With the rapid development of optoelectronic tracking and measurement technology, tracking equipments become more
complex and more precise, and the system faults happen at higher probability. The fault orientation, the fault analysis
and the fault exclusion change more difficult. The single information and the simple process of multi-information have
many deficiencies, which need fusion to improve the reliability. The D-S theory of evidence is a way to resolve the
uncertain problems, which fuses evidences to reason the decision results in the same recognition frame used at the
decisional level. Using the D-S theory of evidence, a diagnosis frame of multi-feature information fusion is proposed.
The deviation ranks of the fault characters is defined according to their offsets from the normal and their happening
probabilities were also computed by using the statistical results and the existing knowledge. The data reasoning of rough
set theory is employed to construct the key fault evidence space from the multi features. Further, Gaussian subjection
function from the fuzzy theory is used to describe the distribution of the key evidences and the distribution of the test
data, and the basic probabilities of the evidence are weighed by the matching degree of the two distributions. The multiperiod
and space feature information are employed and fused, and the final diagnosis decision is made by some effective
methods. A multi-feature information fusion diagnosis for the servo system of the tracking equipment is discussed. The
test shows that the diagnosis reliability is improved and the diagnosis uncertainty is reduced, and the fault diagnosis for
the precise device and other parts are also effectively resolved by using this fusion method.