数字图像相关（Digital Image Correlation, DIC）试验系统因其能够实现对全场应变的非接触式精确测量，被广泛应用于高温环境下结构的力学性能评估。然而，基于DIC测量技术的试验方法难以直接表征结构应力场，且高温环境下材料参数与温度密切相关，有限元法高度依赖材料参数而导致应力结果精度不足。因此，如何结合高温DIC试验与有限元法实现结构全场应力的精确表征，对理解和测评结构的力学性能具有重要意义。本文提出了一种高温DIC试验应力表征的数据融合—知识迁移方法，针对航空结构中典型高温钛合金搭建了高温DIC试验系统、高精度有限元模型以及迁移学习框架，实现了基于小样本试验数据的高精度应力场表征。首先，基于多层感知机神经网络对大样本仿真数据进行预训练，捕捉复杂高温环境下结构坐标与应力间的映射关系；其次，基于小样本高温DIC试验数据对预训练模型进行微调，表征了高温环境下的结构应力场，将有限元模型中的知识有效迁移至试验数据；最后，利用均方误差和决定系数等指标，验证了所提方法用于结构应力场预测的准确性及适用性，为表征高温环境下的试验应力场提供了一种新思路。

The Digital Image Correlation (DIC) experimental system is widely used for mechanical performance evaluation of structures under high-temperature environments due to its ability to achieve non-contact precise measurements of full-field strain. Howev-er, experimental methods based on DIC measurement technology face challenges in directly characterizing the stress field of structures, particularly in high-temperature environments where material parameters are closely related to temperature, and the heavy reliance of the finite element method (FEM) on these parameters leads to insufficient accuracy of stress outcomes. There-fore, it is of great significance to understand and evaluate the mechanical properties of structures by combining high-temperature DIC experiments and FEM to accurately characterize the full-field stress of structures. This paper proposes a data fusion-knowledge transfer method for stress characterization in high-temperature DIC experiments. A high-temperature DIC experimental system, a high-precision FEM model, and a transfer learning framework are developed for typical high-temperature titanium alloys in aerospace structures, achieving accurate characterization of stress fields based on small-sample experimental data. Firstly, a multi-layer perceptron neural network is employed to pre-train large-sample simulation data, cap-turing the mapping relationship between structural coordinates and stress under complex high-temperature environments; sec-ondly, based on small-sample high-temperature DIC test data, the pre-trained model is fine-tuned to characterize a structural stress field under high-temperature environments, and effectively transferring knowledge from the finite element model to the experimental data; finally, the accuracy and applicability of the proposed method for predicting structural stress fields are veri-fied using indicators such as the mean square error and the coefficient of determination, providing a new approach for character-izing experimental stress fields under high-temperature environments.