Search

• Objective fatigue detection studies using physiological sensing are reviewed. • 43 recent articles are selected after a comprehensive quality assessment. • Signal modalities, experimental environments, and fatigue detection models are analyzed. • Directions for future research are provided based on identified gaps. • Challenges and future solutions for fatigue detection in workplaces are discussed. Fatigue is considered to have a life-threatening effect on human health and it has been an active field of research in different sectors. Deploying wearable physiological sensors helps to detect the level of fatigue objectively without any concern of bias in subjective assessment and interfering with work. This paper provides an in-depth review of fatigue detection approaches using physiological signals to pinpoint their main achievements, identify research gaps, and recommend avenues for future research. The review results are presented under three headings, including: signal modality, experimental environments, and fatigue detection models. Fatigue detection studies are first divided based on signal modality into uni-modal and multi-modal approaches. Then, the experimental environments utilized for fatigue data collection are critically analyzed. At the end, the machine learning models used for the classification of fatigue state are reviewed. The directions for future research are provided based on critical analysis of past studies. Finally, the challenges of objective fatigue detection in the real-world scenario are discussed. [ABSTRACT FROM AUTHOR]

The construction industry substantially contributes to the economic growth of a country. However, it records a large number of workplace injuries and fatalities annually due to its hesitant adoption of automated safety monitoring systems. To address this critical concern, this study presents a real-time monitoring approach that uses the Internet of Things and ensemble learning. This study leverages wearable sensor technology, such as photoplethysmography and electroencephalography sensors, to continuously track the physiological parameters of construction workers. The sensor data is processed using an ensemble learning approach called the ChronoEnsemble Fatigue Analysis System (CEFAS), comprising deep autoregressive and temporal fusion transformer models, to accurately predict potential physical and mental fatigue. Comprehensive evaluation metrics, including mean square error, mean absolute scaled error, and symmetric mean absolute percentage error, demonstrated the superior prediction accuracy and reliability of the proposed model compared to standalone models. The ensemble learning model exhibited remarkable precision in predicting physical and mental fatigue, as evidenced by the mean square errors of 0.0008 and 0.0033, respectively. The proposed model promptly recognizes potential hazards and irregularities, considerably enhancing worker safety and reducing on-site risks. [ABSTRACT FROM AUTHOR]

Abstract The construction industry substantially contributes to the economic growth of a country. However, it records a large number of workplace injuries and fatalities annually due to its hesitant adoption of automated safety monitoring systems. To address this critical concern, this study presents a real-time monitoring approach that uses the Internet of Things and ensemble learning. This study leverages wearable sensor technology, such as photoplethysmography and electroencephalography sensors, to continuously track the physiological parameters of construction workers. The sensor data is processed using an ensemble learning approach called the ChronoEnsemble Fatigue Analysis System (CEFAS), comprising deep autoregressive and temporal fusion transformer models, to accurately predict potential physical and mental fatigue. Comprehensive evaluation metrics, including mean square error, mean absolute scaled error, and symmetric mean absolute percentage error, demonstrated the superior prediction accuracy and reliability of the proposed model compared to standalone models. The ensemble learning model exhibited remarkable precision in predicting physical and mental fatigue, as evidenced by the mean square errors of 0.0008 and 0.0033, respectively. The proposed model promptly recognizes potential hazards and irregularities, considerably enhancing worker safety and reducing on-site risks.

Despite longstanding traditional construction health and safety management (CHSM) methods, the construction industry continues to face persistent challenges in this field. Neuroscience tools offer potential advantages in addressing these safety and health issues by providing objective data to indicate subjects' cognition and behavior. The application of neuroscience tools in the CHSM has received much attention in the construction research community, but comprehensive statistics on the application of neuroscience tools to CHSM is lacking to provide insights for the later scholars. Therefore, this study applied bibliometric analysis to examine the current state of neuroscience tools use in CHSM. The development phases; the most productive journals, regions, and institutions; influential scholars and articles; author collaboration; reference co-citation; and application domains of the tools were identified. It revealed four application domains: monitoring the safety status of construction workers, enhancing the construction hazard recognition ability, reducing work-related musculoskeletal disorders of construction workers, and integrating neuroscience tools with artificial intelligence techniques in enhancing occupational safety and health, where magnetoencephalography (EMG), electroencephalography (EEG), eye-tracking, and electrodermal activity (EDA) are four predominant neuroscience tools. It also shows a growing interest in integrating the neuroscience tools with artificial intelligence techniques to address the safety and health issues. In addition, future studies are suggested to facilitate the applications of these tools in construction workplaces by narrowing the gaps between experimental settings and real situations, enhancing the quality of data collected by neuroscience tools and performance of data processing algorithms, and overcoming user resistance in tools adoption. [ABSTRACT FROM AUTHOR]

Carbon nanoparticle (CNP)-polymer sensors are good candidates for monitoring structural damage. A combined numerical-analytical approach with considering the stiffness degradation of composite is proposed to calculate the resistance variations with the cyclic loads. The electro-mechanical behavior of the sensor can be simulated through the finite element analysis of a random representative volume element model and the equivalent resistance calculation of microcircuit. Then, taking the glass fiber-reinforced composite coated with the CNP-epoxy resin as example, its electro-mechanical behavior under tension-tension cyclic loading is investigated experimentally and numerically. Furthermore, by microscopic analysis, the fatigue damage monitoring mechanism of the sensor is revealed. [ABSTRACT FROM AUTHOR]

Limited research has reported the reliability of rapid force generation characteristics during isometric assessments of the hamstrings. Therefore, the purpose of the present study was to determine the between-session reliability of rapid force generating characteristics of the hamstrings and relationship to maximal force production. Twenty-three female soccer players (age: 20.7 ± 4.7 years; height: 168.7 ± 5.9 cm; body mass: 64.4 ± 6.7 kg) performed three unilateral trials of the 90–90 isometric hamstring assessment, on two separate occasions, separated by 7 days. Peak force, force at 100- and 200 ms and average rate of force development (aRFD) over 100- and 200 ms epochs were calculated. Absolute and fair-good reliability was observed for peak force and all rapid force generating measures (<8.33CV%, ICC >0.610). Significant and meaningful relationships (p < 0.001, r > 0.802) were observed for all rapid force generating measures and peak force. The 90–90 isometric assessment can be used to assess peak and rapid force generating reliably to enable practitioners to confidently track changes in performance over time as part of fatigue monitoring and management. [ABSTRACT FROM AUTHOR]

The functionality of load-bearing parts remains a central challenge for laser-powder bed fusion (L-PBF). However, the understanding and quantification of the process–quality–fatigue (P-Q-F) causal relationship are still lacking. The variable fatigue behavior is randomized by the PBF process variations and the subsequent quality uncertainty, e.g., random geometrical defects. In particular, the bulk literature is limited to gross fatigue fracture, while the fatigue initiation and development process is poorly understood due to the constraint of available online fatigue monitoring techniques. Addressing these challenges is critical to qualify L-PBF as a standard industrial process for fabricating load-bearing metal parts. From the scientific point of view, the effect of a wide range of porosity on fatigue performance is yet to be studied to understand the P-Q-F causal relationship even though low porosity more completely is desired in L-PBF parts. This work focuses on resonance-based fatigue testing of as-PBFed SS-316L material with random porosity. The results have shown that frequency and power are process signatures for fatigue initiation, development, and gross fracture. The porosity-induced fatigue life and fatigue limit scattering show normal distributions. [ABSTRACT FROM AUTHOR]

Despite longstanding traditional construction health and safety management (CHSM) methods, the construction industry continues to face persistent challenges in this field. Neuroscience tools offer potential advantages in addressing these safety and health issues by providing objective data to indicate subjects’ cognition and behavior. The application of neuroscience tools in the CHSM has received much attention in the construction research community, but comprehensive statistics on the application of neuroscience tools to CHSM is lacking to provide insights for the later scholars. Therefore, this study applied bibliometric analysis to examine the current state of neuroscience tools use in CHSM. The development phases; the most productive journals, regions, and institutions; influential scholars and articles; author collaboration; reference co-citation; and application domains of the tools were identified. It revealed four application domains: monitoring the safety status of construction workers, enhancing the construction hazard recognition ability, reducing work-related musculoskeletal disorders of construction workers, and integrating neuroscience tools with artificial intelligence techniques in enhancing occupational safety and health, where magnetoencephalography (EMG), electroencephalography (EEG), eye-tracking, and electrodermal activity (EDA) are four predominant neuroscience tools. It also shows a growing interest in integrating the neuroscience tools with artificial intelligence techniques to address the safety and health issues. In addition, future studies are suggested to facilitate the applications of these tools in construction workplaces by narrowing the gaps between experimental settings and real situations, enhancing the quality of data collected by neuroscience tools and performance of data processing algorithms, and overcoming user resistance in tools adoption.

About 40% of the US construction workforce experiences high-level fatigue, which leads to poor judgment, increased risk of injuries, a decrease in productivity, and a lower quality of work. Therefore, it is essential to monitor fatigue to reduce its adverse effects and prevent long-term health problems. However, since fatigue demonstrates itself in several complex processes, there is no single standard measurement method for fatigue detection. This study aims to develop a system for continuous workers' fatigue monitoring by predicting the aerobic fatigue threshold (AFT) using forearm muscle activity and motion data. The proposed system consists of five modules: Data acquisition, activity recognition, oxygen uptake prediction, maximum aerobic capacity (MAC) estimation, and continuous AFT monitoring. The proposed system was evaluated on the participants performing fourteen scaffold-building activities. The results show that the AFT features have achieved a higher accuracy of 92.31% in assessing the workers' fatigue level compared to heart rate (51.28%) and percentage heart rate reserve (50.43%) features. Moreover, the overall performance of the proposed system on unseen data using average two-min AFT features was 76.74%. The study validates the feasibility of using forearm muscle activity and motion data to workers' fatigue levels continuously. [ABSTRACT FROM AUTHOR]

Analyzing the opening and closing states of eyes and mouths by detecting the driver’s face feature points is an effective method for judging driver fatigue. However, in practical engineering applications, with the expansion of user groups, the false identification problem caused by the differentiation of individual facial features of drivers is prominent, especially for people with small eyes. To solve this problem, this paper uses the Mediapipe Facemesh module to detect face feature points and designs a perception-free calibration method for setting personalized eye opening and closing threshold combined with head postures. Compared with the traditional method of setting a fixed threshold, the precision of eye state recognition is improved by 36.4%. Finally, the model deployment and post-processing compilation are completed on the Xavier vehicle chip, achieving a running speed of 34 frames per second at most, and the subjective evaluation experience of the fatigue monitoring system is significantly improved.

• Damping ratio of (0/90) and (±45) GFRP laminates increase with the fatigue damage. • Natural frequency of GFRP laminates decreases with the loading cycles. • The decreasing trend of natural frequency can be expressed by theoretical models. • Frequency-based damage index is proposed to evaluate fatigue damage. As Glass Fiber Reinforced Polymers (GFRP) have increasingly been used in civil infrastructures construction, their mechanical properties have received more and more attention. Although its performance under static loading has been studied widely, experimental and analytical research on its dynamic response is still insufficient. In particular, the relationship between fatigue damage occurring in woven cloth GFRP and its dynamic properties has not been quantitatively evaluated. Therefore, by carrying out impact and fatigue loading tests, investigated in this study is the variation of dynamic properties on GFRP orthogonal laminate with fatigue damage. The experiments revealed that the damping ratio of GFRP laminates with both 0/90 degrees fibers and ± 45 degrees fibers showed an increasing trend with the number of loading cycles, while the natural frequency showed a decreasing trend. Based on this trend, this study proposed a method to monitor fatigue damage progression of the material through the variation of natural frequencies. The decreasing trend of natural frequency could be simulated well by the theoretical model proposed in this study. Furthermore, based on previous studies and the experimental results of this study, a new frequency-based damage index to monitor GFRP's fatigue life was proposed. [ABSTRACT FROM AUTHOR]

To verify the performance of a basalt fiber reinforced polymer (BFRP) fiber-encapsulated long-gauge strain sensor in railway bridge health monitoring, this paper studies the fatigue resistance and durability of the BFRP fiber-encapsulated FBG sensor under train loads. First, the influences of the length of the anchorage section and the length ratio of the sensing section on the accuracy of the sensor were studied. Then, the BFRP sensor was applied to a sleeper for 2 million cycles of tension fatigue testing. The strain-time history of the whole fatigue test was monitored and compared. After the test, a calibration test was carried out to verify the accuracy and repeatability of the sensor. Finally, the slip and fatigue cracking of the fiber in the anchorage section of the sensor were observed by electron microscopy. The results show that the gap between the anchoring section and the bare optical fiber was filled with epoxy resin, and there was no slip behavior. No fatigue cracking occurred in the fiber, and the strain coefficient and linearity of the sensor showed no obvious changes after 2 million cycles of loading. The long-gauge strain sensor encapsulated by BFRP fibers exhibited good fatigue resistance and can meet long-term monitoring requirements under train loads. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Henan University of Science & Technology, Natural Science is the property of Editorial Office of Journal of Henan University of Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In this paper, aiming at the detection of fatigue driving scene of drivers, a diagnostic model based on machine learning is proposed under the scene of long-time driving. The validity of the model is verified by simulation experiments. The simulation result shows that the model can effectively fit the fatigue condition of drivers under long-time driving, and accurately judge and warn the fatigue state of drivers. At the same time, the model also extends the application of fatigue classification detection.

Monitoring and analyzing the state of human muscle is becoming a focus of research in exercise and medicine. Traditional devices (EMG, MRI, X-ray, etc.) cannot provide long-term and stable dynamic monitoring of human muscles due to usage scenarios and expert diagnosis. Here we propose a new triboelectric nanogenerator of modular muscle sensor (MMS-TENG), which is based on a flexible conductive sponge, polyurethane sponge, Fluorinated ethylene propylene film, and nylon elastic bandage that can be fixed to the torso of the human body. Due to the modular design of the sensor and three-dimensional grid structure from conductive sponge, and polyurethane sponge, it features an adjustable sensitivity function, allowing for sensitivity adjustments based on workout mode and measurement position. It is fastened to the measured component using an elastic band, with a minimum resolution of 0.001 N and a response delay of 2 ms, with a minimum frequency of 0.1 Hz. It keeps the current output stable for 360,000 cycles. MMS-TENG can capture signals related to the stretching and trembling of muscles. It has great potential in the personal gym and health management, such as correcting train posture, gathering ride data, and monitoring fatigue displays. [Display omitted] • Shortening the preparation time, a simple structural design can simplify the optimization process of sensor. • Adjustable sensitivity collects muscle states from different parts. • Muscle stretching changes can be detected as low as 0.1hz. [ABSTRACT FROM AUTHOR]

The objective measurement of fatigue is of critical relevance in areas such as occupational health and safety as fatigue impairs cognitive and motor performance, thus reducing productivity and increasing the risk of injury. Wearable systems represent highly promising solutions for fatigue monitoring as they enable continuous, long-term monitoring of biomedical signals in unattended settings, with the required comfort and non-intrusiveness. This is a p rerequisite for the development of accurate models for fatigue monitoring in real-time. However, monitoring fatigue through wearable devices imposes unique challenges. To provide an overview of the current state-of-the-art in monitoring variables associated with fatigue via wearables and to detect potential gaps and pitfalls in current knowledge, a systematic review was performed. The Scopus and PubMed databases were searched for articles published in English since 2015, having the terms "fatigue," "drowsiness," "vigilance," or "alertness" in the title, and proposing wearable device-based systems for non-invasive fatigue quantification. Of the 612 retrieved articles, 60 satisfied the inclusion criteria. Included studies were mainly of short duration and conducted in laboratory settings. In general, researchers developed fatigue models based on motion (MOT), electroencephalogram (EEG), photoplethysmogram (PPG), electrocardiogram (ECG), galvanic skin response (GSR), electromyogram (EMG), skin temperature (Tsk), eye movement (EYE), and respiratory (RES) data acquired by wearable devices available in the market. Supervised machine learning models, and more specifically, binary classification models, are predominant among the proposed fatigue quantification approaches. These models were considered to perform very well in detecting fatigue, however, little effort was made to ensure the use of high-quality data during model development. Together, the findings of this review reveal that methodological limitations have hindered the generalizability and real-world applicability of most of the proposed fatigue models. Considerably more work is needed to fully explore the potential of wearables for fatigue quantification as well as to better understand the relationship between fatigue and changes in physiological variables. [ABSTRACT FROM AUTHOR]

In this paper, aiming at the detection of fatigue driving scene of drivers, a diagnostic model based on machine learning is proposed under the scene of long-time driving. The validity of the model is verified by simulation experiments. The simulation result shows that the model can effectively fit the fatigue condition of drivers under long-time driving, and accurately judge and warn the fatigue state of drivers. At the same time, the model also extends the application of fatigue classification detection. [ABSTRACT FROM AUTHOR]

In this paper, a vision-based physiological signal measurement system is proposed to instantly measure driver fatigue. A remote photoplethysmography (rPPG) signal is a type of physiological signal measured by a camera without any contact device, and it also retains the characteristics of the PPG, which is useful to evaluate fatigue. To solve the inconvenience caused by the traditional contact-based physiological fatigue detection system and to improve the accuracy, the system measures both the motional and physiological information by using one image sensor. In a practical application, the environmental noise would affect the measured signal, and therefore, we performed a preprocessing step on the signal to extract a clear signal. The experiment was designed in collaboration with Taipei Medical University, and a questionnaire-based method was used to define fatigue. The questionnaire that could directly react to the feeling of the subject was treated as our ground truth. The evaluated correlation was 0.89 and the root mean square error was 0.65 for ten-fold cross-validation on the dataset. The trend of driver fatigue could be evaluated without a contact device by the proposed system. This advantage ensures the safety of the driver and reliability of the system.

The objective measurement of fatigue is of critical relevance in areas such as occupational health and safety as fatigue impairs cognitive and motor performance, thus reducing productivity and increasing the risk of injury. Wearable systems represent highly promising solutions for fatigue monitoring as they enable continuous, long-term monitoring of biomedical signals in unattended settings, with the required comfort and non-intrusiveness. This is a p rerequisite for the development of accurate models for fatigue monitoring in real-time. However, monitoring fatigue through wearable devices imposes unique challenges. To provide an overview of the current state-of-the-art in monitoring variables associated with fatigue via wearables and to detect potential gaps and pitfalls in current knowledge, a systematic review was performed. The Scopus and PubMed databases were searched for articles published in English since 2015, having the terms “fatigue,” “drowsiness,” “vigilance,” or “alertness” in the title, and proposing wearable device-based systems for non-invasive fatigue quantification. Of the 612 retrieved articles, 60 satisfied the inclusion criteria. Included studies were mainly of short duration and conducted in laboratory settings. In general, researchers developed fatigue models based on motion (MOT), electroencephalogram (EEG), photoplethysmogram (PPG), electrocardiogram (ECG), galvanic skin response (GSR), electromyogram (EMG), skin temperature (Tsk), eye movement (EYE), and respiratory (RES) data acquired by wearable devices available in the market. Supervised machine learning models, and more specifically, binary classification models, are predominant among the proposed fatigue quantification approaches. These models were considered to perform very well in detecting fatigue, however, little effort was made to ensure the use of high-quality data during model development. Together, the findings of this review reveal that methodological limitations have hindered the generalizability and real-world applicability of most of the proposed fatigue models. Considerably more work is needed to fully explore the potential of wearables for fatigue quantification as well as to better understand the relationship between fatigue and changes in physiological variables.

About 40% of the US construction workforce experiences high-level fatigue, which leads to poor judgment, increased risk of injuries, a decrease in productivity, and a lower quality of work. Therefore, it is essential to monitor fatigue to reduce its adverse effects and prevent long-term health problems. However, since fatigue demonstrates itself in several complex processes, there is no single standard measurement method for fatigue detection. This study aims to develop a system for continuous workers’ fatigue monitoring by predicting the aerobic fatigue threshold (AFT) using forearm muscle activity and motion data. The proposed system consists of five modules: Data acquisition, activity recognition, oxygen uptake prediction, maximum aerobic capacity (MAC) estimation, and continuous AFT monitoring. The proposed system was evaluated on the participants performing fourteen scaffold-building activities. The results show that the AFT features have achieved a higher accuracy of 92.31% in assessing the workers’ fatigue level compared to heart rate (51.28%) and percentage heart rate reserve (50.43%) features. Moreover, the overall performance of the proposed system on unseen data using average two-min AFT features was 76.74%. The study validates the feasibility of using forearm muscle activity and motion data to workers’ fatigue levels continuously.

The purpose of this study was to investigate acute effects of match-play on neuromuscular performance and subjective recovery and stress state and the relationship between training load (TL) and changes in neuromuscular performance in female soccer players. Twelve National Collegiate Athlete Association Division I players participated (20.7 ± 2.3 years; 64.4 ± 7.2 kg; 164.5 ± 6.0 cm) and completed countermovement jump (CMJ) at 0 kg (CMJ0) and 20 kg (CMJ20) and the Short Recovery Stress Scale (SRSS) at 3 hours pre-match (Pre), 12 hours post-match (Post12), and 38 hours post-match (Post38). Countermovement jump variables included body mass, jump height (JH), modified reactive strength index (RSI), peak force (PF), relative PF, eccentric impulse, concentric impulse (CI), peak power (PP), relative PP (RPP), eccentric average PP, and concentric average power (CAP). The SRSS consists of 4 Stress Scales (SSs) and 4 Recovery Scales (RSs). Training loads included total distance, total PlayerLoad, high-speed running, and session ratings of perceived exertion. Significant moderate to large decreases were observed from Pre to Post12 in JH, RSI, CI, PP, RPP, and CAP in CMJ0 and CMJ20 (p < 0.05, effect size [ES] = 0.63-1.35). Significant changes were observed from Pre to Post12 in all RSs (p < 0.05, ES = 0.65-0.79) and 3 SSs (p < 0.05, ES = 0.71-0.77). Significant correlations were observed between CMJ20 PP from Pre to Post12 and all TLs (p < 0.05, r520.58 to 20.68). CMJ0 and CMJ20 JH and PP may indicate acute neuromuscular changes after match-play. The magnitude of CMJ20 PP decrements from Pre to Post12 may be affected by soccer match-play volumes. [ABSTRACT FROM AUTHOR]

Driver assistance systems are at the peak of their development and are already actively used by the world’s leading automakers as an effective tool to improve traffic safety (reducing accident rates). The driver fatigue monitoring systems at the methodological level and functional purpose are actively developing and have outlined a trend, including the transition of a number of functions from the category of assistant systems to the category of active safety systems operating in automatic mode. The most effective method of automatically interpreting the driver’s functional state in terms of driver fatigue (deep relaxation, when the number of driver errors significantly increases which can lead to an accident, the driver’s functional state preceding the fall asleep) is the most effective, having the least probability of a dangerous failure. It is based on monitoring and analysis of parameters of the electrodermal activity. Methods of automatic interpretation of the functional state of the driver allow us to expand the functionality of a number of security systems and increase their effectiveness. It shows the relevance of monitoring the driver’s functional state before the vehicles achieve full autonomy of traffic.

Fatigue monitoring can effectively reduce or even avoid traffic accidents. Head posture estimation is one of the focuses in the field of fatigue monitoring. In this paper, according to the coordinate rotation transformation and neural network theory, a method for predicting the change of head posture with sight-line coordinates is proposed. First, the coordinate rotation transformation theory is used to replace the head posture change amount with the coordinate change amount, and the first-order difference value of the sight-line point coordinate is obtained by the difference method. Then, under the unified Cartesian coordinate system, the MP-MTM-LSTM neural network is established with the input information of first-order difference value and the output information of coordinate change amount. The innovation of this method is that the Cartesian coordinate change is employed instead of the Euler angle transformation. In the model verification phase, the true value of the head pose is collected by the posture meter. The experimental results show that the absolute error between the predicted value and the true value estimated by the new method is less than 15%. In the field of fatigue monitoring, the proposed method can estimate the amount of head posture change effectively, which is suitable for the case where the head center point is not fixed. [ABSTRACT FROM AUTHOR]

Fiber Bragg grating (FBG) sensors provide excellent capability for the structural health monitoring (SHM) of load-bearing structures by allowing for local internal strain measurements within structures. However, the integration of these sensors to composite materials is associated with several challenges that have to be addressed to have the correct strain measurement and in turn to perform reliable SHM. One of the most important issues is the presence of uneven strain fields around FBGs, which significantly affect the response of the sensors and hence the reliability of the acquired data. The uniformity of the strain fields around sensors is important for dependable data acquisition; however, to generate such a condition, tow width-to-FBG length relationship, optical fiber configuration with respect to reinforcement fiber orientation, and crack density resulting from fatigue loading are very important factors that have to be considered. In this paper, these issues are addressed by investigating the signal properties of FBG sensors with 1 and 10 mm lengths embedded within the composite specimens during the manufacturing process. After fatigue testing of the specimens, it is shown that 1-mm-long FBGs embedded in-line with adjacent reinforcement fibers with tow widths of ∼2 mm provide much more reliable signals than 10-mm-long FBGs embedded perpendicular to adjacent tows.

Abstract Polyvinylidene fluoride (PVDF) has been widely used in piezoelectric applications because of its outstanding properties such as low permittivity, high thermal stability, high chemical resistance, and flexibility. In this study, PVDF film sensors were prepared for fatigue damage monitoring of single-lap adhesive joints. PVDF films were fabricated using the solvent casting method, and post treatment, including mechanical stretching and heat setting, was conducted to increase the β-phase crystallinity of the films. Subsequently, the PVDF films were polarized to align the molecular dipoles. The crystal structures of the PVDF films were investigated using X-ray diffraction (XRD) and the thermal behaviors were analyzed using differential scanning calorimetry (DSC). The piezoelectric constants of the prepared PVDF films were measured using a d 33 meter. The sensing performance of the films for fatigue damage monitoring of single-lap adhesive joints was assessed by fatigue tests under various stress levels. In addition, a fatigue failure manual based on the PVDF sensor signal, which can predict the failure of the adhesive joints, was constructed. [ABSTRACT FROM AUTHOR]

This article aims at developing a generic system for the damage and retrofitting monitoring along with long-term strength and first-stage fatigue monitoring of reinforced concrete structures using embedded Lead Zirconate Titanate sensors in the form of concrete vibration sensors. The concrete vibration sensor is a ready-to-use sensor, and its unique packaging renders it very compatible for embedment in reinforced concrete structures. In addition to cost-effectiveness, the concrete vibration sensors are also characterized by excellent structure-compatibility and durability. In this article, both finite element method and experimental investigations have been employed to establish the feasibility of using curvature (second-order derivative) and other higher order derivatives of displacement mode shapes for damage detection and retrofitting assessment. The experiments are conducted on a real-life-sized reinforced concrete beam. The concrete vibration sensors embedded on the outer faces of the reinforced concrete beam are coupled to obtain the curvature and higher order mode shapes of the beam in pristine, damaged and retrofitted conditions. It is found that the curvature mode shape–based response of concrete vibration sensors can successfully identify the location of damage both numerically and experimentally. However, the third-order mode shape is unable to correctly identify the location of damage. Before introducing damage in the beam, the effect of long-term dynamic loading from Day 6 to Day 108 after casting of the reinforced concrete beam is also monitored. Both the global monitoring technique (in which flexural rigidity of the beam is monitored) and the local electro-mechanical impedance technique (where the equivalent stiffness identified by concrete vibration sensors is monitored) successfully detected the decreasing fatigue strength of the reinforced concrete beam. Degradation of the strength of reinforced concrete beam results due to the development of micro-cracks in the concrete because of the continuous vibrations (9.3 million load cycles) experienced by it via shaker. This is the first-of-its-kind proof-of-concept application of equivalent stiffness concept for monitoring curing of a large-sized reinforced concrete structure. It is also the first study on first-stage fatigue monitoring carried out before the 'retrofitting-stage' of the structure. Complete experimental investigations after the 'retrofitting-stage' covering all three stages of fatigue have been covered by the authors in their related publication. [ABSTRACT FROM AUTHOR]

Aiming at the human-computer interaction problem during the movement of the rehabilitation exoskeleton robot, this paper proposes an adaptive human-computer interaction control method based on real-time monitoring of human muscle state. Considering the efficiency of patient health monitoring and rehabilitation training, a new fatigue assessment algorithm was proposed. The method fully combined the human neuromuscular model, and used the relationship between the model parameter changes and the muscle state to achieve the classification of muscle fatigue state on the premise of ensuring the accuracy of the fatigue trend. In order to ensure the safety of human-computer interaction, a variable impedance control algorithm with this algorithm as the supervision link was proposed. On the basis of not adding redundant sensors, the evaluation algorithm was used as the perceptual decision-making link of the control system to monitor the muscle state in real time and carry out the robot control of fault-tolerant mechanism decision-making, so as to achieve the purpose of improving wearing comfort and improving the efficiency of rehabilitation training. Experiments show that the proposed human-computer interaction control method is effective and universal, and has broad application prospects.

Drowsiness detection mechanisms have been extensively studied in the last years since they are one of the prevalent causes of accidents within the mining, driving and industrial activities. Many research efforts were done to quantify the drowsiness levels using behavioral analyses based on camera eye tracking systems as well as by analyzing physiological features contained in EEG signals. Detection systems typically use specific drowsiness indicators from only one of these methods, leaving a risk of missed detection since not all the population presents same symptoms of drowsiness. Thus, multi-feature systems are preferable even though most of the current State-of-the-Art (SoA) solutions are based on power-hungry platforms and they have meager chance to be used in embedded wearable applications with long battery lifetime. This work presents a drowsiness detection scheme fusing behavioral information coming from user motion through an IMU sensor and physiological information coming from brain activity through a single EEG electrode. The solution is implemented and tested on a low power programmable platform based on an ARM Cortex-M4 microcontroller, resulting in a wearable device capable to detect 5 different levels of drowsiness with an average accuracy of 95.2% and a battery life of 6 hours, using a 200 mAh battery. We also study the energy optimization achievable by accelerating the sensor fusion-based drowsiness detector on a parallel ultra-low power (PULP) platform. Results show that the use of PULP as efficient processing platform provides an energy improvement of 63x with respect to a solution based on a commercial microcontroller. This may extend the battery life of the complete system up to 46 h with a 7x improvement, paving the way for a completely wearable, always-on system. [ABSTRACT FROM AUTHOR]

Copyright of Engineering Mechanics / Gongcheng Lixue is the property of Engineering Mechanics Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The aim of the current investigation was to understand the impact of pretraining neuromuscular performance and creatine kinase (CK) status on subsequent training performance in elite soccer players. Thirty soccer players (age: 25.3 ± 3.1 years; height: 183 ± 7 cm; mass: 72 ± 7 kg) were involved in this observational study. Each morning before training, players completed assessments for neuromuscular performance (countermovement jump; CMJ) and CK levels. Global positioning technology provided external load: total distance, high-speed distance, sprint distance, accelerations, decelerations, average metabolic power, explosive distance, and high metabolic power distance (.25.5⋅kg-1). Mixed-effect linear models revealed significant effects for CK and CMJ Z-score on total high-speed distance, very high-speed distance, accelerations, decelerations, explosive distance, and maximal velocity. Effects are reported with 90% confidence limits. A CK Z-score of +1 corresponded to a 25.5 ± 1.1, 23.9 ± 0.5, 24.3 6 2.9%, 24.1 ± 2.9%, 23.1 ± 2.9%, and 24.6 ± 1.9%, reduction in total high-speed distance, very high-speed distance, accelerations, decelerations, explosive distance, and maximal velocity, respectively. Countermovement jump Z-score of 21 corresponded to a 23.5 ± 1.1, 22.9 ± 0.5, 22.1 ± 1.4, 25.3 6 2.9%, 23.8 ± 2.9%, 21.1 ± 2.9%, and 25.6 ± 1.2% reduction in these external load measures. Magnitude-based analysis revealed that the practical size of the effect of a pretraining CMJ Z-score of 21 and CK Z-score of +1 would have on total high-speed distance, very high-speed distance, high metabolic power distance (.25.5 ⋅kg-1), accelerations, decelerations, explosive distance, and maximal velocity was likely negative. The results of this study suggest that systematic pretraining monitoring of neuromuscular and muscle stress within soccer cohorts can provide coaches with information about the training output that can be expected from individual players during a training session. [ABSTRACT FROM AUTHOR]

Purpose: Being able to identify how an athlete is responding to training would be useful to optimise adaptation and performance. The maximal rate of heart rate increase (rHRI), a marker of heart rate acceleration has been shown to correlate with performance changes in response to changes in training load in male athletes; however, it has not been established if it also correlates with performance changes in female athletes.Methods: rHRI and cycling performance were assessed in six female cyclists following 7 days of light training (LT), 14 days of heavy training (HT) and a 10 day taper period. rHRI was the first derivative maximum of a sigmoidal curve fit to R-R data recorded during 5 min of cycling at 100 W. Cycling performance was assessed as work done (kJ) during time-trials of 5 (5TT) and 60 (60TT) min duration.Results: 5TT was possibly decreased at HT (ES ± 90% confidence interval = - 0.16 ± 0.25; p = 0.60), while, 5TT and 60TT very likely to almost certainly increased from HT to taper (ES = 0.71 ± 0.24; p = 0.007 and ES = 0.42 ± 0.19; p = 0.02, respectively). Large within-subject correlations were found between rHRI, and 5TT (r = 0.65 ± 0.37; p = 0.02) and 60TT (r = 0.70 ± 0.31; p = 0.008).Conclusions: rHRI during the transition from rest to light exercise correlates with training induced-changes in exercise performance in females, suggesting that rHRI may be a useful monitoring tool for female athletes. [ABSTRACT FROM AUTHOR]

Extensive monitoring comes at a prohibitive cost, limiting Predictive Maintenance strategies for vehicle fleets. This paper presents a measurement-based virtual sensing technique where local strain gauges are only required for few reference vehicles, while the remaining fleet relies exclusively on accelerometers. The scattering transform is used to perform feature extraction, while principal component analysis provides a reduced, low dimensional data representation. This enables direct fatigue damage regression, parameterized from unlabeled usage data. Identification measurements allow for a physical interpretation of the reduced representation. The approach is demonstrated using experimental data from a sensor equipped eBike, which is made publicly available. • Virtual sensing enables fatigue monitoring using a reduced sensor setup. • Scattering transform and PCA provide a compact and interpretable data representation. • Fatigue damage regression is parameterized using unlabeled data. • Maneuver identification based on a small additional labeled dataset is achieved. • Demonstration on an experimental dataset of a sensor equipped eBike. [ABSTRACT FROM AUTHOR]

About 40% of reactors in the world are being operated beyond design life or are approaching the end of their life cycle. During long-term operation, various degradation mechanisms occur. Fatigue caused by alternating operational stresses in terms of temperature or pressure change is an important damage mechanism in continued operation of nuclear power plants. To monitor the fatigue damage of components, Fatigue Monitoring System (FMS) has been installed. Most FMSs have used Green's Function Approach (GFA) to calculate the thermal stresses rapidly. However, if temperature-dependent material properties are used in a detailed FEM, there is a maximum peak stress discrepancy between a conventional GFA and a detailed FEM because constant material properties are used in a conventional method. Therefore, if a conventional method is used in the fatigue evaluation, thermal stresses for various operating cycles may be calculated incorrectly and it may lead to an unreliable estimation. So, in this paper, the modified GFA which can consider temperature-dependent material properties is proposed by using an artificial neural network and weight factor. To verify the proposed method, thermal stresses by the new method are compared with those by FEM. Finally, pros and cons of the new method as well as technical findings from the assessment are discussed.

The purpose of the present study was to establish the intrasession and intersession reliability of variables obtained from a force plate that was used to quantitate lower extremity inter-limb asymmetry during the bilateral countermovement jump (CMJ). Secondarily, a comparison was performed to determine the influence of the jump protocol CMJ with or without an arm swing (CMJ AS and CMJ NAS, respectively) on inter-limb asymmetries. Twenty-two collegiate basketball players performed three CMJ AS and three CMJ NAS on dual force platforms during two separate testing sessions. A majority of variables met the acceptable criterion of intersession and intrasession relative reliability (ICC > 0.700), while fewer than half met standards established for absolute reliability (CV < 10%). CMJ protocol appeared to influence asymmetries; Concentric Impulse-100 ms, Eccentric Braking Rate of Force Development, Eccentric Deceleration, and Force at Zero velocity were significantly different between jumping conditions (CMJAS versus CMJ NAS; p < 0.05). The present data establish the reliability and smallest worthwhile change of inter-limb asymmetries during the CMJ, while also identifying the influence of CMJ protocol on inter-limb asymmetries, which can be useful to practitioners and clinicians in order to effectively monitor changes associated with performance, injury risk, and return-to-play strategies.

The purpose of the present investigation was to evaluate differences in Reactive Strength Index Modified (RSIMod) and Flight Time to Contraction Time Ratio (FT:CT) during the countermovement jump (CMJ) performed without the arm swing (CMJNAS) compared to the CMJ with the arm swing (CMJAS), while exploring the relationship within each variable between jump protocols. A secondary purpose sought to explore the relationship between RSIMod and FT:CT during both jump protocols. Twenty-two collegiate basketball players performed both three CMJNAS and three CMJAS on a force plate, during two separate testing sessions. RSIMod was calculated by the flight-time (RSIModFT) and impulse-momentum methods (RSIModIMP). CMJ variables were significantly greater during the CMJAS compared to CMJNAS (p < 0.001). There were large to very large correlations within each variable between the CMJAS and CMJNAS. There were significant positive correlations among RSIModFT, RSIModIMP, and FT:CT during both the CMJAS (r ≥ 0.864, p < 0.001) and CMJNAS (r ≥ 0.960, p < 0.001). These findings identify an increase in RSIMod or FT:CT during the CMJAS, that may provide independent information from the CMJNAS. In addition, either RSIMod or FT:CT may be utilized to monitor changes in performance, but simultaneous inclusion may be unnecessary.

The purpose of this study was to assess the concurrent validity and test-retest reliability of a linear position transducer (LPT) for the squat jump (SJ) and counter-movement jump (CMJ) height. Twenty-eight subjects (25.18 ± 7.1 years) performed three SJs followed by three CMJs using a force plate concurrently with the LPT to test validity. Subjects returned on a separate day, at least 48 h apart, to measure test-retest reliability. A t-test showed a significant difference between the two devices for both SJ (p < 0.001) and CMJ (p < 0.001) while Bland⁻Altman analysis for validity revealed that the LPT overestimated jump height for both SJ (mean difference (MD) = 8.01 ± 2.93 cm) and CMJ (MD = 8.68 ± 2.99 cm). With regards to reliability of the LPT, mean intraclass correlation (ICC) for both SJ (ICC = 0.84) and CMJ (ICC = 0.95) were high, and Bland⁻Altman analysis showed mean differences lower than minimal detectable change (MDC) between the days for both SJ (MD = 1.89 ± 4.16 cm vs. MDC = 2.72 cm) and CMJ (MD = 0.47 ± 3.23 cm vs. MDC = 2.11 cm). Additionally, there was a low coefficient of variation (CV) between days for both SJ (CV = 3.25%) and CMJ (CV = 0.74%). Therefore, while the LPT overestimates jump height, it is a reliable tool for tracking changes in jump height to measure performance improvement and monitor fatigue.

Aircraft structure fatigue monitoring has been developed over decades presently reaching the stage where it became mandatory for all combat aircraft to be equipped with an airborne fatigue monitoring system. These systems usually collect operational data for calculating the safe fatigue life or inspection interval for the aircraft structure. This paper presents an analysis of the current state of fatigue monitoring systems on the IAR-99 SOIM based on the experience of international fatigue monitoring programs and analysis of structure resource improvement.Aspects related to strain gauge and calibration, flight parameter data gathering, data integrity, comparison with fatigue test results and fatigue damage models are also investigated by means of flight tests.

Modern state-of-the-art fatigue monitoring approaches gain in importance in the context of renewables such as wind power plants. Fatigue is of utmost importance in terms of potential damage mechanisms and in the perspective of scheduled plant lifetime periods of 20 years. A qualified fatigue monitoring approach considering the real loads provides - the best possible knowledge of the state of the plant (protection of investment) - the basis for long term operation projects and - the basis for a load ranking within a wind park in case of partial load operation. It is the aim to ensure a constant damage accumulation across the wind park. AREVA disposes of a long tradition in the development of fatigue and structural health monitoring solutions. The methodology established for power plant applications is transferred to mechanical loading conditions of components of wind energy plants. The core challenge is the identification and qualified processing of realistic load-time histories. The related methodological requirements will be explained in detail. In terms of components of wind energy plants the wind loads are producing inner structural loads (forces and moments). Hence, the main target is gaining knowledge about the histories of these inner load series. The approach is based on a modern standard acceleration measurement at specific positions on the wind turbine tower. The fatigue monitoring process is as follows: 1. Measurement of the tower acceleration with modern acceleration measurement equipment; 2. Evaluation of displacement histories based on the acceleration measurements using double integration functions; 3. Calculation of internal loads histories based on the equation of motion and the knowledge of towers stiffness; 4. Scaling and superposition of elementary stress responses for getting component stress histories and 5. Evaluation of fatigue accumulation based on stress histories and the Palmgren-Miner rule. [ABSTRACT FROM AUTHOR]

The aim of the present study was to examine the ability of a GPS-imbedded accelerometer to assess stride variables and vertical stiffness (K), which are directly related to neuromuscular fatigue during field-based high-intensity runs. The ability to detect stride imbalances was also examined. A team sport player performed a series of 30-s runs on an instrumented treadmill (6 runs at 10, 17 and 24 km⋅h-1) with or without his right ankle taped (aimed at creating a stride imbalance), while wearing on his back a commercially-available GPS unit with an embedded 100-Hz tri-axial accelerometer. Contact (CT) and flying (FT) time, and K were computed from both treadmill and accel-erometers (Athletic Data Innovations) data. The agreement between treadmill (criterion measure) and accelerometer-derived data was examined. We also compared the ability of the different systems to detect the stride imbalance. Biases were small (CT and K) and moderate (FT). The typical error of the estimate was trivial (CT), small (K) and moderate (FT), with nearly perfect (CT and K) and large (FT) correlations for treadmill vs. accelerometer. The tape induced very large increase in the right - left foot Δ in CT, FT and K measured by the treadmill. The tape effect on CT and K Δ measured with the accelerometers were also very large, but of lower magnitude than with the treadmill. The tape effect on accelerometer-derived Δ FT was unclear. Present data highlight the potential of a GPS-embedded accelerometer to assess CT and K during ground running. [ABSTRACT FROM AUTHOR]