Method, device, air conditioner and computer-readable storage medium for air conditioning energy saving

Abstract

The present application relates to the technical field of air conditioning, and discloses a method for air conditioning energy saving, including: obtaining the hardware parameters and state prediction model of the air conditioner; predicting the state of the air conditioner according to the hardware parameters and the state prediction model; when the state of the air conditioner meets the preset repair conditions, controlling the air conditioner to execute the corresponding repair strategy; when the state of the air conditioner cannot be repaired, inputting the predicted state of the air conditioner into the parameter prediction model to predict the optimal operating parameters of the air conditioner. In this way, by predicting the state of the air conditioner, executing the repair strategy, and predicting the optimal operating parameters, the self-perception, self-repair, and self-regulation of the state of the air conditioner are achieved, and finally the effect of long-term energy saving is achieved and improved. The present application also discloses a device for air conditioning energy saving, an air conditioner, and a computer-readable storage medium.

Description

Technical Field

[0001] The present application relates to the technical field of air conditioning, for example, to a method, a device, an air conditioner and a computer-readable storage medium for energy saving of an air conditioner. Background Art

[0002] Air conditioners are commonly used electrical equipment in production and life. With the increasing demand for energy conservation, how to control the long-term energy-saving operation of air conditioners has become a new research direction.

[0003] The optimal operating parameters of air conditioners under various working conditions are an important factor in achieving energy saving. At present, the optimal operating parameters of air conditioners are obtained by testing under standard working conditions in an enthalpy difference room when the air conditioner is new. It can ensure that the air conditioner operates at the optimal energy consumption ratio in the latest state.

[0004] In the process of implementing the embodiments of the present disclosure, it is found that there are at least the following problems in the related art:

[0005] For air conditioners that are used for a long time, when the state of the air conditioner changes, the optimal operating parameters set under the standard operating conditions of the enthalpy difference room can no longer meet the optimal operation of the air conditioner, which can easily cause an increase in energy consumption. The energy consumption caused by the state change caused by long-term use of the air conditioner is called long-term energy consumption.

[0006] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present application, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0007] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical components or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0008] The embodiments of the present disclosure provide a method, a device, an air conditioner and a computer-readable storage medium for energy saving of an air conditioner, so as to improve the effect of long-term energy-saving operation of the air conditioner.

[0009] In some embodiments, the method for energy saving of air conditioners includes: obtaining hardware parameters and a state prediction model of the air conditioner; predicting the state of the air conditioner based on the hardware parameters and the state prediction model; when the state of the air conditioner meets preset repair conditions, controlling the air conditioner to execute a corresponding repair strategy; when the state of the air conditioner cannot be repaired, inputting the predicted state of the air conditioner into the parameter prediction model to predict the optimal operating parameters of the air conditioner.

[0010] In some embodiments, the apparatus for air conditioning energy saving includes: a processor and a memory storing program instructions, and the processor is configured to execute the aforementioned method for air conditioning energy saving when running the program instructions.

[0011] In some embodiments, the air conditioner includes: an air conditioner body; and the aforementioned device for air conditioner energy saving, which is installed on the air conditioner body.

[0012] In some embodiments, the computer-readable storage medium stores program instructions, and when the program instructions are run, the aforementioned method for air conditioning energy saving is executed.

[0013] The method, device, air conditioner and computer-readable storage medium for air conditioner energy saving provided by the embodiments of the present disclosure can achieve the following technical effects:

[0014] The method for air conditioning energy saving provided by the embodiment of the present disclosure is divided into two stages: the first stage is: based on the hardware parameters of the air conditioner and using the state prediction model to predict the state of the air conditioner. When the state of the air conditioner meets the preset repair conditions, the air conditioner is controlled to execute the corresponding repair strategy to repair the state of the air conditioner. If the state of the air conditioner fails to change after executing a series of repair strategies, that is, the state of the air conditioner cannot be repaired, then enter the second stage: input the predicted state of the air conditioner into the parameter prediction model to predict the optimal operating parameters of the air conditioner when the state of the air conditioner cannot be repaired. In this way, by predicting the state of the air conditioner, executing the repair strategy and predicting the optimal operating parameters, the self-perception, self-repair and self-regulation of the air conditioner state are achieved, and finally the effect of long-term energy saving is achieved and improved.

[0015] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] One or more embodiments are exemplarily described by corresponding drawings, which do not limit the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements, and the drawings do not constitute a scale limitation, and wherein:

[0017] Figure 1 is a schematic diagram of a method for air conditioning energy saving provided by an embodiment of the present disclosure;

[0018] Figure 2 is a schematic diagram of another method for air conditioning energy saving provided by an embodiment of the present disclosure;

[0019] Figure 3 is an application schematic diagram for air conditioning energy saving provided by an embodiment of the present disclosure;

[0020] Figure 4is a schematic diagram of a device for air conditioning energy saving provided by an embodiment of the present disclosure;

[0021] Figure 5 is a schematic diagram of another device for air conditioning energy saving provided by an embodiment of the present disclosure;

[0022] Figure 6 It is a schematic diagram of an air conditioner provided in an embodiment of the present disclosure.

[0023] Reference numerals:

[0024] 40. Device for air conditioning energy saving; 41. Acquisition module; 42. State prediction module; 43. Control module; 44. Parameter prediction module;

[0025] 50. Device for energy saving of air conditioner; 51. Processor; 52. Memory; 53. Communication interface; 54. Bus;

[0026] 60. Air conditioning. DETAILED DESCRIPTION

[0027] In order to be able to understand the features and technical contents of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the accompanying drawings. The attached drawings are for reference only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.

[0028] The terms "first", "second", etc. in the specification and claims of the embodiments of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged where appropriate, so that the embodiments of the embodiments of the present disclosure described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

[0029] Unless otherwise stated, the term "plurality" means two or more.

[0030] In the embodiment of the present disclosure, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B indicates: A or B.

[0031] The term "and / or" is a description of the association relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or, A and B.

[0032] The term "correspondence" may refer to an association relationship or a binding relationship. The correspondence between A and B means that there is an association relationship or a binding relationship between A and B.

[0033] Combination Figure 1 As shown, the embodiment of the present disclosure provides a method for energy saving of air conditioner, comprising:

[0034] S101: The processor obtains hardware parameters and a state prediction model of the air conditioner.

[0035] S102: The processor predicts the air conditioning state according to the hardware parameters and the state prediction model.

[0036] S103, when the air conditioner state meets the preset repair condition, the processor controls the air conditioner to execute the corresponding repair strategy.

[0037] S104: When the air-conditioning state cannot be repaired, the processor inputs the predicted air-conditioning state into a parameter prediction model to predict the optimal operating parameters of the air-conditioning.

[0038] The processor of the air conditioner obtains the hardware parameters of the air conditioner and multiple state prediction models pre-stored in the memory. The multiple state prediction models include a dirty blockage model and a refrigerant quantity model. The dirty blockage model is used to predict the dirty blockage level of the air conditioner. Optionally, the dirty blockage level includes six levels, namely 0% (no dirty blockage), 20%, 40%, 60%, 80%, and 100% (all dirty blockage). The refrigerant quantity model is used to predict the refrigerant quantity, refrigerant shortage, and refrigerant leakage status.

[0039] Input the hardware parameters into the corresponding state prediction model to predict the air conditioner state. It is understandable that since there are multiple state prediction models, there will be multiple predicted air conditioner states, such as predicting that the air conditioner is in a dirty and blocked state and a refrigerant-deficient state. The air conditioner state can reflect the faults faced by the air conditioner. Then determine whether the predicted air conditioner state meets the preset repair conditions. When one or more air conditioner states meet the preset repair conditions, control the air conditioner to execute the repair strategy corresponding to the air conditioner state to try to repair the air conditioner fault.

[0040] The memory of the air conditioner also stores a parameter prediction model in advance. If the air conditioner state cannot be repaired, the processor calls the parameter prediction model and inputs the air conditioner state into the parameter prediction model to predict the optimal operating parameters of the air conditioner in the current state.

[0041] The method for air conditioning energy saving provided by the embodiment of the present disclosure is divided into two stages: the first stage is: based on the hardware parameters of the air conditioner and using the state prediction model to predict the state of the air conditioner. When the state of the air conditioner meets the preset repair conditions, the air conditioner is controlled to execute the corresponding repair strategy to repair the state of the air conditioner. If the state of the air conditioner fails to change after executing a series of repair strategies, that is, the state of the air conditioner cannot be repaired, then enter the second stage: input the predicted state of the air conditioner into the parameter prediction model to predict the optimal operating parameters of the air conditioner when the state of the air conditioner cannot be repaired. In this way, by predicting the state of the air conditioner, executing the repair strategy and predicting the optimal operating parameters, the self-perception, self-repair and self-regulation of the air conditioner state are achieved, and finally the effect of long-term energy saving is achieved and improved.

[0042] Optionally, the hardware parameters of the air conditioner include: parameters obtained by the air conditioner sensor and user-set parameters. Optionally, the parameters obtained by the air conditioner sensor include: exhaust temperature, intake temperature and other parameters. The parameters obtained by the air conditioner sensor can characterize the operating state and operating environment of the air conditioner. Optionally, the user-set parameters include: set temperature, set wind speed, set wind direction and other parameters. The user-set parameters can characterize the operating state of the air conditioner that the user expects. Therefore, the hardware parameters of the air conditioner can reflect the difference between the actual operating state of the air conditioner and the operating state expected by the user, so that the air conditioner state can be predicted more accurately.

[0043] Combination Figure 2 As shown, the embodiment of the present disclosure provides another method for air conditioning energy saving, including:

[0044] S101: The processor obtains hardware parameters and a state prediction model of the air conditioner.

[0045] S112: The processor selects characteristic parameters from the hardware parameters of the air conditioner.

[0046] S122: The processor preprocesses the parameter data corresponding to the characteristic parameter to obtain preprocessed parameter data.

[0047] S132, the processor inputs the preprocessed parameter data into the corresponding state prediction model to predict the air conditioning state.

[0048] S103, when the air conditioner state meets the preset repair condition, the processor controls the air conditioner to execute the corresponding repair strategy.

[0049] S104: When the air-conditioning state cannot be repaired, the processor inputs the predicted air-conditioning state into a parameter prediction model to predict the optimal operating parameters of the air-conditioning.

[0050] Among the hardware parameters of the air conditioner obtained, some parameters are variables with a high correlation with the predicted air conditioner state, and these parameters need to be selected. Therefore, characteristic parameters are selected from the hardware parameters of the air conditioner. Then, the parameter data corresponding to the characteristic parameters are preprocessed, abnormal values ​​are detected and excluded, and then the processed parameter data is obtained. Optionally, the Hample algorithm is used to detect abnormal values.

[0051] The processed parameter data is related to different air-conditioning states, and the processed parameter data is numerically input to the state prediction model corresponding to the characteristic parameter. For example, the parameter data related to air-conditioning dirt and blockage is input to the dirt and blockage model, and the parameter data related to the refrigerant quantity is input to the refrigerant quantity model. The air-conditioning state is predicted by the corresponding state prediction model.

[0052] In this way, characteristic parameters are selected from the numerous parameters in the hardware parameters to ensure a high correlation between the parameters and the air-conditioning state. At the same time, the selected characteristic parameters are preprocessed to exclude abnormal data, which is conducive to accurately predicting the air-conditioning state. Moreover, the processed parameter data is input into the matching state prediction model to predict different air-conditioning states, so as to further improve the accuracy of predicting the air-conditioning state.

[0053] Optionally, at S112, the processor selects characteristic parameters from the hardware parameters of the air conditioner, including:

[0054] The processor selects the first type of characteristic parameters from the hardware parameters of the air conditioner according to the dirty and blocked characteristics of the air conditioner. And / or,

[0055] The processor selects the second type of characteristic parameters from the hardware parameters of the air conditioner according to the refrigerant characteristics of the air conditioner.

[0056] According to the dirty and blocked characteristics of the air conditioner, for example, the dirty and blocked air conditioner will affect the coil temperature, the compressor suction temperature, the compressor exhaust temperature, etc., and the first type of characteristic parameters are selected from the hardware parameters of the air conditioner. Optionally, the first type of characteristic parameters include: exhaust temperature, suction temperature, temperature of the defrost sensor, outdoor ambient temperature, total current, compressor speed, first outdoor unit fan speed, second outdoor unit fan speed, outdoor valve opening, outdoor coil temperature, auxiliary valve opening, heat exchanger inlet temperature, set temperature, set wind speed and other parameters. In this way, the first type of characteristic parameters are input into the dirty and blocked model to predict the dirty and blocked state of the air conditioner.

[0057] According to the refrigerant characteristics of the air conditioner, for example, insufficient refrigerant in the air conditioner will affect the heat exchange effect, etc., the SHAP algorithm is used to select the second type of characteristic parameters from the hardware parameters of the air conditioner. In this way, the second type of characteristic parameters are input into the refrigerant quantity model to predict the refrigerant quantity state of the air conditioner.

[0058] Optionally, the processor selects a second type of characteristic parameter from the hardware parameters of the air conditioner according to the refrigerant characteristics of the air conditioner, including:

[0059] The processor obtains the contribution of various parameters and the amount of refrigerant.

[0060] The processor selects parameters corresponding to a plurality of contribution degrees according to a preset rule as the second type of characteristic parameters.

[0061] First, calculate the contribution of various parameters included in the hardware parameters and the amount of refrigerant, and then obtain multiple contributions. Optionally, use the SHAP (SHapley Additive exPlanations, theoretically optimal machine learning explanation) algorithm to calculate the contribution of multiple parameters and the amount of refrigerant. The essence of the SHAP algorithm is a subset and problem. It gives each feature a reliable explanatory weight by approximating the Shapley value, and shows how to distribute costs or impacts to different participants in a complex problem. The SHAP algorithm approximates the Shapley value through the Shapley kernel, thereby providing a reasonable and reliable explanatory weight for each feature and the prediction results of the model, effectively improving the interpretability and application value of the model.

[0062] Then, according to the preset rules, multiple parameters corresponding to the contribution degrees are selected, and these selected parameters are used as the second type of characteristic parameters. The greater the contribution degree, the greater the correlation between this parameter and the corresponding state, and the more accurately the air conditioning state can be predicted by using this parameter as a characteristic parameter. Therefore, the preset rule is to select the parameters corresponding to the contribution degrees arranged from large to small and ranked in the top N, where N is set by the user as needed. For example, if the user wants to select ten second type characteristic parameters, the ten parameters corresponding to the larger contribution degrees are selected as the second type characteristic parameters.

[0063] In this way, by calculating the contribution of each parameter to the refrigerant quantity, and selecting corresponding characteristic parameters from the multiple calculated contributions based on preset rules, the high correlation between the selected parameters and the refrigerant quantity is ensured, thereby improving the accuracy of the refrigerant quantity prediction.

[0064] Optionally, the processor obtains the contribution of multiple parameters to the amount of refrigerant, including:

[0065] The processor uses a variety of parameters to train the DT model and perform parameter optimization to obtain the optimal DT model.

[0066] The processor uses the TreeExplainer in the SHAP library, which is specifically for tree models, to explain the DT model.

[0067] The processor inputs the data set including various parameters into the TreeExplainer function in the SHAP library, calculates the SHAP value, and obtains the contribution of various parameters to the amount of refrigerant.

[0068] The DT (Decision Tree Model) model is trained using a variety of parameters included in the hardware parameters. Specifically, the characteristic variables are recorded by sensors arranged at the preset temperature measurement points and preset pressure measurement points of the unit, totaling 74 variables and 122,927 samples. Some samples are selected, for example, 80% of the samples are selected for training the DT model. The parameters are optimized, and the optimization range is: tree_param_grid = {'min_samples_split':[10,15,20], 'min_samples_leaf':[5,7,9], 'max_depth':[5,10,15]}. After optimization, the optimal DT model for explanation is obtained.

[0069] Since the DT model is a tree model, the TreeExplainer in the SHAP library, which is specifically for tree models, is used to explain the DT model obtained above.

[0070] Next, the training dataset X_train is input into TreeExplainer to calculate the SHAP values, which characterize the importance of each feature to the model prediction. This importance information can help understand how the model makes predictions and the degree of influence of each feature on the final prediction results. In this way, the contribution of parameters to the amount of refrigerant can be obtained.

[0071] In the SHAP library, the SHAP value is calculated using the following formula:

[0072]

[0073] in:

[0074] Represents feature x j The SHAP value of the feature we want to calculate.

[0075] S: represents the feature set, consisting of features other than feature x j It consists of p-1 features other than .

[0076] |S|: represents the number of elements in the feature set S.

[0077] p: represents the total number of features.

[0078] |S|!: represents the factorial of the number of elements in the feature set S.

[0079] (p-|S|-1)! : represents the factorial of the remaining features.

[0080] val(S∪{x j}): represents the feature set S plus feature x j The predicted output of the combination in the model.

[0081] val(S): represents the predicted output of the feature set S in the model.

[0082] The meaning of this formula is: for any feature x j , when added to a feature set S, its contribution to the final prediction result is by adding x j It is calculated by combining with other features in S. Specifically, S is calculated without considering x j In the case of features, all possible subset combinations, that is, those that do not contain x j All feature subsets of features. val(S∪{x j})-val(S) means to convert x j The change in the prediction result when the feature is added to the feature set S. Represents feature x j The number of different combinations of features from other features in S is the coefficient in the Shapley value. This coefficient ensures the fairness and consistency of the Shapley value.

[0083] Through this formula, key characteristic parameters with greater contribution to fault diagnosis such as insufficient refrigerant can be obtained. The contribution of each parameter feature (i.e., Shapley value) is sorted from large to small, and the first N characteristic parameters with greater contribution are selected as the second type of characteristic parameters.

[0084] Alternatively, the SHAP value can be calculated using the following formula:

[0085]

[0086] in:

[0087] Indicates that in sample m, feature x j The predicted output of the model when is set to the observed value and other features are held constant.

[0088] Indicates that in sample m, feature x j The predicted output of the model when the feature is removed (or set to missing value) and other features remain unchanged.

[0089] This formula is to approximate the feature x by using the sample average method.j Specifically, it evaluates the feature x on each sample j The contribution of x is then averaged over all samples. This method is often used for model interpretation in practical applications because it is relatively simple and fast to calculate, especially for some complex models. In other words, the calculation process of the formula is that for each sample m, the feature x is calculated. j Set to the observed value The predicted output of the model when j The predicted output of the model when removing (or setting as missing values) The difference of all samples is summed up and the average is taken. In this way, the feature x is obtained. j The SHAP value of , that is, the average contribution of the feature to the model prediction.

[0090] Optionally, at S122, the processor preprocesses parameter data corresponding to the characteristic parameter, including:

[0091] The processor uses a preset length as a window to calculate the median absolute deviation of the plurality of parameter data.

[0092] The processor removes the parameter data when the parameter data does not meet the preset conditions regarding the absolute deviation of the median number.

[0093] The processor replaces the excluded data with the median within the window.

[0094] Use the Hampel algorithm to detect outliers. The Hampel filter is a median-based outlier detection method and a linear filter. It is mainly used to remove impulse noise from signals and has strong anti-interference capabilities. Therefore, it is widely used in signal processing, communication systems and other fields. This filter can effectively eliminate outliers in the data, which may be caused by data corruption, errors or abnormal conditions of the real data. Regardless of the cause, outliers will have a negative impact on data analysis and modeling. Therefore, the Hampel filter plays a very important role in the data preprocessing stage.

[0095] For the parameter data X that needs to be filtered i , select a window of a preset length, optionally, the preset length is 2k+1. Then, calculate the median absolute deviation of multiple parameter data, and determine X by the median absolute deviation (MAD). i The validity of the parameter data is determined. Determine whether the parameter data meets the preset conditions for the absolute deviation of the median number. If it does, the data is judged to be valid, and the output is X iIf it does not meet the requirement, that is, the data is judged as singular data (i.e., outliers), the data will be removed and the removed X will be replaced by the median in the window. i In actual use, for a set of data to be tested, the first number X i Start by padding k zeros forward, and then for the first number X i Hampel filtering is performed on the k numbers on the left and right, and then the window slides backward one by one.

[0096] The calculation formula for the median absolute deviation (MAD) is as follows:

[0097] MAD=Median{|X i -median|}

[0098] Where median is the median in the window, and Median{} indicates the calculation of the median.

[0099] Optionally, the precondition is |X i -median|>t 0 ×MAD

[0100] Among them, t 0 It is a floating point number, which is the threshold for outlier detection.

[0101] After the hardware parameters are preprocessed, the data is input into the matching state prediction model to predict the air conditioning state.

[0102] Optionally, the optimal operating parameters of the air conditioner predicted by the processor include: compressor frequency, internal fan speed, external fan speed, expansion valve opening, etc. In this way, when the amount of refrigerant is insufficient or the heat exchanger is dirty and blocked and cannot be cleaned in time, the optimal operating parameters of the air conditioner in the current state are predicted, thereby achieving energy saving.

[0103] Optionally, the dirty congestion model includes a BP (Back Propagation) neural network model to determine the dirty congestion level. Through training and tuning of the model, a 23-layer BP network is finally used to identify the dirty congestion level.

[0104] Optionally, the refrigerant quantity model includes: a Bi-LSTM (Bi-directional Long Short-Term Memory) model to identify the refrigerant quantity. After the air conditioner refrigerant quantity is identified, a regression prediction is performed on the refrigerant quantity from 60% to 110%, that is, the result of the refrigerant quantity is predicted, and a corresponding alarm prompt is provided when the result shows that the refrigerant quantity is insufficient. In this way, a multi-output LSTM model is used to predict the compressor frequency, internal and external fan speeds, and expansion valve opening, and the sequence-to-sequence method is used to improve the prediction accuracy.

[0105] Optionally, the repair strategy includes: when the air conditioner is predicted to be in a dirty and blocked state, controlling the air conditioner to execute cleaning strategies of different intensities according to the dirty and blocked level to achieve high-precision self-cleaning. When the air conditioner is predicted to be in a state of insufficient refrigerant, an alarm is issued.

[0106] Combination Figure 3 As shown, the specific implementation steps of the embodiment of the present disclosure will be described below by way of example;

[0107] S301: The processor selects a first type of characteristic parameter and a second type of characteristic parameter from hardware parameters of the air conditioner.

[0108] S302, the processor pre-processes the first type of characteristic parameters and the second type of characteristic parameters to remove abnormal values; then, executes S303 and S308.

[0109] S303, the processor inputs the processed first-category characteristic parameters into the dirty and clogging model to predict the dirty and clogging level of the heat exchanger.

[0110] S304, the processor determines whether the heat exchanger needs to be cleaned; if yes, execute S305; if no, execute S301.

[0111] S305, the processor executes a self-cleaning strategy; then, executes S306.

[0112] S306, the processor determines whether the dirty blockage fault of the heat exchanger has been repaired; if yes, execute S301; if not, execute S307.

[0113] S307, the processor inputs the dirty and blocked state into the parameter prediction model; and then executes S313.

[0114] S308: The processor inputs the processed second-category characteristic parameters into the refrigerant quantity model to predict the refrigerant quantity.

[0115] S309, the processor determines whether the amount of refrigerant is insufficient; if yes, execute S310; if not, execute S301.

[0116] S310, the processor performs a refrigerant quantity fault repair report; then, executes S311.

[0117] S311, the processor determines whether the refrigerant shortage fault has been repaired; if yes, execute S301; if not, execute S312.

[0118] In S312, the processor inputs the refrigerant quantity state into the parameter prediction model; and then executes S313.

[0119] S313, the processor uses the parameter prediction model to predict optimal parameters such as the optimal frequency of the compressor, the optimal speed of the internal fan, the optimal speed of the external fan, and the optimal opening of the expansion valve.

[0120] Combination Figure 4 As shown, an embodiment of the present disclosure provides a device 40 for energy saving of an air conditioner, comprising: an acquisition module 41, a state prediction module 42, a control module 43 and a parameter prediction module 44. The acquisition module 41 is configured to acquire hardware parameters and a state prediction model of the air conditioner. The state prediction module 42 is configured to predict the state of the air conditioner based on the hardware parameters and the state prediction model. The control module 43 is configured to control the air conditioner to execute a corresponding repair strategy when the state of the air conditioner meets a preset repair condition. The parameter prediction module 44 is configured to input the predicted state of the air conditioner into the parameter prediction model to predict the optimal operating parameters of the air conditioner when the state of the air conditioner cannot be repaired.

[0121] The device 40 for air conditioning energy saving provided by the embodiment of the present disclosure is divided into two stages: the first stage is: based on the hardware parameters of the air conditioner and using the state prediction model to predict the state of the air conditioner. When the state of the air conditioner meets the preset repair conditions, the air conditioner is controlled to execute the corresponding repair strategy to repair the state of the air conditioner. If the state of the air conditioner fails to change after executing a series of repair strategies, that is, the state of the air conditioner cannot be repaired, then enter the second stage: input the predicted state of the air conditioner into the parameter prediction model to predict the optimal operating parameters of the air conditioner when the state of the air conditioner cannot be repaired. In this way, by predicting the state of the air conditioner, executing the repair strategy and predicting the optimal operating parameters, the self-perception, self-repair and self-regulation of the air conditioner state are achieved, and finally the effect of long-term energy saving is achieved and improved.

[0122] Combination Figure 5 As shown, the embodiment of the present disclosure provides a device 50 for air conditioning energy saving, including a processor 51 and a memory 52. ​​Optionally, the device 50 may also include a communication interface 53 and a bus 54. The processor 51, the communication interface 53, and the memory 52 may communicate with each other through the bus 54. The communication interface 53 may be used for information transmission. The processor 51 may call the logic instructions in the memory 52 to execute the method for air conditioning energy saving of the above embodiment.

[0123] In addition, the logic instructions in the memory 52 described above can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product.

[0124] The memory 52 is a computer-readable storage medium that can be used to store software programs and computer executable programs, such as program instructions / modules corresponding to the method in the embodiment of the present disclosure. The processor 51 executes the function application and data processing by running the program instructions / modules stored in the memory 52, that is, the method for air conditioning energy saving in the above embodiment is implemented.

[0125] The memory 52 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 52 may include a high-speed random access memory and may also include a non-volatile memory.

[0126] Combination Figure 6 As shown, an embodiment of the present disclosure provides an air conditioner 60, including: an air conditioner body, and the above-mentioned device 40 (50) for air conditioner energy saving. The device 40 (50) for air conditioner energy saving is installed on the air conditioner body. The installation relationship described here is not limited to placement inside the air conditioner body, but also includes installation connections with other components of the air conditioner 60, including but not limited to physical connections, electrical connections or signal transmission connections. It can be understood by those skilled in the art that the device 40 (50) for air conditioner energy saving can be adapted to a feasible product body, thereby realizing other feasible embodiments.

[0127] An embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to execute the above-mentioned method for energy saving of air conditioners.

[0128] The technical solution of the embodiment of the present disclosure can be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiment of the present disclosure. The aforementioned storage medium may be a non-transient storage medium, such as: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes.

[0129] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process and other changes. The embodiments represent only possible changes. Unless explicitly required, separate components and functions are optional, and the order of operation may vary. The parts and features of some embodiments may be included in or replace the parts and features of other embodiments. Moreover, the words used in this application are only used to describe the embodiments and are not used to limit the claims. As used in the description of the embodiments and the claims, unless the context clearly indicates, the singular forms of "a", "an" and "the" are intended to include plural forms as well. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of listings containing one or more associated ones. In addition, when used in the present application, the term "comprise" and its variants "comprises" and / or comprising refer to the presence of stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof. In the absence of further restrictions, the elements defined by the sentence "comprising a ..." do not exclude the presence of other identical elements in the process, method or device comprising the elements. In this article, each embodiment may focus on the differences from other embodiments, and the same and similar parts between the various embodiments may refer to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can refer to the description of the method part.

[0130] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. The technicians may use different methods for each specific application to implement the described functions, but such implementations should not be considered to exceed the scope of the embodiments of the present disclosure. The technicians may clearly understand that, for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above may refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0131] In the embodiments disclosed herein, the disclosed methods and products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units can be only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to implement this embodiment. In addition, each functional unit in the embodiment of the present disclosure may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit.

[0132] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A method for air conditioning energy saving, characterized in that: include: Obtaining hardware parameters and a state prediction model of the air conditioner; wherein the state prediction model includes: a dirty blockage model and a refrigerant quantity model; According to the hardware parameters and the state prediction model, the state of the air conditioner is predicted; wherein the hardware parameters include: parameter data related to the dirty blockage of the air conditioner and parameter data related to the amount of refrigerant; according to the hardware parameters and the state prediction model, the state of the air conditioner is predicted, including: inputting the parameter data related to the dirty blockage of the air conditioner into the dirty blockage model to predict the dirty blockage level of the air conditioner; inputting the parameter data related to the amount of refrigerant into the refrigerant amount model to predict the state of the refrigerant amount, the insufficient amount of refrigerant, and the refrigerant leakage; When the air conditioner status meets the preset repair conditions, the air conditioner is controlled to execute the corresponding repair strategy; When the air conditioning state cannot be repaired, the predicted air conditioning state is input into the parameter prediction model to predict the optimal operating parameters of the air conditioner; wherein, inputting the predicted air conditioning state into the parameter prediction model includes: when the dirty blockage fault cannot be repaired, inputting the predicted dirty blockage state into the parameter prediction model; when the refrigerant fault cannot be repaired, inputting the predicted refrigerant quantity state into the parameter prediction model.

2. The method according to claim 1, characterized in that: The hardware parameters include: parameters acquired by the air conditioner's sensors and parameters set by the user.

3. The method according to claim 1, characterized in that According to the hardware parameters and status prediction model of the air conditioner, the status of the air conditioner is predicted, including: Select characteristic parameters from the hardware parameters of the air conditioner; Preprocessing parameter data corresponding to the characteristic parameters to obtain preprocessed parameter data; The preprocessed parameter data is input into the corresponding state prediction model to predict the air conditioning state.

4. The method according to claim 3, characterized in that Select characteristic parameters from the hardware parameters of the air conditioner, including: According to the dirty and blocked characteristics of the air conditioner, a first type of characteristic parameter is selected from the hardware parameters of the air conditioner; and / or, According to the refrigerant characteristics of the air conditioner, the second type of characteristic parameters are selected from the hardware parameters of the air conditioner.

5. The method according to claim 4, characterized in that The hardware parameters of the air conditioner include multiple parameters. According to the refrigerant characteristics of the air conditioner, the second type of characteristic parameters are selected from the hardware parameters of the air conditioner, including: Obtain the contribution of various parameters and refrigerant quantity; According to preset rules, parameters corresponding to multiple contribution degrees are selected as the second type of characteristic parameters.

6. The method according to claim 5, characterized in that Get the contribution of various parameters to the amount of refrigerant, including: Use multiple parameters to train the DT model and optimize the parameters to obtain the optimal DT model; Use TreeExplainer in the SHAP library, which is specifically designed for tree models, to explain the DT model; The data set including various parameters is input into the TreeExplainer function in the SHAP library, the SHAP value is calculated, and the contribution of various parameters to the amount of refrigerant is obtained.

7. The method according to claim 3, characterized in that Preprocess the parameter data corresponding to the characteristic parameters, including: Using the preset length as the window, calculate the median absolute deviation of multiple parameter data; If the parameter data do not meet the preset conditions regarding the absolute deviation of the median number, the parameter data will be eliminated; Use the median of the window to replace the removed data.

8. A device for air conditioning energy saving, comprising a processor and a memory storing program instructions, characterized in that: The processor is configured to execute the method for air conditioning energy saving according to any one of claims 1 to 7 when running the program instructions.

9. An air conditioner, characterized in that: include: Air conditioner body; The device for energy saving in air conditioning as claimed in claim 8 is installed on the air conditioning body.

10. A computer-readable storage medium storing program instructions, characterized in that: When the program instructions are executed, the computer is used to execute the method for air conditioning energy saving as claimed in any one of claims 1 to 7.

Images