This research paper investigates the integration of Explainable Artificial Intelligence (XAI) into Predictive Maintenance (PdM) systems, aiming to enhance transparency, interpretability, and reliability in industrial applications. The primary contribution is the introduction of the Explainability Parameters (XPA) framework, which offers a structured methodology for evaluating and applying XAI in PdM. The study systematically reviews recent advancements and challenges in the literature, categorising explanations into pre-modelling, in-modelling, and post-modelling processes. It presents and analyses significant case studies across various industrial sectors to illustrate the practical implications and hurdles of XAI methodologies. Key findings indicate that while XAI significantly improves the effectiveness and trustworthiness of PdM by clarifying model predictions, its implementation is hindered by the complexity of industrial data and the absence of standardised evaluation methods. The XPA framework addresses these challenges by providing tailored metrics for specific applications and advocating for a multi-phase approach to convert technical outputs into actionable maintenance recommendations. The originality of this paper lies in its comprehensive review and the establishment of rigorous standards for assessing XAI methodologies, thereby bridging the gap between theoretical frameworks and practical applications. By promoting adaptable XAI frameworks that cater to real-world industrial needs, this study fosters trust in automated decision-making processes. It enhances the overall understanding of XAI's role in PdM.

The article presents a five-year industrial validation of eliminating open gear drives in spiral classifiers by implementing a direct drive with a torque arm, alongside an assessment of cumulative effects on reliability, process efficiency, and operating economics. The relevance of the study is conditioned by the fact that a substantial share of the classifier fleet remains structurally obsolete: open gear trains constitute the root cause of mechanical instability (wear, lubricant leakage, misalignment) while simultaneously degrading the quality of diagnostic signals, thereby impeding the deployment of PdM/AI. The objective is to deliver a comprehensive, instrumentally substantiated evaluation of the long-term reliability and economic feasibility of direct drive under real-world conditions, and to demonstrate how removal of the failure root cause creates a data-ready mechanical platform for predictive maintenance and digital twins. The novelty consists in an industry-scale confirmation (January 2020, June 2025) of a fundamental transition from managing wear consequences to eliminating wear at the kinematic-scheme level: a sealed gearmotor (IP66) in combination with a torque arm and flanged connection obviates the open gear pair, dramatically elevating the vibration signal-to-noise ratio and rendering vibrodata coherent for PdM. It is shown that mechanical stabilization of the drive is in itself a critical precondition for trustworthy condition analytics. The principal findings confirm a multifactor modernization effect: a 33% increase in section throughput and a 19% rise in classification efficiency; 100% drive technical availability with zero unplanned downtime over 43,800 h; a lower confidence bound of MTBF at 14,600 h versus a characteristic service life of ~2,800 h for traditional drives; a persistently low vibration level < 2.0 mm/s (ISO 10816 category A) instead of 4.5–7.8 mm/s (C) for open gears; a 20% OPEX reduction and a 95% decrease in lubricant consumption, with payback in 14–18 months. The article will be of use to concentrator and plant managers, mechanical engineers, and reliability specialists.

Manufacturers employ AI for monitoring vehicle mileage, inspecting components, and scheduling maintenance. Past studies underscore the need for auto-related plans to prioritize environmental protection, concentrating on AI-driven environmental solutions promoted by AI for Good. AI enhances brand success by improving investment, technology, and promotional capabilities. This study emphasizes consistency in AI application across the automotive value chain for brand sustainability. A web-based poll surveyed 120 AI users in marketing, HR, sustainability, as well as 180 sustainability specialists and regulators. The primary goal is to assess, via structural model evaluation, how extraneous variables affect the development of AI-powered brand sustainability strategies. The study highlights AI's sustainability benefits in the automotive industry improving transportation safety, forecasting maintenance, and creating eco-friendly vehicles. However, challenges involve over-reliance on AI, predicting human behavior, and addressing sustainability threats. AI development should consider regional differences, prioritizing openness, policy harmony, and consumer agency. These findings aid marketing and HR professionals in devising customer-centric long-term plans.

Accurate Remaining Useful Life (RUL) prediction is essential for reliable battery management and cost-effective maintenance in lithium-ion energy storage applications. This study proposes a leakage-safe learning framework for battery RUL prediction from numerical cycling features, emphasizing realistic generalization to unseen batteries through group-aware splitting. The core contribution is a proper out-of-fold (OOF) stacking ensemble trained under GroupKFold to prevent information leakage across samples from the same battery while enabling an effective meta-learner to combine diverse learners. Experiments are conducted on a public Battery RUL dataset from Kaggle, and performance is evaluated using complementary regression metrics (R², MAE, RMSE) and robust percentage errors (sMAPE, WAPE). Results show that the proposed stacking approach (OOF GroupKFold with Meta-XGBoost) achieves the best overall performance (R² = 0.999550, MAE = 5.297907, RMSE = 6.834146, sMAPE = 3.080569, WAPE = 0.958618), outperforming strong baselines including XGBoost and Random Forest. These findings confirm that leakage-safe group-aware stacking can significantly enhance accuracy and stability for battery RUL prediction in practical deployment settings.

The FMCG sector in developing nations is still not prepared to withstand any disruption brought on by the worldwide pandemic. In order to adapt to the new normal, businesses must make both micro and broad changes to their supply chain strategy. The goal of this research is to create plans to minimize any disruptions caused by upcoming pandemics. To restore the broken supply chain, a number of new implications and adjustments to the current attributes were proposed in the areas of sourcing, manufacturing, and distribution. Finding the fundamental drivers that are frequently impacted by the disturbance is part of the technique. The afflicted locations were the focus of the models' development. The ideas work as preventative measures intended to thwart the disturbance when and if it happens. In order to assess the model's viability, the Key Performance Indicators (KPI) value was ultimately retrieved with the aid of 25 industry experts. These suggestions may result in improved transparency, real-time monitoring, cost effectiveness, and responsiveness, among other benefits. Our analysis indicates that the KPI scores for procurement, production, and distribution are 92.86%, 82.14%, and 87.50%, respectively. The models' total viability is 87.50%. The most recent Covid-19 pandemic has provided us with a vivid illustration of what could go wrong in such circumstances. In both pandemic and non-pandemic conditions, the adaptation of stated suggestions at the aspect of sourcing, production, and distribution might result in a significant shift to organization-wide activities.