【摘要】 人工智能技术与大学物理实验的结合已成为物理教学发展的重要趋势，探索二者深度融合的路径对于实现数智化教学新模式具有重要意义。本研究聚焦于一种广泛应用于非线性实验教学的机器学习方法——储备池计算(Reservoir Computing, RC),探索其在耦合蔡氏电路实验教学中进行同步预测的应用。研究表明，利用储备池计算对耦合蔡氏电路三个非同步状态下的四路电压信号进行学习，可以实现达到同步状态所需电阻值的准确预测。这不仅为学生提供了一种便捷的同步调节方法，还使他们能够直观感受到人工智能技术在物理实验中的巨大应用潜力，从而丰富了大学物理实验教学的数智化内容。更多还原

【Abstract】 The integration of artificial intelligence(AI) technology and university physics experiments has become an important trend in the development of physics teaching. Exploring the pathways for the deep integration of these two areas is of great significance for realizing new models of digital and intelligent teaching. This study focuses on reservoir computing(RC), a machine-learning method used in nonlinear experiment teaching, and explores its application in synchronization prediction in coupled Chua’s circuit experiment teaching. It is found that RC can learn the four-voltage signals of the three nonsynchronous states of the coupled Chua’s circuit and accurately predict the resistance value needed for synchronization. This not only provides students with a convenient method for synchronous adjustment but also allows them to intuitively experience the great potential of AI technology in physics experiments. As a result, it enriches the digital and intelligent content of university physics experimental teaching.更多还原