Carbon emission accounting method for ground source heat pump air conditioning system
Through the combination of data preprocessing and machine learning models, the complexity and accuracy of carbon emission accounting in ground source heat pump air conditioning systems are solved, and efficient and accurate carbon emission accounting is achieved, which is suitable for the needs of different standards.
Patent Information
- Application Number
- CN202411097946.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-12
- Publication Date
- 2024-11-19
Smart Images

Figure CN118981598A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of accounting, and in particular to a method for calculating carbon emissions from a ground-source heat pump air-conditioning system. Background Art
[0002] With the increasing severity of global climate change and environmental issues, reducing carbon emissions has become a common global challenge. In the building sector, air conditioning systems are a significant source of energy consumption and carbon emissions, making energy conservation and emission reduction crucial. As a highly efficient and environmentally friendly air conditioning technology, ground-source heat pump air conditioning systems (GSHPs) offer carbon emission accounting methods that are valuable for evaluating their environmental benefits and guiding the development of energy conservation and emission reduction strategies.
[0003] Geothermal heat pump air conditioning systems are a highly efficient and environmentally friendly air conditioning technology that utilizes shallow geothermal resources to convert energy into heat and cool buildings. However, these systems also generate a certain amount of carbon emissions during operation, primarily from electricity consumption and the manufacturing, transportation, and installation of the equipment.
[0004] Existing carbon emission accounting methods for geothermal heat pump air conditioning systems primarily include emission factor methods, mass balance methods, and field measurement methods. However, these methods require extensive data support and are complex to calculate, making them difficult to implement in practice. Furthermore, existing carbon emission accounting methods for geothermal heat pump air conditioning systems fail to fully account for their unique characteristics and complexity. Therefore, Kou Dai sought to develop a new carbon emission accounting method that could accurately and intelligently determine carbon emissions in a timely, intelligent, and efficient manner. Summary of the Invention
[0005] The purpose of the present invention is to provide a method for calculating carbon emissions from a ground-source heat pump air-conditioning system.
[0006] To achieve the above object, the present invention is implemented according to the following technical solutions:
[0007] The present invention comprises the following steps:
[0008] Collecting operating data and equipment temperature difference data of a ground source heat pump air conditioning system, and preprocessing the operating data and the equipment temperature difference data;
[0009] Screening the operating data according to carbon relevance to obtain consumption data, performing time series loss analysis on the relevant data to obtain unused energy, and subtracting the unused energy from the consumption data to obtain critical energy consumption;
[0010] Performing a time series impact analysis on the device temperature difference data according to the offset to obtain a temperature barrier coefficient, and using the temperature barrier coefficient to correct the key energy consumption to obtain correction data;
[0011] A carbon emission accounting model for a geothermal heat pump air conditioning system is constructed based on the correction data, the data to be calculated is input into the carbon emission accounting model for the geothermal heat pump air conditioning system, and a calculation result is output.
[0012] Furthermore, the method of screening the operation data according to the carbon relevance to obtain consumption data includes:
[0013] According to the similarity of the running data, a decision tree is used to perform initial classification to obtain classified data;
[0014] Calculate the information content of categorical data:
[0015]
[0016] The amount of information of the b-th classification data is The number of groups where data b is located is m, and the b-th classification data of the c-th group is z c,b , the proportion of the b-th classification data in the c-th group is b c,b , the average value of the classification data of the cth group is
[0017] The classified data with information greater than 0.32 is regarded as important data, and the weight of the important data is calculated:
[0018]
[0019] The number of important data is The number of important data in the cth group is The standard value of the important data of the cth group is ψ o , the τth important data of the cth group is ψ c,τ , the deviation of the τth important data is Δψ τ , the distance between the most informative important data and the τth important data in the cth group is The weight of the bth important data is ξ b ;
[0020] Calculate the carbon relevance of important data:
[0021]
[0022] The carbon correlation of the bth important data is θ b , the probability of carbon-containing substance w appearing under the condition of important data b is k(w|b), the probability of carbon-containing substance w appearing is k(w), and the number of important data b is The amount of carbon-containing matter w is The sth carbon-containing substance is w s , the standard value of carbon-containing material w is w o, the natural constant is e, and the control factor is The optimization coefficient is x;
[0023] The important data with carbon correlation greater than 0.417 are output as consumption data.
[0024] Furthermore, the method of performing a time series loss analysis on the relevant data to obtain unused energy includes:
[0025] Construct a state matrix based on relevant data, take the processing links as nodes, and calculate the conversion rate of the nodes:
[0026]
[0027] The conversion rate of the u-th node is The uth node The input amount of relevant data is The uth node The usage rate of relevant data is The input mass is The remaining output mass of node u is Δm u , the error coefficient is
[0028] Calculate the average probability of being treated:
[0029]
[0030] The probability of node u being processed through the lth path is The number of possible paths for node u to be processed is The average probability of node u being attacked is
[0031] Construct a weighted directed graph based on the directed weighted network and calculate the importance index of the node:
[0032]
[0033] The importance index of node u is ε u , the natural constant is e, and the weight of the node u sending outward connections is S ot (u), the weight of node u receiving the connection is S in (u), the treatment coefficient is υ;
[0034] Weighted processing expectations of computing nodes:
[0035]
[0036] The weighted risk expectation of node u is Node u is in processing state The probability of The weighting factor is λ, and node u is in the processing state The conversion rate is Calculate the unused energy of a step:
[0037]
[0038] The unused energy in the κth step is The number of nodes in the κth step is S.
[0039] Furthermore, the method for obtaining the thermal barrier coefficient by performing a time series impact analysis on the device temperature difference data according to the offset degree includes:
[0040] Input the equipment temperature difference data into the timing impact analysis model to extract the time pattern information of the equipment temperature difference data. The expression is:
[0041]
[0042] The number of sliding windows y is g, and the time pattern information of the device temperature difference data in the ath dimension on the jth convolution kernel A is K a,j , time is The upper limit of time is T, and the temperature difference data of the device in the ath dimension is The temporal pattern information on the convolution kernel is The j-th convolution kernel in the T-g+y dimension is A j,T-g+y ;
[0043] The time pattern information is input into the attention mechanism to calculate the correlation between the device temperature difference data and the time state:
[0044]
[0045] Among them The hidden state at this moment is The weight matrix is β, The a-th dimension time pattern information and hidden state at the moment The correlation is No. The equipment temperature difference data at each moment is: The standard value of the equipment temperature difference data is h o ;
[0046] The equipment temperature difference data with a correlation greater than 0.372 is used as research data. The predicted temperature difference data is obtained based on the long short-term memory network. The difference between the predicted temperature difference data and the research data is calculated. When the difference is less than 0, it indicates that the relevant data is positively correlated with the power generation. When the difference is greater than 0, it indicates that the relevant data is negatively correlated with the power generation.
[0047] Calculate the difference between the research data at different temperatures:
[0048]
[0049] The difference of research data under temperature difference Δt is η Δt , the adjustment coefficient is δ, and the research data h t and research data t+1 The abnormal probability is P(h t ,h t+1 ), the control coefficient is λ, and the research data at temperature t is h t , the research data at temperature t+1 is h t+1 ;
[0050] Calculate the thermal barrier coefficient based on research data:
[0051]
[0052] Among them The thermal barrier coefficient at this moment is No. The difference of the research data at each moment is The difference of the a-th research data is The number of research data is N, The reference value of the research data at each moment is h o , the error constant is σ, the genetic factor is μ, the L2 norm is ||·||2, the The research data of the ath moment is
[0053] Furthermore, the method of using the temperature barrier coefficient to correct the key energy consumption and obtain correction data includes:
[0054]
[0055] The vth correction data is No. The vth temperature barrier coefficient at the moment is The number of key energy consumption is M, and the importance of the vth key energy consumption is The contribution of the vth key energy consumption is ζ v , the vth key energy consumption is Q v , the observation period is R, and the adjustment coefficient of the vth key energy consumption is θ v , the reference value of the vth key energy consumption is Q o , No. The vth critical energy consumption at the moment is The influence coefficient of the vth key energy consumption is
[0056] Furthermore, a method for constructing a carbon emission accounting model for a ground-source heat pump air-conditioning system based on the correction data includes:
[0057] Construct the objective function based on the correction data:
[0058]
[0059] The control factor is The natural constant is e, and the carbon emission error of the i-th test is The loss function for the i-th test is The carbon emissions of the ground source heat pump air conditioning system are The remaining carbon emissions are The pure carbon emission of the unit correction data is ω, and the vth correction data of the ith test is The loss coefficient of the vth correction data is
[0060] Carbon emission accounting models for ground-source heat pump air-conditioning systems include random forest algorithms, decision tree algorithms, machine learning algorithms, and momentum methods;
[0061] The random forest algorithm randomly divides the input data into training data and test data in a ratio of 4:1;
[0062] The decision tree algorithm screens data based on the importance score of the training data to obtain key data;
[0063] The machine learning algorithm predicts the carbon emissions of the ground-source heat pump air conditioning system under different operating conditions by analyzing the identification patterns and relationships of key data. The test data is input into the machine learning algorithm to obtain the predicted carbon emissions;
[0064] The momentum method adjusts the learning rate of the carbon emission accounting model of the ground source heat pump air conditioning system according to the mean square error of the actual carbon emissions and predicted carbon emissions of the training data.
[0065] In a second aspect, an embodiment of the present application further provides an electronic device, including:
[0066] A processor; and a memory arranged to store computer executable instructions, which when executed cause the processor to perform the method steps described in the first aspect.
[0067] In a third aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple applications, the electronic device executes the method steps described in the first aspect.
[0068] The beneficial effects of the present invention are:
[0069] The present invention is a method for calculating carbon emissions from a ground-source heat pump air conditioning system. Compared with the prior art, the present invention has the following technical effects:
[0070] The present invention can improve the accuracy of carbon emission accounting of geothermal heat pump air-conditioning system through preprocessing, data screening, loss analysis, time series impact analysis, data correction and model construction steps, thereby improving the precision of carbon emission accounting of geothermal heat pump air-conditioning system, optimizing carbon emission accounting of geothermal heat pump air-conditioning system, greatly saving resources and improving work efficiency, and can realize automatic accounting of carbon emission of geothermal heat pump air-conditioning system, and perform data correction of carbon emission accounting of geothermal heat pump air-conditioning system in real time, which is of great significance to carbon emission accounting of geothermal heat pump air-conditioning system, can adapt to carbon emission accounting of geothermal heat pump air-conditioning system with different standards and different carbon emission accounting requirements of geothermal heat pump air-conditioning system, and has certain universality. BRIEF DESCRIPTION OF THE DRAWINGS
[0071] Figure 1 This is a flowchart of the steps of a method for calculating carbon emissions from a ground-source heat pump air-conditioning system according to the present invention;
[0072] Figure 2 This is a schematic diagram of the structure of an electronic device in an embodiment of this specification. DETAILED DESCRIPTION
[0073] The present invention will be further described below through specific examples. The illustrative examples and descriptions of the present invention are used to explain the present invention but are not intended to limit the present invention.
[0074] A method for calculating carbon emissions from a ground-source heat pump air-conditioning system according to the present invention comprises the following steps:
[0075] like Figure 1 As shown, in this embodiment, the following steps are included:
[0076] Collecting operating data and equipment temperature difference data of a ground source heat pump air conditioning system, and preprocessing the operating data and the equipment temperature difference data;
[0077] In actual evaluations, operational data includes total system power consumption, power consumption per unit area, energy saving rate, electricity carbon emission factor, total system carbon emissions, cooling / heating power, coefficient of performance, underground pipe length, pipe diameter, pipe material, backfill material and its thermal conductivity, circulating water volume, water temperature, water pump power, control strategy, sensor accuracy, actuator efficiency, equipment production carbon emissions, and equipment transportation carbon emissions; equipment temperature difference data refers to equipment data at different temperatures;
[0078] Screening the operating data according to carbon relevance to obtain consumption data, performing time series loss analysis on the relevant data to obtain unused energy, and subtracting the unused energy from the consumption data to obtain critical energy consumption;
[0079] In the actual evaluation, consumption data includes total system power consumption, power consumption per unit area, energy saving rate, electricity carbon emission factor, cooling / heating power, coefficient of performance, underground pipe length, pipe diameter, pipe circulation water volume, water temperature, water pump power, control strategy, and actuator efficiency. The unused energy of the XX ground-source heat pump air conditioning system in one month is 0.963 tons of water.
[0080] Performing a time series impact analysis on the device temperature difference data according to the offset to obtain a temperature barrier coefficient, and using the temperature barrier coefficient to correct the key energy consumption to obtain correction data;
[0081] In the actual evaluation, the temperature barrier coefficient is 0.314;
[0082] A carbon emission accounting model for a geothermal heat pump air conditioning system is constructed based on the correction data, the data to be calculated is input into the carbon emission accounting model for the geothermal heat pump air conditioning system, and a calculation result is output.
[0083] In this embodiment, the method for filtering the operation data according to the carbon relevance to obtain consumption data includes:
[0084] According to the similarity of the running data, a decision tree is used to perform initial classification to obtain classified data;
[0085] Calculate the information content of categorical data:
[0086]
[0087] The amount of information of the b-th classification data is The number of groups where data b is located is m, and the b-th classification data of the c-th group is z c,b , the proportion of the b-th classification data in the c-th group is b c,b , the average value of the classification data of the cth group is
[0088] The classified data with information greater than 0.32 is regarded as important data, and the weight of the important data is calculated:
[0089]
[0090] The number of important data is The number of important data in the cth group is The standard value of the important data of the cth group is ψ o , the τth important data of the cth group is ψ c,τ, the deviation of the τth important data is Δψ τ , the distance between the most informative important data and the τth important data in the cth group is The weight of the bth important data is ξ b ;
[0091] Calculate the carbon relevance of important data:
[0092]
[0093] The carbon correlation of the bth important data is θ b , the probability of carbon-containing substance w appearing under the condition of important data b is k(w|b), the probability of carbon-containing substance w appearing is k(w), and the number of important data b is The amount of carbon-containing matter w is The sth carbon-containing substance is w s , the standard value of carbon-containing material w is w o , the natural constant is e, and the control factor is The optimization coefficient is x;
[0094] The important data with carbon correlation greater than 0.417 are output as consumption data.
[0095] In this embodiment, the method of performing a time series loss analysis on the relevant data to obtain unused energy includes:
[0096] Construct a state matrix based on relevant data, take the processing links as nodes, and calculate the conversion rate of the nodes:
[0097]
[0098] The conversion rate of the u-th node is The uth node The input amount of relevant data is The uth node The usage rate of relevant data is The input mass is The remaining output mass of node u is Δm u , the error coefficient is
[0099] Calculate the average probability of being treated:
[0100]
[0101] The probability of node u being processed through the lth path is The number of possible paths for node u to be processed is The average probability of node u being attacked is
[0102] Construct a weighted directed graph based on the directed weighted network and calculate the importance index of the node:
[0103]
[0104] The importance index of node u is ε u , the natural constant is e, and the weight of the node u sending outward connections is S ot (u), the weight of node u receiving the connection is S in (u), the treatment coefficient is υ;
[0105] Weighted processing expectations of computing nodes:
[0106]
[0107] The weighted risk expectation of node u is Node u is in processing state The probability of The weighting factor is λ, and node u is in the processing state The conversion rate is Calculate the unused energy of a step:
[0108]
[0109] The unused energy in the κth step is The number of nodes in the κth step is S.
[0110] In this embodiment, the method for obtaining the thermal barrier coefficient by performing a time series impact analysis on the device temperature difference data according to the offset includes:
[0111] Input the equipment temperature difference data into the timing impact analysis model to extract the time pattern information of the equipment temperature difference data. The expression is:
[0112]
[0113] The number of sliding windows y is g, and the time pattern information of the device temperature difference data in the ath dimension on the jth convolution kernel A is K a,j , time is The upper limit of time is T, and the temperature difference data of the device in the ath dimension is The temporal pattern information on the convolution kernel is The j-th convolution kernel in the T-g+y dimension is A j,T-g+y ;
[0114] The time pattern information is input into the attention mechanism to calculate the correlation between the device temperature difference data and the time state:
[0115]
[0116] Among them The hidden state at this moment is The weight matrix is β, The a-th dimension time pattern information and hidden state at the moment The correlation is No. The equipment temperature difference data at each moment is: The standard value of the equipment temperature difference data is h o ;
[0117] The equipment temperature difference data with a correlation greater than 0.372 is used as research data. The predicted temperature difference data is obtained based on the long short-term memory network. The difference between the predicted temperature difference data and the research data is calculated. When the difference is less than 0, it indicates that the relevant data is positively correlated with the power generation. When the difference is greater than 0, it indicates that the relevant data is negatively correlated with the power generation.
[0118] Calculate the difference between the research data at different temperatures:
[0119]
[0120] The difference of research data under temperature difference Δt is η Δt , the adjustment coefficient is δ, and the research data h t and research data t+1 The abnormal probability is P(h t ,h t+1 ), the control coefficient is λ, and the research data at temperature t is h t , the research data at temperature t+1 is h t+1 ;
[0121] Calculate the thermal barrier coefficient based on research data:
[0122]
[0123] Among them The thermal barrier coefficient at this moment is No. The difference of the research data at each moment is The difference of the a-th research data is The number of research data is N, The reference value of the research data at each moment is h o , the error constant is σ, the genetic factor is μ, the L2 norm is ||·||2, the The research data of the ath moment is
[0124] In this embodiment, the method of using the temperature barrier coefficient to correct the key energy consumption to obtain correction data includes:
[0125]
[0126] The vth correction data is No. The vth temperature barrier coefficient at the moment is The number of key energy consumption is M, and the importance of the vth key energy consumption is The contribution of the vth key energy consumption is ζ v , the vth key energy consumption is Q v , the observation period is R, and the adjustment coefficient of the vth key energy consumption is θ v , the reference value of the vth key energy consumption is Q o , No. The vth critical energy consumption at the moment is The influence coefficient of the vth key energy consumption is
[0127] In this embodiment, the method for constructing a carbon emission accounting model for a ground-source heat pump air conditioning system based on the correction data includes:
[0128] Construct the objective function based on the correction data:
[0129]
[0130] The control factor is The natural constant is e, and the carbon emission error of the i-th test is The loss function for the i-th test is The carbon emissions of the ground source heat pump air conditioning system are The remaining carbon emissions are The pure carbon emission of the unit correction data is ω, and the vth correction data of the ith test is The loss coefficient of the vth correction data is
[0131] Carbon emission accounting models for ground-source heat pump air-conditioning systems include random forest algorithms, decision tree algorithms, machine learning algorithms, and momentum methods;
[0132] The random forest algorithm randomly divides the input data into training data and test data in a ratio of 4:1;
[0133] The decision tree algorithm screens data based on the importance score of the training data to obtain key data;
[0134] The machine learning algorithm predicts the carbon emissions of the ground-source heat pump air conditioning system under different operating conditions by analyzing the identification patterns and relationships of key data. The test data is input into the machine learning algorithm to obtain the predicted carbon emissions;
[0135] The momentum method adjusts the learning rate of the carbon emission accounting model of the ground source heat pump air conditioning system according to the mean square error of the actual carbon emissions and predicted carbon emissions of the training data.
[0136] Figure 2 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 2 At the hardware level, the electronic device includes a processor and, optionally, an internal bus, a network interface, and memory. The memory may include internal memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for its services.
[0137] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or one type of bus.
[0138] The memory is used to store programs. Specifically, the program may include program code, which includes computer operating instructions. The memory may include internal memory and non-volatile memory, and provides instructions and data to the processor.
[0139] The processor reads the corresponding computer program from the non-volatile memory into the internal memory and then runs it, logically forming a device for calculating carbon emissions for a ground-source heat pump air conditioning system. The processor executes the program stored in the memory and is specifically configured to perform any of the aforementioned methods for calculating carbon emissions for a ground-source heat pump air conditioning system.
[0140] The above application Figure 1The carbon emissions accounting method for a ground-source heat pump air conditioning system disclosed in the illustrated embodiment can be applied to or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by hardware integrated logic circuits in the processor or by software instructions. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in conjunction with the embodiments of this application can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above method.
[0141] The electronic device may also perform Figure 1 A carbon emission accounting method for ground source heat pump air conditioning system Figure 1 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.
[0142] An embodiment of the present application also proposes a computer-readable storage medium, which stores one or more programs, and the one or more programs include instructions. When the instructions are executed by an electronic device including multiple application programs, any one of the aforementioned ground source heat pump air conditioning system carbon emission accounting methods is executed.
[0143] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.
[0144] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0145] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.
[0146] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.
[0147] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.
[0148] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.
[0149] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.
[0150] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.
[0151] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0152] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.
Claims
1. A method for calculating carbon emissions from ground source heat pump air conditioning systems. It is characterized in that The following steps are involved: Collecting operation data and equipment temperature difference data of the ground source heat pump air conditioning system, and preprocessing the operation data and the equipment temperature difference data; Screening the operation data according to the carbon relevance to obtain consumption data, performing time series loss analysis on the relevant data to obtain unused energy, and subtracting the unused energy from the consumption data to obtain critical energy consumption; Performing a time series impact analysis on the temperature difference data of the equipment according to the offset to obtain a temperature barrier coefficient, and using the temperature barrier coefficient to correct the key energy consumption to obtain correction data; A carbon emission accounting model for a geothermal heat pump air conditioning system is constructed according to the correction data, the data to be calculated is input into the carbon emission accounting model for a geothermal heat pump air conditioning system, and the calculation result is output.
2. According to the carbon emission accounting method of the ground source heat pump air conditioning system described in claim 1, It is characterized in that The method of screening the operation data according to the carbon relevance to obtain consumption data comprises: According to the similarity of the running data, a decision tree is used to perform initial classification to obtain classified data; Calculate the information content of categorical data: The amount of information of the b-th classification data is The number of groups where data b is located is m, and the bth classification data of the cth group is z c,b , the proportion of the b-th classification data in the c-th group is b c,b , the average value of the classification data of the cth group is The classified data with information greater than 0.32 is regarded as important data, and the weight of the important data is calculated: The number of important data is The number of important data in the cth group is The standard value of the important data of the cth group is ψ o , the τth important data of the cth group is ψ c,τ , the deviation of the τth important data is Δψ τ , the distance between the most informative important data and the τth important data in the cth group is The weight of the bth important data is ξ b ; Calculate the carbon relevance of important data: The carbon relevance of the bth important data is θ b , the probability of carbon-containing substance w appearing under the condition of important data b is k(w|b), the probability of carbon-containing substance w appearing is k(w), and the number of important data b is The amount of carbon-containing matter w is The sth carbon-containing substance is w s , the standard value of carbon-containing material w is w o , the natural constant is e, and the control factor is The optimization coefficient is x; The significant data with carbon correlation greater than 0.417 are output as consumption data.
3. According to the carbon emission accounting method of the ground source heat pump air conditioning system described in claim 1, It is characterized in that The method of performing a time series loss analysis on the relevant data to obtain unused energy includes: Construct a state matrix based on relevant data, take the processing links as nodes, and calculate the conversion rate of the nodes: The conversion rate of the u-th node is The uth node The input amount of relevant data is The uth node The usage rate of relevant data is The input mass is The remaining output mass of node u is Δm u , the error coefficient is Calculate the average probability of being treated: The probability that node u is processed through the lth path is The number of possible paths for node u to be processed is The average probability of node u being attacked is Construct a weighted directed graph based on the directed weighted network and calculate the importance index of the node: The importance index of node u is ε u , the natural constant is e, and the weight of the node u sending outward connections is S ot (u), the weight of node u receiving the connection is S in (u), the treatment coefficient is υ; Weighted processing expectations for computing nodes: The weighted risk expectation of node u is Node u is in processing state The probability of The weighting factor is λ, and node u is in the processing state The conversion rate is Calculate the unused energy of a step: The unused energy in the κth step is The number of nodes in the κth step is S.
4. According to the carbon emission accounting method of the ground source heat pump air conditioning system according to claim 1, It is characterized in that The method for obtaining a thermal barrier coefficient by performing a time series impact analysis on the temperature difference data of the device according to the offset includes: The equipment temperature difference data is input into the timing impact analysis model to extract the time pattern information of the equipment temperature difference data. The expression is: The number of sliding windows y is g, and the time pattern information of the device temperature difference data in the ath dimension on the jth convolution kernel A is K a,j , time is The upper limit of time is T, and the temperature difference data of the device in the ath dimension is The temporal pattern information on the convolution kernel is The jth convolution kernel in the T-g+y dimension is A j,T-g+y ; The time pattern information is input into the attention mechanism to calculate the correlation between the device temperature difference data and the time state: Among them The hidden state at this moment is The weight matrix is β, The a-th dimension time pattern information and hidden state at the moment The correlation is No. The equipment temperature difference data at each moment is The standard value of the equipment temperature difference data is h o ; The equipment temperature difference data with a correlation greater than 0.372 is used as research data, and the predicted temperature difference data is obtained according to the long short-term memory network. The difference between the predicted temperature difference data and the research data is calculated. When the difference is less than 0, it means that the relevant data is positively correlated with the power generation, and when the difference is greater than 0, it means that the relevant data is negatively correlated with the power generation; Calculate the difference between the research data at different temperatures: The difference of research data under temperature difference Δt is η Δt , the adjustment coefficient is δ, and the research data is h t and research data t+1 The abnormal probability is P(h t ,h t+1 ), the control coefficient is λ, and the research data at temperature t is h t , the research data at temperature t+1 is h t+1 ; Calculate the thermal barrier coefficient based on research data: Among them The thermal barrier coefficient at this moment is No. The difference of research data at each moment is The difference of the a-th research data is The number of research data is N, The reference value of the research data at a certain moment is h o , the error constant is σ, the genetic factor is μ, and the L2 norm is ||·|| 2 , No. The ath research data at the moment is 5. According to the carbon emission accounting method of the ground source heat pump air conditioning system described in claim 1, It is characterized in that The method of using the temperature barrier coefficient to correct the key energy consumption and obtain correction data includes: The vth correction data is No. The vth temperature barrier coefficient at the moment is The number of key energy consumption is M, and the importance of the vth key energy consumption is The contribution of the vth key energy consumption is ζ v , the vth key energy consumption is Q v , the observation period is R, and the adjustment coefficient of the vth key energy consumption is θ v , the reference value of the vth key energy consumption is Q o , No. The vth critical energy consumption at the moment is The influence coefficient of the vth key energy consumption is 6. According to the carbon emission accounting method of a ground source heat pump air conditioning system as described in claim 1, It is characterized in that The method for constructing a carbon emission accounting model for a ground source heat pump air conditioning system according to the correction data comprises: Construct the objective function based on the correction data: The control factor is The natural constant is e, and the carbon emission error of the ith test is The loss function for the i-th test is The carbon emissions of the ground source heat pump air conditioning system are The remaining carbon emissions are The pure carbon emission of the unit correction data is ω, and the vth correction data of the ith test is The loss coefficient of the vth correction data is The carbon emission accounting models of ground source heat pump air conditioning system include random forest algorithm, decision tree algorithm, machine learning algorithm and momentum method; The random forest algorithm randomly divides the input data into training data and test data in a ratio of 4:1; The decision tree algorithm screens data based on the importance score of the training data to obtain key data; The machine learning algorithm predicts the carbon emissions of the ground source heat pump air conditioning system under different operating conditions by analyzing the recognition patterns and relationships of key data. The test data is input into the machine learning algorithm to obtain the predicted carbon emissions; The momentum method adjusts the learning rate of the carbon emission accounting model of the ground source heat pump air conditioning system according to the mean square error of the actual carbon emissions of the training data and the predicted carbon emissions.
7. An electronic device, include: processor; as well as A memory arranged to store computer executable instructions, wherein when the executable instructions are executed, the processor executes the method according to any one of claims 1 to 6.
8. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, enables the electronic device to execute the method according to any one of claims 1 to 6.
Citation Information
Cited By
Emission reduction data evaluation method and system for water source heat pump air conditioning system
CN121543895A
Water source heat pump air conditioning system emission reduction data evaluation method and system
CN121543895B
Method for evaluating carbon emission reduction of shallow ground source heat pump cold and heat dual-supply system
CN121903172A
