您的位置：首页 > 论文页面
基于控制图几何特征的制造过程质量诊断方法研究
发表时间：2019-04-30 浏览量：1206 下载量：168
| 全部作者： | 沈维蕾，卢敏童，吴善春 |
| 作者单位： | 合肥工业大学机械工程学院 |
| 摘 要： | 制造过程的稳定性是保证产品质量的前提条件。从控制图的几何图样中通过对特征的定义提取出能代表该图特点的特征，建立控制图特征的提取方法，设计了基于特征的神经网络模式识别器。通过对特征的定义完成了由样本函数进行的特征提取，根据不同过程模式的特征自动识别出6种失控模式，从而区分过程处于受控状态还是失控状态，并将该方法应用于发动机缸体制造过程的质量监控中，以对其有效性进行检验。研究结果证明了基于特征的神经网络模式识别器对于识别控制图的异常模式有较高的效率。 |
| 关 键 词： | 工业工程学；特征；失控趋势；识别；统计过程控制；质量监控 |
| Title： | Research on quality diagnosis method of manufacturing process based on geometric features of control chart |
| Author： | SHEN Weilei, LU Mintong, WU Shanchun |
| Organization： | School of Mechanical Engineering, Hefei University of Technology |
| Abstract： | The stability of the manufacturing process is a precondition for ensuring product quality. The features which can show their features have been extracted according to the definition of the features from the geometric pattern of the control chart. The extracted methods of control chart features have been established. A neural network pattern recognizer based on the features has been designed. The feature extraction from the sample function through defining the feature has been completed. According to the features of different process models, six types of out-of-control mode are automatically recognized to distinguish whether the process is in a controlled state or out-of-control. In order to test its effectiveness, the method is applied to the quality monitoring in the manufacturing process of an engine cylinder block. It is proved that the feature-based neural network pattern recognizer has higher efficiency for identifying the abnormal pattern of the control chart. |
| Key words： | industrial engineering; feature; out-of-control trend; recognition; statistical process control; quality monitoring |
| 发表期数： | 2019年4月第2期 |
| 引用格式： | 沈维蕾，卢敏童，吴善春. 基于控制图几何特征的制造过程质量诊断方法研究[J]. 中国科技论文在线精品论文，2019，12（2）：341-347. |
4
评论数 0请您登录
暂无评论
下载全文
多维论文