# Zero-Shot Motor Health Monitoring by Blind Domain Transition

arXiv: https://arxiv.org/abs/2212.06154 · HTML: https://mlsanity.com/paper/2212.06154/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 68 references that are in the map.
- First posted on arXiv 12 Dec 2022.

## Builds on (most cited first, 16 of 16)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Self-Organized Operational Neural Networks with Generative Neurons](https://mlsanity.com/paper/2004.11778/) (2020)
- [Operational Neural Networks](https://mlsanity.com/paper/1902.11106/) (2019)
- [Self-Organized Operational Neural Networks for Severe Image Restoration Problems](https://mlsanity.com/paper/2008.12894/) (2020)
- [FastONN -- Python based open-source GPU implementation for Operational Neural Networks](https://mlsanity.com/paper/2006.02267/) (2020)
- [Heterogeneous Multilayer Generalized Operational Perceptron](https://mlsanity.com/paper/1804.05093/) (2018)
- [Exploiting Heterogeneity in Operational Neural Networks by Synaptic Plasticity](https://mlsanity.com/paper/2009.08934/) (2020)
- [Real-Time Patient-Specific ECG Classification by 1D Self-Operational Neural Networks](https://mlsanity.com/paper/2110.02215/) (2021)
- [Real-Time Glaucoma Detection from Digital Fundus Images using Self-ONNs](https://mlsanity.com/paper/2109.13604/) (2021)
- [Robust Peak Detection for Holter ECGs by Self-Organized Operational Neural Networks](https://mlsanity.com/paper/2110.02381/) (2021)
- [Blind ECG Restoration by Operational Cycle-GANs](https://mlsanity.com/paper/2202.00589/) (2022)
- [Global ECG Classification by Self-Operational Neural Networks with Feature Injection](https://mlsanity.com/paper/2204.03768/) (2022)
- [Operational vs Convolutional Neural Networks for Image Denoising](https://mlsanity.com/paper/2009.00612/) (2020)
- [Machine Learning and Deep Learning Algorithms for Bearing Fault Diagnostics -- A Comprehensive Review](https://mlsanity.com/paper/1901.08247/) (2019)
- [BM3D vs 2-Layer ONN](https://mlsanity.com/paper/2103.03060/) (2021)
- [Speech Command Recognition in Computationally Constrained Environments with a Quadratic Self-organized Operational Layer](https://mlsanity.com/paper/2011.11436/) (2020)

## Built on by (most cited first, 4 of 4)

- [Expert Operational GANS: Towards Real-Color Underwater Image Restoration](https://mlsanity.com/paper/2507.11562/) (2025)
- [Exploring Sound vs Vibration for Robust Fault Detection on Rotating Machinery](https://mlsanity.com/paper/2312.10742/) (2023)
- [High-Quality and Full Bandwidth Seismic Signal Synthesis using Operational GANs](https://mlsanity.com/paper/2407.11040/) (2024)
- [Multi-Pass, Multi-View Blended Learning for High-Fidelity Volumetric CT Synthesis from Chest X-Rays](https://mlsanity.com/paper/2609.09920/) (2026)

## Abstract (arXiv)

Continuous long-term monitoring of motor health is crucial for the early detection of abnormalities such as bearing faults (up to 51% of motor failures are attributed to bearing faults). Despite numerous methodologies proposed for bearing fault detection, most of them require normal (healthy) and abnormal (faulty) data for training. Even with the recent deep learning (DL) methodologies trained on the labeled data from the same machine, the classification accuracy significantly deteriorates when one or few conditions are altered. Furthermore, their performance suffers significantly or may entirely fail when they are tested on another machine with entirely different healthy and faulty signal patterns. To address this need, in this pilot study, we propose a zero-shot bearing fault detection method that can detect any fault on a new (target) machine regardless of the working conditions, sensor parameters, or fault characteristics. To accomplish this objective, a 1D Operational Generative Adversarial Network (Op-GAN) first characterizes the transition between normal and fault vibration signals of (a) source machine(s) under various conditions, sensor parameters, and fault types. Then for a target machine, the potential faulty signals can be generated, and over its actual healthy and synthesized faulty signals, a compact, and lightweight 1D Self-ONN fault detector can then be trained to detect the real faulty condition in real time whenever it occurs. To validate the proposed approach, a new benchmark dataset is created using two different motors working under different conditions and sensor locations. Experimental results demonstrate that this novel approach can accurately detect any bearing fault achieving an average recall rate of around 89% and 95% on two target machines regardless of its type, severity, and location.