
基于可拓神经网络的排涝泵站主机组动力特性大数据修正方法
杨玉泉, 张仁贡
基于可拓神经网络的排涝泵站主机组动力特性大数据修正方法
Big Data Correction Method for Dynamic Characteristics of Main Unit of Drainage Pumping Station Based on Extension Neural Networks
为解决泵站主机组真机试验困难,无法获取动力特性方程的技术难题,提出一种通过制造厂家提供的模型运转综合特性曲线获取泵站主机组真机动力特性方程的方法。首先,通过模型运转综合特性曲线获取离散特性数据,对其进行二乘法拟合形成泵站主机组模型动力特性方程;其次,通过真机计算机监控历史数据库和泵站运行管理云端数据库,获取静态运行数据样本,采用3次指数矩阵数据处理方法进行静态点修正,初步获得泵站主机组真机动力特性方程;最后,将可拓理论与神经网络计算方法相结合,创新一种可拓神经网络训练方法,实现对初始泵站主机组真机动力特性方程的动态修正,且该方法具有自适应性、自学习性和可拓性等特点。应用实践表明,三次指数矩阵数据处理方法和可拓神经网络训练方法的创新性结合运用,能够较精确、有效、可靠地获取泵站主机组真机动力特性方程, 为整个泵站的安全可靠运行、主机组组合调度和负载优化分配等提供了科学决策依据。
In view of the technical problem that it is difficult to obtain the dynamic characteristic equation of the main engine unit of most pumping stations in China, a method is proposed to obtain the dynamic characteristic equation of the main unit of the pumping station through the comprehensive characteristic curve of the model operation provided by the manufacturer of the main unit of the pumping station. Firstly, the discrete characteristic data is obtained through the comprehensive characteristic curve of the model operation, and then the dynamic characteristic equation of the main unit model of the pumping station is formed by the double multiplication fitting. Secondly, the static operation data samples are obtained through the real computer monitoring historical database and the cloud database of the pump station operation management, and the static point correction is carried out by using the cubic index matrix data processing method. Finally, the extension theory and neural network calculation method are combined to create an extension neural network training method to realize the dynamic correction of the dynamic characteristic equation of the original main unit of the pumping station, and the method has the characteristics of self adaptability, self-learning habit and extension. The application practice shows that the innovative combination of the cubic index matrix data processing method and the extension neural network training method can accurately, effectively and reliably obtain the dynamic characteristic equation of the main unit of the pumping station, which provides a scientific decision-making basis for the safe and reliable operation of the whole pumping station, the combined dispatching of the main units and the optimal load distribution.
动力特性 / 安全运行 / 可拓神经网络 / 排涝泵站 / 主机组 / 大数据 {{custom_keyword}} /
dynamic characteristics / safety operation / extension neural network / drainage pumping station / host group / big data {{custom_keyword}} /
表1 各典型扬程下的流量功率聚类更新数据样本Tab.1 Cluster updating data samples of traffic and power under each typical head |
H/m | Q/(m3·s-1) | P/kW | H/m | Q/(m3·s-1) | P/kW | H/m | Q/(m3·s-1) | P/kW |
---|---|---|---|---|---|---|---|---|
3.5 3.5 3.5 3.5 3.5 | 4.63 | 485 | 4.8 4.8 4.8 4.8 4.8 4.8 4.8 4.8 4.8 4.8 4.8 4.8 4.8 4.8 | 3.88 | 440 | 5.4 5.4 5.4 5.4 5.4 5.4 5.4 5.4 5.4 5.4 5.4 5.4 5.4 | 4.51 | 528 |
5.12 | 537 | 4.01 | 451 | 4.95 | 564 | |||
7.21 | 634 | 4.82 | 541 | 5.21 | 587 | |||
9.03 | 757 | 5.08 | 560 | 5.42 | 598 | |||
10.61 | 795 | 5.53 | 584 | 5.60 | 627 | |||
4.1 4.1 4.1 4.1 4.1 4.1 4.1 4.1 4.1 4.1 4.1 4.1 4.1 | 3.98 | 430 | 5.68 | 609 | 5.98 | 636 | ||
4.26 | 460 | 6.96 | 678 | 6.38 | 657 | |||
4.41 | 477 | 7.24 | 692 | 6.67 | 687 | |||
4.46 | 482 | 7.56 | 709 | 7.01 | 692 | |||
4.60 | 496 | 7.81 | 723 | 7.12 | 740 | |||
5.65 | 589 | 8.22 | 740 | 7.78 | 754 | |||
6.56 | 640 | 9.38 | 782 | 8.28 | 761 | |||
7.21 | 680 | 9.54 | 791 | 8.78 | 786 | |||
6.52 | 730 | 9.62 | 798 | 6.0 6.0 6.0 6.0 6.0 | 4.18 | 532 | ||
8.38 | 740 | 5.4 5.4 5.4 5.4 | 3.61 | 432 | 6.24 | 676 | ||
8.82 | 755 | 3.81 | 456 | 7.92 | 756 | |||
8.92 | 762 | 4.11 | 478 | 8.41 | 784 | |||
9.02 | 769 | 4.38 | 509 | 8.82 | 796 |
1 |
张勇传 .水电站经济运行原理[M].北京:中国水利水电出版社,1998.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
2 |
王绍丹,王宜怀,刘锴 .基于射频识别和无线传感网融合技术的仓储定位方法研究[J].计算机应用研究,2018,35(1):195-199.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
3 |
杨武 .水电站综合自动化数据库管理系统的研究[J].机电工程技术,2008(7):33-35.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
4 |
王万良 .人工智能及其应用[M].北京:高等教育出版社,2006.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
5 |
张仁贡 .水电站动力特性分析数据库系统的研究与应用[J].水力发电学报,2010,29(4):240-244.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
6 |
陈鸿蔚,张桂香,白裔峰 .鲁棒递推偏最小二乘法[J].湖南大学学报(自然科学版),2009,36(9):42-46.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
7 |
张仁东 .具有块基型泵房的大型泵站动力特性分析研究-南水北调东线工程台儿庄泵站地震响应分析[D].南京:河海大学,2006.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
8 |
丁晓唐,王云极,江泉,等 .淮安第三抽水泵站贯流泵房动力特性的数值和测试研究[J].河海大学学报:自然科学版,2008,36(5):615-619.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
9 |
李雪佳,封红旗,梅宇,等 .基于三次多项式拟合三角函数的地理空间距离计算算法[J].计算机测量与控制,2016,24(5):199-201.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
10 |
冯雁敏 .基于综合运行特性模型的某抽水蓄能机组发电工况运行区域划分[J].水电能源科学,2018,36(5):127-132.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
11 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
12 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
13 |
江深 .云仓模式构成及其发展对策研究[J].物流科技,2020,43(5):76-77.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
14 |
周鸣争,杨益民 .菱形思维的可拓神经网络实现[J].系统工程理论与实践,2000,20(6):123-130.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
15 |
蔡文 .可拓集与可拓数据挖掘[M].北京:科学出版社,2008.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
16 |
赵燕伟 .可拓设计[M].北京:科学出版社,2010.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
17 |
赵燕伟,周建强,洪欢欢,等 .可拓设计理论方法综述与展望[J].计算机集成制造系统[J].2015,21(5):1 157-1 167.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
18 |
周飞燕,金林鹏,董军 .卷积神经网络研究综述[J].计算机学报,2020,56(1):1 229-1 251.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
19 |
徐金寿,张仁贡 .水电站计算机监控技术与应用[M].杭州:浙江大学出版社,2011.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
20 |
庆忠,徐青 .大型泵站计算机监控系统的若干问题探讨[J]. 中国农村水利水电,2008(2):74-76.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
21 |
Wiley-Wrox.Beginning Database Design[M]. E-books,2008.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
22 |
American Institute of Down-to-earth Quality of Learning. Microsoft SQL Server 2005 based Technology[M]. World Book Publishing Company,2007.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
23 |
张力丹,李超,陈飙松,等 .多级多受灾点连续消耗应急物资调度优化策略[J].大连理工大学学报,2017,57(5):501-510.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
24 |
张仁贡.水电站厂内经济运行智能决策支持系统的设计与应用[J].水力发电学报,2012,31(4):243-246.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
25 |
宋晓宇,张卿,常春光 .求解双层应急物资调度的改进蜂群算法[J].信息与控制,2015,44(6):729-738.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_ref.label}} |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
/
〈 |
|
〉 |