Automated surface inspection (ASI) is critical to quality control in industrial manufacturing processes. Recent advances deep learning have produced new ASI methods that automatically learn high-level features from training samples while being robust changes and capable of detecting different types surfaces defects. However, they usually rely heavily on manpower collect label samples. In this paper, a generic semi-supervised learning-based approach for requires small quantity labeled data...

Catastrophic interlocking chemical accidents (CICAs) are the most frequent hazardous events that occur in parks, and they result severe human casualties property losses. Emergency rescue facilities play an important role ensuring safety of as their locations determine efficiency effectiveness emergency management process. This paper proposes a multi-objective location (ERFsL) model for CICAs. Due to special characteristics CICAs, proposed considers not only spatial but also potential risks...

Non-intrusive Load Monitoring is a technology that can identify the users' internal energy consumption by using data measured at single point on bus and event detection key technical problem need to be solved. An algorithm combining probability expert heuristic models proposed for in this study, including an pre-detection sub-algorithm called Voting Improved Isolated Forest high-sensitivity events verification Time Shift Downsampling Matching high-accuracy verification. used detect...

Electromagnetic field has a great impact on the performance of wireless sensor networks (WSNs). The influence electromagnetic generated by power equipment (WS) nodes is designated as two parameters: environmental interference factor (EEIF) and path loss index (PLI). EEIF used to describe probability in node sensing coverage model. PLI substituted into communication model; then, packet receiving success rate model can be obtained above models, which evaluate quality environment. Combined with...

Heterogeneous vehicle routing problem with time windows (HVRPTW) aspect of hazardous material (HazMat) transportation is studied in this article. Given the multiobjective nature HazMat transportation, a three-objective optimization model defined for HVRPTW transportation. The objective to determine fleet size and routes so as meet all given constraints well minimize objectives total traveling cost, risk, average redundancy. A load-variant risk assessment considering type waiting presented...

Crowd counting has received extensive attention in the field of computer vision, and methods based on deep convolutional neural networks (CNNs) have made great progress this task. However, challenges such as scale variation, nonuniform distribution, complex background, occlusion crowded scenes hinder performance these crowd counting. In order to overcome challenges, article proposes a multiscale spatial guidance perception aggregation network (MGANet) achieve efficient accurate MGANet...

In rotary ultrasonic machining (RUM), the yutilization of contactless energy transfer (CET) theory addresses limitations imposed by traditional contact power supply systems on rotational speed, however, it also introduces challenge inadequate transmission performance. Specifically, impedance variations oscillator pose challenges for CET system (CETS). These include maintaining high efficiency and desirable characteristics, which can impact performance quality workpiece. To address issue,...

This paper proposes a NARX (Nonlinear Auto-Regressive with Exogenous Inputs) model for the water distribution network real-time prediction and control. The estimates time-variable nodal demand equivalently by exploiting historical operating data establishes functional relationship between major variables among network. In addition, training scheme combination of offline online training, corresponding algorithm are proposed. And is established real results demonstrate applicative...

This work focuses on a hazardous material (HazMat) vehicle routing problem with time windows (VRPTW). Given the multi‐objective and uncertainty natures of HazMat transportation, robust VRPTW (MO‐RVRPTW) model is proposed, which simultaneously optimise both number vehicles uncertain transportation risk. An set containing 32 potential incident scenarios constructed to parameter. To handle (MOP), this develops two versions criterion transform MO‐RVRPTW its counterpart . A hybrid evolutionary...

An improved path planning algorithm based on dynamic window approach (DWA) is proposed to optimize real-time paths for agents moving in complex environments with plenty of static and/or obstacles, constraints, and performance constraints. In order improve the accuracy evaluation function adaptability different obstacle environments, weight ameliorated by designing adaptive laws this article. Meanwhile, aiming at defect local minima DWA algorithm, a low-speed steering strategy presented help...

A new probabilistic Hough transform algorithm for line detection was proposed. Instead of treating edge pixels in a binary image equally, weight is bestowed to each pixel according the surround suppression strength at pixel, which can be used either sampling stage or voting both transform. This put emphasis on those points located clear boundaries between different objects, leading higher probability from perceptually reasonable real lines image, as well suppressed false peaks space formed...

The recognition of non-line-of-sight (NLOS) state is a prerequisite for alleviating NLOS errors and crucial to ensure the accuracy positioning. Recent studies only identify line-of-sight (LOS) state, but ignore contribution occlusion categories spatial information perception. This paper proposes bidirectional search algorithm based on maximum correlation, minimum redundancy, computational cost (BS-mRMRMC). optimal channel impulse response (CIR) feature set, which can LOS states well, as well...

The production and storage of major hazard installations (MHIs) bring potential risks to chemical industrial park (CIP). In the system MHIs, its dangerous degree is mainly determined by key parameters, abnormal parameters often lead accidents. To predict real‐time risk values MHIs improve accident prevention ability CIP, we need a method that can combine dynamic prediction assessment. Quantitative assessment (QRA) not capable modelling variations during operation process. Therefore, this...

With the rapid development of information and Internet technology, online education has become an increasingly popular way education. Online allows learners to learn any content at place time. However, in process learning, learners' learning mood state is usually not paid attention to. Due a long time face monotonous non-communication computer screen, are prone physical or psychological fatigue, resulting decreased efficiency. In view this phenomenon, taking into account characteristics we...