Operation and maintenance data analysis optimization system and method based on deep neural network

Through the operation and maintenance data analysis and optimization system based on deep neural network, we deal with the problem of high-dimensional sparse data and data drift in the life cycle of the equipment, extract low-dimensional features and introduce life cycle recognition and transfer learning mechanisms, solving the problem of low fault prediction accuracy Problem, achieving more accurate and adaptive fault prediction.

CN119398762AInactive Publication Date: 2025-02-07SHAANXI RUIYA INTELLIGENT TECH CO LTD
View PDF 7 Cites 1 Cited by

Patent Information

Application Number
CN202510000166.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-01-02
Publication Date
2025-02-07
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The prior art is difficult to effectively deal with the features sparseness in high-dimensional sparse data and data drift in the life cycle of the equipment, resulting in low fault prediction accuracy.

Method used

Adopting an operation and maintenance data analysis and optimization system based on deep neural networks, low-rank matrix decomposition is carried out by building a high-latitude sparse matrix, low-dimensional features are extracted, and equipment life cycle stage recognition mechanism and multi-stage transfer learning mechanism are introduced, combining incremental learning Algorithm, dynamically update the fault prediction model.

Benefits of technology

Effectively compress high-dimensional sparse data into low-dimensional features, remove redundancy and irrelevant features, improve the accuracy and adaptability of fault prediction, adapt to changes in different life cycle stages of the equipment, and reduce prediction deviations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119398762A_ABST
    Figure CN119398762A_ABST
Patent Text Reader

Abstract

The invention provides an operation and maintenance data analysis and optimization system and method based on a deep neural network, and relates to the technical field of intelligent operation and maintenance management, and the method comprises the steps: constructing a high-latitude sparse matrix according to preprocessed first data and second data, and employing a low-rank matrix to decompose the high-latitude sparse matrix, extracting potential low-dimensional features in the first data and the second data according to low-rank matrix decomposition, performing weighted fusion on the potential low-dimensional features, and forming a comprehensive feature vector according to the weighted fusion; introducing an equipment life cycle stage identification mechanism, constructing a fault prediction model, and training the fault prediction model according to the comprehensive feature vector to obtain a trained fault prediction model; and introducing a multi-stage transfer learning mechanism, and carrying out knowledge transfer on the trained fault prediction model to obtain a fault prediction model after knowledge transfer. The problems of feature sparsity in high-dimensional data and data drift in an equipment life cycle are solved through low-dimensional feature extraction and transfer learning.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Aero-engine degradation state fault diagnosis method based on transfer learning

    CN113283004A

  • Inverter fault diagnosis method and system of multi-mode deep residual filter network

    CN116203466A

  • Equipment life prediction method and device based on transfer learning

    CN117851921A

  • Intelligent electric power distribution station operation fault prediction method and system

    CN118568471A

  • Construction method, system and equipment of sliding bearing fault diagnosis model and medium

    CN119150020A

Cited By

  • Router, gateway and camera operation and maintenance method and system

    CN120856586A