Toward the quality prognostic of an aircraft engine workpiece in Inconel Alloy 625: case study and proposed system architecture
Bibliographic record
Abstract
Manufacturing companies are under a constant pressure due to multiple factors: new competition, disruptive innovations, cost reduction request, etc.To survive, they must strive to innovate and adapt their business model to improve their productivity.Recent developments based on the concept of Industry 4.0 such as big data, new communication protocols and artificial intelligence provide several new avenues to explore.In the specific context of machining, we are working toward the development of a system capable of making the prognostic of the quality (in terms of dimensional conformance) of a workpiece in real time while it is being manufactured.The goal of this paper is to showcase a prototype of the data acquisition aspect of this system and a case study presenting our first results.This case study has been conducted at our industrial partner facility (Quebec, Canada) and is based on the manufacturing of an aircraft component made from Inconel alloy 625 (AMS5666).The proposed prototype is a data acquisition system installed on a 5 axis CNC machines (GROB model G352) used to acquire and to contextualize the vibration signal obtained from the CNC machine sensor.The contextualization of the data is a key component for future work regarding the development of a prognostic system based on supervised machine learning algorithms.In the end, this paper depicts the system architecture as well as its interactions between the multiple systems and software already in place at our industrial partner.This paper also shows preliminary results describing the relationship between the workpiece quality (in terms of respect toward the dimensional requirements) and the extracted features from the sensors signals.We conclude that it is now possible to do the diagnostic of a cutting operation.Additionally, with the same information we show that it is possible to quickly do the general diagnostic of the health state of the machine.Future work regarding this project will include data acquisition from a wider range of products (i.e.different shapes, materials, processes, etc.) and the development of a machine learning based prognostic model.
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) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".