# Domain-Adaptive Health Indicator Learning with Degradation-Stage Synchronized Sampling and Cross-Domain Autoencoder

Source: [Domain-Adaptive Health Indicator Learning with Degradation-Stage Synchronized Sampling and Cross-Domain Autoencoder](<https://www.sota2.com/research/paper/69b248a6d030084c22e2f9b6>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-13T05:00:04.336Z

Authors: Jungho Choo, Hanbyeol Park, Gawon Lee, Yunkyung Park, Hyerim Bae

Published: 2026-03-11T05:24:18.000Z

## Abstract

The construction of high quality health indicators (HIs) is crucial for effective prognostics and health management. Although deep learning has significantly advanced HI modeling, existing approaches often struggle with distribution mismatches resulting from varying operating conditions. Although domain adaptation is typically employed to mitigate these shifts, two critical challenges remain: (1) the misalignment of degradation stages during random mini-batch sampling, resulting in misleading discrepancy losses, and (2) the structural limitations of small-kernel 1D-CNNs in capturing long-range temporal dependencies within complex vibration signals. To address these issues, we propose a domain-adaptive framework comprising degradation stage synchronized batch sampling (DSSBS) and the cross-domain aligned fusion large autoencoder (CAFLAE). DSSBS utilizes kernel change-point detection to segment degradation stages, ensuring that source and target mini-batches are synchronized by their failure phases during alignment. Complementing this, CAFLAE integrates large-kernel temporal feature extraction with cross-attention mechanisms to learn superior domain-invariant representations. The proposed framework was rigorously validated on a Korean defense system dataset and the XJTU-SY bearing dataset, achieving an average performance enhancement of 24.1% over state-of-the-art methods. These results demonstrate that DSSBS improves cross-domain alignment through stage-consistent sampling, whereas CAFLAE offers a high-performance backbone for long-term industrial condition monitoring.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [HI construction on XJTU-SY B1-2](<https://www.sota2.com/research/sota/hi-construction-on-xjtu-sy-b1-2.md>): HI construction; XJTU-SY B1-2; Mon: 65.01.

- [HI construction on XJTU-SY B2-4](<https://www.sota2.com/research/sota/hi-construction-on-xjtu-sy-b2-4.md>): HI construction; XJTU-SY B2-4; Mon Score: 77.29.

- [Health Indicator construction on KWS (RC1-3)](<https://www.sota2.com/research/sota/health-indicator-construction-on-kws-rc1-3.md>): Health Indicator construction; KWS (RC1-3); Mon Score: 50.69.

- [HI construction on XJTU-SY Bearing1-1-b](<https://www.sota2.com/research/sota/hi-construction-on-xjtu-sy-bearing1-1-b.md>): HI construction; XJTU-SY Bearing1-1-b; Mon Score: 0.5785.

- [HI construction on XJTU-SY Bearing1-2-b](<https://www.sota2.com/research/sota/hi-construction-on-xjtu-sy-bearing1-2-b.md>): HI construction; XJTU-SY Bearing1-2-b; Mon Score: 0.5845.

- [HI construction on XJTU-SY Bearing2-3-b](<https://www.sota2.com/research/sota/hi-construction-on-xjtu-sy-bearing2-3-b.md>): HI construction; XJTU-SY Bearing2-3-b; Mon Score: 51.25.

- [Health Indicator construction on KWS AC2-2](<https://www.sota2.com/research/sota/health-indicator-construction-on-kws-ac2-2.md>): Health Indicator construction; KWS AC2-2; Mon Score: 49.65.

- [HI construction on XJTU-SY B1-1](<https://www.sota2.com/research/sota/hi-construction-on-xjtu-sy-b1-1.md>): HI construction; XJTU-SY B1-1; Mon Score: 57.02.

- [Health Indicator construction on KWS (RC1-2)](<https://www.sota2.com/research/sota/health-indicator-construction-on-kws-rc1-2.md>): Health Indicator construction; KWS (RC1-2); Mon: 50.55.

- [HI construction on XJTU-SY B2-3](<https://www.sota2.com/research/sota/hi-construction-on-xjtu-sy-b2-3.md>): HI construction; XJTU-SY B2-3; Mon Score: 50.46.

- [HI construction on XJTU-SY B2-5](<https://www.sota2.com/research/sota/hi-construction-on-xjtu-sy-b2-5.md>): HI construction; XJTU-SY B2-5; Mon Score: not recorded.

- [HI construction on XJTU-SY Bearing2-3](<https://www.sota2.com/research/sota/hi-construction-on-xjtu-sy-bearing2-3.md>): HI construction; XJTU-SY Bearing2-3; Mon Score: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.10430>)

[PDF](<https://arxiv.org/pdf/2603.10430.pdf>)
