Industrial big data intelligent operation and maintenance solution
A solution and big data technology, applied in the field of industrial big data intelligent operation and maintenance solutions, can solve problems such as low prediction accuracy, low efficiency, inability to adapt to diversified, complex and high-speed operation and maintenance needs, etc., to improve efficiency Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0035] Such as Figure 1 to Figure 4 As shown, this embodiment discloses a solution method for intelligent operation and maintenance of industrial big data, which mainly includes the modeling process stage and the prediction stage executed in sequence; the modeling process stage includes modeling data collection, building Model data normalization, data division, model establishment, effect verification, and model output are six steps; the forecast stage includes four steps of sequentially executed forecast data collection, forecast data normalization, model import, and result output step:
[0036] Phases of the modeling process:
[0037] Step S1: The modeling data collection refers to the process of obtaining data from the data center operation and maintenance management system. The types of data obtained include structured data, semi-structured and unstructured data at the application level, system resource level, and network level data.
[0038] Step S2: Normalization of ...
Embodiment 2
[0056] This embodiment discloses: in this technical solution, this fault analysis and prediction system is based on industrial big data, and will clean, mine and feature extract the operation and maintenance monitoring data of the data center, and archive and organize the data, Based on data center software and hardware configuration and performance monitoring data, combined with log data, APM data and other related data, build a fault prediction, fault rapid location and resource capacity prediction model, monitor the established model, and analyze the performance of the model and effects, and record relevant result data, and optimize the model iteratively.
[0057] Preferably, model establishment, effect verification and model output are the fourth, fifth and sixth stages of the modeling process. In this scheme, this part is the core part of the project, which is realized by providing a solution for intelligently selecting models and optimizing model parameters. Technicians...
Embodiment 3
[0060] This embodiment discloses an industrial big data intelligent operation and maintenance solution, including the first stage: mining of causal rules, and the second stage: inference based on causal rules.
[0061] Phase 1: Causal Rule Mining
[0062] The given event-fault sample set is , where , and and are respectively the flag bits of the fault and event in the sample. Let and represent the occurrence of a fault and the occurrence of an event, respectively, then the cause of the fault leading to the occurrence of the event can be expressed by the causal rule as .
[0063] In causality discovery, often the figure 2 The typical causal network structure shown is discussed. Since the V-structure is not statistically equivalent to any other structure containing the same variables, the V-structure is more robust and identifiable in causality identification problems than other Markov equivalence class structures . between the event and the failure figure 2 The V-structu...
PUM
Login to view more Abstract
Description
Claims
Application Information
Login to view more - 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