Methods and devices for optimizing the start-up time of air conditioning systems

Abstract

The application discloses an air conditioning system starting time optimization method and device, the method comprises the following steps: obtaining original data, wherein the original data is composed of influence factors in the running of the air conditioning system; determining a target model based on the original data and a preset model; evaluating the target feature data when the target model is used for reasoning to obtain an evaluation result; and determining the starting time based on the evaluation result and a preset condition. The application not only considers the static and dynamic factors of the air conditioning system, but also performs evaluation and expansion in the model reasoning process, so that the optimized starting time is more accurate, and the energy-saving effect of the air conditioning system is better.

Description

Technical Field

[0001] This application relates to the field of air conditioning technology, and more specifically, to a method and apparatus for optimizing the start-up time of an air conditioning system. Background Technology

[0002] Besides operational optimization, energy-saving optimization of air conditioning systems also hinges on managing the system's start-up and shutdown times. Shopping malls typically have clearly defined start times and temperature requirements for air conditioning cooling. Often, air conditioning maintenance personnel turn on the system too early to meet these requirements, leading to premature start-up and excessively low indoor temperatures. Therefore, optimizing the start-up time of air conditioning systems is a pressing issue that needs to be addressed.

[0003] Currently, there are two main approaches to optimizing the start-up time of air conditioning systems: one is the mechanistic model, which involves analyzing the influencing factors related to the target time, such as water supply temperature, room temperature difference, indoor temperature, and outdoor temperature difference, and then performing linear regression fitting on the target time. The other is the black-box model, which considers the static factors affecting the target time and models the target time accordingly.

[0004] However, when the above method is used to optimize the start-up time of the air conditioning system, the accuracy of the optimized start-up time is low, resulting in poor energy-saving effect of the air conditioning system. Summary of the Invention

[0005] The main objective of this application is to provide a method and apparatus for optimizing the start-up time of an air conditioning system, which can improve the accuracy of the optimized start-up time and thus enhance the energy-saving effect of the air conditioning system.

[0006] To achieve the above objectives, firstly, this application provides a method for optimizing the start-up time of an air conditioning system, comprising:

[0007] Obtain the raw data, which consists of data composed of influencing factors in the operation of the air conditioning system;

[0008] Based on the original data and the pre-set model, determine the target model;

[0009] When using the target model for reasoning, the target feature data is evaluated to obtain the evaluation results;

[0010] Based on the evaluation results and preset conditions, the power-on time is determined.

[0011] In one implementation, determining the target model based on the original data and a preset model includes:

[0012] Based on the raw data, determine the target feature data;

[0013] The target model is obtained by training the preset model using the target feature data.

[0014] In one embodiment, determining target feature data based on raw data includes:

[0015] The raw data is cleaned to obtain a list of boot time indexes;

[0016] Filter the boot time index list to obtain a valid boot time index list, a qualified boot time index list, and a midnight time index list;

[0017] Based on the list of valid power-on indexes, the list of indexes of time of compliance, and the list of indexes of time of early morning, the influencing factors of time of compliance are determined, and the influencing factors of time of compliance are used as the initial feature data.

[0018] The initial feature data is subjected to feature ablation to obtain the target feature data.

[0019] In one embodiment, feature ablation is performed on the initial feature data to obtain target feature data, including:

[0020] The preset model is trained using initial feature data to obtain the output result;

[0021] Features exceeding a preset threshold in the output are removed to obtain the target feature data.

[0022] In one embodiment, when using the target model for inference, the target feature data is evaluated to obtain an evaluation result, including:

[0023] When using the target model for inference, a corresponding evaluation interval is configured for the target feature data, and the full feature space is generated based on the evaluation interval;

[0024] The feature data in the full feature space are evaluated to obtain the evaluation results.

[0025] In one implementation, the power-on time is determined based on the evaluation results and preset conditions, including:

[0026] If the evaluation results meet the preset conditions, obtain the current time, and determine the boot time based on the current time and the target model;

[0027] If the evaluation results do not meet the preset conditions, the power-on time will be determined based on the target feature data.

[0028] In one implementation, if the evaluation result meets preset conditions, the current time is obtained, and the power-on time is determined based on the current time and the target model, including:

[0029] When using the target model for reasoning, calculate the time to achieve the target;

[0030] Calculate the theoretical time to achieve the target based on the time to achieve the target and the current time;

[0031] If the theoretical time to reach the target is greater than the current time, output the boot time.

[0032] In one embodiment, the method further includes:

[0033] If the theoretical target time is less than or equal to the current time, return to the step of obtaining the current time.

[0034] In one implementation, if the evaluation result does not meet the preset conditions, the power-on time is determined based on the target feature data, including:

[0035] Based on target feature data, determine the positive and negative relationship between the time to achieve the target;

[0036] Based on the positive and negative relationship of the achievement time and the evaluation matrix, statistical analysis of positive sample data was conducted.

[0037] Calculate the minimum achievement time in the positive sample data, and statistically analyze the negative sample data based on the minimum achievement time and the evaluation matrix;

[0038] Calculate the minimum time to achieve the target in the negative sample data;

[0039] Calculate the minimum time to achieve the target in the positive sample data and the mean of the minimum time to achieve the target in the negative sample data, and use the mean as the startup time.

[0040] Secondly, embodiments of this application provide an air conditioning system start-up time optimization device, comprising:

[0041] The data acquisition module is used to acquire raw data, which consists of data composed of influencing factors in the operation of the air conditioning system.

[0042] The target model determination module is used to determine the target model based on the original data and the preset model.

[0043] The evaluation module is used to evaluate the target feature data when using the target model for inference, and obtain the evaluation results;

[0044] The power-on time determination module is used to determine the power-on time based on the evaluation results and preset conditions.

[0045] Thirdly, embodiments of this application provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any of the methods described above.

[0046] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of any of the methods described above.

[0047] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the steps of any of the methods described above.

[0048] This application provides a method and apparatus for optimizing the start-up time of an air conditioning system, comprising: acquiring raw data, wherein the raw data consists of data composed of influencing factors in the operation of the air conditioning system; then, determining a target model based on the raw data and a preset model; further, evaluating the target feature data during inference using the target model to obtain an evaluation result; and finally, determining the start-up time based on the evaluation result and preset conditions. This application not only considers the static and dynamic factors of the air conditioning system, but also performs evaluation and expansion during the model inference process, making the optimized start-up time more accurate and the energy-saving effect of the air conditioning system better. Attached Figure Description

[0049] The accompanying drawings, which form part of this application, are used to provide a further understanding of the application and to make other features, objects, and advantages of the application more apparent. The illustrative embodiments and descriptions of this application are used to explain the application and do not constitute an undue limitation of the application. In the drawings:

[0050] Figure 1 This is a flowchart illustrating a method for optimizing the start-up time of an air conditioning system according to an embodiment of this application;

[0051] Figure 2 This is a schematic diagram illustrating the factors influencing the compliance time provided in the embodiments of this application;

[0052] Figure 3 This is a flowchart illustrating the process of determining the power-on time provided in an embodiment of this application;

[0053] Figure 4 This is a flowchart illustrating the calculation and prediction results provided in an embodiment of this application;

[0054] Figure 5 This is a schematic diagram of the structure of an air conditioning system start-up time optimization device provided in an embodiment of this application;

[0055] Figure 6 This is a schematic diagram of the computer device provided in the embodiments of this application. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0057] The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein.

[0058] In this application embodiment, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0059] It should be understood that in the various embodiments of this application, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0060] It should be understood that in this application, "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such process, method, product or device.

[0061] It should be understood that in this application, "multiple" refers to two or more. "And / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, "and / or B" can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "Contains A, B, and C", "Contains A, B, and C" means that all three A, B, and C are contained; "Contains A, B, or C" means that one of A, B, and C is contained; "Contains A, B, and / or C" means that any one, two, or three of A, B, and C are contained.

[0062] It should be understood that in this application, "B corresponding to A", "B corresponding to A", "A corresponds to B", or "B corresponds to A" means that B is associated with A, and B can be determined based on A. Determining B based on A does not mean determining B solely based on A; B can also be determined based on A and / or other information. Matching A and B is defined as a similarity between A and B that is greater than or equal to a preset threshold.

[0063] Depending on the context, "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection."

[0064] The data involved in this application may be data authorized by the tester or fully authorized by all parties. The collection, dissemination, and use of the data shall comply with the relevant laws, regulations and standards of the relevant countries and regions. The implementation methods / executives of this application may be combined with each other.

[0065] The technical solutions of this application will be described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0066] The present application will now be described in conjunction with the accompanying drawings and specific embodiments.

[0067] Please see Figure 1 , Figure 1 This is a flowchart illustrating a method for optimizing the start-up time of an air conditioning system, as provided in an embodiment of this application. Figure 1 As shown, it includes the following steps:

[0068] Step S101: Obtain raw data.

[0069] The raw data consists of factors influencing the operation of the air conditioning system. Raw data includes, but is not limited to, indoor temperature, supply water temperature, return water temperature, start-up time, and time to reach target levels.

[0070] Step S102: Determine the target model based on the original data and the preset model.

[0071] The preset model is an AI model, including but not limited to neural network models and deep learning models.

[0072] To determine the target model based on the original data and the preset model, it is necessary to first determine the target feature data based on the original data, and then use the target feature data to train the preset model to obtain the target model.

[0073] The process of determining target feature data based on raw data includes: cleaning the raw data to obtain a power-on time index list; filtering the power-on time index list to obtain a valid power-on index list, a qualified time index list, and an early morning time index list; determining the influencing factors of qualified time based on the valid power-on index list, qualified time index list, and early morning time index list, and using the influencing factors of qualified time as initial feature data; and performing feature ablation on the initial feature data to obtain target feature data.

[0074] Each influencing factor in the original data has its corresponding boundary, such as the upper and lower limits of indoor temperature in Table 1.

[0075] Table 1 Boundaries of Each Influence Factor

[0076]

[0077]

[0078] Therefore, this application mainly uses the threshold method to remove abnormal data from the original data for cleaning. After removing abnormal data, the abnormal data is filled with NAN values.

[0079] Once the startup time index list (start_up_index_List) is obtained through the above cleaning process, it is then filtered according to the target temperature (target_t_indoor). Indexes that fail to reach the target temperature on the day of startup or whose room temperature has already reached the target temperature at startup are removed. Finally, the valid startup index list, the target-reaching time index list, and the early morning time index list are obtained.

[0080] After obtaining the list of valid power-on indexes, the list of indexes for achieving the target time, and the list of indexes for the early morning time, the influencing factors of the target time can be determined based on these lists, and the influencing factors of the target time can be used as the initial feature data.

[0081] The time to reach the target temperature refers to the time required for the machine to reach the target temperature after power-on.

[0082] like Figure 2 As shown, the factors influencing the time to achieve the standard include four aspects: circulating water factor, building energy storage factor, internal disturbance factor, and external disturbance factor. The circulating water factor includes the flow rate after startup, the water temperature at startup, the number of main units operating after startup, and the water temperature setpoint after startup. The building energy storage factor includes the indoor temperature before startup and the outdoor temperature before startup. The internal disturbance factor includes the indoor temperature at startup. The external disturbance factor includes the outdoor temperature after startup.

[0083] Specifically, as shown in Table 2 below, the average indoor temperature is calculated from the time of early morning to the time of power-on, and the average outdoor temperature is calculated from the time of early morning to the time of power-on.

[0084] Table 2. Calculation of Influence Factors on Completion Time

[0085]

[0086]

[0087] Next, feature ablation is performed on the initial feature data to obtain target feature data, including: training a preset model using the initial feature data to obtain output results; removing features in the output results that exceed a preset threshold to obtain target feature data.

[0088] Since redundant features not only affect modeling accuracy but also increase the difficulty of subsequent model applications, feature ablation is used to remove redundant features. Specifically, the preset model is trained based on the current initial feature data. Taking feature R2 in the initial feature data as an example, its corresponding model evaluation result S is calculated. Then, feature removal experiments with replacement are performed on the features in the initial feature data. The model is trained based on the remaining features. Taking feature R2 as an example, the model evaluation result Si (i = 1, 2, 3...n) of each removal experiment is calculated, and the maximum value Smax = max(Si) is calculated.

[0089] If Smax is greater than S, then remove the feature corresponding to Smax from the current feature set, assign a value to S: S = Smax, and return to execute the step of training the preset model based on the current initial feature data until all features have been traversed; if Smax is less than or equal to S, then end.

[0090] Step S103: When using the target model for reasoning, evaluate the target feature data and obtain the evaluation results.

[0091] The evaluation of target feature data during inference using the target model includes: configuring corresponding evaluation intervals for target feature data and generating a full feature space based on the evaluation intervals; and evaluating the feature data in the full feature space to obtain evaluation results.

[0092] In order to evaluate the degree of matching of a sample in the trained model during inference, the training samples (i.e. target feature data) need to be evaluated. First, the evaluation interval shown in Table 3 below needs to be set for each sample.

[0093] Table 3 Feature Evaluation Interval Table

[0094]

[0095] Then, a full feature space is generated based on the evaluation interval, and finally, the coverage of the samples is evaluated (i.e., the evaluation result) in the feature space.

[0096] Step S104: Determine the power-on time based on the evaluation results and preset conditions.

[0097] For determining the boot time based on the evaluation results and preset conditions, the following steps are taken: if the evaluation results meet the preset conditions, the current time is obtained, and the boot time is determined based on the current time and the target model; if the evaluation results do not meet the preset conditions, the boot time is determined based on the target feature data.

[0098] Among them, the preset conditions can be set according to specific circumstances, and the credibility of the optional model in this application.

[0099] like Figure 3 As shown, if the evaluation result meets the preset conditions, the current time is obtained, and the boot time is determined based on the current time and the target model, including: calculating the target time when using the target model for inference; calculating the theoretical target time based on the target time and the current time; if the theoretical target time is greater than the current time, the boot time is output; if the theoretical target time is less than or equal to the current time, the process returns to the step of obtaining the current time.

[0100] like Figure 4 As shown, if the evaluation results do not meet the preset conditions, the startup time is determined based on the target feature data, including: determining the positive and negative relationship of the achievement time based on the target feature data; statistically analyzing positive sample data based on the positive and negative relationship of the achievement time and the evaluation matrix; calculating the minimum achievement time in the positive sample data, and statistically analyzing negative sample data based on the minimum achievement time and the evaluation matrix; calculating the minimum achievement time in the negative sample data; calculating the mean of the minimum achievement time in the positive sample data and the minimum achievement time in the negative sample data, and using the mean as the startup time.

[0101] The positive / negative relationship of the time to meet the standard is shown in Table 4. For example, the positive relationship of the indoor temperature before the machine is turned on is 1.

[0102] Table 4: Positive / Negative Relationship between Completion Time and Standard

[0103]

[0104] This application provides a method for optimizing the start-up time of an air conditioning system, comprising: acquiring raw data, wherein the raw data consists of data composed of influencing factors in the operation of the air conditioning system; then, determining a target model based on the raw data and a preset model; further, evaluating the target feature data during inference using the target model to obtain an evaluation result; and finally, determining the start-up time based on the evaluation result and preset conditions. This application not only considers the static and dynamic factors of the air conditioning system, but also performs evaluation and expansion during the model inference process, making the optimized start-up time more accurate and the energy-saving effect of the air conditioning system better.

[0105] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0106] The following are device embodiments of this application. For details not described in detail, please refer to the corresponding method embodiments described above.

[0107] Figure 5 This illustration shows a schematic diagram of an air conditioning system start-up time optimization device according to an embodiment of this application. For ease of explanation, only the parts related to the embodiment of this application are shown. The air conditioning system start-up time optimization device includes a data acquisition module 501, a target model determination module 502, an evaluation module 503, and a start-up time determination module 504, as detailed below:

[0108] The data acquisition module 501 is used to acquire raw data, which consists of data composed of influencing factors in the operation of the air conditioning system.

[0109] The target model determination module 502 is used to determine the target model based on the original data and the preset model;

[0110] Evaluation module 503 is used to evaluate the target feature data when using the target model for inference, and obtain evaluation results;

[0111] The power-on time determination module 504 is used to determine the power-on time based on the evaluation results and preset conditions.

[0112] In one embodiment, the target model determination module 502 is further configured to determine target feature data based on the original data;

[0113] The target model is obtained by training the preset model using the target feature data.

[0114] In one embodiment, the target model determination module 502 is further used to clean the raw data to obtain a boot time index list;

[0115] Filter the boot time index list to obtain a valid boot time index list, a qualified boot time index list, and a midnight time index list;

[0116] Based on the list of valid power-on indexes, the list of indexes of time of compliance, and the list of indexes of time of early morning, the influencing factors of time of compliance are determined, and the influencing factors of time of compliance are used as the initial feature data.

[0117] The initial feature data is subjected to feature ablation to obtain the target feature data.

[0118] In one embodiment, the target model determination module 502 is further configured to train a preset model using initial feature data to obtain an output result;

[0119] Features exceeding a preset threshold in the output are removed to obtain the target feature data.

[0120] In one embodiment, the evaluation module 503 is further configured to configure a corresponding evaluation interval for the target feature data when reasoning using the target model, and generate a full feature space based on the evaluation interval;

[0121] The feature data in the full feature space are evaluated to obtain the evaluation results.

[0122] In one embodiment, the power-on time determination module 504 is further configured to obtain the current time if the evaluation result meets the preset conditions, and determine the power-on time based on the current time and the target model;

[0123] If the evaluation results do not meet the preset conditions, the power-on time will be determined based on the target feature data.

[0124] In one embodiment, the power-on time determination module 504 is also used to calculate the target time when using the target model for inference;

[0125] Calculate the theoretical time to achieve the target based on the time to achieve the target and the current time;

[0126] If the theoretical time to reach the target is greater than the current time, output the boot time.

[0127] In one embodiment, the device further includes a loop module, which is used to return to the step of obtaining the current time if the theoretical target time is less than or equal to the current time.

[0128] In one embodiment, the power-on time determination module 504 is further configured to determine the positive and negative relationship of the target time based on the target feature data;

[0129] Based on the positive and negative relationship of the achievement time and the evaluation matrix, statistical analysis of positive sample data was conducted.

[0130] Calculate the minimum achievement time in the positive sample data, and statistically analyze the negative sample data based on the minimum achievement time and the evaluation matrix;

[0131] Calculate the minimum time to achieve the target in the negative sample data;

[0132] Calculate the minimum time to achieve the target in the positive sample data and the mean of the minimum time to achieve the target in the negative sample data, and use the mean as the startup time.

[0133] This application provides an air conditioning system start-up time optimization device, specifically used for: acquiring raw data, wherein the raw data consists of data composed of influencing factors in the operation of the air conditioning system; then, based on the raw data and a preset model, determining a target model; then, during inference using the target model, evaluating the target feature data to obtain an evaluation result; and finally, based on the evaluation result and preset conditions, determining the start-up time. This application not only considers the static and dynamic factors of the air conditioning system, but also performs evaluation and expansion during the model inference process, making the optimized start-up time more accurate and the energy-saving effect of the air conditioning system better.

[0134] This application Figure 6 A schematic diagram of a computer device is provided. (Example) Figure 6 As shown, the computer device 6 in this embodiment includes a processor 601, a memory 602, and a computer program 603 stored in the memory 602 and executable on the processor 601. When the processor 601 executes the computer program 603, it implements the steps in the various air conditioning system start-up time optimization method embodiments described above, for example... Figure 1 Steps 101 to 104 are shown. Alternatively, when processor 601 executes computer program 603, it implements the functions of each module / unit in the above-described embodiments of the air conditioning system start-up time optimization device, for example... Figure 5 The functions of modules / units 501 to 504 are shown.

[0135] This application also provides a readable storage medium storing a computer program, which, when executed by a processor, is used to implement the air conditioning system start-up time optimization method provided in the various embodiments described above.

[0136] The readable storage medium can be a computer storage medium or a communication medium. A communication medium includes any medium that facilitates the transfer of computer programs from one location to another. A computer storage medium can be any available medium accessible to a general-purpose or special-purpose computer. For example, a readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application-Specific Integrated Circuit (ASIC). Alternatively, the ASIC can be located in a user device. Of course, the processor and the readable storage medium can also exist as discrete components in a communication device. The readable storage medium can be a read-only memory (ROM), random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0137] This application also provides a program product including executable instructions stored in a readable storage medium. At least one processor of the device can read the executable instructions from the readable storage medium, and the at least one processor executes the executable instructions to cause the device to implement the air conditioning system start-up time optimization method provided in the various embodiments described above.

[0138] In the embodiments of the above-described device, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this application can be directly manifested as being executed by a hardware processor, or executed by a combination of hardware and software modules within the processor.

[0139] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. An air conditioning system start-up time optimization method, characterized by, The method comprises the following steps: acquiring original data, wherein the original data is composed of influencing factors in the operation of an air conditioning system; determining a target model based on the original data and a preset model; evaluating target feature data when the target model is used for reasoning to obtain an evaluation result; determining a start-up time based on the evaluation result and a preset condition; the step of determining the target model based on the original data and the preset model comprises the following steps: determining target feature data based on the original data; training the preset model using the target feature data to obtain the target model; the step of determining the target feature data based on the original data comprises the following steps: cleaning the original data to obtain a start-up time index list; screening the start-up time index list to obtain an effective start-up index list, a standard time index list and a pre-dawn time index list; determining influencing factors of the standard time based on the effective start-up index list, the standard time index list and the pre-dawn time index list, and taking the influencing factors of the standard time as initial feature data; performing feature ablation on the initial feature data to obtain the target feature data.

2. The method for optimizing the start-up time of an air conditioning system as described in claim 1, characterized in that, the step of performing feature ablation on the initial feature data to obtain the target feature data comprises the following steps: training a preset model using the initial feature data to obtain an output result; removing features in the output result that exceed a preset threshold to obtain the target feature data.

3. The method for optimizing the start-up time of an air conditioning system as described in claim 1, characterized in that, the step of evaluating the target feature data when the target model is used for reasoning to obtain an evaluation result comprises the following steps: when the target model is used for reasoning, configuring a corresponding evaluation interval for the target feature data, and generating a full-quantity feature space according to the evaluation interval; evaluating feature data in the full-quantity feature space to obtain the evaluation result.

4. The method for optimizing the start-up time of an air conditioning system as described in claim 1, characterized in that, the step of determining the start-up time based on the evaluation result and the preset condition comprises the following steps: if the evaluation result meets the preset condition, acquiring a current time, and determining the start-up time based on the current time and the target model; if the evaluation result does not meet the preset condition, determining the start-up time based on the target feature data.

5. The method for optimizing the start-up time of an air conditioning system as described in claim 4, characterized in that, the step of determining the start-up time based on the evaluation result and the preset condition comprises the following steps: when the target model is used for reasoning, calculating a standard time; based on the standard time and the current time, calculating a theoretical standard time; if the theoretical standard time is greater than the current time, outputting the start-up time.

6. The method for optimizing the start-up time of an air conditioning system as described in claim 5, characterized in that, The method further comprises the following steps: if the theoretical standard time is less than or equal to the current time, returning to perform the step of acquiring the current time.

7. The method for optimizing the start-up time of an air conditioning system as described in claim 4, characterized in that, the step of determining the start-up time based on the evaluation result and the preset condition comprises the following steps: determining a positive and negative relationship of the standard time based on the target feature data; based on the positive and negative relationship of the standard time and an evaluation matrix, counting positive sample data; calculating a minimum standard time in the positive sample data, and based on the minimum standard time and the evaluation matrix, counting negative sample data; Calculate the minimum compliance time in the negative sample data; Calculate the mean of the minimum compliance time in the positive sample data and the minimum compliance time in the negative sample data, and take the mean as the start-up time.

8. An apparatus for optimizing the start-up time of an air conditioning system, characterized by: Comprise: Data acquisition module, for acquiring original data, wherein the original data is composed of data of influencing factors in the operation of the air conditioning system; Target model determination module, for determining a target model based on the original data and a preset model; Evaluation module, for evaluating target feature data when reasoning with the target model to obtain an evaluation result; Start-up time determination module, for determining a start-up time based on the evaluation result and a preset condition; The target model is determined based on the original data and the preset model, comprising: Determine the target feature data based on the original data; Train the preset model using the target feature data to obtain the target model; The target feature data is determined based on the original data, comprising: Cleaning the original data to obtain a start-up time index list; Filtering the start-up time index list to obtain an effective start-up index list, a compliance time index list and a pre-dawn time index list; Determine the influencing factors of the compliance time based on the effective start-up index list, the compliance time index list and the pre-dawn time index list, and take the influencing factors of the compliance time as the initial feature data; Feature ablation is performed on the initial feature data to obtain the target feature data.

Images