【作者】 巨永锋；

【导师】 龙水根；

【作者基本信息】 长安大学 ， 机械设计及理论， 2006， 博士

【摘要】 在2001年国家“863”计划“先进制造与自动化技术”领域设置的“机器人技术”主题中，将“机群智能化工程机械”列为4个专题方向之一，机群智能化的基础是单机的智能化。本文主要从“压实智能控制”、“故障智能诊断”、“人机智能交互”三个方面，研究振动压路机的智能化技术，为机群智能化工程机械的研究开发做了有益的探索和开拓性的工作。论文研究的成果如下： 1．在介绍振动压实机理的基础上，通过建立振动压路机动力学模型，分析了振动压路机主要工作参数对压实效果的影响，给出了振动压路机压实智能控制系统的基本组成，为振动压路机压实智能控制系统的研究与设计奠定了理论基础。 2．在分析振动压路机压实智能控制系统的功能及要求的基础上，提出了基于CAN总线技术和专用PLC构成的振动压路机压实智能控制系统总体设计方案，完成了智能控制系统的硬件选型与设计。 3．在实验室和现场试验的基础上，提出了压实度仪的技术改进方案，解决了压实度仪使用过程中的标定、与控制器的连接等关键技术难点，实现了压实度的在线检测。 4．将模糊系统与神经网络相结合，提出了一种由模糊化层、模糊推理层和清晰化层组成的振动压路机压实模糊神经网络控制器结构，运用补偿模糊神经网络的学习算法解决参数的自动调整问题。把实践中得出的模糊控制规则表作为训练模糊神经网络的样本，仿真结果表明该模糊神经网络控制器具有在误差限度范围内的泛化能力，可用于振动压路机的压实控制中。 5．在分析振动压路机故障机理的基础上，提出了一种基于人工神经网络专家系统(ANNES)的振动压路机故障智能诊断系统，深入研究了知识库、推理机制、学习机制、解释机制、数据库以及神经网络与专家系统的相互导入机制等关键技术。在知识库中，用神经网络来表示浅层知识，以实现对故障的直觉联想；用框架来表示振动压路机的深层知识，以实现对故障诊断的逻辑验证。在推理机制中，基于神经网络的推理采用正向推理的方法，基于框架的推理则分为对神经网络诊断结果的逻辑验证和重新对故障逻辑推理，以保证故障诊断的正确性。在学习机制中，包括了神经网络对专家经验的学习以及对新的故障的学习。 6．在分析振动压路机压实智能控制系统人机交互软件设计需求的基础上，更多还原

【Abstract】 In the robot technology Priority , which is in the field of the advanced manufacturing and automation technology under the National High Technology Research and Development Program of China (863 Program), airmada intelligentized engineering machinery is identified as one of 4 Subject areas. Airmada intelligentized fundamental is the single machine intelligence. The intelligentized technologies of vibratory road roller are researched in this paper from the three aspects: intelligent compaction control, intelligent fault diagnosis and intelligent human-machine interaction so as to do beneficial exploration and pioneering work for the research and development of the airmada engineering machinery. Research results of this paper are as follows:1. On the basis of introducing the vibratory compaction mechanism , impacts of the vibratory road roller’s main working parameters on compacting effect are analysed by building the dynamic model of vibratory road roller. The ultimate composition of intelligent compaction control system of vibratory road roller is given.Therefore, the theoretical basis is laid for the research and design of intelligent compaction control system of vibratory road roller.2. On the basis of analyzing the function and requirement of intelligent compaction control system of vibratory road roller, the general design planning is presented based on CANbus and special purpose PLC. The hardware lectotype and design of the intelligent control system are accoplished.3. On the basis of test in the laboratory and on site, technique improvement planning of compaction degree measuring instrument is made an offer. Some key technology dificulties are solved about calibration of compaction degree measuring instrument during use and connection with the controller. Compaction degree on-line detection is realized.4. A kind of structure of fuzzy neural network for compaction control of road roller is put forward by connecting fuzzy system with artificial neural network in this paper, which consists of the fuzzification layer, fuzzy inference layer and clarification layer and is used. Self-adjusting of fuzzy neural network parameters are settled by learning algorithms of compensated fuzzy neural network. Fuzzy control更多还原