查看更多>>摘要：? 2022 Elsevier LtdThe inspection of underground sewer defects plays a considerable role in estimating the structural integrity and avoiding various unforeseen functional failures. However, the conventional sewer defect inspection approaches suffer from the blurry and vaporous environment inside the sewer pipes, which significantly lowers the performance. Besides, it is challenging to achieve efficient and accurate condition assessment by the common manual inspection. Therefore, this manuscript introduces an automatic instance segmentation-based defect analysis framework. The main contributions include 1) a novel defect segmentation model called Pipe-SOLO is firstly presented to segment six common types of defects at the instance level by proposing an efficient backbone structure (Res2Net-Mish-BN-101) and designing an enhanced BiFPN (EBiFPN), 2) a GAN-based dehazing model is applied to effectively solve the image blurring problem, and 3) a publicly available sewer defect segmentation dataset. The experimental results show the proposed Pipe-SOLO achieved an improvement of 7.3% compared with the state-of-the-art method in terms of the mean Average Precision (mAP). Therefore, the proposed defect segmentation method is promising to be integrated with real-life applications that require defect localization and estimation.
查看更多>>摘要：? 2022 Elsevier LtdAccurate identification of obstacles shows great significance to improve the safety of automatic operation trains. The ME Mask R-CNN is proposed to improve the accuracy of active identification. The SSwin-Le Transformer is used as the feature extraction network and the ME-PAPN is used as the feature fusion network. A variety of multi-scale enhancement methods are integrated to improve the detection ability of small target objects. PrIme sample attention is used as the sampling method, the anchor boxes size and ratio suitable for the characteristics of train obstacles are adopted. The train obstacle dataset is based on a variety of test scenarios such as Nanning Metro Line 1 test line, tunnel line and night test. The test results show that ME Mask R-CNN achieves 91.3 % mAP with an average detection time of 4.2 FPS, which is 11.1 % higher than that of Mask R-CNN.
查看更多>>摘要：? 2022 Elsevier LtdEvaluation of masonry damage is considerably challenging because of the non-homogeneous nature of masonry materials and the rapid attenuation of signals. To this end, a methodology combining qualitative analysis employing support vector machine-based acoustic emission (AE) monitoring and quantitative analysis using AE rate process theory was proposed. In this work, firstly, the propagation attenuation characteristics of the AE amplitude and frequency were studied using pencil-lead break tests. The hybrid PSO-SVM model was employed to automatically identify the damage stages of the AE signals based on the field in-situ axial compression test data. Then, laboratory compression and shear tests on small-scale specimens were performed with AE monitoring. The Boltzmann sigmoidal modified function between relative stress and AE hits was established. Based on qualitative and quantitative analysis, a damage index-based early warning range was proposed, which can help to decide the damage level of masonry structures. The results of this paper can provide some new insight for the analysis of masonry damage.
查看更多>>摘要：? 2022 Elsevier LtdRolling bearings are key components in rotating machines, and their health condition is an important guarantee for the safety of the whole machine. In order to extract fault features of rolling bearings more accurately, a novel signal processing method named Second-order Iterative Time-rearrangement Synchrosqueezing Transform (2-ITSST) with a fast algorithm is proposed in this paper. Firstly, based on Time-reassigned SynchroSqueezing Transform (TSST), the approximation order is increased from the first order to the second order. Then, multiple iterations are conducted to calculate a more accurate group delay (GD) estimation operator. After that, the rearrangement operation is carried out to maximize the concentration of energy near the time-frequency (TF) ridgeline and obtain the result with higher TF aggregation. Lastly, the fast algorithm for 2-ITSST is introduced to overlap TF matrices into segments, which effectively reduced the computational complexity and ensured the TF aggregation of impact signal energy. Meanwhile, in order to make 2-ITSST more efficiently applied in bearing fault diagnosis, impulse extraction method is introduced to extract useful impulse features from the signal processed by 2-ITSST algorithm, and then the bearing fault frequency can be accurately extracted by envelope spectrum analysis. The effectiveness of the proposed method is verified by simulation and experimental studies.
查看更多>>摘要：? 2022 Elsevier LtdSeizure detection is a particularly difficult task for neurologists to correctly identify the Electroencephalography (EEG)-based neonatal seizures in a visual manner. There is a strong demand to recognize the seizures in more automatic manner. Developing an expert seizure detection system with an acceptable performance level can partly fill this research gap. This paper proposes a new framework for the automated detection of neonatal seizures based on the Morse Wavelet approach that is coupled with a local binary pattern algorithm, and a graph-based community detection algorithm. An ensemble classifier method is designed to detect neonatal seizures prevalent in EEG signals. Our findings show that only 59 of the texture features can exhibit the abnormal increase in an EEG amplitude and the spikes notable during a seizure. The present results demonstrate that the proposed seizure detection model is more accurate for the detection of seizures compared with some of the traditional approaches.
查看更多>>摘要：? 2022 Elsevier LtdIn road traffic, adjusting the tracking distance between your vehicle and the one in front of your vehicle is necessary for safe driving. The systems developed for this purpose must detect object distance with high reliability. Accordingly, this article presents a stereo-vision-based method for estimating the distance between a given vehicle and the vehicle in front of it. In the proposed method, cameras are positioned such that their optical axes are equally tilted toward and intersect each other (i.e., the toe-in style). The tilt of the optical axes toward each other makes the different horizontal positions of the front vehicle important in the proposed distance estimation. Images of different horizontal deviation values at specified distances from the front vehicle are used to develop an artificial neural network (ANN) model. The results obtained from the test data show that, the proposed methodology is effective for determining the distance between vehicles.
查看更多>>摘要：? 2022 Elsevier LtdThis paper presents a procedure and a set-up of an electronic nose system analyzing exhaled breath to detect the patients suffering from dengue – a mosquito-borne tropical disease. Low-power resistive gas sensors (MiCS-6814, TGS8100) were used to detect volatile organic compounds (VOCs) in the exhaled breath. The end-tidal phase of patients exhaled breath was collected with a BioVOCTM breath sampler. Two strategies were assessed for breath samples measurement: either direct transfer from the BioVOCTM into the sensors test chamber, or storage in Tenax TA sorbent tubes followed by VOCs release through thermal desorption and then transfer into sensors test chamber. DC sensor resistances were recorded and processed by multivariate classifier algorithms to detect infected patients. The experimental studies were run on a group of 26 individuals (16 dengue diagnosed patients and 10 control volunteers). The detection accuracy of dengue patients was over 90%.
查看更多>>摘要：? 2022 Elsevier LtdThe polarization compass used for unmanned aerial vehicle (UAV) navigation is usually hypothesized to be arranged horizontally in conventional heading measurement, which leads to a noticeable heading error due to the inevitable tilts called the pitch angle and the roll angle during UAV flight process. In addition, we found that the coupling of the angle between the solar meridian and the body axis of a carrier (A-SMBA) and tilted-angles will produce more remarkable heading errors. Consequently, we first introduce a comprehensive analysis of heading error in terms of variable attitude angles of the compass including the A-SMBA, the pitch angle and the roll angle. A novel heading error modeling and compensation for attitude-changed of the polarization compass by gated recurrent unit (GRU) neural network is developed subsequently. The experimental results demonstrate the proposed heading error modeling and compensation method performs best compared to state-of-the-art algorithms in predicting the UAV orientation.
查看更多>>摘要：? 2022 The Author(s)The precision manufacturing industry depends on precision measurement instruments capable of tracing the measurement results to national and international standards. This paper presents a calibration model for a high precision telescopic instrument (HPTI) for machine tool verification together with its estimated uncertainty budget. The instrument tracks autonomously a target using an interferometric sensor to measure distances and allows the simultaneous use of three HPTIs for multilateration, decreasing data capture time and improving measurement accuracy. A calibrating ball beam artefact, previously calibrated with a coordinate measurement machine, is used to trace the calibration results. The uncertainty of the HPTI is estimated in laboratory conditions. The uncertainty budget of the HPTI, as well as the uncertainty of simultaneous multilateration, in workshop conditions are analysed and estimated with Monte Carlo. The calibration model defined gives traceability to the measurement results obtained with the HPTI allowing its use in machine tool verification processes.
查看更多>>摘要：? 2022 Elsevier LtdIn this work, a new calibration apparatus, which employs the flowmeter method and the orifice method, was developed to get the low pumping speed of the miniature sputter ion pump (SIP), and the two methods were compared in the measurement of the low pumping speed. A low pumping speed of the order of 10-4 m3 s?1 was calibrated in the pressure range of 10-6 Pa to 10-2 Pa, and the combined standard uncertainty was 4.5–8.8% for nitrogen. The measurement results of the spinning rotor gauge (SRG) and the extractor gauge (IE514) were contrasted, and it can be found that the measurement error of the extractor gauge is obvious. Hence a method to measure the pumping speed and the outgassing rate of the extractor gauge is introduced, and the influence of the extractor gauge on the measurement was evaluated in the pressure range of 10-6 Pa to 10-4 Pa. The low pumping speed of the miniature SIP, which is a single-cylinder diode SIP, was calibrated in these high purity gases (N2, He, and Ar), and the flowmeter method performs better than the orifice method.
NSTL
Elsevier