声明
Acknowledgement
摘要
ABSTRACT
Preface
1 Introduction
1.1 Background and Significance
1.2 National and International Researches Status
1.3 Dissertation Outline
2 Maintenance Management and Related Techniques
2.1 Maintenance Management
2.1.1 Run to Failure Management
2.1.2 Preventive Maintenance
2.1.3 Predictive Maintenance
2.2 Predictive Maintenance via Big Data Technology
2.3 Case Study-Predictive Maintenance Keep Trains Rolling
2.4 Data Mining
2.4.1 Data Mining Process
2.4.2 Data Mining Techniques
2.5 Hadoop Framework
2.6 Apache Spark Ecosystem
3 Apriori Algorithm and Optimization
3.1 Association Rule Analysis
3.1.1 Itemset and Support Count
3.1.2 Frequent Itemset Generation
3.1.3 Brute-Force Approach
3.2 Apriori Principle
3.2.1 Apriori Algorithm
3.2.2 Rule Generation in Apriori Algorithm
3.2.3 Pseudocode of Rule Generation
3.3 Limitation of Apriori Algorithm
3.4 Optimization Techniques
3.4.1 Ant Colony Optimization
3.4.2 Space-Efficient(The Bloom Filter)
3.5 Proposed Implementation of Improved Apriori Algorithm
4 Experimental Results of Improved Apriori
4.1 Experimental Data Source Analyse
4.2 Experimental Dataset Preprocessing
4.2.1 Data Cleaning
4.2.2 Remove Empty or Null Data
4.2.3 Transformation of Data
4.3 Systems Specifications
4.4 Steps Involved in Experiment
4.5 Results of EMU Fault Association Rules
4.5.1 Rules Generation
4.6 Performance Evaluation
5 Conclusion and Future Work
References
Author Profile and Research Achievements Obtained during the Study for A Master’s Degree
Data for the Master’s Thesis