4.5 Article

Hierarchical Intelligent Control Method for Mineral Particle Size Based on Machine Learning

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Computer Science, Artificial Intelligence

Deep graph feature learning-based diagnosis approach for rotating machinery using multi-sensor data

Kaibo Zhou et al.

Summary: In this study, a deep graph feature learning-based diagnosis approach is proposed for rotating machinery using multi-sensor data. By constructing graph data and utilizing graph convolutional network to extract high-level features, feature fusion for fault classification is achieved. Experimental results demonstrate that this method performs well even with small training datasets.

JOURNAL OF INTELLIGENT MANUFACTURING (2023)

Article Engineering, Chemical

Grinding effect of sodium silicate on muscovite and its mechanism analysis

Chenyu Fan et al.

Summary: In this study, the effect of sodium silicate on the grinding effect of muscovite was investigated. The samples were characterized by FT-IR, SEM, Zeta potential and XPS, respectively. The results indicate that adding sodium silicate in the grinding process of muscovite can significantly accelerate the refinement of muscovite particles, and the surface structure of muscovite is destroyed. This study has some reference significance for improving the production efficiency of muscovite powder and the application of grinding aids.

MINERALS ENGINEERING (2023)

Article Automation & Control Systems

Image-based thickener mud layer height prediction with attention mechanism-based CNN

Chenyu Fang et al.

Summary: This study proposes a mud layer height prediction method based on attention mechanism and convolutional neural network (CNN). By extracting dynamic features and embedding attention mechanisms, more accurate prediction results can be achieved.

ISA TRANSACTIONS (2022)

Article Automation & Control Systems

Siamese Time Series and Difference Networks for Performance Monitoring in the Froth Flotation Process

Hu Zhang et al.

Summary: Accurate and in-time performance monitoring is crucial in industrial processes. However, current methods often overlook the valuable information provided by labeled performance at the previous moment. Therefore, this article proposes an STS-D net that effectively integrates input features at different time steps and labeled performance at the previous moment.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2022)

Article Chemistry, Physical

An HGA-LSTM-Based Intelligent Model for Ore Pulp Density in the Hydrometallurgical Process

Guobin Zou et al.

Summary: This study proposes an intelligent model based on LSTM and HGA to accurately measure the feed ore pulp density in the hydrometallurgical process. The model is successfully applied to an actual thickener case in China and outperforms other models, satisfying the measurement accuracy requirements in the factory.

MATERIALS (2022)

Article Automation & Control Systems

LSTM-based soft sensor design for oxygen content of flue gas in coal-fired power plant

Hongguang Pan et al.

Summary: This paper proposes a method based on LSTM network to estimate the oxygen content in the flue gas of coal-fired power plant boilers, which improves accuracy through model optimization and auxiliary variables. The model is validated through actual application, showing good prediction performance and industrial value.

TRANSACTIONS OF THE INSTITUTE OF MEASUREMENT AND CONTROL (2021)

Article Computer Science, Artificial Intelligence

Surface crack detection using deep learning with shallow CNN architecture for enhanced computation

Bubryur Kim et al.

Summary: The study emphasizes the importance of surface cracks in concrete structures and proposes a shallow CNN architecture for concrete crack detection. By optimizing hyperparameters and training the model, the proposed method achieves a maximum accuracy of 99.8% with minimal computation.

NEURAL COMPUTING & APPLICATIONS (2021)

Article Automation & Control Systems

Feature Reconstruction-Regression Network: A Light-Weight Deep Neural Network for Performance Monitoring in the Froth Flotation

Hu Zhang et al.

Summary: With the rapid development of deep neural networks, a new feature reconstruction-regression network (FR-R net) is proposed to address the challenges of industrial performance monitoring, utilizing feature vector series extraction, feature reconstruction network design, and fully connected regression network to achieve performance monitoring.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2021)

Review Engineering, Electrical & Electronic

A Review on Soft Sensors for Monitoring, Control, and Optimization of Industrial Processes

Yuchen Jiang et al.

Summary: In the past twenty years, there have been numerous research outcomes related to the design and implementation of soft sensors. Various types of soft sensors are essential in modern industrial processes for monitoring, control, and optimization. Advances in theories, techniques, and information infrastructure have improved the performance of soft sensing, but new opportunities also bring new challenges. This work aims to provide a comprehensive review of developments in soft sensors since the year 2000, focusing on the most up-to-date advancements from the perspective of systems and control.

IEEE SENSORS JOURNAL (2021)

Article Computer Science, Information Systems

A Novel and Reliable Framework of Patient Deterioration Prediction in Intensive Care Unit Based on Long Short-Term Memory-Recurrent Neural Network

Tariq I. Alshwaheen et al.

Summary: Early recognition and intervention are crucial in preventing clinical deterioration in ICU patients. A new predictive model based on LSTM-RNN and an optimization model based on GA were proposed in this study, showing significantly better classification performance compared to other studies utilizing deep learning models.

IEEE ACCESS (2021)

Article Engineering, Electrical & Electronic

Online Fault Diagnosis Method Based on Transfer Convolutional Neural Networks

Gaowei Xu et al.

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2020)

Article Computer Science, Information Systems

Deep Dual-Channel Neural Network for Image-Based Smoke Detection

Ke Gu et al.

IEEE TRANSACTIONS ON MULTIMEDIA (2020)

Article Engineering, Chemical

Bayesian Network-Based Modeling and Operational Adjustment of Plantwide Flotation Industrial Process

Hao Yan et al.

INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH (2020)

Article Mathematics, Applied

Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) network

Alex Sherstinsky

PHYSICA D-NONLINEAR PHENOMENA (2020)

Article Automation & Control Systems

Timed key-value memory network for flotation reagent control

Jin Zhang et al.

CONTROL ENGINEERING PRACTICE (2020)

Article Computer Science, Information Systems

Convolutional Recurrent Neural Networks for Glucose Prediction

Kezhi Li et al.

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS (2020)

Article Computer Science, Artificial Intelligence

SRGC-Nets: Sparse Repeated Group Convolutional Neural Networks

Yao Lu et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2020)

Article Computer Science, Information Systems

Artificial Intelligence Image Recognition Method Based on Convolutional Neural Network Algorithm

Youhui Tian

IEEE ACCESS (2020)

Article Geochemistry & Geophysics

Deep Recurrent Neural Networks for Hyperspectral Image Classification

Lichao Mou et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2017)

Review Computer Science, Interdisciplinary Applications

Data-driven Soft Sensors in the process industry

Petr Kadlec et al.

COMPUTERS & CHEMICAL ENGINEERING (2009)

Article Computer Science, Interdisciplinary Applications

A hybrid GA-SQP optimization technique for determination of kinetic parameters of hydrogenation reactions

Behrang Mansoornejad et al.

COMPUTERS & CHEMICAL ENGINEERING (2008)

Article Multidisciplinary Sciences

Reducing the dimensionality of data with neural networks

G. E. Hinton et al.

SCIENCE (2006)