Acidic Welding Research And Development, Intelligent Expert System

The frame of the expert system of acidity electrodes (WMPS) has been designed. There are four modules: material recording, electrodes properties prediction, quality management and knowledge consultation. A Windows standard interface has been developed with Visual Basic. It is very convenient and practicable.Based on the Artificial Neural Network, the E4303 acidity electrodes are studied in the electrodes properties prediction module. After tracing the production, the stylebook data has been collected. A mechanical properties prediction model for weld metal was built upon the production data. In the model, the content of Mn, C of electrode (including covering and core wire) are used as the input of network, and the mechanical properties of weld metal are used as output of network. In the research, a back propagation algorithm is used as a neural network's learning rule. Based on the result of network's estimating, the prediction of electrode property can be realized. The result shows: There are good correlations between the predicted results and the experimental data.WMPS has established the integrated database. It can add, demand and analyze the electrodes information. It offers an intelligent means to welding material design, production and management. It is not only suitable for acidity electrodes, but also for others. WMPS has been tested well, it can run effectively.