Aiming at traffic sign problem, the traditional LeNet-5 network structure has low accuracy of traffic sign recognition, slow identification speed and ignores natural factors such as weather. A convolutional network structure model with two-channel and multi-scale based on LeNet-5 improvement is proposed by convolutional neural network technology. In the dual-channel structure, each channel contains two branching structure, and the number of convolution and image scale of each channel is different, making the feature extraction of different image scales richer. Secondly, the improved network structure greatly increases the number of convolutional kernels compared to the traditional LeNet-5 network structure. Finally, by changing the Sigmoid activation function to the ReLu activation function, changing the stochastic gradient descent algorithm to the Adam algorithm, and adding Dropout layers to prevent overfitting and setting the learning rate, thus increasing the traffic sign recognition rate. The recognition rate of the improved network is 98.6%, floating by 0.5%, relative to the traditional LeNet-5 network structure, the recognition rate increases by more than 15%, verifying that the improved network structure has a certain robustness.

大型工业锅炉内部燃烧环境恶劣复杂,对于炉膛内温度场的监测具有非常重要的意义.声学法测温作为一种新型的非接触测温方法,具有传播速度快、测量范围广、不受环境干扰等优点.为得到炉膛的温度场可视化结果,基于有限元法,利用COMSOL平台构建炉膛单峰偏斜温度场模型,模拟声波在炉膛内的传播情况,并根据互相关算法计算声波飞行时间,运用最小二乘法和插值算法对炉膛温度场进行还原.结果表明:运用互相关算法求得的飞行时间和理论飞行时间最大相对误差为 0.81%,误差原因在于声源信号的伪前移现象,还原出来的温度场和单峰偏斜温度场模型平均绝对误差为31 K,具有很好的重建效果.

There are many deficiencies in contact temperature measurement, which can not provide a good guarantee for economy, efficiency and safety. Ultrasonic sensor temperature measurement technology has a good effect on the real-time monitoring of complex temperature field. This study takes the boiler furnace as the research object and the reconstruction of the temperature field in the furnace as the research purpose. Based on the finite element method, a single peak symmetrical temperature field model of the furnace is established on COMSOL platform to simulate the propagation of sound waves in the furnace, calculate the flight time according to the cross-correlation algorithm, and restore the temperature field of the furnace temperature field model by using the least square method and interpolation algorithm. The results show that the maximum relative error of flight time and theoretical flight time obtained by cross-correlation algorithm is 0.85%, and the average absolute error of reconstructed temperature field and single peak symmetric temperature field is 31K, which has a good reconstruction effect.