Search results

The current popular image processing technologies based on convolutional neural network have the characteristics of large computation, high storage cost and low accuracy for tiny defect detection, which is contrary to the high real-time and accuracy, limited computing resources and storage required by industrial applications. Therefore, an improved YOLOv4 named as YOLOv4-Defect is proposed aim to solve the above problems.

On the one hand, this study performs multi-dimensional compression processing on the feature extraction network of YOLOv4 to simplify the model and improve the feature extraction ability of the model through knowledge distillation. On the other hand, a prediction scale with more detailed receptive field is added to optimize the model structure, which can improve the detection performance for tiny defects.

The effectiveness of the method is verified by public data sets NEU-CLS and DAGM 2007, and the steel ingot data set collected in the actual industrial field. The experimental results demonstrated that the proposed YOLOv4-Defect method can greatly improve the recognition efficiency and accuracy and reduce the size and computation consumption of the model.

This paper proposed an improved YOLOv4 named as YOLOv4-Defect for the detection of surface defect, which is conducive to application in various industrial scenarios with limited storage and computing resources, and meets the requirements of high real-time and precision.

Rapid prototyping (RP) technology is widely used in many fields in recent years. Bone tissue engineering (TE) is an interdisciplinary field involving life sciences, engineering and materials science. Hydroxyapatite (HAp) are similar to natural bone and it has been extensively studied due to its excellent biocompatibility and osteoconductivity. This paper aims to review nanoscaled HAp-based scaffolds with high porosity fabricated by various RP methods for bone regeneration.

The review focused on the fabrication methods of HAp composite scaffolds through RP techniques. The paper summarized the evaluation of these scaffolds on the basis of their biocompatibility and biodegradability through in vitro and in vivo tests. Finally, a summary and perspectives on this active area of research are provided.

HAp composite scaffold fabricated by RP methods has been widely used in bone TE and it has been deeply studied by researchers during the past two decades. However, its brittleness and difficulty in processing have largely limited its wide application in TE. Therefore, the formability of HAp combined with biocompatible organic materials and fabrication techniques could be effectively enhanced, and it can be used in bone TE applications finally.

This review paper presented a comprehensive study of the various types of HAp composite scaffold fabricated by RP technologies and introduced their potential application in bone TE, as well as future roadmap and perspective.

In this paper, the authors study the effect of consumers' fairness preferences on dynamic pricing strategies adopted by platforms in a non-cooperative game.

This study applies fair game and repeated game theory.

This study reveals that, in a one-shot game, if consumers have fairness preferences, dynamic prices will slightly decline. In a repeated game, dynamic prices will be reduced even when consumers do not have fairness preferences. When fairness preferences and repeated game are considered simultaneously, dynamic prices are most likely to be set at fair prices. The authors also discuss the effect of platforms' discounting factors, the consumers' income and alternative choices of consumption on the dynamic prices.

The study findings illustrate the importance of incorporating behavioral elements in understanding and designing the dynamic pricing strategies for platforms and the implications on social welfare in general.

The authors developed a theoretical model to incorporate consumers' fairness preference into the decision-making process of platforms when they design the dynamic pricing strategies.

This paper aims to illustrate the tolerance optimization method based on the assembly accuracy constrain, precession constrain and the cost of production of the assembly product.

A tolerance optimization method is an excellent way to perform product assembly performance. The tolerance optimization method is adapted to the process analysis of the hatch and skin of an aircraft. In this paper, the tolerance optimization techniques are applied to the tolerance allocation for step difference analysis (example: step difference between aircraft cabin door and fuselage outer skin). First, a mathematical model is described to understand the relationship between manufacturing cost and tolerance cost. Second, the penalty function method is applied to form a new equation for tolerance optimization. Finally, MATLAB software is used to calculate 170 loops iteration to understand the efficiency of the new equation for tolerance optimization.

The tolerance optimization method is based on the assembly accuracy constrain, machinery constrain and the cost of production of the assembly product. The main finding of this paper is the lowest assembly and lowest production costs that met the product tolerance specification.

This paper illustrated an efficient method of tolerance allocation for products assembly. After 170 loops iterations, it founds that the results very close to the original required tolerance. But it can easily say that the different number of loops iterations may have a different result. But optimization result must be approximate to the original tolerance requirements.

It is evident from Table 4 that the tolerance of the closed loop is 1.3999 after the tolerance distribution is completed, which is less than and very close to the original tolerance of 1.40; the machining precision constraint of the outer skin of the cabin door and the fuselage is satisfied, and the assembly precision constraint of the closed loop is satisfied.

The research may support further research studies to minimize cost tolerance allocation using tolerance cost optimization techniques, which must meet the given constrain accuracy for assembly products.