Papers by Author: Jian Guo Yang

Abstract: Quality prediction is an important means of the quality management in modern spinning production. This paper proposed a yarn quality prediction model based on Genetic Algorithm and back propagation neural network to predict the yarn quality and optimize the process parameters. The main identification model parameters were optimized by using genetic algorithm, and the prediction performance of the model has been compared against that of the BP neural network model. The effectiveness and availability of the proposed model are verified with the use of actual production data.

Abstract: This paper deals with an intelligent multi-sensor monitoring system, which focus on the characteristic of transient occurrence in high speed grinding and its application to the machining of brittle and hard materials. Different sensors are used to collect workpiece vibration, acoustic emission, force and displacement signals, which are used to define the stability of grinding process and monitoring the fault in high speed machining. Although there is a lot of methods have been reported in recent literature for monitoring grinding process, they have not a systematic method which can totally reflect the characteristic of high speed grinding. On the other hand，no single sensor or feature has been shown to be successfully and precisely all grinding faults. This paper combined different feature selection including time-frequency domain or wavelet methods and sensor fusion based on clustering method to deal with the stability condition test in high-speed grinding. The validity of the proposed method and the excellent detection accuracy is demonstrated through tests with SiC machining in high-speed grinding.

Abstract: Demands of automatic recognition of abnormal patterns in control charts have been increasing nowadays in manufacturing process. Control chart pattern recognition is an important statistical process control tool used to determine whether a process is run in its intended range or not and eliminate the potential attribution factors as far as possible according to the abnormal condition shown in the control chart. This paper uses the time domain features as input vector and genetic algorithm to obtain the optimal parameters of SVM in a self-adapted manner. Design anomaly detection model for dynamic process is made to realize control chart pattern recognition under the complex condition. The experimental results show that the proposed approach method has higher detection accuracy and stronger generalization ability than other methods, so it is more suitable for quality control in production field.

Abstract: Before the working speed of high-speed spindle system reaches the critical speed, violent vibration which directly affects the quality of the work piece has been already discovered. To precisely study the speed at which violent vibration happens and the modes of vibration, this paper provided an order vibration approach through studying the model analysis and order of spindle system. The nature frequencies of model analysis were verified and the order of spindle system was confirmed by speed ascend experiment. The result shows that the violent vibration is caused by the manufacturing error of outer ring race of bearing and the mode of vibration mainly located on the grinding wheel which greatly affects the accuracy of spindle system. It is useful for optimizing the structure and operation procedure of high-speed spindle system.

Abstract: In the aerospace and auto industries, the residual tensile stresses will cause the structures broke and damaged. Hence, different methods were considered to optimize the machining processes. In this article, a residual stresses calculation model using AdvantEdge 2D turning was integrated with 2D milling physical model in order to analyze high-speed milling thin-walled workpiece. Through optimizing the processing parameters (improving the cutting speed and decreasing the cutting depth) during high-speed milling, not only we can get a high removal rate and receive a distribution of equably surface residual stresses, but also a slowing down trend of in-depth residual stress can be obtained. In addition, we evaluate this method using a typical part at the sensitive area, and the machining quality can be improved obviously.

Abstract: Friction stir welding (FSW) technology requires a meticulous understanding of the process and consequent mechanical properties of the welds in order to be used in the production of high performance components. This paper deals with an experimental campaign aimed at the evaluation of the mechanical properties of AA6061-T6 friction stir welded joints. The joints are obtained by varying the welding parameters, namely, tool rotating speed and feed rate. The non-threaded tool is made of hot work die steel H13. The quality of the joints is evaluated in terms of both hardness and tensile strength. Moreover, for going a step further to study and control welding heat input in FSW process, a piezoelectric load cell is installed between the fixture table and the machine tool workbench in order to measure the welding forces in different directions.

Abstract: The clamping force and clamping sequence in the process of thin-walled parts is an important factor affecting the quality of the workpiece. This article focused on solving the parts clamping force of the locating point and clamping sequence, according to the process of clamping force on the workpiece, by the means of screw theory and the minimum modulus principle, taking the contact friction into account, the article established a mathematical model. Furthermore, a new approach to optimize clamping and clamping sequence has been put forward combining Matlab optimization toolbox, which provided guidance basic theory for the preload design of the clamping process and flexible clamping. Finally a detailed discussion was conducted to the calculation of clamping force and clamping sequence by using some practical examples.

Abstract: High speed motorized spindle plays an important role in high speed grinding. However, for high-speed machining, the spindle system usually generates excessive vibration due to the high speed and large mass. The vibration transfers to the bed of grinding machine and affects the precision of machining. To analyze and control the vibration generated by the spindle system, this paper develops a dynamic model for the high-speed spindle system, and further analyzes the eccentricity and the mass of the spindle system which affects the amplitude of the vibration of the bed by producing the impulse. Based on the result of analysis, the vibration is finally controlled by modifying the structure of the shaft. After optimization, the amplitude of the vibration of the bed of reduces significantly to 0.046um, which was 0.056um before. In addition the eccentricity of the spindle is decrease by 0.1um.

Abstract: The yarn production is a complex industrial process, and the relation between the spinning variables and the yarn properties has not been established conclusively so far. The SVM regression algorithms are briefly introduced in this study, and then SVM models for predicting yarn properties have been presented. Model selection which amounts to search in hyper-parameter space is performed for study of suitable parameters with Genetic Algorithms. The yarn experimental results indicate that GA- SVM models are capable of remaining the stability of predictive accuracy, and more suitable for noisy and dynamic industrial process.

Abstract: The high speed machine tool spindle plays an important role in machining operations. Based on modal test techniques and rotating machinery signature techniques, the research focused on the test and analysis of the dynamic characteristics of spindle system of high speed grinder. First, an experimental modal analysis (EMA) is performed in the spindle system; then, the frequency response characteristics and the FRFs of the system should be considered. Furthermore, rotating machinery signature techniques are used to analyze the dynamic behavior of the spindle system in process due to the limitation of modal test techniques, and the theoretical proof is given to explain the spindle system order. The results show that it requires the machine tool to avoid the use of vibration-sensitive speed in the production process and the machine production process, especially bearing manufacturing to improve its accuracy.