Fault prediction method and system, electronic equipment and computer program product
A fault prediction and fault technology, applied in geometric CAD, special data processing applications, etc., can solve problems such as increasing the workload of the staff, inability to adapt to uniqueness, etc., and achieve high fault detection performance, high accuracy, and low false alarm rate. Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0080] see figure 1 , is a schematic flowchart of a fault prediction method for a gear transmission according to an exemplary embodiment of the present invention. Specifically, the method includes the steps:
[0081] S101, build a fault prediction model based on the acquired training set.
[0082] In some embodiments, in order to ensure a sufficient amount of data, the first historical vibration data of a plurality of first gear transmissions are acquired in advance as a training set to construct a fault prediction model, and the training set has been marked in advance, such as: marking For the historical vibration data representing the normality of the first gear transmission, ie, normal data / normal samples, and to mark the historical vibration data representing the failure of the first gear transmission, ie, fault data / fault samples. For example, in order to ensure a sufficient amount of data, the historical vibration data of the corresponding gear transmission device (ie t...
Embodiment 2
[0116] The fault prediction method of the present invention is described in detail by taking the gearbox of the wind turbine as an example.
[0117] In some embodiments, the fault prediction method of the embodiment of the present invention includes offline training and online testing. For details, see Figure 5a , the marked historical vibration data includes a large amount of source domain (SD) data (for example, obtained by experts marking the first historical vibration data of a plurality of first transmission gear devices in advance) and a small amount of target domain data (that is, based on the target obtained by automatically marking the second historical vibration data of the second gear transmission), and extract the source domain features (that is, the fourth harmonic frequency of the meshing frequency and its sidebands of the first historical vibration data) and the target domain features (that is, the first historical vibration data). The meshing frequency of the ...
Embodiment 3
[0154] see Figure 4 , the present invention also provides a fault prediction system of the gear transmission, specifically, it includes:
[0155] Database 401 for storing a training set and second historical vibration data of a second transmission gear device; the training set includes: marked first historical vibration data, the first historical vibration data from a plurality of first gear transmission devices ;
[0156] A model building module 402, configured to build a fault prediction model based on the obtained training set;
[0157] a model preheating module 403, configured to preheat the fault prediction model constructed by the model construction module based on the pre-built preheat set, so that the fault prediction model is adapted to the individual characteristics of the second gear transmission;
[0158] The fault prediction module 404 is configured to perform fault prediction based on the preheated fault prediction model and the collected real-time vibration d...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


