U.S. flag

An official website of the United States government

Dot gov

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Https

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

PubAg

Main content area

You searched for: Journal Industrial & engineering chemistry process design and development Remove constraint Journal: Industrial & engineering chemistry process design and development Subject process monitoring Remove constraint Subject: process monitoring Text Availability Citation in PubAg Remove constraint Text Availability: Citation in PubAg
Start Over

Search

71  Search Results

« Previous | 1 - 50 of 71 |
Number of results to display per page

Search Results

1. Accelerated Kernel Canonical Correlation Analysis with Fault Relevance for Nonlinear Process Fault Isolation

Author:
Jiaxin Yu; Kai Wang; Lingjian Ye; Zhihuan Song
Source:
Industrial & engineering chemistry process design and development 2019 v.58 no.39 pp. 18280-18291
ISSN:
1520-5045
Subject:
isolation techniques; multivariate analysis; nonlinear models; process design; process monitoring; product quality
Abstract:
... In the field of multivariate statistical process monitoring (MSPM), fault isolation has attracted increasing attention, due to its importance in ensuring process reliability and product quality. However, the existing fault isolation methods are mostly limited to linear settings with single variable isolation. For nonlinear modeling, the kernel method is commonly used, but the time for solving a ke ...
DOI:
10.1021/acs.iecr.9b03069

2. Adaptive Model Predictive Batch Process Monitoring and Control

Author:
Masoud Kheradmandi; Prashant Mhaskar
Source:
Industrial & engineering chemistry process design and development 2018 v.57 no.43 pp. 14628-14636
ISSN:
1520-5045
Subject:
arc furnaces; batch systems; model validation; models; prediction; process design; process monitoring
Abstract:
... The present work addresses the problem of loss of model validity in batch process control via online monitoring and adaptation based model predictive control. To this end, a state space subspace-based model identification method suitable for batch processes is utilized and then a model predictive controller is designed. To monitor model performance, a model validity index is developed for batch pr ...
DOI:
10.1021/acs.iecr.8b02738

3. Adaptive Selection of Latent Variables for Process Monitoring

Author:
Lijia Luo; Shiyi Bao; Jianfeng Mao
Source:
Industrial & engineering chemistry process design and development 2019 v.58 no.21 pp. 9075-9086
ISSN:
1520-5045
Subject:
case studies; chemistry; process monitoring
Abstract:
... Latent-variable (LV) methods have been widely applied to multivariate statistical process monitoring. Using LV methods can simplify the process-monitoring problem through a projection of the high-dimensional process data into a low-dimensional LV space that retains most of the important information for fault detection. A key issue is the optimal selection of a subset of LVs to constitute such a lo ...
DOI:
10.1021/acs.iecr.8b05847

4. Adaptive Selective Ensemble-Independent Component Analysis Models for Process Monitoring

Author:
Zhichao Li; Xuefeng Yan
Source:
Industrial & engineering chemistry process design and development 2018 v.57 no.24 pp. 8240-8252
ISSN:
1520-5045
Subject:
Bayesian theory; algorithms; independent component analysis; models; process design; process monitoring; wastewater treatment
Abstract:
... Independent component analysis (ICA) has been widely used in non-Gaussian industrial process monitoring. However, the stability of performance and determination of dominant ICs are still the main problems for ICA. Constructing a monitoring model to achieve the best performance for different faults is a great challenge owing to the diversity and unknowability of faults. This study develops an adapt ...
DOI:
10.1021/acs.iecr.8b00591

5. Adaptive k-Nearest-Neighbor Method for Process Monitoring

Author:
Wenbo Zhu; Wei Sun; José Romagnoli
Source:
Industrial & engineering chemistry process design and development 2018 v.57 no.7 pp. 2574-2586
ISSN:
1520-5045
Subject:
process design; process monitoring; prototypes; pyrolysis
Abstract:
... In this paper, an adaptive process monitoring method based on the k-nearest neighbor rule (k-NN) is proposed to address the issues arising from nonlinearity, insufficient training data, and time-varying behaviors. Instead of recursively updating every measurement for adaptation, a distance-based updating rule is applied to search target prototypes, thus reducing the computational load for online i ...
DOI:
10.1021/acs.iecr.7b03771

6. Automated Model Selection in Principal Component Analysis: A New Approach Based on the Cross-Validated Ignorance Score

Author:
Stefania Russo; Guangyu Li; Kris Villez
Source:
Industrial & engineering chemistry process design and development 2019 v.58 no.30 pp. 13448-13468
ISSN:
1520-5045
Subject:
artificial intelligence; automation; data collection; models; prediction; principal component analysis; process design; process monitoring
Abstract:
... Principal component analysis (PCA) is by far the most widespread tool for unsupervised learning with high-dimensional data sets. It is popularly studied for exploratory data analysis and online process monitoring. Unfortunately, fine-tuning PCA models and particularly the number of components remains a challenging task. Today, this selection is often based on a combination of guiding principles, e ...
DOI:
10.1021/acs.iecr.9b00642

7. A Bibliometric Review and Analysis of Data-Driven Fault Detection and Diagnosis Methods for Process Systems

Author:
Md Alauddin; Faisal Khan; Syed Imtiaz; Salim Ahmed
Source:
Industrial & engineering chemistry process design and development 2018 v.57 no.32 pp. 10719-10735
ISSN:
1520-5045
Subject:
accident prevention; algorithms; data analysis; developing countries; independent component analysis; industry; least squares; models; principal component analysis; process design; process monitoring; China; Singapore
Abstract:
... Accident prevention is one of the most desired and challenging goals in process industries. For accident prevention, fault detection and diagnosis (FDD) is critical. FDD has been an active area of research for decades. The focus of the current review is on the data-driven techniques as we are now in a digital era and data analytics is getting more emphasis in all areas including process industries ...
DOI:
10.1021/acs.iecr.8b00936

8. Concurrent Monitoring Strategy for Static and Dynamic Deviations Based on Selective Ensemble Learning Using Slow Feature Analysis

Author:
Huifen Hong; Chao Jiang; Xin Peng; Weimin Zhong
Source:
Industrial & engineering chemistry process design and development 2020 v.59 no.10 pp. 4620-4635
ISSN:
1520-5045
Subject:
Bayesian theory; algorithms; case studies; models; principal component analysis; process monitoring
Abstract:
... Slow feature analysis (SFA) has been extensively adopted for process monitoring. Since the prominent ability of exploring dynamic information of the industrial process, SFA could monitor the process static and dynamic deviations concurrently. However, for complex and large-scale processes, it is difficult for a single SFA model to monitor the whole process well because of the complex relationship ...
DOI:
10.1021/acs.iecr.9b05547

9. Data-Driven Dynamic Modeling and Online Monitoring for Multiphase and Multimode Batch Processes with Uneven Batch Durations

Author:
Kai Wang; Lee Rippon; Junghui Chen; Zhihuan Song; R. Bhushan Gopaluni
Source:
Industrial & engineering chemistry process design and development 2019 v.58 no.30 pp. 13628-13641
ISSN:
1520-5045
Subject:
algorithms; batch systems; data collection; dynamic models; fermentation; penicillins; process design; process monitoring
Abstract:
... Batch processes are often characterized by piecewise linear dynamics due to varying operating conditions. Multiphase and multimode modeling of batch processes is a common technique that offers insight into the process operation and improved online monitoring. However, existing monitoring methods have several drawbacks such as neglecting process dynamics, requiring separate treatment of transient b ...
DOI:
10.1021/acs.iecr.9b00290

10. A Debottlenecking Study of an Industrial Pharmaceutical Batch Plant

Author:
Franz D. Bähner; Jakob K. Huusom
Source:
Industrial & engineering chemistry process design and development 2019 v.58 no.43 pp. 20003-20013
ISSN:
1520-5045
Subject:
algorithms; business enterprises; case studies; equipment; information processing; models; process design; process monitoring; systems engineering
Abstract:
... Operational complexity in batch-operated plants is large, and companies struggle to produce at high equipment utilization. Owing to high fixed costs, capacity utilization is an important operational directive. Many current plants are not in a state that allows the application of rigorous process systems engineering tools due to modeling challenges. This work proposes identifying the right engineer ...
DOI:
10.1021/acs.iecr.9b03134

11. Decentralized Modified Autoregressive Models for Fault Detection in Dynamic Processes

Author:
Chudong Tong; Ting Lan; Haizhen Yu; Xuhua Shi
Source:
Industrial & engineering chemistry process design and development 2018 v.57 no.46 pp. 15794-15802
ISSN:
1520-5045
Subject:
autocorrelation; models; process design; process monitoring
Abstract:
... Generally, the variations inherited in every single variable measured in dynamic processes consist of autocorrelated, cross-correlated, and unique variations. The filtering of both autocorrelation and cross-correlation from the given data should therefore be given full consideration in modeling dynamic process data as well as implementing fault detection in dynamic processes. Recognition of this i ...
DOI:
10.1021/acs.iecr.8b03463

12. Distributed Statistical Process Monitoring Based on Multiblock Canonical Correlation Analysis

Author:
Xinchun Wan; Chudong Tong; Lijia Luo
Source:
Industrial & engineering chemistry process design and development 2019 v.59 no.3 pp. 1193-1201
ISSN:
1520-5045
Subject:
algorithms; models; process monitoring; regression analysis
Abstract:
... A novel multiblock canonical correlation analysis (MBCCA) algorithm is proposed for multiblock modeling and distributed process monitoring purposes. The MBCCA algorithm is formulated to seek for different projecting bases in accordance with different multiple blocks so that the squared sum of canonical correlation coefficients between the latent variables from different blocks could be maximized. ...
DOI:
10.1021/acs.iecr.9b04971

13. Efficient Process Monitoring via the Integrated Use of Markov Random Fields Learning and the Graphical Lasso

Author:
Changsoo Kim; Hodong Lee; Kyeongsu Kim; Younggeun Lee; Won Bo Lee
Source:
Industrial & engineering chemistry process design and development 2018 v.57 no.39 pp. 13144-13155
ISSN:
1520-5045
Subject:
Bayesian theory; algorithms; probabilistic models; process design; process monitoring; variance covariance matrix
Abstract:
... Process monitoring is an important aspect of safe operation of process plants. Various methods exist that monitor the process using data-driven methods, but they all have certain limitations. For instance, most of the fault detection methods are not able to detect the fault propagation path, and some methods require a priori knowledge on the faults, or the relationships between the monitored varia ...
DOI:
10.1021/acs.iecr.8b02106

14. Enhancing Quality of Multivariate Process Monitoring Based on Vine Copula and Active Learning Strategy

Author:
Yang Zhou; Xiang Ren; Shaojun Li
Source:
Industrial & engineering chemistry process design and development 2018 v.57 no.23 pp. 7961-7974
ISSN:
1520-5045
Subject:
models; probability; process design; process monitoring; vines
Abstract:
... This paper proposes a new process monitoring method based on vine copula and active learning strategy under a limited number of labeled samples. The proposed method uses active learning strategy and the generalized Bayesian inference-based probability (GBIP) index to choose samples that can provide the most significant information for the process monitoring model. An adaptive strategy is used to s ...
DOI:
10.1021/acs.iecr.7b05128

15. Estimation of Disturbance Propagation Path Using Principal Component Analysis (PCA) and Multivariate Granger Causality (MVGC) Techniques

Author:
Usama Ahmed; Daegeun Ha; Seolin Shin; Nadeem Shaukat; Umer Zahid; Chonghun Han
Source:
Industrial & engineering chemistry process design and development 2017 v.56 no.25 pp. 7260-7272
ISSN:
1520-5045
Subject:
algorithms; distillation; fractionation; industry; principal component analysis; process design; process monitoring; product development; variance covariance matrix
Abstract:
... Process monitoring and fault diagnosis using the multivariate statistical methodologies has been extensively used in the process and product development industries for the last several decades. The fault in one process variable readily affects all the other associated variables, which makes the fault detection process not only more difficult but also time-consuming. In this study, principal compon ...
DOI:
10.1021/acs.iecr.6b02763

16. Exponential Smoothing Reconstruction Approach for Incipient Fault Isolation

Author:
Hongquan Ji; Xiao He; Jun Shang; Donghua Zhou
Source:
Industrial & engineering chemistry process design and development 2018 v.57 no.18 pp. 6353-6363
ISSN:
1520-5045
Subject:
heaters; process design; process monitoring; simulation models
Abstract:
... Accurate detection and isolation of an incipient fault is crucial for efficient and optimal operation of industrial processes. In the area of statistical process monitoring (SPM), reconstruction-based methods are widely used for fault isolation purposes. Though possessing several merits, most existing conventional reconstruction methods are not efficient in isolating incipient faults that have sma ...
DOI:
10.1021/acs.iecr.8b00478

17. Fault Detection Based on a Manifold Learning Bilinear Regression Method

Author:
Lin Feng; Zhiyuan Liu; Yingwei Zhang
Source:
Industrial & engineering chemistry process design and development 2020 v.59 no.13 pp. 6329-6335
ISSN:
1520-5045
Subject:
chemistry; discriminant analysis; learning; magnesium oxide; models; probability; process design; process monitoring; regression analysis
Abstract:
... The fused magnesia smelting process is a very complex industrial process, and the fault probability is quite high. Current process monitoring and fault detection methods have difficulty accurately capturing the small fault signals in the smelting process, resulting in serious irreversible consequences. Under the background of big data, the performance of the fused magnesia smelting process fault d ...
DOI:
10.1021/acs.iecr.9b06904

18. Fault Detection and Root Cause Analysis of a Batch Process via Novel Nonlinear Dissimilarity and Comparative Granger Causality Analysis

Author:
He Fei; Wang Chaojun; Fan Shu-Kai S
Source:
Industrial & engineering chemistry process design and development 2019 v.58 no.47 pp. 21842-21854
ISSN:
1520-5045
Subject:
algorithms; batch systems; case studies; data collection; entropy; fermentation; penicillins; process monitoring
Abstract:
... Data-driven fault detection and root cause analysis methods become attractive in modern industrial production that can guarantee the safety and stability of process operation. If process monitoring technology is implemented for fault detection, and the root cause of faults is analyzed timely, it is beneficial to maintain and improve the quality of coming batches. In this paper, a framework of faul ...
DOI:
10.1021/acs.iecr.9b04471

19. Finding Significant Qualitative Trend Combinations for Multivariate Systems from Historical Data

Author:
Kuang Chen; Jiandong Wang
Source:
Industrial & engineering chemistry process design and development 2019 v.58 no.11 pp. 4518-4533
ISSN:
1520-5045
Subject:
algorithms; decision making; models; process design; process monitoring
Abstract:
... Data segments in similar patterns are often prerequisites for process monitoring, data mining, and decision making tasks. This paper proposes a probabilistic clustering method to automatically find significant qualitative trend combinations from historical time sequences of multiple process variables. The main idea is to obtain the histograms of decreasing, steady, and increasing qualitative trend ...
DOI:
10.1021/acs.iecr.8b05864

20. Formulation of a New Trend Cumulative Sum Chart to Monitor Batch Process Variables

Author:
Laibin Zhang; Xi Ma; Jinqiu Hu; Shaohua Dong; Ahmet Palazoglu
Source:
Industrial & engineering chemistry process design and development 2018 v.57 no.18 pp. 6303-6316
ISSN:
1520-5045
Subject:
batch systems; manufacturing; polypropylenes; process design; process monitoring; product quality; value added
Abstract:
... In the chemical and biochemical industries, batch processes play an important role in producing high-quality and value-added specialty products. The variables measured in such processes often have periodic trajectories with varying batch duration and fixed operational stages. The measured value of a process variable provides only part of the information about process conditions, while the process ...
DOI:
10.1021/acs.iecr.7b04851

21. Functional Modeling View on Product and Process Engineering in Design and Operations

Author:
Sten Bay Jørgensen; Morten Lind; Niels Jensen
Source:
Industrial & engineering chemistry process design and development 2019 v.58 no.26 pp. 11129-11148
ISSN:
1520-5045
Subject:
chemical engineering; chemistry; models; process design; process monitoring; systems engineering
Abstract:
... Recent significant developments within process systems engineering demonstrate a need for more-flexible tools to handle the many diverse model-based tasks within product and process synthesis, design, innovation, and operation. Consequently, it is relevant to have a closer look at one of the modeling methodologies that have emerged. This paper addresses functional modeling for the purpose of the o ...
DOI:
10.1021/acs.iecr.8b06338

22. Hierarchically Distributed Monitoring for the Early Prediction of Gas Flare Events

Author:
Mengqi Fang; Fadi Ibrahim; Hariprasad Kodamana; Biao Huang; Noel Bell; Mark Nixon
Source:
Industrial & engineering chemistry process design and development 2019 v.58 no.26 pp. 11352-11363
ISSN:
1520-5045
Subject:
chemistry; data collection; environmental impact; prediction; principal component analysis; process design; process monitoring; wavelet
Abstract:
... Flare events in industrial processes are undesirable because of their negative economic and environmental impacts. Early warnings of flare events are needed in preventing occurrences of flaring, as corrective manual interventions can be performed by the plant operators. This article reports the successful application of a hierarchically distributed monitoring approach for flare event prediction. T ...
DOI:
10.1021/acs.iecr.8b06186

23. Improved Vine Copula-Based Dependence Description for Multivariate Process Monitoring Based on Ensemble Learning

Author:
Yang Zhou; Shaojun Li; Ning Xiong
Source:
Industrial & engineering chemistry process design and development 2019 v.58 no.9 pp. 3782-3796
ISSN:
1520-5045
Subject:
Bayesian theory; acetic acid; probabilistic models; probability; process design; process monitoring; vines
Abstract:
... This paper proposes a boosting vine copula-based dependence description (BVCDD) method for multivariate and multimode process monitoring. The BVCDD aims to improve the standard vine copula-based dependence description (VCDD) method by establishing an ensemble of submodels from sample directions based on a boosting strategy. The generalized Bayesian inference-based probability (GBIP) index is intro ...
DOI:
10.1021/acs.iecr.8b04081

24. Incipient Fault Detection for Chemical Processes Using Two-Dimensional Weighted SLKPCA

Author:
Xiaogang Deng; Jiawei Deng
Source:
Industrial & engineering chemistry process design and development 2019 v.58 no.6 pp. 2280-2295
ISSN:
1520-5045
Subject:
principal component analysis; process design; process monitoring
Abstract:
... Early detection of incipient faults is a challenging task in chemical process monitoring field. As an effective incipient fault detection tool, statistical local kernel principal component analysis (SLKPCA) has demonstrated its advantage over the traditional kernel principal component analysis (KPCA). However, how to improve its incipient fault detection performance is still a valuable problem. In ...
DOI:
10.1021/acs.iecr.8b04794

25. Incipient Fault Detection for Complex Industrial Processes with Stationary and Nonstationary Hybrid Characteristics

Author:
Chunhui Zhao; Biao Huang
Source:
Industrial & engineering chemistry process design and development 2018 v.57 no.14 pp. 5045-5057
ISSN:
1520-5045
Subject:
algorithms; case studies; covariance; process design; process monitoring; variance
Abstract:
... For a nonstationary process which has a time-varying mean, a time-varying variance, or both, it can be difficult to detect incipient disturbances which may be hidden by the time-varying process variations. Besides, stationary and nonstationary characteristics may coexist in complex industrial processes which, however, have not been studied for process monitoring. In the present work, a triple subs ...
DOI:
10.1021/acs.iecr.8b00233

26. Industrial Process Monitoring Based on Knowledge–Data Integrated Sparse Model and Two-Level Deviation Magnitude Plots

Author:
Lijia Luo; Shiyi Bao; Jianfeng Mao; Zhenyu Ding
Source:
Industrial & engineering chemistry process design and development 2018 v.57 no.2 pp. 611-622
ISSN:
1520-5045
Subject:
case studies; models; normal values; process design; process monitoring
Abstract:
... Data-driven process monitoring methods use only process data to build monitoring models, while useful process knowledge is completely ignored. Consequently, data-driven monitoring models usually have poor interpretability, which may reduce fault detection and diagnosis capabilities. To overcome such drawbacks, a novel knowledge–data integrated sparse monitoring (KDISM) model and two-level deviatio ...
DOI:
10.1021/acs.iecr.7b02150

27. Integrated Data-Driven Process Monitoring and Explicit Fault-Tolerant Multiparametric Control

Author:
Melis Onel; Baris Burnak; Efstratios N. Pistikopoulos
Source:
Industrial & engineering chemistry process design and development 2019 v.59 no.6 pp. 2291-2306
ISSN:
1520-5045
Subject:
models; penicillins; process monitoring; regression analysis; support vector machines
Abstract:
... We propose a novel active fault-tolerant control strategy that combines machine learning based process monitoring and explicit/multiparametric model predictive control (mp-MPC). The strategy features (i) data-driven fault detection and diagnosis models by using the support vector machine (SVM) algorithm, (ii) ranking via a nonlinear, kernel-dependent, SVM-based feature selection algorithm, (iii) d ...
DOI:
10.1021/acs.iecr.9b04226

28. Joint Structure Preserving Embedding Model and Its Application for Process Monitoring

Author:
Yuanjian Fu; Chaomin Luo
Source:
Industrial & engineering chemistry process design and development 2019 v.58 no.45 pp. 20667-20679
ISSN:
1520-5045
Subject:
case studies; geometry; learning; models; principal geodesic analysis; process design; process monitoring
Abstract:
... Currently, dimensionality reduction methods based on manifold learning are widely applied to industrial process monitoring. However, considering that a number of manifold-based monitoring methods extract only the global geometric information of the original data or the local manifold structure of the neighboring data points, in this article, a novel dimensionality reduction method called joint str ...
DOI:
10.1021/acs.iecr.9b03077

29. Large-Scale Supervised Process Monitoring Based on Distributed Modified Principal Component Regression

Author:
Mengyu Rong; Hongbo Shi; Shuai Tan
Source:
Industrial & engineering chemistry process design and development 2019 v.58 no.39 pp. 18223-18240
ISSN:
1520-5045
Subject:
Bayesian theory; algorithms; models; probability; process design; process monitoring
Abstract:
... Traditional process monitoring methods construct a single monitoring model to detect if a fault happened. But the development of industrial technology has made industrial processes increasingly complex and huge. When considering local or quality-related faults, especially tiny faults in complex large-scale industrial processes, it is difficult to accurately detect these faults using a single monit ...
DOI:
10.1021/acs.iecr.9b02163

30. Layer-by-Layer Enhancement Strategy of Favorable Features of the Deep Belief Network for Industrial Process Monitoring

Author:
Jianbo Yu; Xuefeng Yan
Source:
Industrial & engineering chemistry process design and development 2018 v.57 no.45 pp. 15479-15490
ISSN:
1520-5045
Subject:
employment; process design; process monitoring; vector data
Abstract:
... Recently, owing to its powerful feature extraction capability, deep learning has been applied to the field of fault detection, in which fault information is reflected in data fluctuation. Deep learning networks transmit fluctuation to the abstract feature layer, and the running state is determined on the basis of the fluctuation of the feature layer. Adjacent layers are connected by weights, where ...
DOI:
10.1021/acs.iecr.8b04689

31. Locally Weighted Canonical Correlation Analysis for Nonlinear Process Monitoring

Author:
Qingchao Jiang; Xuefeng Yan
Source:
Industrial & engineering chemistry process design and development 2018 v.57 no.41 pp. 13783-13792
ISSN:
1520-5045
Subject:
models; multivariate analysis; process design; process monitoring
Abstract:
... A locally weighted canonical correlation analysis (LWCCA) method is proposed to achieve efficient nonlinear process monitoring. The basic idea of the LWCCA is to approximate a nonlinear process through several local linear canonical correlation analysis (CCA) models, in which the determination of sample weights is a key step. Slowly decreasing weights will ignore the local behaviors, whereas rapid ...
DOI:
10.1021/acs.iecr.8b01796

32. Monitoring Batch Processes Using Sparse Parallel Factor Decomposition

Author:
Lijia Luo; Shiyi Bao; Jianfeng Mao; Di Tang
Source:
Industrial & engineering chemistry process design and development 2017 v.56 no.44 pp. 12682-12692
ISSN:
1520-5045
Subject:
batch fermentation; models; multivariate analysis; process design; process monitoring
Abstract:
... Traditional multivariate statistical analysis methods used for batch process monitoring fail to build high-performance monitoring models partly because of the inability to extract sparse and interpretable latent variables from the batch data. To overcome this deficiency, we propose sparse parallel factor (SPARAFAC) decomposition for the sparse modeling of three-way data arrays of batch processes. ...
DOI:
10.1021/acs.iecr.7b02618

33. Multimode Continuous Processes Monitoring Based on Hidden Semi-Markov Model and Principal Component Analysis

Author:
Zhijiang Lou; Youqing Wang
Source:
Industrial & engineering chemistry process design and development 2017 v.56 no.46 pp. 13800-13811
ISSN:
1520-5045
Subject:
Markov chain; algorithms; models; principal component analysis; probability distribution; process design; process monitoring
Abstract:
... Several studies have applied the hidden Markov model (HMM) in multimode process monitoring. However, because the inherent duration probability density of HMM is exponential, which is inappropriate for modeling the multimode process, the performance of these HMM-based approaches is not satisfactory. As a result, the hidden semi-Markov model (HSMM), which integrated the mode duration probability int ...
DOI:
10.1021/acs.iecr.7b01721

34. Multimode Process Fault Detection Based on Local Density Ratio-Weighted Support Vector Data Description

Author:
Han Li; Huangang Wang; Wenhui Fan
Source:
Industrial & engineering chemistry process design and development 2017 v.56 no.9 pp. 2475-2491
ISSN:
1520-5045
Subject:
models; process design; process monitoring; vector data
Abstract:
... Industrial process fault detection plays an important role for process security, and data-based process monitoring is an effective way to detect fault. Industrial processes typically have multiple operating modes with different data distribution and outliers. This paper proposes a novel multimode process fault detection method based on local density ratio-weighted support vector data description ( ...
DOI:
10.1021/acs.iecr.6b03306

35. Multimode Process Monitoring Approach Based on Moving Window Hidden Markov Model

Author:
Lin Wang; Chunjie Yang; Youxian Sun
Source:
Industrial & engineering chemistry process design and development 2018 v.57 no.1 pp. 292-301
ISSN:
1520-5045
Subject:
Markov chain; algorithms; mathematical models; process design; process monitoring
Abstract:
... Due to the existence of multiple operating modes, traditional fault detection techniques are ill-suited for complex industrial processes. Although there are more and more literature studies concerning this problem, only a few of them are based on the hidden Markov model (HMM). However, there is no exploration to concern the unknown mode in the industrial process based on it. This article proposes ...
DOI:
10.1021/acs.iecr.7b03600

36. Multimode and Multiphase Batch Processes Understanding and Monitoring Based on between-Mode Similarity Evaluation and Multimode Discriminative Information Analysis

Author:
Yan Qin; Chunhui Zhao; Shumei Zhang; Furong Gao
Source:
Industrial & engineering chemistry process design and development 2017 v.56 no.34 pp. 9679-9690
ISSN:
1520-5045
Subject:
algorithms; batch systems; discriminant analysis; injection molding; models; process design; process monitoring
Abstract:
... The high requirements of safe production and quality products have greatly spurred the development of understanding analysis and monitoring technologies of batch processes. However, for the multimode and multiphase batch processes with serious process dynamics, few process monitoring studies have been reported. To address the above issues, a novel process monitoring method based on between-mode si ...
DOI:
10.1021/acs.iecr.7b02981

37. Multiple Fault Diagnosis in Distillation Column Using Multikernel Support Vector Machine

Author:
Syed A. Taqvi; Lemma Dendena Tufa; Haslinda Zabiri; Abdulhalim Shah Maulud; Fahim Uddin
Source:
Industrial & engineering chemistry process design and development 2018 v.57 no.43 pp. 14689-14706
ISSN:
1520-5045
Subject:
data collection; decision support systems; discriminant analysis; distillation; feed composition; industry; neural networks; process design; process monitoring; product quality; support vector machines; temperature
Abstract:
... Fault detection and diagnosis (FDD) in process industries is an important task for efficient process monitoring and plant safety. It is also essential for improving product quality and reducing production cost by reducing process downtime. Real-time multiscale classification of faults plays a vital role in process monitoring. However, some major issues such as high correlation, complexity, and non ...
DOI:
10.1021/acs.iecr.8b03360

38. Mutual Information–Dynamic Stacked Sparse Autoencoders for Fault Detection

Author:
Jie Yin; Xuefeng Yan
Source:
Industrial & engineering chemistry process design and development 2019 v.58 no.47 pp. 21614-21624
ISSN:
1520-5045
Subject:
autocorrelation; models; process monitoring; time series analysis
Abstract:
... Data-based process monitoring is gaining increasing attention, especially deep learning modeling methods. Given that process data are inherently dynamic, the dynamic relationship of process data needs to be incorporated into the monitoring model. Measured variables have diverse characteristics; some variables have strong autocorrelation, but some have no or weak autocorrelation. Hence, a new nonli ...
DOI:
10.1021/acs.iecr.9b04389

39. New Dynamic Predictive Monitoring Schemes Based on Dynamic Latent Variable Models

Author:
Yining Dong; S. Joe Qin
Source:
Industrial & engineering chemistry process design and development 2020 v.59 no.6 pp. 2353-2365
ISSN:
1520-5045
Subject:
case studies; data collection; models; prediction; process monitoring; uncertainty
Abstract:
... In this paper, dynamic predictive monitoring schemes based on dynamic latent variable models are proposed. We consider the most typical case in industrial data where dynamics usually exist in a reduced dimensional subspace. First, using dynamic latent variable models, predictions are made to reduce the dynamic latent space variability and focus on the unpredictable variabilities for process monito ...
DOI:
10.1021/acs.iecr.9b04741

40. A New Nonlinear Process Monitoring Method Based on Linear and Nonlinear Partition

Author:
Fan Wang; Sen Zhang; Yixin Yin
Source:
Industrial & engineering chemistry process design and development 2019 v.58 no.37 pp. 17445-17454
ISSN:
1520-5045
Subject:
data collection; mathematical models; process design; process monitoring
Abstract:
... Traditional nonlinear process monitoring approaches deal with all process variables directly, without carefully investigating their complex relationships. In this Article, key performance indicators (KPIs) are monitored objects. Maximal information coefficient (MIC) is used to analyze correlation between process variables and KPIs. MIC is able to find complex associations and assess their signific ...
DOI:
10.1021/acs.iecr.9b03197

41. Nonlinear and Non-Gaussian Process Monitoring Based on Simplified R-Vine Copula

Author:
Nan Zhou; Shaojun Li
Source:
Industrial & engineering chemistry process design and development 2018 v.57 no.22 pp. 7566-7582
ISSN:
1520-5045
Subject:
acetic acid; distillation; models; probability; process design; process monitoring; vines
Abstract:
... In the field of chemical process monitoring, the vine copula model provides a new idea for describing the interdependence between high-dimensional complex variables, and directly characterizes the correlation without dimensional reduction. However, in actual industrial processes, the number of pair copulas to be optimized and the parameters to be estimated increase rapidly when the dimensionality ...
DOI:
10.1021/acs.iecr.8b00701

42. Nonparametric Density Estimation of Hierarchical Probabilistic Graph Models for Assumption-Free Monitoring

Author:
Jiusun Zeng; Shihua Luo; Jinhui Cai; Uwe Kruger; Lei Xie
Source:
Industrial & engineering chemistry process design and development 2017 v.56 no.5 pp. 1278-1287
ISSN:
1520-5045
Subject:
Bayesian theory; furnaces; models; probability; process design; process monitoring
Abstract:
... Probabilistic graphical models, such as Bayesian networks, have recently gained attention in process monitoring and fault diagnosis. Their application, however, is limited to discrete or continuous Gaussian distributed variables, which results from the difficulty in efficiently estimating multivariate density functions. This article shows that decomposing the graphical model into a hierarchical st ...
DOI:
10.1021/acs.iecr.6b04068

43. Normal and Abnormal Data Segmentation Based on Variational Directions and Clustering Algorithms

Author:
Kuang Chen; Jiandong Wang
Source:
Industrial & engineering chemistry process design and development 2017 v.56 no.27 pp. 7799-7813
ISSN:
1520-5045
Subject:
algorithms; data collection; process design; process monitoring
Abstract:
... Historical normal and abnormal data sets are prerequisites for process monitoring, alarm system rationalization, fault detection, and diagnosis. This paper proposes a new method to automatically find normal and abnormal data segments from historical data sets based on variational directions of multiple process variables. The minimum time duration and the minimum amplitude shift are introduced as e ...
DOI:
10.1021/acs.iecr.7b01868

44. Novel Distributed Alarm Visual Analysis Using Multicorrelation Block-Based PLS and Its Application to Online Root Cause Analysis

Author:
Qun-Xiong Zhu; Yi Luo; Yan-Lin He
Source:
Industrial & engineering chemistry process design and development 2019 v.58 no.45 pp. 20655-20666
ISSN:
1520-5045
Subject:
alarm systems; case studies; least squares; models; process design; process monitoring
Abstract:
... Process monitoring and alarm systems play an important role in production safety. Distributed alarm systems have been utilized to effectively reduce the burden of data calculations, contributing to fast-track root causes of alarms. However, the traditional distributed contribution analysis method cannot be well applied to online monitoring in time. In addition, the correlation-based variable recon ...
DOI:
10.1021/acs.iecr.9b02963

45. Novel Pattern-Matching Integrated KCVA with Adaptive Rank-Order Morphological Filter and Its Application to Fault Diagnosis

Author:
Yuan Xu; Cuihuan Fan; Qun-Xiong Zhu; Abbas Rajabifard; Nengcheng Chen; Yiqun Chen; Yan-Lin He
Source:
Industrial & engineering chemistry process design and development 2019 v.59 no.4 pp. 1619-1630
ISSN:
1520-5045
Subject:
case studies; models; multivariate analysis; process monitoring; seeds
Abstract:
... With the scale expansion of industrial processes, the relationship between process variables has become complex and highly nonlinear. As a result, the requirements for fault diagnosis and safety monitoring has become demanding. To address this problem, a novel and effective pattern-matching method using kernel canonical variate analysis (KCVA) integrated with an adaptive rank-order morphological f ...
DOI:
10.1021/acs.iecr.9b05403

46. Optimal Feature Selection for Distributed Data-Driven Process Monitoring

Author:
Shaaz Khatib; Prodromos Daoutidis
Source:
Industrial & engineering chemistry process design and development 2019 v.59 no.6 pp. 2307-2317
ISSN:
1520-5045
Subject:
algorithms; case studies; computers; mathematical theory; process monitoring
Abstract:
... Two methods are proposed in this article to address distributed data-driven process monitoring. The first method selects sensors and allocates these sensors among subsystems with the objective of optimizing the diagnostic performance of a pattern recognition method when it is implemented in a distributed configuration subject to constraints that are imposed to meet operational requirements. The se ...
DOI:
10.1021/acs.iecr.9b03872

47. Process Monitoring Based on Orthogonal Locality Preserving Projection with Maximum Likelihood Estimation

Author:
Jingxin Zhang; Maoyin Chen; Hao Chen; Xia Hong; Donghua Zhou
Source:
Industrial & engineering chemistry process design and development 2019 v.58 no.14 pp. 5579-5587
ISSN:
1520-5045
Subject:
algorithms; case studies; process design; process monitoring; statistical analysis
Abstract:
... By integrating two powerful methods of density reduction and intrinsic dimensionality estimation, a new data-driven method, referred to as OLPP–MLE (orthogonal locality preserving projection-maximum likelihood estimation), is introduced for process monitoring. OLPP is utilized for dimensionality reduction, which provides better locality preserving power than locality preserving projection. Then, t ...
DOI:
10.1021/acs.iecr.8b05875

48. Process Monitoring Based on the Multiblock Rolling Pin Vine Copula

Author:
Qiong Jia; Shaojun Li
Source:
Industrial & engineering chemistry process design and development 2020 v.59 no.40 pp. 18050-18060
ISSN:
1520-5045
Subject:
chemical engineering; chemistry; process design; process monitoring; vines
Abstract:
... This paper presents a process-monitoring method based on multiblock rolling pin vine copula. The multiblock strategy not only reduces the impact of the local errors of the global variable during the monitoring process but also reduces the number of parameters that must be estimated and the number of copula trees. Introduction of rolling pin solves the problem that vine copula is difficult to accur ...
DOI:
10.1021/acs.iecr.0c02989

49. Process Monitoring Method Based on Double-Model and Multi-Subspace Vine Copula

Author:
Qiong Jia; Hongtao Deng; Xiang Ren; Shaojun Li
Source:
Industrial & engineering chemistry process design and development 2019 v.58 no.27 pp. 12137-12148
ISSN:
1520-5045
Subject:
chemistry; mathematical models; multivariate analysis; probability; process design; process monitoring; vines
Abstract:
... A process monitoring method based on double-model and multi-subspace vine copula (DMVC) is proposed in this paper. To improve the fault detection performance, process variables are divided into two sets according to their correlation, in which C-vine and D-vine are used to build models, respectively. The variables with stronger correlation are selected to build the C-vine model, and those with wea ...
DOI:
10.1021/acs.iecr.9b01781

50. A Quality-Related Statistical Process Monitoring Method Based on Global plus Local Projection to Latent Structures

Author:
J. L. Zhou; S. L. Zhang; H. Zhang; J. Wang
Source:
Industrial & engineering chemistry process design and development 2018 v.57 no.15 pp. 5323-5337
ISSN:
1520-5045
Subject:
least squares; process design; process monitoring; statistical models; yield monitoring
Abstract:
... The partial least-squares (PLS) method is widely used in the quality monitoring of process control systems, but it has poor monitoring capability in some locally strong nonlinear systems. To enhance the monitoring ability of such nonlinear systems, a novel statistical model based on global plus local projection to latent structures (GPLPLS) is proposed. First, the characteristics and nature of glo ...
DOI:
10.1021/acs.iecr.7b04554