Technometrics

ISSN: (Print) (Online) Journal homepage: www.tandfonline.com/journals/utch20

Data Analytics for Process Engineers; Prediction,

Eduwin Saputra, Taufik Hidayat, Fajri Khatami & Muh. Rizal B

To cite this article: Eduwin Saputra, Taufik Hidayat, Fajri Khatami & Muh. Rizal B (2024) Data
Analytics for Process Engineers; Prediction, Control, and Optimization, Technometrics, 66:2,
313-314, DOI: 10.1080/00401706.2024.2339788

To link to this article: https://doi.org/10.1080/00401706.2024.2339788

Published online: 01 May 2024.

Submit your article to this journal

Article views: 1084

View related articles

View Crossmark data

Full Terms & Conditions of access and use can be found at

bridge. Some additional sources are described in the references The EDA also involves assessing data quality, examining errors,
(Lipovetsky, 2021, 2022). outliers, and missing data points, along with summary statistical
calculations. This chapter is complex, addressing the identifica-
Stan Lipovetsky tion and management of unusual data points and missing values,
Minneapolis, MN employing techniques like correlograms, clustering, and data
stan.lipovetsky@gmail.com complexity reduction.
Entering the core of the book, Chapter 3 elucidates data-
based modeling using mathematical models. This differs from
first-principle-based models, which provide a fundamental
understanding of physical-chemical phenomena like fluid
References mechanics, heat transfer, and mass transfer. In data-based
modeling, quantitative data analysis methods identify and
Lipovetsky, S. (2021), “Advanced Engineering Mathematics,” Technometrics,
63, 566–570. [313] study a set of variables and their relationships. This chapter
(2022), “Mathematical Modeling: Models, Analysis and Applica- provides an overview of simple regression models, nonlinear
tions,” Technometrics, 64, 580–581. [313] regression models, nonlinear machine learning algorithms, and
distribution models. The book also outlines tools to evaluate and
Data Analytics for Process Engineers; Prediction, validate modeling performance and briefly explores research
Control, and Optimization, Daniela Galatro and Stephen methods distinguishing predictive mathematical modeling
Dawe, Cham: Springer, 2024, 145 pp., €32.09 (eBook), ISBN: from cause-and-effect modeling. Moving on to the direct
978-3-031-46866-7 application of modeling in industries for control functions,
Chapter 4 discusses control theory in industry from chemical
The industry-focused data analytics approach for process plants to using machine learning to enhance control and
engineering plays a vital role in minimizing errors, a clear and optimization.
concise approach explored in the book Data Analytics for Process Control functions rely on sensor or control system data, with
Engineers by Daniela Galatro and Stephen Dawe. This book machine learning used to address complex control issues and
delves into an industry-oriented data analytics approach for improve system performance. The comprehensive optimization
process engineers, specifically aimed at selecting and practically process is discussed in Chapter 5, emphasizing the vital role
applying data analytics approaches to analyze process engineer- of process optimization in transforming systems and manu-
ing problems. The book is effectively divided into six chapters, facturing processes to enhance efficiency and reduce produc-
each seamlessly continuing from the data sources to the latest tion costs. In machine learning, optimization aims to improve
data analysis techniques in process engineering at the end of the model accuracy by minimizing errors and strengthening pre-
book. It covers methods and data sources, exploratory analy- diction capabilities. As previously explained, data analysis and
sis, data-based modeling for prediction, modeling for monitor- machine learning are crucial in redefining process prediction,
ing and control, and process optimization. Designed for reader control, and eventually, optimization. This chapter introduces
comprehension, the book systematically employs mathematical various simple optimization algorithms for process engineers,
equations and, in some cases, real-world physical understanding such as grid search, random search, gradient search, and next-
of the analyzed phenomena, making it easily understandable. generation techniques, including evolutionary algorithms, par-
The book is specially designed to align with Education 4.0 and ticle swarm, Bayesian inference, and optimization. This chapter
Industry 4.0, becoming a new trend in the world of data analysis. also covers multi-objective optimization, a vital tool for engi-
It highlights crucial content regarding data visualization tech- neers in decision-making for solving design and monitoring
niques, prediction, modeling, and optimization for application problems. The final chapter summarizes crucial findings from
in process control. the preceding examples.
The initial chapter defines data acquisition as the process The authors provide insights and useful resources regarding
of sampling physical or electrical phenomena through a Data data analytics tools, including references to open datasets, dis-
Acquisition System (DAQ), which converts generated samples tinguishing concepts between data analysis and data analytics,
into digital numeric values. The DAQ includes sensors, measur- and defining machine learning. They emphasize the importance
ing devices, and computers. This chapter focuses on modeling of evaluating data analysis, modeling, control, and optimization
for predicting, controlling, and optimizing chemical processes, considering the physical aspects of phenomena within datasets.
using data sources such as factory process data analysis based This chapter is intriguing as it outlines the future of data analyt-
on Instrumentation and Control (I&C) data acquisition, pilot ics in process engineering, providing several examples of current
plant and laboratory data, and process simulation data. The research.
obtained data is termed measurable data, while artificially gen- In our review, this book can serve as a reference for
erated synthetic data from measured or observed data serves as researchers involved in the industry, especially in chemical
a critical data source, explored in cases where measured data is and mechanical engineering processes. It’s also highly suitable
insufficient or biased. The second chapter discusses data visual- for undergraduate and graduate students seeking relevant data
ization techniques, including Exploratory Data Analysis (EDA), analytics skills for their workplace. Furthermore, it can be a
used to evaluate datasets. This statistical modeling technique reference for professionals, offering quick guidance on data
aims to assess the overall structure of datasets, create descriptive analytics tools to support their process engineering tasks and
summaries, and serve as the foundation for model formation. the latest trends in data analysis for process engineers.
314 BOOK REVIEWS

Funding customization of the IDE settings, and the use of the IDE to
import a tabular data file. RStudio’s Integrated Development
The authors would like to express their gratitude to Indonesia Endowment
Fund for Education (LPDP) from the Ministry of Finance Republic Indone-
Environment (IDE) is a popular choice among R users for
sia for granting the scholarship and funding this paper. its comprehensive set of features designed to enhance the R
programming experience.
In Tidying Data with dplyr, loading the dplyr package, a
ORCID brief summary of the most common dplyr functions, and
Eduwin Saputra https://orcid.org/0009-0001-5485-8956 using the dplyr functions to normalize fields in a dataset are
Taufik Hidayat https://orcid.org/0009-0003-6376-3902 discussed. dplyr is an R package designed for data manipulation
Fajri Khatami https://orcid.org/0009-0007-8958-1073 tasks, providing a set of functions optimized for efficiently
Muh. Rizal B https://orcid.org/0009-0009-6397-1641 working with data frames and data tables. Developed by Hadley
Wickham and the RStudio team, dplyr offers a concise and
intuitive grammar for data manipulation, making it a popular
Eduwin Saputra
choice among R users for tasks such as filtering, selecting,
Department of Chemistry, Faculty of Mathematics and
summarizing, mutating data, and arranging data.
Natural Sciences, Universitas Gadjah Mada,
Visualizing YourProject with ggplot2 describes the various
Bulaksumur, Indonesia
geom functions in ggplot2 for making plots. This chapter
eduwinsaputra@mail.ugm.ac.id
also demonstrates how to load the ggplot2 package and other
Taufik Hidayat relevant libraries into RStudio using appropriate code. ggplot2
Department of Chemistry, Faculty of Mathematics and Natural is a powerful data visualization package in R, created by Hadley
Sciences, Universitas Gadjah Mada, Bulaksumur, Indonesia Wickham. It is based on the grammar of graphics, which
provides a consistent and flexible framework for constructing
Fajri Khatami plots. ggplot2 allows users to create complex plots with relatively
Department of Chemistry, Faculty of Mathematics and Natural simple code, making it popular among data analysts and
Sciences, Universitas Gadjah Mada, Bulaksumur, Indonesia scientists.
Webscraping with rvest explains how to determine which
Muh. Rizal B
HTML tags will provide the desired data. It also explains how
Department of Chemistry, Faculty of Mathematics and Natural
the rvest package can be used to scrape webpage content into the
Sciences, Universitas Gadjah Mada, Bulaksumur, Indonesia
RStudio IDE. rvest is an R package designed for web scraping.
It allows users to extract data from HTML web pages using
CSS selectors and XPath expressions. Web scraping involves
extracting data from websites, which can then be used for anal-
Reference ysis, visualization, or other purposes.
Daniela, G., and Stephen, D. (2024), Data Analytics for Process Mapping with tmap starts with defining the geographic con-
Engineers: Prediction, Control, and Optimazation, Cham: Springer. cepts (such as the geographic coordinate system, projected coor-
DOI:10.1007/978-3-031-46866-7. [318] dinate system, datum, and spheroid) that are relevant to cartog-
raphy. It also describes vector and raster data. Interestingly, tmap
may also be employed to achieve a data transformation of spatial
Hands-On Data Science for Librarians, Sarah Lin and data into an appropriate projection. tmap is an R package for
Dorris Scott, Boca Raton, FL: CRC Press, 2023, 200 pp., creating thematic maps, which are maps that represent spatial
$69.95, ISBN: 9781003218012 data by visualizing thematic variables. Thematic maps are useful
for showing distribution, patterns, and relationships of spatial
On the one hand, librarians are adept and comfortable with phenomena.
storing, using, and analyzing their collections or data; on the Textual Analysis with tidytext explains how the tidytext pack-
other hand, they are not known for their coding skills. This age can be used to load textual dataset into the IDE. It also shows
book aims to address this issue. It aims to equip librarians with how a sentiment analysis of a textual dataset can be done using
essential skills for interpreting visual data, including web scrap- it. Using the tf-idf functions to identify a text’s most common
ing, map analysis, interactive report generation, and machine words is also discussed. tidytext is an R package that provides
learning techniques. Despite the abundance of resources for tools for text mining and natural language processing (NLP)
learning R scattered across the internet, librarians from diverse tasks within the framework of the tidyverse. It facilitates the pro-
backgrounds may struggle to find a comprehensive guide specif- cess of tidying and analyzing text data by providing functions for
ically focused on mastering coding skills for excelling in library tokenization, stemming, sentiment analysis, and other common
sciences. text processing tasks.
By explaining the meaning of data science and its importance, Creating Dynamic Documents with rmarkdown introduces
as well as elucidating the possibilities and benefits of introducing the R Markdown package that allows the user to create various
coding in library sciences, the authors beautifully set the tone of documents including PDFs, MS Word documents, and HTML
the book in its first chapter, Introduction. files, as well as the creation of websites, presentations, and dash-
Thereafter, in Using RStudio’s IDE, they explain the instal- boards. rmarkdown is an R package that enables dynamic docu-
lation of RStudio, the functions of each pane in the IDE, ment generation within the R environment. It allows you to cre-