Multi-sensor data fusion and its application to industrial control

In this paper, a new cluster fusion control strategy based on multisensor data fusion technique is presented from a perspective of industrial control application. The MSIF system consists of n sensors, n data-fusion nodes, a data-fusion database, and a expert knowledge database. Data-fusion mechanisms, including data coordination, data-fusion method and expert knowledge database, are discussed. A modified ART-2 neural network which can process analog data is applied to realize the data-fusion machine. Details about data acquisition and process, cluster-fusion control, interpretative mechanism and executive framework are discussed.