Application of genetic-algorithm improved BP Neural Network in automated deformation monitoring

The outlier detection in deformation is always a hard problem to solve. As the requirements on automation and accuracy is becoming stronger and stronger, it is also more and more important to detect and remove the outliers in monitoring observations as fast as possible. In the paper the approximation of nonlinear function mapping relation using Artificial Neural Network (ANN) was introduced, and issues about BP NN were discussed. To overcome the drawbacks of BP NN, Genetic Algorithm (GA) was introduced into the BP method to reduce the shortcomings of BP NN as much as possible. Aiming at the automated deformation monitoring, the GA-improved BP NN greatly raised the converging speed of ANN and preventing the model from reaching local minimum and thus improved the accuracy of model fitting. The results of some examples show that the method is easy for programming, real-time and highly efficient, which applies for automated deformation monitoring.