Power plant equipment maintenance decision support method and system based on bimodal data

The invention discloses a power plant equipment maintenance decision support method and system based on bimodal data. The method comprises the steps of obtaining a target image and obtaining an equipment feature vector corresponding to target equipment in the target image; a first voice signal and a second voice signal are obtained, the first voice signal reflects the equipment state of the target equipment, the second voice signal reflects the maintenance target of the target equipment, the first voice signal is converted into a first voice feature vector, and the second voice signal is converted into a second voice feature vector; and matching the equipment feature vector, the first voice feature vector and the second voice feature vector with a preset maintenance scheme to obtain a target maintenance scheme corresponding to the target equipment. According to the invention, the maintenance scheme searching efficiency can be improved. 本发明公开了一种基于双模态数据的电厂设备维修决策支持方法及系统，方法包括：获取目标图像并获取所述目标图像中的目标设备对应的设备特征向量；获取第一语音