Mid Sweden University

Autonomous condition monitoring is essential for advancing intelligent systems in both industrial and domestic Internet of Things (IoT) applications. However, continuous long-term condition monitoring is challenged by the limited energy availability for wireless sensor nodes (WSNs). Therefore, energy harvesting offers a promising approach by converting ambient or host energy into electrical power to sustain WSN operation. To bridge the gap between energy harvesting and condition monitoring, this review provides an overview and synthesis of recent advances in energy harvesting technologies tailored for condition monitoring applications. State-of-the-art developments in energy harvesting are categorized into six domains: healthcare, ocean, machinery, grid, railway, and infrastructure. The characteristics of these energy sources and their domain-specific monitoring requirements are analyzed. Furthermore, this review examines harvesting transducers, structural designs, and optimization methods employed in energy harvesters. Finally, the review discusses current challenges and future prospects for energy-autonomous condition monitoring systems, aiming to support the deployment of sustainable IoT sensing solutions. 

Structural health monitoring of offshore oil and gas pipelines is critical for energy security and environmental protection. Acoustic emission technology has been widely adopted as a non-destructive approach for pipeline valve leakage detection. However, it faces severe challenges in real marine environments. Offshore platform pipelines exhibit strong background noise interference that significantly undermines leakage signal identifiability. This requires distributed sensor deployment to expand monitoring coverage. But installation constraints cause spatially uneven distributions that limit information propagation and create monitoring blind spots. Consequently, collaborative response patterns among multiple sensors are difficult to extract effectively. Traditional fusion methods fail to exploit spatial dependencies between sensors. To address these challenges, this paper proposes a novel graph learning-based end-to-end intelligent monitoring method. The method employs a time-frequency domain graph to suppress noise interference and encode spatial relationships between sensors. Building upon this, a spatial-topological adaptive graph neural network (STAG) captures global collaborative patterns and balances information propagation in non-uniform networks. On datasets simulating real offshore platform pipeline leakage, the proposed method achieved 94.64%-97.74% accuracy and maintained 91.56% under -15 dB noise. Generalization and superiority were validated on public benchmark datasets. Statistical tests confirmed the method significantly outperformed existing approaches. With only 30% training data, accuracy exceeded 88%. Ablation studies validated component effectiveness. STAG required only three layers for high-precision detection and localization. This research provides an effective solution for intelligent offshore pipeline monitoring with significant engineering value.

Intelligent acoustic emission-based pipeline leak detection technology plays a critical role in Internet of Things structural health monitoring for offshore platforms. However, traditional deep networks possess large parameter counts and high computational complexity, making them infeasible for deployment on resource-constrained edge nodes, while lightweight methods universally adopt single-scale feature extraction and cannot simultaneously capture short-duration burst and long-range attenuation characteristics of acoustic emission signals, resulting in insufficient discriminative capability for adjacent valves. To address this, this paper proposes Tiny Leak Sense Net (TinyLSN), a novel lightweight leak localization framework specifically designed for Internet of Things edge nodes. TinyLSN achieves optimal balance between computational efficiency and detection performance through three innovative components we designed including the Inverted Residual Block (IRB), Multi-Scale Dilated Perception Module (MSDPM), and Large Kernel Feed-Forward Network (LK-FFN), which respectively enhance cross-channel interactions, capture multi-scale temporal features, and extract global attenuation patterns. On our self-constructed experimental dataset simulating real offshore platform operational pipeline leakage, TinyLSN achieved detection accuracy of 97.11% to 97.45% and an extremely low false positive rate of 0.27% to 0.32%, significantly outperforming lightweight baseline methods. Validation on publicly available benchmark datasets further confirmed its generalization capability. When deployed on the STM32H7B3I-DK microcontroller, TinyLSN requires only 267.16 KiB Flash memory and achieves 3.417 ms inference latency. Furthermore, TinyLSN maintains over 90% accuracy under strong noise and achieves 94.83% accuracy with only 10% training samples, fully validating its reliability in harsh industrial environments and providing an efficient and feasible solution for offshore platform Internet of Things edge intelligence.

Enabling broad use of electromagnetic energy harvesting in wireless sensor screws requires robust systems that work with weak vibrations and varying frequency profiles. This contribution presents an energy management circuit incorporating two cooperating DC-DC converters controlled by self-powered MOSFET switches and a passive voltage multiplier enabling low-voltage start-up. The circuit operates effectively over an acceleration range of 0.07-0.21 g. It consistently harvests energy across a wider frequency range than energy management circuits based on single DC-DC converters. For example, at an acceleration of 0.21 g, the frequency range is 20–30 Hz. Thereby it realizes, e.g. at 25 Hz, an efficiency of 72%. The proposed circuit enables robust energy harvesting in a wide frequency range, supporting wireless sensor operation even under low-vibration conditions typical of industrial predictive maintenance. 

Keyword spotting (KWS) is a key component of smart devices, enabling efficient and intuitive audio interaction. However, standard KWS systems deployed on embedded devices often suffer performance degradation under real-world operating conditions. Resilient KWS systems address this issue by enabling dynamic adaptation, with applications such as adding or replacing keywords, adjusting to specific users, and improving noise robustness. However, deploying resilient, standalone KWS systems with low latency on resource-constrained devices remains challenging due to limited memory and computational resources. This study proposes a low computational approach for continuous noise adaptation of pretrained neural networks used for KWS classification, requiring only 1-shot learning and one epoch. The proposed method was assessed using two pretrained models and three real-world noise sources at signal-to-noise ratios (SNRs) ranging from 24 to -3 dB. The adapted models consistently outperformed the pretrained models across all scenarios, especially at SNR≤18 dB, achieving accuracy improvements of 4.9% to 46.0%. These results highlight the efficacy of the proposed methodology while being lightweight enough for deployment on resource-constrained devices.

Human Activity Recognition using wearable sensors has applications in health monitoring, entertainment, and industrial settings. However, the performance of Human Activity Recognition models in real-life settings is usually lower than in laboratory settings due to the reduced quantity and quality of the sensors available in the former. Here, we propose using a suitable shared representation space to incorporate the information of additional sensors available during training time to address these limitations. We evaluate two representation spaces: one created using Feature Agglomeration and the other using Uniform Manifold Approximation and Projection (UMAP) under three conditions to evaluate their performance and robustness to noise: clean data, Gaussian noise, and Magnitude Warping noise using three datasets: Opportunity, Cooking, and PAMAP2. Our results consistently show that the representation spaces enhances performance relative to the conventional single-sensor method. The UMAP approach outperforms Feature Agglomeration, achieving up to a 14% improvement in the F1-Score metric when using clean data. In the presence of Gaussian noise, the UMAP representation space not only improves classification performance but also exhibits resilience to noise in the Opportunity and PAMAP2 datasets. While the UMAP method exhibits lower robustness to noise in the Cooking dataset, it still achieves the highest performance. When experimenting with Magnitude Warping noise, the UMAP representation space shows varying levels of robustness across datasets but still enhances performance to some extent. Using shared representations, we leverage the higher number and quality of sensors available in laboratory settings for training HAR models, while releasing the usual requirement of using the same number of sensors at the final deployment. 

The mining sector harnesses advancements in automation, digitalization, and interconnected technologies from Industry 4.0 to enhance efficiency, safety, and sustainability. Conveyor belts play a critical role in mining operations, facilitating the continuous and efficient transport of bulk materials over long distances, directly impacting productivity. While anomaly detection in specific conveyor belt components has been extensively studied, continuous monitoring to identify root causes of failures remains in its early stages. Existing methods for anomaly detection in mining conveyor belt duty cycles rely on supervised machine learning (ML) to classify internal machine modes as an intermediate step. While these approaches offer high explainability, they are constrained by the need for extensive labeled data for internal machine modes. This study proposes a novel pattern recognition approach combining unsupervised and supervised ML models for real-time anomaly detection in conveyor belt operational cycles. By evaluating combinations of TinyML models, the approach achieved average F1-scores of 83.2% for abnormal cycles and 97.0% for normal cycles, surpassing the state-of-the-art by 11.4% and 3.3%, respectively. Deployed on low-power microcontrollers, the proposed methods demonstrated efficient, real-time operation, reducing energy consumption by up to 84.5% (4.1 μJ per inference) and program memory usage by up to 72.1%. These results provide valuable insights for detecting early mechanical failures and enabling targeted preventive maintenance. 

Energy harvesting enables the supply of low-power embedded sensor systems that perform important tasks, such as condition monitoring. In applications with rotating elements, like bearings, variable reluctance energy harvesters (VREHs) can provide a significant amount of power to the system; however, a power conditioning system is needed to extract the maximum power, manage an energy storage element, and regulate the output voltage. Previous works focus either on the optimum design of the harvester that maximizes the output power level with given space constraints or concentrate on the optimum design of the power conditioning system for a fixed harvester design. This work proposes co-designing both elements to optimize the power delivered to the energy storage element. The results show that the main variable connecting both systems is voltage. On the harvester side, it is demonstrated that different designs can provide different voltage levels while maintaining the maximum output power, while on the power conditioning side, a trade-off between rectification and conversion losses must be considered. This analysis is presented with simulations and validated with experimental results. Finally, the limitations of commercial power management units (PMUs) are exposed.

Keyword spotting (KWS) is an essential function that enables interaction with ubiquitous smart devices. However, in resource-limited devices, KWS models are often static and can thus not adapt to new scenarios, such as added keywords. To overcome this problem, we propose a Continual Learning (CL) approach for KWS built on Binary Neural Networks (BNNs). The framework leverages the reduced computation and memory requirements of BNNs while incorporating techniques that enable the seamless integration of new keywords overtime. This study evaluates seven CL techniques on a 16-classuse case, reporting an accuracy exceeding 95% for a single additional keyword and up to 86% for four additional classes. Sensitivity to the amount of training samples in the CL phase, and differences in computational complexities are being evaluated. These evaluations demonstrate that batch-based algorithms are more sensitive to the CL dataset size, and that differences between the computational complexities are insignificant. These findings highlight the potential of developing an effective and computationally efficient technique for continuously integrating new keywords in KWS applications that is compatible with resource-constrained devices.

Efficient firmware distributions in energy-harvesting (EH) LoRa networks require that EH LoRa sensors simultaneously receive data fragments from a server without facing power failures. This requirement is difficult to satisfy due to the impact of EH rates and LoRa transmission parameters on the efficiency of firmware distributions. We present FioRa+, a novel energy neutrality-aware multicast firmware distribution framework for EH LoRa networks. It gradually distributes a firmware image to EH LoRa sensors in an energy-neutral manner according to their future energy availability predicted using embedded machine learning models. Consequently, the need for additional firmware distributions caused by unsuccessful firmware image reconstructions is reduced. Through one-hop neighbor discovery, on-demand relay, flexible energy query, and coverage assessment mechanisms, FioRa+ ensures that all EH LoRa sensors can receive data fragments from the server at the scheduled time using high data rates. Equipped with a relay scheduling algorithm, it circumvents the collision of data fragments relayed by EH LoRa sensors using identical data rates. The experimental results show that FioRa+ renders up to 113 × shorter distribution time and 22.7 × less distribution overhead than the state of the art.