Quantitative Detection for Gas Mixtures Based on the Adaptive Genetic Algorithm and BP Network

Based on the advantages and disadvantages of genetic algorithm (GA) and artificial neural network (ANN), an optimization model with the adaptive genetic algorithm and the traditional BP neural network is presented for the quantitative detection of gas mixtures. To overcome the disadvantages of ANN with inherent slowly searching rate and partially leading to minimum, the adaptive genetic algorithm is used to get better initial weights and thresholds of the BP network in the early stage, which combines the advantages of genetic algorithm with parallel-computing and strong whole searching capacity. In the later, the network is trained by the error back propagation method. A three-layer 7×18×3 BP network is designed for a group of gas mixtures with five samples. The results show that the convergence speed and the learn precision of adaptive genetic algorithm optimizing neural network are better than that of the traditional BP algorithm, which can make shorter the calculation time three times at the begin of the same weights and thresholds and at the end of global error with the magnitude of 0.00001.The application of GA optimizing BP network to the recognition of gas mixtures is reliable and the method can improve the detection efficiency of gas mixtures, which can give some references for developing intelligent detection apparatus.