The fracture damage of oil and gas pipelines usually initiates from micro?cracks. The weak magnetic detection method is of practical significance for the detection of microcracks in long distance oil and gas pipelines. However, the microstructure of pipeline microcracks is complex, and the traditional weak magnetic field detection model is difficult to achieve accurate quantitative calculation of pipeline microcracks. Based on the theory of magnetoelectric coupling, a mathematical model of weak magnetic signal of pipeline micro?crack is established. The weak magnetic signal of micro?crack under different excitation conditions is compared and analyzed. The propagation characteristics of micro?crack at different depths and the signal detection characteristics under different lifting values are analyzed and calculated. The results show that the weak magnetic signal generated by the microcrack is much larger than the geomagnetic field, and the difference increases as the increase of the stress value. The weak magnetic signal increases with the increase of stress value. When the critical point of microcrack propagation is reached, the magnetic energy is released due to microcrack propagation, and the weak magnetic signal decreases with the increase of stress value. After microcrack propagation, the magnetic sensitivity of the material decreases, but the linear characteristics are more obvious. The larger the crack depth is, the stronger the weak magnetic signal is, and the damage is more easily detected. With the increase of the lift value, the weak magnetic signal decreases exponentially, and the detection accuracy of the signal in the linear region is the highest.

Due to the complexity and variability of atmospheric and vacuum distillation process, the coupling between process variables is serious, and the direct modeling will increase the difficulty of problem analysis. In order to improve the performance of the model, KPCA algorithm was used to select the variables of the model, and then the processed data were used as the input of the Gaussian process regression (GPR) model, and KPCA?GPR was used to establish the estimation model of the gasoline dry point on the atmospheric tower roof. The method solves the strong nonlinear correlation between different variables, and has the advantages of flexible nonparametric generalization and super?parameter adaptive adjustment. By calculating the empirical confidence interval, not only can the dry point of gasoline be predicted and estimated, but also can do the probability interpretation. The simulation results show that the KPCA?GPR method achieves better estimation results.

With the development of artificial intelligence technology and big data Internet technology, the pipeline leak detection technology is developing in the direction of intelligence. Based on the classification of continuous pipeline leak detection technology and discontinuous pipeline leak detection technology, this paper introduced the principles of various leak detection methods, summarized and analyzed the research status of long?distance oil pipeline leak detection technology at home and abroad. The application of combined oil pipeline leak detection and location technology in long?distance oil pipeline detection was prospected.

The dry point of gasoline on the top of atmospheric tower is closely related to product quality, but it is difficult to measure the gasoline dry point online, and the soft sensor is a technical way to solve the estimation and control prediction of such variables. Due to the complexity of atmospheric and vacuum distillation process, the correlation between the variables increases. In this paper, sparse principal component analysis (SPCA) was introduced into kernel principal component analysis（KPCA） algorithm, and the input variables of the model were selected by sparse kernel principal component analysis（SKPCA） algorithm. The nonlinear dimensionality reduction between data was realized, the principal component structure was simplified, and the sparsity of principal component variables was increased. The selected sparse principal components were used as the input of the least squares support vector machine (LSSVM), and the soft sensor prediction model for the top dry point of atmospheric tower was established. The simulation results show that the SKPCA?LSSVM model has higher prediction accuracy and superior model performance compared with the traditional PCA?LSSVM and KPCA?LSSVM methods.