Water machine load control method and device of air conditioner, air conditioner and medium

Abstract

The embodiment of the invention provides a water machine load control method and device of an air conditioner, the air conditioner and a medium, and the method comprises the steps that after the load of a water machine is adjusted, current adjustment data and multiple pieces of historical adjustment data are obtained; the multiple pieces of historical adjustment data comprise historical adjustment data of multiple adjustment categories; in the historical adjustment data, determining a target adjustment category matched with the adjustment data; according to the historical adjustment data of the target adjustment category, determining a target load and target pre-adjustment time; and when the target pre-adjustment time is reached, adjusting the load of the water machine according to the target load, and upgrading the control of the water machine from passive response to active prediction by mining an operation rule in historical data, so that the collaborative optimization problem of energy consumption, comfort and equipment life is systematically solved.

Description

Technical Field

[0001] The present invention relates to the technical field of water machine control for air conditioners, and in particular to a method and device for controlling the load of a water machine for an air conditioner, an air conditioner, and a medium. Background Art

[0002] A water-cooled air conditioning system consists of a water cooler and a fan unit. Generally, the water cooler adjusts its load only after detecting a change in water temperature, which itself occurs some time after the fan unit is turned on or off. For example, when the room temperature rises, the fan unit turns on, and the chilled water in the water cooler begins to circulate, absorbing heat, causing the water temperature to rise. The water cooler, however, only begins to add load to lower the water temperature after detecting that the water temperature has risen to a certain level. During this process, since the water cooler can't add load until the water temperature reaches a certain level, there's a time lag between the water cooler's load change and the room's desired temperature. This causes the water cooler to adjust its load more slowly than the desired temperature, resulting in an excessively slow temperature change rate.

[0003] In existing technologies, room temperature regulation relies on the on / off cycles of the fan coils and the response of the water cooler to these cycles. However, the water cooler's load regulation always lags behind changes in room temperature demand. This can cause users to experience delays such as excessive temperatures, waiting for cooling, and then temperature recovery. This can be particularly detrimental in crowded environments or when the environment changes suddenly, leading to significant room temperature fluctuations and a significant impact on the user experience. Summary of the Invention

[0004] In view of the above problems, the embodiments of the present invention are proposed to provide a method, device, air conditioner and medium for controlling water load of an air conditioner that overcomes the above problems or at least partially solves the above problems.

[0005] In order to solve the above problems, an embodiment of the present invention discloses a method for controlling the water load of an air conditioner, the method comprising:

[0006] After adjusting the load of the water machine, obtaining current adjustment data and multiple historical adjustment data; the multiple historical adjustment data include historical adjustment data of multiple adjustment categories; multiple historical adjustment data of the same adjustment category have similar data change patterns;

[0007] Determining a target adjustment category matching the current adjustment data among the multiple adjustment categories;

[0008] determining a target load and a target pre-regulation time based on historical regulation data of the target regulation category;

[0009] When the target pre-adjustment time is reached, the load of the water machine is adjusted according to the target load.

[0010] Optionally, the historical adjustment data includes: the water temperature of the water machine when the load adjustment of the water machine is completed, the water temperature change rate during the adjustment process, the load of the water machine when the load adjustment of the water machine is completed, the load adjustment time, and at least one of the time when the load adjustment of the water machine is completed.

[0011] Optionally, determining a target adjustment category matching the current adjustment data from among the multiple adjustment categories includes:

[0012] Determine the mean of historical reconciliation data for various reconciliation categories;

[0013] respectively determining similarities between the current adjustment data and averages of historical adjustment data of the multiple adjustment categories;

[0014] The adjustment category corresponding to the mean of the historical adjustment data whose similarity is greater than a preset threshold is used as the target adjustment category.

[0015] Optionally, determining the target load and the target pre-adjustment time according to the historical adjustment data of the target adjustment category includes:

[0016] Determining target historical adjustment data from a plurality of historical adjustment data of the target adjustment category; wherein the time when the load adjustment is completed in the target historical adjustment data is closest to the current time;

[0017] The load of the water machine when the load adjustment in the target historical adjustment data is completed is used as the target load;

[0018] The target pre-adjustment time is determined according to the time when the load adjustment is completed in the plurality of historical adjustment data of the target adjustment category.

[0019] Optionally, determining the target pre-adjustment time according to the load adjustment completion time in the plurality of historical adjustment data of the target adjustment category includes:

[0020] Determine the time interval between the load adjustment completion times of two adjacent historical adjustment data in the target adjustment category;

[0021] Determine an average time interval based on the time intervals of the pairwise adjacent historical adjustment data;

[0022] A target pre-adjustment time is determined according to the average time interval and the current time.

[0023] Optionally, determining the target pre-adjustment time according to the average time interval and the current time includes:

[0024] The difference between the average time interval and the load adjustment time of the target historical adjustment data is used as the target interval time;

[0025] The sum of the current time and the target interval time is used as the target pre-adjustment time.

[0026] Optionally, the method further includes:

[0027] In the case that there is no adjustment category corresponding to the mean value of the historical adjustment data whose similarity is greater than the preset threshold, the target load and the target pre-adjustment time are determined according to the current adjustment data.

[0028] Optionally, the method further includes:

[0029] For the plurality of historical adjustment data, determining the similarity between each pair of the historical adjustment data

[0030] The adjustment categories to which the plurality of historical adjustment data belong are determined according to the similarities between any two of the historical adjustment data.

[0031] On the other hand, an embodiment of the present invention discloses a water machine load control device for an air conditioner, the device comprising:

[0032] A data acquisition module is used to acquire current adjustment data and multiple historical adjustment data after adjusting the load of the water machine; the multiple historical adjustment data include historical adjustment data of multiple adjustment categories; multiple historical adjustment data of the same adjustment category have similar data change patterns;

[0033] a category determination module, configured to determine, from among the multiple adjustment categories, a target adjustment category that matches the current adjustment data;

[0034] a data determination module, configured to determine a target load and a target pre-adjustment time based on historical adjustment data of the target adjustment category;

[0035] The load adjustment module is used to adjust the load of the water machine according to the target load when the target pre-adjustment time is reached.

[0036] Optionally, the historical adjustment data includes: the water temperature of the water machine when the load adjustment of the water machine is completed, the water temperature change rate during the adjustment process, the load of the water machine when the load adjustment of the water machine is completed, the load adjustment time, and at least one of the time when the load adjustment of the water machine is completed.

[0037] Optionally, the category determination module includes:

[0038] A mean determination submodule, used to determine the mean of historical adjustment data of multiple adjustment categories;

[0039] a similarity determination submodule, configured to respectively determine similarities between the current adjustment data and the average values of the historical adjustment data of the multiple adjustment categories;

[0040] The target category determination submodule is configured to take the adjustment category corresponding to the mean of the historical adjustment data whose similarity is greater than a preset threshold as the target adjustment category.

[0041] Optionally, the data determination module includes:

[0042] an adjustment data determination submodule, configured to determine target historical adjustment data from a plurality of historical adjustment data of the target adjustment category; wherein the time when the load adjustment is completed in the target historical adjustment data is closest to the current time;

[0043] a load determination submodule, configured to use the load of the water machine when the load adjustment in the target historical adjustment data is completed as the target load;

[0044] The time determination submodule is configured to determine a target pre-adjustment time according to the load adjustment completion time in a plurality of historical adjustment data of the target adjustment category.

[0045] Optionally, the time determination submodule includes:

[0046] a time interval determining unit, configured to determine a time interval between load adjustment completion times of two adjacent historical adjustment data in the target adjustment category;

[0047] an average interval determining unit, configured to determine an average time interval according to the time intervals of the pairwise adjacent historical adjustment data;

[0048] The target time determination unit is configured to determine a target pre-adjustment time according to the average time interval and the current time.

[0049] Optionally, the target time determination unit includes:

[0050] a target interval determination unit, configured to use the difference between the average time interval and the load adjustment time of the target historical adjustment data as the target interval;

[0051] The pre-adjustment time determining unit is configured to take the sum of the current time and the target interval time as the target pre-adjustment time.

[0052] Optionally, the device further comprises:

[0053] The non-category data determination module is used to determine the target load and the target pre-adjustment time according to the current adjustment data when there is no adjustment category corresponding to the mean value of the historical adjustment data whose similarity is greater than the preset threshold.

[0054] Optionally, the device further comprises:

[0055] The adjustment data similarity determination module is used to determine the similarity between the historical adjustment data.

[0056] The adjustment data category determination module is configured to determine the adjustment categories to which the plurality of historical adjustment data belong based on similarities between any two of the historical adjustment data.

[0057] Accordingly, an embodiment of the present invention discloses an electronic device, comprising: a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, the various steps of the above-mentioned air conditioner water machine load control method embodiment are implemented.

[0058] Accordingly, an embodiment of the present invention discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, each step of the above-mentioned air conditioner water machine load control method embodiment is implemented.

[0059] The embodiments of the present invention include the following advantages: by matching the current adjustment data with the categories of multiple historical adjustment data, the adjustment category to which the current adjustment data belongs can be known. Multiple historical adjustment data in the same adjustment category have similar data change patterns. By matching with the adjustment category, the data change pattern of the current adjustment data can be identified; based on the historical adjustment data of the target adjustment category, the appropriate target load and target pre-adjustment time under the data change pattern of the current adjustment data can be determined, thereby pre-adjusting the water machine according to the target load and target pre-adjustment time. This pre-adjustment method enables the water machine to be adjusted to the optimal load state before the actual demand arrives, thereby avoiding the energy waste caused by frequent loading and unloading in traditional control. This advance pre-adjustment method greatly shortens the time difference of the water machine responding to terminal demand, enables the system to adapt to changes in room temperature more quickly, reduces the time users wait for cooling or heating, and improves the overall response speed and operating efficiency of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is a flow chart of water machine load control in the prior art;

[0061] Figure 2 This is a flow chart of steps of an embodiment of a method for controlling water machine load of an air conditioner according to the present invention;

[0062] Figure 3 This is a control flow chart of an embodiment of a water machine load control method for an air conditioner according to the present invention;

[0063] Figure 4 It is a structural block diagram of an embodiment of a method and device for controlling water machine load of an air conditioner according to the present invention. DETAILED DESCRIPTION

[0064] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0065] Reference Figure 1 , shows the water machine load control process of the prior art:

[0066] Traditional chiller load control is a passive response mechanism that relies entirely on real-time temperature detection. Adjustments are achieved through a chain reaction of water temperature fluctuations caused by the start and stop of the terminal fan, which in turn causes the chiller to be loaded and unloaded. The core process is as follows:

[0067] When the room temperature is maintained at the set value (such as 24℃±0.5℃), the terminal fan disc is in the closed state, the compressor runs at the basic load (such as 40%), and the water temperature is stable in the set range (such as 12℃±0.5℃). Since the fan disc is closed, the room temperature will slowly rise. When the room temperature sensor detects that the temperature exceeds the upper limit (such as 24.5℃), the terminal fan disc is triggered to open. After the terminal fan disc is turned on, the chilled water begins to circulate and absorb the heat from the room. In this process, the chilled water return temperature will gradually rise as the heat absorbed from the room increases (such as from 12℃ to 13℃). When the water temperature exceeds the limit, the water compressor is triggered to load (such as from 40% to 70%). As the compressor is loaded, the cooling capacity of the air conditioner increases, and the water temperature gradually drops to the set range. As the room temperature drops, when the room temperature is lower than the lower limit (such as 23.5°C), the terminal fan disc is triggered to close; as the terminal fan disc is closed, the chilled water circulation stops, and the chilled water return temperature also gradually drops (such as from 12°C to 11°C). When the chilled water temperature is lower than the lower limit (such as 11.5°C), the compressor is triggered to unload (such as from 70% to 30%). As the cooling capacity decreases, the water temperature gradually returns to the set range and then starts to circulate. It can be found that in the existing technology, the water machine system is always in a state of water machine catching up with the temperature, and it cannot be stabilized at the optimal energy efficiency point, which will cause a certain amount of energy waste.

[0068] One of the core concepts of the embodiment of the present invention is to match the current adjustment data with historical data to obtain data categories, and then identify the data change rules corresponding to the current adjustment data, so as to adjust the load of the water machine in advance and achieve the effect of early adjustment.

[0069] Reference Figure 2 , shows a flow chart of steps of an embodiment of a method for controlling water load of an air conditioner according to the present invention, which may specifically include the following steps:

[0070] Step 101: After adjusting the load of the water machine, obtain current adjustment data and multiple historical adjustment data; the multiple historical adjustment data include historical adjustment data of multiple adjustment categories; multiple historical adjustment data of the same adjustment category have similar data change patterns;

[0071] After the load adjustment operation of the water machine is completed, the system synchronously collects the real-time operating data generated by this adjustment and jointly analyzes it with the adjustment records in the historical database. This adjustment data refers to the set of characteristic parameters directly obtained in the current operation, which can characterize the dynamic characteristics of this adjustment. From the introduction of the above water machine control method, it can be seen that the load adjustment of the water machine is often periodic, and after analyzing the historical adjustment data, it can be found that different historical adjustment data often have similar data change patterns. If the historical adjustment data with similar data change patterns are classified into the same category, the data change pattern of this type of historical adjustment data can be clearly known; after matching the current adjustment data with different types of historical adjustment data, the type of historical adjustment data to which the current adjustment data belongs can be known. The future adjustment data can be predicted by the data change pattern represented by this category, thereby realizing the pre-adjustment of the water machine.

[0072] In one embodiment, the historical adjustment data includes: the water temperature of the water machine when the load adjustment of the water machine is completed, the water temperature change rate during the adjustment process, the load of the water machine when the load adjustment of the water machine is completed, the load adjustment time, and at least one of the time when the load adjustment of the water machine is completed.

[0073] After analysis, the current adjustment data will also become one of the historical adjustment data, so the data types of the current adjustment data and the historical adjustment data have certain common data types; for example, the historical adjustment data may include the water temperature of the water machine when the load adjustment of the water machine is completed, the water temperature change rate during the adjustment process, the load of the water machine when the load adjustment of the water machine is completed, the load adjustment time, and the time when the load adjustment of the water machine is completed. The specific parameter type can be set according to business needs.

[0074] Exemplarily, historical adjustment data may include the following types of data:

[0075] Water temperature (symbol T t ), that is, the instantaneous temperature of the chilled water system when the regulation is completed, which can reflect the thermal equilibrium state; the water temperature change rate (symbol ΔT t ), refers to the change in water temperature per minute during the regulation process, which can be used to characterize the system inertia. For example, ΔTt = 0.5 ° C / min means that the water temperature rises by 0.5 ° C per minute; load (symbol is L t) refers to the percentage of the compressor's operating power. For example, Lt = 70% means it is currently operating at 70% of the rated power. The adjustment time (symbol is H t ), refers to the duration from the start of adjustment to the target load, for example, the loading operation takes 3 minutes; the timestamp (symbol TM t ), which refers to the operation completion time accurate to the minute, and is used to analyze daily / weekly periodicity;

[0076] In one embodiment, the method further comprises the steps of:

[0077] For the plurality of historical adjustment data, determining the similarity between each pair of the historical adjustment data

[0078] Similarity is a numerical indicator that quantifies the degree of similarity between two adjustment operations (i.e., two historical adjustment data) in terms of characteristic parameters. Its essence is to use mathematical methods to determine whether two operations belong to the same operating mode.

[0079] In this application, each piece of historical adjustment data may contain multiple parameters (such as T t , ΔT t 、L t 、H t ,TM t ). Similarity calculation requires the integration of these parameters, and the purpose of calculating similarity is to determine whether the operation mode of the operation is similar to that of other operations in the database; because the operation rules of the chiller under different data change rules are significantly different. For example, in the midday high-load data change rule under a refrigeration environment, due to the large number of terminals opened, the water temperature will rise quickly, and the load adjustment will also be greater; and in the nighttime low-load data change rule under a refrigeration environment, due to the small number of terminals opened or the short opening time, the water temperature fluctuation is relatively gentle. If classification is not performed, the predicted data will be interfered with by data of different modes, and the accuracy will be reduced.

[0080] The adjustment categories to which the plurality of historical adjustment data belong are determined according to the similarities between any two of the historical adjustment data.

[0081] In the process of determining the adjustment category of the plurality of historical adjustment data by using similarity, the similarity may adopt a value of Euclidean distance or a value of Manhattan distance;

[0082] For example, after the first load adjustment, if there is no category data, the current adjustment data is used as the first category data. The specific form can be: let T1 = Tt, ΔT1 = ΔTt, H1 = Ht, L1 = Lt, and the corresponding category identifier is C1, then the category data is represented as: (T1, ΔT1, H1, L1, C1); then, after the second load adjustment, since there is category C1 data in the historical adjustment data, the similarity between the current adjustment data and C1 is directly calculated. If the similarity is greater than the set threshold, the current adjustment data is used as the category data. Correspondingly, the category data representation is changed to the average value of the category data. The category data is represented as: (T n , ΔT n , H n , L n , C1), where T n =avg_T t , ΔT n =avg_ΔT t 、H n =avg_H t , L n =avg_L t If the calculated similarity does not meet the threshold after the second load adjustment, the second adjustment data will be taken as a new category and added to the historical adjustment data. After three load adjustments, the above process is repeated. After multiple adjustments, multiple adjustment data categories C1, C2, ..., C n ;

[0083] For example, the similarity calculation method can be Euclidean distance, that is, assuming that there are two similarities

[0084] In another example, the similarity calculation method can also use Manhattan distance;

[0085] S n =ω T |T1-T n |+ω ΔT |ΔT1-ΔT n |+ω H |H1-H n |+ω L |L1-L n |, where ω T represents the water temperature weight, ω ΔT represents the water temperature change rate weight, ω H Represents the time weight used for adjustment, ω LRepresents load weights, which can be freely set based on business needs and industry experience. By adjusting the values of different weights, the classification basis can be flexibly modified to correspond to different data variation patterns. For example, when the water temperature weight increases, the water temperature has a greater impact on the distance calculation at this time, so it can reflect the data variation pattern under different water temperatures. Similarly, if the water temperature change rate weight increases, it means that the regulation category at this time will more likely reflect the data variation pattern dominated by the water temperature change rate. Adjustments to the time weight and load weight will also synchronously affect the data variation pattern reflected by the regulation category.

[0086] Step 102: Determine a target adjustment category matching the current adjustment data from among the multiple adjustment categories.

[0087] In one embodiment, step 102 includes the following sub-steps:

[0088] Sub-step S11, determining the mean of historical adjustment data of multiple adjustment categories;

[0089] As mentioned above, each adjustment category, such as C1 and C2, may contain multiple historical data with similar characteristics. Therefore, the feature center of each category can be obtained by calculating the arithmetic mean of all data parameters in each category. For example, the process of calculating the mean can be:

[0090] Assume that category C1 contains three historical data: [Tt = 12.1°C, ΔTt = 0.5°C / min, Lt = 68%, Ht = 3 min]; [Tt = 12.3°C, ΔTt = 0.6°C / min, Lt = 70%, Ht = 2 min]; [Tt = 11.9°C, ΔTt = 0.4°C / min, Lt = 65%, Ht = 4 min]. Then the average value of C1 is: avg_T t =12.1,avg_ΔT t =0.5,avg_L t =67.7%,avg_H t =3; using the mean to represent the overall characteristics of the category avoids the high computational overhead of comparing historical data one by one, and can also smooth out random fluctuations in individual data;

[0091] Sub-step S12, respectively determining similarities between the current adjustment data and the average values of historical adjustment data of the multiple adjustment categories;

[0092] On the basis of the two similarity calculations mentioned above, existing technologies can also be used to standardize the data, such as using the Z-score method to standardize the data and eliminate the impact of data dimension. Since existing technologies are used, this will not be described in detail.

[0093] Sub-step S13: taking the adjustment category corresponding to the mean of the historical adjustment data whose similarity is greater than a preset threshold as the target adjustment category.

[0094] The preset threshold can be set as a fixed value based on experience, or can be calculated based on the numerical distribution of historical similarities;

[0095] In one embodiment, the method may further include the following steps:

[0096] In the case that there is no adjustment category corresponding to the mean value of the historical adjustment data whose similarity is greater than the preset threshold, the target load and the target pre-adjustment time are determined according to the current adjustment data.

[0097] If there is no corresponding category, it means that this data belongs to a category by itself, so it can be pre-adjusted according to the data content;

[0098] Step 103: determining a target load and a target pre-regulation time according to the historical regulation data of the target regulation category;

[0099] By analyzing the historical data of the target adjustment category, the optimal load that the chiller should reach under the current data change law is predicted and the optimal load is used as the target load. The time point for starting the adjustment in advance is determined and the time point is used as the target pre-adjustment time. Therefore, the effect of completing the load adjustment before the terminal demand changes can be achieved based on these two parameters.

[0100] In one embodiment, step 103 includes the following sub-steps:

[0101] Sub-step S21, determining target historical adjustment data from a plurality of historical adjustment data of the target adjustment category; the time when the load adjustment is completed in the target historical adjustment data is closest to the current time;

[0102] From all historical data for the target regulation category, select the records whose load regulation completion time is closest to the current time. System states within similar time periods are similar. For example, if the current time is 2:20 PM, then the regulation record at 2:15 PM better reflects the current data variation pattern than the record at 10:00 AM, making it more reasonable to use the regulation record at that time as the adjustment benchmark.

[0103] For example, when selecting target historical adjustment data, all data within a certain time window may be selected, and the average value of these data may be used as the target adjustment data to avoid deviations caused by seasonality or day-night differences.

[0104] Sub-step S22, taking the load of the water generator when the load adjustment in the target historical adjustment data is completed as the target load;

[0105] Directly extract the compressor load value at the time load regulation was completed from the target historical regulation data as the current target load. This load value has been successfully used to maintain water temperature stability under similar data variation patterns, and reuse ensures reliability.

[0106] For example, if the average value of the data within a certain time window is adopted, if the data within the time window shows that the fluctuation of the target load exceeds a certain threshold after multiple adjustments, the average value of the load data in the time window is taken; if the load fluctuation is not large, the load of the most recent data in the window is taken.

[0107] Sub-step S23 : determining a target pre-adjustment time according to the load adjustment completion time in the plurality of historical adjustment data of the target adjustment category.

[0108] In one embodiment, sub-step S23 includes the following sub-steps:

[0109] Sub-step S231, determining the time interval between the load adjustment completion times of two adjacent historical adjustment data in the target adjustment category;

[0110] Calculate the time difference between the completion times of two consecutive adjustments in the target adjustment category and make the next calculation based on this time difference;

[0111] For example, if there are three data items in a certain adjustment category, and their corresponding historical adjustment times are 10:00, 10:35, and 11:10, then the corresponding time intervals are 35 minutes and 35 minutes respectively.

[0112] Sub-step S232, determining an average time interval based on the time intervals of the pairwise adjacent historical adjustment data;

[0113] Taking the arithmetic mean of the time interval can characterize the typical adjustment cycle under the change law of this type of data.

[0114] As shown in the above example, the average time interval is the mean time interval: (35+35) / 2=35 minutes;

[0115] Sub-step S233: determining a target pre-adjustment time according to the average time interval and the current time.

[0116] In one embodiment, sub-step S233 includes the following sub-steps:

[0117] Sub-step S2331, taking the difference between the average time interval and the load adjustment time of the target historical adjustment data as the target interval time;

[0118] Subtract the load adjustment time in the target historical adjustment data from the average time interval to get the target interval time. For example, if the data shows that the average interval is 35 minutes and the load adjustment time in the target historical data is 5 minutes, then the target interval time is 35 minutes - 5 minutes = 30 minutes.

[0119] Sub-step S2332: taking the sum of the current time and the target interval time as the target pre-adjustment time.

[0120] Load regulation takes time, so it's necessary to start ahead of the predicted regulation period to ensure that adjustments are completed when demand changes. For example, if the current time is 14:20 and the target interval is 30 minutes, then the target pre-regulation time = 14:20 + 30 minutes = 14:50. By capturing the periodic pattern through the time interval mean, regulation can be started ahead of time, eliminating the lag of traditional control.

[0121] Step 104: When the target pre-adjustment time is reached, adjust the load of the water machine according to the target load.

[0122] By matching the current adjustment data with the categories of multiple historical adjustment data, the adjustment category to which the current adjustment data belongs can be determined. Multiple historical adjustment data in the same adjustment category have similar data change patterns. By matching with the adjustment category, the data change pattern of the current adjustment data can be identified. Based on the historical adjustment data of the target adjustment category, the appropriate target load and target pre-adjustment time under the data change pattern of the current adjustment data can be determined, thereby pre-adjusting the water machine according to the target load and target pre-adjustment time. This pre-adjustment method enables the water machine to adjust to the optimal load state before actual demand arrives, thereby avoiding the energy waste caused by frequent loading and unloading in traditional control. This advance pre-adjustment method greatly shortens the time difference for the water machine to respond to terminal demand, enabling the system to adapt to changes in room temperature more quickly, reducing the time users wait for cooling or heating, and improving the overall response speed and operating efficiency of the system.

[0123] Reference Figure 3 , shows the control flow of an embodiment of a water machine load control method for an air conditioner of the present invention:

[0124] This solution uses predictive active control to learn terminal demand patterns through historical data and adjust the water machine load in advance before the room temperature actually changes, forming a closed loop of pre-adjustment, terminal response, and re-adjustment. The core process is as follows:

[0125] According to historical data, it is predicted that the terminal demand will increase, and the water machine is loaded to the target load in advance (such as from 40% to 65%), and the chilled water temperature is lowered in advance (such as from 12°C to 11°C). As time goes by, the room temperature naturally rises, and the terminal fan disk is turned on. Because the water temperature has been pre-cooled, the fan disk immediately outputs sufficient cold air after it is turned on, and there is no cooling delay; when it is detected that the terminal demand is met and the water temperature is stable, the water machine is unloaded in advance (such as from 65% to 50%), so that the chilled water temperature slowly recovers in advance (such as from 11°C to 11.5°C). Because the water temperature is pre-cooled in advance, the room temperature is quickly stabilized and the fan disk is closed as needed; then this process is repeated. It is not difficult to find that the present application achieves the effect of changing load regulation from post-remedy to pre-prevention. This preemptive control logic enables the system to change from catching up with demand to matching demand in advance, so as to achieve a comprehensive improvement in energy efficiency, comfort, and equipment life.

[0126] It should be noted that for the sake of simplicity, the method embodiments are described as a series of actions. However, those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0127] Reference Figure 4 , shows a structural block diagram of an embodiment of a method and device for controlling water machine load of an air conditioner according to the present invention, which may specifically include the following modules:

[0128] The data acquisition module 201 is used to acquire the current adjustment data and multiple historical adjustment data after adjusting the load of the water machine; the multiple historical adjustment data include historical adjustment data of multiple adjustment categories; multiple historical adjustment data of the same adjustment category have similar data change patterns;

[0129] From the introduction of the above water machine control method, it can be seen that the load regulation of the water machine is often periodic, and after analyzing the historical regulation data, it can be found that different historical regulation data often have similar data change patterns. If the historical regulation data with similar data change patterns are classified into the same category, the data change pattern of this type of historical regulation data can be clearly known; after matching the current regulation data with different types of historical regulation data, the type of historical regulation data to which the current regulation data belongs can be known, and the future regulation data can be predicted through the data change pattern represented by the category, thereby realizing pre-regulation of the water machine.

[0130] A category determination module 202 is configured to determine a target adjustment category matching the current adjustment data from among the multiple adjustment categories;

[0131] A data determination module 203 is configured to determine a target load and a target pre-adjustment time based on historical adjustment data of the target adjustment category;

[0132] By analyzing the historical data of the target adjustment category, the optimal load that the chiller should reach under the current data change law is predicted and the optimal load is used as the target load. The time point for starting the adjustment in advance is determined and the time point is used as the target pre-adjustment time. Therefore, the effect of completing the load adjustment before the terminal demand changes can be achieved based on these two parameters.

[0133] The load adjustment module 204 is configured to adjust the load of the water generator according to the target load when the target pre-adjustment time is reached.

[0134] In one embodiment, the historical adjustment data includes: the water temperature of the water machine when the load adjustment of the water machine is completed, the water temperature change rate during the adjustment process, the load of the water machine when the load adjustment of the water machine is completed, the load adjustment time, and at least one of the time when the load adjustment of the water machine is completed.

[0135] After analysis, the current adjustment data will also become one of the historical adjustment data, so the data types of the current adjustment data and the historical adjustment data have certain common data types; for example, the historical adjustment data may include the water temperature of the water machine when the load adjustment of the water machine is completed, the water temperature change rate during the adjustment process, the load of the water machine when the load adjustment of the water machine is completed, the load adjustment time, and the time when the load adjustment of the water machine is completed. The specific parameter type can be set according to business needs.

[0136] Exemplarily, historical adjustment data may include the following types of data:

[0137] Water temperature (symbol T t ), that is, the instantaneous temperature of the chilled water system when the regulation is completed, which can reflect the thermal equilibrium state; the water temperature change rate (symbol ΔT t ), refers to the change in water temperature per minute during the regulation process, which can be used to characterize the system inertia. For example, ΔTt = 0.5 ° C / min means that the water temperature rises by 0.5 ° C per minute; load (symbol is L t ) refers to the percentage of the compressor's operating power. For example, Lt = 70% means it is currently operating at 70% of the rated power. The adjustment time (symbol is H t ), refers to the duration from the start of adjustment to the target load, for example, the loading operation takes 3 minutes; the timestamp (symbol TM t), which refers to the operation completion time accurate to the minute, and is used to analyze daily / weekly periodicity;

[0138] In one embodiment, the category determination module includes:

[0139] A mean determination submodule, used to determine the mean of historical adjustment data of multiple adjustment categories;

[0140] Each adjustment category, such as C1 and C2, may contain multiple historical data with similar characteristics. Therefore, the characteristic center of each category can be obtained by calculating the arithmetic mean of all data parameters in each category. For example, the process of calculating the mean can be:

[0141] Assume that category C1 contains three historical data: [Tt = 12.1°C, ΔTt = 0.5°C / min, Lt = 68%, Ht = 3 min]; [Tt = 12.3°C, ΔTt = 0.6°C / min, Lt = 70%, Ht = 2 min]; [Tt = 11.9°C, ΔTt = 0.4°C / min, Lt = 65%, Ht = 4 min]. Then the average value of C1 is: avg_T t =12.1,avg_ΔT t =0.5,avg_L t =67.7%,avg_H t =3; using the mean to represent the overall characteristics of the category avoids the high computational overhead of comparing historical data one by one, and can also smooth out random fluctuations in individual data;

[0142] a similarity determination submodule, configured to respectively determine similarities between the current adjustment data and the average values of the historical adjustment data of the multiple adjustment categories;

[0143] On the basis of the two similarity calculations mentioned above, existing technologies can also be used to standardize the data, such as using the Z-score method to standardize the data and eliminate the impact of data dimension. Since existing technologies are used, this will not be described in detail.

[0144] The target category determination submodule is configured to take the adjustment category corresponding to the mean of the historical adjustment data whose similarity is greater than a preset threshold as the target adjustment category.

[0145] The preset threshold can be set as a fixed value based on experience, or can be calculated based on the numerical distribution of historical similarities;

[0146] In one embodiment, the data determination module includes:

[0147] an adjustment data determination submodule, configured to determine target historical adjustment data from a plurality of historical adjustment data of the target adjustment category; wherein the time when the load adjustment is completed in the target historical adjustment data is closest to the current time;

[0148] From all historical data for the target regulation category, select the records whose load regulation completion time is closest to the current time. System states within similar time periods are similar. For example, if the current time is 2:20 PM, then the regulation record at 2:15 PM better reflects the current data variation pattern than the record at 10:00 AM, making it more reasonable to use the regulation record at that time as the adjustment benchmark.

[0149] For example, when selecting target historical adjustment data, all data within a certain time window may be selected, and the average value of these data may be used as the target adjustment data to avoid deviations caused by seasonality or day-night differences.

[0150] a load determination submodule, configured to use the load of the water machine when the load adjustment in the target historical adjustment data is completed as the target load;

[0151] Directly extract the compressor load value at the time load regulation was completed from the target historical regulation data as the current target load. This load value has been successfully used to maintain water temperature stability under similar data variation patterns, and reuse ensures reliability.

[0152] For example, if the average value of the data within a time window is adopted, if the data within the time window shows that the fluctuation of the target load exceeds a certain threshold after multiple adjustments, the average value of the load data in the time window is taken; if the load fluctuation is not large, the load of the most recent data in the window is taken.

[0153] The time determination submodule is configured to determine a target pre-adjustment time according to the load adjustment completion time in a plurality of historical adjustment data of the target adjustment category.

[0154] In one embodiment, the time determination submodule includes:

[0155] a time interval determining unit, configured to determine a time interval between load adjustment completion times of two adjacent historical adjustment data in the target adjustment category;

[0156] Calculate the time difference between the completion times of two consecutive adjustments in the target adjustment category and make the next calculation based on this time difference;

[0157] For example, if there are three data items in a certain adjustment category, and their corresponding historical adjustment times are 10:00, 10:35, and 11:10, then the corresponding time intervals are 35 minutes and 35 minutes respectively.

[0158] an average interval determining unit, configured to determine an average time interval according to the time intervals of the pairwise adjacent historical adjustment data;

[0159] Taking the arithmetic mean of the time interval can characterize the typical adjustment cycle under the change law of this type of data.

[0160] As shown in the above example, the average time interval is the mean time interval: (35+35) / 2=35 minutes;

[0161] The target time determination unit is configured to determine a target pre-adjustment time according to the average time interval and the current time.

[0162] In one embodiment, the target time determination unit includes:

[0163] a target interval determination unit, configured to use the difference between the average time interval and the load adjustment time of the target historical adjustment data as the target interval;

[0164] Subtract the load adjustment time in the target historical adjustment data from the average time interval to get the target interval time. For example, if the data shows that the average interval is 35 minutes and the load adjustment time in the target historical data is 5 minutes, then the target interval time is 35 minutes - 5 minutes = 30 minutes.

[0165] The pre-adjustment time determining unit is configured to take the sum of the current time and the target interval time as the target pre-adjustment time.

[0166] Load regulation takes time, so it's necessary to start ahead of the predicted regulation period to ensure that adjustments are completed when demand changes. For example, if the current time is 14:20 and the target interval is 30 minutes, then the target pre-regulation time = 14:20 + 30 minutes = 14:50. By capturing the periodic pattern through the time interval mean, regulation can be started ahead of time, eliminating the lag of traditional control.

[0167] In one embodiment, the apparatus further comprises:

[0168] The non-category data determination module is used to determine the target load and the target pre-adjustment time according to the current adjustment data when there is no adjustment category corresponding to the mean value of the historical adjustment data whose similarity is greater than the preset threshold.

[0169] If there is no corresponding category, it means that this data belongs to a category by itself, so it can be pre-adjusted according to the data content;

[0170] In one embodiment, the apparatus further comprises:

[0171] an adjustment data similarity determination module, configured to determine, for the plurality of historical adjustment data, similarities between any two of the historical adjustment data;

[0172] Similarity is a numerical indicator that quantifies the degree of similarity between two adjustment operations (i.e., two historical adjustment data) in terms of characteristic parameters. Its essence is to use mathematical methods to determine whether two operations belong to the same operating mode.

[0173] In this application, each piece of historical adjustment data may contain multiple parameters (such as T t , ΔT t 、L t 、H t ,TM t ). Similarity calculation requires the integration of these parameters, and the purpose of calculating similarity is to determine whether the operation mode of the operation is similar to that of other operations in the database; because the operating rules of the chiller under different data change rules are significantly different. For example, in the midday high-load data change rule under a refrigeration environment, due to the large number of terminals being opened, the water temperature will rise quickly, and the load adjustment will also be greater; and in the nighttime low-load data change rule under a refrigeration environment, due to the small number of terminals being opened or the short opening time, the water temperature fluctuation is relatively gentle. If classification is not performed, the predicted data will be interfered with by data of different modes, and the accuracy will be reduced.

[0174] The adjustment data category determination module is configured to determine the adjustment categories to which the plurality of historical adjustment data belong based on similarities between any two of the historical adjustment data.

[0175] In the process of determining the adjustment category of the plurality of historical adjustment data by using similarity, the similarity may adopt a value of Euclidean distance or a value of Manhattan distance;

[0176] For example, after the first load adjustment, if there is no category data, the current adjustment data is used as the first category data. The specific form can be: let T1 = Tt, ΔT1 = ΔTt, H1 = Ht, L1 = Lt, and the corresponding category identifier is C1, then the category data is represented as: (T1, ΔT1, H1, L1, C1); then, after the second load adjustment, since the category C1 data already exists in the historical adjustment data, the similarity between the current adjustment data and C1 is directly calculated. If the similarity is greater than the set threshold, the current adjustment data is used as the category data. Correspondingly, the category data representation is changed to the average value of the category data. The category data is represented as: (T n , ΔT n , H n , L n , C1), where T n =avg_Tt , ΔT n =avg_ΔT t 、H n =avg_H t , L n =avg_L t If the calculated similarity does not meet the threshold after the second load adjustment, the second adjustment data will be taken as a new category and added to the historical adjustment data. After three load adjustments, the above process is repeated. After multiple adjustments, multiple adjustment data categories C1, C2, ..., C n ;

[0177] For example, the similarity calculation method can be Euclidean distance, that is, assuming that there are two similarities Because the parameters involved in the calculation of this method are more comprehensive and have no weight influence, classification according to the similarity calculated by this method can reflect the data change rules under different data change rules.

[0178] In another example, the similarity calculation method can also use Manhattan distance;

[0179] S n =ω T |T1-T n |+ω ΔT |ΔT1-ΔT n |+ω H |H1-H n |+ω L |L1-L n |, where ω T represents the water temperature weight, ω ΔT represents the water temperature change rate weight, ω H Represents the time weight used for adjustment, ω L Represents load weights, which can be freely set based on business needs and industry experience. By adjusting the values of different weights, the classification basis can be flexibly modified to correspond to different data variation patterns. For example, when the water temperature weight increases, the water temperature has a greater impact on the distance calculation at this time, so it can reflect the data variation pattern under different water temperatures. Similarly, if the water temperature change rate weight increases, it means that the regulation category at this time will more likely reflect the data variation pattern dominated by the water temperature change rate. Adjustments to the time weight and load weight will also synchronously affect the data variation pattern category reflected by the regulation category.

[0180] By matching the current adjustment data with the categories of multiple historical adjustment data, the adjustment category to which the current adjustment data belongs can be determined. Multiple historical adjustment data in the same adjustment category have similar data change patterns. By matching with the adjustment category, the data change pattern of the current adjustment data can be identified. Based on the historical adjustment data of the target adjustment category, the appropriate target load and target pre-adjustment time under the data change pattern of the current adjustment data can be determined, thereby pre-adjusting the water machine according to the target load and target pre-adjustment time. This pre-adjustment method enables the water machine to adjust to the optimal load state before actual demand arrives, thereby avoiding the energy waste caused by frequent loading and unloading in traditional control. This advance pre-adjustment method greatly shortens the time difference for the water machine to respond to terminal demand, enabling the system to adapt to changes in room temperature more quickly, reducing the time users wait for cooling or heating, and improving the overall response speed and operating efficiency of the system.

[0181] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0182] An embodiment of the present invention also provides an air conditioner, comprising: a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, the various processes of the above-mentioned air conditioner water machine load control method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0183] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the above-mentioned air conditioner water machine load control method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0184] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0185] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, apparatus, or computer program products. Thus, embodiments of the present invention may take the form of a fully hardware embodiment, a fully software embodiment, or an embodiment combining software and hardware. Furthermore, embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0186] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the process in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0187] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0188] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0189] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they become aware of the basic creative concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0190] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or terminal device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or terminal device that includes the element.

[0191] The above is a detailed introduction to the water machine load control method, device, air conditioner and medium of an air conditioner provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for controlling water load of an air conditioner, characterized in that: The method comprises: After adjusting the load of the water machine, obtaining current adjustment data and multiple historical adjustment data; the multiple historical adjustment data include historical adjustment data of multiple adjustment categories; multiple historical adjustment data of the same adjustment category have similar data change patterns; Determining a target adjustment category matching the current adjustment data among the multiple adjustment categories; determining a target load and a target pre-regulation time based on historical regulation data of the target regulation category; When the target pre-adjustment time is reached, the load of the water machine is adjusted according to the target load.

2. The water machine load control method for an air conditioner according to claim 1, characterized in that: The historical adjustment data includes: the water temperature of the water machine when the load adjustment of the water machine is completed, the water temperature change rate during the adjustment process, the load of the water machine when the load adjustment of the water machine is completed, the load adjustment time, and at least one of the time when the load adjustment of the water machine is completed.

3. The water machine load control method for an air conditioner according to claim 2, characterized in that: Determining a target adjustment category matching the current adjustment data from among the multiple adjustment categories includes: Determine the mean of historical reconciliation data for various reconciliation categories; respectively determining similarities between the current adjustment data and averages of historical adjustment data of the multiple adjustment categories; The adjustment category corresponding to the mean of the historical adjustment data whose similarity is greater than a preset threshold is used as the target adjustment category.

4. The water machine load control method for an air conditioner according to claim 2, characterized in that: The determining of the target load and the target pre-adjustment time according to the historical adjustment data of the target adjustment category includes: Determining target historical adjustment data from a plurality of historical adjustment data of the target adjustment category; wherein the time when the load adjustment is completed in the target historical adjustment data is closest to the current time; The load of the water machine when the load adjustment in the target historical adjustment data is completed is used as the target load; The target pre-adjustment time is determined according to the time when the load adjustment is completed in the plurality of historical adjustment data of the target adjustment category.

5. The water machine load control method for an air conditioner according to claim 4, characterized in that: The determining the target pre-adjustment time according to the load adjustment completion time in the plurality of historical adjustment data of the target adjustment category includes: Determine the time interval between the load adjustment completion times of two adjacent historical adjustment data in the target adjustment category; Determine an average time interval based on the time intervals of the pairwise adjacent historical adjustment data; A target pre-adjustment time is determined according to the average time interval and the current time.

6. The water machine load control method for an air conditioner according to claim 5, characterized in that: The determining the target pre-adjustment time according to the average time interval and the current time includes: The difference between the average time interval and the load adjustment time of the target historical adjustment data is used as the target interval time; The sum of the current time and the target interval time is used as the target pre-adjustment time.

7. The water machine load control method for an air conditioner according to claim 3, characterized in that: The method further comprises: In the case that there is no adjustment category corresponding to the mean value of the historical adjustment data whose similarity is greater than the preset threshold, the target load and the target pre-adjustment time are determined according to the current adjustment data.

8. The water machine load control method for an air conditioner according to claim 1, characterized in that: The method further comprises: For the plurality of historical adjustment data, determining similarities between any two of the historical adjustment data; The adjustment categories to which the plurality of historical adjustment data belong are determined according to the similarities between any two of the historical adjustment data.

9. A method and device for controlling water load of an air conditioner, characterized in that: The device comprises: A data acquisition module is used to acquire current adjustment data and multiple historical adjustment data after adjusting the load of the water machine; the multiple historical adjustment data include historical adjustment data of multiple adjustment categories; multiple historical adjustment data of the same adjustment category have similar data change patterns; a category determination module, configured to determine, from among the multiple adjustment categories, a target adjustment category that matches the current adjustment data; a data determination module, configured to determine a target load and a target pre-adjustment time based on historical adjustment data of the target adjustment category; The load adjustment module is used to adjust the load of the water machine according to the target load when the target pre-adjustment time is reached.

10. An air conditioner, characterized in that: include: A processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, the steps of the water machine load control method for the air conditioner according to any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the water machine load control method for the air conditioner according to any one of claims 1 to 8 are implemented.

Images