将免疫算法与神经网络理论相结合,提出了免疫神经网络预报模型以预报油库油气浓度。该模型首先用历史数据对网络进行训练,然后利用训练好的模型进行油气浓度的趋势预测,最后结合某油气预报实例检验了免疫神经网络模型的可行性。结果表明,该智能预报模型能够较好地识别油气扩散的变化规律,预报精度明显高于神经网络模型。 Combining immune algorithm with neural network theory, an immune neural network prediction model is proposed to predict oil and gas concentration in oil depots. The model first uses the historical data to train the network, and then uses the trained model to predict the trend of oil-gas concentration. Finally, the feasibility of an immune neural network model is tested with an example of a hydrocarbon forecast. The results show that the intelligent forecasting model can better identify the variation of oil and gas diffusion, and the prediction accuracy is obviously higher than that of the neural network model.