An optimization and adjustment method for ground source heat pump system

Abstract

The present invention discloses an optimization and regulation method for a ground source heat pump system, comprising obtaining historical data and operation data of the ground source heat pump system, calculating historical released heat according to the historical data, optimizing and judging according to the pump side data and the environmental indicators, calculating heat correlation, calculating the use degree coefficient according to the user indicators, determining liquid flow efficiency, first power demand and second power demand, constructing a ground source heat pump system target optimization function according to the energy consumption indicators, constructing a ground source heat pump system optimization and regulation model, inputting the operation data of the ground source heat pump system to be optimized into the ground source heat pump system optimization and regulation model to obtain the power demand and liquid flow demand, and optimizing and regulating according to the power demand and liquid flow demand. This method can not only improve the accuracy and efficiency of the optimization and regulation of the ground source heat pump system, but also has good interpretability, which is of great significance to reducing operating costs and energy conservation and emission reduction.

Description

Technical Field

[0001] The present invention relates to the technical field of ground source heat pumps, and in particular to an optimization and regulation method for a ground source heat pump system. Background Art

[0002] The ground source heat pump system is a system that uses shallow geothermal resources on the earth's surface as cold and heat sources. It achieves efficient conversion and utilization of energy through a heating system composed of a water source heat pump unit, a geothermal energy exchange system and a system within the building. It has the advantages of high energy efficiency, stable operation and environmental friendliness, and is widely used in the field of building heating and cooling.

[0003] In practical applications, the operating efficiency of ground-source heat pump systems is often affected by geological conditions, climatic conditions, system configuration and operating strategies. The traditional ground-source heat pump system adjustment methods mostly rely on empirical parameters or fixed modes, which are difficult to adjust accurately according to real-time working conditions, resulting in large differences in the operating efficiency of the system in different seasons and under different load conditions, and facing challenges such as reduced energy efficiency and increased operating costs. The rapid development of technologies such as big data and artificial intelligence has provided new ideas and methods for the optimization and adjustment of ground-source heat pump systems. By collecting system operating parameters, establishing a historical database, and combining intelligent algorithms for data analysis and prediction, the ground-source heat pump system can be accurately controlled and optimized. Based on this background, a timely, accurate and efficient optimization and adjustment method for ground-source heat pump systems is designed by comprehensively using a variety of intelligent prediction and optimization algorithms to overcome the shortcomings of existing optimization and adjustment methods, and to optimize and adjust the operating parameters of ground-source heat pump systems in a timely and accurate manner, which is of great significance to improving system energy efficiency and user experience and reducing operating costs. Summary of the invention

[0004] The purpose of the present invention is to provide an optimization regulation method for a ground source heat pump system.

[0005] To achieve the above object, the present invention is implemented according to the following technical solutions:

[0006] The present invention comprises the following steps:

[0007] Acquire historical data and operating data of the ground source heat pump system, and pre-process the historical data and the operating data;

[0008] Feature extraction of the historical data to obtain seasonal parameters and historical liquid flow, calculation of historical heat release according to the historical data, and formation of a seasonal database with the historical heat release and historical liquid flow;

[0009] The operation data is divided into pump side data and user side data, the user side data is clustered to obtain environment indicators, user indicators and energy consumption indicators, optimization and judgment are performed according to the pump side data and the environment indicators, and heat correlation is calculated according to the pump side data;

[0010] Input the user class index into a usage degree function to obtain a usage degree coefficient, determine a liquid flow efficiency and a first required power according to the usage degree coefficient and the season database, and determine a second required power according to the heat correlation, the usage degree coefficient and the first required power;

[0011] A target optimization function of a geothermal heat pump system is constructed according to the energy consumption indicators, an optimization and regulation model of a geothermal heat pump system is constructed according to the second required power, the heat correlation, the usage coefficient and the liquid flow efficiency, and the operating data of the geothermal heat pump system to be optimized is input into the optimization and regulation model of the geothermal heat pump system to obtain the required power and the required liquid flow.

[0012] Furthermore, the method for calculating the historical heat release according to the historical data includes:

[0013] Feature extraction of the historical data to obtain seasonal parameters and historical fluid flow; the seasonal parameters include historical geothermal exchange fluid temperature, historical pump total power, historical outdoor temperature and historical time;

[0014] The historical heat is calculated based on the historical geothermal exchange fluid temperature, the historical outdoor temperature and the historical fluid flow rate. The historical heat demand is calculated based on the historical total pump power and the historical fluid flow rate. The historical heat release is calculated based on the historical heat and the historical heat demand. The historical heat release expression is:

[0015]

[0016] Where Q he is the temperature adjustment time Δt u Historical heat release of the local source heat pump system, P i is the power of the i-th pump, n is the number of pumps, COP is the standard heating performance coefficient of the pump, V h is the historical liquid flow rate, V0 is the liquid flow rate corresponding to the standard heating performance coefficient COP of the standard pump, ρ w is the density of the geothermal exchange fluid, c w is the specific heat capacity of the geothermal exchange fluid, ΔT1 is the difference between the historical geothermal exchange fluid temperature and the historical outdoor temperature;

[0017] The historical heat release and historical liquid flow are taken as a set of seasonal data, and the seasonal data are labeled according to the historical outdoor temperature and historical time, and a seasonal database is formed based on the seasonal data.

[0018] Furthermore, the method for optimizing and determining based on the pump-side data and the environmental indicators includes:

[0019] The pump side data includes current pump power, current pump power quantity, current geothermal exchange fluid temperature and current fluid flow rate;

[0020] A hierarchical clustering algorithm is used to divide the user-side data into environmental indicators, user indicators and energy consumption indicators; the environmental indicators include the current outdoor temperature, the current time and the preset temperature;

[0021] If the current geothermal exchange fluid temperature is consistent with the preset temperature, the ground source heat pump system temperature is balanced, and the current pump power is further compared with the optimal pump power;

[0022] If the current pump power is equal to the optimal pump power, the current ground source heat pump system reaches the optimal working state and no optimization adjustment operation is performed; if the current pump power is not equal to the optimal pump power, the number and power of pumps are adjusted;

[0023] If the current geothermal exchange fluid temperature is inconsistent with the preset temperature, the geothermal heat pump system is optimized and adjusted according to the operating data and the seasonal database.

[0024] Furthermore, the method for optimizing and determining based on the pump-side data and the environmental indicators includes:

[0025] The pump side data includes current pump power, current pump power quantity, current geothermal exchange fluid temperature and current fluid flow rate;

[0026] A hierarchical clustering algorithm is used to divide the user-side data into environmental indicators, user indicators and energy consumption indicators; the environmental indicators include the current outdoor temperature, the current time and the preset temperature;

[0027] If the current geothermal exchange fluid temperature is consistent with the preset temperature, the ground source heat pump system temperature is balanced, and the current pump power is further compared with the optimal pump power;

[0028] If the current pump power is equal to the optimal pump power, the current ground source heat pump system reaches the optimal working state and no optimization adjustment operation is performed; if the current pump power is not equal to the optimal pump power, the number and power of pumps are adjusted;

[0029] If the current geothermal exchange fluid temperature is inconsistent with the preset temperature, the geothermal heat pump system is optimized and adjusted according to the operating data and the seasonal database.

[0030] Furthermore, the method for calculating the heat correlation degree according to the pump side data includes:

[0031] According to the current time and the current outdoor temperature, the seasonal database tag is matched to obtain seasonal data. The current heat is calculated according to the current geothermal exchange fluid temperature and the current fluid flow rate. The correlation between the current heat and the historical released heat is calculated. The expression is:

[0032]

[0033] Where r(Q he , Q nh ) is used to calculate the current heat Q nh and historical heat release Q he The heat correlation, n is the number of data sets, w Q is the heat weight, is the current heat Q of the i-th group nhi The distribution probability of Heat Q released for the i-th group of history hei The distribution probability, w T is the temperature weight, is the historical heat exchange fluid temperature T of the i-th group hi The distribution probability of is the current geothermal exchange fluid temperature T of the i-th group ni The distribution probability, w V is the liquid flow weight coefficient, is the historical liquid flow rate V of the i-th group hi The distribution probability of is the current liquid flow rate V of the i-th group ni The distribution probability of .

[0034] Furthermore, the method for obtaining the usage degree coefficient includes:

[0035] The user-type indicators include heating floor height, number of heating households and heating duration. The user-type indicators are input into the usage degree function to obtain the usage degree coefficient, which is expressed as:

[0036]

[0037] Among them U i is the usage coefficient corresponding to the user class index of group i, w H is the heating floor weight, H i is the heating floor height, H max is the building height, w N is the weight of heating households, N i is the number of heating households, N maxi =N max ·H i / H max is the maximum number of heating households corresponding to the current heating floor height, N max is the total number of households in the building, t iis the heating time, and t0 is the standard heating time.

[0038] Further, the method for determining the liquid flow efficiency, the first required power and the second required power includes:

[0039] The historical liquid flow rate and historical heat release are determined by matching seasonal data, and the liquid flow efficiency is determined based on the utilization coefficient and historical liquid flow rate. The expression is:

[0040]

[0041] where η V is the liquid flow efficiency, V h is the historical liquid flow rate, V max is the maximum liquid flow rate;

[0042] The preset heat is calculated based on the preset temperature and liquid flow efficiency, and the first required power is determined based on the preset heat, historical released heat and the standard heating performance coefficient of the pump. The expression is:

[0043]

[0044] Where P first is the first required power, is the preset heat, ΔT2 is the difference between the preset temperature and the current outdoor temperature, and the preset heat Q plan With the historical release of heat Q he The sum is the first heat requirement;

[0045] The second required power is determined according to the heat correlation, the usage degree coefficient and the first required power, and the expression is:

[0046]

[0047] Where P second is the second required power, w1 and w2 are weight coefficients, and U0 is the common usage coefficient.

[0048] Furthermore, a method for constructing a target optimization function of a ground source heat pump system according to the energy consumption index includes:

[0049] The energy consumption indicators include electricity unit price, pump power deviation, pipeline heat loss and carbon emission. The target optimization function is constructed according to the energy consumption indicators. The goal of the target optimization function is to reduce the economic operation cost and environmental pollution of the system. The target optimization function expression of the ground source heat pump system is:

[0050]

[0051] Where f(P) is the target optimization function of the ground source heat pump system, P secondiis the second required power of the ground source heat pump system corresponding to period i, t i is the working time corresponding to the second power demand, m is the number of segments of the second power demand, w3 is the economic weight, PRICE i is the electricity price in period i, w4 is the pollution weight, ε e is the electricity carbon emission coefficient, w5 is the energy consumption weight, P ij is the power of the pump in period i, P0 is the optimal power of the pump, t is the total heating time, γ is the heat loss of the pipeline system in the ground source heat pump system, and δ is the loss rate of the geothermal exchange fluid.

[0052] Furthermore, the method for constructing the optimization and regulation model of the ground source heat pump system includes:

[0053] The second required power, heat correlation, usage degree coefficient and liquid flow efficiency are used to form an optimization data set, and the optimization data set is divided into a training set and a test set;

[0054] Construct an optimization and regulation model of the ground source heat pump system based on a multi-objective cosmic optimization algorithm. The optimization and regulation of the ground source heat pump system includes an input layer, a hidden layer, and a data output layer.

[0055] The training set is preprocessed through the input layer, and the preprocessed data enters the hidden layer. The number of hidden layer nodes is set, and the ReLU activation function is used. The training set is used to train the model to obtain the prediction results. The prediction results are output through the output layer to output the required power and required liquid flow;

[0056] The multi-objective universe optimization algorithm is used to optimize the weights of the optimization and regulation model of the ground-source heat pump system. The target optimization function of the ground-source heat pump system is used to evaluate the quality of each generation of solutions, and the solutions and model weights that meet the economic operation cost and the lowest environmental pollution are selected. Multiple iterations are performed until the set convergence standard is reached.

[0057] The economic cost difference between the predicted value and the true value is evaluated by the mean square loss function, the environmental impact difference between the predicted value and the standard value is measured by the cross entropy loss function, the stochastic gradient descent optimizer is used to perform secondary weight optimization on the optimization and regulation model of the ground source heat pump system, and the test set is used to evaluate the optimization and regulation model of the ground source heat pump system;

[0058] The operating data of the ground source heat pump system to be optimized is input into the ground source heat pump system optimization and regulation model to obtain the required power and required liquid flow, and the liquid flow, the number of pumps and the operating power are adjusted according to the required power and the required liquid flow.

[0059] The beneficial effects of the present invention are:

[0060] The present invention is an optimization and adjustment method for a ground source heat pump system. Compared with the prior art, the present invention has the following technical effects:

[0061] The present invention can improve the accuracy of optimization and regulation through feature extraction, optimization judgment, calculation of heat correlation and usage degree coefficient, determination of liquid flow efficiency and first demand power, determination of second demand power and model construction steps, thereby improving the speed and accuracy of optimization and regulation of the ground source heat pump system, can greatly save resources, improve the efficiency of optimization and regulation, can realize the economy and efficiency of optimization and regulation of the ground source heat pump system, optimize and regulate the ground source heat pump system in real time, provide guarantee for the timeliness and accuracy of optimization and regulation of the ground source heat pump system, have important significance for improving system energy efficiency, reducing operating costs and enhancing user experience, can adapt to the optimization and regulation needs of ground source heat pump systems of different ground source heat pump systems and different users, and has certain universality. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 The present invention is a flowchart of the steps of an optimization and adjustment method for a ground source heat pump system. DETAILED DESCRIPTION

[0063] The present invention is further described below by means of specific embodiments. The illustrative embodiments and descriptions of the present invention are used to explain the present invention but are not intended to limit the present invention.

[0064] The present invention provides an optimization and adjustment method for a ground source heat pump system, comprising the following steps:

[0065] like Figure 1 As shown, in this embodiment, the following steps are included:

[0066] Acquire historical data and operating data of the ground source heat pump system, and pre-process the historical data and the operating data;

[0067] Feature extraction of the historical data to obtain seasonal parameters and historical liquid flow, calculation of historical heat release according to the historical data, and formation of a seasonal database with the historical heat release and historical liquid flow;

[0068] The operation data is divided into pump side data and user side data, the user side data is clustered to obtain environment indicators, user indicators and energy consumption indicators, optimization and judgment are performed according to the pump side data and the environment indicators, and heat correlation is calculated according to the pump side data;

[0069] Input the user class index into a usage degree function to obtain a usage degree coefficient, determine a liquid flow efficiency and a first required power according to the usage degree coefficient and the season database, and determine a second required power according to the heat correlation, the usage degree coefficient and the first required power;

[0070] A target optimization function of a geothermal heat pump system is constructed according to the energy consumption indicators, an optimization and regulation model of a geothermal heat pump system is constructed according to the second required power, the heat correlation, the usage coefficient and the liquid flow efficiency, and the operating data of the geothermal heat pump system to be optimized is input into the optimization and regulation model of the geothermal heat pump system to obtain the required power and the required liquid flow.

[0071] In this embodiment, the method for calculating the historical released heat according to the historical data includes:

[0072] Feature extraction of the historical data to obtain seasonal parameters and historical fluid flow; the seasonal parameters include historical geothermal exchange fluid temperature, historical pump total power, historical outdoor temperature and historical time;

[0073] The historical heat is calculated based on the historical geothermal exchange fluid temperature, the historical outdoor temperature and the historical fluid flow rate. The historical heat demand is calculated based on the historical total pump power and the historical fluid flow rate. The historical heat release is calculated based on the historical heat and the historical heat demand. The historical heat release expression is:

[0074]

[0075] Where Q he is the temperature adjustment time Δt u Historical heat release of the local source heat pump system, P i is the power of the i-th pump, n is the number of pumps, COP is the standard heating performance coefficient of the pump, V h is the historical liquid flow rate, V0 is the liquid flow rate corresponding to the standard heating performance coefficient COP of the standard pump, ρ w is the density of the geothermal exchange fluid, c w is the specific heat capacity of the geothermal exchange fluid, ΔT1 is the difference between the historical geothermal exchange fluid temperature and the historical outdoor temperature;

[0076] The historical heat release and historical liquid flow are taken as a set of seasonal data, and the seasonal data are labeled according to the historical outdoor temperature and historical time, and a seasonal database is formed based on the seasonal data;

[0077] In the actual evaluation, two sets of historical data of the ground source heat pump system of a 24-story residential community were randomly obtained: (2023-01-05-12:00, historical liquid flow rate 1m 3 / h, historical geothermal exchange fluid temperature 18°C, historical outdoor temperature -2°C, historical pump total power 10kW), (2023-11-15-12:00, historical fluid flow 0.8m 3 / h, historical geothermal exchange fluid temperature 20℃, historical outdoor temperature 10℃, historical total pump power 6kW,);

[0078] The liquid flow rate V0 corresponding to the standard heating performance coefficient COP of the standard pump is 0.8m 3 , the standard heating performance coefficient COP of the pump is 3.5, and the heating time Δt u The geothermal exchange fluid is shallow surface water. Substituting the above two sets of data into the historical heat release expression, the heat release in the 60-minute heating time is 73900kJ and 42160kJ.

[0079] In this embodiment, the method for optimizing and determining based on the pump-side data and the environmental indicators includes:

[0080] The pump side data includes current pump power, current pump power quantity, current geothermal exchange fluid temperature and current fluid flow rate;

[0081] A hierarchical clustering algorithm is used to divide the user-side data into environmental indicators, user indicators and energy consumption indicators; the environmental indicators include the current outdoor temperature, the current time and the preset temperature;

[0082] If the current geothermal exchange fluid temperature is consistent with the preset temperature, the ground source heat pump system temperature is balanced, and the current pump power is further compared with the optimal pump power;

[0083] If the current pump power is equal to the optimal pump power, the current ground source heat pump system reaches the optimal working state and no optimization adjustment operation is performed; if the current pump power is not equal to the optimal pump power, the number and power of pumps are adjusted;

[0084] If the current geothermal exchange fluid temperature is inconsistent with the preset temperature, optimizing and adjusting the geothermal heat pump system according to the operation data and the seasonal database;

[0085] In the actual evaluation, a set of ground source heat pump system operation data of a 24-story residential community was randomly obtained: 2024-11-05-12:00, (pump side data: current total pump power 5.8kW, current geothermal exchange fluid temperature 16℃, current fluid flow 0.7m 3 / h), (user-side data: 1. Environmental indicators: current outdoor temperature 11°C, preset temperature 20°C; 2. User indicators: heating floor height 22 floors, heating number 71 households, heating time 18 hours);

[0086] The current geothermal exchange fluid temperature of 16°C is inconsistent with the preset temperature of 20°C. The optimization judgment result is to optimize the adjustment of power and liquid flow.

[0087] In this embodiment, the method for calculating the heat correlation degree according to the pump side data includes:

[0088] According to the current time and the current outdoor temperature, the seasonal database tag is matched to obtain seasonal data. The current heat is calculated according to the current geothermal exchange fluid temperature and the current fluid flow rate. The correlation between the current heat and the historical released heat is calculated. The expression is:

[0089]

[0090] Where r(Q he , Q nh ) is used to calculate the current heat Q nh and historical heat release Q he The heat correlation, n is the number of data sets, w Q is the heat weight, is the current heat Q of the i-th group nhi The distribution probability of Heat Q released for the i-th group of history hei The distribution probability, w T is the temperature weight, is the historical heat exchange fluid temperature T of the i-th group hi The distribution probability of is the current geothermal exchange fluid temperature T of the i-th group ni The distribution probability, w V is the liquid flow weight coefficient, is the historical liquid flow rate V of the i-th group hi The distribution probability of is the current liquid flow rate V of the i-th group ni The distribution probability of

[0091] In the actual evaluation, the current heat Q corresponding to the operation data of the ground source heat pump system of a 24-story residential community in this group is calculated. nh The historical heat release is 14630 kJ. The seasonal data is obtained by matching the seasonal database tag with the current time and the current outdoor temperature: he The historical liquid flow rate is 28760 kJ and 0.8 m 3 / h;

[0092] Combining the data of the previous and next time points corresponding to the current heat and the historical heat release, the heat correlation is calculated to be 0.789.

[0093] In this embodiment, the method for obtaining the usage degree coefficient includes:

[0094] The user-type indicators include heating floor height, number of heating households and heating duration. The user-type indicators are input into the usage degree function to obtain the usage degree coefficient, which is expressed as:

[0095]

[0096] Among them U iis the usage coefficient corresponding to the user class index of group i, w H is the heating floor weight, H i is the heating floor height, H max is the building height, w N is the weight of heating households, N i is the number of heating households, N maxi =N max ·H i / H max is the maximum number of heating households corresponding to the current heating floor height, N max is the total number of households in the building, t i is the heating time, t0 is the standard heating time;

[0097] In the actual assessment, a 24-story residential community has a building height of 24 floors and a single-story household number of 4 /

[0098] The standard heating time is 16 hours. The user-type indicators of this group of operating data are substituted into the degree function to obtain the utilization degree coefficient of the ground source heat pump system corresponding to this group of operating data, which is 0.738.

[0099] In this embodiment, the method for determining the liquid flow efficiency, the first required power and the second required power includes:

[0100] The historical liquid flow rate and historical heat release are determined by matching seasonal data, and the liquid flow efficiency is determined based on the utilization coefficient and historical liquid flow rate. The expression is:

[0101]

[0102] where η V is the liquid flow efficiency, V h is the historical liquid flow rate, V max is the maximum liquid flow rate;

[0103] The preset heat is calculated based on the preset temperature and liquid flow efficiency, and the first required power is determined based on the preset heat, historical released heat and the standard heating performance coefficient of the pump. The expression is:

[0104]

[0105] Where P first is the first required power, is the preset heat, ΔT2 is the difference between the preset temperature and the current outdoor temperature, and the preset heat Q plan With the historical release of heat Q he The sum is the first heat requirement;

[0106] The second required power is determined according to the heat correlation, the usage degree coefficient and the first required power, and the expression is:

[0107]

[0108] Where P second is the second required power, w1 and w2 are weight coefficients, and U0 is the common use degree coefficient;

[0109] In the actual evaluation, the liquid flow efficiency of the ground source heat pump system operating data of a 24-story residential area in this group is 94.23%, the first demand power is 5.46154kW, the weight coefficient w1 is 0.4, w2 is 0.4, the common usage coefficient U0 is 0.85, and the second demand power is calculated to be 6.92829kW.

[0110] In this embodiment, the method for constructing a target optimization function of a ground source heat pump system according to the energy consumption index includes:

[0111] The energy consumption indicators include electricity unit price, pump power deviation, pipeline heat loss and carbon emission. The target optimization function is constructed according to the energy consumption indicators. The goal of the target optimization function is to reduce the economic operation cost and environmental pollution of the system. The target optimization function expression of the ground source heat pump system is:

[0112]

[0113] Where f(P) is the target optimization function of the ground source heat pump system, P secondi is the second required power of the ground source heat pump system corresponding to period i, t i is the working time corresponding to the second power demand, m is the number of segments of the second power demand, w3 is the economic weight, PRICE i is the electricity price in period i, w4 is the pollution weight, ε e is the electricity carbon emission coefficient, w5 is the energy consumption weight, P ij is the power of the pump in period i, P0 is the optimal power of the pump, t is the total heating time, γ is the heat loss of the pipeline system in the ground source heat pump system, and δ is the loss rate of the geothermal exchange fluid;

[0114] In the actual evaluation, the electricity price is calculated based on the peak and valley values ​​and phased pricing according to local standards, and the carbon emission coefficient of electricity is ε e Taking 0.5703tCO2 / MWh, the optimal pump power is 1.2kW / unit, γ is 30%, and δ is 3%.

[0115] In this embodiment, the method for constructing the optimization and regulation model of the ground source heat pump system includes:

[0116] The second required power, heat correlation, usage degree coefficient and liquid flow efficiency are used to form an optimization data set, and the optimization data set is divided into a training set and a test set;

[0117] Construct an optimization and regulation model of the ground source heat pump system based on a multi-objective cosmic optimization algorithm. The optimization and regulation of the ground source heat pump system includes an input layer, a hidden layer, and a data output layer.

[0118] The training set is preprocessed through the input layer, and the preprocessed data enters the hidden layer. The number of hidden layer nodes is set, and the ReLU activation function is used. The training set is used to train the model to obtain the prediction results. The prediction results are output through the output layer to output the required power and required liquid flow;

[0119] The multi-objective universe optimization algorithm is used to optimize the weights of the optimization and regulation model of the ground-source heat pump system. The target optimization function of the ground-source heat pump system is used to evaluate the quality of each generation of solutions, and the solutions and model weights that meet the economic operation cost and the lowest environmental pollution are selected. Multiple iterations are performed until the set convergence standard is reached.

[0120] The economic cost difference between the predicted value and the true value is evaluated by the mean square loss function, the environmental impact difference between the predicted value and the standard value is measured by the cross entropy loss function, the stochastic gradient descent optimizer is used to perform secondary weight optimization on the optimization and regulation model of the ground source heat pump system, and the test set is used to evaluate the optimization and regulation model of the ground source heat pump system;

[0121] The operating data of the ground source heat pump system to be optimized is input into the ground source heat pump system optimization adjustment model to obtain the required power of 7.2kW and the required liquid flow of 0.75m 3 / h, the adjusted liquid flow rate is 0.75m 3 / h, and 5 pumps are turned on at the same time, with each pump operating at a power of 1.2kW.

Claims

1. An optimization and adjustment method for a ground source heat pump system, characterized in that: The following steps are involved: S1. Acquire historical data and operating data of a ground source heat pump system, and pre-process the historical data and the operating data; S2. feature extracting the historical data to obtain seasonal parameters and historical liquid flow, calculating historical heat release according to the historical data, and forming a seasonal database with the historical heat release and historical liquid flow; S3, dividing the operation data into pump side data and user side data, clustering the user side data to obtain environmental indicators, user indicators and energy consumption indicators, performing optimization and judgment based on the pump side data and environmental indicators, and calculating the heat correlation based on the pump side data; S4, inputting the user class index into a usage degree function to obtain a usage degree coefficient, determining a liquid flow efficiency and a first required power according to the usage degree coefficient and the season database, and determining a second required power according to the heat correlation, the usage degree coefficient and the first required power; S5. Construct a target optimization function of the ground source heat pump system according to the energy consumption indicators, construct an optimization and regulation model of the ground source heat pump system according to the second required power, the heat correlation, the usage coefficient and the liquid flow efficiency, and input the operating data of the ground source heat pump system to be optimized into the optimization and regulation model of the ground source heat pump system to obtain the required power and required liquid flow.

2. The optimization and adjustment method of a ground source heat pump system according to claim 1, characterized in that: The method for calculating historical heat release according to the historical data comprises: Feature extraction of the historical data to obtain seasonal parameters and historical fluid flow; the seasonal parameters include historical geothermal exchange fluid temperature, historical pump total power, historical outdoor temperature and historical time; The historical heat is calculated based on the historical geothermal exchange fluid temperature, the historical outdoor temperature and the historical fluid flow rate. The historical heat demand is calculated based on the historical total pump power and the historical fluid flow rate. The historical heat release is calculated based on the historical heat and the historical heat demand. The historical heat release expression is: Where Q he is the temperature adjustment time Δt u Historical heat release of the local source heat pump system, P i is the power of the i-th pump, n is the number of pumps, COP is the standard heating performance coefficient of the pump, V h is the historical liquid flow rate, V0 is the liquid flow rate corresponding to the standard heating performance coefficient COP of the standard pump, ρ w is the density of the geothermal exchange fluid, c w is the specific heat capacity of the geothermal exchange fluid, ΔT1 is the difference between the historical geothermal exchange fluid temperature and the historical outdoor temperature; The historical heat release and historical liquid flow are taken as a set of seasonal data, and the seasonal data are labeled according to the historical outdoor temperature and historical time, and a seasonal database is formed based on the seasonal data.

3. The optimization and adjustment method of a ground source heat pump system according to claim 1, characterized in that: The method for optimizing and determining based on the pump-side data and environmental indicators includes: The pump side data includes current pump power, current pump power quantity, current geothermal exchange fluid temperature and current fluid flow rate; A hierarchical clustering algorithm is used to divide the user-side data into environmental indicators, user indicators and energy consumption indicators; the environmental indicators include the current outdoor temperature, the current time and the preset temperature; If the current geothermal exchange fluid temperature is consistent with the preset temperature, the ground source heat pump system temperature is balanced, and the current pump power is further compared with the optimal pump power; If the current pump power is equal to the optimal pump power, the current ground source heat pump system reaches the optimal working state and no optimization adjustment operation is performed; if the current pump power is not equal to the optimal pump power, the number and power of pumps are adjusted; If the current geothermal exchange fluid temperature is inconsistent with the preset temperature, the geothermal heat pump system is optimized and adjusted according to the operating data and the seasonal database.

4. The optimization and adjustment method of a ground source heat pump system according to claim 1, characterized in that: The method for calculating the heat correlation degree according to the pump side data includes: According to the current time and the current outdoor temperature, the seasonal database tag is matched to obtain seasonal data. The current heat is calculated according to the current geothermal exchange fluid temperature and the current fluid flow rate. The correlation between the current heat and the historical released heat is calculated. The expression is: Where r(Q he , Q nh ) is used to calculate the current heat Q nh and historical heat release Q he The heat correlation of n is the number of data sets, w is Q is the heat weight, is the current heat Q of the i-th group nhi The distribution probability of Heat Q released for the i-th group of history hei The distribution probability, w T is the temperature weight, is the historical heat exchange fluid temperature T of the i-th group hi The distribution probability of is the current geothermal exchange fluid temperature T of the i-th group ni The distribution probability, w V is the liquid flow weight coefficient, is the historical liquid flow rate V of the i-th group hi The distribution probability of is the current liquid flow rate V of the i-th group ni The distribution probability of .

5. The optimization and adjustment method of a ground source heat pump system according to claim 1, characterized in that: The method for obtaining the usage degree coefficient includes: The user-type indicators include heating floor height, number of heating households and heating duration. The user-type indicators are input into the usage degree function to obtain the usage degree coefficient, which is expressed as: Among them U i is the usage coefficient corresponding to the user class index of group i, w H is the heating floor weight, H i is the heating floor height, H max is the building height, w N is the weight of heating households, N i is the number of heating households, N maxi =N max ·H i / H max is the maximum number of heating households corresponding to the current heating floor height, N max is the total number of households in the building, t i is the heating time, and t0 is the standard heating time.

6. The optimization and adjustment method of a ground source heat pump system according to claim 1, characterized in that: The method for determining the liquid flow efficiency, the first required power and the second required power comprises: The historical liquid flow rate and historical heat release are determined by matching seasonal data, and the liquid flow efficiency is determined based on the utilization coefficient and historical liquid flow rate. The expression is: where η V is the liquid flow efficiency, V h is the historical liquid flow rate, V max is the maximum liquid flow rate; The preset heat is calculated based on the preset temperature and liquid flow efficiency, and the first required power is determined based on the preset heat, historical released heat and the standard heating performance coefficient of the pump. The expression is: Where P first is the first required power, is the preset heat, ΔT2 is the difference between the preset temperature and the current outdoor temperature, and the preset heat Q plan With the historical release of heat Q he The sum is the first heat requirement; The second required power is determined according to the heat correlation, the usage degree coefficient and the first required power, and the expression is: Where P second is the second required power, w1 and w2 are weight coefficients, and U0 is the common usage coefficient.

7. The optimization and adjustment method of a ground source heat pump system according to claim 1, characterized in that: The method for constructing a target optimization function of a ground source heat pump system according to the energy consumption index comprises: The energy consumption indicators include electricity unit price, pump power deviation, pipeline heat loss and carbon emission. The target optimization function is constructed according to the energy consumption indicators. The goal of the target optimization function is to reduce the economic operation cost and environmental pollution of the system. The target optimization function expression of the ground source heat pump system is: Where f(P) is the target optimization function of the ground source heat pump system, P secondi is the second required power of the ground source heat pump system corresponding to period i, t i is the working time corresponding to the second power demand, m is the number of segments of the second power demand, w3 is the economic weight, PRICE i is the electricity price in period i, w4 is the pollution weight, ε e is the electricity carbon emission coefficient, w5 is the energy consumption weight, P ij is the power of the pump in period i, P0 is the optimal power of the pump, t is the total heating time, γ is the heat loss of the pipeline system in the ground source heat pump system, and δ is the loss rate of the geothermal exchange fluid.

8. The optimization and adjustment method of a ground source heat pump system according to claim 1, characterized in that: The method for constructing the optimization and regulation model of the ground source heat pump system comprises: The second required power, heat correlation, usage degree coefficient and liquid flow efficiency are used to form an optimization data set, and the optimization data set is divided into a training set and a test set; Construct an optimization and regulation model of the ground source heat pump system based on a multi-objective cosmic optimization algorithm. The optimization and regulation of the ground source heat pump system includes an input layer, a hidden layer, and a data output layer. The training set is preprocessed through the input layer, and the preprocessed data enters the hidden layer. The number of hidden layer nodes is set, and the ReLU activation function is used. The training set is used to train the model to obtain the prediction results. The prediction results are output through the output layer to output the required power and required liquid flow; The multi-objective universe optimization algorithm is used to optimize the weights of the optimization and regulation model of the ground-source heat pump system. The target optimization function of the ground-source heat pump system is used to evaluate the quality of each generation of solutions, and the solutions and model weights that meet the economic operation cost and the lowest environmental pollution are selected. Multiple iterations are performed until the set convergence standard is reached. The economic cost difference between the predicted value and the true value is evaluated by the mean square loss function, the environmental impact difference between the predicted value and the standard value is measured by the cross entropy loss function, the stochastic gradient descent optimizer is used to perform secondary weight optimization on the optimization and regulation model of the ground source heat pump system, and the test set is used to evaluate the optimization and regulation model of the ground source heat pump system; The operating data of the ground source heat pump system to be optimized is input into the ground source heat pump system optimization and regulation model to obtain the required power and required liquid flow, and the liquid flow, the number of pumps and the operating power are adjusted according to the required power and the required liquid flow.

Images