Solar heat pump hot water system control strategy optimization method based on machine learning

A technology for solar heat pumps and hot water systems, applied in solar heating systems, solar collector controllers, solar collectors in specific environments, etc., can solve control strategy verification, coupling and matching problems that do not use load dynamic prediction methods, etc. question

Active Publication Date: 2020-03-24
SOUTH CHINA UNIV OF TECH
View PDF6 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Some scholars (Huang Wenhong. Research on the operating characteristics and optimization of solar-air source heat pump hot water system [D]. Jimei University, 2017. Lou Jing. Research on intelligent control system of parallel solar heat pump hot water units [D]. Central South University, 2009. Chen Qingjie. Research on the prediction model and control strategy of solar heat pump heating capacity [D]. Central South University, 2012.) only analyzed and optimized the control strategy of the system for the static water condition, and did not use the dynamic prediction method of load and consider the heat consumption The coupling matching problem of heating, and the control strategy used in the test bench has not been verified in the actual water supply system, so there are limitations

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Solar heat pump hot water system control strategy optimization method based on machine learning
  • Solar heat pump hot water system control strategy optimization method based on machine learning
  • Solar heat pump hot water system control strategy optimization method based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0113] Taking the student dormitory of Sun Yat-sen University Xinhua College in Dongguan City, Guangdong Province as the research object, the built solar heat pump hot water system has been put into operation for a period of time. On the basis of the existing hot water system device, a hot water system data interaction platform is built, and the data is uploaded to the cloud platform database in real time. The hot water system of the student dormitory building in this campus is a parallel solar heat pump hot water system. In order to meet the large demand for hot water, multiple water tanks are arranged in series, and the connection mode of the heat pump and the water tank is parallel. Take one of the student dormitory buildings. The student dormitory building has 13 floors, 50 dormitory rooms on each floor, two of which are single rooms, and the rest are four-person rooms. :00-9:00, 11:30-13:30 at noon, 17:00-24:00 in the evening, the target water temperature for the three pe...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a solar heat pump hot water system control strategy optimization method based on machine learning. The method includes the steps that an air source heat pump thermal model anda solar collector thermal model are constructed; related data are collected; a hot water system model is constructed; load prediction is conducted; and strategy optimization is conducted. According tothe solar heat pump hot water system control strategy optimization method, a thermodynamic model of a system is constructed, an input-output relationship of a heat collection process of an air sourceheat pump and a solar collector is established, a KNN(K-Nearest Neighbor) supervised learning algorithm in machine learning is utilized to realize hourly prediction of a hot water load, a predicted value is used as a demand load value, the established thermal models are utilized to analyze an optimal control strategy and the energy saving rate of the system, thus a theoretical basis is provided for engineers, and it is ensured that the hot water system operates more stably and energy-efficiently.

Description

technical field [0001] The invention relates to the technical field of control of a solar energy-air source heat coupled hot water system, in particular to a method for optimizing a control strategy of a solar heat pump hot water system based on machine learning. Background technique [0002] According to statistics, building energy consumption accounts for about 30% of the country's total energy consumption. Hot water energy consumption is an important aspect of energy consumption in our country. At present, the energy consumption of hot water in commercial buildings in my country accounts for 20-40% of the total energy consumption of buildings, and the energy consumption of hot water in civil buildings accounts for 15-20% of the total energy consumption of buildings. The use of domestic hot water has become an important symbol to measure the degree of social civilization and people's living standards. Therefore, the development and promotion of energy-saving and consumpt...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): F24S20/40F24H4/02F24S50/00F24H9/20G06Q50/06G06Q10/04G06N20/00
CPCF24H4/02F24H9/2007F24S20/40F24S50/00G06Q10/04G06Q50/06G06N20/00Y02E10/40
Inventor 刘雪峰路坦蒋航航王家绪郑宇蓝陈琰叶灿滔
Owner SOUTH CHINA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products