Research On Intelligent Integration Optimization Technology For High-speed Multi-station Forging Process

The high-speed multi-station forging process is a kind of advanced near net-shape forgingprocess. Due to the advantages of technology and economic benefits, it is widely applied inmanufacturing industry. Because it owns a series of forming stations which have closerelationships, the requirement of process design is very high. Improper design of die shapes ofpreform stations often results in too high forming load, unreasonable distribution of load andforming defects, such as folding and underfill. For a long time, in order to obtain the properdesign, designers often have to test or simulate the process design, and then optimize andredesign by experience iteratively. The trial-and-error optimization method depends on thedesign’s subjective experience and intuitive determination. It is random and inefficient, so it isdifficult to get the optimal design. With the rapid development of society and the increasingcompetition of enterprises, it is required to achieve the goals of process design for highefficiency, high quality and low cost. Thus, the application of advanced theory and method isdesired in the process of optimization to free the designers from the heavy work oftrial-and-error process. As a result, the intelligent technology, the numerical simulationtechnology and the optimization technology are necessary to be applied in the optimization formulti-station forging. In cooperation with HATEBUR, the following research results areobtained in the thesis.A combined optimization strategy based on surrogate model is proposed for theoptimization of high-speed multi-station forging process, which has the characteristics of theclose relationship between forming stations, lots of optimization goals and constraints, noexplicit expression between response and variables, long simulation time of the whole processand the complex parts that can not be simplified into2D. The combined optimization strategyapplies the techniques of orthogonal experiment design and analysis of variance (ANOVA) toevaluate the initial variables at first. According to the significance, the unimportant variables areejected to reduce scale of the optimization problem. After that, the latin hypercube sampling(LHS) method is applied to obtain the samples and the surrogate models are constructed toapproximate the relationships between variables and responds (objective functions andconstraints). Based on these surrogate models, an evaluation function is constructed by penaltymethod. In this way, the complex constrained nonlinear optimization problem can be changedinto a single-objective optimization problem of the evaluation function. Finally, the globaloptimization algorithm is applied to search the optimal solution. In the calculation process, theestablished surrogate models are used to predict the response value quickly instead of the numerical simulation. Therefore, it can reduce the optimization time significantly.Different DOE methods and surrogate modeling methods for approximate models arestudied and compared. For the optimization of high-speed multi-station forging process, thecombination of LHS and Kriging is proposed for the case of numerical response value, and BPnetwork is used for the case of linguistic response value. Two DOE methods, which includeorthogonal experimental design and LHS, together with four modeling methods, which includeleast square (LS) response surface, moving least square (MLS) response surface, BP neuralnetwork and Kriging model, are applied to establish the approximate relationship modelsbetween variables and response values of an actual case. And the prediction accuracies of thedifferent models are compared.In order to automatically obtain the response values corresponding to the modification ofdesign, the CAD/CAE intelligent integration technique is proposed in this thesis. It provides anintelligent integration platform for optimization to reduce the complex interactive operation. Itcontains the processes of the automatic modification of tools’ geometry models according tovariables, the intelligent modeling of CAE analysis model and the automatic acquisition andfeedback of the CAE simulation result. The knowledge integration method based on template ofparameterized geometry model and optimization case model is proposed. Through theoptimization case model, variables are corresponding to the parameters of tools’ geometrymodels in one or different forming stations automatically, and the highly integration ofoptimization information and geometry information is realized. Based on the parameterizedgeometry template of cavity, the automatic acquisition technique is applied to obtain the tools’geometry models according to the values of variables, which ensure the correct constraints andassembly relationships between tools. The knowledge based CAE intelligent modeling techniqueis proposed. It achieves the intelligent establishment and automatic modification of CAEanalysis model, so that the simulation of the forging process is carried out by sequence ofstations automatically. The knowledge based intelligent post simulation feedback technology isproposed. Based on knowledge acquisition and intelligent model reconstruction, the usefulinformation is analyzed and transformed from the CAE simulation result. Therefore, theautomatic mapping process from simulation result to response values (objective functions andconstraints) is implemented. Further more, the intelligent integration and automatic process,feedback of response values according to the modification of variables, is implemented.Based on the studies of surrogate model based combined optimization strategy andCAD/CAE intelligent integration technique, an intelligent optimization system for high-speedmulti-station forging process is developed on the platform of UG NX and DEFORM by usingthe software of Visual C++.net, MATLAB and EXCEL. The surrogate model based optimizationmethod and related knowledge is integrated in the intelligent optimization system, which guidesdesigners to complete the optimization task of high-speed multi-forging process. Meanwhile, theintelligent system provides effective intelligent support in the process of optimization. Theoptimization case study of combring produced by high-speed multi-station forging hasdemonstrated the reliability and practicality of the intelligent optimization system. Based on the intelligent optimization system, the intelligent integration optimizationtechnology is applied to optimize the2D hot forging cases, which include combring and gearblank, and3D cold forging case of gear. After optimization, the forging process is improvedsignificantly. As compared to the initial design, the maximum forming load is decreased, and theforming quality is improved without defect. The effectivity and rationality of the intelligentintegration optimization technology are proved.