论文部分内容阅读
人工神经网络或神经网络又可叫连接网络模型,并行分布处理模型及神经组织系统。它是依据现有对人脑思维过程研究和掌握的基础,用数学办法对其进行简化、抽象和模拟,并反映人脑功能的基本特性。 近年来,由于计算机、现代测置技术和信号处理技术的迅速发展,机械故障诊断技术取得了很大的进展。人们已开发和研究了一些较成熟和完善的诊断技术和理论方法,如铁谱分析、声发射、红外测温、油液分析和各种无损监测等技术及信号处理、模式识别、专家系统和模糊识别等理论方法。应用这些技术手段和理论方法,人们可对在多种工作环境条件及运行状态下的机器式工程系统的许多故障模式进行监测、识别、诊断和排除。
Artificial neural network or neural network can also be called connected network model, parallel distributed processing model and neural tissue system. It is based on the existing research and mastery of human brain thinking process, using mathematical methods to simplify, abstract and simulate, and reflect the basic characteristics of human brain function. In recent years, due to the rapid development of computer, modern measuring technology and signal processing technology, great progress has been made in mechanical fault diagnosis technology. People have developed and studied some mature and complete diagnostic techniques and theoretical methods, such as iron spectrum analysis, acoustic emission, infrared temperature measurement, oil analysis and various non-destructive monitoring techniques and signal processing, pattern recognition, expert systems and Fuzzy recognition and other theoretical methods. Using these technical and theoretical methods, one can monitor, identify, diagnose and eliminate many failure modes of a machine-typed engineering system under a wide range of operating conditions and operating conditions.