Submit to Processes Review for Processes Propose a Special Issue

Journal Browser

Fault Detection and Process Diagnostics by Using Big Data Analytics in Industrial Applications

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of Processes (ISSN 2227-9717). This special issue belongs to the section "Process Control and Monitoring".

Deadline for manuscript submissions: closed (20 February 2021) | Viewed by 70522

Share This Special Issue

Special Issue Editors

Prof. Dr. Shu-Kai S. Fan

E-Mail Website
Guest Editor

Department of Industrial Engineering and Management, National Taipei University of Technology, Taipei 10608, Taiwan
Interests: advanced process control; engineering optimization; quality engineering; big data analytics; intelligent computing

Dr. Chia-Yu Hsu

E-Mail Website
Guest Editor

Department of Industrial Engineering and Management, National Taipei University of Technology, Taipei 10608, Taiwan
Interests: big data analytics; machine learning and deep learning; manufacturing intelligence; fault detection; time series data analysis

Dr. You-Jin Park

E-Mail Website
Guest Editor

Department of Industrial Engineering and Management, National Taipei University of Technology, Taipei 10608, Taiwan
Interests: big data analytics; data mining; scheduling; quality engineering

Special Issue Information

Dear Colleagues,

Fault detection and process diagnostics poses an important challenge in industrial processes. It is the central component of abnormal event management, which has attracted abundant attention in recent literature. Abnormal event management deals with the timely detection, diagnosis, and correction of abnormal conditions of faults in a process. Early detection and diagnosis of process faults while the engineering process is still operating in a controllable status can help to circumvent abnormal event progression and reduce yield loss.

Process diagnostics takes a deep dive into process phenomena through onsite measurement, key parameter and key processing time step identification, data crunching and analysis, understanding the relationships between operating conditions, materials and production quality for improved efficiency, solving process challenges, and for novel design/redesign.

This Special Issue on “Fault Detection and Process Diagnostics by Using Big Data Analytics in Industrial Applications” aims to curate novel advances in the development and application of big data analytics to address long-standing challenges in fault detection and process diagnostics in state-of-the-art industrial processes. Related topics include but are not limited to:

Machine learning techniques for fault detection and process diagnostics;
Deep learning techniques for fault detection and process diagnostics;
Fault detection and process diagnostics using image processing techniques;
Advanced process monitoring and control schemes developed within the framework of big data analytics;
Strategy palnning and deployment of fault detection and process diagnostics;
Intelligent alarm system and fault analysis;
Fault detection and process diagnostics using dimension reduction and data visualization.

Papers submitted to this Special Issue are expected to provide an original contribution, proposing new solutions/frameworks, improvements to existing solutions, and new applications in emerging sectors. The paper can address the potential solution of specific problems in the sector of interest using algorithms, predictive analytics and prognostics, experimental tests, and numerical analysis within the context of big data analytics.

Prof. Dr. Shu-Kai S. Fan
Dr. Chia-Yu Hsu
Dr. You-Jin Park
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Processes is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

fault detection and classification (FDC)
process diagnostics
fault analysis
big data analytics
data mining
machine learning
deep learning

Published Papers (13 papers)

Download All Papers

Research

Jump to: Review

18 pages, 5007 KiB

Open AccessArticle

Research on On-Line Monitoring System of Hydraulic Actuator of Combine Harvester

by Ruichuan Li, Yi Cheng, Jikang Xu, Yanchao Li, Xinkai Ding and Shan Zhao

Processes 2022, 10(1), 35; https://doi.org/10.3390/pr10010035 - 24 Dec 2021

Cited by 6 | Viewed by 2996

Abstract

In view of the complicated hydraulic system, the many driving parts and the great load variation in the combine harvester, and on-line monitoring methods of hydraulic actuating parts such as cutting tables, conveyors and threshing drums were studied. By analyzing the working principle of the hydraulic system of the combine harvester, a mathematical model of the hydraulic system of the combine harvester was established; a simulation model for the fault diagnosis of the hydraulic system of the combine harvester was established based on AMESim. The load signal was introduced to simulate the feeding amount, and the simulation test was carried out. According to the simulation analysis results, the best position of each monitoring point was determined. The on-line monitoring system of the hydraulic actuators of the combine harvester was designed by using LabView, which can collect and display the working parameters of the main working parts of a combine harvester in real time, and alarm the user to faulty working conditions. The field experiment results show that the function and precision of the monitoring system completely meet the requirements of field operation condition monitoring of combine harvesters. The accuracy rate of the fault alarm is 96.5%, and the automatic diagnosis time of the fault alarm is less than 1 min and 18 s, which greatly improves the operation efficiency of the combine harvester. Full article

(This article belongs to the Special Issue Fault Detection and Process Diagnostics by Using Big Data Analytics in Industrial Applications)

► Show Figures

Figure 1

23 pages, 4132 KiB

Open AccessArticle

A Novel Mutual Information and Partial Least Squares Approach for Quality-Related and Quality-Unrelated Fault Detection

by Majed Aljunaid, Yang Tao and Hongbo Shi

Processes 2021, 9(1), 166; https://doi.org/10.3390/pr9010166 - 18 Jan 2021

Cited by 10 | Viewed by 2462

Abstract

Partial least squares (PLS) and linear regression methods are widely utilized for quality-related fault detection in industrial processes. Standard PLS decomposes the process variables into principal and residual parts. However, as the principal part still contains many components unrelated to quality, if these components were not removed it could cause many false alarms. Besides, although these components do not affect product quality, they have a great impact on process safety and information about other faults. Removing and discarding these components will lead to a reduction in the detection rate of faults, unrelated to quality. To overcome the drawbacks of Standard PLS, a novel method, MI-PLS (mutual information PLS), is proposed in this paper. The proposed MI-PLS algorithm utilizes mutual information to divide the process variables into selected and residual components, and then uses singular value decomposition (SVD) to further decompose the selected part into quality-related and quality-unrelated components, subsequently constructing quality-related monitoring statistics. To ensure that there is no information loss and that the proposed MI-PLS can be used in quality-related and quality-unrelated fault detection, a principal component analysis (PCA) model is performed on the residual component to obtain its score matrix, which is combined with the quality-unrelated part to obtain the total quality-unrelated monitoring statistics. Finally, the proposed method is applied on a numerical example and Tennessee Eastman process. The proposed MI-PLS has a lower computational load and more robust performance compared with T-PLS and PCR. Full article

(This article belongs to the Special Issue Fault Detection and Process Diagnostics by Using Big Data Analytics in Industrial Applications)

► Show Figures

Figure 1

18 pages, 5378 KiB

Open AccessFeature PaperArticle

An Autoencoder Gated Recurrent Unit for Remaining Useful Life Prediction

by Yi-Wei Lu, Chia-Yu Hsu and Kuang-Chieh Huang

Processes 2020, 8(9), 1155; https://doi.org/10.3390/pr8091155 - 15 Sep 2020

Cited by 35 | Viewed by 4851

Abstract

With the development of smart manufacturing, in order to detect abnormal conditions of the equipment, a large number of sensors have been used to record the variables associated with production equipment. This study focuses on the prediction of Remaining Useful Life (RUL). RUL prediction is part of predictive maintenance, which uses the development trend of the machine to predict when the machine will malfunction. High accuracy of RUL prediction not only reduces the consumption of manpower and materials, but also reduces the need for future maintenance. This study focuses on detecting faults as early as possible, before the machine needs to be replaced or repaired, to ensure the reliability of the system. It is difficult to extract meaningful features from sensor data directly. This study proposes a model based on an Autoencoder Gated Recurrent Unit (AE-GRU), in which the Autoencoder (AE) extracts the important features from the raw data and the Gated Recurrent Unit (GRU) selects the information from the sequences to forecast RUL. To evaluate the performance of the proposed AE-GRU model, an aircraft turbofan engine degradation simulation dataset provided by NASA was used and a comparison made of different recurrent neural networks. The results demonstrate that the AE-GRU is better than other recurrent neural networks, such as Long Short-Term Memory (LSTM) and GRU. Full article

(This article belongs to the Special Issue Fault Detection and Process Diagnostics by Using Big Data Analytics in Industrial Applications)

► Show Figures

Figure 1

19 pages, 2641 KiB

Open AccessArticle

Temporal-Spatial Neighborhood Enhanced Sparse Autoencoder for Nonlinear Dynamic Process Monitoring

by Nanxi Li, Hongbo Shi, Bing Song and Yang Tao

Processes 2020, 8(9), 1079; https://doi.org/10.3390/pr8091079 - 1 Sep 2020

Cited by 18 | Viewed by 2258

Abstract

Data-based process monitoring methods have received tremendous attention in recent years, and modern industrial process data often exhibit dynamic and nonlinear characteristics. Traditional autoencoders, such as stacked denoising autoencoders (SDAEs), have excellent nonlinear feature extraction capabilities, but they ignore the dynamic correlation between sample data. Feature extraction based on manifold learning using spatial or temporal neighbors has been widely used in dynamic process monitoring in recent years, but most of them use linear features and do not take into account the complex nonlinearities of industrial processes. Therefore, a fault detection scheme based on temporal-spatial neighborhood enhanced sparse autoencoder is proposed in this paper. Firstly, it selects the temporal neighborhood and spatial neighborhood of the sample at the current time within the time window with a certain length, the spatial similarity and time serial correlation are used for weighted reconstruction, and the reconstruction combines the current sample as the input of the sparse stack autoencoder (SSAE) to extract the correlation features between the current sample and the neighborhood information. Two statistics are constructed for fault detection. Considering that both types of neighborhood information contain spatial-temporal structural features, Bayesian fusion strategy is used to integrate the two parts of the detection results. Finally, the superiority of the method in this paper is illustrated by a numerical example and the Tennessee Eastman process. Full article

(This article belongs to the Special Issue Fault Detection and Process Diagnostics by Using Big Data Analytics in Industrial Applications)

► Show Figures

Figure 1

16 pages, 1149 KiB

Open AccessArticle

Integrated Control Policy for a Multiple Machines and Multiple Product Types Manufacturing System Production Process with Uncertain Fault

by Jia You, Ming Li, Kai Guo and Hao Li

Processes 2020, 8(8), 952; https://doi.org/10.3390/pr8080952 - 7 Aug 2020

Viewed by 2461

Abstract

The optimization of production cost has always been a key issue in manufacturing systems; for the single product type manufacturing systems, lots of research studies have proved the validity of the hedging point control policy in production cost control. However, due to the complexity of the multiple machines and multiple product types manufacturing systems with uncertain fault, it is difficult to achieve a good control effect only by using the hedging point control policy. To optimize the total production cost under constantly changing demands, an integrated control policy that combines the prioritized hedging point (PHP) control policy with the production capacity planning during production is proposed, and the decision variables are obtained by a particle swarm optimization (PSO) algorithm. The simulation experiments show the effectiveness of the proposed integrated control policy in production cost control for the multiple machines and multiple product types manufacturing system. Full article

(This article belongs to the Special Issue Fault Detection and Process Diagnostics by Using Big Data Analytics in Industrial Applications)

► Show Figures

Figure 1

22 pages, 3944 KiB

Open AccessArticle

Product Quality Detection through Manufacturing Process Based on Sequential Patterns Considering Deep Semantic Learning and Process Rules

by Liguo Yao, Haisong Huang and Shih-Huan Chen

Processes 2020, 8(7), 751; https://doi.org/10.3390/pr8070751 - 28 Jun 2020

Cited by 6 | Viewed by 4852

Abstract

Companies accumulate a large amount of production process data during product manufacturing. Sequence data from the mining production process can enable a company to evaluate the manufacturing process, to find the key factors affecting product quality, and to improve product quality. However, the production process mainly exists in the form of text. To solve this problem, we propose a novel frequent pattern mining algorithm (EABMC) based on the text context semantics and rules of the manufacturing process to remove redundant sequences and to obtain good mining results. In this algorithm, first, we use embeddings from language models (ELMo ) to improve the process of text similarity matching and to classify similar semantic processes into one class. Then, the manufacturing process unit (MPU) is proposed by extracting the characteristics of manufacturing process data according to the constraints of the manufacturing process and other conditions. The above two steps cause the complex manufacturing process sequence to merge and simplify. Once again, a frequent pattern mining algorithm (CloFAST) is used to explore the important manufacturing process relationships behind a large amount of manufacturing data. In addition, taking the data from a production enterprise in Guizhou Province as an example, the validity of the method is verified. Compared with other methods, this method is shown to have greater mining efficiency and better results and can find out the key factors that affect product quality, especially for text data. Full article

(This article belongs to the Special Issue Fault Detection and Process Diagnostics by Using Big Data Analytics in Industrial Applications)

► Show Figures

Figure 1

14 pages, 1861 KiB

Open AccessArticle

Semi-Supervised Ensemble Classification Method Based on Near Neighbor and Its Application

by Chuang Li, Yongfang Xie and Xiaofang Chen

Processes 2020, 8(4), 415; https://doi.org/10.3390/pr8040415 - 1 Apr 2020

Cited by 4 | Viewed by 2810

Abstract

Semi-supervised learning can be used to solve the problem of insufficient labeled samples in the process industry. However, in an actual scenario, traditional semi-supervised learning methods usually do not achieve satisfactory performance when the small number of labeled samples is subjective and inaccurate and some do not consider how to develop a strategy to expand the training set. In this paper, a new algorithm is proposed to alleviate the above two problems, and consequently, the information contained in unlabeled samples can be fully mined. First, the multivariate adaptive regression splines (MARS) and adaptive boosting (Adaboost) algorithms are adopted for co-training to make the most of the deep connection between samples and features. In addition, the strategies, pseudo-labeled dataset selection algorithm based on near neighbor degree (DSSA) and pseudo-labeled sample detection algorithm based on near neighbor degree selection (SPDA) are adopted to enlarge the dataset of labeled samples. When we select the samples from the pseudo-labeled data to join the training set, the confidence degree and the spatial relationship with labeled samples are considered, which are able to improve classifier accuracy. The results of tests on multiple University of California Irvine (UCI) datasets and an actual dataset in the aluminum electrolysis industry demonstrate the effectiveness of the proposed algorithm. Full article

(This article belongs to the Special Issue Fault Detection and Process Diagnostics by Using Big Data Analytics in Industrial Applications)

► Show Figures

Figure 1

18 pages, 5905 KiB

Open AccessFeature PaperArticle

Improvement of Productivity through the Reduction of Unexpected Equipment Faults in Die Attach Equipment

by You-Jin Park and Sun Hur

Processes 2020, 8(4), 394; https://doi.org/10.3390/pr8040394 - 27 Mar 2020

Cited by 3 | Viewed by 5142

Abstract

As one of the semiconductor back-end processes, die attach process is the process that attaches an individual non-defective die (or chip) produced from the semiconductor front-end production to the lead frame on a strip. With most other processes of semiconductor manufacturing, it is very important to improve productivity by lessening the occurrence of defective products generally represented as losses, and then find the fault causes which lower productivity of the die attach process. Thus, as the case study to analyze quantitatively the faults of the die attach process equipment, in this research, we developed analysis systems including statistical analysis functions to improve the productivity of die attach process. This research shows that the developed system can find the causes of equipment faults in die attach process equipment and help improve the productivity of the die attach process by controlling the critical parameters which cause unexpected equipment faults and losses. Full article

(This article belongs to the Special Issue Fault Detection and Process Diagnostics by Using Big Data Analytics in Industrial Applications)

► Show Figures

Figure 1

12 pages, 2368 KiB

Open AccessArticle

A Graphical Model to Diagnose Product Defects with Partially Shuffled Equipment Data

by Gilseung Ahn, Sun Hur, Dongmin Shin and You-Jin Park

Processes 2019, 7(12), 934; https://doi.org/10.3390/pr7120934 - 8 Dec 2019

Cited by 1 | Viewed by 3071

Abstract

The diagnosis of product defects is an important task in manufacturing, and machine learning-based approaches have attracted interest from both the industry and academia. A high-quality dataset is necessary to develop a machine learning model, but the manufacturing industry faces several data-collection issues including partially shuffled data, which arises when a product ID is not perfectly inferred and yields an unstable machine learning model. This paper introduces latent variables to formulate a supervised learning model that addresses the problem of partially shuffled data. The experimental results show that our graphical model deals with the shuffling of product order and can detect a defective product far more effectively than a model that ignores shuffling. Full article

(This article belongs to the Special Issue Fault Detection and Process Diagnostics by Using Big Data Analytics in Industrial Applications)

► Show Figures

Figure 1

15 pages, 6146 KiB

Open AccessArticle

Study on a Fault Identification Method of the Hydraulic Pump Based on a Combination of Voiceprint Characteristics and Extreme Learning Machine

by Wanlu Jiang, Zhenbao Li, Jingjing Li, Yong Zhu and Peiyao Zhang

Processes 2019, 7(12), 894; https://doi.org/10.3390/pr7120894 - 1 Dec 2019

Cited by 25 | Viewed by 3018

Abstract

Aiming at addressing the problem that the faults in axial piston pumps are complex and difficult to effectively diagnose, an axial piston pump fault diagnosis method that is based on the combination of Mel-frequency cepstrum coefficients (MFCC) and the extreme learning machine (ELM) is proposed. Firstly, a sound sensor is used to realize contactless sound signal acquisition of the axial piston pump. The wavelet packet default threshold denoises the original acquired sound signals. Afterwards, windowing and framing are added to the de-noised sound signals. The MFCC voiceprint characteristics of the processed sound signals are extracted. The voiceprint characteristics are divided into a training sample set and test sample set. ELM models with different numbers of neurons in the hidden layers are established for training and testing. The relationship between the number of neurons in the hidden layer and the recognition accuracy rate is obtained. The ELM model with the optimal number of hidden layer neurons is established and trained with the training sample set. The trained ELM model is applied to the test sample set for fault diagnosis. The fault diagnosis results are obtained. The fault diagnosis results of the ELM model are compared with those of the back propagation (BP) neural network and the support vector machine. The results show that the fault diagnosis method that is proposed in this paper has a higher recognition accuracy rate, shorter training and diagnosis times, and better application prospect. Full article

(This article belongs to the Special Issue Fault Detection and Process Diagnostics by Using Big Data Analytics in Industrial Applications)

► Show Figures

Figure 1

13 pages, 1420 KiB

Open AccessArticle

Fault Classification Decision Fusion System Based on Combination Weights and an Improved Voting Method

by Fanliang Zeng, Zuxin Li, Zhe Zhou and Shuxin Du

Processes 2019, 7(11), 783; https://doi.org/10.3390/pr7110783 - 1 Nov 2019

Cited by 6 | Viewed by 2136

Abstract

It is difficult to correctly classify all faults by using only one classifier, and the performance of most classifiers varies under different conditions. In view of this, a new decision fusion system is proposed to solve the problem of fault classification. The proposed decision fusion system is innovative in two aspects: the use of combined weights and a new improved voting method. The combined weights integrate the subjective and objective weights, where the analytic hierarchy process and entropy weight-technique for order performance by similarity to ideal solution are used to determine the subjective and objective weights of different base classifiers under multiple performance evaluation indicators. Moreover, a new improved voting method based on the concept of classifier validity is proposed to increase the accuracy of the decision system. Finally, the method is validated by the Tennessee Eastman benchmark process, and the classification accuracy of the new method is shown to be improved by more than 5.06% compared to the best base classifier. Full article

(This article belongs to the Special Issue Fault Detection and Process Diagnostics by Using Big Data Analytics in Industrial Applications)

► Show Figures

Graphical abstract

Review

Jump to: Research

26 pages, 605 KiB

Open AccessFeature PaperReview

A Review on Fault Detection and Process Diagnostics in Industrial Processes

by You-Jin Park, Shu-Kai S. Fan and Chia-Yu Hsu

Processes 2020, 8(9), 1123; https://doi.org/10.3390/pr8091123 - 9 Sep 2020

Cited by 128 | Viewed by 16992

Abstract

The main roles of fault detection and diagnosis (FDD) for industrial processes are to make an effective indicator which can identify faulty status of a process and then to take a proper action against a future failure or unfavorable accidents. In order to enhance many process performances (e.g., quality and throughput), FDD has attracted great attention from various industrial sectors. Many traditional FDD techniques have been developed for checking the existence of a trend or pattern in the process or whether a certain process variable behaves normally or not. However, they might fail to produce several hidden characteristics of the process or fail to discover the faults in processes due to underlying process dynamics. In this paper, we present current research and developments of FDD approaches for process monitoring as well as a broad literature review of many useful FDD approaches. Full article

(This article belongs to the Special Issue Fault Detection and Process Diagnostics by Using Big Data Analytics in Industrial Applications)

► Show Figures

Figure 1

47 pages, 2439 KiB

Open AccessReview

A Review of Kernel Methods for Feature Extraction in Nonlinear Process Monitoring

by Karl Ezra Pilario, Mahmood Shafiee, Yi Cao, Liyun Lao and Shuang-Hua Yang

Processes 2020, 8(1), 24; https://doi.org/10.3390/pr8010024 - 23 Dec 2019

Cited by 76 | Viewed by 15712

Abstract

Kernel methods are a class of learning machines for the fast recognition of nonlinear patterns in any data set. In this paper, the applications of kernel methods for feature extraction in industrial process monitoring are systematically reviewed. First, we describe the reasons for using kernel methods and contextualize them among other machine learning tools. Second, by reviewing a total of 230 papers, this work has identified 12 major issues surrounding the use of kernel methods for nonlinear feature extraction. Each issue was discussed as to why they are important and how they were addressed through the years by many researchers. We also present a breakdown of the commonly used kernel functions, parameter selection routes, and case studies. Lastly, this review provides an outlook into the future of kernel-based process monitoring, which can hopefully instigate more advanced yet practical solutions in the process industries. Full article

(This article belongs to the Special Issue Fault Detection and Process Diagnostics by Using Big Data Analytics in Industrial Applications)

► Show Figures