Search Results (321)

Background: The growing complexity of production processes in the metal–mechanical industry demands ever more effective strategies for managing machine and equipment maintenance, as unexpected failures can incur high operational costs and compromise productivity by interrupting workflows and delaying deliveries. However, few studies have combined end-to-end data analytics and data mining methods to proactively predict and mitigate such failures. This study aims to develop and validate a comprehensive framework combining data analytics and data mining to prevent machine failures and support decision-making in a metal–mechanical manufacturing environment. Methods: First, exploratory data analytics were performed on the sensor and logistics data to identify significant relationships and trends between variables. Next, a preprocessing pipeline including data cleaning, data transformation, feature selection, and resampling was applied. Finally, a decision tree model was trained to identify conditions prone to failures, enabling not only predictions but also the explicit representation of knowledge in the form of decision rules. Results: The outstanding performance of the decision tree (82.1% accuracy and a Kappa index of 78.5%), which was modeled from preprocessed data and the insights produced by data analytics, demonstrates its ability to generate reliable rules for predicting failures to support decision-making. The implementation of the proposed framework enables the optimization of predictive maintenance strategies, effectively reducing unplanned downtimes and enhancing the reliability of production processes in the metal–mechanical industry. Full article

As the global energy transition accelerates, the integration of solar power and artificial intelligence (AI) technologies offers new pathways for sustainable local development. This study examines four Serbian municipalities—Šabac, Sombor, Pirot, and Čačak—to assess how AI-enabled solar power systems can enhance energy resilience, reduce emissions, and support community-level sustainability goals. Using a mixed-method approach combining spatial analysis, predictive modeling, and stakeholder interviews, this research study evaluates the performance and institutional readiness of local governments in terms of implementing intelligent solar infrastructure. Key AI applications included solar potential mapping, demand-side management, and predictive maintenance of photovoltaic (PV) systems. Quantitative results show an improvement >60% in forecasting accuracy, a 64% reduction in system downtime, and a 9.7% increase in energy cost savings. These technical gains were accompanied by positive trends in SDG-aligned indicators, such as improved electricity access and local job creation in the green economy. Despite challenges related to data infrastructure, regulatory gaps, and limited AI literacy, this study finds that institutional coordination and leadership commitment are decisive for successful implementation. The proposed AI–Solar Integration for Local Sustainability (AISILS) framework offers a replicable model for emerging economies. Policy recommendations include investing in foundational digital infrastructure, promoting low-code AI platforms, and aligning AI–solar projects with SDG targets to attract EU and national funding. This study contributes new empirical evidence on the digital–renewable energy nexus in Southeast Europe and underscores the strategic role of AI in accelerating inclusive, data-driven energy transitions at the municipal level. Full article

Unexpected machine failures in industrial environments lead to high maintenance costs, unplanned downtime, and safety risks. This study proposes a proactive predictive model using a hybrid of eXtreme Gradient Boosting (XGBoost) and Neural Networks (NN) to forecast machine failures. A synthetic dataset capturing recent breakdown history and time since last failure was used to simulate industrial scenarios. To address class imbalance, SMOTE and class weighting were applied, alongside a focal loss function to emphasize difficult-to-classify failures. The XGBoost model was tuned via GridSearchCV, while the NN model utilized ReLU-activated hidden layers with dropout. Evaluation using stratified 5-fold cross-validation showed that the NN achieved an F1-score of 0.7199 and a recall of 0.9545 for the minority class. XGBoost attained a higher PR AUC of 0.7126 and a more balanced precision–recall trade-off. Sample predictions demonstrated strong recall (100%) for failures, but also a high false positive rate, with most prediction probabilities clustered between 0.50–0.55. Additional benchmarking against Logistic Regression, Random Forest, and SVM further confirmed the superiority of the proposed hybrid model. Model interpretability was enhanced using SHAP and LIME, confirming that recent breakdowns and time since last failure were key predictors. While the model effectively detects failures, further improvements in feature engineering and threshold tuning are recommended to reduce false alarms and boost decision confidence. Full article

Lubricant condition analysis is a valuable diagnostic tool for assessing engine performance and ensuring the reliable operation of diesel engines. While traditional diagnostic techniques—such as Fourier transform infrared spectroscopy (FTIR)—are constrained by slow response times, high costs, and the need for specialized personnel. In contrast, dielectric spectroscopy, impedance analysis, and soft computing offer real-time, non-destructive, and cost-effective alternatives. This review examines recent advances in integrating these techniques to predict lubricant properties, evaluate wear conditions, and optimize maintenance scheduling. In particular, dielectric and impedance spectroscopies offer insights into electrical properties linked to oil degradation, such as changes in viscosity and the presence of wear particles. When combined with soft computing algorithms, these methods enhance data analysis, reduce reliance on expert interpretation, and improve predictive accuracy. The review also addresses challenges—including complex data interpretation, limited sample sizes, and the necessity for robust models to manage variability in real-world operations. Future research directions emphasize miniaturization, expanding the range of detectable contaminants, and incorporating multi-modal artificial intelligence to further bolster system robustness. Collectively, these innovations signal a shift from reactive to predictive maintenance strategies, with the potential to reduce costs, minimize downtime, and enhance overall engine reliability. This comprehensive review provides valuable insights for researchers, engineers, and maintenance professionals dedicated to advancing diesel engine lubricant monitoring. Full article

Electric submersible pumps (ESPs) are critical for artificial lift operations; however, they are prone to frequent failures, often resulting in high operational costs and production downtime. Traditional ESP failure classifications are limited by lack of standardization and the conflation of failure modes with root causes. To address these limitations, this study proposes a new two-step integrated failure modes and root cause (IFMRC) classification system. The new framework clearly distinguishes between failure modes and root causes, providing a systematic, structured approach that enhances fault diagnosis and failure analysis and can lead to better failure prevention strategies. This methodology was validated using a case study of over 4000 ESP installations. The data came from Egypt’s Western Desert, covering a decade of operational data. The sources included ESP databases, workover records, and detailed failure investigation (DIFA) reports. The failure modes were categorized into electrical, mechanical, hydraulic, chemical, and operational types, while root causes were linked to environmental, design, operational, and equipment factors. Statistical analysis, in this case study, revealed that motor short circuits, low flow conditions, and cable short circuits were the most frequent failure modes, with excessive heat, scale deposition, and electrical grounding faults being the dominant root causes. This study underscores the importance of accurate root cause failure classification, robust data acquisition, and expanded failure diagnostics to improve ESP reliability. The proposed IFMRC framework addresses limitations in conventional taxonomies and facilitates ongoing enhancement of ESP design, operation, and maintenance in complex field conditions. Full article

The continuous, effective operation of grid-connected photovoltaic (GCPV) systems depends on dependable inverter failure detection. Early, precise fault diagnosis improves general system dependability, lowers maintenance costs, and saves downtime. Although computing efficiency remains a difficulty, particularly in resource-limited contexts, machine learning-based fault detection presents interesting prospects in accuracy and responsiveness. By streamlining data complexity and allowing faster and more effective fault diagnosis, dimensionality reduction methods play vital role. Using dimensionality reduction and ML techniques, this work explores inverter fault detection in GCPV systems. Photovoltaic inverter operational data was normalized and preprocessed. In the next step, dimensionality reduction using Principal Component Analysis (PCA) and autoencoder-based feature extraction were explored. For ML training four classifiers which include Random Forest (RF), logistic regression (LR), decision tree (DT), and K-Nearest Neighbors (KNN) were used. Trained on the whole standardized dataset, the RF model routinely produced the greatest accuracy of 99.87%, so efficiently capturing complicated feature interactions but requiring large processing resources and time of 36.47sec. LR model showed reduction in accuracy, but very fast training time compared to other models. Further, PCA greatly lowered computing demands, especially improving inference speed for LR and KNN. High accuracy of 99.23% across all models was maintained by autoencoder-derived features. Full article

Industrial maintenance has shifted from reactive repairs and calendar-based servicing toward data-driven predictive strategies. This paper presents a non-intrusive, low-cost IoT hardware platform for sustainable predictive maintenance of rotating machinery. The system integrates an ESP32-S3 sensor node that captures vibration (100 kHz) and temperature data, performs local logging, and communicates wirelessly. An automated spectral band segmentation framework is introduced, comparing equal-energy, linear-width, nonlinear, clustering, and peak–valley partitioning methods, followed by a weighted feature scheme that emphasizes high-value bands. Three unsupervised one-class classifiers—transformer autoencoders, GANomaly, and Isolation Forest—are evaluated on these weighted spectral features. Experiments conducted on a custom pump test bench with controlled anomaly severities demonstrate strong anomaly classification performance across multiple configurations, supported by detailed threshold-characterization metrics. Among 150 model–segmentation configurations, 25 achieved perfect classification (100% precision, recall, and F1 score) with ROC-AUC = 1.0, 43 configurations achieved ≥90% accuracy, and the lowest-performing setup maintained 81.8% accuracy. The proposed end-to-end solution reduces the downtime, lowers maintenance costs, and extends the asset life, offering a scalable, predictive maintenance approach for diverse industrial settings. Full article

Reducing setup costs and improving product quality are critical objectives in a sustainable production processes. The significance of these goals lies in their direct impact on efficiency. It affects competitiveness and customer satisfaction. Businesses can reduce setup costs to maximize resource usage. It can reduce downtime between production runs and improve overall operational agility. Sustained performance and expansion in contemporary manufacturing environments focus on setup cost reduction and product quality improvement. The present paper discusses a production inventory model for the product, which produces by-products as secondary products from the same manufacturing process. Setup cost is reduced for the setup of production and refining processes. A production process may change from being under control to an uncontrolled one. As a result of this, imperfect products are formed. This paper considers product quality improvement for both produced and processed items. The outcome shows that dealing with by-products helps make the system more profitable. Sensitivity analysis is performed for various costs and parameters. Mathematica 11 software was used for calculation and graphical work. Full article

Large turbine generators rely on shaft earthing brushes to safely divert harmful shaft currents to ground, protecting bearings from electrical damage. This paper presents a novel deep learning-based diagnostic framework to detect and classify faults in shaft earthing brushes of large turbine generators. A key innovation lies in the use of FFT-derived spectrograms from both voltage and current waveforms as dual-channel inputs to the CNN, enabling automatic feature extraction of time–frequency patterns associated with different SEB fault types. The proposed framework combines advanced signal processing and convolutional neural networks (CNNs) to automatically recognize fault-related patterns in shaft grounding current and voltage signals. In the approach, raw time-domain signals are converted into informative time–frequency representations, which serve as input to a CNN model trained to distinguish normal and faulty conditions. The framework was evaluated using data from a fleet of large-scale generators under various brush fault scenarios (e.g., increased brush contact resistance, loss of brush contact, worn out brushes, and brush contamination). Experimental results demonstrate high fault detection accuracy (exceeding 98%) and the reliable identification of different fault types, outperforming conventional threshold-based monitoring techniques. The proposed deep learning framework offers a novel intelligent monitoring solution for predictive maintenance of turbine generators. The contributions include the following: (1) the development of a specialized deep learning model for shaft earthing brush fault diagnosis, (2) a systematic methodology for feature extraction from shaft current signals, and (3) the validation of the framework on real-world fault data. This work enables the early detection of brush degradation, thereby reducing unplanned downtime and maintenance costs in power generation facilities. Full article

Tracking the state of the health of electrical insulation in high-power electric machines has always been a topic of great interest due to the high cost of downtime associated with unexpected failures. Over the years, there have been continuous efforts to develop and improve upon methods for testing and categorizing the health and expected lifetime of stator insulation. Methods such as partial discharge, surge, and dissipation factor testing are common examples. With the increasing use of high-specific-power electric machines in new applications such as traction and wind power generation, coupled with the increasing use of wide-bandgap semiconductor device-based inverters, some traditional methods for insulation health tracking may need adjustments or be combined with newer methods to remain accurate and useful. This paper outlines a review of the traditional insulation health tracking methods and newer methods and improvements that have been proposed to address the concerns and shortcomings of traditional methods. Full article

As electric multiple unit (EMU) operations and maintenance demands have expanded, spare parts supply chain management has become increasingly crucial. This study emphasizes the supply challenges of EMU spare parts, including inadequate minimum inventory levels and prolonged response times. Redesigning the OEM–railway bureau vendor-managed inventory (VMI) model contract incentive and penalty system is the key goal. Connecting the spare parts supply system with its characteristics yields a game theory model. This study analyzes and compares the equilibrium strategies and profits of supply chain members under different mechanisms for managing critical spare parts. The findings demonstrate that mechanism contracts can enhance supply chain performance in a Pareto-improving manner. An in-depth analysis of downtime loss costs, procurement challenges, and order losses reveals their effects on supply chain coordination and profit allocation, providing railway bureaus and OEMs with a theoretical framework for supply chain decision-making. This study offers theoretical justification and a framework for decision-making on cooperation between OEMs and railroad bureaus in the management of spare parts supply chains, particularly for extensive EMU operations. Full article

Predictive maintenance (PdM) is a proactive strategy that enhances safety, minimizes unplanned downtime, and optimizes operational costs by forecasting equipment failures before they occur. This study presents a novel Field Programmable Gate Array (FPGA)-accelerated predictive maintenance framework for UAV engines using a Singular Value Decomposition (SVD)-optimized Long Short-Term Memory (LSTM) model. The model performs binary classification to predict the likelihood of imminent engine failure by processing normalized multi-sensor data, including temperature, pressure, and vibration measurements. To enable real-time deployment on resource-constrained UAV platforms, the LSTM’s weight matrices are compressed using Singular Value Decomposition (SVD), significantly reducing computational complexity while preserving predictive accuracy. The compressed model is executed on a Xilinx ZCU-104 FPGA and uses a pipelined, AXI-based hardware accelerator with efficient memory mapping and parallelized gate calculations tailored for low-power onboard systems. Unlike prior works, this study uniquely integrates a tailored SVD compression strategy with a custom hardware accelerator co-designed for real-time, flight-safe inference in UAV systems. Experimental results demonstrate a 98% classification accuracy, a 24% reduction in latency, and substantial FPGA resource savings—specifically, a 26% decrease in BRAM usage and a 37% reduction in DSP consumption—compared to the 32-bit floating-point SVD-compressed FPGA implementation, not CPU or GPU. These findings confirm the proposed system as an efficient and scalable solution for real-time UAV engine health monitoring, thereby enhancing in-flight safety through timely fault prediction and enabling autonomous engine monitoring without reliance on ground communication. Full article

Gearbox failures are a major cause of unplanned downtime and increased maintenance costs, making accurate diagnosis crucial in ensuring wind turbine reliability and cost-efficiency. However, most existing diagnostic methods fail to fully extract the spatiotemporal features in SCADA data and neglect the impact of class imbalance, thereby limiting diagnostic accuracy. To address these challenges, this paper proposes a fault diagnosis model for wind turbine gearboxes based on CNN-SA-GRU and Focal Loss. Specifically, a CNN-SA-GRU network is constructed to extract both spatial and temporal features, in which CNN is employed to extract local spatial features from SCADA data, Shuffle Attention is integrated to efficiently fuse channel and spatial information and enhance spatial representation, and GRU is utilized to capture long-term spatiotemporal dependencies. To mitigate the adverse effects of class imbalance, the conventional cross-entropy loss is replaced with Focal Loss, which assigns higher weights to hard-to-classify fault samples. Finally, the model is validated using real wind farm data. The results show that, compared with the cross-entropy loss, using Focal Loss improves the accuracy and F1 score by an average of 0.24% and 1.03%, respectively. Furthermore, the proposed model outperforms other baseline models with average gains of 0.703% in accuracy and 4.65% in F1 score. Full article

Machine predictive maintenance plays a critical role in reducing unplanned downtime, lowering maintenance costs, and improving operational reliability by enabling the early detection and classification of potential failures. Artificial intelligence (AI) enhances these capabilities through advanced algorithms that can analyze complex sensor data with high accuracy and adaptability. This study introduces an explainable AI framework for failure detection and classification using symbolic expressions (SEs) derived from a genetic programming symbolic classifier (GPSC). Due to the imbalanced nature and wide variable ranges in the original dataset, we applied scaling/normalization and oversampling techniques to generate multiple balanced dataset variations. Each variation was used to train the GPSC with five-fold cross-validation, and optimal hyperparameters were selected using a Random Hyperparameter Value Search (RHVS) method. However, as the initial Threshold-Based Voting Ensembles (TBVEs) built from SEs did not achieve a satisfactory performance for all classes, a meta-dataset was developed from the outputs of the obtained SEs. For each class, a meta-dataset was preprocessed, balanced, and used to train a Random Forest Classifier (RFC) with hyperparameter tuning via RandomizedSearchCV. For each class, a TBVE was then constructed from the saved RFC models. The resulting ensemble demonstrated a near-perfect performance for failure detection and classification in most classes (0, 1, 3, and 5), although Classes 2 and 4 achieved a lower performance, which could be attributed to an extremely low number of samples and a hard-to-detect type of failure. Overall, the proposed method presents a robust and explainable AI solution for predictive maintenance, combining symbolic learning with ensemble-based meta-modeling. Full article

Users of technical blades expect new generations of tools to feature reduced power requirements for process and maximized tool life. The second aspect is reflected in the reduction in costs associated with the purchase of tools and in the reduction in process line downtime due to tool replacement. Meeting these demands is particularly challenging in cutting operations involving heterogeneous materials, especially when the processed raw material contains inclusions and impurities significantly harder than the material itself. This situation occurs, among others, during flatfish skinning operations analyzed in this paper, a common process in the fish processing industry. These fish, due to their natural living environment and behavior, contain a significant proportion of hard inclusions and impurities (shell fragments, sand grains) embedded in their skin. Contact between the tool and hard inclusions causes deformation, wrapping, crushing, and even chipping of the cutting edge of planar knives, resulting in non-uniform blade wear, which manifests as areas of uncut skin on the fish fillet. This necessitates frequent tool changes, resulting in higher tooling costs and longer operating times. This study provides a unique opportunity to review the results of in-service pre-implementation tests of planar knives in the skinning operation conducted under industrial conditions. The main objective was to verify positive laboratory research results regarding the extension of technical blade tool life through optimization of sharpening conditions during grinding. Durability test results are presented for the skinning process of fillets from plaice (Pleuronectes platessa) and flounder (Platichthys flesus). The study also examined the effect of varying cooling and lubrication conditions in the grinding zone on the tool life of technical planar blades. Sharpening knives under flood cooling conditions and using the hybrid method (combining minimum quantity lubrication and cold compressed air) increased their service life in the plaice skinning process (Pleuronectes platessa) by 12.39% and 8.85%, respectively. The increase in effective working time of knives during flounder (Platichthys flesus) skinning was even greater, reaching 17.7% and 16.3% for the flood cooling and hybrid methods, respectively. Full article