An early fault prediction method for hydraulic equipment based on the fusion of multi-source condition monitoring information and reliability features
A technology for monitoring information and early failures, applied in character and pattern recognition, instruments, computer components, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0059] Specific implementation method
[0060] 1. Identify the signal feature quantity, the method is as follows:
[0061] Take the state space of the feature quantity as the vertical direction and the time scale as the horizontal direction to quantitatively characterize the signal feature quantity;
[0062] 2. Based on the fusion of multi-source monitoring information for state comprehensive feature value recognition, the method is as follows:
[0063] The self-organizing mapping neural network is used to merge the feature layer of multi-source signals, and the minimum quantization error (MQE), that is, the distance between the input data and the normal state data, is used as the comprehensive feature quantity of the monitoring state of the device, which can be expressed by the following formula:
[0064] MQE(t)=||D(t)-m BMU ||
[0065] Among them, D(t) is the multi-source signal feature vector at time t, and it is used as the input of the neural network; m BMU Represents the weight vec...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap