1、附录 Research of identification of shaft orbit for rotating machine XIAO Sheng-guang （ Test Center of Chongqing University， Chongqing 400044， China） Abstract： A novel approach for the identification of shaft orbit is presented. The vibration displacement signalsacquired in two mutually vertical direct
2、ions were treated through noise suppression and fitted to form a shaft orbit.Then the direction changing character was extracted and all shaft orbits were classified and identified with thefunction discriminated method according to the pattern recognition theory. Each type of shaft orbit was describ
3、ed indetail with one character， which can help to judge the operation status of the mechanical and the extent of thefailure. The analysis and simulation got good results. Key words： Shaft orbits； Fault diagnosis； Geometric features； Pattern recognition；Thinning classification 1 The introduction With
4、 the development of science and technology and modern industry, to rotating machines the large-scale, high-speed and automation direction, the shape of rotating machinery state monitoring and fault diagnosis is put forward higher request, the axis trajectory for rotating machinery is an important st
5、ate characteristic parameters, can be simple and straight view, vividly reflect the running status of equipment. Through to the axis of track observation, can determine some of the common faults, such as oil film vortexStill, oil film oscillation, shaft not medium. The traditional axis locus and sha
6、pe the dynamic characteristics identification is based on the man-machine dialogue mode, serious affect the level of intelligent fault diagnosis.In order to improve the degree of intelligent fault diagnosis, it is necessary to in-depth study the trajectory of the axis of rotating machinery automatic
7、 identification technology. Axis path at present, already have several identification methods, including 1-2 invariant moment method, a two-dimensional image gray level matrix 3.literature 1-2 axis path with seven moment invariants as feature vectors, recognition by the distance between the characte
8、ristics of axial trajectory shape, literature 3 the axis trajectory image coding, using neural network for identification.Both methods can better identify axis path, but the method is complex, relatively large amount of calculation.On the basis of summarizing predecessors work, according to the char
9、acteristics of the axis trajectory itself changes, this paper proposes a new recognition method, by extracting a cycle in the direction of the axis of track change features for classification, and for each categories of axis trajectory, put forward a kind of ability, refine to describe the deformati
10、on degree of parameters, further understand the severity of the fault, and feature extraction speed, high efficiency. 2 Axis locus corresponding fault mechanism analysis Axis path refers to the axis on a bit relative to the trajectory of the bearing, the trajectory is in a plane perpendicular to the
11、 axis, so it requires the setting sensors in both directions in the plane. Axis path clearly describes the fault characteristics of implication in the unit, the axis trajectory can get in on the rotor bending, imbalance, instability and dynamic-static friction bearing and other information.Through t
12、he actual operation of rotating machinery fault mechanism analysis and theoretical analysis, it sums up the axis of some typical trajectories of the fault. Actual sampling of the signal is not a whole cycle, so needs to be carried out in accordance with the maximum cycle component to sampling data i
13、nterception, make one complete cycle of the closed curve. In the collected signal is: x (n), y (n) : n = 0, 1,. , N - 1, through the analysis of a sequence of change characteristics of x, y axis path to identify. 3 Image processing axis path recognition principle 4 In image recognition, is the simplest method of identification for template matching. Is the unknown image compared to a standard image, see whether they are the same or similar.
