论文部分内容阅读
针对辐射能可以反映燃料量变化的事实,利用炉膛内热平衡的方法推导出了辐射能与燃料量的关系式,可知燃料量发生量的变化后辐射能的量的变化。通过分析辐射能的检测方法,得出辐射能与辐射图像R、G、B值之间存在非线性关系,因此提出一种用BP神经网络测量辐射能的方法,并在实验室黑体炉上进行了试验。该神经网络为一个具有三输入、一输出、含有两个隐含层的BP网络。试验拍摄的辐射图像R、G、B值作为BP神经网络的三个输入值,试验得到的辐射能值作为BP神经网络的输出值,将代表输入输出的18组样本利用BP神经网络进行学习后得到了较为理想的测量辐射能的网络。试验表明该方法精度是比较高的。结合辐射能与燃料量的关系式,该试验方法可应用到实际炉膛中。
According to the fact that the radiant energy can reflect the change of the fuel quantity, the relationship between the radiant energy and the fuel quantity is deduced by means of the heat balance in the furnace. It can be seen that the amount of the radiant energy changes after the amount of the fuel is changed. By analyzing the detection method of radiant energy, it is concluded that there exists a nonlinear relationship between the radiant energy and the radiance R, G, B values. Therefore, a method of measuring radiant energy using BP neural network is proposed and carried out on a laboratory blackbody furnace The test. The neural network is a BP network with three inputs, one output and two hidden layers. The R, G, B values of the radiographic images taken by the experiment were taken as the three input values of the BP neural network. The radiant energy value obtained by the experiment was used as the output value of the BP neural network. After learning the 18 input and output samples by the BP neural network Get the ideal network of measuring radiation. Experiments show that the accuracy of the method is relatively high. Combining the relationship between radiant energy and fuel quantity, this test method can be applied to the actual furnace.