Central air conditioning terminal energy consumption processing method based on large language model

Abstract

The present application relates to air conditioning energy consumption technical field, especially central air conditioning terminal energy consumption processing method based on large language model, including the following steps: S1: air conditioning principle material, air conditioning fault material, heat transfer document, refrigeration document in air conditioning science material and air conditioning related data in recent years are stored to data lake, and the numerical data is normalized to obtain data set;S2: air conditioning science material is input to large language model and is learned, training set is input to regression model and is trained to obtain training model, and prediction set is input to training model to obtain coil control coefficient;S3: according to coil control coefficient and real-time data, the energy consumption of central air conditioning is calculated and energy consumption statistical report is generated.The present application learns air conditioning science material through large language model, obtains coil control coefficient according to historical data, realizes the accurate calculation of central air conditioning room energy consumption according to coil control coefficient and real-time data, provides scientific basis for energy saving optimization, and improves the efficiency of air conditioning fault rate diagnosis and maintenance.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of air conditioning energy consumption, and particularly relates to a central air conditioning terminal energy consumption processing method, device and storage medium based on a large language model. BACKGROUND

[0002] Central air conditioning systems have been widely used because they can provide comfortable cooling and heating environments for large spaces. A central air conditioning system usually consists of outdoor units, indoor units, and complex pipelines and control systems. Among them, the indoor unit is the key part of the heat exchange with the indoor environment, and its energy consumption plays an important role in the energy management of the entire central air conditioning system. The energy consumption accounting of the indoor unit is of great significance to improve energy efficiency and achieve energy saving and emission reduction.

[0003] The traditional central air conditioning indoor unit energy consumption calculation method has many limitations. On the one hand, the method of relying on manual recording of energy consumption data is not only inefficient, but also prone to human error. The recording personnel may be negligent, the recording time interval is unreasonable, and other factors may result in incomplete or inaccurate data. On the other hand, simple automation calculation is usually based on a relatively rough model, only considering a few fixed parameters such as running time and set temperature, without fully considering the actual operating conditions of the indoor unit. For example, the fan speed of the indoor unit, the actual heat exchange efficiency, and the influence of environmental temperature and humidity changes in different seasons and time periods on energy consumption are not fully considered in the calculation. This makes the indoor unit energy consumption calculated by the traditional method deviate from the actual energy consumption, which is difficult to accurately reflect the real energy consumption, and thus is not conducive to formulating accurate and effective energy-saving strategies and energy management measures.

[0004] At the same time, central air conditioning systems inevitably encounter various faults during long-term operation. When a fault occurs, maintenance personnel usually need to go to the scene for investigation and diagnosis. The traditional fault diagnosis method mainly relies on the experience of maintenance personnel. Maintenance personnel rely on their memory and understanding of common fault phenomena to gradually check the possible problem components and system links. However, this experience-based diagnosis method has obvious shortcomings. First, the accumulation of experience requires a long time, and it is difficult for new employees or relatively inexperienced maintenance personnel to accurately determine the fault. Second, even experienced maintenance personnel may misdiagnose or take too long to diagnose when faced with complex, rare, or multiple fault superimposed situations. For example, some faults may exhibit similar symptoms, but the actual fault root is completely different, and it is difficult to quickly and accurately determine the true fault point simply relying on experience, which not only leads to low maintenance efficiency, but also causes additional energy waste due to maintenance delays, increasing user costs and inconvenience. SUMMARY

[0005] The object of the present application is to solve the shortcomings existing in the prior art, and to provide a central air conditioner terminal energy consumption processing method based on a large language model, comprising the following steps:

[0006] S1: store air conditioner principle materials, air conditioner fault materials, heat transfer documents, refrigeration documents, fluid mechanics documents, air conditioning materials and air conditioning related data of previous years into a data lake, and normalize the numerical data of the air conditioning related data of previous years to obtain a data set;

[0007] S2: input the air conditioning materials into a large language model for learning, select a gradient boosting tree GBM as a regression model, input a training set of the data set into the regression model for training to obtain a training model, and input a prediction set of the data set into the training model to obtain a coil control coefficient;

[0008] S3: calculate the central air conditioner energy consumption based on the coil control coefficient and real-time data and generate an energy consumption statistical report.

[0009] Preferably, the real-time data includes:

[0010] Obtain the physical space positions and the correlation of the central air conditioner outdoor unit, the coil, the total electric meter and the sub-meter;

[0011] Obtain the brand, brand rated power, room area and current electricity price of the room air conditioner;

[0012] Collect air conditioner related data related to the air conditioner on the air conditioner sensor, including air conditioner mode, air speed, set temperature, air sweeping mode, indoor temperature, outdoor temperature, air conditioner running time, and associated sub-meter readings, and clean the air conditioner related data to ensure data validity.

[0013] Preferably, in step S3, calculating the central air conditioner energy consumption based on the coil control coefficient and real-time data further comprises:

[0014] S31: obtain the number of coil floors and the number of sub-meter floors according to the correlation, calculate the coil electricity allocation proportion according to the number of coil floors and the number of sub-meter floors of the electric meter, and the calculation formula of the coil electricity allocation proportion is as follows:

[0015]

[0016] wherein, the number of coil floors, the number of sub-meter floors of the electric meter;

[0017] ​S32: Calculate the single coil power consumption coefficient according to the coil regulation coefficient and the coil running time, the single coil power consumption coefficient The calculation formula is as follows:

[0018]

[0019] Wherein, The coil regulation coefficient is the coil regulation coefficient, The coil running time is the coil running time;

[0020] S33: Calculate the total power consumption of all coils according to the coil power consumption allocation ratio and the sub-meter power consumption, the total power consumption of all coils The calculation formula is as follows:

[0021]

[0022] Wherein, The floor end sub-meter power consumption in the instruction time is the floor end sub-meter power consumption in the instruction time;

[0023] S34: Calculate the power consumption per second of each coil, that is, the total power consumption of all coils in unit time divided by the running time of each coil in unit time multiplied by the sum of the coil regulation coefficient, which is equal to the power consumption per second of each coil, according to the total power consumption of all coils and the coil regulation coefficient. The calculation formula is as follows:

[0024]

[0025] S35: Calculate the fan power consumption according to the brand fan rated power and the coil regulation coefficient;

[0026] S36: Calculate the energy consumption per second of each coil according to the coil power consumption allocation ratio, the power consumption per second of each coil and the fan power consumption.

[0027] S37: Calculate the room power consumption according to the power consumption per second of the coil and the running time, and calculate the room electricity according to the electricity price and the total power consumption of the room.

[0028] Preferably, in step S35, the fan power consumption is calculated according to the brand fan rated power and the coil regulation coefficient, further comprising:

[0029]

[0030] Wherein, The brand fan rated power is the brand fan rated power, The fan power consumption is the fan power consumption.

[0031] Preferably, in step S36, the energy consumption of each coil per second is calculated according to the electricity allocation ratio of the coil, the electricity consumption of each coil per second, and the electricity consumption of the fan, and further comprising:

[0032]

[0033] wherein, is the energy consumption of each coil per second.

[0034] Preferably, in step S37, the electricity consumption of the room is calculated according to the electricity consumption of each coil per second and the running time of the machine, and the electricity bill of the room is calculated according to the electricity price and the total electricity consumption of the room, and further comprising:

[0035] The electricity consumption of the room is calculated according to the electricity consumption of each coil per second and the running time of the machine, and the electricity consumption of the room The calculation formula is as follows:

[0036]

[0037] wherein, represents the running time of the machine per unit time;

[0038] The electricity bill of the room per unit time is calculated according to the electricity price and the total electricity consumption of the room, and the electricity bill of the room per unit time The calculation formula is as follows:

[0039]

[0040] wherein, is the electricity price.

[0041] Preferably, according to the electricity allocation ratio of the coil, the electricity consumption coefficient of the single coil, the total electricity consumption of all coils, the electricity consumption of each coil per second, the electricity consumption of the fan, the energy consumption of each coil per second, the electricity consumption of the room, and the electricity bill of the room, the energy consumption statistical report including daily energy consumption, monthly energy consumption, and annual energy consumption is generated, the energy consumption statistical report is displayed through a visualization tool, and energy-saving suggestions are provided according to the energy consumption statistical report.

[0042] Preferably, when the air conditioner fault information is monitored, the air conditioner fault information is transmitted to the large language model, the large prediction model obtains real-time data of the indoor unit, and diagnostic information is obtained according to the air conditioner data, a diagnostic scheme is proposed according to the diagnostic information, and the diagnostic information is pushed to the person in charge in the form of a mobile phone APP or a short message, and the person in charge processes according to the diagnostic scheme.

[0043] The application also provides a computer device based on the same concept, comprising a memory and a processor, wherein the memory stores computer readable instructions, and the computer readable instructions are executed by the processor to make the processor execute the steps of the central air conditioner terminal energy consumption processing method based on the large language model according to any one of the embodiments.

[0044] The application also provides a storage medium storing computer readable instructions, which are executed by one or more processors to make the one or more processors execute the steps of the central air conditioner terminal energy consumption processing method based on the large language model according to any one of the embodiments.

[0045] Compared with the prior art, the application has the following beneficial effects:

[0046] The application stores air conditioner principle materials, air conditioner fault materials, heat transfer documents, refrigeration documents, fluid mechanics documents, air conditioning materials and air conditioning related data in the data lake, which is easy to manage data and materials, facilitates maintenance and updating, and obtains a data set through numerical data normalization of the air conditioning related data, so that different orders of magnitude and different scales of data are unified in a standard range, the influence caused by the differences in data dimensions is eliminated, the consistency of data in subsequent processes such as large language models and fault diagnosis is ensured, and the accuracy and reliability of the model are improved.

[0047] The application inputs air conditioning materials into a large language model for learning, mines the association between different knowledge points, forms a complete knowledge network, and facilitates updating and learning of new air conditioning materials, which makes it better adapt to and use new knowledge to assist analysis and judgment when facing changing air conditioning application scenarios; the gradient boosting tree GBM is selected as the regression model, which has robustness and noise resistance, so that the prediction result output by the model can more accurately approach the real coil control coefficient.

[0048] The application calculates the central air conditioner energy consumption and generates an energy consumption statistical report through the coil control coefficient and real-time data, effectively solves the deficiencies of the traditional energy consumption calculation method, especially when the air conditioner real-time data is lost, provides a scientific and reasonable inference, has important significance for improving energy utilization efficiency and reducing operation cost, and combines the large language model to make a more scientific diagnosis scheme for air conditioner faults, improves the efficiency of air conditioner fault repair and reduces maintenance cost. BRIEF DESCRIPTION OF DRAWINGS

[0049] Various other advantages and benefits will become apparent to those of ordinary skill in the art, upon reading the following detailed description of the preferred embodiment. The accompanying drawings are included to provide a description of preferred embodiments and are not meant to limit the present application.

[0050] Figure 1 Flow chart of the central air conditioning terminal energy consumption processing method based on a large language model of the present application;

[0051] Figure 2 Another flow chart of the central air conditioning terminal energy consumption processing method based on a large language model of the present application;

[0052] Figure 3 Room six-layer and meter relationship diagram of the central air conditioning terminal energy consumption processing method based on a large language model of the present application;

[0053] Figure 4 Structure diagram of the central air conditioning terminal energy consumption processing system based on a large language model of the present application. DETAILED DESCRIPTION

[0054] In order to make the objectives, technical solutions and advantages of the present application clearer, the following will further describe the present application in detail with reference to the accompanying drawings and examples. It should be understood that the specific examples described herein are only used to explain the present application and are not intended to limit the present application. Obviously, the described examples are part of the examples of the present application, but not all the examples. Based on the examples in the present application, all other examples obtained by those of ordinary skill in the art without creative labor fall within the scope of the present application.

[0055] Those skilled in the art can understand that, unless specifically stated otherwise, the singular form "a", "an", "the" used herein can also include the plural form. It should be further understood that the use of the word "comprise" in the specification of the present application means that the features, integers, steps, operations, elements and / or components exist, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0056] Example 1

[0057] Referring to Figure 1 and Figure 2 In this embodiment, the large prediction model is combined with the central air conditioning energy consumption calculation and maintenance to more accurately calculate the energy consumption and fault diagnosis of the central air conditioning terminal, and a central air conditioning terminal energy consumption processing method based on a large language model is provided, which includes the following steps:

[0058] S1: Store the air conditioning principle materials, air conditioning fault materials, heat transfer documents, refrigeration documents, fluid mechanics documents, air conditioning materials including heating, ventilation and air conditioning, and air conditioning related data over the years into the data lake, and normalize the numerical data of the air conditioning related data over the years to obtain a data set. Specifically, in this embodiment, the related data of the air conditioner in the past 10 years is stored in the data lake. The data lake is a storage system used to centrally store data information, and can accommodate any structured and unstructured data.

[0059] More preferably, the collected document materials in multiple formats including PDF, Word, HTML, etc. are uniformly converted into formats suitable for processing and storage, such as plain text format or structured database format (such as extracting table data into a relational database table).

[0060] The air conditioning related data over the years is cleaned to remove duplicate data records, incorrect data values (such as temperature or pressure values that are obviously outside the reasonable range), and incomplete data rows or columns. For missing data, data filling techniques (such as mean filling, model-based filling, etc.) can be used for processing.

[0061] Since the air conditioning related data over the years has the characteristics of relatively uniform data distribution and known data range, the minimum-maximum normalization formula is used for conversion, as shown below:

[0062]

[0063] wherein, is the normalized value, is the original data value, and are the minimum and maximum values of the variable, respectively. This method can map the data to the [0, 1] interval.

[0064] S2: Input the air conditioning materials into the large language model for learning, select the gradient boosting tree GBM as the regression model, input the training set of the data set into the regression model for training to obtain the training model, and input the prediction set of the data set into the training model to obtain the coil control coefficient. Specifically, in this embodiment, 80% of the data in the data set is used as the training set, and 20% of the data is used as the prediction set to supervise the fine-tuning of the large language model LLM. The large language model is a pre-trained language model used to pre-train large-scale data and can simulate human learning and thinking.

[0065] The Gradient Boosting Model (GBM) effectively captures this complex nonlinearity. During training, it continuously adjusts the weights of each decision tree, allowing the model's output to more accurately approximate the actual coil control coefficient. Compared to simpler models like linear regression, it offers significant accuracy advantages in handling such complex relationships. In actual air conditioning data collection, some noise is inevitable, such as individual abnormal temperature and flow values ​​caused by sensor measurement errors. The GBM model has a certain tolerance for this type of noise. During training, it avoids severe overfitting due to small amounts of abnormal data and can still stably learn the key patterns in the data. This ensures the reliability of the resulting trained model in predicting coil control coefficients and reduces prediction bias caused by data quality issues.

[0066] Preferably, numerical variables such as indoor and outdoor temperature, humidity, supply and return air temperature of the air conditioning system, refrigerant temperature and pressure at the coil inlet and outlet, fan speed, as well as non-numerical variables that may affect the control (such as whether the air conditioner is operating in cooling or heating mode, etc.) are input into the large language model.

[0067] The large language model analyzes the potential correlation between each variable in the data and the coil control coefficient. Using data analysis methods (such as calculating correlation coefficients between variables and assessing feature importance), it removes variables with low correlation, redundancy, or insignificant impact on the coil control coefficient, thereby selecting feature variables with a significant impact on the coil control coefficient. For example, by calculating correlation coefficients between variables (such as the Pearson correlation coefficient), variables with high correlation to the control coefficient, such as the coil inlet and outlet temperature difference, the indoor and outdoor temperature difference, and fan air volume, are identified as key features.

[0068] Import key features into the corresponding machine learning library and select the Gradient Boosted Tree (GBM)-related classes or functions to initialize the regression model. Initially set the key parameters of the Gradient Boosted Tree (GBM) based on the data characteristics and problem requirements. For example, start by setting the number of decision trees (n_estimators parameter) to a moderate value (such as 100), the maximum tree depth (max_depth parameter) to a certain number of layers (such as 5), and the learning rate (learning_rate parameter) to a low value (such as 0.1). These parameters will be further adjusted and optimized during training based on model performance.

[0069] The training set data is input into the initialized GBM regression model and iterative training begins. In each iteration, GBM constructs a new decision tree based on the residual between the current prediction result and the true control coefficient target value to continuously optimize the model's prediction ability, thereby reducing this residual and obtaining a trained GBM regression model.

[0070] The pretreated prediction set data is input into the trained GBM regression model, and the model predicts the corresponding coil control coefficient of each data in the prediction set according to the relationship between the learned features and the coil control coefficient, and outputs the corresponding prediction result.

[0071] S3: Calculate the central air conditioning energy consumption based on the coil control coefficient and real-time data, and generate an energy consumption statistical report. Specifically, in this embodiment, the coil control coefficient is a billing coefficient value calculated by the large language model, and the real-time data related to the air conditioner is collected by the collection system. The default initial coil control coefficient is 1.

[0072] Preferably, the real-time data includes:

[0073] Obtain the physical space positions and association relationships of the central air conditioner outdoor unit, coil, total electric meter, and sub-meter electric meter;

[0074] Obtain the brand, brand rated power, room area, and current electricity price of the room air conditioner;

[0075] Collect air conditioner related data related to the air conditioner on the air conditioner sensor, including air conditioner mode, wind speed, set temperature, air sweeping mode, indoor temperature, outdoor temperature, air conditioner running time, and associated sub-meter reading, and clean the air conditioner related data to ensure data validity. Specifically, in this embodiment, the collected real-time data is cleaned, denoised, and standardized.

[0076] Preferably, in step S3, calculating the central air conditioning energy consumption based on the coil control coefficient and real-time data further includes:

[0077] S31: Obtain the number of coil floors and the number of sub-meter floors based on the association relationship, and calculate the coil electricity allocation proportion based on the number of coil floors and the number of sub-meter floors. The formula for calculating the coil electricity allocation proportion is as follows:

[0078]

[0079] wherein, is the number of coil floors, is the number of sub-meter floors. Specifically, in this embodiment, please refer to Figure 3 As shown in the figure, assuming that a building has 10 floors, 9 floors are installed with sub-meters, and 8 floors are installed with coils, then , , so that the floors without coils and sub-meters can be excluded;

[0080] S32: Calculate the single coil electricity coefficient based on the coil control coefficient and the coil running time, and the single coil electricity coefficient​ The calculation formula is as follows:

[0081]

[0082] in, is the coil control coefficient, is the coil running time;

[0083] S33: Calculate the total power consumption of all coils based on the coil power consumption ratio and the power consumption of the sub-meter. The calculation formula is as follows:

[0084]

[0085] in, The power consumption of the terminal sub-meter on the floor within the command time;

[0086] S34: Calculate the power consumption of each coil per second based on the total power consumption of all coils and the coil control coefficient. That is, the total power consumption of all coils per unit time divided by the running time of each coil per unit time multiplied by the sum of the coil control coefficients equals the power consumption of each coil per second. The calculation formula is as follows:

[0087]

[0088] S35: Calculate fan power consumption based on brand fan rated power and coil control coefficient;

[0089] S36: Calculate the energy consumption of each coil per second based on the coil power consumption allocation ratio, the power consumption of each coil per second, and the power consumption of the fan;

[0090] S37: Calculate the room power consumption based on the coil power consumption per second and the startup operation time, and calculate the room electricity fee based on the unit price of electricity and the total power consumption of the room. Specifically, in this embodiment.

[0091] Preferably, in step S35, the fan power consumption is calculated according to the brand fan rated power and the coil control coefficient, further comprising:

[0092]

[0093] in, is the rated power of the brand fan, Power for the fan.

[0094] Preferably, in step S36, the energy consumption of each coil per second is calculated based on the coil power consumption allocation ratio, the power consumption of each coil per second, and the power consumption of the fan, further comprising:

[0095]

[0096] wherein, is the energy consumption per second of each coil.

[0097] Preferably, in step S37, the room electricity consumption is calculated according to the electricity consumption per second of the coil and the running time of the start-up operation, the room electricity charge is calculated according to the electricity rate and the total electricity consumption of the room, and further comprising:

[0098] The room electricity consumption is calculated according to the electricity consumption per second of the coil and the running time of the start-up operation, and the room electricity consumption The calculation formula of is as follows:

[0099]

[0100] wherein, represents the running time of the start-up operation per unit time;

[0101] The room electricity charge per unit time is calculated according to the electricity rate and the total electricity consumption of the room, and the room electricity charge per unit time The calculation formula of is as follows:

[0102]

[0103] wherein, is the electricity rate.

[0104] Preferably, according to the electricity consumption allocation ratio of the coil, the electricity consumption coefficient of a single coil, the total electricity consumption of all coils, the electricity consumption per second of each coil, the electricity consumption of the fan, the energy consumption per second of each coil, the room electricity consumption, and the room electricity charge, a energy consumption statistical report including daily energy consumption, monthly energy consumption, and annual energy consumption is generated, the energy consumption statistical report is displayed through a visualization tool, and energy saving suggestions are provided according to the energy consumption statistical report.

[0105] Preferably, when the air conditioner fault information is monitored, the air conditioner fault information is transmitted to the large language model, the large prediction model obtains the real-time data of the indoor unit, and the diagnosis information is obtained according to the air conditioning data, the diagnosis scheme is proposed according to the diagnosis information, the diagnosis information is pushed to the person in charge in the form of a mobile phone APP or a short message, the person in charge processes according to the diagnosis scheme, and specifically, in the embodiment, if the payment is overdue, the person in charge can pay, and if it is a maintenance personnel, the diagnosis scheme can be quickly processed, thereby saving the troubleshooting time of the air conditioner and improving the work efficiency of the maintenance personnel.

[0106] Embodiment 2

[0107] Please refer to Figure 4 , the embodiment also provides a central air conditioning terminal energy consumption processing system based on a large language model, comprising:

[0108] The data lake module stores the data storage unit including a heat transfer unit, a refrigeration unit, a fluid mechanics unit, an air conditioner fault and maintenance unit, an air conditioner component principle unit and an air conditioner collection database unit, and is used to collect air conditioning data including air conditioning principle data, air conditioning fault data, heat transfer documents, refrigeration documents, fluid mechanics documents, heating, ventilation and air conditioning, and air conditioning related data in previous years, and store them in the data storage unit;

[0109] The large language model processing module, the large language model learns from the data storage unit to obtain air conditioning data, selects gradient boosting tree GBM as a regression model, normalizes the numerical data of the air conditioning related data in previous years to obtain a data set, inputs the training set of the data set into the regression model to obtain a training model, inputs the prediction set of the data set into the training model to obtain a coil control coefficient, and sends the coil control coefficient to the intelligent air conditioner management module;

[0110] The data middle platform module is used to obtain real-time data and the coil control coefficient from the intelligent air conditioner management module through the collection unit, store the real-time data in the distributed database unit, calculate the central air conditioner energy consumption based on the coil control coefficient and the real-time data, and generate an energy consumption statistical report;

[0111] The intelligent air conditioner management module includes a building management unit, an air conditioner management unit, a billing unit, a notification unit, a fault unit and a warning unit, is used to collect air conditioner real-time data, process central air conditioner energy consumption and energy consumption statistical reports, the building management unit is used to obtain the physical space position and the correlation of the central air conditioner outdoor unit, the coil, the total electric meter, the sub-meter electric meter and the like, the air conditioner management unit is used to obtain the air conditioner mode, the wind speed, the set temperature, the sweep wind mode and the like, the billing unit is used to calculate the fee based on the central air conditioner energy consumption, the warning unit is used to obtain the air conditioner fault information based on the energy consumption statistical report, the fault unit is used to generate diagnosis information and propose a diagnosis scheme based on the air conditioner fault information, and the notification unit is used to send the diagnosis information and the diagnosis scheme to the person concerned.

[0112] Embodiment 3

[0113] In some embodiments of the present application, a computer device is also provided, including a memory and a processor, the memory has computer readable instructions stored therein, and the computer readable instructions are executed by the processor to enable the processor to perform the steps of the large language model based central air conditioner terminal energy consumption processing method in embodiment 1 of the present application.

[0114] The present application also provides a storage medium having computer readable instructions stored therein, and the computer readable instructions are executed by one or more processors to enable the one or more processors to perform the steps of the large language model based central air conditioner terminal energy consumption processing method as described in any one of embodiment 1.

[0115] It can be understood that, for the foregoing mentioned central air conditioning terminal energy consumption processing method based on a large language model, if each is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer server, or a network device, etc.) to execute all or part of the steps of the embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program code storage media.

[0116] The computer readable storage medium can include a data signal carried in the baseband or as part of a carrier wave propagating through the program code readable by the computer. Such a propagating data signal can take various forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The readable storage medium can also be any readable medium other than the readable storage medium, which can send, propagate or transmit programs for use by or in conjunction with an instruction execution system, device or apparatus. The program code contained on the readable storage medium can be transmitted by any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0117] The above is only the preferred embodiment of the present application, and the protection scope of the present application is not limited to the above-mentioned embodiments. Any technical solution falling within the scope of the present application is within the protection scope of the present application. It should be noted that, for ordinary skilled persons in the art, some improvements and refinements without departing from the principles of the present application are also considered to be within the protection scope of the present application.

Claims

1. A central air conditioning terminal energy consumption processing method based on a large language model, characterized in that: The following steps are involved: S1: Store air conditioning theory data, air conditioning failure data, heat transfer documents, refrigeration documents, fluid mechanics documents, HVAC data, and historical air conditioning data into the data lake, and normalize the numerical data of the historical air conditioning data to obtain a dataset; S2: Input the air conditioning data into a large language model for learning, select the gradient boosting tree GBM as the regression model, input the training set of the data set into the regression model for training to obtain a training model, and input the prediction set of the data set into the training model to obtain the coil control coefficient; S3: Calculate the energy consumption of the central air conditioner based on the coil control coefficient and real-time data and generate an energy consumption statistical report; In step S3, calculating the energy consumption of the central air conditioner according to the coil control coefficient and the real-time data further includes: S31: Obtain the number of floors of the coil and the number of floors of the sub-meter according to the correlation relationship, and calculate the proportion of the coil electricity consumption according to the number of floors of the coil and the number of floors of the sub-meter. The calculation formula is as follows: in, is the number of floors of the coil, The number of floors of the electric meter sub-meter; S32: Calculate the power consumption coefficient of a single coil according to the coil control coefficient and the coil operation time. The calculation formula is as follows: in, is the coil control coefficient, is the coil operation time; S33: Calculate the total power consumption of all coils based on the coil power consumption proportion and the power consumption of the sub-meter. The calculation formula is as follows: in, The power consumption of the terminal sub-meter on the floor within the command time; S34: Calculate the power consumption of each coil per second based on the total power consumption of all coils and the coil control coefficient, that is, the total power consumption of all coils per unit time divided by the operation time of each coil per unit time multiplied by the sum of the coil control coefficients equals the power consumption of each coil per second. The calculation formula is as follows: S35: Calculating fan power consumption based on the brand fan rated power and the coil control coefficient; S36: Calculating the energy consumption of each coil per second based on the coil power consumption apportionment ratio, the power consumption of each coil per second, and the power consumption of the fan; S37: Calculating the power consumption of the room based on the power consumption per second of the coil and the power-on operation time, and calculating the room electricity fee based on the unit price of electricity and the total power consumption of the room; Among them, the coil control coefficient is a billing coefficient value calculated by the large language model.

2. The central air-conditioning terminal energy consumption processing method based on a large language model according to claim 1 is characterized in that: Real-time data includes: Obtain the physical location and relationship of the central air conditioning outdoor unit, coil, main electricity meter, and sub-meters; Get the brand, rated power, room area, and current electricity price of the room's air conditioner; Collect air conditioning related data on air conditioning sensors including air conditioning mode, wind speed, set temperature, sweep mode, indoor temperature, outdoor temperature, air conditioning running time, and related sub-meter readings, and clean the air conditioning related data to ensure data validity.

3. The central air-conditioning terminal energy consumption processing method based on a large language model according to claim 1 is characterized in that: In step S35, the fan power consumption is calculated according to the rated power of the fan of the brand and the coil control coefficient, further comprising: in, is the rated power of the fan of the brand mentioned, Power is used for the fan.

4. The central air-conditioning terminal energy consumption processing method based on a large language model according to claim 3 is characterized in that: In step S36, the energy consumption of each coil per second is calculated based on the coil power consumption allocation ratio, the power consumption of each coil per second, and the power consumption of the fan, further comprising: in, The energy consumption per coil per second.

5. The central air-conditioning terminal energy consumption processing method based on a large language model according to claim 4 is characterized in that: In step S37, the power consumption of the room is calculated based on the power consumption per second of the coil and the power-on operation time, and the electricity fee of the room is calculated based on the unit price of electricity and the total power consumption of the room, further comprising: The room power consumption is calculated based on the power consumption of the coil per second and the startup operation time. The calculation formula is as follows: in, Indicates the boot-up running time per unit time; Calculate the room electricity cost per unit time based on the unit price of electricity and the total electricity consumption of the room. The calculation formula is as follows: in, The unit price of electricity.

6. The central air-conditioning terminal energy consumption processing method based on a large language model according to claim 5 is characterized in that: An energy consumption statistical report including daily energy consumption, monthly energy consumption and annual energy consumption is generated based on the coil electricity consumption sharing ratio, the single coil electricity consumption coefficient, the total electricity consumption of all coils, the electricity consumption of each coil per second, the fan electricity consumption, the energy consumption of each coil per second, the room electricity consumption and the room electricity fee. The energy consumption statistical report is displayed through a visualization tool, and energy-saving suggestions are provided based on the energy consumption statistical report.

7. The central air-conditioning terminal energy consumption processing method based on a large language model according to claim 6 is characterized in that: When air conditioning fault information is monitored, the air conditioning fault information is passed to the large language model. The large language model obtains real-time data of the indoor unit and obtains diagnostic information based on the air conditioning data. A diagnostic plan is proposed based on the diagnostic information. The diagnostic information is pushed to stakeholders through forms including mobile phone APP or mini-program text messages, and the stakeholders handle it according to the diagnostic plan.

8. A computer device, characterized in that: It includes a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the steps of the central air-conditioning terminal energy consumption processing method based on a large language model as described in any one of claims 1 to 7.

9. A storage medium storing computer-readable instructions, characterized in that: When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the central air-conditioning terminal energy consumption processing method based on a large language model as described in any one of claims 1 to 7.

Images