In modern industries, machine health monitoring systems (MHMS) have been applied wildly with the goal of realizing predictive maintenance including failures tracking, downtime reduction, and assets ...preservation. In the era of big machinery data, data-driven MHMS have achieved remarkable results in the detection of faults after the occurrence of certain failures (diagnosis) and prediction of the future working conditions and the remaining useful life (prognosis). The numerical representation for raw sensory data is the key stone for various successful MHMS. Conventional methods are the labor-extensive as they usually depend on handcrafted features, which require expert knowledge. Inspired by the success of deep learning methods that redefine representation learning from raw data, we propose local feature-based gated recurrent unit (LFGRU) networks. It is a hybrid approach that combines handcrafted feature design with automatic feature learning for machine health monitoring. First, features from windows of input time series are extracted. Then, an enhanced bidirectional GRU network is designed and applied on the generated sequence of local features to learn the representation. A supervised learning layer is finally trained to predict machine condition. Experiments on three machine health monitoring tasks: tool wear prediction, gearbox fault diagnosis, and incipient bearing fault detection verify the effectiveness and generalization of the proposed LFGRU.
The maximum pit volume is a significant parameter to evaluate the pitting extent on metal materials, which could be associated with the charge transfer during a pitting event. Direct integration of ...the anodic current spike to count the involved charge for minor pit is feasible due to the similar impedance of both electrodes. But more complex pitting kinetics might appear during long time immersion resulting in abnormal current spike, which may disobey the regular distribution rule based on the stationary process. A transfer ratio was employed to estimate the proportion of the charge transfer during single event with the help of cathodic kinetic parameters to estimate the real anodic current. Considerable conformity between the calculated and the microscopic found maximum pit volume indicates a valuable method to estimate the pitting extent during a non-stationary pitting propagation process.
This paper addresses the issue of cooperative control concerning the output synchronization of the linear time-invariant multi-input multi-output multi-agent system i.e., multi-unmanned aerial ...vehicle (a swarm of the drone), by designing observer-based consensus protocol with directed communication topology. Considering the leader following consensus tracking problem, an observer-based protocol is designed to obtain desirable output synchronization. The protocol design consists of a local observer for the leader drone and a distributed observer for the follower drones. Observer gains are optimized through a multi-step algorithm based on linear quadratic regulator controller and linear matrix inequalities. Most of the existing literature on cooperative control considers full state information for the controller as well as observer design. However, the protocol for the controller and observer design for consensus tracking of multi-unmanned aerial vehicles presented in this paper considers that only the relative partial states information from the corresponding neighboring drones are utilized. The designed algorithm is robust and guarantees that all the states of follower drones track the states of the leader drone and the consensus is achieved asymptotically even in the presence of external disturbances. Finally, considering the ideal and perturbed system, the efficacy of the analytical results are illustrated by comparative analysis using numerical simulations.
In this work, iron was recovered from a kind of iron-rich pickling sludge by an acid leaching process, and the recycled iron was used as a catalyst to activate peroxydisulfate (PS) for the ...degradation of phenol. Different kinds of sludge catalysts were prepared by different drying methods such as ordinary drying (Ods), freeze drying (Fds) and vacuum drying (Vds). The degradation performance of the different catalysts/PS system under different conditions was explored, the vacuum drying sludge catalyst (Vds) has the best activity in a wide pH range (pH = 3-10) and a wide temperature range (0-40 °C). At the same time, the effect of a series of chelating agents (Oxalic acid (OA), Citric acid (CA), Tartaric acid (TA), Malic acid (DL-MA) and Ethylenediaminetetraacetic acid (EDTA)) on Vds/PS system was verified, and TA was selected as the best chelating agent to promote the degradation of the second stage where the degradation rate is limited. The quenching experiment and electron paramagnetic resonance (EPR) analysis indicated that hydroxyl radical (·OH) and sulfate radical (SO
) were responsible for the abatement of the organic contaminant with ·OH playing a more important role. In summary, this study proposed an environmentally-friendly approach for the application of iron-rich pickling sludge in the remediation of phenol-contaminated water.
Fire risk assessment is important in heritage-village risk management and cultural relics protection. This study aims to establish a fire risk assessment system and model to assess fire safety for ...heritage villages. Given the complexity and openness of the heritage village system, the nonlinearity of the driving factors, and the dual attributes of residence and tourism, this paper constructs an index system of three aspects: cultural relic value sensitivity, village fire hazard, and evacuation accessibility. Based on ANP and the Bayes algorithm, a hybrid intelligent model is developed, and the index is weighted by combining subjective expert scoring and objective fact statistics. Finally, ArcGIS buffer and network analysis functions are used for grid processing to quantify and evaluate the difference in fire risk distribution in spatial units of heritage villages. We apply this assessment method to Chengkan Village, a national critical cultural relic protection unit. The results reveal that the cluster settlement layout pattern of the ancestral temple buildings plays a decisive role in the fire risk distribution in Chengkan Village; furthermore, the main factors leading to fire risk were analyzed. In Chengkan Village’s core area, the focus of the local government should be on strengthening active fire prevention measures to reduce the probability of fire. In contrast, in the northern and southern areas, it should focus on enhancing passive fire prevention measures to reduce the possibility of significant fires.
With the rising adoption of renewable energy sources worldwide, the uncertainty within electrical power systems is amplifying, leading to rising challenges in wind power assimilation and operational ...costs. In addressing these pressing issues, this research emphasizes a sophisticated modeling technique for the energy-intensive electro-fused magnesium loads on demand. Furthermore, we introduce a coordinated scheduling approach for power systems, harnessing the regulatory capabilities of these loads. Initially, an in-depth analysis of the characteristics of the electro-fused magnesium energy-intensive load is carried out, from which a refined model is developed. Subsequently, considering the flexible regulatory potential of the electro-fused magnesium furnace apparatus, a bi-level optimization scheduling model is crafted, prioritizing the maximization of wind power absorption at the upper level and minimizing system operational costs at the lower level. The efficacy and rationale of the proposed methodology are corroborated through computational analyses.
The microstructure and texture of three 316L foils of 25 μm thickness, which were subjected to different manufacturing process, were systematically characterized using advance analytical techniques. ...Then, the electrochemical property of the 316L foils in simulated pressurized water reactor (PWR) solution was analyzed using potentiodynamic polarization. The results showed that final rolling strain and annealing temperature had evident effect on grain size, fraction of recrystallization, grain boundary type and texture distribution. It was suggested that large final rolling strain could transfer Brass texture to Copper texture; low annealing temperature could limit the formation of preferable orientations in the rolling process to reduce anisotropy. Potentiodynamic polarization test showed that all samples exhibited good corrosion performance in the simulated primary PWR solution.
The double-aging strengthening effect of the γ’ phase in 945A nickel-based alloy was investigated. The double-aging treatment significantly improved the compressive yield stress. The sample after 8 h ...aging at 725 °C and 96 h at 800 °C exhibited the highest compressive yield stress of 1007 MPa, which greatly exceeded the original state of 229 MPa. The strengthening mechanism is mainly attributed to the Orowan strengthening mechanism. After double-aging treatment, high density γ’ phase precipitate was formed, which effectively improves the strength. The precipitate behavior and the strengthening mechanism of γ’ phase precipitates were clarified in detail.
Ni-based superalloys have attracted much attention due to their good resistance to high-temperature and -pressure environments. Compared with the traditional 718 Ni-based superalloy, 945A Ni-based ...superalloy with a lower Ni content showed better performance in terms of precipitated hardening and corrosion resistance. In this study, the aging behavior and the evolution of mechanical properties of the wrought 945A Ni-based superalloy were investigated. Microstructures were analyzed by scanning electron microscopy (SEM), bright field transmission electron microscopy (TEM), high-resolution TEM and high-angle annular dark field scanning TEM. Mechanical properties were measured by tensile and compressive tests. The results illustrated that the compressive yield stress was significantly improved by increasing aging time from 229 to 809 MPa. The increase was greater than 220%. This improvement was mainly attributed to the precipitates of the γ′ phase and carbides during the aging treatment. The residual dislocations generated by the plastic processes stimulated the formation of these precipitates. The precipitation behavior and the strengthening mechanism are discussed in detail.
The good generalization performance of conventional pattern classifiers often relies on the size of training data labeled by costly human labor. These days, publicly available web resources grow ...explosively, and this allows us to easily obtain abundant and cheap web data. Yet, web data are usually not as cooperative as human labeled data. In this paper, we explore the use of web text data to aid image classification. Without requiring the previous collection of auxiliary data from the web, we directly retrieve the web text information with the aid of the powerful reverse image search engine. We develop a novel textual modeling method named semantic matching neural network (SMNN) that is capable of learning semantic features from the associated text of web images. The SMNN text features have improved reliability and applicability, compared to the text features obtained from other methods. The SMNN text features and convolutional neural network (CNN) visual features are merged into a shared representation, which learns to capture the correlations between the two modalities. Experimental results on benchmark UIUC-Sports, Scene-15, Caltech-256, and Pascal VOC-2012 data sets show that the visual and text modalities of data from different sources are remarkably complementary and the fusion of them achieves substantial performance improvement.