State Estimation Using Cross-Individual Data Synthesis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing state estimation methods for mass-produced industrial products, such as fuel cell vehicles, face challenges in accurately predicting future states, especially for abnormal individuals, as they require large quantities of high-quality data, making long-term predictions costly and time-consuming.
Innovation Solution
A state estimation device that calculates a first estimated extrapolation value from data relevant to the product and a second estimated extrapolation value from a same-type different-individual product, then synthesizes these values based on a decided ratio to improve estimation accuracy for abnormal individuals and enable long-term predictions at a lower cost.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If modeling is performed to consider influence for abnormal individuals, then estimation accuracy for abnormal individuals is improved, but cost and time increase
Solution Approach 1:
The patent uses data from same-type different-individuals as a substitute or supplement for own-individual data when own-individual data is insufficient or when the individual is abnormal. By copying and adapting patterns from similar individuals, the system achieves accurate estimation for abnormal individuals without requiring extensive own-individual historical data or complex custom modeling, thus reducing time and cost while maintaining accuracy.
Solution Approach 2:
The patent creates a universal estimation framework that can handle both normal and abnormal individuals using the same synthesis mechanism. The system universally applies the synthesis of first and second estimated extrapolation values across all estimation targets, adapting the synthesis ratio based on individual characteristics rather than requiring separate modeling approaches. This universal approach reduces development time and cost while maintaining accuracy for different individual types.
Data Source
AI summary
In estimation of a future state of a first product (an estimation-target individual), a first estimated extrapolation value is calculated from data on a past side of data relevant to the first product, and a second estimated extrapolation value is calculated from data relevant to a second product (a same-type different-individual of the estimation-target individual) that is different from the first product. A synthesis ratio between the first estimated extrapolation value and the second estimated extrapolation value is decided from data on a present side of the data relevant to the first product, and an estimation value is calculated by performing synthesis between the first estimated extrapolation value and the second estimated extrapolation value based on the decided synthesis ratio.