Dynamic PSO-Neural Network: A Case Study for Urban Microcosmic Mobile Emission

Road traffic is widely accepted as being a substantial source of air pollution in urban environments. It is necessary to understand the real-world emission factors and identify the operational factors related to emissions. The objective of this study was to develop a particle swarm optimization (PSO)-neural network method for uncovering the relationship between operational status and emission rates. First, a neural network model was proposed to express the relationship between operational status of vehicles and their emission rates (include nitrogen oxides (NOx), hydrocarbon (HC) and carbon monoxide (CO)). The training of neural network is convergent through introducing dynamic searching particle swarm optimization method. A case study in Wuhan city was developed to test the applicability of the proposed model. The results indicate that the dynamic searching particle swarm optimization method can generate more useful solutions than thee basic particle swarm optimization method.