• Notice: Due to the high submission rate this month, decisions may take longer than usual. We appreciate your patience.

Journal of Scientific Reports

Hidden Faults Under Partial Sensor Acquisition: Revisiting the AI4I-PMDI Benchmark and the Value of Machine History

Author (s)

Christiana Lebbie, José da Conceição Ernesto Langa Júnior, Marvin Sinclair Mkaliainga, & Chernor Illah Jalloh

Abstract

This study audits AI4I-PMDI, a public predictive maintenance benchmark with inspection-dependent missing values built on the AI4I 2020 data, and finds that it is easier than the same data with nothing missing. Its design assigns every failure record to an inspection type that measures that failure’s causal sensors, so the published file contains no hidden faults, that is, faults recorded under an inspection that did not measure all the sensors their cause depends on. XGBoost reaches a PR-AUC (the area under the precision-recall curve, which summarises how well faults are ranked above normal records) of 0.878 on the published schedule but only 0.778 when no values are missing. The study separates random dropout, the usual way of simulating missing sensors, from schedule-dependent missingness, in which the inspection plan can leave out exactly the sensors that respond to a fault. To test the second case, the benchmark was rebuilt from the AI4I 2020 values so that a failure can fall under any inspection type. All models were evaluated with five-fold cross-validation grouped by machine, at fixed false-alarm rates (the share of normal records that trigger an alarm), and compared with a paired bootstrap over machines. Under the realistic schedule PR-AUC falls to 0.452, and at one false alarm per 100 normal records only 20% of hidden faults are detected; a model developed on the published schedule detects just 4%. Imputation, missingness indicators and separate models for each inspection type do not close this gap. Adding the last earlier reading of each sensor from the same machine raises PR-AUC by 0.130 (95% CI 0.088 to 0.165) and hidden-fault recall from 20% to 45%. The gain holds across five classifiers, and history features with XGBoost outperform GRU-D, a recurrent model designed for missing observations, on this benchmark. On C-MAPSS FD001 the gain is in the same direction; on MetroPT-3 history ranks windows better but detects leaks later; a combined rule recovers the leaks that history alone misses but does not outperform current readings alone. The benefit comes from the machine’s history rather than from the exact way it is encoded. Benchmarks with schedule-dependent missing values should therefore also be evaluated under schedules that can hide faults, and monitoring systems should keep each sensor’s last reading for every machine.

Key words: Predictive maintenance, Partial sensor acquisition, Missing data, Hidden faults, Fault identification, Benchmark evaluation, Gradient boosting, AI4I-PMDI.

Download PDF

Title:Hidden Faults Under Partial Sensor Acquisition: Revisiting the AI4I-PMDI Benchmark and the Value of Machine History
Author:Christiana Lebbie, José da Conceição Ernesto Langa Júnior, Marvin Sinclair Mkaliainga, & Chernor Illah Jalloh
Journal Name:Journal of Scientific Reports
Website:http://ijsab.com/jsr
ISSN:ISSN: 2708-7085 (Online), ISSN: 3079-9317 (Print)
PublisherIJSAB International
DOI:https://doi.org/10.58970/JSR.1258
Media:Online
Volume:15
Issue:1
Acceptance Date:20/11/2026
Date of Publication:22/11/2026
PDF URL:http://ijsab.com/wp-content/uploads/1258.pdf
Free download:Available
Page:415-434
First Page:415
Last Page:434
Paper Type:Research paper
Current Status:Published

Cite This Article:

Lebbie, C., Langa Júnior, J. da C. E., Mkaliainga, M. S., & Jalloh, C. I. (2026). Hidden Faults Under Partial Sensor Acquisition: Revisiting the AI4I-PMDI Benchmark and the Value of Machine History, Journal of Scientific Reports, 15(1), 415-434. https://doi.org/10.58970/JSR.1258

About Author (s)

Christiana Lebbie (Corresponding Author), School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China. ORCID: https://orcid.org/0009-0001-7110-3651

José da Conceição Ernesto Langa Júnior, School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China; Marshal Samora Machel Military Academy, Office of Study and Planning, Nampula, Mozambique. ORCID: https://orcid.org/0009-0007-4881-3667

Marvin Sinclair Mkaliainga, School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China; National AIDS Commission, ICT Department, Lilongwe, Malawi. ORCID: https://orcid.org/0009-0003-0882-0900

Chernor Illah Jalloh, School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China. ORCID: https://orcid.org/0009-0002-4803-1474

 

Download PDF

DOI: https://doi.org/10.58970/JSR.1258

This Post Has Been Viewed 2,375 Times

Summarize this article with:
ChatGPT
ChatGPT
Perplexity
Perplexity
Mistral
Mistral
HuggingChat
HuggingChat
You.com
You.com
Grok
Grok