摘 要螺旋叶片是螺旋输送设备上的重要零部件，它的制造历史悠久。在生产螺

摘 要<br>螺旋叶片是螺旋输送设备上的重要零部件，它的制造历史悠久。在生产螺旋叶片的各种工艺中，目前最先进的是锥辊辗轧成形螺旋叶片。但是，这种工艺也有一个弱点，那就是设备的工艺轧制参数调整相当困难仍然停留在经验调节上。目前采用这种螺旋叶片制造工艺的各国均采用“经验调节试轧法”来生产螺旋叶片，这种调整方法效率低，容易造成大量浪费。因此，本文在螺旋叶片锥辊辗轧理论的基础上，运用遗传基因法（GA）来优化辗轧工艺参数，克服了“经验调节试轧法”的弱点。<br>本文在介绍了螺旋叶片的国内外研究现状和目前主要的螺旋叶片成形工艺形式（图1），指出了螺旋叶片参数调整优化研究的重要意义基础上，首先介绍了螺旋叶片锥辊异面辗轧成型的工艺的分析。其次介绍了遗传基因的基本概论，确定了遗传基因优化的运行参数和优化中的约束问题的处理，讨论了惩罚函数法在求解非线性方程中的应用。然后，把遗传基因应用于辗轧工艺参数的优化，结合内点惩罚函数法处理约束，建立了优化的数学模型，目标函数和适应度函数，确定了具体实施过程，给出了实施优化流程，最后分别给出了标准遗传基因优化和遗传基因结合内点惩罚优化过程中各个工艺参数和目标函数的变化曲线，得到了最佳工艺参数，并通过实验，把轧出的叶片与标准叶片做比较，以验证遗传基因对辗轧参数调整优化的效果，进一步确定优化的可行性和可适用性。<br>本文还介绍了螺旋叶片成形模具的研究。介绍了模具成形的设计理论，模具成形的两种方法和模具的基本结构分析。进一步分析了模具成形主要的工艺参数。<br>研究结果表明：用标准遗传基因法优化工艺参数在120代左右时开始收敛，制出的螺旋叶片跟目标螺旋叶片在几何尺寸误差相对较大，还需要进一步经验调节才达到要求，而用遗传基因法结合惩罚函数的优化在80～90代就已经开始收敛，试轧出来的产品则完全符合产品的质量要求，这就克服了“经验调节试轧法”的弱点，达到了研究目的。<br>关键词: 螺旋叶片 辗轧成形 遗传基因法 参数优化 模具成形

摘 要<br>螺旋叶片是螺旋输送设备上的重要零部件，它的制造历史悠久。 在生产螺旋叶片的各种工艺中，目前最先进的是锥辊辗轧成形螺旋叶片。 但是，这种工艺也有一个弱点，那就是设备的工艺轧制参数调整相当困难仍然停留在经验调节上。 目前采用这种螺旋叶片制造工艺的各国均采用“经验调节试轧法”来生产螺旋叶片，这种调整方法效率低，容易造成大量浪费。 因此，本文在螺旋叶片锥辊辗轧理论的基础上，运用遗传基因法（GA）来优化辗轧工艺参数，克服了“经验调节试轧法”的弱点。<br>本文在介绍了螺旋叶片的国内外研究现状和目前主要的螺旋叶片成形工艺形式（图1），指出了螺旋叶片参数调整优化研究的重要意义基础上，首先介绍了螺旋叶片锥辊异面辗轧成型的工艺的分析。 其次介绍了遗传基因的基本概论，确定了遗传基因优化的运行参数和优化中的约束问题的处理，讨论了惩罚函数法在求解非线性方程中的应用。 然后，把遗传基因应用于辗轧工艺参数的优化，结合内点惩罚函数法处理约束，建立了优化的数学模型，目标函数和适应度函数，确定了具体实施过程，给出了实施优化流程，最后分别给出了标准遗传基因优化和遗传基因结合内点惩罚优化过程中各个工艺参数和目标函数的变化曲线，得到了最佳工艺参数，并通过实验，把轧出的叶片与标准叶片做比较， 以验证遗传基因对辗轧参数调整优化的效果，进一步确定优化的可行性和可适用性。<br>本文还介绍了螺旋叶片成形模具的研究。 介绍了模具成形的设计理论，模具成形的两种方法和模具的基本结构分析。 进一步分析了模具成形主要的工艺参数。<br>研究结果表明：用标准遗传基因法优化工艺参数在120代左右时开始收敛，制出的螺旋叶片跟目标螺旋叶片在几何尺寸误差相对较大，还需要进一步经验调节才达到要求，而用遗传基因法结合惩罚函数的优化在80～90代就已经开始收敛，试轧出来的产品则完全符合产品的质量要求，这就克服了“经验调节试轧法”的弱点，达到了研究目的。<br>关键词: 螺旋叶片 辗轧成形 遗传基因法 参数优化 模具成形

Abstract<br>Spiral blade is an important part of screw conveying equipment, and its manufacturing history is long. Among the various processes for producing spiral blades, the most advanced one is cone roll rolling. However, this process also has a weakness, that is, it is very difficult to adjust the rolling parameters of the equipment, which still stays on the experience adjustment. At present, the experience adjustment trial rolling method is adopted in the manufacturing process of spiral blade in many countries. This adjustment method is inefficient and easy to cause a lot of waste. Therefore, based on the theory of spiral blade cone roll rolling, the genetic algorithm (GA) is used to optimize the rolling process parameters, which overcomes the weakness of "empirical adjustment trial rolling method".<br>This paper introduces the research status of spiral blade at home and abroad and the main forming process forms of spiral blade at present (Fig. 1), and points out the important significance of research on parameter adjustment and optimization of spiral blade. Firstly, it introduces the analysis of different surface rolling process of spiral blade cone roll. Secondly, it introduces the basic introduction of genetic gene, determines the operation parameters of genetic optimization and the treatment of constraint problems in optimization, and discusses the application of penalty function method in solving nonlinear equations. Then, the genetic gene is applied to the optimization of rolling process parameters, and the mathematical model, objective function and fitness function of the optimization are established, the specific implementation process is determined, and the implementation process is given. Finally, the process parameters and objectives in the process of standard genetic gene optimization and genetic gene combination interior point penalty optimization are given respectively The best process parameters were obtained by the change curve of the standard function. Through the experiment, the rolled blade was compared with the standard blade to verify the effect of genetic gene on the adjustment and optimization of rolling parameters, and further determine the feasibility and applicability of optimization.<br>This paper also introduces the research of forming die for spiral blade. The design theory of die forming, two methods of die forming and the basic structure analysis of die are introduced. The main process parameters of die forming were analyzed.<br>The results show that: the process parameters optimized by standard genetic method begin to converge at about 120 generations, and the geometric dimension error between the produced spiral blade and the target spiral blade is relatively large, which needs further empirical adjustment to meet the requirements. However, the optimization with genetic method combined with penalty function has already begun to converge in 80-90 generations, and the products produced by trial rolling are fully in line with the products This overcomes the weakness of "experience adjustment trial rolling method" and achieves the research purpose.<br>Key words: spiral blade rolling, genetic algorithm, parameter optimization, die forming<br>