Collaborative optimization control method for central air conditioning system

Abstract

The invention discloses a central air-conditioning system collaborative optimization control method, which relates to the field of energy-saving control, and comprises the following steps: analyzing the operation energy consumption data of each device of a central air-conditioning system, establishing an energy consumption model of each device of the central air-conditioning system, and predicting the energy consumption of each device; according to the central air-conditioning indoor thermal environment influence factors, a thermal environment prediction model is established, and the central air-conditioning system indoor temperature is predicted; and on the basis of the energy consumption of each device and the indoor predicted temperature of the central air-conditioning system, operating parameters of each device of the central air-conditioning system are adjusted by adopting a global optimization control method, so that the central air-conditioning system keeps operating under the working condition of lowest energy consumption, and efficient control over the indoor thermal environment by the central air-conditioning system is realized. The problems that the indoor temperature is unreasonable, comfort is poor, energy consumption is wasted and performance is reduced due to the fact that an existing control method cannot adapt to the difference of real environments are solved.

Description

Technical Field

[0001] The present invention relates to the field of energy-saving control, and in particular to a collaborative optimization control method for a central air-conditioning system. Background Art

[0002] With the continuous increase in global energy consumption and the increasingly serious environmental problems, energy conservation and emission reduction has become a global hot topic. Central air conditioning is a basic equipment used to control and adjust the ambient temperature, relative humidity, air flow velocity, cleanliness and other parameters in the building. It plays a key role in the building and aims to provide people with a comfortable working and living environment. With the increasing requirements of people for the internal environment of buildings, air conditioning systems have gradually become the main source of building energy consumption. In my country, the energy consumption of central air conditioning systems can generally reach more than 40% of the total energy consumption of building operation. Therefore, how to effectively reduce the energy consumption of air conditioning systems and ensure a comfortable indoor environment has become an urgent problem to be solved.

[0003] The energy consumption of central air conditioning system is mainly composed of the energy consumption of air conditioning cold and heat source and the transmission energy consumption of air and water system of air conditioning. At present, the energy-saving research on central air conditioning system mainly focuses on two aspects. One is to save energy in air conditioning cold and heat source, such as the use of new energy and some optimization of cooling and heating control. The other is to study the energy-saving of air and water transmission and distribution system in air conditioning device, such as variable flow, variable air volume, variable supply and return water temperature difference and other technical means. Traditional central air conditioning system usually adopts a relatively single control strategy or relies on empirical rules for control, ignoring the impact of many changing factors such as indoor and outdoor environment, equipment characteristics, user behavior on environment and energy consumption, and cannot accurately optimize the real-time energy demand and indoor comfort. The disadvantage of this control method is that it cannot adapt to the differences in the real environment, which often leads to unreasonable indoor temperature, poor comfort, energy waste and performance degradation. Summary of the invention

[0004] In view of the above-mentioned deficiencies in the prior art, a collaborative optimization control method for a central air-conditioning system provided by the present invention solves the problem that the existing control method cannot adapt to the differences in the real environment, resulting in unreasonable indoor temperature, poor comfort, energy waste and performance degradation.

[0005] In order to achieve the above-mentioned invention object, the technical solution adopted by the present invention is: a collaborative optimization control method for a central air-conditioning system, comprising the following steps:

[0006] S1: Analyze the operating energy consumption data of each device in the central air-conditioning system, establish the energy consumption model of each device in the central air-conditioning system, and predict the energy consumption of each device;

[0007] S2: According to the factors affecting the indoor thermal environment of the central air-conditioning system, a thermal environment prediction model is established to predict the indoor temperature of the central air-conditioning system;

[0008] S3: Based on the energy consumption of each device and the predicted indoor temperature of the central air-conditioning system, a global optimization control method is used to adjust the operating parameters of each device in the central air-conditioning system, so that the central air-conditioning system can operate under the condition of minimum energy consumption, and realize efficient control of the indoor thermal environment by the central air-conditioning system.

[0009] Furthermore, the energy consumption models of the equipment in the central air-conditioning system in S1 include an energy consumption model of a refrigeration unit, an energy consumption model of a variable frequency water pump and an energy consumption model of a terminal fan.

[0010] Furthermore, the refrigeration unit energy consumption model is constructed using a BP neural network, and the initial weights and thresholds of the BP neural network are optimized using an improved gray wolf optimization algorithm. The variables of the input layer of the BP neural network include the current room temperature T i,n , outdoor temperature T am,n , Air conditioning refrigeration main unit water supply temperature T chw and water pump frequency f; the air conditioning refrigeration host is an air-cooled heat pump unit;

[0011] The refrigeration unit energy consumption model P c Build as:

[0012] P c =f(T am,n ,T chw ,T i,n ,f)

[0013] Among them, f(·) is the activation function.

[0014] Furthermore, the variable frequency water pump energy consumption model P pump The polynomial regression fit is constructed as:

[0015]

[0016] Among them, α 3 , α 2 , α 1 and α 0 are coefficients, Enter the power frequency for the pump.

[0017] Furthermore, the terminal fan energy consumption model P fan The polynomial regression fit is constructed as:

[0018] P fan =α 3 D 3 +α 2 D2 +α 1 D+α 0

[0019] Where D is the fan input power frequency.

[0020] Furthermore, the thermal environment prediction model is established in S2, including the following sub-steps:

[0021] S21: Screen the variables of factors affecting the thermal environment in the building and perform preprocessing;

[0022] S22: Optimize the initial weights and thresholds of the BP neural network using the improved grey wolf optimization algorithm;

[0023] S23: Input the preprocessed thermal environment influencing factor variables into the optimized BP neural network to obtain a thermal environment prediction model.

[0024] Furthermore, the S22 includes the following sub-steps:

[0025] S221: Initialize the gray wolf population and set the number of iterations and fitness function;

[0026] S222: According to the set fitness function, the position of the gray wolf population is updated by adopting a dynamic weight update strategy based on the step-length Euclidean distance, and the fitness value of the updated gray wolf population is calculated;

[0027] S223: Determine whether the current iteration meets the set number of iterations. If not, return to step S222. If yes, obtain the optimal individual based on the updated fitness value of the gray wolf population, and use the optimal individual as the initial weight and threshold of the BP neural network for network training, and enter step S224.

[0028] S224: Calculate the output error of the BP neural network and adjust the initial weight and threshold through error back propagation;

[0029] S225: Based on the adjusted initial weights and thresholds, calculate the average error of the BP neural network at the current moment, and determine whether the current iteration meets the preset conditions. If not, return to step S224. If so, output the BP neural network prediction result to complete the optimization of the BP neural network.

[0030] Furthermore, the global optimization control method is used in S3 to adjust the operating parameters of each device of the central air-conditioning system so that the central air-conditioning system operates under the condition with the lowest energy consumption, including the following sub-steps:

[0031] S31: Get the current outdoor temperature T am,n , Heat source intensity R in each room iand the current room temperature T i,n , and set the initial opening degree K of each terminal branch water valve i , each terminal equipment fan gear D i , water pump frequency f and air conditioning refrigeration host water supply temperature T chw ;

[0032] S32: The current outdoor temperature T am,n , Heat source intensity R in each room i 、Current room temperature T i,n , and the initial opening degree K of each terminal branch water valve i , each terminal equipment fan gear D i , water pump frequency f and air conditioning refrigeration host water supply temperature T chw Input into the thermal environment prediction model to obtain the indoor temperature T of each room at the next moment i,n+1 ;

[0033] S33: Determine the indoor temperature T of each room at the next moment i,n+1 Whether they are all within the range of 24℃-26℃, or whether the maximum value of the terminal branch water valve opening is less than or equal to 20. If any condition is met, record the calculated opening K of each terminal branch water valve i , water pump frequency f, fan gear position D of each terminal equipment i and the air conditioning refrigeration host water supply temperature T chw , go to step S42, otherwise go to step S34;

[0034] S34: The number of loop iterations m is increased by 1, and the pump frequency after iteration is f m Record the current pump frequency f and determine whether there is T i,n+1 Greater than or equal to 26°C, if yes, proceed to step S35, otherwise proceed to step S38;

[0035] S35: Determine the current water supply temperature T of the air conditioning refrigeration host chw Is it 5°C? If yes, go to step S37; otherwise, go to step S36;

[0036] S36: Determine whether the current water pump frequency f is 50 Hz. If so, set the current air conditioning refrigeration host water supply temperature T chw Decrease by 1°C and return to step S32; otherwise, increase the current water pump frequency f by 1Hz and return to step S32;

[0037] S37: Determine the opening degree K of the branch water valve at the end of the current room i Is it 100? If yes, go to step S38. Otherwise, set the current room terminal branch water valve opening K i Increase by 1%, and return to step S32;

[0038] S38: Determine whether there is T i,n+1 Less than or equal to 24°C, if yes, go to step S39, otherwise keep the room terminal branch water valve opening K i No change, and return to step S32;

[0039] S39: Determine whether the current water pump frequency f is 30 Hz or the iterated water pump frequency f m Is it greater than the pump frequency f before iteration? m-1 , if any condition is met, proceed to step S40, otherwise reduce the current water pump frequency f by 1 Hz and return to step S32;

[0040] S40: Determine the fan gear position D of the terminal equipment in the room i Is it greater than or equal to 2? If so, set the fan gear of the terminal equipment in the room to D i Reduce by 1 gear and return to step S32, otherwise go to step S41:

[0041] S41: Determine the opening degree K of the water valve at the end branch of the room i Is it 0? If so, keep the water valve opening K at the end of the room. i unchanged, and return to step S32, otherwise the room end branch water valve opening K i Decrease by 1%, and return to step S32;

[0042] S42: Calculate the water valve opening K of each terminal branch of the first group of central air conditioning systems in the current record output i , water pump frequency f, fan gear position D of each terminal equipment i , Air conditioning refrigeration main unit water supply temperature T chw and the total energy consumption value P at the main engine water supply temperature 1 , and determine the currently recorded air conditioning refrigeration host water supply temperature T chw Is it 5°C? If yes, go to step S45; otherwise, go to step S43;

[0043] S43: Record the water supply temperature T of the air conditioning refrigeration host chw Decrease by 1℃ and reset the water valve opening K of each terminal branch i , water pump frequency f, fan gear position D of each terminal equipment i To the initial maximum value, and repeat steps S32 to S41, record the second group of calculated outputs of each terminal branch water valve opening K i，2 , pump frequency f 2 , each terminal equipment fan gear D i，2 , Air conditioning refrigeration main unit water supply temperature T chw，2 and the total energy consumption value P at the main engine water supply temperature 2, and proceed to step S44;

[0044] S44: Determine P 1 Is it less than P 2 If yes, then the water valve opening degree K of each terminal branch of the first group output i , water pump frequency f, fan gear position D of each terminal equipment i , Air conditioning refrigeration main unit water supply temperature T chw and the total energy consumption value P at the main engine water supply temperature 1 Set as the opening degree K of each terminal branch water valve of the second group output i，2 , pump frequency f 2 , each terminal equipment fan gear D i，2 , Air conditioning refrigeration main unit water supply temperature T chw，2 and the total energy consumption value P at the main engine water supply temperature 2 , and return to step S42, otherwise go to step S45;

[0045] S45: Output P 1 The corresponding terminal branch water valve opening K i , water pump frequency f, fan gear position D of each terminal equipment i , Air conditioning refrigeration main unit water supply temperature T chw And adjust the equipment parameters of the central air-conditioning system to the output values, completing the global optimization control of the operating parameters of each device in the central air-conditioning system.

[0046] The beneficial effects of the present invention are:

[0047] In order to realize energy-saving control of the central air-conditioning system, the present invention studies the energy consumption characteristics of each device in the air-conditioning system. By analyzing the operating characteristics of the air-conditioning equipment, the characteristic data of the equipment energy consumption and the influence of various factors on the system energy consumption are determined. Under the premise of meeting the equipment performance requirements, the equipment operating conditions with the lowest energy consumption can be found.

[0048] The present invention can calculate and set various equipment parameters that can keep the indoor thermal environment comfortable at all times through the global optimization control method when the indoor and outdoor environments change, so that the central air-conditioning system always operates under the condition of minimum energy consumption, and effectively realize the global coordinated optimization control of the central air-conditioning system equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 The present invention is a flow chart of a collaborative optimization control method for a central air-conditioning system. DETAILED DESCRIPTION

[0050] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0051] like Figure 1As shown, a collaborative optimization control method for a central air conditioning system includes the following steps:

[0052] S1: Analyze the operating energy consumption data of each device in the central air-conditioning system, establish the energy consumption model of each device in the central air-conditioning system, and predict the energy consumption of each device;

[0053] S2: According to the factors affecting the indoor thermal environment of the central air-conditioning system, a thermal environment prediction model is established to predict the indoor temperature of the central air-conditioning system;

[0054] S3: Based on the energy consumption of each device and the predicted indoor temperature of the central air-conditioning system, a global optimization control method is used to adjust the operating parameters of each device in the central air-conditioning system, so that the central air-conditioning system can operate under the condition of minimum energy consumption, and realize efficient control of the indoor thermal environment by the central air-conditioning system.

[0055] The energy consumption models of the central air-conditioning system equipment in S1 include a refrigeration unit energy consumption model, a variable frequency water pump energy consumption model and a terminal fan energy consumption model.

[0056] The present invention uses BP neural network to construct a data-driven refrigeration unit energy consumption model. First, SPSS software is used to perform Spearman correlation analysis on the energy consumption P of the air-conditioning refrigeration host using 700 sets of experimental working condition data. The refrigeration host is an air-cooled heat pump unit. The variables for correlation calculation include the temperature and humidity T of each room at the current moment. i,n , Rh i,n , outdoor temperature and humidity T am,n , Rh am,n , main engine water supply temperature T chw , pump frequency f, opening of each terminal valve K i , each terminal fan gear position D i and the heat source intensity R in each room i According to the calculation results of the correlation analysis, the variables with weaker influence are excluded, and the remaining variables are ranked from the largest to the smallest in terms of their correlation with the energy consumption P of the refrigeration host: T am,n , T chw , T i,n and f. Therefore, the following refrigeration unit energy consumption model can be constructed.

[0057] The energy consumption model of the refrigeration unit is constructed using a BP neural network, and the initial weights and thresholds of the BP neural network are optimized using an improved gray wolf optimization algorithm. The variables of the input layer of the BP neural network include the current room temperature T i,n , outdoor temperature T am,n , Air conditioning refrigeration main unit water supply temperature T chw and water pump frequency f; the air conditioning refrigeration host is an air-cooled heat pump unit;

[0058] The refrigeration unit energy consumption model Pc Build as:

[0059] P c =f(T am,n ,T chw ,T i,n ,f)

[0060] Among them, f(·) is the activation function.

[0061] For variable frequency water pumps, the power and flow, head and speed satisfy the similarity law shown in the following formula:

[0062]

[0063] Where, P is the working power, P 0 is the rated power, Q is the actual flow rate of the pump, Q 0 is the actual working head of the water pump, n is the working speed, n 0 is the rated speed.

[0064] It can be seen that there is a proportional relationship between the power of the water pump and the square of the water pump head, and between the water pump flow and the cube of the speed. The speed of the water pump and the power frequency of the input water pump have the following relationship:

[0065]

[0066] in, is the input power frequency of the pump, and c is the number of motor poles.

[0067] For existing equipment, the number of motor pole pairs is generally a fixed value. From the above formula, we can see that there is also a proportional relationship between the pump power P and the cube of the pump frequency f. Therefore, for the energy consumption of the pump, a black box model or a polynomial regression model can be established:

[0068]

[0069] The variable frequency water pump energy consumption model P pump The polynomial regression fit is constructed as:

[0070]

[0071] Among them, α 3 , α 2 , α 1 and α 0 are coefficients, Enter the power frequency for the pump.

[0072] The terminal fan energy consumption model P fan The polynomial regression fit is constructed as:

[0073] P fan =α 3 D 3 +α 2 D 2 +α 1 D+α 0

[0074] Where D is the fan input power frequency.

[0075] By establishing an improved GWO-BP neural network model for the energy consumption of the refrigeration host and a polynomial regression model for the energy consumption of the water pump and the terminal fan, the calculation cost is reduced and the calculation speed is improved while ensuring a high prediction accuracy, which can provide a reference for the energy consumption of equipment for the energy-saving optimization control of the central air-conditioning system.

[0076] The thermal environment prediction model is established in S2, including the following steps:

[0077] S21: Screen the variables of factors affecting the thermal environment in the building and perform preprocessing;

[0078] In this embodiment, the variables of thermal environment influencing factors include outdoor meteorological data (outdoor temperature and outdoor humidity), indoor thermal disturbance data (heat dissipation of personnel, lighting and office equipment), central air-conditioning operation parameter data (water supply temperature of cold and hot source equipment, water supply flow and air volume of room terminal equipment) and current indoor thermal environment data (indoor temperature and humidity);

[0079] S22: Optimize the initial weights and thresholds of the BP neural network using the improved grey wolf optimization algorithm;

[0080] S23: Input the preprocessed thermal environment influencing factor variables into the optimized BP neural network to obtain a thermal environment prediction model.

[0081] The S22 includes the following sub-steps:

[0082] S221: Initialize the gray wolf population and set the number of iterations and fitness function;

[0083] In this embodiment, Circle chaotic mapping is used to initialize the gray wolf population, and the formula is:

[0084]

[0085] Among them, x i+1 is the chaotic value of the i+1th iteration, x i is the chaotic value of the i-th iteration, mod(·) is the modulus operation;

[0086] S222: According to the set fitness function, the position of the gray wolf population is updated by adopting a dynamic weight update strategy based on the step-length Euclidean distance, and the fitness value of the updated gray wolf population is calculated;

[0087] The dynamic weight update strategy based on the step length Euclidean distance is:

[0088]

[0089] Among them, ω 1 ,ω 2 and ω 3 For different weights, X 1 , X 2 and X 3 are different individuals, X(·) is the step length Euclidean distance, and t is the current iteration number;

[0090] The convergence factor α of the improved grey wolf optimization algorithm is:

[0091]

[0092] Where T is the maximum number of iterations;

[0093] S223: Determine whether the current iteration meets the set number of iterations. If not, return to step S222. If yes, obtain the optimal individual based on the updated fitness value of the gray wolf population, and use the optimal individual as the initial weight and threshold of the BP neural network for network training, and enter step S224.

[0094] S224: Calculate the output error of the BP neural network and adjust the initial weight and threshold through error back propagation;

[0095] S225: Based on the adjusted initial weights and thresholds, calculate the average error of the BP neural network at the current moment, and determine whether the current iteration meets the preset conditions. If not, return to step S224. If so, output the BP neural network prediction result to complete the optimization of the BP neural network.

[0096] In S3, the global optimization control method is used to adjust the operating parameters of each device of the central air-conditioning system so that the central air-conditioning system operates under the condition of minimum energy consumption, including the following sub-steps:

[0097] S31: Get the current outdoor temperature T am,n , Heat source intensity R in each room i and the current room temperature T i,n , and set the initial opening degree K of each terminal branch water valve i , each terminal equipment fan gear D i , water pump frequency f and air conditioning refrigeration host water supply temperature Tchw ;

[0098] S32: The current outdoor temperature T am,n , Heat source intensity R in each room i 、Current room temperature T i,n , and the initial opening degree K of each terminal branch water valve i , each terminal equipment fan gear D i , water pump frequency f and air conditioning refrigeration host water supply temperature T chw Input into the thermal environment prediction model to obtain the indoor temperature T of each room at the next moment i,n+1 ;

[0099] S33: Determine the indoor temperature T of each room at the next moment i,n+1 Whether they are all within the range of 24℃-26℃, or whether the maximum value of the terminal branch water valve opening is less than or equal to 20. If any condition is met, record the calculated opening K of each terminal branch water valve i , water pump frequency f, fan gear position D of each terminal equipment i and the air conditioning refrigeration host water supply temperature T chw , go to step S42, otherwise go to step S34;

[0100] S34: The number of loop iterations m is increased by 1, and the pump frequency after iteration is f m Record the current pump frequency f and determine whether there is T i,n+1 Greater than or equal to 26°C, if yes, proceed to step S35, otherwise proceed to step S38;

[0101] S35: Determine the current water supply temperature T of the air conditioning refrigeration host chw Is it 5°C? If yes, go to step S37; otherwise, go to step S36;

[0102] S36: Determine whether the current water pump frequency f is 50 Hz. If so, set the current air conditioning refrigeration host water supply temperature T chw Decrease by 1°C and return to step S32; otherwise, increase the current water pump frequency f by 1Hz and return to step S32;

[0103] S37: Determine the opening degree K of the branch water valve at the end of the current room i Is it 100? If yes, go to step S38. Otherwise, set the current room terminal branch water valve opening K i Increase by 1%, and return to step S32;

[0104] S38: Determine whether there is T i,n+1 Less than or equal to 24°C, if yes, go to step S39, otherwise keep the room terminal branch water valve opening K iNo change, and return to step S32;

[0105] S39: Determine whether the current water pump frequency f is 30 Hz or the iterated water pump frequency f m Is it greater than the pump frequency f before iteration? m-1 , if any condition is met, proceed to step S40, otherwise reduce the current water pump frequency f by 1 Hz and return to step S32;

[0106] S40: Determine the fan gear position D of the terminal equipment in the room i Is it greater than or equal to 2? If so, set the fan gear of the terminal equipment in the room to D i Reduce by 1 gear and return to step S32, otherwise go to step S41:

[0107] S41: Determine the opening degree K of the water valve at the end branch of the room i Is it 0? If so, keep the water valve opening K at the end of the room. i unchanged, and return to step S32, otherwise the room end branch water valve opening K i Decrease by 1%, and return to step S32;

[0108] S42: Calculate the water valve opening K of each terminal branch of the first group of central air conditioning systems in the current record output i , water pump frequency f, fan gear position D of each terminal equipment i , Air conditioning refrigeration main unit water supply temperature T chw and the total energy consumption value P at the main engine water supply temperature 1 , and determine the currently recorded air conditioning refrigeration host water supply temperature T chw Is it 5°C? If yes, go to step S45; otherwise, go to step S43;

[0109] S43: Record the water supply temperature T of the air conditioning refrigeration host chw Decrease by 1℃ and reset the water valve opening K of each terminal branch i , water pump frequency f, fan gear position D of each terminal equipment i To the initial maximum value, and repeat steps S32 to S41, record the second group of calculated outputs of each terminal branch water valve opening K i，2 , pump frequency f 2 , each terminal equipment fan gear D i，2 , Air conditioning refrigeration main unit water supply temperature T chw，2 and the total energy consumption value P at the main engine water supply temperature 2 , and proceed to step S44;

[0110] S44: Determine P 1 Is it less than P 2 If yes, then the water valve opening degree K of each terminal branch of the first group outputi , water pump frequency f, fan gear position D of each terminal equipment i , Air conditioning refrigeration main unit water supply temperature T chw and the total energy consumption value P at the main engine water supply temperature 1 Set as the opening degree K of each terminal branch water valve of the second group output i，2 , pump frequency f 2 , each terminal equipment fan gear D i，2 , Air conditioning refrigeration main unit water supply temperature T chw，2 and the total energy consumption value P at the main engine water supply temperature 2 , and return to step S42, otherwise go to step S45;

[0111] S45: Output P 1 The corresponding terminal branch water valve opening K i , water pump frequency f, fan gear position D of each terminal equipment i , Air conditioning refrigeration main unit water supply temperature T chw And adjust the equipment parameters of the central air-conditioning system to the output values, completing the global optimization control of the operating parameters of each device in the central air-conditioning system.

[0112] Compared with adjusting the water flow rate, adjusting the terminal air volume to meet the load requirements of different rooms is more convenient and has a more obvious control effect. It can also save the energy consumption of the terminal fan. Therefore, in order to coordinate the various devices of the central air-conditioning system to achieve global optimization control, it is necessary to jointly regulate the water supply temperature, water pump frequency, terminal fan and terminal water valve of the central air-conditioning system. The regulation strategy is to first adjust the water supply temperature of the refrigeration host to ensure that the chilled water temperature can meet the refrigeration requirements of each room, and then adjust the overall flow of the water system through the water pump, and then adjust the air volume of each room through the terminal fan, and finally adjust the flow of each room branch through the terminal water valve. This control method combines the indoor thermal environment prediction model with the energy consumption model of each device in the system, ensuring that the thermal environment always remains comfortable while allowing the air-conditioning system to operate in the lowest energy consumption condition.

[0113] Those skilled in the art will appreciate that the embodiments described herein are intended to help readers understand the principles of the present invention, and should be understood that the protection scope of the present invention is not limited to such specific statements and embodiments. Those skilled in the art can make various other specific variations and combinations that do not deviate from the essence of the present invention based on the technical revelations disclosed by the present invention, and these variations and combinations are still within the protection scope of the invention.

Claims

1. A collaborative optimization control method for a central air conditioning system, characterized in that: The following steps are involved: S1: Analyze the operating energy consumption data of each device in the central air-conditioning system, establish the energy consumption model of each device in the central air-conditioning system, and predict the energy consumption of each device; S2: According to the factors affecting the indoor thermal environment of the central air-conditioning system, a thermal environment prediction model is established to predict the indoor temperature of the central air-conditioning system; S3: Based on the energy consumption of each device and the predicted indoor temperature of the central air-conditioning system, a global optimization control method is used to adjust the operating parameters of each device in the central air-conditioning system, so that the central air-conditioning system can operate under the condition of minimum energy consumption, and realize efficient control of the indoor thermal environment by the central air-conditioning system.

2. A collaborative optimization control method for a central air conditioning system according to claim 1, characterized in that: The energy consumption models of the central air-conditioning system equipment in S1 include a refrigeration unit energy consumption model, a variable frequency water pump energy consumption model and a terminal fan energy consumption model.

3. A collaborative optimization control method for a central air conditioning system according to claim 2, characterized in that: The energy consumption model of the refrigeration unit is constructed using a BP neural network, and the initial weights and thresholds of the BP neural network are optimized using an improved gray wolf optimization algorithm. The variables of the input layer of the BP neural network include the current room temperature T i,n , outdoor temperature T am,n , Air conditioning refrigeration host water supply temperature T chw and water pump frequency f; the air conditioning refrigeration host is an air-cooled heat pump unit; The refrigeration unit energy consumption model P c Build as: P c =f(T am,n ,T chw ,T i,n ,f) Among them, f(·) is the activation function.

4. A collaborative optimization control method for a central air conditioning system according to claim 3, characterized in that: The variable frequency water pump energy consumption model P pump The polynomial regression fit is constructed as: Among them, α3, α2, α1 and α0 are coefficients, Enter the power frequency for the pump.

5. A collaborative optimization control method for a central air conditioning system according to claim 4, characterized in that: The terminal fan energy consumption model P fan The polynomial regression fit is constructed as: P fan =α3D 3 +α2D 2 +α1D+α0 Where D is the fan input power frequency.

6. A collaborative optimization control method for a central air conditioning system according to claim 1, characterized in that: The thermal environment prediction model is established in S2, including the following steps: S21: Screen the variables of factors affecting the thermal environment in the building and perform preprocessing; S22: Optimize the initial weights and thresholds of the BP neural network using the improved grey wolf optimization algorithm; S23: Input the preprocessed thermal environment influencing factor variables into the optimized BP neural network to obtain a thermal environment prediction model.

7. A collaborative optimization control method for a central air conditioning system according to claim 6, characterized in that: The S22 includes the following sub-steps: S221: Initialize the gray wolf population and set the number of iterations and fitness function; S222: According to the set fitness function, the position of the gray wolf population is updated by adopting a dynamic weight update strategy based on the step-length Euclidean distance, and the fitness value of the updated gray wolf population is calculated; S223: Determine whether the current iteration meets the set number of iterations. If not, return to step S222. If yes, obtain the optimal individual based on the updated fitness value of the gray wolf population, and use the optimal individual as the initial weight and threshold of the BP neural network for network training, and enter step S224. S224: Calculate the output error of the BP neural network and adjust the initial weight and threshold through error back propagation; S225: Based on the adjusted initial weights and thresholds, calculate the average error of the BP neural network at the current moment, and determine whether the current iteration meets the preset conditions. If not, return to step S224. If so, output the BP neural network prediction result to complete the optimization of the BP neural network.

8. A collaborative optimization control method for a central air conditioning system according to claim 1, characterized in that: In S3, the global optimization control method is used to adjust the operating parameters of each device of the central air-conditioning system so that the central air-conditioning system operates under the condition of minimum energy consumption, including the following sub-steps: S31: Get the current outdoor temperature T am,n , Heat source intensity R in each room i and the current room temperature T i,n , and set the initial opening degree K of each terminal branch water valve i , each terminal equipment fan gear D i , water pump frequency f and air conditioning refrigeration host water supply temperature T chw ; S32: The current outdoor temperature T am,n , Heat source intensity R in each room i 、Current room temperature T i,n , and the initial opening degree K of each terminal branch water valve i , each terminal equipment fan gear D i , water pump frequency f and air conditioning refrigeration host water supply temperature T chw Input into the thermal environment prediction model to obtain the indoor temperature T of each room at the next moment i,n+1 ; S33: Determine the indoor temperature T of each room at the next moment i,n+1 Whether they are all within the range of 24℃-26℃, or whether the maximum value of the terminal branch water valve opening is less than or equal to 20. If any condition is met, record the calculated opening K of each terminal branch water valve i , water pump frequency f, fan gear position D of each terminal equipment i and the air conditioning refrigeration host water supply temperature T chw , go to step S42, otherwise go to step S34; S34: The number of loop iterations m is increased by 1, and the pump frequency after iteration is f m Record the current pump frequency f and determine whether there is T i,n+1 Greater than or equal to 26°C, if yes, proceed to step S35, otherwise proceed to step S38; S35: Determine the current water supply temperature T of the air conditioning refrigeration host chw Is it 5°C? If yes, go to step S37; otherwise, go to step S36; S36: Determine whether the current water pump frequency f is 50 Hz. If so, set the current air conditioning refrigeration host water supply temperature T chw Decrease by 1°C and return to step S32; otherwise, increase the current water pump frequency f by 1Hz and return to step S32; S37: Determine the opening degree K of the branch water valve at the end of the current room i Is it 100? If yes, go to step S38. Otherwise, set the current room terminal branch water valve opening K i Increase by 1%, and return to step S32; S38: Determine whether there is T i,n+1 Less than or equal to 24°C, if yes, go to step S39, otherwise keep the room terminal branch water valve opening K i No change, and return to step S32; S39: Determine whether the current water pump frequency f is 30 Hz or the iterated water pump frequency f m Is it greater than the pump frequency f before iteration? m-1 , if any condition is met, proceed to step S40, otherwise reduce the current water pump frequency f by 1 Hz and return to step S32; S40: Determine the fan gear position D of the terminal equipment in the room i Is it greater than or equal to 2? If so, set the fan gear of the terminal equipment in the room to D i Reduce by 1 gear and return to step S32, otherwise go to step S41: S41: Determine the opening degree K of the water valve at the end branch of the room i Is it 0? If so, keep the water valve opening K at the end of the room. i unchanged, and return to step S32, otherwise the room end branch water valve opening K i Decrease by 1%, and return to step S32; S42: Calculate the water valve opening K of each terminal branch of the first group of central air conditioning systems in the current record output i , water pump frequency f, fan gear position D of each terminal equipment i , Air conditioning refrigeration host water supply temperature T chw and the total energy consumption value P1 at the main unit water supply temperature, and determine the currently recorded air conditioning refrigeration main unit water supply temperature T chw Is it 5°C? If yes, go to step S45; otherwise, go to step S43; S43: Record the water supply temperature T of the air conditioning refrigeration host chw Decrease by 1℃ and reset the water valve opening K of each terminal branch i , water pump frequency f, fan gear position D of each terminal equipment i To the initial maximum value, and repeat steps S32 to S41, record the second group of calculated outputs of each terminal branch water valve opening K i，2 , water pump frequency f2, fan gear position D of each terminal equipment i，2 , Air conditioning refrigeration host water supply temperature T chw，2 and the total energy consumption value P2 at the main engine water supply temperature, and proceed to step S44; S44: Determine whether P1 is less than P2. If so, adjust the opening degree K of each terminal branch water valve output by the first group. i , water pump frequency f, fan gear position D of each terminal equipment i , Air conditioning refrigeration host water supply temperature T chw The total energy consumption value P1 at the main engine water supply temperature is set as the opening degree K of each terminal branch water valve of the second group output i，2 , water pump frequency f2, fan gear position D of each terminal equipment i，2 , Air conditioning refrigeration host water supply temperature T chw，2 and the total energy consumption value P2 at the main engine water supply temperature, and return to step S42, otherwise go to step S45; S45: Output P1 corresponding to the terminal branch water valve opening K i , water pump frequency f, fan gear position D of each terminal equipment i , Air conditioning refrigeration host water supply temperature T chw And adjust the equipment parameters of the central air-conditioning system to the output values, completing the global optimization control of the operating parameters of each device in the central air-conditioning system.

Images