摘要
建立了基于深层知识处理石油蒸馏过程故障诊断知识库不完善问题的学习模型。对于学习模型进行知识获取,对完善知识库过程中产生的多个断口问题进行数学抽象,并提出了较通用的解决策略。同时提出了知识库一致性维护操作方法,使机器学习获得的新知识在确认非矛盾和非冗余后输入到原始知识库中。
In this paper.a learning model based on deep-knowledge for trouble shooting of petroleum distillation process is proposed.It can study by use of the learning model when domain knowledge base is not complete.A solving strategy for a multi-broken-points problem occured in learning procedure and solving strategy is developed.And this paper put forward a knowledge-base-consistency maintenance method which can input learning results into knowledge base after determining its non-contradiction and non-redundance.
出处
《计算机与应用化学》
CAS
CSCD
1996年第4期277-281,共5页
Computers and Applied Chemistry
基金
国家自然科学基金
关键词
石油
蒸馏
故障诊断
机器学习系统
Petroleum distillation process.Trouble shooting, Machine learning system