共查询到19条相似文献,搜索用时 234 毫秒
1.
2.
为提高生产决策水平,提出了基于人机交互仿真的生产决策专家系统构建方法.针对生产决策专家知识难以采集和控制策略复杂等特点,采用神经网络和专家遴选算法实现对专家知识的评估和优选,结合融合分类算法解决知识推理的问题,并提出TR-TREE算法构建专家系统规则解释机制.以某摩托车发动机关键零部件生产单元的换线决策为应用背景,对所提出的实现原理和关键技术进行了应用实践.与基于经验的人工决策相比,基于专家系统的换线决策对生产目标的优化作用显著,并具有良好的学习机制. 相似文献
3.
4.
智能型磨粒识别是铁谱技术发展的主要趋势,人工神经网络技术的出现,为这种智能化提供了一条崭新的途径。介绍了神经网络专家系统的基本原理,叙述了BP学习算法,以及基于该算法的磨粒识别神经网络专家系统的设计。 相似文献
5.
6.
7.
提出了一种可以减小网络规模的故障表示方法,并将Alopex算法引入神经网络模型的训练过程,将人工神经网络与规则推理相结合,建立了旋转机械故障诊断的神经网络专家系统。该系统充分利用了神经网络与规则推理的优点,采用正反向混合推理方式调用知识库中的各种知识进行诊断。采用二进制数码表示机械的各种故障,基于Alopex算法训练神经网络。建立的专家系统克服了基于规则专家系统的自学习困难问题和基于神经网络诊断系统的系统控制能力弱的缺点,具有较强的诊断能力。 相似文献
8.
9.
10.
基于人工智能的机械系统多学科优化探讨 总被引:5,自引:0,他引:5
针对多学科的优化计算复杂性和信息交换复杂性 ,在分析前人多学科优化方法基础上 ,提出将人工神经网络、专家系统、模糊评判等人工智能技术引入多学科优化领域 ,充分利用神经网络专家系统所具有的高度容错性、鲁棒性、实时性、自适应性和系统可以自组织、自学习以及联想记忆等功能 ,探索一种适用基于人工智能技术的多学科优化设计新方法 相似文献
11.
Seok Jo Got Min Cheol Lee Min Kyu Park 《Journal of Mechanical Science and Technology》2001,15(5):580-591
This paper proposes a fuzzy-sliding mode control which is designed by a self tuning fuzzy inference method based on a genetic algorithm. Using the method, the number of inference rules and the shape of the membership functions of the proposed fuzzy-sliding mode control are optimized without the aid of an expert in robotics. The fuzzy outputs of the consequent part are updated by the gradient descent method. It is further guaranteed that the selected solution becomes the global optimal solution by optimizing Akaike’s information criterion expressing the quality of the inference rules. In order to evaluate the learning performance of the proposed fuzzy-sliding mode control based on a genetic algorithm, a trajectory tracking simulation of the polishing robot is carried out. Simulation results show that the optimal fuzzy inference rules are automatically selected by the genetic algorithm and the trajectory control result is similar to the result of the fuzzy-sliding mode control which is selected through trial error by an expert. Therefore, a designer who does not have expert knowledge of robot systems can design the fuzzy-sliding mode controller using the proposed self tuning fuzzy inference method based on the genetic algorithm. 相似文献
12.
基于遗传算法的动态调度知识获取 总被引:5,自引:0,他引:5
张纪会 《计算机集成制造系统》1999,5(3):64-68
用普通方法难以很好地解决动态调度的问题,仿真方法和专家系统相结合是一个较好的解决办法,但是知识的缺乏制约了它的应用,机器学习是获取调度知识的一个重要途径。提出一种新的机器学习方法,并用实例说明其可行性。 相似文献
13.
Professor Zone-Ching Lin Chun-Yao Hsu 《The International Journal of Advanced Manufacturing Technology》1996,11(1):1-11
The purpose of this paper is to develop an expert system for shearing cut progressive die, with the aim of enhancing the design of shearing cut progressive dies. This study is different from previous research on shearing cut die design by the author in that the design of one station was extended into a progressive die design. The major research objectives achieved in this study can be summarised as follows:
- This study presents a pattern recognition method called the new combined structural approach to let the user interpret blanks by a better and more direct method, thereby achieving the goal of communicating with this expert system.
- The layout of the strip can affect the material cost shared by the press-worked pieces. This study presents the near optimal method for seeing a better layout of the strip in order to save material.
- Owing to the great variety of blank shapes which cause the variations in pressing procedures, this study proposes a matching combination learning method, which is a learning conscious system for pressing procedures, in order to obtain the optimal number of operation stations in shearing cut progressive die design.
- The establishment of the knowledge-base system for shearing cut progressive die should improve the efficiency for die design problems.
14.
将人工神经网络与规则推理相结合,建立了薄板裂纹诊断的专家系统,该系统充分利用神经网络与规则推理的优点,采用正反向混合推理方式调用知识库中的各种知识进行薄板结构的裂纹诊断,采用基于实验的计算机仿真技术建立裂纹诊断的标准谱,基于模拟退火算法训练神经网络,实例表明,本文建立的专家系统克服了基于规则专家系统的自学习困难问题和基于神经网络诊断系统系统控制能力弱的缺点,具有较强的诊断能力。 相似文献
15.
16.
本文提出了带时滞的ADALINE神经网络对时变复杂线性系统的自适应建模方法,通过对性能函数是权系数二次型的神经网络的算法改进,以梯度变化的共轭向量为搜索方向,以解析式确定最优步长,理论分析和仿真实验证明了此算法的快速性和高精度逼近能力,也证明了基于这种快速算法的带时滞的ADALINE网络实现复杂时变线性系统高精度动态自适应建模的有效性。 相似文献
17.
18.
19.
1IntroductionInrecentyears,themainfunctionsofCADarenu-mericalcalculations,dataretrievalandcomputergraphics.Thereis,however,somekindofworkstilltobedonebydesignerhimself,suchasorganizingdesigninformation,in-troducingcreativity,intelligenceandexperience,andc… 相似文献