An Explainable Transfer Learning Framework Based on Acoustic Spectral Portraits for Pipeline Leak Diagnosis Across Composite Operating and Acquisition Conditions.
- 1Department of Electrical, Electronic, and Computer Engineering, University of Ulsan, Ulsan 44610, Republic of Korea.
- 2Prognosis and Diagnostics Technologies Co., Ltd., Ulsan 44610, Republic of Korea.
Abstract
This study proposes an explainable and lightweight pipeline leak-diagnosis framework based on a leak-oriented Acoustic Spectral Portrait (ASP) processing pipeline and transfer learning. The ASP processing pipeline converts one-dimensional acoustic emission signals into compact two-dimensional spectral representations through AR pre-whitening, overlapping Hann-window segmentation, zero-padded fast Fourier transform analysis, logarithmic scaling, percentile-based normalization, and temporal spectral aggregation. These spectral portraits are processed by a lightweight convolutional neural network, in which source-domain knowledge is adapted using limited labeled target-domain data. Gradient-weighted class activation mapping is further employed to provide qualitative post hoc interpretation of the spectral regions contributing to model predictions, rather than direct physical validation, supported by supplementary perturbation, model-randomization, and attribution-stability analyses. The framework was evaluated using three gas- and water-pipeline datasets through six directed source-to-target transfer tasks, with each experiment repeated 10 times using mutually exclusive data partitions. Scenario-averaged classification accuracies of 98.36%, 97.09%, and 98.58% were achieved across the three transfer scenarios. For the representative DS-1 to DS-2 transfer task, transfer learning improved target-domain accuracy from 91.80% to 96.85% while reducing target-model training time from 17.3 min for training from scratch to 9.2 min for fine-tuning. The proposed spectral portrait representation also achieved a mean scenario-averaged classification accuracy of 98.01%, outperforming conventional time-frequency representations. These results demonstrate effective source-to-target adaptation for pipeline leak diagnosis across the three investigated composite operating and acquisition domains.
Related
- Reconstruction Assisted Semi-Supervised Conformer for Bolt Looseness Diagnosis in Large-Scale Bolted Mechanical Structures Under Heterogeneous Acquisition Conditions
- Measuring Whether Explainable AI Improves Nuclear Fault Diagnosis: A Human-Centred Evaluation Framework
- XAI-ECGNet: an explainable hybrid CNN-BiLSTM framework for multi-label cardiac diagnosis classification from 12-lead ECG signals using the PTB-XL dataset
- A Multimodal Explainable Deep Learning Framework for Alzheimer's Disease Diagnosis using 3D Magnetic Resonance Imaging and Clinical Data
- A federated attention-based stacked LSTM framework for interpretable malaria diagnosis under simulated non-IID federated conditions
BibTeX
@article{ahmad2026explainable,
title = {{An Explainable Transfer Learning Framework Based on Acoustic Spectral Portraits for Pipeline Leak Diagnosis Across Composite Operating and Acquisition Conditions.}},
author = {Zahoor Ahmad and Niamat Ullah and Jong-Myon Kim},
journal = {Sensors (Basel, Switzerland)},
year = {2026},
month = oct,
doi = {10.3390/s26206521},
url = {https://europepmc.org/article/MED/42944384},
note = {CC BY},
}
RIS
TY - JOUR
TI - An Explainable Transfer Learning Framework Based on Acoustic Spectral Portraits for Pipeline Leak Diagnosis Across Composite Operating and Acquisition Conditions.
AU - Zahoor Ahmad
AU - Niamat Ullah
AU - Jong-Myon Kim
PY - 2026
DA - 2026/10/14
JO - Sensors (Basel, Switzerland)
DO - 10.3390/s26206521
UR - https://europepmc.org/article/MED/42944384
AB - This study proposes an explainable and lightweight pipeline leak-diagnosis framework based on a leak-oriented Acoustic Spectral Portrait (ASP) processing pipeline and transfer learning. The ASP processing pipeline converts one-dimensional acoustic emission signals into compact two-dimensional spectral representations through AR pre-whitening, overlapping Hann-window segmentation, zero-padded fast Fourier transform analysis, logarithmic scaling, percentile-based normalization, and temporal spectral aggregation. These spectral portraits are processed by a lightweight convolutional neural network, in which source-domain knowledge is adapted using limited labeled target-domain data. Gradient-weighted class activation mapping is further employed to provide qualitative post hoc interpretation of the spectral regions contributing to model predictions, rather than direct physical validation, supported by supplementary perturbation, model-randomization, and attribution-stability analyses. The framework was evaluated using three gas- and water-pipeline datasets through six directed source-to-target transfer tasks, with each experiment repeated 10 times using mutually exclusive data partitions. Scenario-averaged classification accuracies of 98.36%, 97.09%, and 98.58% were achieved across the three transfer scenarios. For the representative DS-1 to DS-2 transfer task, transfer learning improved target-domain accuracy from 91.80% to 96.85% while reducing target-model training time from 17.3 min for training from scratch to 9.2 min for fine-tuning. The proposed spectral portrait representation also achieved a mean scenario-averaged classification accuracy of 98.01%, outperforming conventional time-frequency representations. These results demonstrate effective source-to-target adaptation for pipeline leak diagnosis across the three investigated composite operating and acquisition domains.
SN - 1424-8220
ER -