Search results

To enhance the pleasure experience of clothes shopping online, finding satisfactory clothing and similar clothing recommendations to customers should be available and accurate. The purpose of this paper is to present a method for automatically computing the similarity between two apparels and giving an effective recommendation.

Based on a tabular layout of article characteristics the authors built a clothing information model to describe clothing. The clothing attributes are classified according to excavating features of the model. After the proposal of the computation algorithm for various attributes, an efficient similarity computation method is developed to obtain similar clothes with the given cloth. To prevent error and information omission during the computation, the analytic hierarchy process method and entropy method are adopted by the integrated weights as a control.

Clothing is a non‐rigid product which has a lot of crossover and complicated attributes and features. This paper found a tabular layout of article characteristics can explain the clothing clearly. Through experiments the authors found the weight of attributes to have a great influence on similar results during the similarity computation.

This paper presents a new way to describe clothing information, and present the algorithm for attributes computation.

The purpose of this paper is to accurately obtain the deformation of a hybrid robot and rapidly enable real-time compensation in friction stir welding (FSW). In this paper, a prediction algorithm based on the back-propagation neural network (BPNN) optimized by the adaptive genetic algorithm (GA) is presented.

Via the algorithm, the deformations of a five-degree-of-freedom (5-DOF) hybrid robot TriMule800 at a limited number of positions are taken as the training set. The current position of the robot and the axial force it is subjected to are used as the input; the deformation of the robot is taken as the output to construct a BPNN; and an adaptive GA is adopted to optimize the weights and thresholds of the BPNN.

This algorithm can quickly predict the deformation of a robot at any point in the workspace. In this study, a force-deformation experiment bench is built, and the experiment proves that the correspondence between the simulated and actual deformations is as high as 98%; therefore, the simulation data can be used as the actual deformation. Finally, 40 sets of data are taken as examples for the prediction, the errors of predicted and simulated deformations are calculated and the accuracy of the prediction algorithm is verified.

The entire algorithm is verified by the laboratory-developed 5-DOF hybrid robot, and it can be applied to other hybrid robots as well.

Robots have been widely used in FSW. Traditional series robots cannot bear the large axial force during welding, and the deformation of the robot will affect the machining quality. In some research studies, hybrid robots have been used in FSW. However, the deformation of a hybrid robot in thick-plate welding applications cannot be ignored. Presently, there is no research on the deformation of hybrid robots in FSW, let alone the analysis and prediction of their deformation. This research provides a feasible methodology for analysing the deformation and compensation of hybrid robots in FSW. This makes it possible to calculate the deformation of the hybrid robot in FSW without external sensors.

This paper aims to propose a suitable atomizing solidification chitosan (CS) gel liquid extrusion molding technology for the three dimensional (3D) printing method, and experiments verify the feasibility of this method.

This paper mainly uses experimental means, combined with theoretical research. The preparation method, solidification forming method and 3D printing method of CS gel solution were studied. The CS gel printing mechanism and printing error sources are analyzed on the basis of the CS gel ink printing results, printing performance with different ratios of components by constructing a gel print prototype, experiments evaluating the CS gel printing technology and the effects of the process parameters on the scaffold formation.

CS printing ink was prepared; the optimal formula was found; the 3 D printing experiment of CS was completed; the optimal printing parameters were obtained; and the reliability of the forming prototype, printing ink and gel printing process was verified, which allowed for the possibility to apply the 3 D printing technology to the manufacturing of a CS gel structure.

This study can provide theoretical and technical support for the potential application of CS 3 D printed gels in tissue engineering.

Clothing retrieval is very useful to help the clients to efficiently search out the apparel they want. Currently, the mainstream clothing retrieval methods are attribute semantics based, which however are inconvenient for common clients. The purpose of this paper is to provide an easy‐to‐operate apparels retrieval mode with the authors' novel approach of clothing image similarity measurement.

The authors measure the similarity between two clothing images by computing the weighted similarities between their bundled features. Each bundled feature consists of the point features (SIFT) which are further quantified into local visual words in a maximally stable extremal region (MSER). The authors weight the importance of bundled features by the precision of SIFT quantification and local word frequency that reflects the frequency of the common visual words appeared in two bundled features. The bundled features similarity is computed from two aspects: local word frequency; and SIFTs distance matrix that records the distances between every two SIFTs in a bundled feature.

Local word frequencies improves the recognition between two bundled features with the same common visual words but different local word frequency. SIFTs distance matrix has the merits of scale invariance and rotation invariance. Experimental results show that this approach works well in the situations with large clothing deformation, background exchange and part hidden, etc. And the similarity measurement of Weight+Bundled+LWF+SDM is the best.

This paper presents an apparel retrieval mode based on local visual features, and presents a new algorithm for bundled feature matching and apparel similarity measurement.

The assembly simulation in tolerance analysis is one of the most important steps for the tolerance design of mechanical products. However, most assembly simulation methods are based on the rigid body assumption, and those assembly simulation methods considering deformation have a poor efficiency. This paper aims to propose a novel efficient and precise tolerance analysis method based on stable contact to improve the efficiency and reliability of assembly deformation simulation.

The proposed method comprehensively considers the initial rigid assembly state, the assembly deformation and the stability examination of assembly simulation to improve the reliability of tolerance analysis results. The assembly deformation of mating surfaces was first calculated based on the boundary element method with optimal initial assembly state, then the stability of assembly simulation results was assessed by the density-based spatial clustering of applications with noise algorithm to improve the reliability of tolerance analysis. Finally, combining the small displacement torsor theory, the tolerance scheme was statistically analyzed based on sufficient samples.

A case study of a guide rail model demonstrated the efficiency and effectiveness of the proposed method.

The present study only considered the form error when generating the skin model shape, and the waviness and the roughness of the matching surface were not considered.

To the best of the authors’ knowledge, the proposed method is original in the assembly simulation considering stable contact, which can effectively ensure the reliability of the assembly simulation while taking into account the computational efficiency.

The purpose of this study is to solve the issues of time-consuming and complicated computation of traditional measures, as well as the underutilization of two-dimensional (2D) phase-trajectory projection matrix, so a new set of features were proposed based on the projection of attractors trajectory to characterize the friction-induced attractors and to reveal the tribological behavior during the running-in process.

The frictional running-in experiments were conducted by sliding a ball against a static disk, and the friction coefficient was collected to reconstruct the friction-induced attractors. The projection of the attractors in 2D subspace was then mapped and the distribution of phase points was adapted to conduct the feature extraction.

The evolution of the proposed moment measures could be described as “initial rapid decrease/increase- midterm gradual decrease/increase- finally stable,” which could effectively reveal the convergence degree of the friction-induced attractors. Moreover, the measures could also describe the relative position of the attractors in phase–space domain, which reveal the amplitude evolution of signals to some extent.

The proposed measures could reveal the evolution of tribological behaviors during the running-in process and meet the more precise real-time running-in status identification.

This study aims to satisfy the thermal management of gallium nitride (GaN) high-electron mobility transistor (HEMT) devices, microchannel-cooling is designed and optimized in this work.

A numerical simulation is performed to analyze the thermal and flow characteristics of microchannels in combination with computational fluid dynamics (CFD) and multi-objective evolutionary algorithm (MOEA) is used to optimize the microchannels parameters. The design variables include width and number of microchannels, and the optimization objectives are to minimize total thermal resistance and pressure drop under constant volumetric flow rate.

In optimization process, a decrease in pressure drop contributes to increase of thermal resistance leading to high junction temperature and vice versa. And the Pareto-optimal front, which is a trade-off curve between optimization objectives, is obtained by MOEA method. Finally, K-means clustering algorithm is carried out on Pareto-optimal front, and three representative points are proposed to verify the accuracy of the model.

Each design variable on the effect of two objectives and distribution of temperature is researched. The relationship between minimum thermal resistance and pressure drop is provided which can give some fundamental direction for microchannels design in GaN HEMT devices cooling.

Based on goal content theory (GCT), this study examines the associations between different work goal contents (intrinsic and extrinsic goals) and early retirement intentions and reveals the underlying mechanisms of abovementioned relations.

The paper tested the proposed model by using a sample of 265 workers in China using a two-wave survey.

Findings(1) employees' intrinsic and extrinsic goals are both negatively related to early retirement intentions, and the effect of extrinsic goals on early retirement intentions is more significant. (2) Work passion was found to be a strong mediator between work goal content and employees' early retirement intentions. (3) Human resource (HR) practices’ flexibility significantly moderates the relationship between work passion and early retirement intentions.

The contribution of the current study is that this study first takes into account individuals’ psychological and organizational factors, aiming to reveal the differential effect of different work goals on individuals' early retirement intentions as well as the mediating effect of work passion and the moderating effect of HR practices’ flexibility in the abovementioned relations.

The geomagnetic field vector is a function of the satellite’s position. The position and speed of the satellite can be determined by comparing the geomagnetic field vector measured by on board three-axis magnetometer with the standard value of the international geomagnetic field. The geomagnetic model has the disadvantages of uncertainty, low precision and long-term variability. Therefore, accuracy of autonomous navigation using the magnetometer is low. The purpose of this paper is to use the geomagnetic and sunlight information fusion algorithm to improve the orbit accuracy.

In this paper, an autonomous navigation method for low earth orbit satellite is studied by fusing geomagnetic and solar energy information. The algorithm selects the cosine value of the angle between the solar light vector and the geomagnetic vector, and the geomagnetic field intensity as observation. The Adaptive Unscented Kalman Filter (AUKF) filter is used to estimate the speed and position of the satellite, and the simulation research is carried out. This paper also made the same study using the UKF filter for comparison with the AUKF filter.

The algorithm of adding the sun direction vector information improves the positioning accuracy compared with the simple geomagnetic navigation, and the convergence and stability of the filter are better. The navigation error does not accumulate with time and has engineering application value. It also can be seen that AUKF filtering accuracy is better than UKF filtering accuracy.

Geomagnetic navigation is greatly affected by the accuracy of magnetometer. This paper does not consider the spacecraft’s environmental interference with magnetic sensors.

Magnetometers and solar sensors are common sensors for micro-satellites. Near-Earth satellite orbit has abundant geomagnetic field resources. Therefore, the algorithm will have higher engineering significance in the practical application of low orbit micro-satellites orbit determination.

This paper introduces a satellite autonomous navigation algorithm. The AUKF geomagnetic filter algorithm using sunlight information can obviously improve the navigation accuracy and meet the basic requirements of low orbit small satellite orbit determination.

AISI 52100-AISI 1045 specimens were used as the ring-on-disc tribopairs in the experiments to investigate the stability of friction process.

The coefficient of friction (COF) signals were measured throughout the friction process and the recurrence plots (RPs) and recurrence quantification analysis (RQA) are adapted to analyze the stability of the tribosystem.

The results show that the COF time-series acquired from different tests possess the same dynamic evolution laws. The evolution of RPs follows the rules of “disrupted-homogeneous-disrupted,” which corresponds to the “running-in, steady-state and increasing stages” of friction process. Additionally, the evolution laws of RQA measures LAM, Vmax and TT accord with the “bathtub curve.” Therefore, both RPs and RQA measures can inform quantitative interpretations of tribological behaviors and friction process identification.

The both RPs and RQA are capable of characterizing the tribological behaviors and can depict the various stages of friction process.