Queensland University ENN541: Research Methods Article Critique

This report presents a critique of the research article "A Novel Design Framework for Smart Operating Robot in Power System" by Qiang Wang et al. (2018). The article, published in IEEE/CAA JOURNAL OF AUTOMATICA SINICA, explores the application of machine learning and artificial intelligence (AI) t...Read More

Running head: RESEARCH METHODS FOR ENGINEERS
RESEARCH METHODS FOR ENGINEERS
Name of Student
Institution Affiliation

RESEARCH METHODS FOR ENGINEERS 2
BIBLIOGRAPHY \l 1033 Qiang Wang, X. Y. (2018). A Novel Design Framework for Smart
Operating Robot in Power System. IEEE/CAA JOURNAL OF AUTOMATICA SINICA, 5,
532-537.
Introduction
This article was written by several authors including Qiang Wang, Xiaojing Yang, Zhigang Huang,
Shiqian Ma, Qiao Li, and David Wenzhong Gao. This article was published in March 2018 in Tianjin,
China and it was published through IEEE. The main purpose of this article is to illustrate how machine
learning can be employed in power system control. The paper suggests the use of machine training
where the SCADA system is employed to aid in controlling the whole system. The machine will help
in increasing the speed of operation, efficiency and reduces the errors of the human in the operation of
the power system. The process of training the machine involves a procedure of repairing a ticket,
translation, generation of operation tickets, checking the operation and do the simulation, operators
check the operation manually and then the desired tickets are produced.
Summary
(Qiang Wang, 2018). The operator will have to manually check the operation until he or she is
satisfied with the fed operation. The variable in this experiment was compiling the tickets while some
of the limitations of the experiment are that training of the machine takes a lot of time and training is
also tiresome.

RESEARCH METHODS FOR ENGINEERS 3
Assessment
This article is very reliable and the information it contains is more relevant, this can be witnessed from
the authors´ information. Most of the authors have PhD in electrical engineering like David Wenzhong
Gao this therefore affirms that the authors have enough information in electrical engineering making
most information relevant and highly reliable. Some of the authors like Zhigang Huang are from
Tianjin thus giving relevant information. The article was published on MARCH 2018 this makes the
article updated as the time of publication is a long time ago from the current year (2020). The structure
of the article is properly put, it is given in the IEEE format (double column). The paper commences
with an abstract which gives the audience an overview of what the paper is all about. The references
are properly put in the IEEE format to conform to the general structure of the paper. The content of the
article is highly valid as it talks about the training of machines to make the machine work properly and
give the desired output. The usage of SCADA in the paper is highly relevant since SCADA can be
employed in supervisory and controlling of a distributed system like the power system in this article
(Qiang Wang, 2018). The experiment in this article is very reliable as it majorly focuses on training a
machine, training of machine basically involves tweaking the weights until the desired outputs are
attained. The strength of the paper is that it talks about the training of the machine to attain the required
output it also talks about AI which is able to make a decision after training. The paper has a limitation
as it failed to give an elaborate experiment to illustrate how many tweaking is needed when using an
Artificial Neural Network to make the machine operate as required.
Conclusion
From the above critique, the article is well structured and presented, the contents of the article are
reliable and are full facts about SCADA and machine learning. Therefore the article meets my
judgment and it is perfect for anyone learning electrical engineering or anyone who wants to know

RESEARCH METHODS FOR ENGINEERS 4
more about SCADA, machine learning, training of machines and Artificial control of power system.
References
C. Q. Jiang, H. Zhou, and Q. J. Deng. (2011). “A new system of operation ticket for generation
and misoperation prevention in smart distribution network,” in Proc. 2011 Int. Conf. Electric
Information and Control Engineering, Wuhan, China,pp. 60−64.
D. Silver, A. Huang, C. J. Maddison, A. Guez, L. Sifre, G. Van Den Driessche, J. Schrittwieser,
I. Antonoglou, V. Panneershelvam, M. Lanctot, S. Dieleman, D. Grewe, J. Nham, N.
Kalchbrenner, I. Sutskever, T. Lillicrap, M. Leach, K. Kavukcuoglu, T. Graepel, and D.
Hassabis.( Jan. 2016). “Mastering the game of go with deep neural networks and tree search,”
Nature, vol. 529, no. 7587, pp. 484−489,
F. Rodrigues, C. Cardeira, and J. M. F. Calado. (Dec. 2014). “The daily and hourly energy
consumption and load forecasting using artificial neural network method: a case study using a set
of 93 households in Portugal,” Energy Proc., vol. 62, pp. 220−229,

RESEARCH METHODS FOR ENGINEERS 5
K. N. Chen, B. M. Zhang, W. C. Wu, and H. B. Sun. (2011). “An intelligent checking system for
power system operation tickets,” in Proc. 4th Int. Conf. Electric Utility Deregulation and
Restructuring and Power Technologies, Weihai, Shandong, China, , pp. 757−762.
K. T. Williams and J. D. Gomez. (Sep. 2016) “Predicting future monthly residential energy
consumption using building characteristics and climate data: A statistical learning approach,”
Energy Buildings, vol. 128, pp. 1−11,
Qiang Wang, X. Y. (March 2018). A Novel Design Framework for Smart Operating Robot in
Power System. IEEE/CAA JOURNAL OF AUTOMATICA SINICA, 5, 532-537.