| High sour gas well mining is strength increasing with the rapid development of national economy, while the deposition of elemental sulfur corrosion of pipeline is quite serious. The general corrosion resistant method is welding monolayer or multilayer of nickel-based alloys on the internal surface of pipeline. Inconel 625 wire and X65 steel is commonly used materials in resources exploitation, predicting welding quality of X65 steel pipe inner surface surfacing Inconel 625 nickel base alloy in order to achieve the good mechanical properties and corrosion resistance ability is very necessary. In order to make welded Inconel 625 keep good ability of resistance to pitting corrosion and stress corrosion, the dilution rate of the layers welded by Inconel 625 alloy must be strictly controlled.Nickel-based alloy welding is a complex process of multivariable coupling and a clear welding process window is not necessarily obtained only through limited process experience or trial and error. However, based on the limited process test, effective mathematical modeling algorithm can be adopted to predict the suitable process window, which is a reasonable technological approach.The current welding process prediction algorithm cannot satisfy the applicability, reliability and efficiency of algorithm design principles. According to the requirements of the project, set up the error Back Propagation(BP) network model of the 5-8-3 structure with arc length, welding current, welding speed and wire feed speed and protection gas flow rate as input, weld width and weld height and the dilution rate after surfacing as output. Particle Swarm Optimization(PSO) was used to optimize the BP network to get the optimal weights and threshold to predict the quality of Inconel 625 nickel-based alloy surfacing X65 steel after welding. The results show that the PSO+BP algorithm has higher accuracy compared with the single BP algorithm, and is more efficient than Genetic optimizing BP network(GA+BP) algorithm. To contrast the optimal weights are optimized by PSO and Chebyshev direct method, it is concluded that coincided basically with the weights of the two models. At the end of the paper, with the dilution rate function ?=f(arc length, welding current, wire feed speed) ?5% as the target, welding process parameters-four dimensional function image of the dilution rate is established on the basis of the simulation calculation results of the model to predict the welding process window which meets the engineering requirements(? ?5%). Within the process window, welding the dilution rate of the simulation forecast is 2.55%, and the relative error is about 0.8% compared with the welding test results(3.32%) which reach the requirement of controlling Inconel 625 alloy dilution rate.When the welding location is for horizontal welding, arc length of welding is less than 5 mm to avoid causing drop prolapse. According to rule of the mathematical model, the optimal welding process parameters of hot wire TIG welding are obtained and used in finite element analysis. It is concluded that the temperature field and stress field of the X65 steel pipe surfacing Inconel 625 nickel-based alloy. The results show that it can have a better fusion welding interface and satisfy the requirement of welding quality when the hot wire welding technology parameter is: 5 mm(arc length), 150A(welding current), 35A(hot wire current), 18cm/min(welding speed), 105cm/min(wire feed speed), 16L/min(shielding gas flow rate). |
PDF Full Text Request