Design of Anomaly Detection Research Model for Multi-Dimensional Temporal Data

In the production and daily life of various industries in today's society, it is often necessary to arrange a large number of sensors to collect data on a scheduled basis. However, due to factors such as collection errors, sensor failures, network transmission anomalies, and human influence, the obtained multidimensional temporal data may exhibit anomalies. In order to better analyze multidimensional temporal data, understand patterns, trends, and correlations in observed phenomena, and help people better analyze problems and make decisions, a design scheme for anomaly detection models that have always been oriented towards multidimensional temporal data is proposed. This scheme utilizes Convolutional Neural Networks (CNN) to extract local features, Long Short Term Memory Networks (LSTM) to store and extract time-series data features, combined with attention mechanisms to enhance feature extraction capabilities, and uses Variational Autoencoder (VAE) for anomaly detection, significantly improving the accuracy and efficiency of detection. Through experimental verification, this method performs well in practical applications and has broad application prospects.