In order to improve effectively the accuracy rate and reliability of remaining oil distribution forecast in oil field,a new model is proposed,which utilizes the merits of BP neural network combination model and two-level D-S evidence reasoning model and avoids their demerits.

An algorithm of combined BP neural network data mining based on fuzzy clustering;

This paper introduces an algorithm of combined BP neural network data mining based on fuzzy clustering,and produces the combined BP neural network model and improved Heuristicbp algorithm,then puts this algorithm into mathematical function-value prediction,and gets the purpose of short training-time and high predicting-precision.

The soft sensor is realized by combined BP neural network.

Based on financial indicators and corporate governance indicators, the paper develops two disclosure fraud detection models by applying the Logistic regression and hybrid BP neural network method respectively.

Analysis of lateral deformation of deep excavation based on back propagation neural network and fuzzy logical control;

Reliability analysis of distributed sensor network based on back propagation neural network;

According to its features a short-term load forecasting model is built in which the autoregressive integrated moving average (ARIMA) is integrated with back propagation neural network (BPNN).