Papers by Keyword: Immune Genetic Algorithm

Abstract: In this paper, we address the project scheduling problem with the aim of making the best use of people's talents while minimizing project makespan and the amount of wasted resources. The purpose of proposing this problem is to assist project managers to improve the quality of products and save cost. To solve this problem, we also proposed an immune genetic algorithm (IGA). This algorithm designs feasible schedule for projects. By designing computational experiments carried out on j60 from PSPLIB, we evaluate the performance of proposed IGA as well as compare it with traditional GA. It turns out that proposed IGA performs much better in the aspect of improving diversity and minimizing makespan, which provides more diverse and effective solutions.

Abstract: Web-based learning system is a means of learning-oriented construction and education informationization for vocational & technical colleges at present. Basing on the analysis of the instructors' learning characteristics, the author has designed an intelligent web-based learning system which can be used for learning management, learning evaluation and discussion. The system has been realized by .NET Platform and Immune Genetic Algorithm.

Abstract: As for a wide variety of faults that happen frequently during the aluminum electrolysis process, a new method of multi-fault diagnosis method using neural network based on immune genetic algorithm (IGA) is proposed. IGA has the abilities of searching for global optima and better convergence. By applying these abilities and the diagnosis characteristics of the aluminum electrolysis process, the study builds the layered fault diagnosis model structure . The results of simulations show that this model is of the better ability of convergent on whole solution space and the capacity of fast learning than that of the traditional fault diagnosis model, therefore, the method worths applying widely.

Abstract: This paper designs the multilayer feed-forward neural network based on the immune genetic algorithm to solve the problem that BP algorithm is prone to get the local minimum in the failure diagnosis system. It is of both the learning ability and robustness of the neural network, as well as the strong global random searching ability of the immune genetic algorithm. The simulation results indicate the neural network can fulfill failure diagnosis of the complicated production better.

Abstract: Aiming to guide the manufacture process of carbon fiber and obtain high properties productions, we propose a hybrid algorithm named father-keeping immune genetic algorithm based on back propagation neural network (FKIGA-BP) as a properties prediction model. The present study also compares it with BP neural network forecasting method. It shows better search precision and convergence efficiency. The prediction results are consistent with the practical experiment data.

Abstract: The two hybrid algorithms of back propagation neural network and immune genetic algorithm were used in the optimum design of the hot pressing parameters of Ti(C, N) matrix nano-composite ceramic die material. The BP algorithm could set up the relationship well between the hot pressing parameters and single mechanical property. Compared with the experimental value, the relative error of fracture toughness, hardness and flexural strength is only 4.65%, 0.23% and 4.05%, respectively. After analyzed the predicted results, the best predicted results were the sintering temperature was about 1455°C and the holding time was 11 min. Under these hot pressing parameters, the best flexural strength and the best fracture toughness of the material could be obtained.

Abstract: The immune genetic algorithm is a kind of heuristic algorithm which simulates the biological immune system and introduces the genetic operator to its immune operator. Conquering the inherent defects of genetic algorithm that the convergence direction can not be easily controlled so as to result in the prematureness；it is characterized by a better global search and memory ability. The basic principles and solving steps of the immune genetic algorithm are briefly introduced in this paper. The immune genetic algorithm is applied to the survey data processing and experimental results show that this method can be practicably and effectively applied to the survey data processing.

Abstract: To solve the task allocation of multi-robot systems, a novel explosive evolution - based immune genetic algorithm (EIGA) is presented. On the basis of the immune genetic algorithm (IGA), the population number of EIGA is increased quickly through explosive evolutionary mode, and then the better individuals are selected through the comparison of allelic genes, which can improve the population quality with the premise of ensuring the population diversity, and enhance the search speed and search precision of EIGA. Compared with the IGA and genetic algorithm (GA), the simulation results indicate that the proposed EIGA is characterized by quick convergence speed, high optimization precision and good stability, and the tasks are allocated rationally and scientifi-cally which realizes the task cooperation of multi-robot systems well.

Abstract: As a bridge links the upper enterprise planning system and the lower shop floor control system, enormous real-time information interact in shop floor, which poses great difficulty for scheduling of manufacturing execution system(MES). To meet the requirement of MES agility in the volatile information environment, dynamic scheduling becomes one of most widely used methods. In this paper, a modified immune genetic algorithm which incorporates artificial immune mechanism into genetic algorithm is presented to solve dynamic job shop scheduling problems. Owing to its good solving capability and computing speed, the algorithm could utilize real-time production information to generate predictive and reactive scheduling solutions. At last, the algorithm is applied in a MT10×10 job shop proved to be effective in obtaining better solutions than traditional genetic algorithm.

Abstract: It is very important to predict ground settlement and provide effective dada for construction on soft soil foundation. There are several prediction methods.However, back analysis method is identified as the most effective method in all these methods. The most primarily used method in back analysis methods is optimization algorithm. In this paper, to realize accurate prediction and calculation of soft soil foundation settlement, an improved immune genetic algorithm is presented by introducing immune mechanism to genetic algorithm. A example was given and illustrated that this algorithm can greatly improve calculation speed and accuracy in predicting soft soil foundation settlement.