Real-time risk early warning system and production scheduling method for in-field mobile machinery based on AI large model capability

Abstract

The invention relates to the technical field of risk early warning, in particular to an in-field mobile machinery real-time risk early warning system based on AI large model capability and a production scheduling method. The method comprises the following steps: a data acquisition and processing unit acquires operation state parameters and operation environment parameters of the in-field flow machinery, and preprocesses the operation state parameters and the operation environment parameters; the AI large model analysis and risk identification unit is used for extracting feature vectors of the operation state parameters and the operation environment parameters, modeling the interaction relation between the operation track, the behavior mode and the environment of the mobile machinery by utilizing a BERT model and a long-short-term memory network model, and generating a risk index; and the risk early warning and response unit generates alarm information based on the risk index. According to the method, a sensing neural radiation field (F-NeRF) environment modeling method is introduced, and discrete sensor data is converted into continuous space-time representation of working environments (such as temperature and humidity, visibility and ground conditions).

Images