On the selection of aircraft noise-distance characteristic(NPD) regression model,By analyzing the characteristic of NPD curves,four regression models such as linear model,polynomial model,neural network and support vector machine(SVM) are nominated,and their effect are studied and compared with an example of F16 fighter plane’s NPD data.The results indicate that SVM model is the stablest and accuratest while other models work well in interpolation but not in extrapolation.

To predict the erosion and abrasion of high bore pressure tank gun barrel, the least square support vector machine （LSSVM） algorithm was used. Based on the gun firing test data, the prediction model for barrel’s erosion and abrasion was established. It was adopted to predict the wear increment of gun barrel. The results show that the prediction values given by the model coincide with the measured data better, and the model can predict the barrel’s wear accurately and rapidly.

Aiming at the difficulties of residual life prediction for barrel of tank gun under high chamber pressure,combined with characteristics of small volume of data and nonlinearity of tank ball firing experiment, model of residual life prediction for barrel of tank gun based on LS-SVM is built, and parameter selection method of the model is obtained. Based on firing experiment of a certain tank gun, model of residual life prediction for barrel of tank gun is validated. The results show that the residual life prediction effect with the model is good.

A technique condition forecasting model of military equipment based on fractal theory and support vector regression(SVR)was presented.Take the feature data that reflect equipment operation condition as a time series,techniques of phase space reconstruction were used to calculate the minimum embedding dimension,which regard it as the input nodes of support vector regression.The forecasting model was built up after samples series training.The case study of equipment vibration signal forecasting shows that,take the time series minimum embedding dimension as the input nodes of support vector regression,the model is optimal.Compared with true value,the SVR forecasting result is estimated with less error,the model can better meet the requirement of equipment technique condition analysis and forecasting.

A new strategy of finance management is put forward in the oil field at present, which combines budget control and cost control. This paper researches this strategy and designs a system and realizes the system based on B/S and Java Applet. At last, through practice, it proves that it can meet the need of finance decision support in the oil field and lower costs and improve the efficiency of production further.