【摘要】 锅炉受热面在高温的作用下会在一定程度上向外膨胀,实时监测锅炉的热膨胀可提高机组运行的安全性和稳定性。通过使用两台相机对锅炉外壁上的棋盘格标靶进行拍摄,再基于BP神经网络进行图像处理,实现了锅炉热膨胀三维位移的精准监测,且无需单独对相机进行畸变矫正与双目矫正,标定之后即可用于现场实际环境锅炉热膨胀的测量。实验结果表明:该系统测量的标准差小于0.05 mm,位移测量误差小于0.6%,单点测量时间小于0.1 s,可满足锅炉热膨胀实时测量及精度的要求。更多还原

【Abstract】 The heating surface of the boiler will expand outwards to a certain extent under the action of high temperature and high pressure, real-time monitoring of the thermal expansion of the boiler can improve the operation safety and stability of the unit.Two cameras were used to photograph the checkerboard targets on the boiler walls, and BP neural network is used for image processing.The three-dimensional displacement of boiler thermal expansion is accurately monitored, and does not require distortion correction or binocular correction of the camera alone. After calibration in the laboratory, it can work in the actual environment.The tests show that the standard deviation measured by the system was less than 0.05 mm, the displacement measurement error is less than 0.6%, and the single point measurement time is less than 0.1 s, which can meet the real-time measurement accuracy requirements of boiler thermal expansion.更多还原