论文部分内容阅读
提出了一种在并行工程环境下用于小批量生产的质量反馈两层模型，能够准确、客观、在线动态地评价现行加工工序的状况和进行相应的加工过程质量仿真，以便对新零件的公差带设计提供指导；针对多批次小批量问题，提出了一种抑制数据中系统噪声和观测噪声的方法，可以有效地提高建模的精度；利用多组实验数据对提出的模型进行研究，充分说明了以上方法的有效性和实用性；针对广东省惠阳机械厂生产的ＺＪＴ－４０型全自动胶囊充填机的充填杆外圆磨削加工过程，运用提出的多批次数据建模方法，有效地弥补了因小批量数据所固有的信息不完整性而无法精确建模的缺陷。为了推广应用，开发了一套原型系统以实现上述的各种模型功能。
A two-layer model of quality feedback for small-batch production in parallel engineering environment is proposed, which can accurately, objectively and dynamically evaluate the current machining process status and carry out the corresponding quality simulation of machining process so that the tolerance of new parts With the design of the system to provide guidance; For small batches of small batches of the problem, put forward a method to suppress the system noise and observation noise in the data, can effectively improve the modeling accuracy; using multiple sets of experimental data to study the proposed model, fully The effectiveness and practicability of the above method are illustrated. According to the cylindrical grinding process of the filling rod of the ZJT-40 automatic capsule filling machine produced by Huiyang Machinery Factory in Guangdong Province, the proposed multi-batch data modeling method is effective To make up for the lack of information inherent in small quantities of data can not accurately model the shortcomings. In order to promote the application, a prototype system has been developed to realize the above various model functions.