, and CCF,

Associate Professor, Vice Advisor,

Institute of Intelligent System,

School of Software,

Dalian University of Technology,

Dalian, China.

Email: clindut@ieee.org

GS: https://scholar.google.com/citations?user=PVHo2-YAAAAJ

 

Dr. Chang Wu Yu

Professor,

Department of Computer Science and Information Engineering,

Chung Hua University,

Hsinchu, Taiwan.

Email: cwyu@chu.edu.tw

GS: https://scholar.google.com/citations?hl=zh-TW&user=M0nQiSwAAAAJ

 

Dr. Ning Wang

Assistant Professor,

Computer Science & Research,

Rowan University, Glassboro,

New Jersey, USA.

Email: wangn@rowan.edu

GS: https://scholar.google.com/citations?hl=zh-TW&user=OnrRV0AAAAAJ