Novel assessment and prediction method for vessel traffic risk degree

2021 ◽  
pp. 1748006X2110394
Author(s):  
Bo Li
Keyword(s):  
Evidence Theory ◽  
Prediction Method ◽  
Optimal Solution ◽  
Fuzzy Membership Functions ◽  
Matrix Deformation ◽  
Probabilistic Assignment ◽  
The Matrix ◽  
Novel Method ◽  
Risk Degree ◽  
Current Risk

To assess the current risk degree and predict the future risk degree of vessel traffic, a novel method is put forward in this study. Different from the existing literature, the available evidence of vessel traffic is directly transformed into the weighted basic probabilistic assignment (BPA) based on the optimal solution to the intersection of fuzzy membership functions in the framework of D-S evidence theory. The matrix deformation algorithm towards the combination rule makes the time complexity low in the process of the risk degree assessment. With respect to the risk degree prediction, the required Sigma points are effectively extracted. We derive the adaptive filtering gain that is suitable for the rapidly changing BPA. Finally, the experiments of vessel traffic in the Dalin Bay are made to indicate performance of the proposed method.

scholarly journals Rolling Bearing Fault Prediction Method Based on QPSO-BP Neural Network and Dempster–Shafer Evidence Theory

Energies ◽  
2020 ◽  
Vol 13 (5) ◽  
pp. 1094 ◽  
Author(s):  
Lanjun Wan ◽  
Hongyang Li ◽  
Yiwei Chen ◽  
Changyun Li
Keyword(s):  
Neural Network ◽  
Working Conditions ◽  
Bp Neural Network ◽  
Evidence Theory ◽  
Prediction Method ◽  
Rolling Bearing ◽  
Fault Prediction ◽  
Fault Classification ◽  
Bearing Fault ◽  
Hidden Layer

To effectively predict the rolling bearing fault under different working conditions, a rolling bearing fault prediction method based on quantum particle swarm optimization (QPSO) backpropagation (BP) neural network and Dempster–Shafer evidence theory is proposed. First, the original vibration signals of rolling bearing are decomposed by three-layer wavelet packet, and the eigenvectors of different states of rolling bearing are constructed as input data of BP neural network. Second, the optimal number of hidden-layer nodes of BP neural network is automatically found by the dichotomy method to improve the efficiency of selecting the number of hidden-layer nodes. Third, the initial weights and thresholds of BP neural network are optimized by QPSO algorithm, which can improve the convergence speed and classification accuracy of BP neural network. Finally, the fault classification results of multiple QPSO-BP neural networks are fused by Dempster–Shafer evidence theory, and the final rolling bearing fault prediction model is obtained. The experiments demonstrate that different types of rolling bearing fault can be effectively and efficiently predicted under various working conditions.

AN EFFECTIVE CONTROL FLOW CHECKING METHOD FOR MULTITASK PROCESSING IN HARSH ENVIRONMENTS

2013 ◽  
Vol 22 (08) ◽  
pp. 1350067 ◽  
Author(s):  
SEYYED AMIR ASGHARI ◽  
ATENA ABDI ◽  
OKYAY KAYNAK ◽  
HASSAN TAHERI ◽  
HOSSEIN PEDRAM
Keyword(s):  
Error Detection ◽  
Optimal Solution ◽  
Control Flow ◽  
Simultaneous Optimization ◽  
Harsh Environments ◽  
Effective Control ◽  
Power Performance ◽  
Single Event Upsets ◽  
Novel Method ◽  
And Performance

Electronic equipment used in harsh environments such as space has to cope with many threats. One major threat is the intensive radiation which gives rise to Single Event Upsets (SEU) that lead to control flow errors and data errors. In the design of embedded systems to be used in space, the use of radiation tolerant equipment may therefore be a necessity. However, even if the higher cost of such a choice is not a problem, the efficiency of such equipment is lower than the COTS equipment. Therefore, the use of COTS with appropriate measures to handle the threats may be the optimal solution, in which a simultaneous optimization is carried out for power, performance, reliability and cost. In this paper, a novel method is presented for control flow error detection in multitask environments with less memory and performance overheads as compared to other methods seen in the literature.

Graphite/UPE Nanocomposite: Transport, Thermal, Mechanical and Viscoelastic Properties

2019 ◽  
Vol 23 ◽  
pp. 201-212
Author(s):  
Shivkumari Panda ◽  
Dibakar Behera ◽  
Tapan Kumar Bastia
Keyword(s):  
Transport Properties ◽  
Unsaturated Polyester ◽  
Homogeneous Distribution ◽  
Thermo Gravimetric ◽  
New Class ◽  
The Matrix ◽  
Novel Method ◽  
Water Transport Properties ◽  
First Time

This chapter presents the preparation and characterization of some unique properties of nanocomposites by dispersing graphite flakes in commercial unsaturated polyester (UPE) matrix. The composite was prepared by a novel method with the use of solvent swelling technique. Three different specimens of UPE/graphite nanocomposites were fabricated with addition of 1, 2 and 3 wt% of graphite flakes. Except mechanical, viscoelastic and thermo gravimetric properties, transport properties like electrical conductivity, thermal conductivity and water transport properties were studied for the first time. Graphite flakes propose enhanced properties to the composites suggesting homogeneous distribution of the nanofiller in the matrix and strong interaction with the matrix. 2wt% nanofiller loading showed superior essential characteristics and after that the properties reduced may be due to the nucleating tendency of the nanofiller particles. The XRD pattern showed the compatibility of the graphite flakes by introducing a peak around 26.550 in the nanocomposites. SEM Properties are also in agreement with the compatibility. Nanocomposite with 2wt% graphite also showed remarkable enhancement in transport, mechanical, viscoelastic and thermo gravimetric properties. So by introduction of a small quantity of graphite endow the new class of multiphase nanocomposites with inimitable structure and tremendous application.

scholarly journals Matrix Neuro-Fuzzy Self-Organizing Clustering Network

2011 ◽  
Vol 45 (1) ◽  
pp. 54-58 ◽  
Author(s):  
Yevgeniy Bodyanskiy ◽  
Valentyna Volkova ◽  
Mark Skuratov
Keyword(s):  
Fuzzy Inference ◽  
Data Sets ◽  
Fuzzy Membership Functions ◽  
Neuro Fuzzy ◽  
The Matrix ◽  
On Line ◽  
Winner Take All ◽  
Overlapping Classes ◽  
Self Learning ◽  
Self Organizing

Matrix Neuro-Fuzzy Self-Organizing Clustering NetworkIn this article the problem of clustering massive data sets, which are represented in the matrix form, is considered. The article represents the 2-D self-organizing Kohonen map and its self-learning algorithms based on the winner-take-all (WTA) and winner-take-more (WTM) rules with Gaussian and Epanechnikov functions as the fuzzy membership functions, and without the winner. The fuzzy inference for processing data with overlapping classes in a neural network is introduced. It allows one to estimate membership levels for every sample to every class. This network is the generalization of a vector neuro- and neuro-fuzzy Kohonen network and allows for data processing as they are fed in the on-line mode.

scholarly journals Kinematic Design of a Seven-Bar Linkage with Optimized Centrodes for Pure-Rolling Cutting

2017 ◽  
Vol 2017 ◽  
pp. 1-11 ◽  
Author(s):  
Biao Liu ◽  
Yali Ma ◽  
Delun Wang ◽  
Shaoping Bai ◽  
Yangyang Li ◽  
...  
Keyword(s):  
Optimal Solution ◽  
Genetic Optimization ◽  
Dimensional Synthesis ◽  
Cutting Mechanism ◽  
Pure Rolling ◽  
Moving Points ◽  
Novel Method ◽  
Design Requirements ◽  
Genetic Optimization Algorithm ◽  
Peak Value

A novel method for designing a seven-bar linkage based on the optimization of centrodes is presented in this paper. The proposed method is applied to the design of a pure-rolling cutting mechanism, wherein close interrelation between the contacting lines and centrodes of two pure-rolling bodies is formulated and the genetic optimization algorithm is adopted for the dimensional synthesis of the mechanism. The optimization is conducted to minimize the error between mechanism centrodes and the expected trajectories, subject to the design requirements of the opening distance, the maximum amount of overlap error, and peak value of shearing force. An optimal solution is obtained and the analysis results show that the horizontal slipping and standard deviation of the lowest moving points of the upper shear blade have been reduced by 78.0% and 80.1% and the peak value of shear stress decreases by 29%, which indicate better cutting performance and long service life.

Predicting Future Diameter Distributions Given Current Stand Attributes

2022 ◽  
Author(s):  
Quang V. Cao
Keyword(s):  
Prediction Method ◽  
Diameter Distribution ◽  
Tree Level ◽  
Individual Tree ◽  
Distribution Parameters ◽  
Level Model ◽  
Novel Method ◽  
Quadratic Mean Diameter ◽  
Stand Attributes ◽  
Individual Trees

This study discussed four methods to project a diameter distribution from age A1 to age A2. Method 1 recovers parameters of the distribution at age A2 from stand attributes at that age. Method 2 uses a stand-level model to grow the quadratic mean diameter, and then recovers the distribution parameters from that prediction. Method 3 grows the diameter distribution by assuming tree-level survival and diameter growth functions. Method 4 first converts the diameter distribution at age A1 into a list of individual trees before growing these trees to age A2. In a numerical example employing the Weibull distribution, methods 3 and 4 produced better results based on two types of error indices and the relative predictive error for each diameter class. Method 4 is a novel method that converts a diameter distribution into a list of individual-trees, and in the process, successfully links together diameter distribution, individual-tree, and whole stand models.

scholarly journals Hashing Based Answer Selection

2020 ◽  
Vol 34 (05) ◽  
pp. 9330-9337
Author(s):  
Dong Xu ◽  
Wu-Jun Li
Keyword(s):  
Question Answering ◽  
Matrix Representation ◽  
Matrix Representations ◽  
Binary Matrix ◽  
Large Memory ◽  
The Matrix ◽  
Novel Method ◽  
Online Prediction ◽  
Memory Cost ◽  
Vector Representations

Answer selection is an important subtask of question answering (QA), in which deep models usually achieve better performance than non-deep models. Most deep models adopt question-answer interaction mechanisms, such as attention, to get vector representations for answers. When these interaction based deep models are deployed for online prediction, the representations of all answers need to be recalculated for each question. This procedure is time-consuming for deep models with complex encoders like BERT which usually have better accuracy than simple encoders. One possible solution is to store the matrix representation (encoder output) of each answer in memory to avoid recalculation. But this will bring large memory cost. In this paper, we propose a novel method, called hashing based answer selection (HAS), to tackle this problem. HAS adopts a hashing strategy to learn a binary matrix representation for each answer, which can dramatically reduce the memory cost for storing the matrix representations of answers. Hence, HAS can adopt complex encoders like BERT in the model, but the online prediction of HAS is still fast with a low memory cost. Experimental results on three popular answer selection datasets show that HAS can outperform existing models to achieve state-of-the-art performance.

Efficient Multi-Scale Registration of 3D Reconstructions Based on Camera Center Constraint

2014 ◽  
Vol 998-999 ◽  
pp. 1018-1023
Author(s):  
Rui Bin Guo ◽  
Tao Guan ◽  
Dong Xiang Zhou ◽  
Ke Ju Peng ◽  
Wei Hong Fan
Keyword(s):  
Experimental Results ◽  
Cayley Transform ◽  
3D Reconstructions ◽  
Multi Scale ◽  
The Matrix ◽  
Novel Method ◽  
3D Scene ◽  
Coordinates Transformation

Recent approaches for reconstructing 3D scenes from image collections only produce single scene models. To build a unified scene model that contains multiple subsets, we present a novel method for registration of 3D scene reconstructions in different scales. It first normalizes the scales of the models building on similarity reconstruction by the constraint of the 3D position of shared cameras. Then we use Cayley transform to fit the matrix of coordinates transformation for the models in normalization scales. The experimental results show the effectiveness and scalability of the proposed approach.

Minimum time multiple-burn optimization of an upper stage with a finite thrust for satellite injection into geostationary orbit

2017 ◽  
Vol 232 (8) ◽  
pp. 1542-1558 ◽  
Author(s):  
Mojtaba Alavipour ◽  
Amir A Nikkhah ◽  
Jafar Roshanian
Keyword(s):  
High Performance ◽  
Shooting Method ◽  
Optimal Solution ◽  
Minimum Time ◽  
Geostationary Orbit ◽  
End Conditions ◽  
Upper Stage ◽  
Thrust Vector ◽  
Novel Method ◽  
Finite Thrust

In this paper, the problem of minimum time multiple-burn optimization of an upper stage with a limited thrust, and engine restart capability for satellite injection into geostationary orbit are considered. The goals are to find thrust vector angle, times of the engine firings, and optimal duration of active phases of the upper stage to minimize fuel consumption and meet the desired boundary conditions. Various flight sequences with multiple burns, from two burns up to six burns, are considered. Also, the optimal trajectory for each sequence is derived. To solve the multi-point boundary value problem, an improved indirect shooting method with high performance is presented and used for an optimal solution. All in all, this novel method presented for multi-burn problem, not only with a very good accuracy, but also with a very fast convergence to the desired end conditions.

Microstructure and Properties of Surface Nanostructured Copper

2011 ◽  
Vol 328-330 ◽  
pp. 1606-1609
Author(s):  
Wan Ming Lin ◽  
Yin Hui Wei ◽  
Li Feng Hou
Keyword(s):  
Copper Plate ◽  
Surface Mechanical Attrition Treatment ◽  
Hardness Testing ◽  
Surface Layers ◽  
Materials Properties ◽  
Transmission Electron ◽  
Mechanical Attrition ◽  
The Matrix ◽  
Novel Method ◽  
Potentiodynamic Anodic Polarization

Surface nanocrystallization (SNC) is a novel method for improving materials properties. Nanostructured surface layers of about 20 μm thickness were produced in copper plate samples by means of surface mechanical attrition treatment (SMAT). The behaviors of the SMAT samples were investigated by using transmission electron microscopy (TEM), Vickers hardness testing and potentiodynamic anodic polarization tests. The experimental results showed that the longer the peening time was performed on the copper pate samples, the thicker the deformation layers formed. The microhardness results for the top surface layer of the copper plate sample are 1.723 GPa and 1.752 GPa for 45 and 60 min, respectively, which are about two times higher than that of the matrix. The primary passivate potential of nanocrystalline copper was more negative than that of coarse-grain copper.

Sign in / Sign up

Export Citation Format

Share Document