Based on the seawater corrosion data collected from China material environmental corrosion test sites,a forecasting model for the seawater corrosion of carbon steel and low alloy steel was built by employing back-propagation neural network(BP neural network).

The corrosion behavior of hot dip Galvanized(GI),Galfan(GF) and Galvalume(GL) coated steels exposed to seawater tidal zone of Qingdao site was investigated with seawater corrosion test and microscopy morphology analysis.

The results indicated that in immersion zone 5%Al-Zn alloy coating resists well to the seawater corrosion because of its low current density and highly protective products from corrosion.

Formation of cast iron protection film resistant to sea water corrosion;

Research into sea water corrosion of condenser in the refrigeration system

The corrosion potential of 16 Mn steel respectively in the zones of full immersion, tide range and splash is measured by putting the independent test pieces put into sea water corrosion simulation test unit and the couple potential, couple current and their corrosion speed of the electrically connected test pieces in the above 3 zones are also measured.

Considering the limitation of the number of samples and the difficulty of the selection of the suitable number in hidden layer cells during constructing a BP prediction model of marine corrosion system,a combined ANN method with SOM(self-organizing feature map) and RBF(radial base function) was proposed to predict marine corrosion rate.

Application of anti-seawater corrosion concrete in rebuilding gates of Diyong Sluice in Wuchuan City;

A base material of thermal shrinkage is selected through experiments and it is then compounded with a sticky sweat size water to form a seal cartridge of seawater corrosin resistance.