Identification of Index Value for Fatigue Features Using K-Means Clustering Approach

This paper focuses on feature classification using data segmentation and clustering for fatigue strain signal. The value of fatigue damage and kurtosis was used for data segmentation analysis. The K-Means clustering technique is applied for data clustering approaches. The objective function after that was calculated in order to determine the best numbers of groups after the clustering approach. Through this method the average distance of each data in the group from its centroid is calculated. Then, the fatigue failure indexes were generated from the best number of group that has been acquired. Based on four data collect from D1 road, the index value generated is not the same for all of data because due to K-Mean clustering, the best group is different for each of the data used. The maximum indexes generated and namely the index 4 for D1 road. Due to the road surface condition, higher distributions of the best groups give higher values of index and reflect to higher fatigue damage experienced by the suspension system.