Data Mining and Analytics in the Process Industry: The Role of Machine Learning

By Zhiqiang Ge, Zhihuan Song, Steven X. Ding, Biao Huang. IEEE Access, 2017

762 citations recorded by the source corpus.

Data mining and analytics have played an important role in knowledge discovery and decision making/supports in the process industry over the past several decades. As a computational engine to data mining and analytics, machine learning serves as basic tools for information extraction, data pattern recognition and predictions. From the perspective of machine learning, this paper provides a review on existing data mining and analytics applications in the process industry over the past several decades. The state-of-the-art of data mining and analytics are reviewed through eight unsupervised learning and ten supervised learning algorithms, as well as the application status of semi-supervised learning algorithms. Several perspectives are highlighted and discussed for future researches on data mining and analytics in the process industry.

Subfields: Control and Systems Engineering, Mechanical Engineering, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/1ce15f4a83706b877e86f29549920651a888b144

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Control and Systems Engineering

1. Haitao Zhao
2. Angelos Angelopoulos
3. Bo Jin
4. T. Zahariadis
5. Panagiotis Trakadas
6. Pubudu N. Pathirana
7. Nikolaos Nomikos
8. Shaoyuan Sun

In Mechanical Engineering

1. Haitao Zhao
2. Bo Jin
3. Shaoyuan Sun

In Statistics and Probability

1. Haitao Zhao
2. Bo Jin
3. Ming Ding
4. Dinh C. Nguyen
5. Shaoyuan Sun

Citations in the corpus

• Federated Learning for Internet of Things: A Comprehensive Survey (2021, background): “industrial machines for process modeling, monitoring, prediction and control in production stages [160].”
• Tackling Faults in the Industry 4.0 Era—A Survey of Machine-Learning Solutions and Key Aspects (2019, methodology): “• Unsupervised learning where there is no feedback provided from anyone and the algorithm finds patterns in unknown data sets (clustering, association rules, self-organised maps) [15,19,21] and so, unlabeled data are used for training purposes.”
• Sequential Fault Diagnosis Based on LSTM Neural Network (2018, methodology): “Due to the data-based nature of SPM, it is relatively convenient to apply to real processes of large scale comparing to other methods based on theoretical modelling or rigorous derivation of process systems [5]–[9].”