Abstract | ||
---|---|---|
When High-speed train runs, the strength of data field signal determines whether the CIR device on the High-speed train can work normally. While proper functioning of the CIR device affects the normal operation of the train deeply. The K-MEANS-analysis-model proposed in this paper, applies the K-MEANS method of machine learning to train numerous data duplicate which generated by different locomotives that run in the same interval. In this way, we obtain the duplicate of normal field strength values in this interval. We employ it and combine with the mean-algorithm and the difference-algorithm to analysis the malfunction reason accurately. In this way we have reduced the run-times of the field inspection vehicle successfully, so as to cut down the operating costs effectively. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/ICPHM.2017.7998328 | 2017 IEEE International Conference on Prognostics and Health Management (ICPHM) |
Keywords | Field | DocType |
High-speed railway,Data Field strength,CIR device,Machine Learning,Big data | Data field,k-means clustering,Algorithm design,Simulation,Communications system,Real-time computing,Feature extraction,Field strength,Engineering,Cluster analysis,Statistical classification | Conference |
ISBN | Citations | PageRank |
978-1-5090-5711-5 | 0 | 0.34 |
References | Authors | |
2 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jia-ming Fan | 1 | 0 | 0.34 |
Jian-ping Fan | 2 | 0 | 0.34 |
Feng Liu | 3 | 46 | 10.34 |