论文部分内容阅读
应用模糊神经网络实现的预测系统通过对历史数据的自适应学习获得初始的模糊预测模型，借助等价结构的ＡＮＮ基于实时数据的梯度信息对系统参数进行ＢＰ训练，具有较强的适应性和自学习能力。以电力短期负荷预测（ＳＴＬＦ）为应用背景，进行了系统化的实验研究，结果表明这一智能化的预测系统的性能是令人满意的．
The prediction system based on fuzzy neural network obtains the initial fuzzy prediction model through the adaptive learning of historical data, and uses the equivalent structure of ANN to carry on the BP training to the system parameters based on the gradient information of real-time data, which has strong adaptability and self- Learning ability. Based on the application of STLF, a systematic experimental study was carried out. The results show that the performance of this intelligent predictive system is satisfactory.