Research On Corrosion Prediction Of Marine Engineering Based On Big Data Technology

Corrosion behavior is the most common phenomenon in nature,and the corrosion behavior of Marine engineering materials is an important part of it.Corrosion behavior of materials will bring two kinds of hazards: safety hidden danger and economic loss.Therefore,improving the corrosion control level of engineering materials and reducing the impact of corrosion behavior on engineering materials has become a global concern.At present,scientific information technology is developing rapidly,including the Internet,big data and other technologies.The world is currently sweeping a wave of information technology with "big data technology" as the mainstream,taking this opportunity to carry out the construction of visualization platform for prediction of big data corrosion in Marine engineering.The visual platform adopts computer network technology to display to the staff in the form of interface,which reduces the construction cost of the platform and eliminates the need to develop client software,greatly reduces the cost of development and later maintenance,and makes the business expansion simple and convenient.The operation interface is a standard web interface,which is friendly,simple and easy to operate.The sharing function of corroding data can be realized based on big data technology.At the same time,a corrosion prediction model was embedded in the platform.In order to improve the prediction accuracy of the corrosion rate of Marine engineering materials,a prediction model of the corrosion rate of Marine engineering based on genetic algorithm(GA)optimization back propagation(BP)neural network was proposed.The weights and thresholds of BP neural network are optimized by genetic algorithm,and the optimized BP neural network is used to predict the experimental data.GA-BP model selected representative data of 2Cr1312 stainless steel,Q235 B carbon steel and 6082 aluminum alloy as basic Marine engineering materials for the test.The error ofprediction results was smaller than that of the traditional BP neural network,and the network training time was shortened and the prediction accuracy was improved.In this paper,the Hadoop big data technology provides a strong guarantee for the field of ocean engineering corrosion,and a visualization platform for the prediction of ocean engineering corrosion big data is established by using data processing,data analysis,data visualization and data prediction functions.The visualization platform is to big data technology,database technology,Marine engineering data of corrosion and corrosion prediction model,the combination of from the concrete Marine engineering material corrosion big data management,has a good application significance and use value,can get considerable economic benefits,the realization of the integrated control of corrosion has a certain role in promoting.And in the study of corrosion prediction of Marine engineering materials,it can control the corrosion behavior of Marine engineering materials,reduce its negative impact,and can be extended,which has certain significance in practical application and promotion.