Search results

Laser-based measurement techniques offer various advantages over conventional measurement techniques, such as no-destructive, no-contact, fast and long measuring distance. In cooperative laser ranging systems, it’s crucial to extract center coordinates of retroreflectors to accomplish automatic measurement. To solve this problem, this paper aims to propose a novel method.

We propose a method using Mask RCNN (Region Convolutional Neural Network), with ResNet101 (Residual Network 101) and FPN (Feature Pyramid Network) as the backbone, to localize retroreflectors, realizing automatic recognition in different backgrounds. Compared with two other deep learning algorithms, experiments show that the recognition rate of Mask RCNN is better especially for small-scale targets. Based on this, an ellipse detection algorithm is introduced to obtain the ellipses of retroreflectors from recognized target areas. The center coordinates of retroreflectors in the camera coordinate system are obtained by using a mathematics method.

To verify the accuracy of this method, an experiment was carried out: the distance between two retroreflectors with a known distance of 1,000.109 mm was measured, with 2.596 mm root-mean-squar error, meeting the requirements of the coarse location of retroreflectors.

The research limitations/implications are as follows: (i) As the data set only has 200 pictures, although we have used some data augmentation methods such as rotating, mirroring and cropping, there is still room for improvement in the generalization ability of detection. (ii) The ellipse detection algorithm needs to work in relatively dark conditions, as the retroreflector is made of stainless steel, which easily reflects light.

The originality/value of the article lies in being able to obtain center coordinates of multiple retroreflectors automatically even in a cluttered background; being able to recognize retroreflectors with different sizes, especially for small targets; meeting the recognition requirement of multiple targets in a large field of view and obtaining 3 D centers of targets by monocular model-based vision.

Part quality inspection is playing a critical role in the metal additive manufacturing (AM) industry. It produces a part quality analysis report which can be adopted to further improve the overall part quality. However, the part quality inspection process puts heavy reliance on the engineer’s background and experience. This manual process suffers from both low efficiency and potential errors and, therefore, cannot meet the requirement of real-time detection. The purpose of this paper is to look into a deep neural network, Convolutional Neural Network (CNN), towards a robust method for online monitoring of AM parts.

The proposed online monitoring method relies on a deep CNN that takes a real metal AM part’s images as inputs and the part quality categories as network outputs. The authors validate the efficacy of the proposed methodology by recognizing the “beautiful-weld” category from material CoCrMo top surface images. The images of “beautiful-weld” parts that show even hatch lines and appropriate overlaps indicate a good quality of an AM part.

The classification accuracy of the developed method using limited information of a small local block of an image is 82 per cent. The classification accuracy using the full image and the ensemble of model outputs is 100 per cent.

A real-world data set of high resolution images of ASTM F75 I CoCrMo-based three-dimensional printed parts (Top surface images with magnification 63×) annotated with categories labels. Development of a CNN-based classification model for the supervised learning task of recognizing a “beautiful-weld” AM parts. The classification accuracy using the full image and the ensemble of model outputs is 100 per cent.

Assembly accuracy is the guarantee of mechanical product performance, and the characterization of the part with geometrical deviations is the basis of assembly accuracy analysis.

The existed small displacement torsors (SDT) model cannot fully describe the part with multiple mating surfaces, which increases the difficulty of accuracy analysis. This paper proposed an integrated characterization method for accuracy analysis. By analyzing the internal coupling relationship of the different geometrical deviations in a single part, the Monomer Model was established.

The effectiveness of the Monomer Model is verified through an analysis of a simulated rotor assembly analysis, and the corresponding accuracy analysis method based on the model reasonably predicts the assembly deviation of the rotor.

The Monomer Model realizes the reverse calculation of assembly deformation for the first time, which can be used to identify the weak links that affect the assembly accuracy, thus support the accuracy improvement in the re-assembly stage.

This study aims to facilitate consistency of information in building information modelling (BIM) and address the current BIM gaps through the perspectives of the productization concept and product structure (PS).

The study follows a conceptual research approach in conjunction with a single case study. First, the previous studies on BIM implementation, productization and PS are reviewed. Further, a case study is used to analyse the current state of productization in the construction sector and develop a functional PS for construction.

A Part-Phase-Elements Matrix is proposed as a construction-specific PS to facilitate consistency in information and to enhance BIM. The proposed matrix provides new avenues to facilitate consistent information exchange through the interconnection between conceptual PS and standard building objects library, and encourage collaborative communication between stakeholders.

This study explores the core of the productization concept and PS as means to facilitate consistency of information and thus address the current gaps in BIM. This as building projects progressively move towards systematic modular and prefabricated construction where the flow of reliable information about product and construction offerings becomes increasingly important.

China is the world's largest consumer of pesticides. To increase the use efficiency and achieve more sustainable and environmentally friendly use of pesticides in China, it is crucial to understand why Chinese farmers use such a large amount of pesticides.

The relationship between farm size and pesticide use was investigated by using national household-level panel data from 1995 to 2016.

Farms that are small and fragmented lead to the use of large amounts of pesticides in China. For a given crop type, three factors contribute to a negative relationship between farm size and pesticide use: the spillover effect from the use of pesticides by other farmers in the same village, the level of mechanization and the management ability of farmers. The first two factors play important roles in the cultivation of grain crops, while the last factor is the main reason why farmers with larger plots of land use fewer pesticides in the cultivation of vegetables. In addition, the effect of agricultural machinery services on reducing the use of pesticides is currently limited, and the service system in China is still insufficient, which has been pointed out that it is also due to the prevalence of small and fragmented farms.

The authors investigate and compare the farm size–pesticide use relationship in both grain and cash crop production. Moreover, the authors systematically explore and explain how farm size is related to a reduction in pesticide use in the cultivation of grain crops and cash crops. These results can help to better understand the role of land scale in pesticide use, lay a foundation for the formulation of policies to reduce pesticide use and provide valuable knowledge about pesticide use for other developing countries around the world.

This paper aims to experimentally investigate the elastic deformation behavior of surface texture in soft contacts under lubricated condition.

Dimples with two typical distribution patterns are fabricated on the contacting surface by Quasi-LIGA technique. In situ observation on the elastic deformation of contacting surface is performed through optical interferometry. Comparisons of the elastic deformation around the dimples in different distribution patterns are conducted.

The results show that the effect of dimple distribution patterns on elastic deformation becomes increasingly serious with the growth of applied load. Dimples in square distribution present a stronger interaction with each other and lead to a more alleviative deformation under heavier load condition. The action range of dimple, especially in square distribution, is seriously compressed by surrounding dimples.

Square distribution is preferentially suggested for surface texture with respect to minimum elastic deformation in soft contacts under elastohydrodynamic lubrication condition.

The implementation of the innovation-driven development strategy is of practical significance for improving the quality and efficiency of economic growth and accelerating the transformation of economic development mode. The purpose of this paper is to study the impact of innovation-driven strategies on marine industry agglomeration and industrial transformation.

In traditional grey correlation analysis, when the positive and negative areas cancel each other out during the integration process, the calculation result of the correlation degree is often inconsistent with the qualitative analysis. For this reason, from the perspective of curve similarity, this paper constructs two response curves through the relative change area of the two curves and the relative area change ratio of similar degree, thus constructing an improved grey relational model.

The authors find that the innovation investment has a better correlation with marine industrial agglomeration. It also found that Guangdong Province has the highest degree of correlation between innovation indicators and marine industrial agglomeration. Much beyond the authors’ expectation, in the areas where marine industrial agglomeration is high, the synergistic effect is not obvious by using the location entropy method.

The improved grey correlation analysis method can effectively overcome the phenomenon that the positive and negative areas cancel each other in the integration process of the original algorithm, and it can also effectively measure the negative correlation between variables. This paper explores the impact of innovation drive on the agglomeration of marine industries, which is of great significance to the sustainable development of marine economy.

This paper aims to investigate the squeeze film lubrication properties of hexagonal patterned surface inspired by the epidermis structure of tree frog’s toe pad and numerically explore the working mechanism of hexagonal micropillar during the acquisition process of high adhesive and friction for wet contacts.

A two-dimensional elastohydrodynamic numerical model is employed for the squeezing contacts. The pressure distribution, load carrying capacity and liquid flow rate of the squeeze film are obtained through a simultaneous solution of the two-dimensional Reynolds equation and elasticity deformation equations.

Higher pressure is found to be longitudinally distributed across individual hexagonal pillar, with pressure peak emerging at the center of hexagonal pillar. Expanding the area density and shrinking the channel depth or initial film thickness will improve the magnitude of squeezing pressure. Relatively lower pressure is generated inside interconnected channels, which reduces the load carrying capacity of the squeeze film. Meanwhile, the introduction of microchannel is revealed to downscale the total mass flow rate of squeezing contacts.

This paper provides a good proof for the working mechanism of surface microstructures during the acquisition process of high adhesive and friction for wet contacts.

The purpose of this paper is to investigate the wear resistance behavior of the striated tool for cross wedge rolling (CWR).

A mechanical-thermal coupled, temperature-dependent FE wear model was developed to explore the wear behaviors for striated CWR tools. To verify the proposed FE model, a newly developed measuring device was also developed to measure wear on the tool ridge. To find the impact order of the parameters of striate unit, orthogonal experiment was carried out.

The experimental and numerical results both indicate that the wear resistance of striated tool is better than that of smooth tool. Minimum tool ridge wear can be achieved by choosing proper tool contact temperature with striated units on crossed ridge. The order of the striation geometrical factors’ impact on ridge wear is striation width > striation interval > striation length.

Because of the specified tool, the research results may lack generalizability. Therefore, researchers are encouraged to test the proposed propositions further.

It is shown that the wear resistance of striated CWR tool is better than that of smooth tool. The information may help CWR manufactures to design and produce tools with less wear.