故障诊断系统中深浅知识集成表示方法的研究

INTEGRATED MODEL OF SHALLOW AND DEEP KNOWLEDGE IN FAULT DIAGNOSIS SYSTEMS

传统的故障智能诊断系统大都只是基于专家的经验 .但是 ,由于现代设备的复杂性 ,使其往往得不到准确的结果 ,这时必须借助于与诊断对象有关的原理性知识 .本文基于设备的层次性理论 ,提出了一种深浅知识集成表示模型 ,并采用面向对象表示和产生式规则相结合的方法予以实现 .深浅知识的有效结合 ,不仅可以提高故障诊断的准确性 。

Traditionally, the intelligent systems for fault diagnosis are only based on expert experience called shallow knowledge. However, they sometimes lead to dissatisfactory conclusions as a result of the complexity of modern equipment. To obtain better results, the knowledge about the principle of equipment called deep knowledge appears in these systems. In this paper, based on the hiberarchy of equiment, we first present an integrated model that combines the two kinds of knowledge. Then, the model is realized by using object oriented programme and production rules. By using shallow and deep knowledge synthetically, the veracity and the efficiency of systems are much improved.