Intelligent building heating ventilation air conditioner energy consumption energy-saving control system based on artificial intelligence

Abstract

The invention relates to the technical field of air conditioner energy-saving control, in particular to an intelligent building heating ventilation air conditioner energy consumption energy-saving control system based on artificial intelligence. Comprising a refrigerator modeling unit, a total energy consumption modeling unit, a target modeling unit, a constraint modeling unit, an energy consumption optimization modeling unit, a model solving unit, an air conditioner control unit, a state prediction unit and an energy-saving control unit, and further comprises a fan modeling unit, and the fan modeling unit is used for constructing a fan air outlet model of the target heating ventilation air conditioner based on the indoor cooling load of the intelligent building, the indoor set temperature of the intelligent building and the air supply temperature. According to the method, the fan modeling unit, the chilled water pump modeling unit and the refrigerator modeling unit are utilized, and the energy consumption of the heating ventilation air conditioning system is accurately predicted and controlled by establishing and optimizing the model, so that accurate control on the energy consumption of each component of the system is ensured, and the energy efficiency is improved to the maximum extent.

Description

Technical Field

[0001] The present invention relates to the technical field of air conditioning energy-saving control, and in particular to an energy-saving control system for heating, ventilation and air conditioning in a smart building based on artificial intelligence. Background Art

[0002] Smart building refers to a type of building that uses advanced information technology (such as the Internet of Things, sensors, data analysis, artificial intelligence, etc.) and automated control technology to manage and optimize the operation and maintenance of building facilities in order to improve the operating efficiency, comfort, safety and sustainability of the building.

[0003] Traditional systems usually lack accurate energy consumption modeling and optimization capabilities, and therefore cannot achieve precise control of the energy consumption of various system components (such as fans, chilled water pumps, and refrigerators). As a result, in actual operation, energy consumption is often not effectively minimized, resulting in low energy efficiency and energy waste; and traditional systems are usually unable to monitor and predict the operating status of the HVAC system in real time, and lack prediction-based intelligent control capabilities, which makes it difficult for the system to dynamically adjust during operation to adapt to environmental changes and fluctuations in energy consumption demand, thereby affecting the stability and efficiency of the system; and traditional systems often use simple adjustment strategies and fixed control parameters for energy consumption optimization, lacking the support of complex optimization algorithms, which results in the system being unable to automatically adjust to achieve optimal energy efficiency under different operating conditions, missing out on opportunities for energy saving and cost reduction. Summary of the invention

[0004] The purpose of the present invention is to address the problems existing in the background technology and propose an energy-saving control system for HVAC in smart buildings based on artificial intelligence.

[0005] The technical solution of the present invention: an energy-saving control system for heating, ventilation and air conditioning in a smart building based on artificial intelligence, including a refrigerator modeling unit, a total energy consumption modeling unit, a target modeling unit, a constraint modeling unit, an energy consumption optimization modeling unit, a model solving unit, an air conditioning control unit, a state prediction unit and an energy-saving control unit, and also includes:

[0006] A fan modeling unit, the fan modeling unit is used to build a fan outlet model of a target HVAC based on the indoor cooling load of the smart building, the indoor set temperature of the smart building and the supply air temperature, obtain the supply air flow of the target HVAC based on the fan outlet model of the target HVAC, build a fan energy consumption model of the target HVAC based on the supply air flow of the target HVAC, obtain the fan energy consumption of the target HVAC based on the fan energy consumption model of the target HVAC, transmit the supply air flow of the target HVAC to a chilled water pump modeling unit, and transmit the fan energy consumption of the target HVAC to a total energy consumption modeling unit;

[0007] A chilled water pump modeling unit, which receives the supply air flow of the target HVAC transmitted by the fan modeling unit, and is used to build a chilled water pump freezing model of the target HVAC based on the supply air temperature, the condenser inlet air temperature, the chilled water supply and return water temperature difference and the supply air flow of the target HVAC, obtain the chilled water flow of the target HVAC based on the chilled water pump freezing model of the target HVAC, build an energy consumption model of the target HVAC based on the chilled water flow of the target HVAC, obtain the chilled water pump energy consumption of the target HVAC based on the chilled water flow of the target HVAC, transmit the chilled water flow of the target HVAC to the refrigerator modeling unit, and transmit the chilled water pump energy consumption of the target HVAC to the total energy consumption modeling unit.

[0008] Preferably, the refrigeration machine modeling unit receives the chilled water flow rate of the target HVAC transmitted by the chilled water pump modeling unit, and is used to construct a refrigeration machine performance model of the target HVAC based on the chilled water outlet temperature, the cooling water return temperature, the chilled water supply and return temperature difference and the chilled water flow rate of the target HVAC, obtain the refrigeration machine performance curve of the target HVAC based on the refrigeration machine performance model of the target HVAC, construct the refrigeration machine energy consumption model of the target HVAC based on the refrigeration machine performance curve of the target HVAC, obtain the refrigeration machine energy consumption of the target HVAC based on the refrigeration machine energy consumption model of the target HVAC, and transmit the refrigeration machine energy consumption of the target HVAC to the total energy consumption modeling unit.

[0009] Preferably, the total energy consumption modeling unit receives the fan energy consumption of the target HVAC transmitted by the fan modeling unit, the chilled water pump energy consumption of the target HVAC transmitted by the chilled water pump modeling unit, and the refrigerator energy consumption of the target HVAC transmitted by the refrigerator modeling unit, and is used to construct a total power model of the target HVAC based on the fan energy consumption, chilled water pump energy consumption and refrigerator energy consumption of the target HVAC, obtain the total power of the target HVAC based on the total power model of the target HVAC, and transmit the total power of the target HVAC to the target modeling unit.

[0010] Preferably, the target modeling unit receives the total power of the target HVAC transmitted by the total energy consumption modeling unit, and constructs a target optimization function to minimize the total power of the target HVAC, and transmits the target optimization function to the energy consumption optimization modeling unit.

[0011] Preferably, the constraint modeling unit is used to construct the constraint conditions of the target HVAC based on the operating parameters of the target HVAC, and transmit the constraint conditions of the target HVAC to the energy consumption optimization modeling unit.

[0012] Preferably, the energy consumption optimization modeling unit receives the target optimization function transmitted by the target modeling unit and the target HVAC constraints transmitted by the constraint modeling unit, and is used to construct an energy consumption optimization model based on the target optimization function and the target HVAC constraints, and transmits the energy consumption optimization model to the model solving unit.

[0013] Preferably, the model solving unit receives the energy consumption optimization model transmitted by the energy consumption optimization modeling unit, and is used to solve the energy consumption optimization model through an optimization algorithm to obtain the first control parameter of the target HVAC, and transmits the first control parameter of the target HVAC to the air conditioning control unit.

[0014] Preferably, the air-conditioning control unit receives the first control parameter of the target HVAC transmitted by the model solving unit, and is used to control the target HVAC based on the first control parameter of the target HVAC, and monitor the operating status data of the target HVAC in real time to obtain the operating status data of the target HVAC, wherein the operating status data includes the high-pressure pressure of the compressor, the low-pressure pressure of the compressor, the actual frequency of the frequency conversion device, the output wind speed of the outdoor fan, the opening degree of the two expansion valves of the indoor unit, the current indoor temperature of the smart building and the energy efficiency ratio of the current target HVAC, and the operating status data of the target HVAC is transmitted to the state prediction unit.

[0015] Preferably, the state prediction unit receives the operating status data of the target HVAC transmitted by the air-conditioning control unit, and is used to input the operating status data of the target HVAC into a trained state prediction model, and outputs the operating status data of the target HVAC at the next preset time through the trained state prediction model. The state prediction model adopts a neural network model to transmit the operating status data of the target HVAC at the next preset time to the energy-saving control unit.

[0016] Preferably, the energy-saving control unit receives the indoor temperature and energy efficiency ratio of the target HVAC at the next preset time transmitted by the state prediction unit, and is used to construct a first intelligent agent of the target HVAC outdoor unit and a second intelligent agent of the target HVAC indoor unit through reinforcement learning based on the indoor temperature and energy efficiency ratio of the target HVAC at the next preset time, solve the first intelligent agent and the second intelligent agent to obtain the second control parameters of the target HVAC, and control the target HVAC based on the second control parameters of the target HVAC.

[0017] Preferably, the fan outlet model of the target HVAC is as follows:

[0018]

[0019] Among them, m a Indicates the actual air flow rate of the fan, Q S represents the indoor cooling load of the smart building, T N Indicates the indoor set temperature of the smart building, T S Indicates the supply air temperature;

[0020] The fan energy consumption model of the target HVAC is as follows:

[0021]

[0022] Among them, P fan represents the actual power of the fan, a1, b1, c1, d1 and e1 represent the fan characteristic fitting coefficients, α fan represents the total efficiency of the fan, ρ air represents the air density, β a represents the fan main load factor, and m a-L Indicates the rated air flow rate of the fan;

[0023] The target HVAC chilled water pump refrigeration model is as follows:

[0024]

[0025] Among them, m e represents the actual chilled water flow of the chilled water pump, T1 represents the inlet air temperature of the cooler, T2 represents the outlet air temperature of the cooler, C p represents the specific heat of water, ΔT e Indicates the temperature difference between the supply and return water of chilled water;

[0026] The energy consumption model of the target HVAC chilled water pump is as follows:

[0027]

[0028] Among them, P e represents the actual power of the chilled water pump, a2, b2, c2 and d2 represent the chilled water pump characteristic fitting coefficients, β e represents the main load factor of the chilled water pump, and m e-L Indicates the rated chilled water flow rate of the chilled water pump, P e-L Indicates the rated power of the chilled water pump.

[0029] Preferably, the target HVAC refrigerator performance model is as follows:

[0030]

[0031] Among them, Q e represents the cooling capacity of the refrigerator, ηch1 The curve showing the relationship between cooling capacity and temperature, η ch2 The curve showing the relationship between the inverse of the energy efficiency ratio and the chilled water outlet temperature and the cooling water return temperature, η ch3 represents the relationship between the inverse of the energy efficiency ratio and the main load rate of the refrigerator, a3, b3, c3, d3, e3 and f3 represent the cooling capacity characteristic fitting coefficients, a4, b4, c4, d4, e4 and f4 represent the chilled water characteristic fitting coefficients, a5, b5 and c5 represent the main load rate characteristic fitting coefficients of the refrigerator, T eo Indicates the chilled water outlet temperature of the refrigerator, T ci Indicates the cooling water return temperature, β ch represents the main load factor of the refrigerator, and Q avail Indicates the available cooling capacity of the refrigerator;

[0032] The target HVAC chiller energy consumption model is as follows:

[0033]

[0034] Among them, P ch Indicates the actual power of the refrigerator, C COP-L represents the rated energy efficiency ratio of the refrigerator, and Q avail =Q N η ch1 , Q N Indicates the rated cooling capacity of the refrigerator;

[0035] The energy consumption optimization model is as follows:

[0036]

[0037] Among them, min P represents the target optimization function, st represents the constraint condition, and m a-min and m a-max They represent the minimum and maximum values ​​of the actual air flow rate of the fan, T S-min and T S-max Respectively represent the minimum and maximum values ​​of the supply air temperature, m e-min and m e-max They represent the minimum and maximum values ​​of the actual chilled water flow of the chilled water pump, ΔT e-min and ΔT e-max Respectively represent the minimum and maximum values ​​of the temperature difference between the supply and return water of the chilled water, T eo-min and T eo-max Respectively represent the minimum and maximum values ​​of the chilled water outlet temperature of the refrigerator, T ci-min and T ci-max Respectively represent the minimum and maximum values ​​of the cooling water return temperature.

[0038] Preferably, solving the energy consumption optimization model by an optimization algorithm to obtain the first control parameter of the target HVAC comprises the following steps:

[0039] A1. Set the proportion of discoverers PD, the proportion of investigators SD and the warning value R2, and initialize the population. The population initialization formula is as follows:

[0040]

[0041] Among them, x i and x i+1 represents the i-th and i+1-th individuals in the population, and mod represents the remainder function;

[0042] A2. Calculate the fitness value of each individual in the population, and sort them according to the fitness value, select the discoverer from the individuals whose fitness value is greater than the preset fitness value threshold, and update the position of the discoverer. The update formula of the discoverer's position is as follows:

[0043]

[0044] in, and represents the position of the discoverer with coordinates (i, j) in the population in the d-dimensional solution space in the t-th and t+1-th iterations, r1 represents the random number that determines the distance the discoverer moves, and r2 represents the random number that determines the direction the discoverer moves. represents the optimal position of the current finder at the tth iteration, y1 and y2 represent the segmentation coefficients, and ST represents the safety threshold;

[0045] A3. After selecting the discoverer from the population, the remaining individuals in the population are taken as joiners, and the positions of the joiners are updated. The joiner position update formula is as follows:

[0046]

[0047] in, and It represents the position of the participant with coordinates (i, j) in the population in the t-th and t+1-th iterations in the d-dimensional solution space. represents the global worst position of the current joiner at the tth iteration, represents the optimal position of the current joiner at the t+1th iteration, A represents a matrix composed of random numbers 1 or -1, L represents the identity matrix, and n represents the total number of individuals in the population;

[0048] A4. Randomly select a scout from the population and update the position of the scout. The scout position update formula is as follows:

[0049]

[0050] in, and represents the position of the scout with coordinates (i, j) in the population in the d-dimensional solution space in the t-th and t+1-th iterations, represents the global worst position of the current scout at the tth iteration, represents the optimal position of the current scout at the t+1th iteration, β represents a random number that obeys a Gaussian distribution with an expectation of 0 and a variance of 1, γ is 10E-8, K represents the random coefficient of direction and step length, and f i represents the fitness value of the scout, f g and f worst Indicates the best and worst fitness values ​​of the scout;

[0051] A5. Perturb the current optimal solution, recalculate the population fitness, and find the optimal solution after perturbation. The perturbation formula of the current optimal solution is as follows:

[0052]

[0053] in, represents the position of the individual with coordinates (i, j) in the population in the d-dimensional solution space in the t+1th iteration, X best (t) represents the current optimal solution, cauchy(0,1) represents the standard Cauchy distribution function;

[0054] A6. Determine whether the termination condition is met. If the termination condition is met, output the optimal individual position and its fitness value. Otherwise, repeat step A2.

[0055] Preferably, the first agent of the target HVAC outdoor unit includes a first state, a first action and a first reward function, and the first state expression is as follows:

[0056] S0=[T set ,T out ,EER,T in ];

[0057] Among them, S0 represents the first state, T set Indicates the set temperature of the indoor unit, T out represents the outdoor temperature, EER represents the energy efficiency ratio at the next preset time, T in Indicates the indoor temperature at the next preset time;

[0058] The first action expression is as follows:

[0059] A0=[f com,PD high ,PD low ,f fan ];

[0060] Among them, A0 represents the first action, f com Indicates the actual frequency of the frequency conversion device, PD high Indicates the compressor high pressure, PD low Indicates the compressor low pressure, f fan Indicates the output wind speed of the outdoor fan;

[0061] The first reward function expression is as follows:

[0062] R0=EER;

[0063] Among them, R0 represents the first reward function;

[0064] The second agent of the target HVAC indoor unit includes a second state, a second action, and a second reward function. The second state expression is as follows:

[0065]

[0066] Among them, S i Indicates the second state, represents the set temperature of the i-th indoor unit, Indicates the indoor temperature of the next preset time of the i-th indoor unit;

[0067] The second action expression is as follows:

[0068]

[0069] Among them, A i Indicates the second action, and Indicates the opening degree of the two expansion valves of the indoor unit;

[0070] The second reward function expression is as follows:

[0071]

[0072] Among them, R i represents the second reward function.

[0073] Compared with the prior art, the above technical solution of the present invention has the following beneficial technical effects:

[0074] 1. The present invention utilizes a fan modeling unit, a chilled water pump modeling unit, and a refrigerator modeling unit to accurately predict and control the energy consumption of the HVAC system by establishing and optimizing models, thereby ensuring accurate control of the energy consumption of each component of the system (fan, chilled water pump, refrigerator), thereby maximizing energy efficiency, and through the energy consumption optimization modeling unit and the model solving unit, the energy consumption model is solved using an optimization algorithm to obtain the optimal control parameters, so that the HVAC system can provide the required cooling effect with the lowest energy consumption under different operating conditions, thereby saving energy costs.

[0075] 2. The present invention monitors the operating status data of the HVAC in real time through the state prediction unit, and uses the trained state prediction model to predict the operating status of the future time period, and adopts reinforcement learning technology to optimize the control of the system. The optimal control parameters are obtained through the solution of the intelligent agent (outdoor unit and indoor unit), and the energy efficiency and performance of the system are further improved. The air-conditioning control unit is responsible for real-time control of the HVAC system and monitoring the operating status data, so as to ensure that the system can be dynamically adjusted during operation to adapt to environmental changes and fluctuations in energy consumption demand, thereby ensuring system stability and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] Figure 1 A schematic diagram of the overall system flow in an embodiment of the present invention.

[0077] Figure numerals: 1. Fan modeling unit; 2. Chilled water pump modeling unit; 3. Refrigeration machine modeling unit; 4. Total energy consumption modeling unit; 5. Target modeling unit; 6. Constraint modeling unit; 7. Energy consumption optimization modeling unit; 8. Model solving unit; 9. Air conditioning control unit; 10. State prediction unit; 11. Energy-saving control unit. DETAILED DESCRIPTION

[0078] Embodiment 1, as Figure 1 As shown, the HVAC energy consumption and energy-saving control system in a smart building based on artificial intelligence proposed by the present invention includes a refrigerator modeling unit 3, a total energy consumption modeling unit 4, a target modeling unit 5, a constraint modeling unit 6, an energy consumption optimization modeling unit 7, a model solving unit 8, an air conditioning control unit 9, a state prediction unit 10 and an energy-saving control unit 11, and also includes:

[0079] The fan modeling unit 1 is used to build a fan outlet model of the target HVAC based on the indoor cooling load of the smart building, the indoor set temperature of the smart building and the supply air temperature, obtain the supply air flow of the target HVAC based on the fan outlet model of the target HVAC, build a fan energy consumption model of the target HVAC based on the supply air flow of the target HVAC, obtain the fan energy consumption of the target HVAC based on the fan energy consumption model of the target HVAC, transmit the supply air flow of the target HVAC to the chilled water pump modeling unit 2, and transmit the fan energy consumption of the target HVAC to the total energy consumption modeling unit 4;

[0080] The chilled water pump modeling unit 2 receives the target HVAC supply air flow transmitted by the fan modeling unit 1, and is used to build a chilled water pump freezing model of the target HVAC based on the supply air temperature, the condenser inlet air temperature, the chilled water supply and return water temperature difference and the target HVAC supply air flow, obtain the target HVAC chilled water flow based on the chilled water pump freezing model of the target HVAC, build a chilled water pump energy consumption model of the target HVAC based on the chilled water flow of the target HVAC, obtain the chilled water pump energy consumption of the target HVAC based on the chilled water consumption model of the target HVAC, transmit the chilled water flow of the target HVAC to the refrigerator modeling unit 3, and transmit the chilled water pump energy consumption of the target HVAC to the total energy consumption modeling unit 4.

[0081] In the present invention, indoor cooling load refers to the total amount of heat inside the building that needs to be cooled by the air-conditioning system, which is usually determined by the indoor heat source, external environmental conditions and building structure; indoor set temperature refers to the indoor comfort temperature set by the user, and the air-conditioning system controls the indoor environment according to this setting; supply air temperature refers to the temperature of the air delivered into the room from the air-conditioning system; supply air flow refers to the volume flow of air delivered from the air supply port to the room by the air-conditioning system; chilled water flow refers to the water flow circulating through the cooling equipment, which is used to control and maintain the operation of the refrigeration system.

[0082] In an optional embodiment, the refrigeration machine modeling unit 3 receives the chilled water flow of the target HVAC transmitted by the chilled water pump modeling unit 2, and is used to construct a refrigeration machine performance model of the target HVAC based on the chilled water outlet temperature, the cooling water return temperature, the chilled water supply and return temperature difference and the chilled water flow of the target HVAC, obtain the refrigeration machine performance curve of the target HVAC based on the refrigeration machine performance model of the target HVAC, construct the refrigeration machine energy consumption model of the target HVAC based on the refrigeration machine performance curve of the target HVAC, obtain the refrigeration machine energy consumption of the target HVAC based on the refrigeration machine energy consumption model of the target HVAC, and transmit the refrigeration machine energy consumption of the target HVAC to the total energy consumption modeling unit 4.

[0083] It should be noted that the chilled water outlet temperature refers to the temperature of the chilled water when it comes out of the refrigeration unit in the refrigeration system; the cooling water return temperature refers to the temperature of the cooling water when it returns from the cooling equipment to the cooling unit in the refrigeration system; the chilled water supply and return temperature difference refers to the temperature difference when the chilled water enters and leaves the refrigeration unit.

[0084] In an optional embodiment, the total energy consumption modeling unit 4 receives the fan energy consumption of the target HVAC transmitted by the fan modeling unit 1, the chilled water pump energy consumption of the target HVAC transmitted by the chilled water pump modeling unit 2, and the refrigeration energy consumption of the target HVAC transmitted by the refrigeration machine modeling unit 3, and is used to construct a total power model of the target HVAC based on the fan energy consumption, chilled water pump energy consumption and refrigeration machine energy consumption of the target HVAC, obtain the total power of the target HVAC based on the total power model of the target HVAC, and transmit the total power of the target HVAC to the target modeling unit 5.

[0085] In an optional embodiment, the target modeling unit 5 receives the total power of the target HVAC transmitted by the total energy consumption modeling unit 4, and constructs a target optimization function to minimize the total power of the target HVAC, and transmits the target optimization function to the energy consumption optimization modeling unit 7.

[0086] In an optional embodiment, the constraint modeling unit 6 is used to construct constraint conditions of the target HVAC based on the operating parameters of the target HVAC, and transmit the constraint conditions of the target HVAC to the energy consumption optimization modeling unit 7 .

[0087] In an optional embodiment, the energy consumption optimization modeling unit 7 receives the target optimization function transmitted by the target modeling unit 5 and the target HVAC constraints transmitted by the constraint modeling unit 6, and is used to construct an energy consumption optimization model based on the target optimization function and the target HVAC constraints, and transmits the energy consumption optimization model to the model solving unit 8.

[0088] In an optional embodiment, the model solving unit 8 receives the energy consumption optimization model transmitted by the energy consumption optimization modeling unit 7, and is used to solve the energy consumption optimization model through an optimization algorithm to obtain the first control parameter of the target HVAC, and transmits the first control parameter of the target HVAC to the air conditioning control unit 9.

[0089] It should be noted that the energy consumption model is solved using an optimization algorithm to obtain the first control parameter of the target HVAC. The optimization algorithm refers to a class of mathematical methods and computing techniques that aim to find the optimal solution or approximate optimal solution to a problem. It is usually widely used when facing complex multi-variable, multi-condition, and multi-constraint problems.

[0090] In an optional embodiment, the air conditioning control unit 9 receives the first control parameter of the target HVAC transmitted by the model solving unit 8, and is used to control the target HVAC based on the first control parameter of the target HVAC, and monitor the operating status data of the target HVAC in real time to obtain the operating status data of the target HVAC, the operating status data including the high-pressure pressure of the compressor, the low-pressure pressure of the compressor, the actual frequency of the frequency conversion device, the output wind speed of the outdoor fan, the opening of the two expansion valves of the indoor unit, the current indoor temperature of the smart building and the current energy efficiency ratio of the target HVAC, and transmits the operating status data of the target HVAC to the state prediction unit 10.

[0091] It should be noted that the compressor refers to the equipment responsible for compressing and pumping refrigerants such as refrigerants in the HVAC system; high-pressure pressure and low-pressure pressure refer to the two key parameters of the compressor in the refrigeration cycle. The pressure values ​​at the high-pressure end and the low-pressure end directly affect the compression and evaporation process of the refrigerant, and are crucial to the system efficiency and performance; frequency conversion equipment refers to equipment that can adjust the output frequency; expansion valve refers to equipment used to control the flow and pressure of the refrigerant, which is located in the indoor part of the HVAC; the opening of the expansion valve refers to the degree of the expansion valve opening, which affects the flow of the refrigerant and the cooling effect of the system.

[0092] In an optional embodiment, the state prediction unit 10 receives the operating status data of the target HVAC transmitted by the air-conditioning control unit 9, and is used to input the operating status data of the target HVAC into a trained state prediction model, and outputs the operating status data of the target HVAC at the next preset time through the trained state prediction model. The state prediction model adopts a neural network model to transmit the operating status data of the target HVAC at the next preset time to the energy-saving control unit 11.

[0093] It should be noted that the state prediction model includes but is not limited to recurrent neural networks, long short-term memory networks, convolutional neural networks and deep neural networks.

[0094] In an optional embodiment, the energy-saving control unit 11 receives the indoor temperature and energy efficiency ratio of the target HVAC at the next preset time transmitted by the state prediction unit 10, and is used to construct a first intelligent agent of the target HVAC outdoor unit and a second intelligent agent of the target HVAC indoor unit through reinforcement learning based on the indoor temperature and energy efficiency ratio of the target HVAC at the next preset time, solve the first intelligent agent and the second intelligent agent to obtain the second control parameters of the target HVAC, and control the target HVAC based on the second control parameters of the target HVAC.

[0095] It should be noted that reinforcement learning is a machine learning method used to train intelligent agents to learn optimal behaviors in interaction with the environment; the first agent and the second agent in reinforcement learning, the agent refers to the learner or controller, here refers to two different agents that control the outdoor unit and the indoor unit, they improve their control strategies through learning to optimize the performance of the overall HVAC system.

[0096] Embodiment 2, the HVAC energy consumption and energy-saving control system in a smart building based on artificial intelligence proposed by the present invention, compared with Embodiment 1, this embodiment also includes: the fan outlet model of the target HVAC is as follows:

[0097]

[0098] Among them, m a Indicates the actual air flow rate of the fan, Q S represents the indoor cooling load of the smart building, T N Indicates the indoor set temperature of the smart building, T S Indicates the supply air temperature;

[0099] The fan energy consumption model of the target HVAC is as follows:

[0100]

[0101] Among them, P fan represents the actual power of the fan, a1, b1, c1, d1 and e1 represent the fan characteristic fitting coefficients, α fan represents the total efficiency of the fan, ρ air represents the air density, β a represents the fan main load factor, and m a-L Indicates the rated air flow rate of the fan;

[0102] The target HVAC chilled water pump refrigeration model is as follows:

[0103]

[0104] Among them, m e represents the actual chilled water flow of the chilled water pump, T1 represents the inlet air temperature of the cooler, T2 represents the outlet air temperature of the cooler, C p represents the specific heat of water, ΔT e Indicates the temperature difference between the supply and return water of chilled water;

[0105] The energy consumption model of the chilled water pump of the target HVAC is as follows:

[0106]

[0107] Among them, P erepresents the actual power of the chilled water pump, a2, b2, c2 and d2 represent the chilled water pump characteristic fitting coefficients, β e represents the main load factor of the chilled water pump, and m e-L Indicates the rated chilled water flow rate of the chilled water pump, P e-L Indicates the rated power of the chilled water pump.

[0108] In an optional embodiment, the performance model of the target HVAC chiller is as follows:

[0109]

[0110] Among them, Q e represents the cooling capacity of the refrigerator, η ch1 The curve showing the relationship between cooling capacity and temperature, η ch2 The curve showing the relationship between the inverse of the energy efficiency ratio and the chilled water outlet temperature and the cooling water return temperature, η ch3 represents the relationship between the inverse of the energy efficiency ratio and the main load rate of the refrigerator, a3, b3, c3, d3, e3 and f3 represent the cooling capacity characteristic fitting coefficients, a4, b4, c4, d4, e4 and f4 represent the chilled water characteristic fitting coefficients, a5, b5 and c5 represent the main load rate characteristic fitting coefficients of the refrigerator, T eo Indicates the chilled water outlet temperature of the refrigerator, T ci Indicates the cooling water return temperature, β ch represents the main load factor of the refrigerator, and Q avail Indicates the available cooling capacity of the refrigerator;

[0111] The target HVAC chiller energy consumption model is as follows:

[0112]

[0113] Among them, P ch Indicates the actual power of the refrigerator, C COP-L represents the rated energy efficiency ratio of the refrigerator, and Q avail =Q N η ch1 , Q N Indicates the rated cooling capacity of the refrigerator;

[0114] The energy consumption optimization model is as follows:

[0115]

[0116] Among them, min P represents the target optimization function, st represents the constraint condition, and m a-min and m a-max They represent the minimum and maximum values ​​of the actual air flow rate of the fan, TS-min and T S-max Respectively represent the minimum and maximum values ​​of the supply air temperature, m e-min and m e-max They represent the minimum and maximum values ​​of the actual chilled water flow of the chilled water pump, ΔT e-min and ΔT e-max Respectively represent the minimum and maximum values ​​of the temperature difference between the supply and return water of the chilled water, T eo-min and T eo-max Respectively represent the minimum and maximum values ​​of the chilled water outlet temperature of the refrigerator, T ci-min and T ci-max Respectively represent the minimum and maximum values ​​of the cooling water return temperature.

[0117] In an optional embodiment, solving the energy consumption optimization model by an optimization algorithm to obtain the first control parameter of the target HVAC includes the following steps:

[0118] A1. Set the proportion of discoverers PD, the proportion of scouts SD and the warning value R2, and initialize the population. The population initialization formula is as follows:

[0119]

[0120] Among them, x i and x i+1 represents the i-th and i+1-th individuals in the population, and mod represents the remainder function;

[0121] A2. Calculate the fitness value of each individual in the population and sort them according to the fitness value. Select the discoverer from the individuals whose fitness value is greater than the preset fitness value threshold, and update the position of the discoverer. The formula for updating the position of the discoverer is as follows:

[0122]

[0123] in, and represents the position of the discoverer with coordinates (i, j) in the population in the d-dimensional solution space in the t-th and t+1-th iterations, r1 represents the random number that determines the distance the discoverer moves, and r2 represents the random number that determines the direction the discoverer moves. represents the optimal position of the current finder at the tth iteration, y1 and y2 represent the segmentation coefficients, and ST represents the safety threshold;

[0124] A3. After selecting the discoverer from the population, the remaining individuals in the population are taken as joiners, and the positions of the joiners are updated. The formula for updating the joiner positions is as follows:

[0125]

[0126] in, and It represents the position of the participant with coordinates (i, j) in the population in the t-th and t+1-th iterations in the d-dimensional solution space. represents the global worst position of the current joiner at the tth iteration, represents the optimal position of the current joiner at the t+1th iteration, A represents a matrix composed of random numbers 1 or -1, L represents the identity matrix, and n represents the total number of individuals in the population;

[0127] A4. Randomly select a scout from the population and update the scout's position. The scout's position update formula is as follows:

[0128]

[0129] in, and represents the position of the scout with coordinates (i, j) in the population in the d-dimensional solution space in the t-th and t+1-th iterations, represents the global worst position of the current scout at the tth iteration, represents the optimal position of the current scout at the t+1th iteration, β represents a random number that obeys a Gaussian distribution with an expectation of 0 and a variance of 1, γ is 10E-8, K represents the random coefficient of direction and step length, and f i represents the fitness value of the scout, f g and f worst Indicates the best and worst fitness values ​​of the scout;

[0130] A5. Perturb the current optimal solution, recalculate the population fitness, and find the optimal solution after perturbation. The perturbation formula of the current optimal solution is as follows:

[0131]

[0132] in, represents the position of the individual with coordinates (i, j) in the population in the d-dimensional solution space in the t+1th iteration, X best (t) represents the current optimal solution, cauchy(0,1) represents the standard Cauchy distribution function;

[0133] A6. Determine whether the termination condition is met. If the termination condition is met, output the optimal individual position and its fitness value. Otherwise, repeat step A2.

[0134] In an optional embodiment, the first agent of the target HVAC outdoor unit includes a first state, a first action, and a first reward function, and the first state expression is as follows:

[0135] S0=[Tset ,T out ,EER,T in ];

[0136] Among them, S0 represents the first state, T set Indicates the set temperature of the indoor unit, T out represents the outdoor temperature, EER represents the energy efficiency ratio at the next preset time, T in Indicates the indoor temperature at the next preset time;

[0137] The first action expression is as follows:

[0138] A0=[f com ,PD high ,PD low ,f fan ];

[0139] Among them, A0 represents the first action, f com Indicates the actual frequency of the frequency conversion device, PD high Indicates the compressor high pressure, PD low Indicates the compressor low pressure, f fan Indicates the output wind speed of the outdoor fan;

[0140] The first reward function expression is as follows:

[0141] R0=EER;

[0142] Among them, R0 represents the first reward function;

[0143] The second agent of the target HVAC indoor unit includes a second state, a second action, and a second reward function. The second state expression is as follows:

[0144]

[0145] Among them, S i Indicates the second state, represents the set temperature of the i-th indoor unit, Indicates the indoor temperature of the next preset time of the i-th indoor unit;

[0146] The second action expression is as follows:

[0147]

[0148] Among them, A i Indicates the second action, and Indicates the opening degree of the two expansion valves of the indoor unit;

[0149] The second reward function expression is as follows:

[0150]

[0151] Among them, R i represents the second reward function.

[0152] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited thereto, and various changes can be made within the knowledge scope of technicians in the relevant technical field without departing from the purpose of the present invention.

Claims

1. An energy-saving control system for heating, ventilation and air conditioning in a smart building based on artificial intelligence, comprising a refrigerator modeling unit (3), a total energy consumption modeling unit (4), a target modeling unit (5), a constraint modeling unit (6), an energy consumption optimization modeling unit (7), a model solving unit (8), an air conditioning control unit (9), a state prediction unit (10) and an energy-saving control unit (11), characterized in that: A fan modeling unit (1), the fan modeling unit (1) is used to construct a fan outlet model of a target HVAC based on the indoor cooling load of the smart building, the indoor set temperature of the smart building and the supply air temperature, obtain the supply air flow of the target HVAC based on the fan outlet model of the target HVAC, construct a fan energy consumption model of the target HVAC based on the supply air flow of the target HVAC, obtain the fan energy consumption of the target HVAC based on the fan energy consumption model of the target HVAC, transmit the supply air flow of the target HVAC to the chilled water pump modeling unit (2), and transmit the fan energy consumption of the target HVAC to the total energy consumption modeling unit (4); A chilled water pump modeling unit (2), wherein the chilled water pump modeling unit (2) receives the air supply flow of the target HVAC transmitted by the fan modeling unit (1), and is used to construct a chilled water pump freezing model of the target HVAC based on the air supply temperature, the inlet air temperature of the condenser, the chilled water supply and return water temperature difference and the air supply flow of the target HVAC, obtain the chilled water flow of the target HVAC based on the chilled water pump freezing model of the target HVAC, construct an energy consumption model of the chilled water pump of the target HVAC based on the chilled water flow of the target HVAC, obtain the chilled water pump energy consumption of the target HVAC based on the chilled water flow of the target HVAC, transmit the chilled water flow of the target HVAC to the refrigerator modeling unit (3), and transmit the chilled water pump energy consumption of the target HVAC to the total energy consumption modeling unit (4).

2. The HVAC energy consumption and energy saving control system in a smart building based on artificial intelligence according to claim 1 is characterized in that: The refrigeration machine modeling unit (3) receives the chilled water flow of the target HVAC transmitted by the chilled water pump modeling unit (2), and is used to construct a refrigeration machine performance model of the target HVAC based on the chilled water outlet temperature, the cooling water return temperature, the chilled water supply and return temperature difference and the chilled water flow of the target HVAC, obtain a refrigeration machine performance curve of the target HVAC based on the refrigeration machine performance model of the target HVAC, construct a refrigeration machine energy consumption model of the target HVAC based on the refrigeration machine performance curve of the target HVAC, obtain the refrigeration machine energy consumption of the target HVAC based on the refrigeration machine energy consumption model of the target HVAC, and transmit the refrigeration machine energy consumption of the target HVAC to the total energy consumption modeling unit (4); The total energy consumption modeling unit (4) receives the fan energy consumption of the target HVAC transmitted by the fan modeling unit (1), the chilled water pump energy consumption of the target HVAC transmitted by the chilled water pump modeling unit (2), and the refrigerator energy consumption of the target HVAC transmitted by the refrigerator modeling unit (3), and is used to construct a total power model of the target HVAC based on the fan energy consumption, chilled water pump energy consumption, and refrigerator energy consumption of the target HVAC, obtain the total power of the target HVAC based on the total power model of the target HVAC, and transmit the total power of the target HVAC to the target modeling unit (5).

3. The HVAC energy consumption and energy saving control system in a smart building based on artificial intelligence according to claim 2 is characterized in that: The target modeling unit (5) receives the total power of the target HVAC transmitted by the total energy consumption modeling unit (4), and constructs a target optimization function to minimize the total power of the target HVAC, and transmits the target optimization function to the energy consumption optimization modeling unit (7); The constraint modeling unit (6) is used to construct the constraint conditions of the target HVAC based on the operating parameters of the target HVAC, and transmit the constraint conditions of the target HVAC to the energy consumption optimization modeling unit (7); The energy consumption optimization modeling unit (7) receives the target optimization function transmitted by the target modeling unit (5) and the target HVAC constraint conditions transmitted by the constraint modeling unit (6), and is used to construct an energy consumption optimization model based on the target optimization function and the target HVAC constraint conditions, and transmit the energy consumption optimization model to the model solving unit (8).

4. The HVAC energy consumption and energy saving control system in a smart building based on artificial intelligence according to claim 3 is characterized in that: The model solving unit (8) receives the energy consumption optimization model transmitted by the energy consumption optimization modeling unit (7), and is used to solve the energy consumption optimization model through an optimization algorithm to obtain a first control parameter of the target HVAC, and transmit the first control parameter of the target HVAC to an air conditioning control unit (9); The air conditioning control unit (9) receives the first control parameter of the target HVAC transmitted by the model solving unit (8), and is used to control the target HVAC based on the first control parameter of the target HVAC, and monitor the operating status data of the target HVAC in real time to obtain the operating status data of the target HVAC, wherein the operating status data includes the high-pressure pressure of the compressor, the low-pressure pressure of the compressor, the actual frequency of the frequency conversion device, the output wind speed of the outdoor fan, the opening of the two expansion valves of the indoor unit, the current indoor temperature of the smart building and the current energy efficiency ratio of the target HVAC, and transmits the operating status data of the target HVAC to the state prediction unit (10).

5. The HVAC energy consumption and energy saving control system in a smart building based on artificial intelligence according to claim 4 is characterized in that: The state prediction unit (10) receives the operating state data of the target HVAC transmitted by the air conditioning control unit (9), and is used to input the operating state data of the target HVAC into a trained state prediction model, and output the operating state data of the target HVAC at the next preset time through the trained state prediction model. The state prediction model adopts a neural network model to transmit the operating state data of the target HVAC at the next preset time to the energy-saving control unit (11); The energy-saving control unit (11) receives the indoor temperature and energy efficiency ratio of the target HVAC at the next preset time transmitted by the state prediction unit (10), and is used to construct a first intelligent agent of the target HVAC outdoor unit and a second intelligent agent of the target HVAC indoor unit through reinforcement learning based on the indoor temperature and energy efficiency ratio of the target HVAC at the next preset time, solve the first intelligent agent and the second intelligent agent to obtain a second control parameter of the target HVAC, and control the target HVAC based on the second control parameter of the target HVAC.

6. The HVAC energy consumption and energy saving control system in a smart building based on artificial intelligence according to claim 3 is characterized in that: The fan outlet model of the target HVAC is as follows: Among them, m a Indicates the actual air flow rate of the fan, Q S represents the indoor cooling load of the smart building, T N Indicates the indoor set temperature of the smart building, T S Indicates the supply air temperature; The fan energy consumption model of the target HVAC is as follows: Among them, P fan represents the actual power of the fan, a1, b1, c1, d1 and e1 represent the fan characteristic fitting coefficients, α fan represents the total efficiency of the fan, ρ air represents the air density, β a represents the fan main load factor, and m a-L Indicates the rated air flow rate of the fan; The target HVAC chilled water pump refrigeration model is as follows: Among them, m e represents the actual chilled water flow of the chilled water pump, T1 represents the inlet air temperature of the cooler, T2 represents the outlet air temperature of the cooler, C p represents the specific heat of water, ΔT e Indicates the temperature difference between the supply and return water of chilled water; The energy consumption model of the target HVAC chilled water pump is as follows: Among them, P e represents the actual power of the chilled water pump, a2, b2, c2 and d2 represent the chilled water pump characteristic fitting coefficients, β e represents the main load factor of the chilled water pump, and m e-L Indicates the rated chilled water flow rate of the chilled water pump, P e -L indicates the rated power of the chilled water pump.

7. The HVAC energy consumption and energy saving control system in a smart building based on artificial intelligence according to claim 6 is characterized in that: The target HVAC chiller performance model is as follows: Among them, Q e represents the cooling capacity of the refrigerator, η ch1 The curve showing the relationship between cooling capacity and temperature, η ch2 The curve showing the relationship between the inverse of the energy efficiency ratio and the chilled water outlet temperature and the cooling water return temperature, η ch3 represents the relationship between the inverse of the energy efficiency ratio and the main load rate of the refrigerator, a3, b3, c3, d3, e3 and f3 represent the cooling capacity characteristic fitting coefficients, a4, b4, c4, d4, e4 and f4 represent the chilled water characteristic fitting coefficients, a5, b5 and c5 represent the main load rate characteristic fitting coefficients of the refrigerator, T eo Indicates the chilled water outlet temperature of the refrigerator, T ci Indicates the cooling water return temperature, β ch represents the main load factor of the refrigerator, and Q avail Indicates the available cooling capacity of the refrigerator; The target HVAC chiller energy consumption model is as follows: Among them, P ch Indicates the actual power of the refrigerator, C COP-L represents the rated energy efficiency ratio of the refrigerator, and Q avail =Q N η ch1 , Q N Indicates the rated cooling capacity of the refrigerator; The energy consumption optimization model is as follows: Among them, min P represents the target optimization function, st represents the constraint condition, and m a-min and m a-max They represent the minimum and maximum values ​​of the actual air flow rate of the fan, T S-min and T S-max Respectively represent the minimum and maximum values ​​of the supply air temperature, m e-min and m e-max They represent the minimum and maximum values ​​of the actual chilled water flow of the chilled water pump, ΔT e-min and ΔT e-max Respectively represent the minimum and maximum values ​​of the temperature difference between the supply and return water of the chilled water, T eo-min and T eo-max Respectively represent the minimum and maximum values ​​of the chilled water outlet temperature of the refrigerator, T ci-min and T ci-max Respectively represent the minimum and maximum values ​​of the cooling water return temperature.

8. The HVAC energy consumption and energy saving control system in a smart building based on artificial intelligence according to claim 4 is characterized in that: Solving the energy consumption optimization model by an optimization algorithm to obtain the first control parameter of the target HVAC includes the following steps: A1. Set the proportion of discoverers PD, the proportion of investigators SD and the warning value R2, and initialize the population. The population initialization formula is as follows: Among them, x i and x i+1 represents the i-th and i+1-th individuals in the population, and mod represents the remainder function; A2. Calculate the fitness value of each individual in the population, and sort them according to the fitness value, select the discoverer from the individuals whose fitness value is greater than the preset fitness value threshold, and update the position of the discoverer. The update formula of the discoverer's position is as follows: in, and represents the position of the discoverer with coordinates (i, j) in the population in the d-dimensional solution space in the t-th and t+1-th iterations, r1 represents the random number that determines the distance the discoverer moves, and r2 represents the random number that determines the direction the discoverer moves. represents the optimal position of the current finder at the tth iteration, y1 and y2 represent the segmentation coefficients, and ST represents the safety threshold; A3. After selecting the discoverer from the population, the remaining individuals in the population are taken as joiners, and the positions of the joiners are updated. The joiner position update formula is as follows: in, and It represents the position of the participant with coordinates (i, j) in the population in the t-th and t+1-th iterations in the d-dimensional solution space. represents the global worst position of the current joiner at the tth iteration, represents the optimal position of the current joiner at the t+1th iteration, A represents a matrix composed of random numbers 1 or -1, L represents the identity matrix, and n represents the total number of individuals in the population; A4. Randomly select a scout from the population and update the position of the scout. The scout position update formula is as follows: in, and represents the position of the scout with coordinates (i, j) in the population in the d-dimensional solution space in the t-th and t+1-th iterations, represents the global worst position of the current scout at the tth iteration, represents the optimal position of the current scout at the t+1th iteration, β represents a random number that obeys a Gaussian distribution with an expectation of 0 and a variance of 1, γ is 10E-8, K represents the random coefficient of direction and step length, fi represents the fitness value of the scout, and f g and f worst Indicates the best and worst fitness values ​​of the scout; A5. Perturb the current optimal solution, recalculate the population fitness, and find the optimal solution after perturbation. The perturbation formula of the current optimal solution is as follows: in, represents the position of the individual with coordinates (i, j) in the population in the d-dimensional solution space in the t+1th iteration, X best (t) represents the current optimal solution, cauchy(0,1) represents the standard Cauchy distribution function; A6. Determine whether the termination condition is met. If the termination condition is met, output the optimal individual position and its fitness value. Otherwise, repeat step A2.

9. The HVAC energy consumption and energy saving control system in a smart building based on artificial intelligence according to claim 5 is characterized in that: The first agent of the target HVAC outdoor unit includes a first state, a first action and a first reward function, and the first state expression is as follows: S0=[T set ,T out ,EER,T in ]; Among them, S0 represents the first state, T set Indicates the set temperature of the indoor unit, T out represents the outdoor temperature, EER represents the energy efficiency ratio at the next preset time, T in Indicates the indoor temperature at the next preset time; The first action expression is as follows: A0=[f com ,PD high ,PD low ,f fan ]; Among them, A0 represents the first action, f com Indicates the actual frequency of the frequency conversion device, PD high Indicates the compressor high pressure, PD low Indicates the compressor low pressure, f fan Indicates the output wind speed of the outdoor fan; The first reward function expression is as follows: R0=EER; Among them, R0 represents the first reward function; The second agent of the target HVAC indoor unit includes a second state, a second action, and a second reward function. The second state expression is as follows: Among them, S i Indicates the second state, represents the set temperature of the i-th indoor unit, Indicates the indoor temperature of the next preset time of the i-th indoor unit; The second action expression is as follows: Among them, A i Indicates the second action, and Indicates the opening degree of the two expansion valves of the indoor unit; The second reward function expression is as follows: Among them, R i represents the second reward function.

Images