MétaCan
Menu
Back to cohort
Record W4389850034 · doi:10.5267/j.dsl.2023.9.006

Machine learning models for condition-based maintenance with regular truncated signals

2023· article· en· W4389850034 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

venuePublished in a venue whose home country is Canada.
no affNo Canadian affiliation: this work is invisible to an affiliation-only frame.
No Canadian affiliation. An affiliation-only frame, the usual design, would never have seen this work. It is one of the works that make the case for inverting the frame.

Bibliographic record

VenueDecision Science Letters · 2023
Typearticle
Languageen
FieldDecision Sciences
TopicAdvanced Statistical Process Monitoring
Canadian institutionsnot available
Fundersnot available
KeywordsImputation (statistics)Missing dataData miningComputer scienceOutlierMachine learningArtificial intelligence

Abstract

fetched live from OpenAlex

Condition-based maintenance (CBM) of industrial machines depends on the continuous, real-time monitoring of the machine’s operational condition via smart sensors attached to different components on the machine. The problem of regularly spaced missing data, which can occur due to a variety of hardware or software issues, is one that is often overlooked in the literature surrounding CBM in industrial machines. Such missing data can cause issues in interpreting the true operational state of the machine, which can reduce the effectiveness of CBM processes. In this paper, we examine the capabilities of five data imputation techniques for handling this regular missing data and examine the impact these techniques have on machine learning (ML) classification algorithms for machine fault diagnosis. We examine the following techniques: simple mean imputation, mean imputation with outliers removed, best and worst-case imputation, and previous day imputation. Each of these methods is configured with the specific parameters that they will only consider data from the previous 24 hours, to ensure that the data is recent, and adequately represents the current status of the machine. The efficacy of each method at accurately reconstructing the missing data and the impact they have on ML classification is recorded in the results. The models are evaluated on a real-world dataset and are evaluated on a variety of common performance metrics.

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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.006
metaresearch head score (Gemma)0.015
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.841
Threshold uncertainty score0.993

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0060.015
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.006
Science and technology studies0.0010.001
Scholarly communication0.0010.001
Open science0.0020.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.113
GPT teacher head0.399
Teacher spread0.286 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it