经济的发展和科技的进步使许多大型结构得以兴建。如何对这些大型结构的健康状况进行监测、日常管理以便在结构发生事故之前提前预警,以减少灾害的损失成为目前人们关心的问题。大型结构健康监测系统的开发为这个问题提供了一种有效的方法。然而,大型结构具有较多的结构冗余度和环境荷载的不确定性;此外,来自监测系统的海量数据也包含大量的噪声和不确定性。如何合理有效地处理来自健康监测系统海量不确定测量数据与信息,进而对结构的健康状况进行评价成为国内外同行关注的热点和难点。智能信息处理是近几年发展起来的新型信息处理技术,它是将不完全、不可靠、不精确、不一致和不确定的知识和信息逐步改变为完全、可靠、精确、一致和确定的知识和信息的过程和方法。它的出现和发展为以上难题提供了一条途径和技术保障。基于此,该文从结构健康监测涉及的以上主要问题入手,对智能信息处理技术从现代信号处理、神经网络、模糊理论、数据融合(信息融合)、分彤理论、粗糙集、进化计算等方面对它们在结构健康监测与损伤诊断领域取得的研究成果进行了归纳总结,并对今后该领域需要进一步开展的工作进行了探讨和展望。研究发现,智能信息处理是结构健康监测与检测领域的有效技术和今后发展趋势。
A number of large-scale complex structures have been built promoted by the development of economy, science and technology. It is an interesting issue how to monitor and manage these large structures so that the alarm will be warned before various accidents occur, thus the disaster loss can be decreased to the minimum. Numerous large long-term structural health monitoring systems have been developed and installed in China. However, another problem arise gradually how to effectively deal with the huge and abundant measured information from a structural health monitoring system, thus to asses structural condition states. In view of this, intelligent information processing, which is a process of transforming the incomplete, imprecise, inconsistent and uncertain information into complete, precise, consistent and certain information, provides an approach and technique assurance to solve the above difficulties. This paper startes from the structural health monitoring and its primary issues, and then presentes a survey and overview of the intelligent information and its application in structural health monitoring and damage diagnosis, including modern signal processing, neural network, fuzzy theory, data/information fusion, fractal theory, rough set and evolutionary computation. Further research in the future are discussed finally. This study shows that intelligent information processing technique is one of the efficient processing tools and techniques in structural health monitoring and it also represents the effort direction in the future.