基于推理模型的产品快速设计方法研究

为了快速、准确地设计出最大程度上满足用户需求的产品,分析了案例推理和规则推理技术的应用特点,提出了基于案例推理和规则推理相结合的产品快速设计方法。根据用户的设计需求,利用规则推理技术在已有产品案例库中筛选出与设计需求相关的产品,利用模糊评估算法挑选出最相近的设计案例,再根据案例推理技术队最相似的案例进行修改,使案例符合最终设计需求。以汽车散热器结构模块为例来详细说明了所提出的产品快速设计方法。     

机械加工工艺实训系统的研究与实现

研究典型零件机械加工工艺的特点及经验知识,利用Visual Basic 6.0开发基于典型零件机械加工工艺实训系统。针对轴、箱体、齿轮、连杆四类典型零件建立工艺知识学习模块、工艺知识测试模块、典型工艺分析模块、典型工艺实训模块和管理模块。同时在典型工艺分析模块里还建立针对轴、箱体、齿轮、连杆四类典型零件常见机械加工表面的典型工艺知识库,通过交互界面的可视化设计,根据指定零件被加工表面的特点自动生成加工方案,针对指定零件进行工艺规程编写实训以及对数据库中的内容进行可视化管理。     

药筒精密成形工艺数字化设计系统

介绍了药筒工艺数字化设计系统的特点、设计流程和各功能模块的主要功能。该系统在药筒成形工艺和模具设计过程中融合了基于规则的推理与基于实例的推理,可智能完成工艺参数计算,半制品与模具参数化建模,同时为设计者提供有效的精密成形工艺设计知识和经验帮助,大幅提高了该类零件成形工艺和模具设计效率。     

关于“机械设计及加工过程专家系统工具(MPPEST)”的研制

本文在分析机械设计及工艺设计的特点基础上,提出了相应的知识表示及推理机,并研制了机械设计及加工工艺设计的专家系统工具(MPPEST)。其知识获取工具的内容包括:知识表达、知识库维护(知识库完整性检验)和知识获取的辅助模块,MPPEST的推理是以框架推理为主导,规则推理为核心的复合型推理系统。本工具系统通过建立滚珠丝杠付工艺设计专家系统的使用,确认达到预期的功能。     

基于知识工程复杂产品开发过程的模型研究

 为了提高复杂产品开发的效率,驾驭复杂产品开发过程各个环节相互关联的复杂性,提出一种基于知识工程的复杂产品开发过程新模型.该模型把知识工程理论融入复杂产品开发全生命周期过程中,通过知识推理技术从数据库和知识库中获取相应开发阶段的知识和数据来驱动和指导整个复杂产品开发过程,以更好地重用设计知识.研究了该模型的关键技术,包括复杂产品开发知识处理技术和基于知识的CAD/CAM/CAE/CAPP集成技术,提出了两种知识处理方法,即基于规则-对象-框架的知识处理方法和基于规则-实例的知识处理方法,并研究了相应的推理算法;以知识库、数据库、规则库和实例库为基础,通过PDM,STEP中型文件、规则、实例和知识等,实现CAD/CAM/CAE/CAPP集成.最后,通过数据库技术、编程语言VC# . NET和CATIA软件实现了隧道掘进机（TBM）主机的快速设计系统,有效地减少了隧道掘进机主机开发的复杂性和缩短开发周期,以TBM主机为应用实例进一步介绍该模型的合理性和有效性.     

基于实例推理的小型液压机参数化

结合小型液压机企业的实际需求,充分利用现有资源,基于实例推理的思想,引入参数化理论和有限元技术,采用vc++对SolidWorks进行二次开发,开发了一个由参数化CAD模块、数据库模块和有限元分析与优化模块构成的小型液压机参数化CAD系统.使用结果表明该系统大大提高了设计效率.     

基于模糊PID在线熔融指数仪测控系统设计

为实现聚合物的熔融指数在线测量,实时监控加工过程,设计自行整定参数的PID控制器。首先,将自整定技术最常用的模糊规则用于PID控制器中,基于LabVIEW的PID控制模块、模糊设计模块、通信模块等搭建模糊PID控制器,并借助Simulink仿真平台进行仿真。仿真结果表明,该控制器稳定性好、抗干扰能力强。然后,在增加毛细管流变仪循环流道的基础上,利用LabVIEW中模糊工具箱和PID函数搭建测控系统并进行实验测试。实验结果表明:熔融指数测量值相对误差为6.7%,系统具有良好在线控制准确度。     

模糊理论在故障诊断专家系统中的应用

针对传统专家系统的故障知识表示及获取难、故障诊断推理效率不高的问题,将模糊理论运用于故障征兆的提取和故障知识的表示、用面向对象的技术对故障知识进行维护,采用正反向混合推理、带回溯的搜索策略构建故障推理机,建立一种基于模糊规则的专家系统.将这种模糊规则的专家系统应用于航空电子系统的故障诊断中,表明基于模糊规则专家系统解决了故障知识表示及获取难的问题,故障的推理效率得到了提高.     

基于模糊PID的螺旋加料机构粉体进料精度控制

目的 螺旋式加料机构存在传感器响应时间差，造成系统延迟，非线性等问题，采用容积式来计量填充物料的质量的填充误差大。本文提出一种基于模糊PID控制的螺旋式加料机构计量控制系统。方法 利用模糊PID对螺杆式粉料加料装置进行控制，通过模糊规则对PID控制比例、积分、微分参数实现参数自调整。基于Matlab中Simulink模块下模拟该模糊PID控制系统。结果 该控制系统稳定时间减少了66%，快速性提高了21%，超调量降低了10%。结论 基于模糊PID控制系统的计量控制性能优于传统PID的。     

产品包装设计方案智能决策系统的设计与实现

讨论了针对产品包装设计方案智能决策系统的框架,它主要由智能包装设计方案模块和典型包装方案智能检索与评价模块组成。智能包装设计方案模块主要采用专家系统和设计系统组合推理、设计来完成产品包装设计方案的整修设计过程;典型包装设计方案智能检索与评价模块主要采用模糊判断、编码技术、规则推理技术和层次分析法来实现相应或相似典型包装方案的检索和评价。     

Effect of electrical discharge machining on the characteristics of carbon fiber reinforced carbon composites

This work investigated electrical discharge machining (EDM) of carbon fiber reinforced carbon composite material. The characteristics of composites machined by EDM were studied in terms of machining parameters. An empirical model of the composites was also proposed based on the experimental data. The composite material was produced by an electrical discharge sinker using a graphite electrode. The workpiece surface and resolidified layers were examined by scanning electron microscopy (SEM). Moreover, surface roughness was determined with a surface profilometer. Experimental results indicate that the extent of delamination, thickness of the recast layer, and surface roughness are proportional to the power input. The EDM process effectively produces excellent surface characteristics and high quality holes in composites under low discharge energy conditions.     

敏捷制造中基于AI及Internet技术的电火花加工工艺决策

以电火花加工为例提出了一种实现敏捷制造技术的新方法。这种方法基于人工智能及因特网技术与传统制造技术的集成，通过网络化电火花加工工艺智能决策系统的软件以低成本远程快速的使用设计制造专家知识，从而实现设计制造的敏捷化。专家知识包括电火花加工工艺参数的智能选择及推理。通过因特网选择不同应用的加工条件与专家进行动态交互。本文得出结论，基于人工智能技术及因特网的敏捷制造技术的未来应用具有潜在的利益。     

Decision algorithm for selection of high-speed machining,EDM or a combination for the manufacture of injection moulds

The paper presents the development of a decision algorithm for a prototype computer-aided process planning system IMOLD_CAPP for the manufacture of an injection mould. A combination of a generative and plan template approach is used for the development of the system. The input to the system is a 3D solid model developed using IMOLD TM . Successful implementation of the prototype IMOLD_CAPP depends on its incorporation to an appropriate machining algorithm. Unfortunately, there is no one standard algorithm to choose the appropriate machining process from high-speed machining (HSM), electrical discharge machining (EDM) or a combination of the two. Consequently, this research undertook the development of a decision algorithm for the selection of the appropriate machining process. The algorithm decides whether HSM, EDM or a combination should be chosen for a particular case. Several case studies are conducted and the economics of these processes have been analysed to verify the suitability of the algorithm.     

A Study of Computerized Process Planning with Continuous and Discrete Data Base

This paper discusses methods for the computerized selection of machining variables to increase productivity and optimize economics of machining. An attempt has been made to use the computer for process planning in situations for which the relationships between the machining variables and the performance measures are complex and nonlinear functions with discrete values. An algorithm is presented which deals directly with the problem of a discrete data base. A comparison of continuous and discrete data base methods for process planning was made using the Electro Discharge Machining (EDM) process.     

特征展开三I Fuzzy推理模型及其在专家系统中的应用

推导出了专家系统中基于三Ⅰ机制的特征展开Fuzzy推理模型。以作物病虫害的诊断与防治专家系统为实例，在雄风4.1专家系统开发平台中，巧妙运用规则对象块的“规则架 规则体“的规则组织知识表示方法，实现了该平台上的特征展开三ⅠFuzzy推理。给出了其Fuzzy EBNF语法定义，讨论了采用知识表示策略实现Fuzzy推理的灵活优越性。该模型在雄风系列专家系统开发平台中尚属首次使用，并且具有广泛的适用性。     

Influences of Process Parameters on MRR Improvement in Simple and Powder-Mixed EDM of AA6061/10%SiC Composite

In the present work, aluminum alloy 6061/10%SiC composite is machined using numerical controlled Z-axis (ZNC) electrical discharge machining (EDM) process. Improvement in material removal rate (MRR) is explored using tungsten powder suspended dielectric fluid in EDM process (powder-mixed electrical discharge machining (PMEDM)). Peak current, pulse on time, pulse off time, and gap voltage are studied as process parameters. Mathematical relation between process parameters and MRR is established on basis of response surface methodology. The results obtained are further compared with MRR achieved from machining using simple EDM. The existence of tungsten particles in kerosene resulted in 48.43% improvement in MRR. The influence of tungsten powder-mixed dielectric fluid on machined surface is analyzed using scanning electron microscope and energy dispersive spectroscopy (EDS). The results revealed improvement in surface finish and reduction in recast layer thickness with PMEDM. EDS analysis reported presence of tungsten and carbon in recast layer deposited on machined surface.     

Multiobjective optimization and analysis of copper–titanium diboride electrode in EDM of monel 400™ alloy

Electrical discharge machining (EDM) is one of the most accepted machining processes in the precision manufacturing industry. In EDM process, finding an alternative tool material is the demand in modern manufacturing industry. Therefore, an attempt had been made to fabricate copper–titanium diboride powder metallurgy electrode to test in EDM on monel 400? material. The experiments are planned using center composite second-order rotatable design and the model is developed by response surface methodology. The machining characteristics have analyzed using the developed model. In this study, four input parameters such as titanium diboride percentage, pulse current, pulse on time, and flushing pressure are selected to evaluate the material removal rate (MRR) and tool wear rate (TWR). The adequacy of the developed regression model has tested through analysis of variance test. The desirability-based multiobjective optimization is used to find the optimal process parameter which has given maximum MRR and minimum TWR. The optimum process parameters obtained were titanium diboride of 16%, pulse current of 6 A, flushing pressure of 1 Mpa, and pulse on time of 35?µs. The validity of the response surface model is further verified by conducting confirmation experiments.     

Electrical Discharge Machining (EDM) Characteristics Associated with Electrical Discharge Energy on Machining of Cemented Tungsten Carbide

In this investigation, cemented tungsten carbides graded K10 and P10 were machined by electrical discharge machining (EDM) using an electrolytic copper electrode. The machining parameters of EDM were varied to explore the effects of electrical discharge energy on the machining characteristics, such as material removal rate (MRR), electrode wear rate (EWR), and surface roughness. Moreover, the effects of the electrical discharge energy on heat-affected layers, surface cracks and machining debris were also determined. The experimental results show that the MRR increased with the density of the electrical discharge energy; the EWR and diameter of the machining debris were also related to the density of the electrical discharge energy. When the amount of electrical discharge energy was set to a high level, serious surface cracks on the machined surface of the cemented tungsten carbides caused by EDM were evident.     

Slotted electrodes for the improvement of machining performances in EDM drilling

In electrical discharge machining (EDM), poor debris removal may occur under certain conditions. This leads to debris accumulation and degrades machining efficiency. In this study, the rotation and retracting movements of slotted electrodes were coordinated during EDM to realize a pumping effect for expelling debris in the gap between the electrodes and workpieces. The study compared the performance of different slotted electrodes with that of a regular cylindrical (RC) electrode. Moreover, a computational fluid dynamics module was adopted to simulate the effects of the RC and slotted electrodes on debris removal capability in EDM under different conditions. The experimental results demonstrated that among all slotted electrodes, the deep slotted electrode engendered the most-favorable debris removal capability. The deep slotted electrode saved machining time by shortening the electrode jump time or even obviating electrode jumping. This increased the material removal rates by 120%–153% during EDM drilling.     

A performance evaluation of three inference engines as expert systems for failure mode identification in shafts

This paper aims to present performance evaluation of three different inference engines (rule based reasoning, fuzzy based reasoning and Bayesian based reasoning) for failure mode identification in shafts. This research was done with a focus on the validation cases and results after their use in failure cases from several industries where the three systems were tested under the same conditions.Each system was implemented using the same user interface and knowledge base, with different frameworks and techniques as follows: rule based inference reasoning (prolog, C#), Mamdani-fuzzy based reasoning (C, MATLAB®) and Bayesian based reasoning with a variable elimination algorithm (C, MATLAB®).The best performance was obtained using the Bayesian inference engine. The conditional probabilities give flexibility when evidence is not listed, while the fuzzy and classical IF-THEN systems depend on the rules in the inference engine.The process presented in this paper could be used for validation of any expert system or for comparison with other expert systems (inference engines) when the knowledge base is the same.