Ata uhi

Machine learning in manufacturing : quality 4.0 and the zero defects vision /

This book explores the integration of artificial intelligence (AI) in manufacturing, focusing on Quality 4.0 and the Zero Defects vision. It discusses the evolution of modern quality control methods, the rise of Quality 4.0, and the application of machine learning techniques to improve the quality o...

Whakaahuatanga katoa

I tiakina i:
Ngā taipitopito rārangi puna kōrero
Ngā kaituhi matua: Escobar, Carlos A.,eauthor, Morales-Menendez, Ruben (Author)
Hōputu: Tāhiko īPukapuka
Reo:Ingarihi
I whakaputaina: Amsterdam, Netherlands ; Cambridge, MA, United States : Elsevier, [2024]
Ngā marau:
Machine learning.
Artificial intelligence > Industrial applications.
Manufacturing industries.
Apprentissage automatique.
Intelligence artificielle > Applications industrielles.
Industrie manufacturière.
Artificial intelligence > Industrial applications
Machine learning
Manufacturing industries
Urunga tuihono:ScienceDirect
Ngā Tūtohu: Tāpirihia he Tūtohu
Kāore He Tūtohu, Me noho koe te mea tuatahi ki te tūtohu i tēnei pūkete!
Rārangi ihirangi:
  • Front Cover
  • Machine Learning in Manufacturing
  • Machine Learning in Manufacturing
  • Copyright
  • Contents
  • Biographies
  • Preface
  • 1
  • Introduction
  • 1.1 Motivation
  • 1.2 Smart manufacturing
  • 1.2.1 Technologies
  • 1.2.2 Building blocks
  • 1.2.3 Characteristics
  • 1.2.4 Research areas
  • 1.3 Evolution of modern quality control in manufacturing
  • 1.4 Breakdown of traditional quality control methods
  • 1.5 The rise of quality 4.0
  • 2
  • The technologies
  • 2.1 Artificial intelligence
  • 2.1.1 Machine learning
  • 2.1.1.1 Desirable characteristics of ML projects
  • 2.1.2 ChatGPT for quality 4.0
  • 2.2 Cloud storage and computing
  • 2.2.1 Cloud framework for quality 4.0
  • 2.2.2 Data lake, data warehouse, and database
  • 2.3 Industrial internet of things
  • 2.3.1 The manufacturing things
  • 2.3.1.1 Smart sensors
  • 2.3.1.2 Actuators
  • 2.3.2 Process monitoring and quality control in manufacturing
  • 3
  • The data
  • 3.1 Big data
  • 3.2 Manufacturing big data
  • 3.3 Transforming big data into a learning data
  • 3.3.1 Data frame
  • 3.3.2 Learning data sets
  • 3.3.2.1 Recommendations on data splits
  • 3.3.2.2 Type of data
  • 3.4 Binary classification of quality data sets
  • 3.4.1 Data annotation
  • 3.4.2 BCoQ data sets examples
  • 4
  • Classification
  • 4.1 Binary Classification
  • 4.2 Binary classification of quality
  • 4.3 Classification errors
  • 4.3.1 Alpha and beta errors
  • 4.3.2 Metrics of classification performance
  • 4.4 Empirical case study on classification metrics
  • 4.5 Binary patterns
  • 4.5.1 Discriminative information
  • 4.5.1.1 Virtual case study one-3D pattern
  • 4.5.1.2 Virtual case study two-separation
  • 5
  • Machine learning theory
  • 5.1 Overfitting and underfitting
  • 5.2 Learning curves
  • 5.3 Curse of dimensionality
  • 5.4 Early stopping
  • 5.5 Loss function for binary classification
  • 5.6 Summary
  • 6
  • Feature engineering
  • 6.1 Feature creation
  • 6.2 Feature selection
  • 6.3 Feature visualization
  • 6.4 Feature preprocessing
  • 6.4.1 Feature imputation
  • 6.4.2 Feature permutation
  • 6.4.3 Outlier analysis
  • 6.4.4 Feature transformation
  • 6.5 Summary
  • 7
  • Classifier development
  • 7.1 Modeling paradigms
  • 7.1.1 Statistical modeling versus machine-learning modeling
  • 7.1.2 Observational data versus experimental data
  • 7.1.3 Data snooping
  • 7.1.4 Accuracy versus interpretability
  • 7.1.5 Model selection
  • 7.2 Machine-learning algorithms
  • 7.2.1 Hyperparameter optimization
  • 7.2.2 Artificial neural networks
  • 7.2.2.1 Fully connected networks
  • 7.2.2.2 Convolutional neural networks
  • 7.2.3 Regularization for artificial neural networks
  • 7.2.3.1 Dropout
  • 7.2.3.2 L1 regularization
  • 7.2.3.3 L2 regularization
  • 7.2.4 Logistic regression
  • 7.2.5 Tree models
  • 7.2.5.1 Random forest
  • 7.2.6 XGBoost
  • 7.2.7 Classification threshold definition
  • 7.2.7.1 ROC curve for finding the optimal threshold
  • 7.3 Classifier fusion

Ngā tūemi rite