Novel multi-sensor data fusion method, electronic equipment and storage medium

The invention belongs to the field of sensor data, and particularly relates to a novel multi-sensor data fusion method which comprises the following steps: step 1, data acquisition: acquiring PM2.5, humidity, wind speed and other data from a website, and acquiring environmental illumination information by using a light intensity sensor; step 2, data preprocessing: performing data preprocessing on the collected data; and step 3, data fusion: constructing a network model composed of a CNN and an LSTM, and inputting the data set prepared in the step 2 into the constructed network model for training. According to the method, richer types of environmental data are adopted as network input, sensor data are cleaned in advance, a CNN-LSTM network is designed for data fusion and parameter sharing, the number of parameters of a model is reduced, and the sequential relationship and mutual influence between different sensor data are better captured by using bidirectional LSTM; the method improves the fusion accuracy, red