Multi-objective regulation method and system for indoor radiant floor system based on load prediction

Abstract

The present application relates to air conditioner control technical field, provide a kind of based on load prediction's indoor radiant floor system multi-objective regulation and control method and system.The method includes, based on indoor environment parameter, outdoor environment parameter, indoor personnel activity information and equipment parameter, using cold and wet load prediction model, obtain cold load and wet load;Based on outdoor environment parameter, cold load, wet load and air conditioning system operation information, using indoor environment and energy consumption prediction model, obtain indoor temperature, dew point temperature difference, wind system energy consumption, water system energy consumption;With outdoor environment parameter, cold load, wet load and air conditioning system operation information as variable, the objective function of indoor temperature, air conditioning PMV, dew point temperature difference, wind system energy consumption and water system energy consumption is respectively constructed, and corresponding weight is configured, to calculate total objective function;Set air conditioning system working parameter as constraint condition, total objective function is solved, and optimal control parameter is obtained.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of air conditioning control, and particularly relates to a multi-objective regulation method and system for an indoor radiant floor system based on load prediction. BACKGROUND

[0002] The statements in this section merely provide background information related to the present application and do not necessarily constitute the prior art.

[0003] At present, the radiant floor air conditioning system is favored by more and more users due to its comfort, stability and energy efficiency. Load prediction is a key link for on-demand control of the air conditioning system and is crucial for system operation control.

[0004] However, the existing radiant floor air conditioning system still has certain limitations in load prediction and system regulation. Traditional load prediction methods often rely on simple statistical models or empirical formulas. These methods have low prediction accuracy when dealing with complex indoor and outdoor environmental factors, especially in predicting cooling load and wet load. In terms of system regulation, the existing radiant floor air conditioning system mostly adopts fixed regulation logic. These methods are difficult to meet multiple demands such as indoor comfort, condensation risk control and reduction of system energy consumption. SUMMARY

[0005] In order to solve the technical problems in the background art, the present application provides a multi-objective regulation method and system for an indoor radiant floor system based on load prediction. The present application can accurately regulate the indoor radiant floor air conditioning system, has stable regulation effect and can achieve the best energy saving effect.

[0006] In order to achieve the above purpose, the present application adopts the following technical solutions:

[0007] The first aspect of the present application provides a multi-objective regulation method for an indoor radiant floor system based on load prediction.

[0008] A multi-objective regulation method for an indoor radiant floor system based on load prediction, comprising:

[0009] Obtaining indoor environmental parameters, outdoor environmental parameters, indoor personnel activity information, device parameters and air conditioning system operation information;

[0010] Based on the indoor environmental parameters, outdoor environmental parameters, indoor personnel activity information and device parameters, a cooling and wet load prediction model is used to obtain cooling load and wet load;

[0011] Based on the outdoor environmental parameters, cooling load, wet load and air conditioning system operation information, an indoor environment and energy consumption prediction model is used to obtain indoor temperature, condensation temperature difference, wind system energy consumption and water system energy consumption;

[0012] With outdoor environment parameters, cooling load, wet load and air conditioning system operation information as variables, the objective functions of indoor temperature, air conditioning PMV, dew point temperature difference, wind system energy consumption and water system energy consumption are respectively constructed, and corresponding weights are configured to calculate the total objective function;

[0013] The working parameters of the air conditioning system are set as constraint conditions, and the total objective function is solved to obtain the optimal control parameters.

[0014] Further, the constraint conditions include air supply volume constraint, water supply pump state constraint and floor water supply temperature constraint.

[0015] Further, the indoor environment parameters include indoor temperature, indoor humidity, floor surface temperature and dew point temperature difference, the outdoor environment parameters include outdoor temperature, outdoor humidity, solar radiation intensity and outdoor wind speed, the indoor personnel activity information includes personnel wet amount, human metabolic rate, clothing thermal resistance and personnel activity time, the equipment parameters include light heat dissipation, equipment heat dissipation and light equipment start-stop time, and the air conditioning system operation information includes fan air volume, radiant floor water supply pump switch, radiant floor water supply temperature, wind system energy consumption and water system energy consumption.

[0016] Further, with outdoor environment parameters, cooling load, wet load and air conditioning system operation information as variables, the objective functions of indoor temperature, air conditioning PMV, dew point temperature difference, wind system energy consumption and water system energy consumption are respectively constructed, and corresponding weights are configured to calculate the total objective function, the method comprising:

[0017] With outdoor temperature, outdoor humidity, cooling load, wet load, fresh air fan air volume, radiant floor water supply temperature and radiant floor water supply pump state as variables, set the indoor air temperature, and based on the difference between the indoor air temperature and the user set value, construct the indoor temperature objective function;

[0018] With outdoor temperature, outdoor humidity, cooling load, wet load, fresh air fan air volume, radiant floor water supply temperature and radiant floor water supply pump state as variables, construct the air conditioning PMV objective function;

[0019] With outdoor temperature, outdoor humidity, cooling load, wet load, fresh air fan air volume, radiant floor water supply temperature and radiant floor water supply pump state as variables, construct the dew point temperature difference objective function;

[0020] With outdoor temperature, outdoor humidity, cooling load, wet load, fresh air fan air volume, radiant floor water supply temperature and radiant floor water supply pump state as variables, construct the wind system energy consumption objective function;

[0021] With outdoor temperature, outdoor humidity, cooling load, wet load, fresh air fan air volume, radiant floor water supply temperature and radiant floor water supply pump state as variables, construct the water system energy consumption objective function.

[0022] Further, taking outdoor environment parameters, cooling load, wet load and air conditioning system operation information as variables, target functions of indoor temperature, air conditioning PMV, dew point temperature difference, wind system energy consumption and water system energy consumption are respectively constructed, and corresponding weights are configured to calculate a total target function; the method comprises:

[0023] Based on the indoor temperature target function, the dew point temperature difference target function, the wind system energy consumption target function and the water system energy consumption target function and the corresponding weights, the product sum is calculated to obtain the total target function.

[0024] Further, taking outdoor environment parameters, cooling load, wet load and air conditioning system operation information as variables, target functions of indoor temperature, air conditioning PMV, dew point temperature difference, wind system energy consumption and water system energy consumption are respectively constructed, and corresponding weights are configured to calculate a total target function; the method comprises:

[0025] Based on the air conditioning PMV target function, the dew point temperature difference target function, the wind system energy consumption target function and the water system energy consumption target function and the corresponding weights, the product sum is calculated to obtain the total target function.

[0026] Further, the total target function is solved to obtain the optimal control parameter, and the method comprises:

[0027] An improved grey wolf optimization algorithm is adopted to randomly generate a grey wolf individual, the grey wolf individual is input into an indoor environment and energy consumption prediction model to obtain indoor temperature, dew point temperature difference, wind system energy consumption and water system energy consumption; the grey wolf individual comprises: outdoor temperature, outdoor humidity, cooling load, wet load, fresh air fan air volume, radiant floor water supply temperature and radiant floor water supply pump state;

[0028] Based on the total target function, the fitness values of the individuals in the population are determined and sorted, and the three grey wolf individuals with the highest fitness are selected, and the fitness from high to low is in turn alpha, beta and delta wolf, and the rest is omega wolf;

[0029] The grey wolf chases prey and updates the position of the grey wolf individual, the fitness values of each grey wolf are calculated using the target function, and ranking is performed, and a certain proportion of grey wolf individuals with low fitness are selected, and Cauchy mutation is performed, and the fitness is recalculated and updated after mutation;

[0030] It is judged whether the maximum iteration number is reached, and the next round of iteration or the result is output.

[0031] The second aspect of the present application provides a multi-objective control system of an indoor radiant floor system based on load prediction.

[0032] A multi-objective control system of an indoor radiant floor system based on load prediction, comprising:

[0033] a data acquisition module configured to acquire indoor environment parameters, outdoor environment parameters, indoor personnel activity information, device parameters, and air conditioning system operation information;

[0034] a load prediction module configured to, based on the indoor environment parameters, the outdoor environment parameters, the indoor personnel activity information, and the device parameters, adopt a cold-wet load prediction model to obtain a cold load and a wet load;

[0035] an environment and energy consumption prediction module configured to, based on the outdoor environment parameters, the cold load, the wet load, and the air conditioning system operation information, adopt an indoor environment and energy consumption prediction model to obtain an indoor temperature, a dew point temperature difference, a wind system energy consumption, and a water system energy consumption;

[0036] a target function construction module configured to, taking the outdoor environment parameters, the cold load, the wet load, and the air conditioning system operation information as variables, construct target functions of the indoor temperature, an air conditioning PMV, the dew point temperature difference, the wind system energy consumption, and the water system energy consumption respectively, and configure corresponding weights to calculate a total target function;

[0037] a solution module configured to set air conditioning system working parameters as constraint conditions, and solve the total target function to obtain optimal control parameters.

[0038] A third aspect of the present application provides a computer readable storage medium.

[0039] A computer readable storage medium having a computer program stored thereon, the program being executed by a processor to implement the steps in the load prediction based multi-objective control method for an indoor radiant floor system according to the first aspect.

[0040] A fourth aspect of the present application provides a computer device.

[0041] A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the steps in the load prediction based multi-objective control method for an indoor radiant floor system according to the first aspect when executing the program.

[0042] Compared with the prior art, the present application has the following advantages:

[0043] The present application aims at the technical problems of existing radiant floor air conditioning system control logic being fixed, control effect being unstable and unable to achieve the best energy saving effect, etc., and provides a multi-objective control method and system for indoor radiant floor system based on load prediction, indoor environment parameters, outdoor environment parameters, indoor personnel activity information, equipment parameters and air conditioning system operation information are obtained; based on the indoor environment parameters, outdoor environment parameters, indoor personnel activity information and equipment parameters, a cold and wet load prediction model is used to obtain the cold load and the wet load; based on the outdoor environment parameters, cold load, wet load and air conditioning system operation information, an indoor environment and energy consumption prediction model is used to obtain the indoor temperature, dew point temperature difference, wind system energy consumption and water system energy consumption; taking the outdoor environment parameters, cold load, wet load and air conditioning system operation information as variables, the objective functions of indoor temperature, air conditioning PMV, dew point temperature difference, wind system energy consumption and water system energy consumption are respectively constructed, and corresponding weights are configured to calculate the total objective function; the air conditioning system working parameters are set as constraint conditions, and the total objective function is solved to obtain the optimal control parameters. The present application uses machine learning algorithm to predict the indoor cold and wet load, can realize relatively accurate load prediction, uses machine learning algorithm to predict the control effect, combines the two to generate the optimal control parameters, so as to maintain the indoor hot and humid environment in the comfortable interval, ensure the indoor dew point temperature difference in the safe interval and reduce the system energy consumption. BRIEF DESCRIPTION OF DRAWINGS

[0044] The accompanying drawings, which form a part of this description, are included to provide a further understanding of the application and are incorporated in and constitute a part of this application. The embodiments of these drawings illustrate the preferred embodiment of the present application and, together with the description, serve to explain the principles of the present application.

[0045] Figure 1 is a flow chart of the multi-objective control method for indoor radiant floor system based on load prediction shown by the present application;

[0046] Figure 2 is a specific flow chart of the multi-objective control method for indoor radiant floor system based on load prediction shown by the present application;

[0047] Figure 3 is a training flow chart of the load prediction model shown by the present application;

[0048] Figure 4 is a training flow chart of the indoor environment and energy consumption model shown by the present application;

[0049] Figure 5 is a flow chart of the improved grey wolf optimization algorithm shown by the present application;

[0050] Figure 6 is a structure diagram of the multi-objective control system for indoor radiant floor system based on load prediction shown by the present application. DETAILED DESCRIPTION

[0051] The present application will be further described with reference to the drawings and examples.

[0052] It should be noted that the following detailed description is exemplary in nature and is intended to provide further description of the application. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0053] It is also to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, steps, operations, elements, components, and / or groups thereof.

[0054] It should be noted that the flowchart and block diagrams in the drawings illustrate the architecture, functionality, and operation of possible implementations of methods and systems according to various embodiments of the present disclosure. It should also be noted that each block in the flowchart and block diagrams and / or combinations of blocks in the flowchart and block diagrams can be implemented by a machine readable medium that can comprise one or more executable instructions for implementing the specified logic function(s). Finally, it should be noted that the order of the blocks presented in the flowcharts and / or block diagrams can vary depending on the implementation. For example, two blocks shown in succession can in fact be executed substantially concurrently or the blocks can sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the flowchart and / or block diagrams and combinations of blocks in the flowchart and / or block diagrams can be implemented by special purpose hardware-based systems that perform the specified functions or operations, or combinations of special purpose hardware and

[0055] Example One

[0056] As Figure 1As shown, the embodiment provides a multi-objective regulation method for an indoor radiant floor system based on load prediction. The embodiment takes the method applied to a server as an example. It can be understood that the method can also be applied to a terminal and can also be applied to a system including a terminal and a server and is realized through the interaction of the terminal and the server. The server can be a stand-alone physical server, a server cluster composed of multiple physical servers or a distributed system, a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network servers, cloud communication, middleware services, domain name services, security services CDN, and basic cloud computing services such as big data and artificial intelligence platforms. The terminal can be a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited thereto. The terminal and the server can be directly or indirectly connected through wired or wireless communication, which is not limited in the present application. In the embodiment, the method includes the following steps:

[0057] Obtaining indoor environment parameters, outdoor environment parameters, indoor personnel activity information, device parameters and air conditioning system operation information;

[0058] Based on the indoor environment parameters, outdoor environment parameters, indoor personnel activity information and device parameters, a cold and wet load prediction model is used to obtain the cold load and the wet load;

[0059] Based on the outdoor environment parameters, the cold load, the wet load and the air conditioning system operation information, an indoor environment and energy consumption prediction model is used to obtain the indoor temperature, the dew point temperature difference, the wind system energy consumption and the water system energy consumption;

[0060] Taking the outdoor environment parameters, the cold load, the wet load and the air conditioning system operation information as variables, the objective functions of the indoor temperature, the air conditioning PMV, the dew point temperature difference, the wind system energy consumption and the water system energy consumption are respectively constructed, and the corresponding weights are configured to calculate the total objective function;

[0061] Setting the air conditioning system working parameters as the constraint condition, the total objective function is solved to obtain the optimal regulation parameters.

[0062] The present application uses a machine learning algorithm to predict indoor cold and wet loads, which can achieve relatively accurate load prediction. The machine learning algorithm is used to predict the regulation effect, and the optimal regulation parameters are generated by combining the two, so as to maintain the indoor thermal and humid environment in the comfort interval and ensure that the indoor dew point temperature difference is in the safety interval, thereby reducing the system energy consumption.

[0063] The embodiment will be described in detail as follows, Figure 2 as shown:

[0064] Step S1: obtaining indoor and outdoor environment historical parameters, indoor personnel and device activity information, and air conditioning system operation historical information.

[0065] Step S11: Collecting indoor and outdoor environmental parameters through sensors, obtaining indoor personnel activities and equipment start-stop conditions, and reading air conditioning system operation history information. The outdoor environmental parameters include temperature, humidity, solar radiation intensity, and wind speed; the indoor environmental parameters include temperature, humidity, floor surface temperature, and dew point temperature difference; the indoor personnel activity time and equipment on-off time include personnel moisture emission, light heat dissipation, equipment heat dissipation, human metabolic rate, clothing thermal resistance, personnel activity time, and light equipment on-off time; and the air conditioning system operation history information includes fan air volume, radiant floor water supply pump on-off, radiant floor water supply temperature, air system energy consumption, and water system energy consumption.

[0066] In some embodiments, the collected parameter information is divided into historical data and real-time data. The historical data is used for training the model and verification, and the real-time data is used for real-time calculation and optimization in the process of system operation to solve the optimal control parameters.

[0067] Step S12: Specifically, the personnel moisture emission, light heat dissipation, equipment heat dissipation, human metabolic rate, clothing thermal resistance, light equipment on-off time, and personnel activity time cannot be obtained through sensors. Among them, the personnel moisture emission, human metabolic rate, and clothing thermal resistance are estimated according to experience, and the light heat dissipation and equipment heat dissipation are obtained in real time according to the actual operation schedule.

[0068] Step S121: The human moisture emission depends on the activity level and environmental conditions. Taking the average value of a single adult as an example:

[0069] Sitting (no activity): about 250-350 g / h;

[0070] Light activity (such as office work): about 350-500 g / h;

[0071] Moderate activity (such as walking): about 500-700 g / h;

[0072] Heavy activity (such as running): about 700-1000 g / h;

[0073] Step S122: The human metabolic rate refers to the energy metabolic rate per square meter of human body surface area, which depends on the activity level and environmental conditions. Taking the average value of a single adult as an example:

[0074] Sitting (light activity, such as reading): about 60-70 W / m 2 ;

[0075] Light activity (such as standing work): about 70-80 W / m 2 ;

[0076] Moderate activity (such as office work): about 80-100 W / m2 ;

[0077] Heavy activity (such as heavy physical labor): about 100-120 W / m 2 ;

[0078] Step S123: The clothing thermal resistance is a parameter for reflecting the clothing heat preservation performance, which is inversely proportional to the thermal conductivity of the clothing, and the unit is Clo:

[0079] Thin summer clothes (such as short-sleeved shirts, shorts): about 0.5-0.6 Clo;

[0080] Spring and autumn clothes (such as long-sleeved shirts, long pants): about 0.7-1.0 Clo;

[0081] Medium-thickness spring and autumn clothes (such as sweaters, light jackets): about 1.1-1.5 Clo;

[0082] Winter clothes (such as thick sweaters, coats or windbreakers): about 1.6-2.0 Clo;

[0083] Thick winter clothes (such as heavy coats, down jackets): about 2.1-2.5 Clo;

[0084] Step S13: The PMV, dew point temperature difference, air system energy consumption and water system energy consumption need to be further calculated.

[0085] The PMV refers to the ASHRAE 55-2017 standard formula:

[0086] PMV = 0.303 × e -0.036×M + 0.028 × (M-W) + 0.00000305 × 5733 - 0.00763 × Pa + 0.000149 × Pa 2 + 0.000438 × M × (M-W) + 0.000119 × M × Pa - 0.000388 × (M-W) × Pa - 0.000006 × M × (M-W) × Pa + 0.0000000016 × M × (M-W) × (34-Ta)

[0087] Where: M represents metabolic rate, unit: megacalorie / hour / square meter (met); W represents external work, unit: megacalorie / hour / square meter (met); Pa represents the environmental air water vapor pressure, unit: Pascal (Pa); Ta represents the indoor air temperature, unit: Celsius (℃).

[0088] Step S131: The dew point temperature difference calculation formula is:

[0089] ΔT l = T d - T ld

[0090] In the formula, T d is the floor surface temperature, ℃; T ld is the dew point temperature of indoor air, ℃; ΔT l is the dewing temperature difference, ℃.

[0091] Step S132: The energy consumption calculation formula of the air system is:

[0092] h = C pa × T + w (C pw × T + R w × T - h ref )

[0093] ΔE x = V × ρ × (h1 - h2)

[0094] In the formula, h is the specific enthalpy, kJ / kg; C pa is the specific heat capacity of dry air, kJ / kg·K; T is the air temperature, ℃; w is the air moisture content, kg H2O / kg DryAir ; C pw is the specific heat capacity of water vapor, kJ / kg·K; R W is the gas constant of water vapor, kJ / kg·K. h ref is the reference enthalpy value, which is simplified as 0 here; V is the air volume of the air system, m 3 / h; h1 is the air specific enthalpy at the inlet of the fresh air fan, kJ / kg; h2 is the air specific enthalpy at the outlet of the fresh air fan, kJ / kg; ΔE x is the energy consumption of the air system per hour, kW / h.

[0095] Step S133: The energy consumption calculation formula of the water system is:

[0096] ΔE s = Q × ρ × C × ΔT

[0097] In the formula, ΔE s is the energy dissipated by the water system per hour, kW / h; Q is the water flow, m 3 / h; ρ is the water density, 1000 kg / m 3 ; C is the specific heat capacity of water, about 4.18 kJ / (kg·K); ΔT is the radiation floor supply and return water temperature difference, K.

[0098] Step S14: The obtained data is preprocessed to remove abnormal data, null data, and duplicate data to obtain a sample data set.

[0099] For example Figure 3As shown, step S2 involves organizing indoor and outdoor environmental parameters, processing the data, and using machine learning to establish a cooling and humidity load prediction model.

[0100] Step S21: Select the required data and organize it into a dataset. Input items: outdoor temperature, outdoor humidity, indoor temperature, indoor humidity, outdoor wind speed, solar radiation intensity, personnel activity (including: personnel moisture dissipation, human metabolic rate, clothing thermal resistance, and personnel activity time), light heat dissipation, equipment heat dissipation, and light equipment start-up and shutdown time. Output items are cooling load and humidity load.

[0101] Step S22: Write a machine learning algorithm, normalize the data, divide it into training and test sets, and import the training set into the machine learning algorithm.

[0102] Step S23: Train the cooling and humidity load prediction model. By optimizing the algorithm, adjust the weights and offsets of the cooling and humidity load prediction model to make the prediction model more accurate.

[0103] Step S24: Input the test set into the cooling and humidity load prediction model to predict the cooling and humidity load, and simultaneously use the root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination: R 2 Evaluate the model. If the model is trained on the same dataset, the smaller the RMSE and MAE values, the better the R-value. 2 The closer a value is to 1, the higher the model accuracy. The formulas for each indicator are as follows:

[0104]

[0105] In the formula, y i This is the actual value. For predicted values, Let n be the mean and n be the sample size.

[0106] like Figure 4 As shown, step S3 involves organizing historical outdoor environmental data, cooling and humidity load data, and historical air conditioning system operation data, processing the data, and using machine learning algorithms to establish an indoor environment and energy consumption prediction model.

[0107] Step S31: Select the necessary data and organize it into a dataset. Input items: fresh air unit airflow, radiant floor water pump status, radiant floor water supply temperature, outdoor temperature, outdoor humidity, indoor cooling load, and indoor humidity load. Output items: indoor temperature, condensation temperature difference, air system energy consumption, and water system energy consumption.

[0108] Step S32: Write a machine learning algorithm, normalize the data, divide it into training and test sets, and import the training set into the machine learning algorithm.

[0109] In one embodiment, the machine learning algorithm is written to normalize the data, divide the training set and test set, and import the training set into the machine learning algorithm, including the following steps:

[0110] S321, read the input items from the historical data: fresh air volume, radiant floor supply pump status, radiant floor supply water temperature, outdoor temperature, outdoor humidity, indoor cooling load and indoor humidity load. The output items are indoor temperature, dew point temperature difference, wind system energy consumption and water system energy consumption.

[0111] S322, write the BP neural network algorithm.

[0112] S323, divide the data set, usually according to the proportion of 70% training set and 30% test set, and normalize all input and output data to the interval [0, 1].

[0113] S324, determine the neural network structure, the number of input layer neurons is 7, try and hide the number of neuron nodes in the layer, and the number of output layer neurons is 4.

[0114] S325, input the hyperparameters of the model and start training.

[0115] S326, complete the indoor environment and energy consumption prediction model training.

[0116] Step S33: input the test set into the indoor environment and energy consumption prediction model, predict the indoor environment and energy consumption, and evaluate, as described above in step S23.

[0117] In some embodiments, the model participates in fitness calculation as part of a multi-objective optimization algorithm.

[0118] It should be noted that the above machine learning algorithm can be based on neural network, support vector machine regression, etc. The embodiments of the present application do not limit this.

[0119] Step S4: the application load prediction model predicts the cold and wet load, sets the target regulation temperature, determines the constraint condition, sets the target function of multi-objective optimization, and the specific process is as follows:

[0120] Step S41: export the real-time data in step S1, including: outdoor temperature, humidity, solar radiation intensity and wind speed; indoor temperature, humidity, floor surface temperature and dew point temperature difference; human sensible heat load, humidity load, light heat dissipation, equipment heat dissipation, human metabolic rate, clothing thermal resistance, personnel activity state and light equipment start-stop state; input the real-time data into the cold and wet load prediction model to predict the real-time cold load and wet load in the room.

[0121] Step S42: Extract the outdoor temperature and humidity in real-time data, combine them with the cooling load and the wet load to form an environmental parameter data set as part of the independent variables, in turn x1, x2, x3, x4.

[0122] Step S43: Obtain the working parameters of the air conditioning system, set the constraints of the optimization algorithm to generate individuals, including: fresh air system air supply range, radiant floor water supply pump state, radiant floor water supply temperature range.

[0123] Step S431: Specifically, the air supply constraint formula is as follows:

[0124]

[0125] In the formula, is the minimum value of the fresh air system air supply, m 3 / h; is the maximum value of the fresh air system air supply, m 3 / h; is the regulated fresh air system air supply, m 3 / h.

[0126] Step S432: Specifically, the water supply pump state constraint formula is as follows:

[0127] 0≤K b ≤1

[0128] In the formula, 0 is closed, 1 is open, K b is the water pump state.

[0129] Step S433: Specifically, the floor water supply temperature constraint formula is as follows:

[0130]

[0131] In the formula, is the minimum value of the floor water supply temperature, ℃; is the maximum value of the floor water supply temperature, ℃; is the regulated floor water supply pump temperature, ℃.

[0132] Specifically, the regulated parameters are part of the independent variables, namely the fresh air fan air volume, the radiant floor water supply temperature, and the radiant floor water supply pump state, in turn x5, x6, x7. Combined with the above environmental parameter independent variables, as the independent variables of the optimization algorithm.

[0133] Step S44: Set the objective function of the optimization algorithm, the present application takes the indoor thermal and humid environment, the dew risk, and the energy consumption as the optimization target, the energy consumption is divided into wind system energy consumption and water system energy consumption, so the objective function is divided into four parts.

[0134] Step S441: Specifically, the indoor thermal and humid environment index is PMV or indoor temperature, which is selected according to actual needs of the user.

[0135] Step S4411: The target function of PMV is set as the minimum value of the absolute value of PMV, and the indoor thermal and humid environment target function f1 is:

[0136] f1 = min |P in (x1, x2, x3, x4, x5, x6, x7)|

[0137] In the formula, P in is the indoor PMV value.

[0138] Step S4412: According to the needs of the user, the indoor air temperature is set, and the target function of the indoor air temperature is set as the minimum value of the difference from the user set value, and the indoor environment temperature target function f1 is:

[0139] f1 = min |T in (x1, x2, x3, x4, x5, x6, x7) - T s |

[0140] In the formula, T in is the indoor temperature predicted by the indoor environment and energy consumption prediction model, ℃; and T s is the indoor temperature value set by the user, ℃.

[0141] Step S442: Specifically, the smaller the dew point temperature difference, the greater the possibility of dew; on the contrary, the greater the temperature difference, the smaller the possibility of dew. In order to realize the minimization of the dew risk, the target function f2 of the dew point temperature difference is maximized to reduce the dew risk.

[0142] f2 = -min |T l (x1, x2, x3, x4, x5, x6, x7)|

[0143] In the formula, T l is the dew point temperature difference predicted by the indoor environment and energy consumption prediction model, ℃.

[0144] Step S443: In this embodiment, the air system of the air conditioning system is mainly the fresh air machine, so the enthalpy difference before and after the fresh air machine is taken as the air system energy consumption; taking low energy consumption as the target, the air system energy consumption target function f3 is:

[0145] f3 = min Q f (x1, x2, x3, x4, x5, x6, x7)

[0146] Step S444: The water system of the air conditioning system is mainly based on radiant floor, so the energy carried by the difference between the floor supply and return water is taken as the water system energy consumption. Meanwhile, the present application takes low energy consumption as the target, and the water system energy consumption target function f4 is obtained as:

[0147] f4 = min Q s (x1, x2, x3, x4, x5, x6, x7)

[0148] Step S445: In order to reduce the algorithm complexity and simplify the multi-objective optimization problem, the above indoor thermal and humid environment, dew risk and energy consumption functions are weighted to form a thermal and humid, dew and energy consumption target function f as:

[0149] f = α1f1 + α2f2 + α3f3 + α4f4

[0150] In the formula, α1, α2, α3, α4 are the weights of each target, which are adjusted according to the actual needs of the user.

[0151] Step S5: An optimization algorithm is applied to solve the target optimization model to calculate the optimal control parameters. In the embodiment, an improved grey wolf optimization algorithm is used, as shown in Figure 5 .

[0152] The steps of the improved grey wolf optimization algorithm are as follows:

[0153] S51: The maximum number of iterations and the population size of the improved grey wolf optimization algorithm are set.

[0154] S52, the initial position of the population is generated using the Logistic mapping, and the expression is:

[0155] y n+1 = r·y n ·(1-y n )

[0156] Wherein, y n represents the position of the nth individual; r is a random number between 0 and 1.

[0157] S53, the population fitness is calculated using the above target function f, and the fitness values are sorted. According to the sorting result, the three grey wolves with the highest fitness are selected as the alpha wolf, beta wolf and delta wolf of the leadership layer, and the rest are omega wolves, and their positions and fitness are recorded as: y α , y β , y δ and F α , F β , F δ ;

[0158] S54, the gray wolf executes prey tracking behavior, and updates the position of the individual. In this step, the present application updates the next iteration position of the wolf in the algorithm.

[0159] The mathematical model of the gray wolf tracking prey is as follows:

[0160] y α (m)=y α (m)-A1·D α

[0161] y β (m)=y β (m)-A2·D β

[0162] y δ (m)=y δ (m)-A3·D δ

[0163]

[0164] +0.1(r1·(y α -y ω )+r2·(y β -y ω )+r2·(y δ -y ω ))

[0165] Wherein, D α , D α , D α are the distances between the alpha wolf, beta wolf and delta wolf and the prey, y α , y β , y δ are the current positions of the alpha wolf, beta wolf and delta wolf, y(m+1) is the next iteration position of the wolf. r1, r2, r3 are random numbers between 0 and 1. Because the fitness of the alpha wolf, beta wolf and delta wolf decreases in turn, the importance decreases in turn, and the weights of the alpha wolf, beta wolf and delta wolf in the above formula decrease in turn, and a certain degree of random disturbance is added.

[0166] In order to enhance the search performance of the algorithm, the present application selects a multi-stage nonlinear convergence strategy, so that the algorithm ensures efficiency while improving exploration ability in the iteration process, therefore the convergence factor a is updated as follows:

[0167]

[0168] In the formula: m is the current iteration number; M is the maximum iteration number; k1, k2 are parameters for controlling the shape of the e exponential function, and k3 is an index for adjusting the descending rate of a in the later iteration, which can be adjusted according to actual needs.

[0169] S55, calculate the fitness value using the objective function, and sort, while selecting the top 5% of gray wolf individuals in the fitness ranking, performing Cauchy mutation, recalculating the fitness after mutation and updating the positions and fitness of alpha, beta and delta wolves, and the Cauchy mutation is:

[0170] y m+1 =y m +0.1x(rxCauchy(0.5)+1)

[0171] In the formula: r is a random number uniformly distributed in the range [0, 1]; Cauchy(0.5) is a random number subject to Cauchy distribution.

[0172] S56, let the iteration number m = m + 1, if m = M max then the algorithm terminates, otherwise return to step S54;

[0173] S57, output the current position and fitness of alpha as the optimal control parameter, and the optimization is completed.

[0174] Example two

[0175] As Figure 6 shown, the embodiment provides a multi-objective regulation system for an indoor radiant floor system based on load prediction, comprising:

[0176] A data acquisition module configured to acquire indoor environmental parameters, outdoor environmental parameters, indoor personnel activity information, device parameters, and air conditioning system operation information;

[0177] A load prediction module configured to obtain cold load and wet load based on indoor environmental parameters, outdoor environmental parameters, indoor personnel activity information, and device parameters, using a cold and wet load prediction model;

[0178] An environmental and energy consumption prediction module configured to obtain indoor temperature, dew point temperature difference, air system energy consumption, and water system energy consumption based on outdoor environmental parameters, cold load, wet load, and air conditioning system operation information, using an indoor environmental and energy consumption prediction model;

[0179] An objective function construction module configured to construct objective functions for indoor temperature, air conditioning PMV, dew point temperature difference, air system energy consumption, and water system energy consumption, respectively, using outdoor environmental parameters, cold load, wet load, and air conditioning system operation information as variables, and configure corresponding weights to calculate a total objective function;

[0180] A solving module configured to set air conditioning system operating parameters as constraint conditions, solve the total objective function, and obtain optimal control parameters.

[0181] In some embodiments, the constraints include an air supply amount constraint, a water supply pump state constraint, and a floor water supply temperature constraint.

[0182] In some embodiments, the indoor environment parameters include an indoor temperature, an indoor humidity, a floor surface temperature, and a dew point temperature difference, the outdoor environment parameters include an outdoor temperature, an outdoor humidity, a solar radiation intensity, and an outdoor wind speed, the indoor personnel activity information includes a personnel moisture emission amount, a human metabolic rate, a clothing thermal resistance, and a personnel activity time, the device parameters include a light heat dissipation amount, a device heat dissipation amount, and a light device start-stop time, and the air conditioning system operation information includes a fan air volume, a radiant floor water supply pump switch, a radiant floor water supply temperature, a wind system energy consumption, and a water system energy consumption.

[0183] In some embodiments, the target function construction module is further configured to:

[0184] with the outdoor temperature, the outdoor humidity, the cooling load, the humidity load, the fresh air fan air volume, the radiant floor water supply temperature, and the radiant floor water supply pump state as variables, set an indoor air temperature, and based on a difference between the indoor air temperature and a user set value, construct an indoor temperature target function;

[0185] with the outdoor temperature, the outdoor humidity, the cooling load, the humidity load, the fresh air fan air volume, the radiant floor water supply temperature, and the radiant floor water supply pump state as variables, construct an air conditioning PMV target function;

[0186] with the outdoor temperature, the outdoor humidity, the cooling load, the humidity load, the fresh air fan air volume, the radiant floor water supply temperature, and the radiant floor water supply pump state as variables, construct a dew point temperature difference target function;

[0187] with the outdoor temperature, the outdoor humidity, the cooling load, the humidity load, the fresh air fan air volume, the radiant floor water supply temperature, and the radiant floor water supply pump state as variables, construct a wind system energy consumption target function;

[0188] with the outdoor temperature, the outdoor humidity, the cooling load, the humidity load, the fresh air fan air volume, the radiant floor water supply temperature, and the radiant floor water supply pump state as variables, construct a water system energy consumption target function.

[0189] In some embodiments, the target function construction module is further configured to: based on the indoor temperature target function, the dew point temperature difference target function, the wind system energy consumption target function, and the water system energy consumption target function and corresponding weights, calculate a product sum to obtain a total target function.

[0190] In some embodiments, the target function construction module is further configured to: based on the air conditioning PMV target function, the dew point temperature difference target function, the wind system energy consumption target function, and the water system energy consumption target function and corresponding weights, calculate a product sum to obtain a total target function.

[0191] In some embodiments, the solving module is further configured to:

[0192] The improved grey wolf optimization algorithm is adopted, the grey wolf individual is randomly generated, the grey wolf individual is input into the indoor environment and energy consumption prediction model, and indoor temperature, dew point temperature difference, wind system energy consumption and water system energy consumption are obtained; the grey wolf individual includes outdoor temperature, outdoor humidity, cooling load, wet load, fresh air fan air volume, radiant floor water supply temperature and radiant floor water supply pump state;

[0193] Based on the total objective function, the fitness values of the individuals in the population are determined and sorted, and the three grey wolf individuals with the highest fitness are selected, and the fitness from high to low is alpha, beta and delta wolf, and the rest is omega wolf;

[0194] The grey wolf chases the prey and updates the position of the grey wolf individual, the fitness values of each grey wolf are calculated using the objective function, and the ranking is performed, and a certain proportion of grey wolf individuals with low fitness are selected, and the Cauchy mutation is performed, and the fitness is recalculated and updated after mutation;

[0195] It is judged whether the maximum iteration number is reached, and the next iteration or the result is output.

[0196] Embodiment three

[0197] The embodiment provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to realize the steps in the indoor radiant floor system multi-objective regulation and control method based on load prediction in the above embodiment one.

[0198] Embodiment four

[0199] The embodiment provides a computer device, which comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor realizes the steps in the indoor radiant floor system multi-objective regulation and control method based on load prediction in the above embodiment one when executing the program.

[0200] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system or a computer program product. Therefore, the present application can be in the form of a hardware embodiment, a software embodiment or an embodiment combining software and hardware aspects. Moreover, the present application can be in the form of a computer program product implemented on one or more computer usable storage media (including but not limited to magnetic disk storage and optical storage, etc.) containing computer usable program code.

[0201] The embodiments of methods, apparatuses (systems) and computer program products according to the present application can be described in the general context of method steps and processes, which can be implemented in one embodiment by a program of instructions on a computer-readable storage medium executed by a computer or other programmable apparatus. The apparatuses can be specially constructed for executing the embodiments of methods, apparatuses (systems) and computer program products according to the present application or can include a computer or other programmable apparatus. Figure 1 one or more functions specified in the flow or flows and / or blocks. Figure 1 one or more functions specified in the flow or flows and / or blocks.

[0202] These computer program instructions can also be stored in a computer-readable storage medium that can direct a computer or other programmable apparatus to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instructions which implement the flow Figure 1 one or more functions specified in the flow or flows and / or blocks. Figure 1 one or more functions specified in the flow or flows and / or blocks.

[0203] These computer program instructions can also be loaded onto a computer or other programmable apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the flow Figure 1 one or more functions specified in the flow or flows and / or blocks. Figure 1 one or more functions specified in the flow or flows and / or blocks.

[0204] Those skilled in the art can understand that all or part of the flow of the above-mentioned embodiment method can be completed by computer program instructions instructing related hardware, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the flow of the above-mentioned embodiment of each method. The storage medium can be a magnetic disc, an optical disc, a read-only memory (ROM) or a random access memory (RAM), etc.

[0205] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. For those skilled in the art, the present application can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A multi-objective control method for indoor radiant floor systems based on load forecasting, characterized in that, include: Acquire indoor environmental parameters, outdoor environmental parameters, indoor occupant activity information, equipment parameters, and air conditioning system operation information; Based on indoor environmental parameters, outdoor environmental parameters, indoor occupant activity information, and equipment parameters, a cooling and humidity load prediction model is used to obtain the cooling load and humidity load. Based on outdoor environmental parameters, cooling load, humidity load and air conditioning system operation information, an indoor environment and energy consumption prediction model is used to obtain indoor temperature, condensation temperature difference, air system energy consumption and water system energy consumption. Using outdoor environmental parameters, cooling load, humidity load, and air conditioning system operation information as variables, objective functions for indoor temperature, air conditioning PMV, condensation temperature difference, air system energy consumption, and water system energy consumption are constructed respectively, and corresponding weights are configured to calculate the overall objective function. By setting the operating parameters of the air conditioning system as constraints, the overall objective function is solved to obtain the optimal control parameters; The constraints include air volume constraints, water pump status constraints, and floor water supply temperature constraints. The indoor environmental parameters include: indoor temperature, indoor humidity, floor surface temperature, and condensation temperature difference; the outdoor environmental parameters include: outdoor temperature, outdoor humidity, solar radiation intensity, and outdoor wind speed; the indoor occupant activity information includes: occupant moisture dissipation, human metabolic rate, clothing thermal resistance, and occupant activity time; the equipment parameters include: lighting heat dissipation, equipment heat dissipation, and lighting equipment start-up and shutdown time; the air conditioning system operation information includes: fan airflow, radiant floor water supply pump on / off status, radiant panel water supply temperature, air system energy consumption, and water system energy consumption.

2. The multi-objective control method for indoor radiant floor systems based on load prediction according to claim 1, characterized in that, Using outdoor environmental parameters, cooling load, humidity load, and air conditioning system operation information as variables, objective functions are constructed for indoor temperature, air conditioning PMV, condensation temperature difference, air system energy consumption, and water system energy consumption, respectively. The methods include: Using outdoor temperature, outdoor humidity, cooling load, wet load, fresh air unit air volume, radiant floor water supply temperature, and radiant floor water supply pump status as variables, the indoor air temperature is set, and an indoor temperature objective function is constructed based on the difference between the indoor air temperature and the user-set value. Using outdoor temperature, outdoor humidity, cooling load, wet load, fresh air unit air volume, radiant floor water supply temperature, and radiant floor water supply pump status as variables, construct the air conditioning PMV objective function; Using outdoor temperature, outdoor humidity, cooling load, wet load, fresh air volume, radiant floor water supply temperature, and radiant floor water supply pump status as variables, construct an objective function for condensation temperature difference; Using outdoor temperature, outdoor humidity, cooling load, wet load, fresh air volume, radiant floor water supply temperature, and radiant floor water supply pump status as variables, construct an objective function for the energy consumption of the air system. Using outdoor temperature, outdoor humidity, cooling load, wet load, fresh air volume, radiant floor water supply temperature, and radiant floor water supply pump status as variables, an objective function for water system energy consumption is constructed.

3. The multi-objective control method for indoor radiant floor systems based on load prediction according to claim 2, characterized in that, Using outdoor environmental parameters, cooling load, humidity load, and air conditioning system operating information as variables, objective functions are constructed for indoor temperature, air conditioning PMV, condensation temperature difference, air system energy consumption, and water system energy consumption, respectively, and corresponding weights are assigned to calculate the overall objective function; the method includes: Based on the objective functions of indoor temperature, condensation temperature difference, air system energy consumption, and water system energy consumption, and their corresponding weights, the sum of their products is calculated to obtain the overall objective function.

4. The multi-objective control method for indoor radiant floor systems based on load prediction according to claim 2, characterized in that, Using outdoor environmental parameters, cooling load, humidity load, and air conditioning system operating information as variables, objective functions are constructed for indoor temperature, air conditioning PMV, condensation temperature difference, air system energy consumption, and water system energy consumption, respectively, and corresponding weights are assigned to calculate the overall objective function; the method includes: Based on the objective functions of air conditioning PMV, condensation temperature difference, air system energy consumption, and water system energy consumption, and their corresponding weights, the sum of their products is calculated to obtain the overall objective function.

5. The multi-objective control method for indoor radiant floor systems based on load prediction according to claim 2, characterized in that, Solving the overall objective function to obtain the optimal control parameters can be achieved through methods including: An improved gray wolf optimization algorithm is used to randomly generate gray wolf individuals. These gray wolf individuals are then input into an indoor environment and energy consumption prediction model to obtain indoor temperature, condensation temperature difference, air system energy consumption, and water system energy consumption. The gray wolf individuals include: outdoor temperature, outdoor humidity, cooling load, wet load, fresh air unit air volume, radiant floor water supply temperature, and radiant floor water supply pump status. Based on the overall objective function, the fitness values ​​of individuals in the population are determined and sorted. The three gray wolf individuals with the highest fitness are selected, and their fitness values ​​from high to low are α, β, and δ wolves, while the rest are ω wolves. The gray wolves track their prey and update the location of individual gray wolves. The fitness value of each gray wolf is calculated using an objective function and ranked. At the same time, a certain proportion of gray wolf individuals with poor fitness ranking are selected and subjected to Cauchy mutation. After mutation, their fitness is recalculated and updated. Determine if the maximum number of iterations has been reached, then proceed to the next iteration or output the result.

6. A multi-objective control system for indoor radiant floor systems based on load prediction, characterized in that, include: The data acquisition module is configured to acquire indoor environmental parameters, outdoor environmental parameters, indoor occupant activity information, equipment parameters, and air conditioning system operation information. The load forecasting module is configured to obtain the cooling load and the wet load based on indoor environmental parameters, outdoor environmental parameters, indoor occupant activity information and equipment parameters, using a cooling and wet load forecasting model. The environment and energy consumption prediction module is configured to: based on outdoor environmental parameters, cooling load, humidity load and air conditioning system operation information, use an indoor environment and energy consumption prediction model to obtain indoor temperature, condensation temperature difference, air system energy consumption and water system energy consumption; The objective function construction module is configured to: construct objective functions for indoor temperature, air conditioning PMV, condensation temperature difference, air system energy consumption and water system energy consumption respectively, using outdoor environmental parameters, cooling load, humidity load and air conditioning system operation information as variables, and configure corresponding weights to calculate the total objective function; The solution module is configured to: set the operating parameters of the air conditioning system as constraints, solve the overall objective function, and obtain the optimal control parameters; The constraints include air volume constraints, water pump status constraints, and floor water supply temperature constraints. The indoor environmental parameters include: indoor temperature, indoor humidity, floor surface temperature, and condensation temperature difference; the outdoor environmental parameters include: outdoor temperature, outdoor humidity, solar radiation intensity, and outdoor wind speed; the indoor occupant activity information includes: occupant moisture dissipation, human metabolic rate, clothing thermal resistance, and occupant activity time; the equipment parameters include: lighting heat dissipation, equipment heat dissipation, and lighting equipment start-up and shutdown time; the air conditioning system operation information includes: fan airflow, radiant floor water supply pump on / off status, radiant panel water supply temperature, air system energy consumption, and water system energy consumption.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps in the multi-objective control method for indoor radiant floor systems based on load prediction as described in any one of claims 1-5.

8. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps in the multi-objective control method for indoor radiant floor systems based on load prediction as described in any one of claims 1-5.

Images