声明
CHAPTER 1:Machine Learning
1.1. Introduction
1.2. Challenges of using Machine learning
1.3. Application of Machine Learning
1.4. Overview of Machine Learning algorithm
1.5. Proposal and the Objectives of the thesis
1.6. Thesis Outline
CHAPTER 2: A quantitative method for assessing smoke associated molecular damage in lung cancers
2.1. Lung cancer
2.2. Methods
2.3. Concluding remarks
CHAPTER 3: Fault detection and diagnosis using kernel PCA and KDE
3.1. Overview of Process Monitoring
3.2. Kernel Principal Component Analysis
3.3. Kernel function
3.4. Kernel tricks
3.5. Kernel density estimation
3.6. KPCA-KDE based fault diagnosis
3.7. Application study
3.8. Fault detection performance results
3.9. KPCA-KDE fault diagnosis performance
CHAPTER 4: Improved KPCA for fault detection and diagnosis using Ensemble learning and Bayesian Inference.
4.1. Ensemble KPCA–Bayes for process monitoring
4.2. Process monitoring strategy based on EKPCA-Bayes
4.3. Fault detection results and discussions
4.4. EKPCA-Bayes based contribution plot results and discussions
CHAPTER 5:Conclusions
参考文献
Participative papers
致谢
天津大学;
