Apparatus State Estimation Using Maintenance Records
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing apparatus state estimation methods lack accuracy in estimating the state of apparatuses, particularly in large-sized air conditioners or refrigerating apparatuses, as they rely solely on operation data without incorporating maintenance records effectively, and struggle with unfixed-format maintenance records.
Innovation Solution
An apparatus state estimation method that stores both apparatus data and maintenance records, estimates malfunction categories and measure content using these records, and learns the relationship between them, enabling high-accuracy state estimation through machine learning, even with unfixed-format records, and expanding the database with service personnel's know-how.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If only operation data from internal sensors is used for state estimation, then the system is simple to operate, but the estimation accuracy is insufficient
Solution Approach 1:
The patent combines multiple data sources including operation data from internal sensors, maintenance records, and work history into a unified state estimation system. This merging of diverse data types enables comprehensive analysis that improves estimation accuracy while the integrated processing framework manages the complexity through systematic data integration.
Solution Approach 2:
The patent introduces an external server as an intermediary that receives maintenance records and work history from multiple apparatuses, processes this data centrally, and provides processed information back to the apparatuses. This intermediary structure allows complex data processing to be distributed, improving local apparatus simplicity while maintaining high estimation accuracy through centralized analysis.
2Ease of operation
If maintenance records are stored in unfixed format, then the system is easy to operate and data collection is simple, but the data processing and analysis become difficult
Solution Approach 1:
The patent transforms unfixed-format maintenance records into structured data with defined parameters and categories. By converting unstructured text and data into standardized formats with specific parameters, the system maintains ease of data collection while enabling systematic processing and analysis through parameter-based organization and classification.
3Measurement precision
If comprehensive maintenance data is collected and processed, then the state estimation accuracy improves, but the processing time and computational resources increase
Solution Approach 1:
The patent performs preliminary processing of maintenance records and work history data by storing them in advance in both original and processed formats. This preliminary action includes pre-categorizing data, pre-computing statistical information, and pre-organizing data structures, which reduces the computational burden during actual state estimation and minimizes processing time when accuracy-critical operations occur.
Data Source
AI summary
An apparatus state estimation method includes: storing first apparatus data that indicates a state of an apparatus; storing a work record, the work record being a record indicating a work that has been carried out for maintenance of the apparatus; estimating a category that is a malfunction of the apparatus or a content of a measure by using the work record; and learning a relationship between the estimated category and the first apparatus data.