Aug 2026· International Conference on Circuit, Power and Computing Technologies· pp. 1909-1916· 0 citations· 10 references
Abstract
With the growing complexity and aging of civil infrastructure, they must be monitored by an intelligent system and predictive maintenance solutions must be provided for the safety and reliability of the structures. The proposed architecture in this paper is founded on the idea of using the concept of AI to enable real-time monitoring and prediction of damage in smart civil infrastructure using the Digital Twin. The proposed framework integrates the three aspects of the IoT-based sensor network, cloud-edge computing and deep learning models and ties them to a dynamic Digital Twin to continuously monitor the circumstances of the structure and identify anomalies. Using a combination of AI algorithms, real-time data from accelerometers, strain gauges and vibration sensors is analysed to identify damage, predict cracks and evaluate structural performance. The Digital Twin connects physical and virtual infrastructure models to enable perpetual visualization and predictive analytics in order to plan maintenance proactively. The framework improves the accuracy of monitoring, lowers inspection costs and increases the resilience of infrastructure to structural failures. The proposed system can be effectively implemented to manage intelligent and sustainable infrastructure for bridges, buildings, tunnels and smart city infrastructure.
The fast changing nature of connected vehicles requires smart systems that can monitor health in real-time and predict failures. This paper introduces an IoT-based Smart Vehicle Monitoring and Predictive Maintenance System that involves onboard sensors, edge computing, and cloud analytics to ensure high reliability and reduce unscheduled downtimes. Multi-modal transportation data (temperature, vibration, fuel consumption, and brake parameters) are continuously measured with the help of ESP32/Arduino devices connected to the CAN bus. An Extended Kalman Filter (EKF) is an algorithm that does nonlinear sensor fusion at the edge to enhance data reliability and noise minimization. The degradation prediction and Remaining Useful Life estimation of the fused time-series data are done with a Long Short-Term Memory (LSTM) network. A new adaptive thresholding system is used to dynamically regulate anomaly sensitivity according to driving context and historical trends. It was evaluated experimentally on 100,000 real-time sample divided into 70% training, 15% validation and 15% testing sample. The proposed framework was found to have 97.4% prediction accuracy with Precision (94.8%), Recall (95.6%), and F1-score (95.2%). EKF preprocessing minimized RMSE by 0.84, and it is a 56-percent improvement in estimation accuracy. The adaptive detection module reduced false positive rate to 4.1% which was 63% lower than the approaches to static threshold. The system forecasted failures almost 22 minutes earlier than it was actually detected which enhanced early detection by almost 30 percent. The edge deployment decreased latency by a factor of 4 to 160 ms, and thus, allowed the creation of nearly real-time alerts. The implementation of visualization and alert management was realized based on the use of Node-RED and Grafana dashboards, along with MQTT-based secure communication. All in all, the framework is statistically proven to be robust, scaled and applicable to next-generation intelligent vehicular IoT ecosystems.
Biswaraj Roy, B. Prasath, Ajit Kumar Singh et al.· 2026 6th International Confe...· 0 citations
Structural health information from continuous monitoring of vibration makes an important contribution to the development of a proactive approach to the management of civil infrastructure. These studies propose an artificial intelligence driven predictive monitoring framework of vibration based structural health assessment under real conditions including where the labelled damage data is unavailable. Structural behavior is evaluated according to baseline referenced deviation based on physics informed vibration features. A Structural Deviation Index is introduced to quantify deviation where median values range from the baseline measurements 0.42-0.45 to 3.68-3.92 in later monitoring tests representing progressive structural change. One-Class Support Vector Machine deviation scores reveal a corresponding deviation from close to zero to -0.76 which indicates that the classifier is highly sensitive to deviation in early stages. Band-limited spectral energy and dominant frequency are the most influential indicators with the value of permutation importance up to 0.231 and correlation coefficients up to 0.78, according to explainability analysis. The results validate that the proposed framework allows for interpretable, scalable and data-driven predictive monitoring. The study is an illustration of the possibilities of artificial intelligence to facilitate early warning, decision-making and smart infrastructure management with continuous structural health assessment.
A. Sil, Suhasini Kulkarni, Awdhesh Kumar et al.· International journal of com...· 0 citations
A number of physically meaningful indicators, including thermal instability, vibration anomalies, smoke-related features, and aggregated risk scores, have a significant impact on maintenance predictions and hence provide better operational interpretability and maintenance transparency.
Chitranjanjit Kaur, S. Chopra, Chitta Ranjan Tripathy· Automation· 0 citations
Structural health monitoring (SHM) is essential for ensuring the safety and longevity of critical civil infrastructure such as bridges, buildings, and dams. Traditional SHM approaches rely heavily on manual inspection and threshold-based alarm systems, which are prone to high false alarm rates and limited sensitivity to incipient damage. This paper proposes an intelligent SHM framework that integrates one-dimensional Convolutional Neural Networks (1D-CNN) with Long Short-Term Memory (LSTM) networks for automated damage detection from vibration sensor data acquired through Internet of Things (IoT) sensor networks. The proposed architecture employs a dual-branch feature extraction strategy: the 1D-CNN branch captures local spatial patterns from raw acceleration signals, while the LSTM branch models temporal dependencies across sequential sensor readings. An attention-based sensor fusion module aggregates information from heterogeneous sensor types including accelerometers, strain gauges, and temperature sensors, enabling comprehensive structural state assessment. Transfer learning is applied to adapt models pre-trained on large-scale simulated datasets to real-world bridge monitoring scenarios. Extensive experiments on the LANL structural damage detection dataset, the Z24 bridge benchmark, and a custom simulated structural dataset demonstrate that the proposed method achieves damage detection accuracy of 96.5%, significantly outperforming conventional machine learning baselines including SVM (84.1%), Random Forest (85.5%), and standard MLP (87.2%), while maintaining a false alarm rate below 3.2%. Ablation studies confirm the contribution of each architectural component to the overall performance.
Yijin Zhang· International Conference on...· 0 citations
The study examines the use of deep learning for predictive maintenance in real-time in the Industrial Internet of Things (IIoT) systems with the aim of improving the accuracy of the prediction of failures through affordable methods of computational intelligence. With the growing dependence of the industries on automated systems, it is critical to ensure the reliability of equipment to maintain the continuity of the processes and decrease the instances of unexpected failures. The conventional methods of maintenance that are usually based on a planned maintenance or a reactive strategy are not efficient and accurate enough to suit the new industrial environment. This paper introduces a deep learning-based architecture, which incorporates neural networks and time-series analysis to enhance the forecasting of equipment breakdowns called DeepTimeNet. Through real-time sensor data of industrial equipment, the model can track equipment health continuously to provide real-time updates and predictions of failures. The most important are significant performance improvements, as the proposed model DeepTimeNet demonstrates 95.50% of accuracy, 93.50% of precision, and 93.85% of F1-score in failure prediction. The findings demonstrate the ability of the model to predict possible failures with high precision and efficiency, and this is much better than conventional machine learning algorithms such as Support Vector Machines (SVM), Random Forest, and Logistic Regression. The paper ends with the identification of the influence of the model in enhancing cost-effectiveness and reliability in IIoT systems and offers future research directions, such as adding more sensors of the IoT, transfer learning methods, and hybrid models to further improve the prediction accuracy of complex industrial systems.
Roohee Khan, Anjali Goswami· 2026 International Conferenc...· 0 citations
An Industrial Internet of Things (IIoT)-based Predictive Maintenance System that integrates smart sensors, edge computing, cloud analytics, artificial intelligence, and digital twin technology is proposed that contributes to the development of intelligent and self-optimizing industrial environments aligned with Industry 4.0 objectives.
Gajula Prasad Gajula Prasad, Bolloju Divya Sri Bolloju Divya Sri, Dr B Ramprasad Dr B Ramprasad· International Journal of Sci...· 0 citations
