We present a novel decision-making framework for accelerated degradation tests and predictive maintenance that exploits prior knowledge and experimental data on the system’s state. As a framework for sequential decision making in these areas, dynamic programming and reinforcement learning are considered, along with data-driven degradation learning when necessary. Furthermore, we illustrate both stochastic and machine learning degradation models, which are integrated in the framework, using data-driven methods. These methods are presented as a valuable tool for designing life-testing experiments and for maintaining lithium-ion batteries.
Advances in Industry 4.0 and the emergence of Industry 5.0 are driving the development of intelligent, sustainable manufacturing systems, where embedded sensing and real-time health diagnostics play a critical role. However, implementing robust predictive maintenance in production environments remains challenging due to the variability in machine operations and the lack of access to internal control data. This paper introduces a lightweight, embedded-compatible framework for health status signature extraction based on empirical mode decomposition (EMD), leveraging only data from a single triaxial accelerometer. The core of the proposed method is a cycle-synchronized segmentation strategy that uses accelerometer-derived velocity profiles and cross-correlation to align signals with machining cycles, eliminating the need for controller or encoder access. This ensures process-aware decomposition that preserves the operational context across diverse and dynamic machining conditions to address the inadequate segmentation of unstable process data that often fails to capture the full scope of the process, resulting in misinterpretation. The performance is evaluated on a challenging real-world manufacturing benchmark where the extracted intrinsic mode functions (IMFs) are analyzed in the frequency domain, including quantitative evaluation. As results show, the proposed method shows its effectiveness in detecting subtle degradations, following a low computational footprint, and its suitability for deployment in embedded predictive maintenance systems on brownfield or controller-limited machinery.
Lithium-ion batteries are widely used across diverse applications due to their high energy density, long cycle life, and fast charging capabilities. As battery-powered systems become increasingly critical, accurate estimation of the Remaining Useful Life (RUL) is essential for ensuring reliability, safety, and effective maintenance planning. This work investigates Evidential Deep Learning (EDL) for data-driven RUL estimation and introduces a novel risk-aware loss function designed to enhance both predictive accuracy and uncertainty quantification in the End-of-Life (EoL) region, where precise and trustworthy predictions are most needed. Using a publicly available dataset of lithium iron phosphate (LFP) cells, we benchmark the proposed approach against a baseline Conv–LSTM model, Monte Carlo (MC) Dropout, and Deep Ensembles. The results show that integrating the risk-aware loss into the EDL framework substantially improves the calibration of predictive uncertainty while achieving state-of-the-art accuracy near EoL. Unlike MC Dropout and Deep Ensembles, which exhibit increasing or unstable uncertainty as degradation accelerates, the proposed EDL model demonstrates a consistent reduction in uncertainty and significantly higher reliability in late-stage predictions. The findings indicate that the risk-aware evidential framework offers a reliable and computationally efficient solution for battery RUL estimation, enabling more informed decision-making in both safety-critical and consumer-oriented applications.
Predictive maintenance in industrial machinery relies on the timely detection of component faults to prevent costly downtime. Rolling bearings, being critical elements, are particularly prone to defects such as outer race faults and ball spin defects, which manifest as characteristic vibration patterns. In this study, we introduce a novel bearing vibration dataset collected on a testbench under both constant and variable rotational speeds (0–5000 rpm), encompassing healthy and faulty conditions. The dataset was used for failure classification and further enriched through feature engineering, resulting in input features that include raw acceleration, signal envelopes, and time- and frequency-domain statistical descriptors, which capture fault-specific signatures. To quantify prediction uncertainty, two different approaches are applied, providing confidence measures alongside model outputs. Our results demonstrate the progressive improvement of classification accuracy from 87.2% using only raw acceleration data to 99.3% with a CNN-BiLSTM (Convolutional Neural Network–Bidirectional Long Short-Term Memory) ensemble and advanced features. Shapley Additive Explanation (SHAP)-based explainability further validates the relevance of frequency-domain features for distinguishing fault types. The proposed methodology offers a robust and interpretable framework for industrial fault diagnosis, capable of handling both stationary and non-stationary operating conditions.
Ultra-short-term photovoltaic (PV) power forecasts are vital for secure grid operation as solar penetration rises. We propose a two-stage hybrid framework, WDT–CRMABIL–Fusion. In Stage 1, we apply a three-level discrete wavelet transform to PV power and key meteorological series (shortwave radiation and panel irradiance). We then forecast the approximation and detail sub-series using specialized component predictors: a 1D-CNN with dual residual multi-head attention (feature-wise and time-wise) together with a BiLSTM. In Stage 2, a compact dense fusion network recombines the component forecasts into the final PV power trajectory. We use 5-min data from a PV plant in Milan and evaluate 5-, 10-, and 15-min horizons. The proposed approach outperforms strong baselines (DCC+LSTM, CNN+LSTM, CNN+BiLSTM, CRMABIL direct, and WDT+CRMABIL direct). For the 5-min horizon, it achieves MAE = 1.60 W and RMSE = 4.21 W with = 0.943 and CORR = 0.973, compared with the best benchmark (MAE = 3.87 W; RMSE = 7.89 W). The gains persist across K-means++ weather clusters (rainy/sunny/cloudy) and across seasons. By combining explicit multi-scale decomposition, attention-based sequence learning, and learned fusion, WDT–CRMABIL–Fusion provides accurate and robust ultra-short-term PV forecasts suitable for storage dispatch and reserve scheduling.
The resilience of electricity networks to extreme weather is an essential component of sustainable energy systems, as power interruptions can affect essential services, economic activities, public safety, and the integration of renewable energy sources. However, this assessment can be challenging due to the inherent differences and complexities between weather and grid data. To address this issue, we developed a data pipeline to acquire, prepare, and integrate power grid outage records, meteorological measurements, and lightning strike data into a unified relational database. The framework was applied to the Italian power grid, with detailed regional analyses conducted for Piedmont and Campania. The results show that, for more than 90% of the matched weather-related failures, at least one relevant weather condition was identified in the integrated datasets. Rainfall showed the most widespread association with failures throughout the year, while lightning was particularly relevant during summer and snowfall during colder months. The proposed framework provides a reproducible basis for monitoring weather-related infrastructure vulnerability and can support evidence-based maintenance prioritization, climate adaptation, and resilience-oriented grid planning. By facilitating the identification of regional risk patterns, the approach contributes to the development of more reliable and sustainable electricity infrastructure.