数据融合在选矿自动控制中的应用

Application of data fusion in automatic control of ore dressing

针对多传感器测控系统应用于选矿自动控制中,导致信息量增加和信息处理难度增大的问题,提出了基于神经网络的信息融合模型,利用神经网络强大的并行运算能力和处理不确定信息的能力,对多传感器检测出的信息进行融合,通过融合,不但消除了信息中的不确定因素,又降低了信息的维数。将融合后的信息作为控制器的输入,从而使控制器的设计简单、可靠。

An information fusion model based on neural network is proposed in this thesis.It aims to solve the difficulties arised from the use of multi-sensors in the automatic control system.Information from all sensors with the help of the great calculating ability of neural network is synthesized.The uncertainty and the dimension of information can be reduced dramatically through the processing of the neural network.The information obtained through the fusion is taken as the input of the controller,which leads to the design of the controller much simpler and more reliable.