Model Generating Device Steady-State Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current control design methods require extensive time to collect measurement data in the steady state under various conditions, making it challenging to generate accurate models for controlled objects like engines, especially as the number of measurement conditions increases.
Innovation Solution
A model generation device and method that acquire measurement data under multiple conditions in a short time by estimating steady-state data using prediction equations and machine learning, allowing for automated data collection without waiting for the object to reach steady state.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If measurement data is collected by waiting for the controlled object to enter steady state under each measurement condition, then measurement accuracy is improved, but the time required for data collection increases significantly
Solution Approach 1:
The patent applies preliminary action by acquiring measurement data at multiple time points before the controlled object reaches steady state, and performing preliminary processing to extract steady-state characteristics without actually waiting for steady state to occur. This allows the system to obtain accurate steady-state measurement data through prediction rather than waiting, thereby reducing data collection time while maintaining measurement accuracy.
2Manufacturing precision
If the number of measurement conditions is increased to improve model accuracy, then model quality is improved, but the time and resources required for data collection increase
Solution Approach 1:
The patent applies partial action by acquiring measurement data at multiple discrete time points during the transient period rather than waiting for complete steady state. This partial sampling approach, combined with signal processing to extract steady-state characteristics, provides sufficient data for accurate modeling without the excessive time investment required to wait for full steady state under each measurement condition, thus improving productivity while maintaining model accuracy.
Data Source
AI summary
A model generating device for generating model data regarding an operation state of a target object to be controlled, includes a memory and a processor coupled to the memory and configured to acquire first measurement data regarding the operation state of the target object under each of a plurality of measurement conditions set in a first sequence, acquire second measurement data regarding the operation state of the target object under each of the plurality of measurement conditions set in a second sequence different from the first sequence, estimate third measurement data indicating the operation state in a case where the target object enters a steady state in each of the plurality of measurement conditions, based on the first measurement data and the second measurement data, generate the model data regarding the operation state of the target object based on the third measurement data, and output the model data.