准确近似聚类算法及其在岸桥拉杆状态监测中的应用

Accurate Approximate Clustering Algorithm and Its Application in the State Monitoring of Crane

为了探究码头岸桥每次作业拉杆的载荷情况,更加准确评估拉杆的使用寿命并确定其维修周期,采用聚类算法与定量统计分析方法,对岸桥拉杆载荷进行分析。考虑到传统K均值算法在处理大规模数据时的局限性,在聚类思想的基础上,提出一种准确近似K均值算法(AAKM)。该算法在聚类数目K的初步确定和提高聚类算法的准确性方面实现了极大的改进,并利用试验结果进行了验证,结果表明该方法对于岸桥载荷状态的识别和工程应用中的监测与评估具有重要意义。

In order to study the crane＇s each work load situation of orbit,service life and determine its maintenance cycle,used clustering algorithm and quantitative statisticalanalysis method,rod load of the crane was analyzed. Considering the limitation of traditional K-means algorithm in dealing with large-scale data,an accurate approximate K-means algorithm （AAKM） wasproposed based on the clustering idea. The accurate of the algorithm in the preliminary determinationand improvement had greatly improved,and was verified by using the experimental resultssignificance for identification of crane load status and the engineering application of monitoring and evaluation.