Łazarska Małgorzata, Ranachowski Zbigniew, Musiał Janusz, Tański Tomasz, Jiang Qingshan
Faculty of Materials Engineering, Kazimierz Wielki University, Chodkiewicza 30, 85-064 Bydgoszcz, Poland.
Institute of Fundamental Technological Research, Polish Academy of Sciences, Pawińskiego 5B, 02-103 Warszawa, Poland.
Materials (Basel). 2025 May 10;18(10):2198. doi: 10.3390/ma18102198.
This research was carried out for selected alloy (bearing) and non-alloy (tool) steel. The steels were subjected to austempering. The hardening temperature range was from 100 °C to 180 °C. The use of acoustic emission in connection with the artificial neural network (ANN) enabled the analysis and identification of phase changes occurring in steels during austempering. Classification of acoustic emission events was carried out with the help of their energy values and with the use of an artificial neural network. On this basis, it was observed that in the process of isothermal hardening of steel at the applied temperatures, complex transformations of austenite into martensite and bainite occur. In addition, it was found that the research methods used enabled the identification of signal components originating from the phase transformation causing the formation of thin-plate martensite midrib. The use of acoustic methods in the field of bainitic transformation creates the possibility of their application in the industry.
本研究针对选定的合金（轴承）钢和非合金（工具）钢进行。这些钢进行了等温淬火处理。淬火温度范围为100℃至180℃。结合人工神经网络（ANN）使用声发射技术，能够分析和识别钢在等温淬火过程中发生的相变。借助声发射事件的能量值并使用人工神经网络对声发射事件进行分类。在此基础上，观察到在所施加温度下钢的等温淬火过程中，奥氏体发生了向马氏体和贝氏体的复杂转变。此外，还发现所使用的研究方法能够识别源自相变的信号成分，这些相变导致了薄板马氏体中肋的形成。在贝氏体转变领域使用声学方法为其在工业中的应用创造了可能性。
