可移动式油水分离智能监测系统设计  

Research on application of short video recommendation model based on collaborative filtering algorithm

作　　者：李洋 史昊天 韩利 丁宁 梅开涛 张莉英[2] 王成龙 LI Yang;SHI Haotian;HAN Li;DING Ning;MEI Kaitao;ZHANG Liying;WAGN Chenglong(Ningdong Power Supply Company of State Grid Ningxia Electric Power Co.,Ltd.,Yinchuan 750411,China;North China Institute of Aerospace Engineering,Langfang Hebei 065000,China;Power Research Institute of State Grid Ningxia Electric Power Co.,Ltd.,Yinchuan 750011,China;EHV Company of State Grid Ningxia Electric Power Co.,Ltd.,Yinchuan 75001,China)

机构地区：[1]国网宁夏电力有限公司宁东供电公司,银川750411 [2]北华航天工业学院,河北廊坊065000 [3]国网宁夏电力有限公司电力科学研究院,银川750011 [4]国网宁夏电力有限公司超高压公司,银川750011

出　　处：《自动化与仪器仪表》2024年第1期218-222,共5页Automation & Instrumentation

基　　金：国网宁夏电力公司2022年科技项目资助(5229ND220003)。

摘　　要：为解决实现电力系统带来的油污染问题,提出一种可移动式油水分离智能系统,以缓解油水混合排放带来的污染问题。研究主要对油水分离装置进行了系统设计,其中包括控制模块和数据采集模块的设计,并对数据采集系统中所使用的传感器进行了优化设计。实验结果表明,设计的介质传感器在油水分离系统中进行数据采集能够保持较高的精度,传感器的灵敏度为4%;使用设计的可移动式油水分离系统进行油水分离测试时,能够始终保持系统含水率在正常范围内,且波动保持在1%以内,性能稳定。综上,本研究设计的可移动式油水分离系统能够实现效果良好的油水分离,能够帮助电力系统大大减少排放溶液中的油浓度,实现减少污染的目的,具有一点实际应用价值。In order to further improve the video recommendation effect of short video platform,a short video recommendation system is constructed based on collaborative filtering algorithm.Among them,singular value decomposition(SVD)and penalty are introduced to optimize the traditional collaborative filtering algorithm,and the performance of the algorithm is improved to some extent.The experimental results show that,compared with the traditional collaborative filtering algorithm,the improved collaborative filtering algorithm proposed in this study has better performance,and the RMSE value of the algorithm result is only 0.948;Compared with the traditional recommendation model,the short video recommendation model proposed in this study based on the improved collaborative filtering algorithm can more accurately predict the user’s video score,and then can more accurately recommend short videos that meet the user's preferences.The above conclusions show that using the recommendation model proposed in this study can achieve better recommendation effect,and can recommend videos more in line with users’preferences,which has certain practical application value.

关 键 词：混合液分离 系统控制 数据采集 介质传感器 

分 类 号：TP392[自动化与计算机技术—计算机应用技术]