基于用户权威度与热度分配聚类的微博热点发现

针对微博热点算法未合理进行微博文本和微博用户相结合的问题,提出基于用户权威度与热度分配聚类的微博热点挖掘算法。对微博文本进行分词,得到特征词并使用改进TF-IDF为特征词分配权重,通过权重大小进行降序排序,对微博文本进行聚类分析得到主题类簇,使用ULRank算法计算用户权威度,综合特征词权重、用户权威度和引用关系为特征词分配热度,得到特征词的热度排序结果,获取特征词对应聚类类簇的大概主题即热点话题。实验结果表明,该方法的吞吐量、运行效率、准确率及F值表现较好,能够较全面地反映当前的热点话题。

OPTIMUM OF PRESSURE RATIOS OF MULTI-STAGE RECIPROCATING COMPRESSOR WITH PRACTICAL INTER-COOLING

The optimum pressure ratio distribution of a multistage reciprocating compressor is presented based on the assumption, i.e. the inter stage cooling is perfect and there are no pressure losses. The optimization of the two or three stage pressure ratio is analyzed in two cases of constant heat transfer rate for the inter cooler or constant inter stage inlet temperature, based on the minimum of the sum of theoretical compression power at each stage about a multi stage reciprocating compressor. Furthermore, with an example of two stage compressor the influence on the sum of the power of each stage is analyzed when practical pressure ratio deviates from the optimum value. It is obtained that under different cooling conditions the optimum pressure ratio distribution of the multi stage compression is various, and the change of the optimum pressure ratio within a small range has little influence on the sum of the power each stage. For the two stage compression, this range can be represented as ε 1=(0 96～1 06)ε 1j .