Structural integrity is essential for safety in infrastructure, as it can help prevent catastrophic failures and financial losses. The significance of vibration-based damage detection has grown substantially in fields such as civil and mechanical engineering. Concurrently, the advancements in computational capacities have facilitated the integration of machine learning into damage detection processes through post-processing algorithms. Nevertheless, these require extensive data from structure-affixed sensors, raising computational requirements. In an effort to address this challenge, we propose a novel approach utilizing a pre-trained convolutional neural network (CNN) based on images to identify and assess structural damage. This method involves employing wavelet transform and scalograms to convert numerical acceleration data into image data, preserving spatial and temporal information more effectively compared to conventional Fourier transform frequency analysis. Six acceleration data channels are collected from carefully chosen nodes on a mini bridge model and a corresponding finite element bridge model, to train the CNN. The efficiency of training is further enhanced by applying transfer machine learning through two pre-trained CNNs, namely Alexnet and Resnet. We evaluate our method using different damage scenarios, and both Alexnet and Resnet show prediction accuracies over 90

This paper proposes an eco-driving framework for electric connected vehicles (CVs) based on reinforcement learning (RL) to improve vehicle energy efficiency at signalized intersections. The vehicle agent is specified by integrating the model-based car-following policy, lane-changing policy, and the RL policy, to ensure safe operation of a CV. Subsequently, a Markov Decision Process (MDP) is formulated, which enables the vehicle to perform longitudinal control and lateral decisions, jointly optimizing the car-following and lane-changing behaviors of the CVs in the vicinity of intersections. Then, the hybrid action space is parameterized as a hierarchical structure and thereby trains the agents with two-dimensional motion patterns in a dynamic traffic environment. Finally, our proposed methods are evaluated in SUMO software from both a single-vehicle-based perspective and a flow-based perspective. The results show that our strategy can significantly reduce energy consumption by learning proper action schemes without any interruption of other human-driven vehicles (HDVs).

Structural health monitoring (SHM) is of critical importance to ensuring safety of civil infrastructure systems. Measuring physical parameters such as inclination angles can provide insights in identifying and locating subtle structural damages, and thus help to evaluate health conditions of structures. With rapid development of wireless communication technologies, wireless sensing networks enable a low-cost and flexible solution compared to conventional cable-based SHM systems. In this paper, a prototype wireless sensing system for measuring inclination of structures is proposed. The sensing node is designed using low-cost electronic components in the market. Long range (LoRa) technology is adopted to offer long-range wireless communication with low power consumption. To obtain reliable inclination measurement, a sensor fusion algorithm is implemented to fully exploit the advantages of both gyroscopes and accelerometers. Laboratory tests are conducted to investigate the performance of the proposed wireless inclination sensing system.

The load that borne by ship mining system is very complex. The vibration of lifting pipe can be significantly affected by ocean current and wind load, which has a key impact on material lifting, ore bin storage and ship towing. Considering the composite load condition, the vibration control equation of mining ship is established based on the transverse swing mechanism of ship hull, and the variation law of transverse disturbance is obtained. The dynamic equation is constructed according to the bearing characteristics of the lifting system and the D'Alembert principle. The Wilson method is used to analyze and obtain the transverse vibration spectrum response of the lifting pipe under different wind loads, hull disturbance velocity and water depth. Based on the analogy method and hammering method, the vibration feedback test-bed of the lifting system is built, and the time-domain and frequency-domain vibration characteristics of the lifting pipe model under different water depths are obtained. The results show that in shallow water, the disturbance of mining ship and the composite load of ocean current are the key factors affecting the vibration amplitude of lifting pipe respectively. With the increase of water depth, the characteristic frequency and amplitude of the system decrease, and the amplitude gradually presents a discontinuous phenomenon.

Objective To develop and validate an interactive nomogram to predict healthcare-associated infections (HCAIs) in the intensive care unit (ICU). Methods A multicenter retrospective study was conducted to review 2017 data from six hospitals in Guizhou Province, China. A total of 1,782 ICU inpatients were divided into either a training set (n = 1,189) or a validation set (n = 593). The patients' demographic characteristics, basic clinical features from the previous admission, and their need for bacterial culture during the current admission were extracted from electronic medical records of the hospitals to predict HCAI. Univariate and multivariable analyses were used to identify independent risk factors of HCAI in the training set. The multivariable model's performance was evaluated in both the training set and the validation set, and an interactive nomogram was constructed according to multivariable regression model. Moreover, the interactive nomogram was used to predict the possibility of a patient developing an HCAI based on their prior admission data. Finally, the clinical usefulness of the interactive nomogram was estimated by decision analysis using the entire dataset. Results The nomogram model included factor development (local economic development levels), length of stay (LOS; days of hospital stay), fever (days of persistent fever), diabetes (history of diabetes), cancer (history of cancer) and culture (the need for bacterial culture). The model showed good calibration and discrimination in the training set [area under the curve (AUC), 0.871; 95% confidence interval (CI), 0.848-0.894] and in the validation set (AUC, 0.862; 95% CI, 0.829-0.895). The decision curve demonstrated the clinical usefulness of our interactive nomogram. Conclusions The developed interactive nomogram is a simple and practical instrument for quantifying the individual risk of HCAI and promptly identifying high-risk patients.

Purpose: We aimed to assess the effect of community-based lifestyle interventions on weight loss and cardio-metabolic risk factors among obese older adults, and to explore the potential factors that impede weight loss during lifestyle interventions. Materials and methods: A 2-arm parallel randomized controlled trial was conducted from 2013 through 2016 in the community health service centers in Nanjing, China. Four hundred and eighty obese older adults were randomly assigned to receive a 24-month lifestyle intervention (242 participants) or usual care (238 participants). The intervention group received a community-based behavioral lifestyle intervention program, which targeted weight loss through dietary changes and increased physical activity, with a combination mode of intervention delivery. Results: Weight loss was statistically significant at the end of the intervention with a mean reduction of 0.03 +/- 2.51 kg in the control group and 3.22 +/- 3.43 kg in the intervention group (p < .001). In the intervention group, 41.1% of participants achieved the target of 5% weight loss significantly (p < .001). Participants in the intervention group had significantly greater improvements in cardiometabolic risk factors. Multivariable logistic regression showed that female, living alone, and having more comorbidities were barriers to weight loss during the intervention. Conclusions: This study demonstrated that community-based lifestyle interventions are effective for managing weight and improving cardiometabolic risk factors in obese older adults.

Passive wireless patch antenna sensors have been developed in recent years to provide convenient and low-cost strain sensing for structural health monitoring (SHM). Current studies mainly focus on strain measurement in one direction, which is not sufficient for quantifying arbitrary strain field in many applications. This paper presents strain sensor rosettes made of two types of antenna sensors, folded patch antenna sensor and slotted patch antenna sensor, for measuring an arbitrary surface strain field. The transverse strain effect in both types of antenna sensors has been discussed. Mechanics-electromagnetics coupled simulation is conducted to validate the strain sensing performance of the strain rosettes made of antenna sensors. Numerical results show that both types of strain sensing rosettes can measure an arbitrary surface strain field with acceptable accuracy.

Passive (battery-free) wireless patch antenna sensors have been developed in recent years for strain sensing, to provide convenient and low-cost instrumentation. Despite past efforts, current analytical and experimental studies have mainly focused on performance in single-axial measurement, which is simple and unrealistic from typically encountered arbitrary plane stress fields. This paper presents strain sensor rosettes made of folded patch antennas and slotted patch antennas for measuring an arbitrary surface strain (plane stress) field. The transverse strain effect of both sensors is discussed and has been validated through laboratory experiments. Multiphysics coupled simulation is conducted to describe accurately the mechanical and electromagnetic behaviours of antenna sensors. Resonance frequency shifts of the antenna sensors are used to derive the three strain components in an arbitrary plane stress scenario – that is, two normal and one shear strain components. Both numerical studies and experimental validations have been performed.

To simulate the behavior of a passive antenna strain sensor, current multiphysics coupled simulation (between mechanics and electromagnetics) has mainly adopted the frequency domain solution. For every frequency point in the sweeping range, the frequency domain solver computes the value of scattering parameter S11. The S11 curve is used to identify the new resonance frequency when the antenna sens...

This paper presents the design, simulation, and validation experiments of a passive (battery-free) wireless frequency doubling antenna sensor for strain and crack sensing. Since the length of a patch antenna governs the antenna's resonance frequency, a patch antenna bonded to a structural surface can be used to measure mechanical strain or crack propagation by interrogating resonance frequency shift due to antenna length change. In comparison with previous approaches such as radio frequency identification, the frequency doubling scheme is proposed as a new signal modulation approach for the antenna sensor. The proposed approach can easily distinguish backscattered passive sensor signal (at the doubled frequency 2 f) from environmental electromagnetic reflections (at original reader interrogation frequency f). To accurately estimate the performance of the frequency doubling antenna sensor, a multi-physics coupled simulation framework is proposed to aid the sensor design while considering both the mechanical and electromagnetic behaviors. Two commercial software packages, COMSOL and Advanced Design System (ADS), are combined to leverage the features from each other. The simulated performance of the frequency doubling antenna sensor is further validated by experiments. The results show that the sensor is capable of detecting small strain changes and the growth of a small crack.