Self-adaptive deep learning optimization energy-saving control algorithm for central air-conditioning cold supply system

A centralized air-conditioning and deep learning technology, applied in the field of air-conditioning, can solve problems such as unfavorable applications, achieve the effects of saving operation and maintenance costs, improving management efficiency, and optimizing energy-saving effects

CN114543273AActive Publication Date: 2022-05-27SHANGHAI JIAO TONG UNIV +1
9 Cites 1 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2022-05-27

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a self-adaptive deep learning optimization energy-saving control algorithm for a central air-conditioning cold supply system. The algorithm comprises a power supply, a server data platform, a data connection port, a plurality of temperature sensors, a plurality of water flow sensors and a plurality of electric power sensors. According to the method, when the data volume is small, the physical model is utilized, global total energy consumption is used as a target function for optimization, a bad solution is eliminated and a new solution is regenerated in each iteration, and a high-dimensional optimization model is solved, so that the optimization calculation efficiency is effectively improved, and effective optimization control parameters are obtained more quickly and better; and a database is updated and a data model is trained by using real-time data, so that the problem that a physical model is not applicable under extreme working conditions is solved, the precision of an energy consumption model or a performance model of system power equipment is improved, and the optimization model is more accurate and effective. The network technology is adopted, cloud storage and remote transmission of data are achieved, the management efficiency of the cold supply system is greatly improved, and the system management cost is saved.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the field of air conditioning, in particular to an adaptive deep learning optimization energy-saving control algorithm for a central air conditioning cooling system. Background technique

[0002] The cooling system has been widely used and paid attention to in the field of building air conditioning due to its significant effect on saving the total energy consumption of the building due to excessive energy consumption. The control of cooling system currently mainly adopts two control methods: (1) fixed control parameters, including chilled water supply temperature or return water temperature, chilled water pump frequency, cooling water pump frequency and cooling tower fan frequency; (2) based on expert strategies, More energy-saving control parameters are given by professionals according to the outdoor environmental conditions. The modeling method of cooling system mainly adopts two methods: physical model and data-driven mathe...

Examples

Embodiment

[0062] Example: as figure 1 As shown, the embodiment of the present invention includes an adaptive deep learning optimized energy-saving control algorithm for a central air conditioner cooling system, and the algorithm is implemented by a control device of the central air conditioner. The control device used in the algorithm of this embodiment includes: a server data platform for implementing the adaptive deep learning optimization energy-saving control method of the central air conditioning and cooling system of the present invention; a plurality of temperature sensors, water flow sensors and electric power sensors, respectively, through data The connection port is connected in communication with the server data platform. The device specifically includes:

[0063] Data transfer module (DTU: Data Transfer Unit) 1, data filter module 2, data I / O interface input end 31, data I / O interface output end 32, RS485 communication interface 4, 4G / 5G communication interface 5, WAN commu...