Wang Zhigang
Email Address
mpewz@nus.edu.sg
Organizational Units
14 results
Publication Search Results
Now showing 1 - 10 of 14
Publication Multi-objective optimization of high-speed milling with parallel genetic simulated annealing(2006-11) Wang, Z.G.; Wong, Y.S.; Rahman, M.; Sun, J.; MECHANICAL ENGINEERINGIn this paper, the optimization of multi-pass milling has been investigated in terms of two objectives: machining time and production cost. An advanced search algorithm-parallel genetic simulated annealing (PGSA)-was used to obtain the optimal cutting parameters. In the implementation of PGSA, the fitness assignment is based on the concept of a non-dominated sorting genetic algorithm (NSGA). An application example is given using PGSA, which has been used to find the optimal solutions under four different axial depths of cut on a 37 SUN workstation network simultaneously. In a single run, PGSA can find a Pareto-optimal front which is composed of many Pareto-optimal solutions. A weighted average strategy is then used to find the optimal cutting parameters along the Pareto-optimal front. Finally, based on the concept of dynamic programming, the optimal cutting strategy has been obtained. © Springer-Verlag London Limited 2006.Publication Effects of coolant supply methods and cutting conditions on tool life in end milling titanium alloy(2006-09-01) Sun, J.; Wong, Y.S.; Rahman, M.; Wang, Z.G.; Neo, K.S.; Tan, C.H.; Onozuka, H.; MECHANICAL ENGINEERINGTitanium machining poses a great challenge to cutting tools due to its severe negative influence on tool life primarily due to high temperature generated and strong adhesion in the cutting area. Thus, various coolant supply methods are widely used to improve the machining process. On account of this, tool life and cutting force are investigated based on dry cutting, flood cooling, and minimum quantity lubrication (MQL) techniques. The experimental results show that MQL machining can remarkably and reliably improve tool life, and reduce cutting force due to the better lubrication and cooling effect.Publication Robust Vehicle Re-identification via Rigid Structure Prior(IEEE COMPUTER SOC, 2021) Jiang, Minyue; Zhang, Xuanmeng; Yu, Yue; Bai, Zechen; Zheng, Zhedong; Wang, Zhigang; Wang, Jian; Tan, Xiao; Sun, Hao; Ding, Errui; Yang, Yi; Dr Zhedong Zheng; DEPARTMENT OF COMPUTER SCIENCE; ELECTRICAL AND COMPUTER ENGINEERING; MECHANICAL ENGINEERINGVehicle re-identification (re-id) is one of the most important components in the current intelligence transport system, benefiting both the smart traffic management and the optimal path planning. In this paper, we focus on developing a robust part-aware structure-based vehicle re-id system against the massive appearance changes due to the pose and illumination variants. Specifically, we apply the strong convolutional neural networks to extract the visual representation, which is based on the detected vehicle images. Taking one step further, we deploy a part detector to recognize different vehicle parts, such as front, back, left, and right, which explicitly introduce the prior knowledge on the structure of the rigid objective, i.e., vehicle. With the geometry information, we further harness different part feature extractors to filter wrong matches. By using this simple but effective strategy, we remove the hard negative candidates while maintaining high recall accuracy, combing general global-level coarse-grained re-id feature models with part-level fine-grained features. We achieved 71.51% mAP in the vehicle re-id track of the AI City Challenge 2021, which verified the effectiveness and scalability of the proposed structure-based method. The code will be available at https://github.com/XuanmengZhang/AICITY2021-Track2.Publication Tool wear characteristics of binderless CBN tools used in high-speed milling of titanium alloys(2005-02) Wang, Z.G.; Rahman, M.; Wong, Y.S.; MECHANICAL ENGINEERINGTitanium alloys are difficult-to-cut materials, and the performance of conventional tools is poor when used to machine them. In this paper, a new tool material, which is binderless cubic boron nitride (BCBN), is used for high-speed milling of a widely used titanium alloy Ti-6Al-4V. The performance and the wear mechanism of the tool have been investigated when slot milling this alloy. This type of tool manifests longer tool life at high cutting speeds. Analyses based on the SEM and EDX suggest that adhesion of workpiece, attrition and diffusion-dissolution are the main wear mechanisms of the BCBN tool when used in high-speed milling of Ti-6Al-4V. © 2004 Elsevier B.V. All rights reserved.Publication A review on high-speed machining of titanium alloys(2006-09-15) Rahman, M.; Wang, Z.-G.; Wong, Y.-S.; MECHANICAL ENGINEERINGTitanium alloys have been widely used in the aerospace, biomedical and automotive industries because of their good strength-to-weight ratio and superior corrosion resistance. However, it is very difficult to machine them due to their poor machinability. When machining titanium alloys with conventional tools, the tool wear rate progresses rapidly, and it is generally difficult to achieve a cutting speed of over 60m/min. Other types of tool materials, including ceramic, diamond, and cubic boron nitride (CBN), are highly reactive with titanium alloys at higher temperature. However, binder-less CBN (BCBN) tools, which do not have any binder, sintering agent or catalyst, have a remarkably longer tool life than conventional CBN inserts even at high cutting speeds. In order to get deeper understanding of high speed machining (HSM) of titanium alloys, the generation of mathematical models is essential. The models are also needed to predict the machining parameters for HSM. This paper aims to give an overview of recent developments in machining and HSM of titanium alloys, geometrical modeling of HSM, and cutting force models for HSM of titanium alloys. Copyright © 2006 by The Japan Society of Mechanical Engineers.Publication Optimisation of multi-pass milling using genetic algorithm and genetic simulated annealing(2004-11) Wang, Z.G.; Wong, Y.S.; Rahman, M.; MECHANICAL ENGINEERINGThe selection of optimal machining parameters plays an important part in computer-aided manufacturing. The optimisation of machining parameters is still the subject of many studies. Genetic algorithm (GA) and simulated annealing (SA) have been applied to many difficult combinatorial optimisation problems with certain strengths and weaknesses. In this paper, genetic simulated annealing (GSA), which is a hybrid of GA and SA, is used to determine optimal machining parameters for milling operations. For comparison, basic GA is also chosen as another optimisation method. An application example that has previously been solved using geometric programming (GP) method is presented. The results indicate that GSA is more efficient than GA and GP in the application of optimisation.Publication Effects of cooling supply strategies and cutting conditions on tool life in end milling titanium alloy(2005) Rahman, M.; Sun, J.; Wong, Y.S.; Wang, Z.G.; Neo, K.S.; Tan, C.H.; MECHANICAL ENGINEERINGTitanium machining poses a great challenge to cutting tools, and yields serious negative influence on tool life. Thus, cooling supply strategies are widely used in its machining process. On account of this, the tool wear performance from dry cutting, flood cooling and minimum quantity lubrication (MQL) techniques is investigated. This study focuses on cutting tool life under the varied cutting conditions and cooling supply strategies so as to establish effective titanium cutting. Experimental results proved that compared with dry cutting and flood cooling. MQL aided machining can remarkably and reliably improve tool life in titanium machining.Publication Effective training data selection in tool condition monitoring system(2006-02) Sun, J.; Hong, G.S.; Wong, Y.S.; Rahman, M.; Wang, Z.G.; MECHANICAL ENGINEERINGWhen neural networks (NNs) are used to identify tool conditions, the richness and size of training data are crucial. The training data set not only has to cover a wide range of cutting conditions, but also to capture the characteristics of the tool wear process. This data set imposes significant computing burdens, results in a complex identification model, and hampers the feasible application of NNs. In this paper, a training data selection method is proposed, and a systematic procedure is provided to perform this data selection. With this method, the generalization error surface is divided into three regions, and proper sampling factors are chosen for each region to prune the data points from the original training set. The quality of the training set is estimated by performance evaluation through decision making. In this work, SVM is used in the decision making method, and the generalization error is used as the performance evaluation criterion. The tradeoff between the generalization performance and the size of the training set is key to this selection. Experimental results have demonstrated that this selection strategy provides an effective and efficient training set, and the developed model based on this set is fast and reliable for tool condition identification. © 2005 Elsevier Ltd. All rights reserved.Publication Multi-niche crowding in the development of parallel simulated annealing(2005) Wang, Z.-G.; Rahman, M.; Wong, Y.-S.; MECHANICAL ENGINEERINGIn this paper, a new hybrid of genetic algorithm (GA) and simulated annealing (SA), referred to as GSA, is presented. In this algorithm, SA is incorporated into GA to escape from the local optima. Then, the idea of hierarchical parallel G A is borrowed to parallelize GSA for the optimization of multimodal functions. In addition, multi-niche crowding is used to maintain the diversity in the population of parallel GSA. The performance of the proposed algorithms is evaluated against a standard set of multimodal benchmark functions. Multi-niche crowding PGSA and normal PGSA show some remarkable improvement in comparison with the conventional parallel GA and the breeder genetic algorithm.Publication An overview of high-speed machining of titanium alloys(2005) Rahman, M.; Wang, Z.-G.; Wong, Y.-S.; MECHANICAL ENGINEERINGTitanium alloys have been widely used in the aerospace, biomedical and automotive industries because of their good strength-to-weight ratio and superior corrosion resistance. However, it is very difficult to machine them due to their poor machinability, which has led many large companies to invest much in developing techniques to minimize machining cost. During machining of titanium alloys, their poor thermal conductivity results in the higher temperature closer to the cutting edge, and there exists strong affinity between the tool and workpiece material. When machining titanium alloys with the conventional tools, the wear rate progresses rapidly, and the cutting speed is generally difficult to be over 60m/min. Other types of tool materials, including ceramic, diamond, and cubic boron nitride (CBN), are highly reactive with titanium alloys at higher temperature, and consequently they are not effective to be used in HSM of titanium alloys. The binder-less CBN (BCBN) tools, which neither have any binder nor a sintering agent or a catalyst, have a remarkably longer tool life than conventional CBN inserts under all cutting conditions (up to 400m/min). The BCBN appears to become a new cutting tool material for HSM of titanium alloys both economically and functionally. In order to get deeper understanding of HSM of titanium alloys, the generation of mathematical models is essential. Therefore, analytical models are needed to be established to predict the machining parameters for HSM of titanium alloys. This paper aims to give an overview of recent developments in machining and HSM of titanium alloys, geometrical modeling of HSM and cutting force models for HSM of titanium alloys.