Research on the BPNN in the Prediction of PMV
In view of the problem that it is difficult to calculate the Fanger’s PMV equation due to its complicated iterative process, a backpropagation neural network (BPNN) model was built to predict PMV. Air temperature, relative humidity, mean radiant temperature, air velocity, metabolic rate and clothing index were used as the input of neural network and PMV output as the output of the neural network. The results show that this prediction approach is very effective and has higher accuracy absolute error below 5%. As a conclusion, this study has a real signiﬁcance, because it gives a new method with reliability and accuracy in the prediction of PMV.
J. Yao and J. Xu, "Research on the BPNN in the Prediction of PMV", Applied Mechanics and Materials, Vols. 29-32, pp. 2804-2808, 2010