Search results

An effective machine vision-based method for micro-crack detection of solar cell can economically improve the qualified rate of solar cells. However, how to extract features which have strong generalization and data representation ability at the same time is still an open problem for machine vision-based methods.

A micro-crack detection method based on adaptive deep features and visual saliency is proposed in this paper. The proposed method can adaptively extract deep features from the input image without any supervised training. Furthermore, considering the fact that micro-cracks can obviously attract visual attention when people look at the solar cell’s surface, the visual saliency is also introduced for the micro-crack detection.

Comprehensive evaluations are implemented on two existing data sets, where subjective experimental results show that most of the micro-cracks can be detected, and the objective experimental results show that the method proposed in this study has better performance in detecting precision.

First, an adaptive deep features extraction scheme without any supervised training is proposed for micro-crack detection. Second, the visual saliency is introduced for micro-crack detection.

This paper aims to improve the generalization capability of feature extraction scheme by introducing a micro-cracks detection method based on self-learning features. Micro-cracks detection of multicrystalline solar cell surface based on machine vision is fast, economical, intelligent and easier for on-line detection. However, the generalization capability of feature extraction scheme adopted by existed methods is limited, which has become an obstacle for further improving the detection accuracy.

A novel micro-cracks detection method based on self-learning features and low-rank matrix recovery is proposed in this paper. First, the input image is preprocessed to suppress the noises and remove the busbars and fingers. Second, a self-learning feature extraction scheme in which the feature extraction templates are changed along with the input image is introduced. Third, the low-rank matrix recovery is applied to the decomposition of self-learning feature matrix for obtaining the preliminary detection result. Fourth, the preliminary detection result is optimized by incorporating the superpixel segmentation. Finally, the optimized result is further fine-tuned by morphological postprocessing.

Comprehensive evaluations are implemented on a data set which includes 120 testing images and corresponding human-annotated ground truth. Specifically, subjective evaluations show that the shape of detected micro-cracks is similar to the ground truth, and objective evaluations demonstrate that the proposed method has a high detection accuracy.

First, a self-learning feature extraction method which has good generalization capability is proposed. Second, the low-rank matrix recovery is combined with superpixel segmentation for locating the defective regions.

As a high-performance engineering plastic, polyimide (PI) is widely used in the aerospace, electronics and automotive industries. This paper aims to review the latest progress in the tribological properties of PI-based composites, especially the effects of nanofiller selection, composite structure design and material modification on the tribological and mechanical properties of PI-matrix composites.

The preparation technology of PI and its composites is introduced and the effects of carbon nanotubes (CNTs), carbon fibers (CFs), graphene and its derivatives on the mechanical and tribological properties of PI-based composites are discussed. The effects of different nanofillers on tensile strength, tensile modulus, coefficient of friction and wear rate of PI-based composites are compared.

CNTs can serve as the strengthening and lubricating phase of PI, whereas CFs can significantly enhance the mechanical properties of the matrix. Two-dimensional graphene and its derivatives have a high modulus of elasticity and self-lubricating properties, making them ideal nanofillers to improve the lubrication performance of PI. In addition, copolymerization can improve the fracture toughness and impact resistance of PI, thereby enhancing its mechanical properties.

The mechanical and tribological properties of PI matrix composites vary depending on the nanofiller. Compared with nanofibers and nanoparticles, layered reinforcements can better improve the friction properties of PI composites. The synergistic effect of different composite fillers will become an important research system in the field of tribology in the future.

The purpose of this study is to investigate the understanding and application of crime of sabotaging production and operation in internet era, and, at the same time, discuss the basic position for criminal law interpretation in cyberspace.

Doctrinal analysis and case study.

Along with the advent of the internet era, how to apply the traditional crime of sabotaging production and operation in virtual space has attracted people’s attention. The controversy caused by the conviction of malicious application of fake transactions is a typical example. The legal interest protected here includes not only the property value of the means of production itself, but also the expectation interest that can be obtained by normal production and operation activities. There is no reliable basis to believe that overlap of articles between special provision and general laws occurs in crime of sabotaging production and operation and crime of intentional damage of property. The production and operation activities carried out online can also be covered by crime of sabotaging production and operation, without doubt. Ejusdem Generis Rule should be fully respected, but crime of sabotaging production and operation has a dual structure of means behavior and purpose behavior, where the purpose behavior, sabotaging production and operation, is the key to the conviction. However, it is not necessarily premised on physical damage and violent characteristics. The understanding and application of traditional crimes should keep pace with the times in the internet era, and we should not stick to a completely rigid subjective interpretation.

This study demonstrates the possible application of crime of sabotaging production and operation in cyberspace, and clarifies many misunderstandings about this crime.

This paper aims to investigate the friction noise properties of M50 matrix curved microporous channel composites filled with solid lubricant Sn-Ag-Cu (MS).

Pure M50 (MA) and MS are prepared by selective laser melting and vacuum-pressure infiltration technology. The tribological and friction noise properties of MA and MS are tested through dry sliding friction and then the influential mechanism of surface wear sate on friction noise is investigated by analyzing the variation law of noise signals and the worn surface characteristics of MS.

Experimental results show that the friction noise sound pressure level of MS is only 75.6 dB, and it mainly consists of low-frequency noise. The Sn-Ag-Cu improves the surface wear state, which reduces self-excited vibration of the interface caused by fluctuation of friction force, leading to the decrease of friction noise.

This investigation is meaningful to improve the tribological property and suppress the friction noise of M50 bearing steel.