论文部分内容阅读
在线密度法在原油含水率测量中有很强的实用价值,但存在着受现场不确定因素影响测量误差波动较大的缺点.为了提高含水率的测量精度和稳定性,将误差反向传播神经网络用于密度法计算含水率数学模型中,针对该算法收敛速度缓慢和易陷入局部极小点的缺点,提出了将模拟退火算法用于该模型的全局寻优,改进后的误差反向传播神经网络的误差预报值对密度法模型计算值进行修正.通过对离线实验数据的训练,该方法能够有效地提高在线快速含水率测定结果的准确性.
On-line density method has strong practical value in the measurement of crude oil moisture content, but there is a shortcoming that the measurement error fluctuates greatly due to the uncertain factors in the field.In order to improve the measurement accuracy and stability of moisture content, In order to overcome the shortcomings of the algorithm such as slow convergence speed and easy falling into local minimum, a new method is proposed to use the simulated annealing algorithm in global optimization of the model and improved error back propagation This method can effectively improve the accuracy of the on-line rapid determination of water content through the training of the offline experimental data.