Time-Specific Thresholds for Batch Process Monitoring: A Study Based on Two-Dimensional Conditional Variational Auto-Encoder DOI Open Access
Jinlin Zhu, Zhong Liu, Xuyang Lou

и другие.

Processes, Год журнала: 2024, Номер 12(4), С. 682 - 682

Опубликована: Март 28, 2024

This paper studies the use of varying threshold in statistical process control (SPC) batch processes. The motivation is driven by how when multiple phases are implicated each repetition, distributions features behind vary with or even time; thus, it inconsistent to uniformly bound them an invariant threshold. In this paper, we paved a new path for learning and monitoring processes based on efficient framework integrating model termed conditional dynamic variational auto-encoder (CDVAE). Phase indicators first used split data then separated, serving as extra input order alleviate complexity. Dissimilar routine using across all timescales, only relevant local timestamps aggregated calculation, producing that more specific variations occurring among timeline. Leveraged upon idea, fault detection panel devised, deep reconstruction-based contribution diagram illustrated locating faulty variables. Finally, comparative results from two case highlight superiority both accuracy diagnostic performance.

Язык: Английский

Digital twin for predicting and controlling food fermentation: a case study of kombucha fermentation DOI

Songguang Zhao,

Tianhui Jiao,

Selorm Yao‐Say Solomon Adade

и другие.

Journal of Food Engineering, Год журнала: 2025, Номер unknown, С. 112467 - 112467

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

3

Real-time identification of acoustic emission signals of rock tension-shear fracture based on machine learning and study on precursory characteristics DOI
Juxian Wang, Peng Liang, Yanbo Zhang

и другие.

Mechanical Systems and Signal Processing, Год журнала: 2025, Номер 230, С. 112665 - 112665

Опубликована: Апрель 4, 2025

Язык: Английский

Процитировано

2

An intelligent hybrid approach for photovoltaic power forecasting using enhanced chaos game optimization algorithm and Locality sensitive hashing based Informer model DOI
Peng Tian,

Yongyan Fu,

Yuhan Wang

и другие.

Journal of Building Engineering, Год журнала: 2023, Номер 78, С. 107635 - 107635

Опубликована: Авг. 21, 2023

Язык: Английский

Процитировано

21

A modeling method of wide random forest multi-output soft sensor with attention mechanism for quality prediction of complex industrial processes DOI
Yin Wan, Ding Liu,

Jun-Chao Ren

и другие.

Advanced Engineering Informatics, Год журнала: 2023, Номер 59, С. 102255 - 102255

Опубликована: Ноя. 20, 2023

Язык: Английский

Процитировано

19

Production capacity prediction based response conditions optimization of straw reforming using attention-enhanced convolutional LSTM integrating data expansion DOI
Yongming Han, Zhiyi Li, Tingting Wei

и другие.

Applied Energy, Год журнала: 2024, Номер 365, С. 123253 - 123253

Опубликована: Апрель 17, 2024

Язык: Английский

Процитировано

7

Virtual Sensor for Sustainable Large-Scale Process Monitoring DOI
Mohammad Reza Boskabadi,

Mahesh Murugaiah,

Torben Nielsen

и другие.

Industrial & Engineering Chemistry Research, Год журнала: 2025, Номер unknown

Опубликована: Фев. 5, 2025

Язык: Английский

Процитировано

1

A soft sensor model based on CNN-BiLSTM and IHHO algorithm for Tennessee Eastman process DOI
Yiman Li, Peng Tian, Wei Sun

и другие.

Measurement, Год журнала: 2023, Номер 218, С. 113195 - 113195

Опубликована: Июнь 11, 2023

Язык: Английский

Процитировано

14

Harnessing biotechnology for penicillin production: Opportunities and environmental considerations DOI Creative Commons
Md Ariful Haque,

Nirmalendu Nath,

Tony V. Johnston

и другие.

The Science of The Total Environment, Год журнала: 2024, Номер 946, С. 174236 - 174236

Опубликована: Июнь 26, 2024

Since the discovery of antibiotics, penicillin has remained top choice in clinical medicine. With continuous advancements biotechnology, production become cost-effective and efficient. Genetic engineering techniques have been employed to enhance biosynthetic pathways, leading new derivatives with improved properties increased efficacy against antibiotic-resistant pathogens. Advances bioreactor design, media formulation, process optimization contributed higher yields, reduced costs, accessibility. While biotechnological advances clearly benefited global this life-saving drug, they also created challenges terms waste management. Production fermentation broths from industries contain residual by-products, other contaminants that pose direct environmental threats, while consumption intensifies risk antimicrobial resistance both environment living organisms. The current geographical spatial distribution antibiotic dramatically reveals a worldwide threat. These are being addressed through development novel management techniques. Efforts aimed at upstream downstream processing minimize costs improve yield efficiency lowering overall impact. Yield using artificial intelligence (AI), along biological chemical treatment waste, is explored reduce adverse impacts. implementation strict regulatory frameworks guidelines essential ensure proper disposal waste. This review because it explores key remaining development, scope machine learning tools such as Quantitative Structure-Activity Relationship (QSAR) modern biotechnology-driven production, for discovering alternative path reducing use agriculture meat addressing practices, offering effective recommendations.

Язык: Английский

Процитировано

6

Advanced Statistical and Meta-Heuristic Based Optimization Fault Diagnosis Techniques in Complex Industrial Processes: A Comparative Analysis DOI Creative Commons
Faizan E Mustafa, Abdul Qayyum Khan,

Abdus Samee

и другие.

IEEE Access, Год журнала: 2023, Номер 11, С. 104373 - 104391

Опубликована: Янв. 1, 2023

Industrial processes are nonlinear and complicated, requiring accurate fault identification to minimize performance deterioration respond quickly emergencies. This work investigates industrial process defect isolation, which is analytically difficult owing their complexity. paper carefully analyzes four design methods for flaw isolation based on Principal Component Analysis (PCA), Fisher Discriminant (FDA), Kernel (KFDA), Sequential quadratic programming (SQP). Our study includes the Tennessee Eastman Process (TEP) Penicillin Fermentation (PFP), among other comparable methods. We assess proposed detection through detailed analysis comparison. The simulation findings from our extensive investigation provide remarkable insights. Simulation show that FDA KFDA well in but PCA has certain limits. also considered SQP as a TEP improvement tool. noted its success restricted optimization problems, making it ideal complicated processes. Data-driven approaches increase problem with greater reliability efficiency than PCA-based shows advanced data-driven techniques can improve diagnosis, improving operational safety system by leveraging FDA, KFDA, SQP.

Язык: Английский

Процитировано

10

Predicting the RUL of Li-Ion Batteries in UAVs Using Machine Learning Techniques DOI Creative Commons

Dragoș Andrioaia,

Vasile Gheorghiță Găitan, George Culea

и другие.

Computers, Год журнала: 2024, Номер 13(3), С. 64 - 64

Опубликована: Фев. 29, 2024

Over the past decade, Unmanned Aerial Vehicles (UAVs) have begun to be increasingly used due their untapped potential. Li-ion batteries are most power electrically operated UAVs for advantages, such as high energy density and number of operating cycles. Therefore, it is necessary estimate Remaining Useful Life (RUL) prediction batteries’ capacity prevent UAVs’ loss autonomy, which can cause accidents or material losses. In this paper, authors propose a method RUL using data-driven approach. To maximize performance process, three machine learning models, Support Vector Machine Regression (SVMR), Multiple Linear (MLR), Random Forest (RF), were compared batteries. The implemented within Predictive Maintenance (PdM) systems.

Язык: Английский

Процитировано

4