当前位置:
X-MOL 学术
›
Atmosphere
›
论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Atmospheric PM2.5 Prediction Based on Multiple Model Adaptive Unscented Kalman Filter
Atmosphere ( IF 2.9 ) Pub Date : 2021-05-07 , DOI: 10.3390/atmos12050607 Jihan Li , Xiaoli Li , Kang Wang , Guimei Cui
Atmosphere ( IF 2.9 ) Pub Date : 2021-05-07 , DOI: 10.3390/atmos12050607 Jihan Li , Xiaoli Li , Kang Wang , Guimei Cui
The PM concentration model is the key to predict PM concentration. During the prediction of atmospheric PM concentration based on prediction model, the prediction model of PM concentration cannot be usually accurately described. For the PM concentration model in the same period, the dynamic characteristics of the model will change under the influence of many factors. Similarly, for different time periods, the corresponding models of PM concentration may be different, and the single model cannot play the corresponding ability to predict PM concentration. The single model leads to the decline of prediction accuracy. To improve the accuracy of PM concentration prediction in this solution, a multiple model adaptive unscented Kalman filter (MMAUKF) method is proposed in this paper. Firstly, the PM concentration data in three time periods of the day are taken as the research object, the nonlinear state space model frame of a support vector regression (SVR) method is established. Secondly, the frame of the SVR model in three time periods is combined with an adaptive unscented Kalman filter (AUKF) to predict PM concentration in the next hour, respectively. Then, the predicted value of three time periods is fused into the final predicted PM concentration by Bayesian weighting method. Finally, the proposed method is compared with the single support vector regression-adaptive unscented Kalman filter (SVR-AUKF), autoregressive model-Kalman (AR-Kalman), autoregressive model (AR) and back propagation neural network (BP). The prediction results show that the accuracy of PM concentration prediction is improved in whole time period.
中文翻译:
基于多模型自适应无味卡尔曼滤波的大气PM2.5预测
下午 浓度模型是预测PM的关键 专注。在大气PM预测中 基于预测模型的浓度,PM的预测模型 通常无法准确描述浓度。对于下午 在同一时期的浓度模型中,该模型的动态特性将在许多因素的影响下发生变化。同样,对于不同的时间段,相应的PM模型 浓度可能有所不同,并且单个模型无法发挥相应的预测PM的能力 专注。单一模型导致预测准确性下降。提高PM的精度 在该解决方案中的浓度预测中,提出了一种多模型自适应无味卡尔曼滤波(MMAUKF)方法。首先,PM 以一天中三个时间段的浓度数据为研究对象,建立了支持向量回归(SVR)方法的非线性状态空间模型框架。其次,将三个时间段内的SVR模型的帧与自适应无味卡尔曼滤波器(AUKF)组合以预测PM 接下来一个小时的浓度。然后,将三个时间段的预测值融合到最终的预测PM中 贝叶斯加权法计算浓度。最后,将所提出的方法与单支持向量回归自适应无味卡尔曼滤波器(SVR-AUKF),自回归模型-卡尔曼(AR-Kalman),自回归模型(AR)和反向传播神经网络(BP)进行了比较。预测结果表明PM的精度 在整个时间段内改善浓度预测。
更新日期:2021-05-07
中文翻译:
基于多模型自适应无味卡尔曼滤波的大气PM2.5预测
下午