基于人工神经网络技术的结构布局优化设计

使用PCL（Patran Command Language）实现了Patran环境下的机翼参数化模型。其优化模型包含两类设计变量：几何位置变量和几何尺寸变量。在采用Nastran软件实现几何尺寸优化的基础上，结舍均匀试验设计方法，利用神经网络的高度非线性映射功能，建立了目标函数与位置设计变量的映射关系。在Matlab环境下，编写了使用改进的可行方向法的优化程序，并对翼梁位置完成优化，最终完成了整个机翼的布局优化设计。可以看出。将参数化建模与神经网络功能结舍进行结构优化，能更好地发挥神经网络的映射功能，使优化结果更加精确、高效。所提方法可以解决在Patran环境下的复杂结构位置变量优化问题，弥补了该软件的不足之处，具有很好的应用推广价值。     

智能仪器的抗干扰技术

本文分析了智能仪器常见干扰的来源,从应用的角度论述了硬件、软件和印制电路板等几个方面抗干扰的技术。     

Application of 3D FEM-slab method to shape rolling

In this paper, a complex model combining the simplicity of the slab method and accuracy of the finite element method was developed to save CPU time. When applied for the shape rolling, the deformation zone in the billet was divided into several proper slabs according to the shape of boundaries, in which each slab must match the force equilibrium along the longitudinal direction. Then, FEM was used to calculate sequentially the velocity field, metal flow, stress and strain distribution for each slab. By using only one slab in each iteration, the iteration range of traditional FEM was significantly reduced. Therefore, the memory capacity and computational time can be significantly reduced. Compared with traditional FEM, the results of this complex model were acceptable, verifying that the model proposed in this paper is an effective method.     

滚动式智能取药柜的设计与实现

为实现医院药房系统自动化管理,提高药房配药效率,智能存取药柜能够更好的完成药房上药出药工作。该智能药柜主体控制环节主要由内部简易PC机和PLC控制器构成。其中PC机主要实现药柜与药房服务器之前的数据传输、药品信息维护等,并基于Microsoft Visual Studio 2008开发了可视化的操作界面。PLC控制器主要负责实现智能药柜的出药、上药及故障检测。该药柜样机以完成试验工作,明显提高了工作效率。     

Roll shape design for foil rolling of a four-high mill

In this paper, a mathematical model for a four-high mill is proposed to analyze the elastic deformation of the backup and work rolls, including their respective axial deflection and surface flatness. The contact pressure between the backup and work rolls and that between the work roll and foil are functions of the roll’s position in the axial direction. In this analytical model, the rolls and foil are divided into many small regions and finite difference or matrix methods are used to derive the deflections of the work and backup rolls as a function of the force density in the foil width direction. A camber shape at the surfaces of the backup and work rolls is designed to counteract the rolls’ elastic deformation and to make the rolled foil as flat as possible. The effects of the selected roll materials upon the rolled thickness distribution are also discussed. A thickness variation within 1 μm can be obtained for a foil of 50-μm thick and 40-mm wide under reduction of 32 % using a WC work roll with a camber radius of 150 m.     

Optimization of injection molding process parameters using integrated artificial neural network model and expected improvement function method

In this study, an adaptive optimization method based on artificial neural network model is proposed to optimize the injection molding process. The optimization process aims at minimizing the warpage of the injection molding parts in which process parameters are design variables. Moldflow Plastic Insight software is used to analyze the warpage of the injection molding parts. The mold temperature, melt temperature, injection time, packing pressure, packing time, and cooling time are regarded as process parameters. A combination of artificial neural network and design of experiment (DOE) method is used to build an approximate function relationship between warpage and the process parameters, replacing the expensive simulation analysis in the optimization iterations. The adaptive process is implemented by expected improvement which is an infilling sampling criterion. Although the DOE size is small, this criterion can balance local and global search and tend to the global optimal solution. As examples, a cellular phone cover and a scanner are investigated. The results show that the proposed adaptive optimization method can effectively reduce the warpage of the injection molding parts.     

Study on the manufacturing process of precision linear guide rail through shape rolling and shape drawing

Guide rails are one of the most important components in terms of equipment because the quality of the linear rail in-fluences on the precision linear motion. For long rails used in the guide rail, high dimensional accuracy as well as a cross-sectional shape is required. As a production method of guide rail, drawing process is mainly used. But, the shape rolling process is open used for the pre-process of the other metal forming process such as forging, extrusion, and shape drawing. The shape rolling process is one of the most effective processes which can make long products with constant irregular cross-sectional shape. Therefore, the tool shape is a very important process variable to obtain the required final product. The objective of this paper is the design of roll shape of the rolling process to produce the initial material with irregular cross sectional shape for shape drawing. Also, the die shape of the drawing process is determined to satisfy the dimensional accuracy of the final product. In this study, FE-analysis and artificial neural network (ANN) were applied to achieve the objective. Further, shape rolling and shape drawing experiments were performed to verify the result of FE-analysis. From results, it was possible to design the roll shape of shape rolling process effectively.     

交流电机智能综合测试系统设计

为解决交流电机性能检测问题,建立了交流电机智能综合测试系统,对低压三相交流电机、高压三相电机、变频电机设计了3种不同的自动测试系统方案。应用结果表明,该测试系统操作方便,安全可靠,能提高交流电机的测试、检修效率,具有一定的工程指导价值。     

人造金刚石合成工艺的智能控制

采用计算机控制技术对Y-500型六面顶压机生产人造金刚石的整个生产工艺过程进行全方位控制和监测,大大提高了压机运行的可靠性和生产效率.根据工艺要求采用智能PID控制和模糊PID控制策略对人造金刚石生产中的工艺参数加热功率和加压压力实现有效控制,大大提高人造金刚石产品的质量和品位.     

滚动轴承故障诊断的神经网络方法

总结分析了轴承的故障形式及原因,给出了振动频率,阐述了Bp网络的结构及算法,并对实例建立BP神经网络。     

Mathematic modeling and FE simulation of radial-axial ring rolling large L-section ring by shape axial roll

An accurate prediction of the ring diameter growth rate of a large L-section ring during radial-axial ring rolling (RARR) by a shape axial roll is quite essential because it determines the stability of the process and thus influences the quality of the rolled ring. In this paper, a mathematic model predicting the ring diameter of the large L-section ring during the new RARR process is first established. Then, 3D thermo-mechanical coupled rigid-plastic finite element (FE) models of the new RARR process are developed based on the implicit code DEFORM-3D to verify the mathematic model. By setting and adjusting the movements of the work rolls, large L-section rings are rolled. The effective strain distribution of the rolled ring is analyzed. Comparisons between the FE simulated and the mathematic predicted parameters including external diameter, growth rate of external diameter, and rotational speed of the rolling ring are made. The simulated and the predicted parameters are in good agreement, indicating that the mathematic model accurately predicted the size of the rolling ring and thus can be used to provide a guideline in real manufacturing of large L-section rings.     

板带轧机辊型在线检测装置的研究

对热轧板带轧机辊型在线检测技术进行了分析,提出采用光电式传感器构造辊型检测系统,其特点是有较强的抗干扰能力,且结构紧凑,工作可靠.轧辊在线检测与修磨技术可以及时消除各种辊面缺陷,提高产品质量.     

基于滚动优化的智能环形叠放立体车库系统设计研究

目前市场上的立体车库种类繁多,然而绝大多数都存在:空间利用率低、管理混乱、系统运行不稳定等问题。设计了一款新型的智能环形叠放立体车库,该立体车库系统主要包括车辆运载模块、车辆识别模块和WIFI智能管控模块。车辆识别和智能管控模块使用数字化、可视化的界面,极大的方便了车库系统的管理、提高了系统运行效率。车辆运载模块使用三个控制精度高的步进电机,相比于传统的开环控制或是PID控制,设计的MPC控制器实现了滚动时域内的优化,使得电机控制更精确、系统运行更稳定。实物模型测试结果,表明该立体车库系统可以高效地存/取车辆、并且能够很好地适应复杂负载,同时有效地提高了资源利用率。     

面向产品数据的智能化集成化CAPP系统研究

提出了一种面向产品数据的智能化集成化CAPP系统实现方案,详细介绍了系统组成与基本结构,并设计了系统的工作流程,对其中的主要问题进行了探讨并提出了作者的见解。     

Fault diagnosis of rolling element bearing based on artificial neural network

Journal of Mechanical Science and Technology - This paper proposes the expert system for accurate fault detection of bearing. The study is based upon advanced signal processing method as wavelet...     

大型冷连轧生产线PCS系统数据接口集成

介绍了大型冷连轧生产线FCS系统数据信息接口的实现,软件平台和结构特点,特别是Wincc和Connectivity Pack的使用,将生产管理层与基础层安全可靠地连接起来。     

基于云图的冷轧板形在线监控系统设计

现有的带材板形呈现手段与描述方式不能全面反映带材的整体型面和局部细节及其变化趋势,制约了生产设备控制系统参数设置的调整和对生产过程的分析.因此,本文提出并设计了一种可视化带材板形实时监控系统,利用板形值与颜色值的对应关系,结合带材在宽度方向上的缺陷分布绘制实时板形云图.实际应用结果表明,本文所设计的系统能够精确绘制出呈...     

省煤器智能设计系统的开发及其关键技术

以超临界锅炉省煤器为研究对象,阐述了基于知识融合(Knowledge Fusion,KF)技术、智能化锅炉零/部件设计系统的开发过程及其关键技术.该系统是在UG/KF语言和用户自定义特征基础上,通过对UG软件的二次开发构建的;是自主开发的省煤器智能化设计系统,为产品设计人员提供了友好的人机交户界面,实现了知识库和CAD系统的无缝集成,从而避免了超临界锅炉省煤器设计过程中的重复性设计工作.     

HC轧机板形液压伺服系统智能控制的研究

针对HC轧机液压弯辊系统的非线形和时变性等特点，设计了基于遗传算法的模糊RBF神经网络智能控制系统，改善了系统的性能。     

智能调度综合预警系统在电网调度中的应用

针对县级电网调度日常工作需要,结合电力系统自动化建设现状,在遵循数据模型国际标准(IEC61970-CIM)的基础上,利用Visual Studio软件设计开发了一个直接面向电网调度的实时智能化辅助平台.通过将电网调度业务关注的SCADA系统、线路单线图、保护配置、设备台帐、线路限额、正常运行方式等不同系统的、分散的信息集中在这个平台上,建立了电力系统的配网拓扑模型,实现了电网实时监控、模拟操作、静态危险点预警、动态风险评估、事故演习及反演、电子值班和操作信息管理等功能,以辅助电力调控员快速、高效、科学应对各类电网突发故障.实例应用结果表明,该系统大大提高了电力调控员的工作效率和电网管控能力,减少了停电损失,提升了电网综合管控和应急管理水平.