Bilingual teaching is the inevitable reform and development trend of higher education, and it is a very important job for us to evaluate the bilingual teaching quality. Currently, we do not have an effective evaluation system for bilingual teaching quality. In this study, the factors which affect bilingual teaching quality are analyzed and the evaluation index system of bilingual teaching quality in universities is established firstly. Then, a knowledge rule mining method for the evaluation of bilingual teaching quality in universities based on an improved genetic algorithm is proposed. In the algorithm, selection operator, dual crossover operator and dual mutation operator are used to generate new knowledge rules. Knowledge rules are evaluated by their accuracy, coverage and reliability. Experimental results show that this knowledge rule mining method is feasible and valid.

Aiming at BP neural network algorithms limitation such as falling into local minimum easily and low convergence speed, an improved BP algorithm with two times adaptive adjust of training parameters (TA-BP algorithm) was proposed. Besides the adaptive adjust of training rate and momentum factor, this algorithm can gain appropriate permitted convergence error by adaptive adjust in the course of training. TA-BP algorithm was applied in fault diagnosis of power transformer. A fault diagnosis model for power transformer was founded based on neural network. The illustrational results show that this algorithm is better than traditional BP algorithm in both convergence speed and precision. We can realize a fast and accurate diagnosis for power transformer fault by this algorithm.

In order to solve knapsack problems efficiently, an improved genetic algorithm based on adaptive evolution in dual population (called DPAGA) is proposed. In DPAGA, the new population produced by selecting operation is regarded as main population. The population composed by the individuals washed out by selecting operation is regarded as subordinate population. The individual evolution strategy of main population is different from that of subordinate population. The crossover operators and mutation operators are all adjusted non-linearly and adaptively. DPAGA is used to solve knapsack problems. The experimental results show that its convergence speed and solution quality are all better then that of simple genetic algorithm. It is also suited to solve other optimization problems.

In this study, the evaluation index system of library service quality is established and the representation method of knowledge rule is analyzed firstly. Then, a knowledge rule mining method for the evaluation of library service quality based on an improved genetic algorithm is proposed. In the algorithm, selection operator, help operator, crossover operator and mutation operator are used to generate new knowledge rules. Knowledge rules are evaluated by their accuracy, coverage and reliability. Experimental results show that this knowledge rule mining method is feasible and valid. It is helpful for us to evaluate the library service quality fairly and objectively.

In this study, a genetic algorithm simulating human reproduction mode (HRGA) is proposed. The genetic operators of HRGA include selection operator, help operator, crossover operator and mutation operator. The sex feature, age feature and consanguinity feature of genetic individuals are considered. Two individuals with opposite sex can reproduce the next generation if they are distant consanguinity individuals and their age is allowable. Based on this genetic algorithm, an improved evolutionary neural network algorithm named HRGA-BP algorithm is formed. In HRGA-BP algorithm, HRGA is used firstly to evolve and design the structure, the initial weights and thresholds, the training ratio and momentum factor of neural network roundly. Then, training samples are used to search for the optimal solution by the evolutionary neural network. HRGA-BP algorithm is used in motor fault diagnosis. The illustrational results show that HRGA-BP algorithm is better than traditional neural network algorithms in both speed and precision of convergence, and its validity in fault diagnosis is proved.