Big data driven ship sheet welding quality prediction method

Abstract

The invention discloses a big data-driven ship sheet welding quality prediction method, and the method comprises the following steps: establishing a framework by utilizing an established internet of things, and carrying out collection and uplink transmission of real-time welding data; carrying out the key data feature optimization on the collected welding quality influence factor data, and completing the data dimension reduction of an initial feature set in the welding big data; through the established BP neural network prediction model optimized by the adaptive simulated annealing particle swarm optimization algorithm, according to the data feature set after data dimension reduction, outputting a ship thin plate welding quality prediction result. According to the method, the SAPSO_BP prediction model is established, the defects that a BP neural network prediction model is prone to falling into local minimum points, low in convergence speed, poor in robustness and the like are overcome, online monitoring of the ship thin plate welding process and accurate prediction of the welding quality are achieved, the prediction result precision is improved, and the prediction efficiency is improved. And a high-reliability reference value is provided for optimization decision-making of a welding process.

Description

technical field [0001] The invention belongs to the technical field of computer integrated manufacturing, and in particular relates to a method for predicting welding quality of ship thin plates driven by big data. Background technique [0002] The shipbuilding industry is an important part of the country's high-end equipment manufacturing industry, and it is also a key application field for promoting the integration of new-generation information technologies such as the Internet of Things, big data, and cloud computing. In the process of shipbuilding, there is gradually a trend of comprehensively promoting the transformation of digitalization, networking, and intelligentization and the upgrading of traditional technologies. Welding technology is one of the most important techniques in shipbuilding, and its welding man-hours generally account for 30% to 40% of the total man-hours of hull construction. In the construction of surface warships and most small and medium-sized s...

AI Technical Summary

Problems solved by technology

[0004] Purpose of the invention: In order to overcome the problems existing in the prior art that cannot meet the development needs of on-line monitoring and accurate prediction of welding quality, provide a big data-driven method for predicting welding quality of ship thin plates

Images