Structure Optimization and Governance of Multilevel Rail Transit Integration under the Background of a Metropolitan Area Based on the Industrial Internet of Things Security Data Fusion Method

Abstract

In recent years, the urban rail transit network architecture has gradually grown, the contradiction between rail transit passenger flow and transport load has been deepening, and its carrying capacity has also been tested. Passenger flow risk has become the most important source of risk in rail transit. The key to restricting rail transit service quality is how to effectively monitor and manage rail transit passenger flow and provide accurate and convenient early warning to staff. In order to effectively manage the complex passenger flow scene, the premise is to distinguish the real-time state of its moving target. The time series data feature extraction and LSTM data fusion were used to analyze the traffic data sequence in the multilevel rail transit network model. The multilevel rail transit integration of the Internet of things is modeled by the method of data fusion. It can be seen from the experimental data that in the data fusion mode, the network comprehensive evaluation prediction value fitting effect can quickly converge, and the error rate is less than 4%. By comparing the mean square error (MSE) and mean absolute error (MAE) data of the traditional method and the experimental method used in this paper through two different datasets, it was understood that the MAE under the data fusion method was reduced by 8 compared with the traditional method, and the MSE was decreased by 33, indicating that this method can bring better simulation effect to the model. The improvement of the synergistic and complementary functional network and the acceleration of the efficient and convenient flow of elements are the inevitable results of the integration of multilayer rail transit in the metropolitan area.