Assessing the applicability of machine learning in manufacturing and design operations
Bibliographic record
Abstract
Throughout the last years, research and applications in artificial intelligence (AI) and its subcategory machine learning (ML) have significantly increased, along with the public interest on this field.This trend has raised the attention of decision makers in manufacturing companies that are seeking for new opportunities to improve processes.However, the absence of instructions on where and how to use learning algorithms impedes applications.A ML project in industry typically consists of two parties: the industrial client, host of the process in question, and the ML expert.Since the ML expert has no or little knowledge about the application domain and the industrial client no expertise in applying ML, it is unclear at the beginning of a project if ML is a suitable solution for the given scenario.In this work, a guide is developed to improve the collaboration between ML experts and their industrial clients on ML projects.The objective of the guide is to assess the applicability of ML on a use case at an early stage by providing action steps, rules, and guidelines.To obtain the desired knowledge, three case studies in manufacturing and design processes are conducted for this research.As a first step, a methodology is developed to systematically perform the same tasks on every case study.It comprises three main steps: the analysis of the current situation and motivation behind applying ML, the definition of the objectives on the project and the learning algorithm, and the analysis of the available data.The methodology is complemented with information from literature such as the categorization of ML tasks and data types, as well as popular techniques to prepare, process, and evaluate data.Then, the methodology is applied to the case studies and the experiences made are noted down in three rules and six guidelines.Finally, the methodology is refined and extended with those findings, turning it into a concise guide to determine the feasibility of ML projects.
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 | 0.004 | 0.026 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| 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".