Extracting Design Information From Optimized Designs of Power Flow Systems: Application to Multisplit Thermal Management System Configuration
Bibliographic record
Abstract
Abstract As engineering systems grow more intricate and technological progress accelerates, traditional sources of design knowledge, such as historical data and expert intuition, struggle to keep pace with the complexity and the speed of knowledge generation. To address this challenge, additional sources of knowledge are necessary, particularly for designing unprecedented engineering systems lacking any design heritage. One promising approach involves analyzing optimized designs to extract valuable insights, enabling designers to break away from incremental improvements over existing designs. This article explores the extraction of design information from optimized designs in power flow systems using various classification machine learning methods, empowering designers to make informed decisions in future design endeavors. This design information can also serve as a foundation for synthesizing engineering system configurations that are more complex than those previously encountered. This approach offers several advantages over traditional methods, including its applicability in the absence of design heritage and its ability to provide normative guidance for system design. This article focuses on power flow systems that can be modeled as graphs with a tree structure, with the case study being multisplit fluid-based thermal management systems. The article presents four case studies demonstrating the effectiveness of using information from optimized designs to enhance the design of complex thermal management systems, in both human-directed and automated design processes. The results show that information extraction significantly improves the design process, with less than 1 percent error in approximating the true optimal configuration. This approach eliminates the need for solving complex control problems, leading to reduced computation costs.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".