International Journal of Prognostics and Health Management

A Fault Diagnosis in Non-Stationary Systems via Interval Observers

Alexey Zhirabok — 2025-05-30

The paper is devoted to the problem of fault diagnosis in technical systems described by non-stationary linear dynamic equations under unmatched disturbances and measurement noise via interval observers. The problem is to design the observer insensitive to the disturbances and having fewer dimension than that of the original system. Such an observer generates two (upper and lower) residuals such that if zero is between these residuals, then the faults in the system are absent; if zero is out of these residuals, one concludes that a fault has occurred. The interval observer consists of two subsystems: the first one generates the lower residual, the second one the upper residual. The relations describing both subsystems are given. Theoretical results are illustrated by practical example of the electric servoactuator for which the fault diagnosis problem is solved.

Evaluating the Influence of Time Domain Feature Distributions on Estimating Rolling Bearing Flaking Size with Explainability

Osamu Yoshimatsu — 2025-05-30

To enhance the maintainability of rotating machines, such as wind turbines, where the response to bearing damage is both costly and time-consuming, it is essential to predict the progression of flaking, which is a common rolling bearing fault. Conventional rule-based methods estimate the magnitude of flaking by analyzing the time interval of feature vibrations. However, this method requires trial-and-error adjustments by experts, limiting its applicability to a wide range of rotating machines. To overcome this limitation, we developed a deep learning-based estimation model and demonstrated that its performance depends on the distribution of time-domain features in the training data, which are associated with flaking damage. We then analyzed the manner in which these feature distributions impose limitations on the estimation accuracy of the model. Additionally, we incorporated explainability using Grad-CAM to verify that the extracted features were aligned with the physical phenomena of flaking damage, thereby confirming the link between the feature vibrations and estimation results. Our experiments under various training–test split conditions indicate that time-domain shifts of these features affect the model’s performance, providing insight into how feature distributions constrain the estimation of the flaking size.

difLIME

David Solís-Martín — 2025-05-30

Predictive maintenance, within the field of Prognostics and Health Management (PHM), aims to identify and anticipate potential issues in equipment before they become serious problems. Deep Learning (DL) models, such as Deep Convolutional Neural Networks (DCNN), Long Short-Term Memory (LSTM) networks, and Transformers, have been widely adopted for this task and have shown great success. However, these models are often considered "black boxes" due to their opaque decision-making processes, making it challenging to explain their outputs to industrial equipment experts. The complexity and vast number of parameters in these models further complicate understanding their predictions.

This paper introduces a novel Explainable AI (XAI) algorithm, an extension of the well-known Local Interpretable Model-agnostic Explanations (LIME). Our approach uses a conditioned Probabilistic Diffusion Model to generate altered samples in the neighborhood of the original sample studied. We validate our method using various rotating machinery diagnosis datasets. Additionally, we compare our approach with state-of-the-art XAI methods, employing nine metrics to evaluate the desirable properties of any XAI method.

Predicting Remaining Useful Life During the Healthy Stage in Rolling Bearings

Sebastián Echeverri Restrepo — 2025-05-30

Quantitative predictions of the time before the spall initiation phase (origination of the first spall) in pristine ball bearings running under an applied load is of great industrial relevance, especially for systems that require high running accuracy and/or high-speed performance. Currently there are no available methodologies to predict the remaining life until the first spalling event exclusively from vibration signals. We present an end-to-end approach, based on deep learning (one dimensional convolutional layers combined with long short-term memory units), that is able to quantify the time before the origination of the first spall in ball bearings, having as sole input vibration measurements. The method has been validated on a set of bearings -- run to failure on independent but identical test-rigs -- which had not been considered during training.

Towards a Universal Vibration Analysis Dataset

Mert Sehri — 2025-05-30

In the realm of machine learning (ML), particularly in visual computing, ImageNet has established itself as an indispensable resource for transfer learning (TL), enabling the development of highly effective models with reduced training time and data requirements. However, the domain of vibration analysis, which is critical in fields such as predictive maintenance, structural health monitoring, and fault diagnosis, lacks a comparable large-scale, annotated dataset to facilitate similar advancements. To address this gap, we propose a dataset framework that begins with a focus on bearing vibration data as an initial step towards creating a universal dataset for vibration-based spectrogram analysis for all machinery.

The initial phase should feature a curated collection of bearing vibration signals, designed to represent a wide array of real-world scenarios, including vibration data of various public bearing datasets. To demonstrate the initial efficacy of this approach, experiments should be conducted using a state-of-the-art deep learning (DL) architecture, showing improvements in model performance when pre-trained on bearing vibration data and fine-tuned on smaller, domain-specific datasets. These findings will illustrate the potential to parallel the success of ImageNet in visual computing, but for vibration analysis.

In future iterations, this proposal will evolve to encompass a broader range of vibration signals from multiple types of machinery and sensors, with an emphasis on generating spectrogram-based representations of the data. Multi-sensor data, including signals from accelerometers, microphones, and other devices should be used, ensuring versatility for both domain-specific and generalized applications. They will be incorporated to create a more holistic and comprehensive dataset, enabling the application of advanced sensor fusion techniques in vibration analysis. Each sample will be labeled with detailed metadata, such as machinery type, operational status, and the presence or type of faults, ensuring its utility for supervised and unsupervised learning tasks. This extension will position this work as a universal resource for various industries, enhancing the ability of researchers and practitioners to apply TL to diverse vibration analysis problems. In addition to the dataset, a comprehensive framework for data preprocessing, feature extraction, and model training specific to vibration data should be developed. This framework will standardize methodologies across the research community, fostering collaboration and accelerating progress in predictive maintenance, structural health monitoring, and related fields.

In conclusion, this proposal represents a transformative step in vibration analysis, starting with bearing data as its foundation and ultimately evolving into a universal dataset for spectrograms and multi-sensor data for all machinery. By mirroring the success of ImageNet in visual computing, it has the potential to significantly improve the development of intelligent systems in industrial applications, enabling more efficient and reliable operations.

Editorial for IJPHM Special Issue on Data-driven Diagnostics in Rotating Machines

Moncef Soualhi — 2025-06-05

Rotating machines are essential in numerous sectors, including railways, energy, and robotics. However, a generalized approach for consistent monitoring across different systems remains challenging. This special issue aims to enhance the generalization and application of data-driven diagnostic methods to diverse systems, emphasizing their robustness.

Rotating machines are essential in numerous sectors, including railways, energy, and robotics. These machines exhibit unique degradation patterns and critical components that require monitoring. Despite the existence of various fault detection and diagnostic methods in current literature, only few techniques that effectively consider the different data sources and variable operating conditions are published. Furthermore, a generalized approach for consistent monitoring across different systems remains challenging. Thus, this special issue aims to enhance the generalization and

application of these methods to diverse systems, emphasizing their robustness.