Water chilling unit combined operation optimal control method based on model prediction

Abstract

The invention provides a GRNN-based water chilling unit energy efficiency model modeling method and a water chilling unit group-control method based on cold load prediction and a water chilling unit energy efficiency model, and belongs to the field of water chilling unit energy saving. The water chilling unit energy efficiency model is established by using a GRNN technology and actual operating data of a refrigeration system, so that the energy consumption of the water chilling unit under different operating conditions can be predicted quickly and accurately. The operating unit number and theload rate distribution of the water chilling unit are optimized in real time by using the cooling load prediction data and the water chilling unit energy efficiency model with a goal of minimum systemenergy consumption, so that the operation energy efficiency of the refrigeration system is effectively improved.

Description

technical field [0001] The invention belongs to the field of energy-saving control of refrigeration systems, and in particular relates to an optimal control method for combined operation of chillers based on model prediction. Background technique [0002] The chiller is the core component of the central air-conditioning system, and its operating energy consumption accounts for more than 40% of the total energy consumption of the central air-conditioning. For a system in which multiple chillers are jointly operated in a large building, the energy efficiency of the chiller is different under different load rates. A reasonable chiller group control method is adopted to keep the chiller running as efficiently as possible and maximize the operating efficiency of the refrigeration system. It is an important technical way to realize energy saving of centralized air conditioning system. [0003] The traditional chiller group control adopts the feedback control method, generally by ...

AI Technical Summary

Problems solved by technology

Although the traditional chiller group control method basically meets the cooling load requirements of the air conditioner, the operation adjustment lags behind and does not consider the characteristics of the energy efficiency of the chiller operating with the load rate and operating conditions, which seriously restricts the energy-saving operation of the refrigeration system.

[0004] Invention patent document CN110222398A discloses an artificial intelligence control method for chillers, including: establishing a cooling load prediction model; acquiring and collecting historical weather and production data of chillers within a certain period of time as first training data; The cooling load forecasting model is trained by the first machine learning algorithm; the trained cooling load forecasting model is input with future weather forecast data and production plan, so that the cooling load forecasting model outputs the cooling load within a predetermined time load demand; also includes: establishing a cooling machine model; obtaining and collecting historical data of the cooling machine within a certain period of time as the second training data; using the second training data to train the cooling machine model through the second machine learning algorithm; The cooling machine model inputs the cooling load demand within the predetermined time output by the cooling load prediction model as input data to output the cooling load demand data after the combination optimization of the cooling load prediction model and the cooling machine model; although the invention The established cooling load prediction model is trained through historical weather and production data to solve the technical problem that it is currently impossible to predict the future cooling load of the chiller, so that the chiller can be adjusted according to the feedback of the end working conditions without the intervention of on-site personnel. The cooling load can be accurately predicted, but the invention does not consider the energy saving problem, especially the optimal energy saving method based on the combined operation of chillers predicted by the model

Although the invention focuses on prediction and energy saving, its operating efficiency and energy saving effect are limited and need to be further improved

Images