Data mining algorithms advancing deep machine learning

in engineering industrial control system programs



By Dr Lalamani Budeli

South Africa




The emergence of machine learning which enables a system to learn from data rather than through explicit programming allows industrial control systems to improve their complex control performance. Machine learning requires that the right set of data be applied to a learning process and big data can help improve the accuracy of machine-learning models possible to virtualize data so it can be stored most efficiently and cost-effectively. Electrical and computer engineers work at the forefront of technological innovation, contributing to the design, development, testing, and manufacturing processes for new generations of devices and equipment. As these professionals strive for innovation, their pursuits may overlap with the rapidly expanding applications for artificial intelligence.

Data mining is a computational technique or process of discovering patterns in large data sets and values involving machine learning, mathematical, statistics, and database system. We can compare both algorithms based on those data set records and find the best classification algorithms. Data mining solves the problem by analyzing a large amount of available data by providing useful patterns and rules using some classification methods.

Historically, most machinery and engineering components used in manufacturing and the operation of power plants, water and wastewater plants, transport industries, and other critical infrastructures were dumb, and those that were computerized typically used proprietary protocols. The networks they belonged to were air-gapped and protected from the outside world. This has changed over the years and components of today’s ICSs are often connected directly or indirectly to the internet.

Keywords: Data mining, machine learning, industrial control systems


Industrial control system (ICS) is a general term used to describe the integration of hardware and software with network connectivity to support critical infrastructure. ICS technologies include, but are not limited to, supervisory control and data acquisition (SCADA) and distributed control systems (DCS), industrial automation and control systems (IACS), programmable logic controllers (PLCs), programmable automation controllers (PACs), remote terminal units (RTUs), control servers, intelligent electronic devices (IEDs) and sensors.

Recent progress in areas like machine learning and natural language processing have affected almost every industry and area of scientific research, including engineering. Machine learning and electrical engineering professionals leverage AI to build and optimize systems and also provide AI technology with new data inputs for interpretation. Besides, harnessing artificial intelligence’s potential may reveal chances to boost system performance while addressing problems more efficiently: AI could be used to automatically flag errors or performance degradation so that engineers can fix problems sooner. Electrical and computer engineering leaders have opportunities to realign how their organizations manage daily operations and grow over time.

Research hypothesis

The following are the research hypothesis

  1. Data mining techniques can improve the machine learning algorithm of the industrial control system
  2. Data mining and machine learning projects success will improve industrial control systems intelligence, creating a competitive advantage for the firms avoiding machine damage.

Control theory in engineering

According to Dullerud and Paganini (2013-12), control theory is an interdisciplinary branch of engineering and mathematics that deals with the behavior of dynamical systems with inputs, and how their behavior is modified by feedback. Tin and Poon (2005-17) said that the typical objective of control theory is to control a system called the plant, so that its output follows a desired control signal, called the reference, which may be a fixed or changing value. The figure below indicates a closed-loop control system.


To read entire paper, click here

How to cite this paper: Budeli, L. (2020). Data mining algorithms advancing deep machine learning in engineering industrial control system programs, PM World Journal, Vol. IX, Issue XII, December. Available online at https://pmworldlibrary.net/wp-content/uploads/2020/12/pmwj100-Dec2020-Budeli-Data-mining-algorith-advancing-deep-machine-learning.pdf



About the Author

Dr Lalamani Budeli

South Africa


Dr Lalamani Budeli obtained his degree in Electrical Engineering at the Vaal University (VUT), BSc honors in Engineering Technology Management at University of Pretoria (UP), Master in engineering development and Management at North West University (NWU), Master of business administration at Regent Business School (RBS) and a Doctor of Philosophy in Engineering Development and Management at North West University (NWU), Potchefstroom, South Africa. Currently, he is a managing director of BLIT, an engineering, research, and project management company based in South Africa.

His research interests include project portfolio management, agile project management, plant life cycle management, advanced systems analytics, project early warning system, and the use of artificial intelligence in project management. Currently, he is spending most of the time on research that is looking at the development of system and application that uses the latest technology like block chain, internet of things (IoT), Big data, and artificial intelligence. Lalamani Budeli can be contacted at budelil@blit.co.za.