The paper introduces a numerical internal corrosion rate prediction method into the internal corrosion direct assessment (ICDA) process for wet gas gathering pipelines based on the back propagation (BP), the genetic algorithm (GA) and BP, and the particle swarm optimization and BP artificial neural networks (ANNs). The basic data were collected in accordance with the terms established by the National Association of Corrosion Engineers in the Wet Gas Internal Corrosion Direct Assessment (WG-ICDA) SP0110, and the corrosion influencing factors, which are the input variables of the ANN model, are identified and refined by the grey relational analysis method. A total of 116 groups of basic data and inspection data from seven gathering pipelines in Sichuan (China) are used to develop the numerical prediction model. Ninety-five of the 116 groups of data are selected to train the neural network. The remaining 21 groups of data are chosen to test the three ANNs. The test results show that the GA and BP ANN yield the smallest number of absolute errors and should be selected as the preferred model for the prediction of corrosion rates. The accuracy of the model was validated by another 54 groups of excavation data obtained from pipeline No. 8, whose internal environment parameters are similar to those found in the training and testing pipelines. The results show that the numerical method yields significantly better absolute errors than either the de Waard 95 model or the Top-of-Line corrosion model in WG-ICDA when applying the approach to specific pipelines, and it can be used to investigate a specific pipeline for which the data have been collected and the ANN has been developed in WG-ICDA SP0110.

The types of pipeline used in oil and gas stations is diverse, and it is difficult to comprehensively and accurately measure pipeline stress using a single detection method. Non-contact pipeline magnetic detection (NPMD), metal magnetic memory, ultrasonic stress measurement (USM) and ultrasonic thickness measurement (UTM)constitute a collaborative detection strategy for station pipelines. The pipeline magnetic abnormal evaluation parameter N is derived according to the sensor arrangement in NPMD devices. The magnetic field distribution based on different extraction heights is determined by the magnetic charge model and the experimental results, and a feature parameter E is constructed that can characterize the degree of stress concentration. The pipeline stress concentration points can be quickly determined in accordance with N and E . Reference stress values can be measured using USM and UTM. Monitoring is implemented at the stress concentration points, and the true stress values at the stress concentration points of the pipeline are established by combining the stress detection results. The collaborative detection method is applied to an oil and gas station, and two stress concentrations of 186.7 and 211.6 MPa are identified, respectively. The stress at the excavation pit is confirmed to be 196 MPa based on the monitoring data. Based on collaborative detection and on-line monitoring, fast and efficient collaborative detection and real-time mastering of station pipeline stress are achieved.

Cutting mixed oil in product pipelines has a great influence on the economy of the pipeline operation processes. The reasonable prediction of CDMS (the concentration distribution in the mixed segment) is important for cutting mixed segments. The classical model cannot explain the tailing phenomenon well which should not be neglected during operation processes. Based on Fick’s diffusion law, a new model for calculating the diffusion coefficient is proposed in this article, which originates from the essence of the diffusion phenomenon and considers the effects of both physical properties of oil products and the turbulence. At the same time, the dynamic fluid equilibrium model of CDMS near the pipe wall is given which has considered the adsorption effect of wall roughness. Based on these two factors, a novel numerical model for simulating the quantity of tailing oil is proposed, which is solved via the characteristic method and the finite difference method. The effects of different physical properties, as well as the adsorption, on both LFMS (the length of the front of the mixed segment) and LTMS (the length of the tail of the mixed segment), are analyzed. The comparison between the simulation results and the experimental data is utilized to validate the proposed numerical model. The simulation results show that the novel model can well describe the mixed segment tailing phenomenon and also explain the mixing essence of two miscible but dissimilar fluids in the pipeline more clearly. To sum up, this model can provide theoretical guidance for the prediction of CDMS and cutting process in practical operation processes; therefore, more economic benefit can be obtained.