Event Classification for Maintenance Information Generation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing maintenance information transmission systems and failure repair support systems fail to accurately match maintenance content with the actual operation status of industrial machines, leading to inefficient maintenance. Additionally, these systems do not consider the pre-failure conditions, resulting in inappropriate and inefficient maintenance.
Innovation Solution
An information management device and method that classify events based on data related to equipment and operation behavior up to the event occurrence, generating event information and associating it with maintenance information. This allows for the management of maintenance information in relation to each classified event, enabling appropriate and efficient maintenance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If maintenance content is simply selected from standard maintenance DB, then maintenance information can be generated quickly, but maintenance content may not appropriately correspond to actual operation status
Solution Approach 1:
The patent segments maintenance information into multiple dimensions: event type, operation status, historical data, and maintenance records. By dividing the maintenance decision process into these segments, the system can selectively combine them to generate accurate maintenance content that corresponds to actual operation status while maintaining efficient information retrieval.
Solution Approach 2:
The system changes parameters by incorporating dynamic operation status data and historical maintenance records into the maintenance information generation process. Instead of using static standard maintenance DB alone, the system adjusts maintenance content based on varying parameters such as current operation status, event history, and equipment conditions, thereby improving accuracy without sacrificing generation speed.
2Quantity of substance
If only failure occurrence data is stored, then storage requirements are reduced, but pre-failure conditions cannot be analyzed
Solution Approach 1:
The patent extracts only the essential pre-failure condition parameters needed for maintenance analysis rather than storing complete historical operation data. By identifying and extracting key parameters such as operation status indicators, event types, and critical measurement data, the system preserves necessary pre-failure information while minimizing storage requirements.
Solution Approach 2:
The system performs preliminary classification and filtering of operation data before storage, organizing data into structured formats that capture pre-failure conditions efficiently. By pre-processing and categorizing data during operation, the system ensures that essential pre-failure information is preserved in a compact, easily retrievable format without requiring extensive storage capacity.
3Measurement precision
If detailed operation behavior data is collected, then event classification accuracy is improved, but data processing complexity increases
Solution Approach 1:
The patent segments operation behavior data into distinct categories such as operation status, event types, temporal patterns, and equipment parameters. This segmentation allows the system to process detailed data more efficiently by handling each category separately with appropriate processing methods, thereby maintaining high classification accuracy while reducing overall processing complexity.
Solution Approach 2:
The system applies different processing qualities to different data segments based on their importance and characteristics. Critical data elements requiring high classification accuracy receive more sophisticated processing, while less critical data undergoes simpler processing. This local quality approach optimizes the balance between classification accuracy and processing complexity by allocating computational resources strategically.
Data Source
AI summary
An information management device includes: a first data storage unit which stores first data relating to at least one of data on equipment and operation behavior data concerning the equipment up to occurrence of an event; an event information generation unit which classifies the event on the basis of the first data and generates event information associated with the first data; a second data storage unit which stores second data in which the data on the equipment encompassing before and after maintenance work in response to the event is associated with maintenance behavior data concerning the equipment; a maintenance information generation unit which associates the event information with the second data and generates maintenance information corresponding to each piece of event information; and a maintenance information storage unit which stores the generated maintenance information.