Abstract: A novel forecasting model of petroleum futures price based on PSO-BP under chaos theory is proposed.The experiment on the prediction of petroleum futures recorded in New York Mercantile Exchange is carried out.BP neural network prediction is also applied to predict petroleum futures prices time series.The results indicate that the best precision of fitting and forecasting can be obtained with PSO-BP prediction model，and PSO-BP prediction model outperforms BP network prediction model.

Key words: chaos theory, prediction, petroleum futures, Back Propagation（BP）, Particle Swarm Optimization-Back Propagation（PSO-BP）

摘要： 建立了基于混沌理论下混合型PSO-BP模型，并运用此模型对纽约商品交易市场的原油期货价格数据进行了预测，并将预测结果与BP神经网络的预测结果进行了对比。结果表明混沌理论下混合型PSO-BP模型比单纯的BP模型具有较高的拟合度以及预测精度。

关键词: 混沌理论, 预测, 原油期货, BP模型, 混合PSO-BP模型