Mid Sweden University

Energy harvesting has been proposed to support or replace battery-based energy supplies in low-power loT systems. However, manual design and optimization is currently required to implement energy harvesters. This implies significant time and cost requirements, reducing the competitiveness of energy harvesting solutions in many applications. In this paper, we propose and study a method for the automated design of ortho-planar springs in vibration energy harvesters. The proposed method uses a Python tool that has been developed to translate parametric descriptions of the spring into 2D and 3D spring CAD models. The tool is combined with a black-box optimization algorithm in order to identify optimized spring parameters. An evaluation of the proposed method on a case study of an electromagnetic vibration energy harvester demonstrates that the approach successfully results in spring designs that perform well in the energy harvesting application. Consequently, the requirement of expert competence to adjust an energy harvester to new application constraints is significantly reduced, contributing to the availability and competitiveness of energy harvesting solutions in real world applications. 

Visual structural inspections in Structural Health Monitoring (SHM) are an important method to ensure the safety and long lifetime of infrastructures. Unmanned Aerial Vehicles (UAVs) with Deep Learning (DL) have gained in popularity to automate these inspections. Yet, the vast majority of research focuses on algorithmic innovations that neglect the availability of reliable generalized DL models, as well as the effect that the model's energy consumption would have on the UAV flight time. This paper highlights the performance of 14 popular CNN models with less than six million parameters for crack detection in concrete structures. Seven of these models were successfully deployed to a low-power, resource-constrained mi-crocontroller using Tiny Machine Learning (TinyML). Among the deployed models, MobileNetV1-x0.25 achieves the highest test accuracy (75.83%) and F1-Score (0.76), the second-lowest flash memory usage (273.5 kB), the second-lowest RAM usage (317.1kB), the fourth-fastest single-trial inference time (15.8ms), and the fourth-lowest number of Multiply-Accumulate operations (MACC) (42126514). Lastly, a hypothetical study of the DJI Mini 4 Pro UAV demonstrated that the TinyML model's energy consumption has a negligible impact on the UAV flight time (34 minutes vs. 33.98 minutes). Consequently, this feasibility study paves the way for future developments towards more efficient, autonomous unmanned structural health inspections. 

Industrial condition monitoring has benefited significantly from developments in machine learning and deep learning. However, textile machines, to a large extent, still use simple sensor systems, requiring additional manual quality inspections. This paper focuses on applying deep neural networks (DNNs) in image-based condition monitoring of air-spinning machines. It specifically focuses on the spinning pressure parameter, which is strongly related to the quality of the produced yarn. The study aims to develop a method to detect structural defects in yarns and assign them to specific machine conditions. DNNs are used to analyze images of yarns generated at different spinning pressures within the spinning box to create a rich dataset for training deep learning models. The study then evaluates the effectiveness of the DNN-based approach in detecting and classifying structural defects in yarns and determining the corresponding machine conditions. The results demonstrate that the developed model can distinguish good yarn from bad yarn, which is used to analyze the proportion of good yarn segments in a longer yarn section. A decreasing proportion with decreasing spinning pressure can thus be used to identify trends in degrading machine conditions. The outcomes of the presented research could potentially help textile enterprises improve the quality and efficiency of their yarn manufacturing processes. 

With the advent of low-cost and low-power computation, communication and sensor devices, novel instrumentation and measurement applications have been enabled, such as real-time industrial condition monitoring and fine-grained environmental monitoring. In these application scenarios, a lack of available infrastructures for communication and power supply is a common problem. In industrial applications, for example, the machine to be monitored and the monitoring system itself have significantly different technology lifespans, which requires that the monitoring system be retrofitted to machines that are already in use. In environmental monitoring, measurement systems are deployed as standalone devices in potentially remote areas. Consequently, the more autonomous the sensor system can be in terms of required infrastructure, the better it can match application and business needs.

Precision livestock farming (PLF) leverages cutting-edge technologies and data-driven solutions to enhance the efficiency of livestock production, its associated management, and its welfare. Continuous monitoring of the masticatory sound of cattle allows the estimation of dry-matter intake, classification of jaw movements (JMs), and recognition of grazing and rumination bouts. Over the past two decades, algorithms for analyzing feeding sounds have seen improvements in performance and computational requirements. Nevertheless, in some cases, these algorithms have been implemented on resource-constrained electronic devices, limiting their functionality to one specific task: either classifying JMs or recognizing feeding activities (such as grazing and rumination). In this work, we present an acoustic monitoring system that comprehensively analyzes grazing cattle's feeding behavior at multiple scales. This embedded system classifies different types of JMs, identifies feeding activities, and provides predictor variables for estimating dry-matter intake. Results are transmitted remotely to a base station using long-range communication (LoRa). Two variants of the system have been deployed on a Raspberry Pi Pico board, based on a low-power ARM Cortex-M0+ microcontroller. Both firmware versions make use of direct access memory, sleep mode, and clock-gating techniques to minimize energy consumption. In laboratory experiments, the first deployment consumes 20.1 mW and achieves an F1-score of 87.3% for the classification of JMs and 87.0% for feeding activities. The second deployment consumes 19.1 mW and reaches an F1-score of 84.1% for JMs and 83.5% for feeding activities. The modular design of the proposed embedded monitoring system facilitates integration with energy-harvesting power sources for autonomous operation in field conditions.

Electro-mechanical systems operating in periodic cycles are pivotal in the Industry 4.0, enabling automated processes that enhance efficiency and productivity. Early detection of failures and anomalies in duty cycles of these machines is crucial to ensure uninterrupted operation and prevent costly downtimes. Although the wear and damage of machines have been extensively studied, a significant proportion of these problems can be traced back to operator errors, underlining the importance of continuously monitoring the machine activity to ensure optimal performance. This work presents an automatic algorithm designed to identify improper duty cycles of industrial machines, exemplified on a mining conveyor belt. To enable the identification of duty cycles, the operational states of the machine are first categorized using machine learning (ML). The study compares six tiny ML techniques on two resource-constrained microcontrollers, reporting an f1-score of 87.6% for identifying normal and abnormal duty cycles and 96.8% for the internal states of the conveyor belt system. Deployed on both low-power microcontrollers, the algorithm processes input data in less than 106 μs, consuming less than 1.16 μJ. These findings promise to facilitate integration into more comprehensive preventive maintenance algorithms. 

This paper presents a comparative study focused on the classification of American Sign Language (ASL) gestures and the challenges involved in interpreting the signs for effective communication. Using transfer learning this study evaluates three variants of MobileNet, a machine-learning model optimized for low-resource environments, on a vision-based dataset. The models are deployed on an STM32F746G microcontroller with a Cortex-M7 core. Two frameworks are compared, namely TensorFlow Lite for Microcontrollers and STM32Cube.AI. An ArduCam Mini camera with a maximum image resolution of 5 megapixels is utilized to capture the hand gestures. The study concludes that STM32Cube.AI is the preferred implementation due to its lower model ROM and RAM requirements. Among the three tested models, MobileNetV1 is the most suitable for the task, achieving the highest F1-score of 0.865, the smallest memory footprint of 290.96 kB of ROM and 85.59 kB of RAM, and the shortest inference time of 103 ms. Despite these promising results, the models encountered some difficulties distinguishing between similar signs, highlighting the challenges involved in real-time sign language recognition and the need for further research. 

Recently, with the development of industrial informatization and intellectualization, the development of smart bearings has attracted a lot of significant attention in an attempt to reduce maintenance costs and increase reliability by providing online health condition monitoring. As a result of advances in miniaturization and low power consumption of wireless sensor nodes (WSNs), self-powered technologies have been considered as a promising method to achieve autonomous WSNs in smart bearings. Although the self-powered technology has received considerable achievements, there are less reviews covering the development of self-powered structures towards smart bearing and providing potential guidelines for the future development. To bridge the gap, this paper presents a comprehensive state-of-the-art review and guidelines on self-powered methods to create smart bearings, including outlining the underlying theory, modeling methods, methodologies and technologies. The topology of a self-powered smart bearing is clarified, and the mechanisms and benefits of piezoelectricity, electromagnetism, triboelectricity, thermoelectricity and wireless power transfer for powering WSNs in smart bearing are discussed. To improve the applicability of self-powered smart bearing in a range of working conditions, the design methodologies and technologies of a variety of transducers are reviewed to provide guidelines for performance enhancement. Finally, the future challenges and perspectives are proposed for outlining potential research directions and opportunities in future self-powered smart bearing systems, including the impact on bearing performance, engineering implementation, reliability, power management and storage. 

Denoising sound is essential for improving signal quality in various applications such as speech processing, sound event classification, and machine failure detection systems. This paper proposes an autoencoder method to remove two types of noise, Gaussian white noise, and environmental noise from water flow, from induction motor sounds. The method is trained and evaluated on a dataset of 246 sounds from the Machinery Fault Database (MAFAULDA). The denoising effectiveness is measured using the mean square error (MSE), which indicates that both noise types can be significantly reduced with the proposed method. The MSE is below or equal to 0.15 for normal operation sounds and misalignment sounds. This improvement in signal quality can facilitate further processing, such as induction motor operation classification. Overall, this work presents a promising approach for denoising machine sounds using an autoencoder, with potential for application in other industrial settings.

Electromagnetic energy harvesting (EM) is an interesting method for obtaining energy from vibration sources to power autonomous wireless sensor systems. This is reached with the help of energy management circuits that can be based on voltage multipliers circuits or boost rectifier circuits. These energy management structures aim to raise the voltage of the EM converter to a level that is adequate for the storage element. In this paper, a dual-mode AC/DC circuit for EM is proposed for fast charging of the supercapacitor. The circuit is based on a boost rectifier and a voltage multiplier using discrete elements and without a startup circuit. This structure can work properly with an EM converter generating power in the range of a few µW. The circuit can work under different frequencies and accelerations. In the first step, the proposed circuit store the energy in a supercapacitor in voltage multiplier mode until it reaches 1.9 V. After that, the supercapacitor will supply the ancillary circuit to activate the boost mode based on bidirectional MOSFETs, which reduce the time to charge the supercapacitor. The maximum power consumption of the ancillary circuit is 34 µW. The experimental investigation shows that the system at acceleration ACC = 0.17 g and Freq = 27 Hz is able to charge the supercapacitor by a voltage of 5.41 V in 7 min. The proposed solution helps to enhance the time to charge comparing conventional voltage multiplier structure by 23 min.