一种基于时间序列大模型的大件货运车载称重方法及系统

By using a timestamp alignment algorithm and a large model fusion based on the Transformer architecture, the problems of spatiotemporal drift of multiple sensors and poor model generalization ability in the weighing of heavy freight vehicles are solved, and high-precision, real-time weighing and load change trend prediction of freight vehicles are achieved.

CN120705544BActive Publication Date: 2026-07-17山西省智慧交通实验室有限公司 +1

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
山西省智慧交通实验室有限公司
Filing Date
2025-06-16
Publication Date
2026-07-17

Smart Images

  • Figure CN120705544B_ABST
    Figure CN120705544B_ABST
Patent Text Reader

Abstract

本发明属于大件货运车辆称重技术领域,公开了一种基于时间序列大模型的大件货运车载称重方法及系统,步骤1:采用时间戳对齐算法将多传感器所采集的多源数据融合,生成具有时空特征的时间序列编码数据并存储;步骤2:对原始时间序列数据进行预处理,构建多模态训练数据集;步骤3:利用数据集进行预训练并微调构建基于Transformer架构的时间序列大模型;步骤4:将最新采集到的具有时间序列特点的载重数据输入到时间序列大模型中进行实时动态称重计算;步骤5:构建误差校正混合系统对称重结果进行精准校正;步骤6:实时输出具有时间序列特点的准确称重结果,并对载重变化趋势作出可靠性预测。
Need to check novelty before this filing date? Find Prior Art