By using methyl methacrylate (MMA) as the harder monomer, butyl acrylate (BA) as the softer monomer, acrylic acid (AA) as the functional monomer, acetoacetoxyethyl methacrylate (AAEM) as the crosslinking monomer, tert⁃butyl peroxybenzoate as the initiator, propylene glycol butyl ether as the solvent for prepared self⁃crosslinking acrylate emulsion by free radical solution polymerization and phase inversion, and the emulsion could be self⁃crosslinked after baking at high temperature without additional crosslinking agent. This article mainly studied the influence of acrylic acid, acetoacetoxyethyl methacrylate and curing time on the performance of the polyacrylic resin dispersion and the film property. The results show that the optimized formula is as follows: The dosage of AA and AAEM are 3.5% and 5.0% of the total monomer mass, respectively, and the baking time is 1.0 h at a curing temperature of 180 ℃. FT⁃IR and GPC analysis showed that AAEM was successfully attached to the molecular chain of acrylic resin; SEM and particle size analyzer analysis showed that the TG of the film is latex particles were spherical and uniformly distributed; DSC analysis showed that after the synthesized resin dispersion is significantly increased after the synthesized resin dispersion is baked at high temperature for a period of time.

The channel prediction of Fuyu reservoir has been always highly emphasized. Using the conventional seismic attribute to predict channel is difficult to achieve the precision requirements because of the complex fault and the fast lithofacies phase in Fuyu reservoir. Aiming at this weak problem, the method of combing gray correlation analysis and support vector machines is used to establish a set of technical process which is suitable for the prediction of fluvial reservoirs under complicated geological conditions. In Fuyu test area in X reservoir of Daqing oilfield as an example, firstly, conventional seismic attribute of sedimentary unit dimensionless, obtained by the method of gray correlation analysis of the seismic attribute correlation factor, the greater the degree of correlation, indicating that the response probability of attribute river is higher. On this basis, the optimal correlation factor sequence a accumulation of large properties, first order accumulative sequence is generated, used as the input into the support vector machine training sample, so as to complete construction of support vector machine river forecast model. Drilling confirms that the prediction based on Gray Correlation Support Vector Machine has a larger coincidence rate of drilling. Combined with the superiority of seismic inversion to predict the channel sand boundary, supplemented by data of core, well logging and mud logging data to complete sedimentary microfacies in X Test Area Fuyu reservoir. Meanwhile, drilling further confirms the reliability of predicting channel and then the industrial oil flow well is successfully obtained. The results of comprehensive research show that this method is suitable for high channel prediction accuracy. It can be used as a better channel prediction method under complicated geological conditions.

Fuzzy C-means clustering algorithm is sensitive to initial clustering center and membership matrix and likely converges into the local minimum, so it can not get the best clustering results. A new image segmentation algorithm based on chaos particle swarm and FCM clustering is proposed. The uniform particles are produced by logical self-map function.When it gets into the premature convergence,the algorithm can start the chaos optimization to improve the performance of convergence into the local minimum because of standstill. The experimental results show that the new algorithm has faster convergence and higher accuracy of segmentation.

By use of searching technique of ant colony algorithm, a rough set attribute reduction method based on ACA was proposed. The core was joined in initial pheromone in order to accelerate convergence. Dynamically adjusting the strategy of selection of the paths and the strategy of the trail information updating based on the distribution of the solutions, the algorithm can advance global capability. Experimental results show that the algorithm is effective, and has better convergence speed and stability.

To deal with the prematurity and low convergence speed when the genetic algorithm is used for global optimization, a rough set attribute reduction algorithm based on adaptive GA was proposed. Based on the adaptive crossover operator and mutation operator that adjust the crossover probability and mutation probability of each individual, the selection probability of every individual of the population was optimized in this algorithm. Experimental results show that the algorithm can evidently improve global optimization capability and convergence speed.