Control Chart Pattern Recognition of Sheet Metal Cutting Data in Shipbuilding Based on XGBoost

Abstract

The accuracy of sheet metal is very important for the accuracy control of shipbuilding. When the sheet metal is cut in shipbuilding process, the actual dimension of sheet metal will deviate from the design dimension due to the influence of various factors. Therefore, recognizing the pattern of sheet metal cutting data accurately plays a very important role to improve the quality of a ship. In this paper, a method based on XGboost is proposed to recognize the pattern of sheet metal in sheet metal cutting process. By using statistical features and shape features of control chart as the input of the pattern recognition model, the pattern of the variation control chart can be recognized. A comparative study between statistical features, shape features and combined features is implemented, and the practicability of the proposed intelligent method was demonstrated by comparing the pattern recognition effect of Support Vector Machine(SVM), Random Forest(RF) and XGboost. The result shows that XGboost has a good recognition effect for control chart pattern recognition of sheet cutting data.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 5 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.