基于数字孪生与深度学习技术的制造加工设备智能化方法研究

针对传统制造加工设备在生产加工过程中存在设备与数据信息联系不紧密，设备使用维护多依赖于人工经验等问题，提出了一种新的设备智能化方法。首先，在信息层建立能反映制造加工设备真实状态的数字孪生体；其次，基于历史加工大数据，通过数字孪生体对加工过程的行为进行建模及深度学习和训练，并利用训练好的人工神经网络根据采集到的实时数据来预测制造加工设备下一时刻的状态，使制造加工设备实现物理层与信息层数据的深度融合，拥有自我感知、自我预测的能力，最终实现智能化；最后，以浆料微流挤出成型设备挤出结构系统的智能化实施过程为例，验证了所提出方法的可行性。实例结果表明该设备智能化方法可有效地对挤出结构系统的运行状态进行监测及预测，为后续提高挤出成型精度提供了有效的数据信息。研究表明数字孪生和深度学习技术能够提升制造加工设备的智能化程度，可为未来智能制造的发展提供理论支撑。

Research on intelligent method of manufacturing and processing equipment based on digital twin and deep learning technology

In view of the problems that the traditional manufacturing and processing equipment is not closely related to the data information during the production and the equipment maintenance greatly depends on the human experience, a new intelligent method for the equipment is proposed. Firstly, the digital twin that can reflect the true state of manufacturing and processing equipment was established in the information layer. Secondly, based on the past big data of processing，the behaviour of the process was modelled and the deep learning and training was performed by the digital twin. The state of manufacturing and processing equipment at the next moment was predicted by the trained artificial neural network based on the collected real-time data，so that the manufacturing and processing equipment could realize the deep integration of data in the physical layer and the information layer, and had the ability of self-awareness and self-prediction to realize the intelligence. Finally, taking the intelligent implementation process of extrusion structure system of slurry microfluidic extrusion forming equipment as an example to verify the feasibility of the proposed method. The example results showed that the intelligent method of the equipment could effectively monitor and predict the operating state of the extrusion structure system, which provides effective data information for the subsequent improvement of the extrusion molding accuracy. Research shows that the digital twin and deep learning technology can enhance the intelligence of manufacturing and processing equipment, and can provide theoretical support for the development of intelligent manufacturing in the future.