Design of Air Cushion Vehicles Using Artificial Intelligence: Expert System and Genetic Algorithm
Bibliographic record
Abstract
In the thesis, initial design of an Air Cushion Vehicle (ACV)is performed with the expert system and its skirt system is further optimized with the genetic algorithm. Both the expert system and genetic algorithm are advanced computerized design techniques of artifical intelligence. Those techniques are specifically developed for the ACVs with programming codes in this thesis. Then the main objective is to show the successful implementation of those techniques in the design of ACVs. The thesis work is divided into two parts. In the first part, the general configuration of ACVs, including the overall dimensions, weight distribution, parametric properties, and several subsystems, is studied and designed by the expert system as an initial design phase. In the second part of the thesis, the skirt system of ACVs is further optimized. In particular, the properties of the bag and finger skirt are optimized for improved ride quality and stability by the genetic algorithm. For the validation of these two artificial intelligence techniques, the CCG (Canadian Coast Guard) 37 ton Waban-Aki and U.S. Navy's 150 ton LCAC (Landing Craft Air Cushion) are selected for the tests. The results of the tests proved that the expert system was successfully implemented and was a powerful tool for the initial design of ACVs. Furthermore, the genetic algorithm optimized the skirt system with significantly improved ride quality and stability. It was also shown that the skirt mass was an important design factor in the heave response of the bag and finger skirt. Hence, this thesis work opened the new possibility of designing ACVs with artificial intelligence techniques.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 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".