Papers by Author: Qian Xiang

Paper TitlePage

Authors: Zhi Jun Lv, Qian Xiang, Jian Guo Yang
Abstract: Rough sets theory (RST) is a new data mining method that effectively deals with the problems with inexact, uncertain or vague knowledge in a complex information system. This paper investigates knowledge discovery methods from the textile industrial database, and then presents a RST-based intelligent control model (ICM) for spinning process. In order to analyze the yarn strength when the characteristics of fibers are given, a rule extraction method based on RST is researched. The logical rules extracted from the decision table indicate that the initial strength of fibers is a key factor influencing on the yarn strength. At the same time, the different values combination of the final reduced attributes also obviously influence on the yarn strength in different degree when the certain nominal yarn is being processed. Therefore, RST method can be taken into account for spinners to choose suitable fiber materials in order to ensure the quality and reduce cost.
87
Authors: Zhi Jun Lv, Qian Xiang, Jing Zhu Pang
Abstract: Grinding is widely used as a precision process for machining difficult-to-cut materials. Grinding productivity is still greatly dependent on the experience and skill of human operators. Focusing on the indirect method, an attempt was made to build up an intelligent system to monitor the condition of grinding wheels with force signals and the acoustic emission (AE) signals. An artificial immune algorithm based multi-signals processing method was presented in this paper. The intelligent system is capable of incremental supervised learning of grinding conditions and quickly pattern recognition, and can continually improve the monitoring precision. The experiment indicates that the accuracy of condition identification is about 87%, and able to meet the industrial need on the whole.
2759
Authors: Zhi Jun Lv, Qian Xiang, Jian Guo Yang
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. In fact, the existing process cases which were recorded to ensure the ability to trace production steps can also be used to optimize the process itself. This paper presents a novel process decision model based on CBR and SVM hybird intelligence for optimization of large numbers of spnning parameters. The applied cases are demonstrated that the intelligent model to optimizing the spinning process is promising.
439
Authors: Qian Xiang, Zhi Jun Lv, Jian Guo Yang, Xiang Gang Yin
Abstract: Due to absence of an integral mathematical model, quality control in spinning process has been hard problem for a long time. Rough sets theory (RST) is a methodology that effectively deals with the problems with inexact, uncertain or vague knowledge in a complex information system. Considering a mass of data from spinning process and inspection, as well as the variety of knowledge and experience from domain experts, an RST-based intelligent control model for spinning process is presented in this paper. In order to analyze the yarn strength when the characteristics of fibers are given, a rule extraction method based on RST is researched. The logical rules extracted from the decision table indicate that the initial strength of fibers is a key factor influencing on the yarn strength. At the same time, the different values combination of the final reduced attributes also obviously influence on the yarn strength in different degree when the certain nominal yarn is being processed. Therefore, RST method can be taken into account for spinners to choose suitable fiber materials in order to ensure the quality and reduce cost.
1021
Authors: Jian Guo Yang, Lan Xu, Zhi Jun Lu, Qian Xiang, Bin Liu, Steven Y. Liang
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.
706
Authors: Jian Guo Yang, Lan Xu, Zhi Jun Lu, Qian Xiang, Bin Liu
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.
377
Showing 1 to 6 of 6 Paper Titles