Comparative Multivariate Characterization of Sensor Signatures Across Manufacturing Conveyor Motors during Recorded Stall Conditions

Predictive maintenance of manufacturing conveyor systems requires understanding how sensor behaviour varies among individual equipment units. This study comparatively characterized the multivariate sensor signatures of three conveyor motors, designated Motor 1 (M1), Motor 3 (M3), and Motor 4 (M4), during recorded stall conditions. The analysis considered temperature (TempC), raw sensor output (Raw), x-, y-, and z-axis measurements, and a derived three-axis resultant magnitude, with available speed records examined as contextual data. After exclusion of initialization observations, 965,610 valid observations were retained for M1, 923,020 for M3, and 404,003 for M4. One-minute median aggregation produced 181, 178, and 77 analytical windows, respectively. Descriptive statistics, Kruskal–Wallis tests with epsilon-squared effect sizes, Bonferroni-adjusted Mann–Whitney U tests with rank-biserial correlations, and within-motor Pearson correlations were applied. Substantial motor-level differences were observed, particularly in the x- and y-axis measurements (ε² ≈ 0.98–0.99). Temperature also differed markedly among motors. Within each motor, temperature and Raw exhibited highly consistent inverse relationships (r = −0.9991, −0.9987, and −0.9983 for M1, M3, and M4). The z-axis was strongly associated with resultant magnitude (r ≥ 0.9998). The findings demonstrate that recorded conveyor stall conditions can exhibit distinct motor-specific multivariate signatures and provide a comparative statistical baseline for subsequent condition-monitoring and predictive-maintenance modelling. Matched normal-operation data and repeated independent fault events will be required to est

Authors

Institutions

Publication Details

Published
2026-11-15
DOI
https://doi.org/10.54117/9t9a4d67
Primary Topic
Machine Fault Diagnosis Techniques
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Comparative Multivariate Characterization of Sensor Signatures Across Manufacturing Conveyor Motors during Recorded Stall Conditions

Olusesan Orebanjo, Lucky Olatunde ODEJIMI, Olorunleke Aregbe
Machine Fault Diagnosis Techniques
article

Comparative Multivariate Characterization of Sensor Signatures Across Manufacturing Conveyor Motors during Recorded Stall Conditions

Olusesan Orebanjo, Lucky Olatunde ODEJIMI, Olorunleke Aregbe
article en

Abstract

Predictive maintenance of manufacturing conveyor systems requires understanding how sensor behaviour varies among individual equipment units. This study comparatively characterized the multivariate sensor signatures of three conveyor motors, designated Motor 1 (M1), Motor 3 (M3), and Motor 4 (M4), during recorded stall conditions. The analysis considered temperature (TempC), raw sensor output (Raw), x-, y-, and z-axis measurements, and a derived three-axis resultant magnitude, with available speed records examined as contextual data. After exclusion of initialization observations, 965,610 valid observations were retained for M1, 923,020 for M3, and 404,003 for M4. One-minute median aggregation produced 181, 178, and 77 analytical windows, respectively. Descriptive statistics, Kruskal–Wallis tests with epsilon-squared effect sizes, Bonferroni-adjusted Mann–Whitney U tests with rank-biserial correlations, and within-motor Pearson correlations were applied. Substantial motor-level differences were observed, particularly in the x- and y-axis measurements (ε² ≈ 0.98–0.99). Temperature also differed markedly among motors. Within each motor, temperature and Raw exhibited highly consistent inverse relationships (r = −0.9991, −0.9987, and −0.9983 for M1, M3, and M4). The z-axis was strongly associated with resultant magnitude (r ≥ 0.9998). The findings demonstrate that recorded conveyor stall conditions can exhibit distinct motor-specific multivariate signatures and provide a comparative statistical baseline for subsequent condition-monitoring and predictive-maintenance modelling. Matched normal-operation data and repeated independent fault events will be required to est

Vol. 1(1)
Igbinedion University (NG)
Machine Fault Diagnosis Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon