决策支持系统

中文字数:3356,中文页数:3  英文字数:1951页数:5

A paradigm shift is emerging in system reliability and maintainability. The military and industrial sectors are moving away from the traditional breakdown and scheduled
maintenance to adopt concepts referred to as Condition Based Maintenance (CBM) and Prognostic Health Management (PHM). In addition to signal processing and subsequent diagnostic and prognostic algorithms these new technologies require storage of large volumes of both quantitative and qualitative information to carry out maintenance tasks effectively. From the volumes of data that can be obtained today, information extraction has been a challenging task and organizing this information, so that it can be considered useful knowledge, is yet another level of abstraction. This not only requires research and development in advanced technologies but also the means to store, organize and access this knowledge in a timely and efficient fashion.
Knowledge-based expert systems have been recently shown to possess capabilities to manage vast amounts of knowledge, but an intelligent systems approach calls for attributes like self-evaluation (feedback), self evolution (learning) and self-organization (maintenance) to build truly autonomous systems for CBM. Furthermore, an intelligent reasoner is required that can make judicious use of this knowledge and provide a substantial support in the decision making process.

摘要 一种模型的转变正在系统的可靠性和可维护性中浮现。军方和工业部门正在摆脱传统的故障和预定维修模式，转而通过称为基于状态的维修（CMB）及预防健康管理（PHM）来进行。此外，信号的处理和随后的诊断及预防算法，这些新的技术需要存储大量的定量和定性信息以执行有效的维护任务。但是在当今时代，从大量的数据中提取信息和组织这些信息以便它被转换为知识，又是一个抽象而又具有挑战性的任务。这不仅需要研究和发展先进的技术手段，而且意味着需要提供一种存储，组织和及时获取这些信息的有效的方式。    最近，以知识为基础的专家系统已显示出拥有的能力来管理大量的知识，但是一个智能系统要求一些属性像自我评价（反馈） ，自我发展（学习）和自我组织（维护）以帮助CBM建立真正自治的系统。此外，还需要可以明智地利用这种知识，并在决策过程提供大量的支持的智能推理。

相关论文