This paper aims to overcome the defect of single-source temperature measurement method and improve the measurement accuracy of FTR. The friction temperature rise (FTR) of brake affects braking performance seriously. However, it was mainly detected by single-source indirect thermometry, which has obvious deviations.,A three-point temperature measurement system was built based on three kinds of single-resource thermometry. Temperature characteristics of these thermometry were analyzed to achieve a standard FTR curve. Two fusion-monitoring models for FTR based on multi-source information were established by artificial neural network (ANN) and support vector machine (SVM).,Finally, the two models were verified based on the experimental results. The results showed that the fusion-monitoring model of SVM was more accurate than that of ANN in monitoring of FTR.,Then the temperature characteristics of the three single-source thermometry were analyzed, and the fusion-monitoring models based on multi-source information were established by ANN and SVM. Finally, the accuracy of the two models was compared by the experimental results. The more suitable fusion-monitoring model for FTR monitoring was determined which would be of theoretical and practical significance for remedying the monitoring defect of FTR.

中文翻译：

---

基于多源信息和AI技术的机械制动器摩擦温升融合监测

本文旨在克服单源测温方法的缺陷，提高FTR的测量精度。制动器摩擦温升（FTR）严重影响制动性能。但主要采用单源间接测温法检测,存在明显偏差。,基于三种单源测温法构建了三点测温系统。分析这些测温仪的温度特性以获得标准的 FTR 曲线。利用人工神经网络(ANN)和支持向量机(SVM)建立了两种基于多源信息的FTR融合监测模型。最后,基于实验结果对两种模型进行了验证。结果表明,SVM的融合监测模型在FTR监测方面比人工神经网络更准确,然后分析了三种单源测温的温度特性,建立了基于多源信息的融合监测模型。由ANN和SVM建立。最后，通过实验结果比较了两种模型的精度。确定了更适合FTR监测的融合监测模型，对于弥补FTR监测缺陷具有理论和实践意义。