Article
Engineering, Multidisciplinary
Zhijiang Lou, Zedong Li, Youqing Wang, Shan Lu
Summary: This paper introduces an improved neural component analysis (INCA) method, which addresses the issue of NCA's inability to handle non-Gaussian features by proposing a new cost function based on kurtosis. It also improves the extraction of key information from process data by selecting principal components (PCs) in the original data space. Experimental results show that INCA outperforms other methods in fault detection.
Article
Mathematics
Muhammad Riaz, Babar Zaman, Ishaq Adeyanju Raji, M. Hafidz Omar, Rashid Mehmood, Nasir Abbas
Summary: This study proposes two adaptive control charts to monitor shifts of different sizes in the process mean vector. By applying dimension reduction techniques and adaptive methods, the monitoring effectiveness of the shifts is improved. The performance of the proposed control charts is evaluated through Monte Carlo simulation and performance comparison measures, and is found to be superior to other control charts.
Article
Engineering, Environmental
Amanda Vitoria Santos, Aline Ribeiro Alkmim Lin, Miriam Cristina Santos Amaral, Silvia Maria Alves Correa Oliveira
Summary: This study investigated the performance of an MBR treating industrial wastewater under different operating variables using PCA and MSPC techniques. The results showed that sludge filterability, temperature, and SDWC were the most influential variables on membrane permeability, and multivariate control charts were effective in predicting MBR performance and detecting operational faults.
CHEMICAL ENGINEERING JOURNAL
(2021)
Article
Environmental Sciences
Mustafa El-Rawy, Heba Fathi, Fathy Abdalla, Fahad Alshehri, Hazem Eldeeb
Summary: Jazan province in Saudi Arabia is facing significant challenges in water management due to its arid climate, limited water resources, and growing population. A study was conducted to assess the adaptability of groundwater for irrigation using hydro-chemical parameters and PCA. The results showed the importance of incorporating different techniques to understand and control groundwater quality in the study area.
Article
Materials Science, Textiles
Chung-Feng Jeffrey Kuo, Chang-Chiun Huang, Cheng-Han Yang
Summary: This study aimed to construct an automatic abnormality diagnosis system for polypropylene (PP) as-spun fiber produced by the melt spinning process. By using the orthogonal array of the Taguchi method and principal component analysis, the optimum processing parameters that affect product quality were determined.
TEXTILE RESEARCH JOURNAL
(2021)
Article
Computer Science, Information Systems
Li Qi, Xiaoyun Yi, Lina Yao, Yixian Fang, Yuwei Ren
Summary: This paper proposes a method combining singular value decomposition (SVD) and kernel principal component regression (KPCR) to achieve quality-related process monitoring with lower computational cost and higher fault detection rate.
Article
Computer Science, Interdisciplinary Applications
Feng Xu, Xiaoqin Deng
Summary: The monitoring methodology in statistical process control is useful but limited in accurately diagnosing responsible components for process changes. This article presents a Bayesian procedure that can simultaneously diagnose shifts in both mean vector and covariance matrix. The proposed method provides directions of shifts and corresponding probabilities, aiding decision makers in quickly identifying root causes of abnormal changes. Compared with existing methods, numerical simulations support the effectiveness of the proposed method.
COMPUTERS & INDUSTRIAL ENGINEERING
(2023)
Article
Water Resources
Hyejung Jung, Kyoochul Ha, Dong-Chan Koh, Yongcheol Kim, Jeonghoon Lee
Summary: Through PCA and correlation analysis, the study identified vulnerable index wells to droughts, reducing monitoring expenses. Additionally, the study found that variables affecting groundwater-level variations differed with temporal resolution changes, emphasizing the importance of a comprehensive groundwater management plan with proper monitoring during droughts.
JOURNAL OF HYDROLOGY-REGIONAL STUDIES
(2021)
Article
Automation & Control Systems
Yang Tao, Hongbo Shi, Bing Song, Shuai Tan
Summary: In this article, a distributed adaptive principal component regression algorithm is proposed for the online indicator monitoring of large-scale dynamic process. The algorithm constructs distributed data subblocks according to the process operation units and uses an adaptive resampling method to extract process local and global information simultaneously. The effectiveness of the proposed method is demonstrated through a numerical example and the Tennessee Eastman process.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Chemistry, Analytical
Carollina de Melo Molinari Ortiz Antunes, Frederico Luis Felipe Soares, Noemi Nagata
Summary: Chemical analyses based on digital images are widely studied due to their non-invasive nature and simplicity. However, controlling instrumental and structural parameters for image acquisition is crucial for analysis repeatability and reproducibility. The high cost of accessing robust instruments is also a practical limitation. To overcome these limitations, a low-cost prototype using Raspberry Pi and multivariate tools was developed.
MICROCHEMICAL JOURNAL
(2023)
Article
Engineering, Chemical
Chun-Chin Hsu, Po-Chou Shih, Fang-Chih Tien
Summary: A novel weight strategy for multiblock PCA was proposed in this study, which considers the dependence and skewness of data to additionally take distribution information into account. The proposed weight matrix based on non-parametric ranks leads to shorter computation time. Experimental results show that the proposed method outperforms regular PCA, dynamic PCA, multiblock PCA, and WCMBPCA in fault detection rate for Tennessee Eastman (TE) process monitoring. Furthermore, the weight matrix calculation time is significantly shorter for the proposed method compared to WCMBPCA.
JOURNAL OF THE TAIWAN INSTITUTE OF CHEMICAL ENGINEERS
(2021)
Article
Chemistry, Analytical
Yusheng Lang, Lilin Zhou, Yutaka Imamura
Summary: Time-of-flight secondary ion mass spectrometry (ToF-SIMS) is an important analysis technique for gathering information from surfaces. This study proposed a new approach that treats ToF-SIMS spectra as images and uses convolutional neural network (CNN) for analysis, avoiding the challenges of descriptor generation.
ANALYTICAL CHEMISTRY
(2022)
Article
Mathematics
Chuen-Sheng Cheng, Pei-Wen Chen, Yu-Chin Hsieh, Yu-Tang Wu
Summary: In this study, a deep learning-based classification model was developed to recognize control chart patterns in multivariate processes. The model outperformed traditional methods in identifying multivariate non-random patterns and achieved a 10% improvement. The results suggest that the developed model can be beneficial for intelligent SPC.
Article
Water Resources
Samuel Obiri, Gloria Addico, Saada Mohammed, Wilson William Anku, Humphry Darko, Okrah Collins
Summary: This study used multivariate statistical techniques to assess the quality of surface water from Tano basin in Ghana, revealing the relationships between water quality and different parameters through correlation analysis and principal component analysis. The results showed correlations between pH and various ions as well as the main sources of variation in the physicochemical properties of the water samples.
APPLIED WATER SCIENCE
(2021)
Article
Materials Science, Textiles
Chung-Feng Jeffrey Kuo, Chang-Chiun Huang, Cheng-Han Yang, Sung-Hua Chen
Summary: The study utilized multivariate statistical process control to analyze abnormal samples, effectively identifying them and establishing a fault processing parameter diagnosis system for melt spinning machines.
TEXTILE RESEARCH JOURNAL
(2021)
Article
Engineering, Chemical
Bundit Boonkhao, Xue Z. Wang
Article
Engineering, Chemical
Bundit Boonkhao, Xue Z. Wang, Thongchai Rohitatisha Srinophakun
Summary: This article introduces a technique called DE-Nonneg that optimizes within the non-negative real number domain through modification of the differential evolution technique. Experimental results show that the PSD predictions using DE-Nonneg are comparable to simulated annealing technique. Furthermore, the performance of DE-Nonneg can be improved by adjusting parameters.
Article
Plant Sciences
Masahiko Isaka, Bundit Boonkhao, Pranee Rachtawee, Patchanee Auncharoen
JOURNAL OF NATURAL PRODUCTS
(2007)