Method and apparatus for energy saving of air conditioner, and air conditioner and computer-readable storage medium

Abstract

The present application relates to the technical field of air conditioners. Disclosed is a method for energy saving of an air conditioner, the method comprising: acquiring hardware parameters and a state prediction model of an air conditioner; on the basis of the hardware parameters and the state prediction model, predicting the state of the air conditioner; when the state of the air conditioner meets a preset restoration condition, controlling the air conditioner to execute a corresponding restoration strategy; and when the state of the air conditioner cannot be restored, inputting the predicted state of the air conditioner into a parameter prediction model, and predicting optimal operating parameters of the air conditioner.

Description

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

[0001] The present application is based on and claims priority to Chinese Patent Application No. 202410865670.3, filed on June 28, 2024, the entire contents of which are incorporated herein by reference. TECHNICAL FIELD

[0002] The present application relates to the air conditioning technical field, for example, relates to a kind of method, device, air conditioner and computer readable storage medium for air conditioner energy saving. BACKGROUND

[0003] Air conditioner is the common electrical equipment in production and life, with the increasing energy-saving demand, how to control air conditioner long-term energy-saving operation becomes new research direction.

[0004] The optimal operating parameters of air conditioner under various working conditions are important factors for air conditioner to achieve energy saving. At present, the optimal operating parameters of air conditioner are obtained by experiment under the standard working condition of enthalpy difference room when the air conditioner is newly manufactured. It can ensure that the air conditioner runs with optimal energy consumption ratio in the newest state.

[0005] In the process of implementing the embodiments of the present disclosure, it is found that at least the following problems exist in the related art:

[0006] For the air conditioner used for a long time, in the case that the state of the air conditioner changes, the optimal operating parameters set under the standard working condition of enthalpy difference room cannot meet the optimal operation of the air conditioner, which is easy to cause the increase of energy consumption, and the energy consumption caused by the state change due to long-term use of the air conditioner is called long-term energy consumption.

[0007] It should be noted that the information disclosed in the above background section is only used to strengthen the understanding of the background of the present application, and therefore can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0008] In order to have a basic understanding of some aspects of the disclosed embodiments, the following is a simple summary. The summary is not a general review, nor is it intended to determine key / important components or delineate the scope of protection of these embodiments, but as a prelude to the detailed description below.

[0009] The embodiments of the present disclosure provide a method, device, air conditioner and computer readable storage medium for air conditioner energy saving, to improve the effect of long-term energy-saving operation of air conditioner.

[0010] In some embodiments, the method for energy saving of an air conditioner comprises: obtaining a hardware parameter and a state prediction model of the air conditioner; predicting an air conditioner state according to the hardware parameter and the state prediction model; in a case where the air conditioner state meets a preset repair condition, controlling the air conditioner to perform a corresponding repair strategy; and in a case where the air conditioner state cannot be repaired, inputting the predicted air conditioner state into a parameter prediction model to predict an optimal operation parameter of the air conditioner.

[0011] In some embodiments, the device for energy saving of an air conditioner comprises: a processor and a memory storing program instructions, the processor being configured to execute the foregoing method for energy saving of an air conditioner when the program instructions are run.

[0012] In some embodiments, the air conditioner comprises: an air conditioner body; and a device for energy saving of an air conditioner as described above, which is installed on the air conditioner body.

[0013] In some embodiments, the computer readable storage medium stores program instructions, which, when run, execute the foregoing method for energy saving of an air conditioner.

[0014] The foregoing general description and the following description are merely exemplary and explanatory, and are not intended to limit the present application. BRIEF DESCRIPTION OF DRAWINGS

[0015] One or more embodiments are exemplarily illustrated by the corresponding drawings, which do not constitute a limitation on the embodiments, elements with the same reference numerals in the drawings are shown as similar elements, the drawings do not constitute a proportional limitation, and wherein:

[0016] FIG. 1 is a schematic diagram of a method for energy saving of an air conditioner according to an embodiment of the present disclosure;

[0017] FIG. 2 is a schematic diagram of another method for energy saving of an air conditioner according to an embodiment of the present disclosure;

[0018] FIG. 3 is a schematic diagram of an application for energy saving of an air conditioner according to an embodiment of the present disclosure;

[0019] FIG. 4 is a schematic diagram of a device for energy saving of an air conditioner according to an embodiment of the present disclosure;

[0020] FIG. 5 is a schematic diagram of another device for energy saving of an air conditioner according to an embodiment of the present disclosure;

[0021] FIG. 6 is a schematic diagram of an air conditioner according to an embodiment of the present disclosure.

[0022] Label: 40, device for air conditioning energy saving; 41, acquisition module; 42, state prediction module; 43, control module; 44, parameter prediction module; 50, device for air conditioning energy saving; 51, processor; 52, memory; 53, communication interface; 54, bus; 60, air conditioner. DETAILED DESCRIPTION

[0023] In order to enable a more detailed understanding of the features and technical content of the embodiments of the present disclosure, the implementation of the embodiments of the present disclosure is described in detail below, and the attached drawings are only used for reference and do not limit the embodiments of the present disclosure. In the following technical description, in order to facilitate explanation, through multiple details, a sufficient understanding of the disclosed embodiments is provided. However, one or more embodiments can still be implemented without these details. In other cases, in order to simplify the drawings, well-known structures and devices can be simplified.

[0024] The terms "first", "second", and the like in the specification and claims of the embodiments of the present disclosure and the above-mentioned drawings are used to distinguish similar objects and do not necessarily describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described herein can be implemented. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion.

[0025] Unless otherwise specified, the term "multiple" means two or more.

[0026] In the embodiments of the present disclosure, the character " / " represents an "or" relationship between the objects before and after it. For example, A / B represents: A or B.

[0027] The term "and / or" is a description of the association between objects, which means that there can be three relationships. For example, A and / or B, which means: A or B, or, A and B, three relationships.

[0028] The term "corresponding" can refer to an association or binding relationship, A corresponding to B means that there is an association or binding relationship between A and B.

[0029] In combination with FIG. 1, the embodiments of the present disclosure provide a method for air conditioning energy saving, comprising:

[0030] S101, acquiring the hardware parameters and state prediction model of the air conditioner.

[0031] S102, predicting the state of the air conditioner according to the hardware parameters and the state prediction model.

[0032] S103, in the case that the state of the air conditioner meets the preset repair condition, controlling the air conditioner to execute the corresponding repair strategy.

[0033] S104, in the case that the air conditioner state cannot be repaired, inputting the predicted air conditioner state into a parameter prediction model to predict optimal operation parameters of the air conditioner.

[0034] The processor of the air conditioner acquires hardware parameters of the air conditioner and a plurality of state prediction models pre-stored in the memory. The plurality of state prediction models include a dirty blockage model and a refrigerant amount model. The dirty blockage model is used to predict a 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 amount model is used to predict a refrigerant amount, a refrigerant deficiency, and a refrigerant leakage state.

[0035] The hardware parameters are input into the corresponding state prediction model to predict the air conditioner state. It can be understood that since the state prediction model is multiple, the predicted air conditioner state is also multiple, for example, the air conditioner is predicted to be in a dirty blockage state and a refrigerant deficiency state. The air conditioner state can reflect the fault faced by the air conditioner. Then it is judged whether the predicted air conditioner state meets the preset repair condition. When one or more air conditioner states meet the preset repair condition, the air conditioner is controlled to execute a repair strategy corresponding to the air conditioner state to attempt to repair the air conditioner fault.

[0036] The memory of the air conditioner also pre-stores a parameter prediction model. 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 optimal operation parameters of the air conditioner in the current state.

[0037] The method for air conditioner energy saving provided by the embodiments of the present disclosure is divided into two stages: the first stage is to predict the state of the air conditioner based on the hardware parameters of the air conditioner and using the state prediction model. When the air conditioner state meets the preset repair condition, the air conditioner is controlled to execute a corresponding repair strategy to repair the state of the air conditioner. If a series of repair strategies are executed and the state of the air conditioner cannot be changed, that is, the air conditioner state cannot be repaired, the second stage is entered: the predicted air conditioner state is input into the parameter prediction model to predict the optimal operation parameters of the air conditioner when the air conditioner state cannot be repaired. In this way, by predicting the air conditioner state, executing the repair strategy, and predicting the optimal operation parameters, the self-sensing, self-repairing, and self-regulating of the air conditioner state are realized, and the long-term energy saving effect is ultimately realized and improved.

[0038] Optionally, the hardware parameters of the air conditioner include parameters obtained by sensors of the air conditioner and user-set parameters. Optionally, the parameters obtained by the sensors of the air conditioner include parameters such as discharge temperature and suction temperature. The parameters obtained by the sensors of the air conditioner can represent the running state of the air conditioner and the running environment. Optionally, the user-set parameters include parameters such as set temperature, set air speed, and set air direction. The user-set parameters can represent the running state of the air conditioner expected by the user. Therefore, the hardware parameters of the air conditioner can reflect the difference between the actual running state of the air conditioner and the running state expected by the user, so as to more accurately predict the state of the air conditioner.

[0039] In combination with FIG. 2, another method for energy saving of an air conditioner is provided, including:

[0040] S101, obtaining hardware parameters of the air conditioner and a state prediction model.

[0041] S112, selecting feature parameters from the hardware parameters of the air conditioner.

[0042] S122, pre-processing parameter data corresponding to the feature parameters to obtain pre-processed parameter data.

[0043] S132, inputting the pre-processed parameter data into a corresponding state prediction model to predict the state of the air conditioner.

[0044] S103, in a case where the state of the air conditioner meets a preset repair condition, controlling the air conditioner to execute a corresponding repair strategy.

[0045] S104, in a case where the state of the air conditioner cannot be repaired, inputting the predicted state of the air conditioner into a parameter prediction model to predict optimal running parameters of the air conditioner.

[0046] Among the obtained hardware parameters of the air conditioner, some parameters are variables with high relevance to the prediction of the state of the air conditioner, which need to be selected. Therefore, the feature parameters are selected from the hardware parameters of the air conditioner. Then, the parameter data corresponding to the feature parameters is pre-processed to detect and exclude outliers, and thus the pre-processed parameter data is obtained. Optionally, the Hample algorithm is used to detect outliers.

[0047] The pre-processed parameter data is related to different states of the air conditioner, and thus the pre-processed parameter data is input into a state prediction model corresponding to the feature parameters. For example, parameter data related to air conditioner blockage is input into a blockage model, and parameter data related to refrigerant quantity is input into a refrigerant quantity model. The state of the air conditioner is predicted by the corresponding state prediction model.

[0048] In this way, the characteristic parameters are selected from a plurality of hardware parameters to ensure high correlation between the parameters and the air conditioner state. Meanwhile, the selected characteristic parameters are preprocessed to exclude abnormal data, thereby facilitating accurate prediction of the air conditioner state. Moreover, the processed parameter data is input into a matched state prediction model to predict different air conditioner states, thereby further improving the accuracy of predicting the air conditioner state.

[0049] Optionally, S112, selecting the characteristic parameters from the hardware parameters of the air conditioner, comprising:

[0050] According to the dirty block characteristics of the air conditioner, the first type of characteristic parameters are selected from the hardware parameters of the air conditioner. And / or,

[0051] 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.

[0052] According to the dirty block characteristics of the air conditioner, for example, the dirty block of the air conditioner will affect the coil temperature, the compressor suction temperature, the compressor discharge temperature, etc., the first type of characteristic parameters are selected from the hardware parameters of the air conditioner. Optionally, the first type of characteristic parameters include: discharge temperature, suction temperature, defrost sensor temperature, outdoor environment temperature, total current, compressor speed, first outdoor fan speed, second outdoor fan speed, outdoor valve opening, outdoor coil temperature, auxiliary valve opening, heat exchanger inlet temperature, set temperature, set wind speed, etc. In this way, the first type of characteristic parameters are input into the dirty block model to predict the dirty block state of the air conditioner.

[0053] According to the refrigerant characteristics of the air conditioner, for example, the insufficient refrigerant of 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 amount model to predict the refrigerant amount state of the air conditioner.

[0054] Optionally, 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, comprising:

[0055] Obtain the contribution degree of a plurality of parameters to the refrigerant amount.

[0056] According to the preset rule, the parameters corresponding to the plurality of contribution degrees are selected as the second type of characteristic parameters.

[0057] Firstly, the contribution degrees of the plurality of parameters included in the hardware parameters to the refrigerant amount are calculated, and then a plurality of contribution degrees are obtained. Optionally, the contribution degrees of the plurality of parameters to the refrigerant amount are calculated by using a SHAP (SHapley Additive exPlanations) algorithm. The essence of the SHAP algorithm is a subset sum problem, which assigns a reliable explanation weight to each feature by approximating the Shapley value, and shows how to allocate costs or impacts to different participants in a complex problem. The SHAP algorithm approximates the Shapley value by using a Shapley kernel, thereby providing a reasonable and reliable explanation weight for each feature and the prediction result of the model, and effectively improving the explainability and application value of the model.

[0058] Then, the parameters corresponding to the plurality of contribution degrees are selected according to a preset rule, and the selected parameters are taken as the second type of feature parameters. The greater the contribution degree is, the greater the relevance of the parameter to the corresponding state is, and the more accurately the parameter can be taken as a feature parameter to predict the state of the air conditioner. Therefore, the preset rule is to arrange the contribution degrees in descending order, and select the parameters corresponding to the top N contribution degrees, wherein N is set by the user according to needs. For example, if the user wants to select ten second type of feature parameters, the ten parameters corresponding to the greater contribution degrees are selected as the second type of feature parameters.

[0059] In this way, by calculating the contribution degrees of the plurality of parameters to the refrigerant amount, and selecting the corresponding feature parameters from the plurality of contribution degrees based on the preset rule, the high relevance between the selected parameters and the refrigerant amount is ensured, and the accuracy of the refrigerant amount prediction is improved.

[0060] Optionally, the contribution degrees of the plurality of parameters to the refrigerant amount are obtained, including:

[0061] The plurality of parameters are used for training the DT model and parameter optimization to obtain an optimal DT model.

[0062] The DT model is explained by using a TreeExplainer in the SHAP library which is specially designed for tree models.

[0063] A dataset including the plurality of parameters is input into the TreeExplainer function in the SHAP library, the SHAP values are calculated, and the contribution degrees of the plurality of parameters to the refrigerant amount are obtained.

[0064] A DT (Decision Tree Model) model is trained using various parameters included in the hardware parameters. Specifically, the characteristic variables are recorded by sensors arranged at preset temperature measuring points and preset pressure measuring points of the unit, a total of 74 variables, and the sample quantity is 122927. Part of the 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 interpretation is obtained.

[0065] Since the DT model is a tree model, TreeExplainer (tree interpreter) in the SHAP library specially for tree models is used to interpret the DT model obtained above.

[0066] Next, the training data set X_train is input into the TreeExplainer to calculate the SHAP values, which can represent the importance of each feature to the model prediction. These importance information can help understand how the model makes predictions and the degree of influence of each feature on the final prediction result. In this way, the contribution of the parameters to the refrigerant quantity can be obtained.

[0067] In the SHAP library, the SHAP value is calculated using the following formula:

[0068] Wherein:

[0069] represents the SHAP value of the feature x j , i.e. the importance of the feature to be calculated.

[0070] S: represents a feature set consisting of p-1 features other than the feature x j

[0071] |S|: represents the number of elements of the feature set S.

[0072] p: represents the total number of features.

[0073] |S|!: represents the factorial of the number of elements of the feature set S.

[0074] (p-|S|-1)!: represents the factorial of the remaining features.

[0075] val(S∪{x j}): represents the feature set S plus the feature x j ​the predicted output of the combination of the features in the model.

[0076] val(S) represents the predicted output of the feature set S in the model.

[0077] The meaning of this formula is: for any one feature x j , when it is added to a feature set S, the contribution to the final prediction result is calculated by combining x j with other features in S. Specifically, S is all possible subset combinations without considering the x j feature, that is, all feature subsets without x j feature. val(S∪{x j})-val(S) represents the change in the prediction result when x j feature is added to the feature set S. And represents the number of different properties of the combination of feature x j with other features in S, which is the coefficient in the Shapley value. This coefficient guarantees the fairness and consistency of the Shapley value.

[0078] Through this formula, key feature 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 in descending order, and the top N feature parameters with greater contribution are selected as the second type of feature parameters.

[0079] Alternatively, the SHAP value can also be calculated using the following formula:

[0080] wherein:

[0081] represents the predicted output of the model when the feature x j is set to the observed value in sample m, while other features remain unchanged.

[0082] represents the predicted output of the model when the feature x j is removed (or set to a missing value) in sample m, while other features remain unchanged.

[0083] This formula is an approximate calculation of the SHAP value of feature x j by the sample average method. Specifically, it evaluates the feature x jThe contribution of each feature x is calculated, and then the average is taken over all samples. This method is often used for model interpretation in practical applications because it is relatively simple and fast to compute, and is particularly suitable for some complex models. In other words, the calculation process of the formula is to calculate the contribution of each feature x to each sample m, and then average it over all samples. j Set as the observed value The predicted output of the time model, and the feature x j The model's predicted output when values ​​are removed (or set to missing values). The difference is calculated, and the differences of all samples are summed, and finally the average is taken. This yields the feature x. j The SHAP value is the average contribution of a feature to the model's predictions.

[0084] Optionally, S122, preprocessing the parameter data corresponding to the feature parameters, including:

[0085] Using a preset length as a window, calculate the absolute deviation of the median of multiple parameter data.

[0086] If the parameter data does not meet the preset conditions for the absolute deviation of the median, the parameter data will be discarded.

[0087] Replace the removed data with the median value within the window.

[0088] The Hampel algorithm is used to detect outliers. The Hampel filter is a median-based outlier detection method and a linear filter primarily used to remove impulse noise from signals. It has strong anti-interference capabilities and is therefore widely used in signal processing, communication systems, and other fields. This filter can effectively eliminate outliers in data, which may be caused by data corruption, errors, or anomalies in the actual data. Regardless of the cause, outliers negatively impact data analysis and modeling. Therefore, the Hampel filter plays a crucial role in the data preprocessing stage.

[0089] For the parameter data X that needs to be filtered i Select a window of preset length, optionally 2k+1. Then, calculate the median absolute deviation (MAD) of multiple parameter data, and use the MAD to determine X. i The validity of the data is determined by checking whether the parameter data meets the preset conditions for the absolute deviation of the median. If the conditions are met, the data is considered valid, and X is output. i If the conditions are not met, meaning the data is determined to be outlier (i.e., an outlier), then that data is removed, and the removed X is replaced with the median within the window. i In practical applications, for a set of data to be tested, the first number X should be used. iFirst, fill k zeros in front of the number, then perform Hampel filtering on the first number X i And perform Hampel filtering on the left and right k numbers, and then slide the window backward one by one.

[0090] The formula for calculating the median absolute deviation (MAD) is as follows: MAD = Median{|X i -median|}

[0091] Where median is the median in the window, and Median{} represents the calculation of the median.

[0092] Optionally, the preset condition is |X i -median|>t0xMAD

[0093] Where t0 is a floating-point number, which is the threshold value for anomaly detection.

[0094] After the hardware parameters are preprocessed, the data is input into the matching state prediction model to predict the state of the air conditioner.

[0095] Optionally, the optimal operating parameters of the predicted air conditioner include: compressor frequency, internal fan speed, external fan speed, expansion valve opening degree and other parameters. In this way, when the refrigerant is insufficient or the heat exchanger is dirty and cannot be cleaned in time, the optimal operating parameters of the air conditioner under the current state are predicted, so as to realize energy saving.

[0096] Optionally, the dirty block model includes a BP (Back Propagation, Back Propagation) neural network model to judge the dirty block level. Through training and optimization of the model, a 23-layer BP network is finally used to identify the dirty block level.

[0097] Optionally, the refrigerant quantity model includes a Bi-LSTM (Bi-directional Long Short-Term Memory, Bi-directional Long Short-Term Memory Network) model to identify the refrigerant quantity. After identifying the refrigerant quantity of the air conditioner, the refrigerant quantity is regressed and predicted 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, the multi-output LSTM model is used to predict the compressor frequency, internal and external fan speed, and expansion valve opening degree, and the sequence-to-sequence method is used to improve the accuracy of the prediction.

[0098] Optionally, the repair strategy includes: when the predicted air conditioner is in a dirty block state, different intensity cleaning strategies are controlled according to the dirty block level to achieve high-precision self-cleaning. When the predicted air conditioner is in a state of insufficient refrigerant, an alarm prompt is issued.

[0099] With reference to FIG. 3, the specific implementation steps of the embodiments of the present disclosure will be illustrated below.

[0100] S301, in the hardware parameters of the air conditioner, the first type of characteristic parameters and the second type of characteristic parameters are selected.

[0101] S302, the first type of characteristic parameters and the second type of characteristic parameters are preprocessed to eliminate abnormal values; then, S303 and S308 are executed.

[0102] S303, the processed first type of characteristic parameters are input into the dirty block model to predict the dirty block level of the heat exchanger.

[0103] S304, it is judged whether the heat exchanger needs to be cleaned; if yes, S305 is executed; if no, S301 is executed.

[0104] S305, a self-cleaning strategy is executed; then, S306 is executed.

[0105] S306, it is judged whether the dirty block fault of the heat exchanger is repaired; if yes, S301 is executed; if no, S307 is executed.

[0106] S307, the dirty block state is input into the parameter prediction model; then, S313 is executed.

[0107] S308, the processed second type of characteristic parameters are input into the refrigerant amount model to predict the refrigerant amount.

[0108] S309, it is judged whether the refrigerant amount is insufficient; if yes, S310 is executed; if no, S301 is executed.

[0109] S310, refrigerant amount fault repair is performed; then, S311 is executed.

[0110] S311, it is judged whether the refrigerant amount insufficient fault is repaired; if yes, S301 is executed; if no, S312 is executed.

[0111] S312, the refrigerant amount state is input into the parameter prediction model; then, S313 is executed.

[0112] S313, the optimal parameters of the compressor, the optimal speed of the inner fan, the optimal speed of the outer fan, the optimal opening of the expansion valve, etc. are predicted by using the parameter prediction model.

[0113] With reference to FIG. 4, the 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 of the air conditioner and a state prediction model. The state prediction module 42 is configured to predict a state of the air conditioner according to 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 in a case where the state of the air conditioner satisfies a preset repair condition. The parameter prediction module 44 is configured to input the predicted state of the air conditioner into a parameter prediction model in a case where the state of the air conditioner cannot be repaired, and predict optimal operating parameters of the air conditioner.

[0114] The device 40 for energy saving of an air conditioner provided by the embodiment of the present disclosure is divided into two stages: in the first stage, the state of the air conditioner is predicted based on the hardware parameters of the air conditioner and by using the state prediction model. When the state of the air conditioner satisfies the preset repair condition, 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 cannot be changed after a series of repair strategies are executed, i.e., the state of the air conditioner cannot be repaired, the second stage is entered: the predicted state of the air conditioner is input into the parameter prediction model to predict the optimal operating parameters of the air conditioner in the case where 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-sensing, self-repairing and self-regulating of the state of the air conditioner are realized, and the long-term energy saving effect is ultimately achieved and improved.

[0115] With reference to FIG. 5, the embodiment of the present disclosure provides a device 50 for energy saving of an air conditioner, comprising a processor 51 and a memory 52. Optionally, the device 50 can further comprise a communication interface 53 and a bus 54. The processor 51, the communication interface 53 and the memory 52 can complete communication with each other through the bus 54. The communication interface 53 can be used for information transmission. The processor 51 can invoke the logical instructions in the memory 52 to execute the method for energy saving of an air conditioner of the above-mentioned embodiments.

[0116] In addition, the logical instructions in the memory 52 described above can be implemented in the form of a software functional unit and sold or used as an independent product, which can be stored in a computer readable storage medium.

[0117] The memory 52 is a computer readable storage medium, which can be used to store software programs, 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, i.e., implements the method for energy saving of an air conditioner in the above-mentioned embodiments.

[0118] The memory 52 can include a program storage area and a data storage area, wherein the program storage area can store an operating system and application programs required by at least one function; and the data storage area can store data created according to the use of the terminal device, etc. In addition, the memory 52 can include a high-speed random access memory, and can also include a non-volatile memory.

[0119] In combination with FIG. 6, the embodiment of the present disclosure provides an air conditioner 60, comprising: an air conditioner body, and the above-mentioned device 40 (50) for energy saving of an air conditioner. The device 40 (50) for energy saving of an air conditioner is installed on the air conditioner body. The installation relationship described herein is not limited to being placed inside the air conditioner body, but also includes installation connection with other components of the air conditioner 60, including but not limited to physical connection, electrical connection or signal transmission connection, etc. Those skilled in the art can understand that the device 40 (50) for energy saving of an air conditioner can be adapted to a feasible product body, and thus realize other feasible embodiments.

[0120] The embodiment of the present disclosure provides a computer-readable non-transitory storage medium, which stores program instructions. When the program instructions are executed, the following steps are performed:

[0121] Obtaining a hardware parameter and a state prediction model of an air conditioner;

[0122] Predicting an air conditioner state according to the hardware parameter and the state prediction model;

[0123] In a case where the air conditioner state meets a preset repair condition, controlling the air conditioner to execute a corresponding repair strategy;

[0124] In a case where the air conditioner state cannot be repaired, inputting the predicted air conditioner state into a parameter prediction model to predict an optimal operating parameter of the air conditioner.

[0125] The embodiment of the present disclosure provides a computer-readable storage medium, which stores computer executable instructions, and the computer executable instructions are configured to execute the above-mentioned method for energy saving of an air conditioner.

[0126] The embodiment of the present disclosure provides a computer program, which, when executed by a computer, causes the computer to implement the above-mentioned method for energy saving of an air conditioner.

[0127] The embodiment of the present disclosure provides a computer program product, which comprises computer instructions stored on a computer-readable storage medium, and when the program instructions are executed by a computer, the computer implements the above-mentioned method for energy saving of an air conditioner.

[0128] The technical solutions of the embodiments of the present disclosure can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes one or more instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method of the embodiments of the present disclosure. The aforementioned storage medium can be a non-transitory storage medium, including: 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 media that can store program codes.

[0129] The above description and drawings sufficiently illustrate the embodiments of the present disclosure to enable one skilled in the art to practice them. Other embodiments can include structural, logical, electrical, process, and other changes. The embodiments represent only a few of the possible variations. Individual components and functions are optional unless explicitly required, and the order of operations can be changed. Parts and features of some embodiments can be included or substituted for parts and features of other embodiments. Also, the words used in this application are used only to describe the embodiments and not to limit the claims. As used in the description of the embodiments and the claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of one or more associated listed items. In addition, when used in this application, the term "comprise" and its variations "comprises" and / or "comprising" and the like mean the presence of the stated features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. Without more limitations, the element defined by the phrase "comprising a" does not exclude the presence of additional identical elements in the process, method, article of manufacture, or apparatus including the element. In this document, each embodiment focuses on the differences from other embodiments, and the same or similar parts between embodiments can be referred to each other. For the method, product, etc. disclosed by the embodiments, if it corresponds to the method part disclosed by the embodiments, the relevant part can be referred to the description of the method part.

[0130] Those skilled in the art can understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. The skilled person can use different methods for each specific application to realize the described functions, but such implementation should not be considered beyond the scope of the embodiments of the present disclosure. The skilled person can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0131] In the embodiments disclosed herein, the disclosed methods, products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the above-described device embodiments are only schematic, for example, the division of the units can only be a logical function division, and actual implementation can have another division manner, for example, a plurality of 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 the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms. The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to implement the embodiments. In addition, each functional unit in the embodiments of the present disclosure can be integrated in one processing unit, or each unit can be a physically independent unit, or two or more units can be integrated in one unit.

[0132] The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other processing device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other processing device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

Claims

1. A method for energy saving in air conditioning, comprising: Obtain the hardware parameters and status prediction model of the air conditioner; Predict the air conditioner status based on hardware parameters and a status prediction model; If the air conditioner meets the preset repair conditions, control the air conditioner to execute the corresponding repair strategy; If the air conditioner's condition cannot be repaired, the predicted air conditioner condition is input into the parameter prediction model to predict the optimal operating parameters of the air conditioner.

2. The method according to claim 1, wherein, The hardware parameters include: parameters acquired by the air conditioner's sensors and user-defined parameters.

3. The method according to claim 1 or 2, wherein, Based on the air conditioner's hardware parameters and state prediction model, predict the air conditioner's state, including: Select characteristic parameters from the air conditioner's hardware parameters; The parameter data corresponding to the feature parameters are preprocessed to obtain the 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, wherein, Select characteristic parameters from the air conditioner's hardware parameters, including: Based on the characteristics of air conditioner clogging, the first type of characteristic parameter is selected from the air conditioner's hardware parameters; and / or, Based on the refrigerant characteristics of the air conditioner, the second type of characteristic parameter is selected from the air conditioner's hardware parameters.

5. The method according to claim 4, wherein, The hardware parameters of an air conditioner include a variety of parameters; based on the refrigerant characteristics of the air conditioner, the second type of characteristic parameters are selected from the hardware parameters, including: Obtain the contribution of various parameters to the refrigerant volume; Multiple parameters corresponding to contribution levels are selected according to preset rules and used as the second type of feature parameters.

6. The method according to claim 5, wherein, Obtain the contribution of various parameters to the refrigerant quantity, including: Multiple parameters are used to train the DT model and parameter optimization is performed to obtain the optimal DT model; Use TreeExplainer from the SHAP library, which is specifically designed for tree models, to interpret the DT model; Input the dataset containing multiple parameters into the TreeExplainer function in the SHAP library to calculate the SHAP value and obtain the contribution of multiple parameters to the refrigerant quantity.

7. The method according to any one of claims 3 to 6, wherein, Preprocessing of the parameter data corresponding to the feature parameters includes: Using a preset length as a window, calculate the absolute deviation of the median of multiple parameter data; If the parameter data does not meet the preset conditions for the absolute deviation of the median, the parameter data will be removed. Replace the removed data with the median value within the window.

8. An apparatus for controlling an air conditioner, comprising a processor and a memory, the processor executing a method for energy saving of an air conditioner as described in any one of claims 1 to 7, stored in the memory.

9. An air conditioner, comprising an air conditioner body and an air conditioner energy-saving device as described in claim 8, which is installed on the air conditioner body.

10. A computer-readable non-transitory storage medium storing program instructions that, when executed, perform the following steps: Obtain the hardware parameters and status prediction model of the air conditioner; Predict the air conditioner status based on hardware parameters and a status prediction model; If the air conditioner meets the preset repair conditions, control the air conditioner to execute the corresponding repair strategy; If the air conditioner's condition cannot be repaired, the predicted air conditioner condition is input into the parameter prediction model to predict the optimal operating parameters of the air conditioner.

11. A computer program, when executed by a computer, causes the computer to implement the method for energy saving in air conditioning as described in any one of claims 1 to 7.

12. A computer program product comprising computer instructions stored on a computer-readable storage medium, which, when executed by a computer, cause the computer to implement the method for energy saving in air conditioning as described in any one of claims 1 to 7.

Images