Shield tunneling machine fault prediction method based on LSTM
A fault prediction and shield machine technology, applied in neural architecture, computer components, computer-aided design, etc., can solve problems such as economic loss, endangering the safety of construction personnel and the surrounding area of the construction site, and affecting the progress of the project
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0046] The invention provides a multi-label prediction method for shield machine faults based on LSTM, utilizes the characteristics of long-short-term memory network that is good at processing time series data, and utilizes actual data collected during shield machine construction to predict multiple faults during shield machine construction.
[0047] combine Figure 1-Figure 4 , an LSTM-based shield fault multi-label prediction method includes the following steps:
[0048] Step 1, integrate the actual construction data of the shield machine, external environment data and shield construction failure data.
[0049] Step 2, combine figure 1 , to perform data preprocessing, including several sub-steps of data cleaning, data integration, labeling of shield failure labels and balancing the number of positive and negative label samples in the data set.
[0050] Firstly, the data cleaning of the shield construction parameters is carried out, and the geological and risk source data a...
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, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com