Papers by Author: Yong Chen

Abstract: The original equipment manufacturing mode of the multi-species, multi-process and multi-unit is the main mode in Zhejiang manufacturing industry, the workshop layout affect directly the production efficiency and cost. The paper analyzed the impact factors of discrete operations workshop layout, established the Multi-Agent mathematical model of discrete operations workshop layout by using Multi-Agent theory, put forward the objective function of the workshop layout, and carried out empirical study by typical enterprises. By analyzing raw data of ZJ manufacturing enterprise, brought forward two layout programs based on mathematical model of Multi-Agent, evaluated the benefits and chose the better one of the two programs according to the objective function. The results after the implementation showed that the logistics measuring pitch of the program after selection is small, and the workshop area utilization is higher, and the equipment cost is reasonable. The model and optimization technology of discrete operations workshop layout based on Multi-Agent theory has important practical significance and good feasibility.

Abstract: A simulation model of dynamic & flexible scheduling about the large-sized components producing workshop was built by using the cellular automata according to both sides’ characteristics. The scheduling system can be divided into 4 parts: work station, buffer, work piece, and scheduling rules. Work station and buffer were viewed as fixed grid nodes, work piece as moving particles, scheduling rules as the local self-evolution rules which include station choosing rule, work piece sequencing rule and task activating rule. Model simulate the job scheduling of a certain generator components producing factory workshop.

Abstract: This paper studies mainly apples non-destructive selection technology, and presents the principle and implementation of non-destructive selection system for apple quality based on the theory of the fuzzy and neural network. Firstly, we can differentiate the kinds of apples by neural network theory. Then, the apple’s quality greatly depends on its size, shape, and color, which are considered as three input parameters in selection system. The pick-up of three character parameters is handled by computer image processing. Only one output parameter is apple rating, which is fall into three grades: A, B and C. Regarding three character parameters as input, we obtain the apple grade based on fuzzy arithmetic. Finally, we set forth the archetypal non-destructive selection system, which includes robot, AGV, conveyor, sensors and etc. Results of experiments show that this method can distinguish the apple’s quality as well as we set before the experiments, and the non-destructive system is feasible.

Abstract: The tool wear detection system based on the image processing and computer vision has better study value and foreground. The paper brings forward the detection method of the tool wear condition, which solves the two main problems. Firstly, gets the high quality images by fuzzy restoration arithmetic. Because the cutting tool is always at the movement state during the cutting, the real-time collected sequence images by CCD sensor are blurred with noise. Then, obtains the character parameter uniformity Q2 by calculating gray co-occurrence matrix, which can distinguish the cutting tool is weared or not weared. The experimental results indicate that detection of the tool wear condition by computer image processing reach our aim.