A Comparative Experimental Study of Acoustic Emission Responses in Healthy and Locally Worn Ball Screws and Their Application to State Recognition

Acoustic emission (AE) signals from ball screws vary with operating conditions, specimen identity, and worn state; overall intensity alone incompletely characterizes wear-related changes. Two nominally identical ball screws were tested under 36 combinations of pre-tension force, load, and speed, covering healthy states and four local wear regions. Controlled comparisons quantified healthy spectral differences and changes in overall power, band power, and spectral shape relative to healthy signals from the same specimen and condition. Matched healthy references provided standardized-difference representations for a condition-paired reference-normalized mean network, evaluated for cross-specimen transfer with matched conditions, one unseen factor, and three jointly unseen factors. Healthy spectral differences associated with speed exceeded those associated with pre-tension force or load. Overall power changed in different directions across wear regions; two regions exhibited decreased 20–400 kHz power alongside increased 115–210 kHz power under 22 and 19 conditions, respectively. Bidirectionally averaged balanced accuracies were 97.15%, 94.99%, and 92.78%. The standardized difference outperformed no-reference, mismatched-reference, and logarithmic-difference controls in the most challenging task. Joint overall- and band-power analysis characterized local wear more completely, while matched-reference standardized differences supported cross-specimen healthy/worn-state recognition in this experiment.

Authors

Publication Details

Journal
Preprints.org
Published
2026-11-16
DOI
https://doi.org/10.20944/preprints202611.1536.v1
Primary Topic
Machine Fault Diagnosis Techniques
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

A Comparative Experimental Study of Acoustic Emission Responses in Healthy and Locally Worn Ball Screws and Their Application to State Recognition

Jianli Wang, Guanghui Huang
Preprints.org
Machine Fault Diagnosis Techniques
preprint

A Comparative Experimental Study of Acoustic Emission Responses in Healthy and Locally Worn Ball Screws and Their Application to State Recognition

Jianli Wang, Guanghui Huang
preprint en

Abstract

Acoustic emission (AE) signals from ball screws vary with operating conditions, specimen identity, and worn state; overall intensity alone incompletely characterizes wear-related changes. Two nominally identical ball screws were tested under 36 combinations of pre-tension force, load, and speed, covering healthy states and four local wear regions. Controlled comparisons quantified healthy spectral differences and changes in overall power, band power, and spectral shape relative to healthy signals from the same specimen and condition. Matched healthy references provided standardized-difference representations for a condition-paired reference-normalized mean network, evaluated for cross-specimen transfer with matched conditions, one unseen factor, and three jointly unseen factors. Healthy spectral differences associated with speed exceeded those associated with pre-tension force or load. Overall power changed in different directions across wear regions; two regions exhibited decreased 20–400 kHz power alongside increased 115–210 kHz power under 22 and 19 conditions, respectively. Bidirectionally averaged balanced accuracies were 97.15%, 94.99%, and 92.78%. The standardized difference outperformed no-reference, mismatched-reference, and logarithmic-difference controls in the most challenging task. Joint overall- and band-power analysis characterized local wear more completely, while matched-reference standardized differences supported cross-specimen healthy/worn-state recognition in this experiment.

Preprints.org
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