Method and device for determining shutdown time of refrigeration equipment
By collecting and utilizing the environmental parameters predicted by machine learning models, intelligent shutdown of refrigeration equipment is achieved, the problem of energy waste in the existing technology is solved, and energy utilization efficiency is improved.
Patent Information
- Application Number
- CN202411409208.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-10
- Publication Date
- 2024-12-03
AI Technical Summary
The prior art cannot shut down refrigeration equipment in time according to real-time environmental changes, resulting in waste of energy.
By collecting environmental parameters of indoor temperature, indoor humidity and outdoor temperature, the trained machine learning model predicts indoor temperature and shuts down the refrigeration device when the predicted temperature is less than the threshold, otherwise data will be reacquired every preset time until the threshold is reached.
It realizes the timely shutdown of refrigeration equipment according to real-time environmental changes, avoids energy waste and improves energy utilization efficiency.
Smart Images

Figure CN119063165A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of equipment control, and in particular to a method and device for determining a shutdown time of a refrigeration device. Background Art
[0002] Refrigeration equipment is needed in many places to adjust the temperature. The operation of refrigeration equipment puts a lot of pressure on the power supply. If the refrigeration equipment can be turned off in time at the right time, a lot of energy can be saved. At present, the shutdown time of refrigeration equipment depends on fixed settings or manual adjustment. It is impossible to flexibly and dynamically turn off the refrigeration equipment according to real-time environmental changes, resulting in energy waste. Summary of the invention
[0003] In view of this, the embodiments of the present application provide a method, device, electronic device and computer-readable storage medium for determining the shutdown time of a refrigeration device, so as to solve the problem in the prior art that the refrigeration device cannot be shut down in time according to real-time environmental changes, resulting in energy waste.
[0004] According to a first aspect of an embodiment of the present application, a method for determining a shutdown time of a refrigeration device is provided, comprising: collecting environmental parameters of a target location at a current time, wherein the environmental parameters include: indoor temperature, indoor humidity, and outdoor temperature; based on the environmental parameters, using a machine learning model to determine a predicted indoor temperature of the target location at a target time, wherein the machine learning model has been trained to predict the indoor temperature of the location at subsequent times of the current time based on the environmental parameters of the location at the current time; if the predicted indoor temperature is less than a temperature threshold, shutting down the refrigeration device; otherwise, re-collecting the environmental parameters at a preset time interval, and re-predicting the indoor temperature based on the re-collected environmental parameters, until the predicted indoor temperature is less than the temperature threshold, shutting down the refrigeration device.
[0005] According to a second aspect of an embodiment of the present application, there is provided a device for determining a shutdown time of a refrigeration device, comprising: an acquisition module, configured to acquire environmental parameters of a target location at a current time, wherein the environmental parameters include: indoor temperature, indoor humidity, and outdoor temperature; a prediction module, configured to determine a predicted indoor temperature of the target location at a target time based on the environmental parameters using a machine learning model, wherein the machine learning model has been trained to predict the indoor temperature of the location at subsequent times of the current time based on the environmental parameters of the location at the current time; a control module, configured to shut down the refrigeration device if the predicted indoor temperature is less than a temperature threshold; the control module is further configured to re-acquire the environmental parameters at preset time intervals, and re-predict the predicted indoor temperature based on the re-acquired environmental parameters until the predicted indoor temperature is less than the temperature threshold, and then shut down the refrigeration device.
[0006] According to a third aspect of an embodiment of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.
[0007] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, which stores a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.
[0008] Compared with the prior art, the embodiments of the present application have the following beneficial effects: collecting the environmental parameters of the target place at the current moment, wherein the environmental parameters include: indoor temperature, indoor humidity, and outdoor temperature; based on the environmental parameters, using a machine learning model to determine the predicted indoor temperature of the target place at the target moment, wherein the machine learning model has been trained to predict the indoor temperature of the place at subsequent moments of the current moment based on the environmental parameters of the place at the current moment; if the predicted indoor temperature is less than the temperature threshold, the refrigeration equipment is turned off; otherwise, the environmental parameters are re-collected at preset time intervals, and the predicted indoor temperature is re-predicted based on the re-collected environmental parameters until the predicted indoor temperature is less than the temperature threshold, and the refrigeration equipment is turned off. The above-mentioned technical means can solve the problem in the prior art that the refrigeration equipment cannot be shut down in time according to real-time environmental changes, resulting in energy waste, and the refrigeration equipment can be shut down in time to avoid energy waste. BRIEF DESCRIPTION OF THE DRAWINGS
[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0010] Figure 1 is a flow chart of a method for determining the shutdown time of a refrigeration device provided in an embodiment of the present application;
[0011] Figure 2 is a flow chart of another method for determining the shutdown time of a refrigeration device provided in an embodiment of the present application;
[0012] Figure 3 It is a structural schematic diagram of a device for determining the shutdown time of a refrigeration device provided in an embodiment of the present application;
[0013] Figure 4 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0014] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.
[0015] A method and device for determining the shutdown time of a refrigeration device according to an embodiment of the present application will be described in detail below with reference to the accompanying drawings.
[0016] Figure 1 It is a flowchart of a method for determining the shutdown time of a refrigeration device provided in an embodiment of the present application. Figure 1 The method for determining the shutdown time of the refrigeration equipment can be executed by a computer or a server, or software on the computer or the server. Figure 1 As shown, the method for determining the shutdown time of the refrigeration equipment includes:
[0017] S101, collecting environmental parameters of the target location at the current moment, wherein the environmental parameters include: indoor temperature, indoor humidity, and outdoor temperature;
[0018] S102, determining a predicted indoor temperature of a target place at a target time using a machine learning model based on the environmental parameters, wherein the machine learning model has been trained to predict the indoor temperature of the place at a subsequent time after the current time based on the environmental parameters of the place at the current time;
[0019] S103, if the predicted indoor temperature is lower than the temperature threshold, shut down the refrigeration equipment;
[0020] S104: Otherwise, the environmental parameters are collected again at a preset time interval, and the indoor temperature is re-predicted based on the re-collected environmental parameters until the predicted indoor temperature is less than the temperature threshold, and the refrigeration device is turned off.
[0021] The environmental parameters of the target place are collected by various sensors and other devices set up in the target place. The indoor temperature is the temperature in the target place, the indoor humidity is the humidity in the target place, and the outdoor temperature is the temperature of the external environment of the target place. The machine learning model can be a support vector machine, a random forest or a neural network. The machine learning model predicts the predicted indoor temperature of the target place at the target time as the indoor temperature, indoor humidity and outdoor temperature change over the day under the current time. The machine learning model predicts that the refrigeration equipment does not work by default. The refrigeration equipment can be a cooling tower, a freezing pump and a chiller. It is determined whether the predicted indoor temperature is less than the temperature threshold. If the predicted indoor temperature is less than the temperature threshold, the refrigeration equipment is turned off. Otherwise, the environmental parameters are collected again at a preset time interval, and the predicted indoor temperature is re-predicted until the predicted indoor temperature is less than the temperature threshold, and the refrigeration equipment is turned off.
[0022] According to the technical solution provided by the embodiment of the present application, the environmental parameters of the target place at the current moment are collected, wherein the environmental parameters include: indoor temperature, indoor humidity, and outdoor temperature; based on the environmental parameters, the predicted indoor temperature of the target place at the target moment is determined using a machine learning model, wherein the machine learning model has been trained to predict the indoor temperature of the place at subsequent moments of the current moment based on the environmental parameters of the place at the current moment; if the predicted indoor temperature is less than the temperature threshold, the refrigeration equipment is turned off; otherwise, the environmental parameters are recollected at preset time intervals, and the predicted indoor temperature is re-predicted based on the recollected environmental parameters until the predicted indoor temperature is less than the temperature threshold, and the refrigeration equipment is turned off. The above-mentioned technical means can solve the problem in the prior art that the refrigeration equipment cannot be shut down in time according to real-time environmental changes, resulting in energy waste, and the refrigeration equipment can be shut down in time to avoid energy waste.
[0023] Furthermore, if the predicted indoor temperature is greater than or equal to the temperature threshold, the following loop is executed: collect the environmental parameters of the target place at the i-th moment, where i is the serial number of the moment; use the machine learning model to predict the predicted indoor temperature of the target place at the target moment based on the environmental parameters at the i-th moment; determine whether the predicted indoor temperature is less than the temperature threshold; if so, turn off the refrigeration equipment and end the loop; if not, update i by adding 1.
[0024] The difference between every two moments is a preset duration, that is, the difference between the i-1th moment, the i-th moment and the i+1th moment is a preset duration.
[0025] For example, if the target time is 21:00, the preset duration is 10 minutes, and the time to shut down the refrigeration equipment is determined from 20:00. Then, the environmental parameters of the target location are collected at 20:00, and the predicted indoor temperature of the target location at 21:00 is determined by the machine learning model based on the environmental parameters, and it is determined whether the predicted indoor temperature is less than the temperature threshold. If so, the refrigeration equipment is shut down; otherwise, the environmental parameters of the target location are collected at 20:10, and the predicted indoor temperature of the target location is determined by the machine learning model based on the environmental parameters, and it is determined whether the predicted indoor temperature is less than the temperature threshold. If so, the refrigeration equipment is shut down; otherwise, the environmental parameters of the target location are collected at 20:20, and the predicted indoor temperature of the target location is determined by the machine learning model based on the environmental parameters... until the predicted indoor temperature is less than the temperature threshold, the refrigeration equipment is shut down.
[0026] In one embodiment, the actual indoor temperature of the target place at the target time is collected; a feedback reward is determined based on the predicted indoor temperature and the actual indoor temperature; and a model parameter of the machine learning model is optimized based on the feedback reward.
[0027] The closer the predicted indoor temperature is to the actual indoor temperature, the smaller the feedback reward is (the feedback reward is a negative value), and the greater the difference between the predicted indoor temperature and the actual indoor temperature, the greater the feedback reward is. Optimizing the model parameters of the machine learning model based on feedback rewards is a common reinforcement learning method, so the specific method will not be repeated here.
[0028] Furthermore, before using the machine learning model to determine the predicted indoor temperature of the target place at the target time based on the environmental parameters, the method also includes: obtaining the environmental parameters of multiple places at different times and the actual indoor temperature of each place at a target time subsequent to the time; using the machine learning model to determine the predicted indoor temperature of each place at the target time subsequent to the time based on the environmental parameters of each place at different times; using the loss function to calculate the loss value between the predicted indoor temperature and the actual indoor temperature corresponding to each place at different times; and optimizing the model parameters of the machine learning model based on the loss value to complete the training of the machine learning model.
[0029] For a place at a moment: the place has a set of environmental parameters at this moment, and the actual indoor temperature of the place at the target moment after this moment is the actual indoor temperature corresponding to this moment; the machine learning model determines the predicted indoor temperature of each place at the target moment after this moment based on the environmental parameters of the place at this moment; the loss value between the predicted indoor temperature corresponding to the place at this moment and the actual indoor temperature is calculated using the loss function, and the model parameters of the machine learning model are optimized according to the loss value. The loss function can be a common loss function such as cross entropy.
[0030] Furthermore, based on the environmental parameters, a machine learning model is used to determine the predicted indoor temperature of the target place at the target time, including: calculating multiple temperature parameters based on the environmental parameters, wherein the multiple temperature parameters include: wet bulb temperature and indoor and outdoor temperature difference; based on the environmental parameters and the multiple temperature parameters, a machine learning model is used to determine the predicted indoor temperature of the target place at the target time.
[0031] Furthermore, multiple temperature parameters are calculated based on the environmental parameters, including: calculating the wet-bulb temperature based on the indoor temperature and the indoor humidity; and calculating the indoor-outdoor temperature difference based on the indoor temperature and the outdoor temperature.
[0032] Generally, wet-bulb temperature is used to characterize the content of water vapor in the air, that is, the humidity of the air, which reflects the degree to which the water vapor in the air is close to saturation. In the embodiment of the present application, the ratio of indoor temperature to indoor humidity can be directly used as the wet-bulb temperature to measure the relationship between indoor temperature and humidity. The difference between indoor temperature and outdoor temperature is used as the indoor and outdoor temperature difference; the difference between evaporation temperature and maintenance temperature is used as the cold storage temperature difference.
[0033] The machine learning model can predict the predicted indoor temperature of the target place at the target time based on the indoor temperature, outdoor temperature, wet-bulb temperature, indoor-outdoor temperature difference and cold storage temperature difference. The indoor temperature, outdoor temperature, wet-bulb temperature, indoor-outdoor temperature difference and cold storage temperature difference can be processed by conventional encoding methods and then spliced, and then the machine learning model determines the predicted indoor temperature based on the spliced features.
[0034] In one embodiment, the following method is performed every preset period: obtaining the predicted indoor temperatures when multiple refrigeration devices are turned off within the preset period; calculating the difference between each predicted indoor temperature and the temperature threshold, and calculating the average of all the differences; optimizing the preset time length based on the average to achieve dynamic adjustment of the preset time length.
[0035] Assuming that the preset cycle is one week, then every week: obtain the predicted indoor temperatures when the refrigeration equipment is turned off seven times in a week (the refrigeration equipment is turned off once a day); calculate the difference between the seven predicted indoor temperatures and the temperature threshold, and calculate the average of the seven differences; optimize the preset duration based on the average to achieve dynamic adjustment of the preset duration.
[0036] The preset duration can be optimized as follows: if the mean is greater than the first preset mean, the preset duration is reduced; if the mean is less than the second preset mean, the preset duration is increased, and the first preset mean is greater than the second preset mean.
[0037] Figure 2 FIG. 1 is a flow chart of another method for determining the shutdown time of a refrigeration device provided in an embodiment of the present application. Figure 2 As shown, the method includes:
[0038] S201, collecting environmental parameters of the target location at the current moment;
[0039] S202, calculating a plurality of temperature parameters based on the environmental parameters, wherein the plurality of temperature parameters include: wet bulb temperature, indoor and outdoor temperature difference, and cold storage temperature difference;
[0040] S203, determining a predicted indoor temperature of a target place at a target time using a machine learning model based on the environmental parameters and the plurality of temperature parameters;
[0041] S204, if the predicted indoor temperature is lower than the temperature threshold, shut down the refrigeration equipment;
[0042] S205: If the predicted indoor temperature is greater than or equal to the temperature threshold, execute the following loop:
[0043] S206, collecting environmental parameters of the target location at the i-th moment, where i is the sequence number of the moment;
[0044] S207, predicting the predicted indoor temperature of the target place at the target time using a machine learning model based on the environmental parameters at the i-th time;
[0045] S208, determining whether the predicted indoor temperature is less than a temperature threshold;
[0046] S209, if it is less than, then turn off the refrigeration equipment and end the cycle;
[0047] S210: If it is not less than, update i by adding 1.
[0048] All the above optional technical solutions can be arbitrarily combined to form optional embodiments of the present application, which will not be described one by one here.
[0049] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.
[0050] Figure 3 Schematic diagram of a device for determining the shutdown time of a refrigeration device provided in an embodiment of the present application. Figure 3 As shown, the device for determining the shutdown time of the refrigeration equipment includes:
[0051] The collection module 301 is configured to collect environmental parameters of the target location at the current moment, wherein the environmental parameters include: indoor temperature, indoor humidity, and outdoor temperature;
[0052] The prediction module 302 is configured to determine the predicted indoor temperature of the target place at the target time using a machine learning model based on the environmental parameters, wherein the machine learning model has been trained to predict the indoor temperature of the place at a subsequent time after the current time based on the environmental parameters of the place at the current time;
[0053] The control module 303 is configured to turn off the refrigeration equipment if the predicted indoor temperature is less than the temperature threshold;
[0054] The control module 304 is further configured to re-collect environmental parameters at preset time intervals, and re-predict the indoor temperature based on the re-collected environmental parameters until the predicted indoor temperature is less than the temperature threshold, and then turn off the refrigeration equipment.
[0055] According to the technical solution provided by the embodiment of the present application, the environmental parameters of the target place at the current moment are collected, wherein the environmental parameters include: indoor temperature, indoor humidity, and outdoor temperature; based on the environmental parameters, the predicted indoor temperature of the target place at the target moment is determined using a machine learning model, wherein the machine learning model has been trained to predict the indoor temperature of the place at subsequent moments of the current moment based on the environmental parameters of the place at the current moment; if the predicted indoor temperature is less than the temperature threshold, the refrigeration equipment is turned off; otherwise, the environmental parameters are recollected at preset time intervals, and the predicted indoor temperature is re-predicted based on the recollected environmental parameters until the predicted indoor temperature is less than the temperature threshold, and the refrigeration equipment is turned off. The above-mentioned technical means can solve the problem in the prior art that the refrigeration equipment cannot be shut down in time according to real-time environmental changes, resulting in energy waste, and the refrigeration equipment can be shut down in time to avoid energy waste.
[0056] In some embodiments, the control module 303 is also configured to execute the following loop if the predicted indoor temperature is greater than or equal to the temperature threshold: collect the environmental parameters of the target place at the i-th moment, where i is the sequence number of the moment; based on the environmental parameters at the i-th moment, use the machine learning model to predict the predicted indoor temperature of the target place at the target moment; determine whether the predicted indoor temperature is less than the temperature threshold; if it is, turn off the refrigeration equipment and end the loop; if it is not, update i by adding 1.
[0057] The difference between every two moments is a preset duration, that is, the difference between the i-1th moment, the i-th moment and the i+1th moment is a preset duration.
[0058] For example, if the target time is 21:00, the preset duration is 10 minutes, and the time to shut down the refrigeration equipment is determined from 20:00. Then, the environmental parameters of the target location are collected at 20:00, and the predicted indoor temperature of the target location at 21:00 is determined by the machine learning model based on the environmental parameters, and it is determined whether the predicted indoor temperature is less than the temperature threshold. If so, the refrigeration equipment is shut down; otherwise, the environmental parameters of the target location are collected at 20:10, and the predicted indoor temperature of the target location is determined by the machine learning model based on the environmental parameters, and it is determined whether the predicted indoor temperature is less than the temperature threshold. If so, the refrigeration equipment is shut down; otherwise, the environmental parameters of the target location are collected at 20:20, and the predicted indoor temperature of the target location is determined by the machine learning model based on the environmental parameters... until the predicted indoor temperature is less than the temperature threshold, the refrigeration equipment is shut down.
[0059] In some embodiments, the prediction module 302 is further configured to collect the actual indoor temperature of the target place at the target time; determine a feedback reward based on the predicted indoor temperature and the actual indoor temperature; and optimize the model parameters of the machine learning model based on the feedback reward.
[0060] The closer the predicted indoor temperature is to the actual indoor temperature, the smaller the feedback reward is (the feedback reward is a negative value), and the greater the difference between the predicted indoor temperature and the actual indoor temperature, the greater the feedback reward is. Optimizing the model parameters of the machine learning model based on feedback rewards is a common reinforcement learning method, so the specific method will not be repeated here.
[0061] In some embodiments, the prediction module 302 is also configured to obtain environmental parameters of multiple places at different times and the actual indoor temperature of each place at a target time subsequent to the time; determine the predicted indoor temperature of each place at the target time subsequent to the time using a machine learning model based on the environmental parameters of each place at different times; calculate the loss value between the predicted indoor temperature and the actual indoor temperature corresponding to each place at different times using a loss function; and optimize the model parameters of the machine learning model based on the loss value to complete the training of the machine learning model.
[0062] For a place at a moment: the place has a set of environmental parameters at this moment, and the actual indoor temperature of the place at the target moment after this moment is the actual indoor temperature corresponding to this moment; the machine learning model determines the predicted indoor temperature of each place at the target moment after this moment based on the environmental parameters of the place at this moment; the loss value between the predicted indoor temperature corresponding to the place at this moment and the actual indoor temperature is calculated using the loss function, and the model parameters of the machine learning model are optimized according to the loss value. The loss function can be a common loss function such as cross entropy.
[0063] In some embodiments, the prediction module 302 is also configured to calculate multiple temperature parameters based on environmental parameters, wherein the multiple temperature parameters include: wet-bulb temperature and indoor and outdoor temperature difference; based on the environmental parameters and multiple temperature parameters, a machine learning model is used to determine the predicted indoor temperature of the target place at the target time.
[0064] In some embodiments, the prediction module 302 is further configured to calculate the wet bulb temperature based on the indoor temperature and the indoor humidity; and calculate the indoor and outdoor temperature difference based on the indoor temperature and the outdoor temperature.
[0065] Generally, wet-bulb temperature is used to characterize the content of water vapor in the air, that is, the humidity of the air, which reflects the degree to which the water vapor in the air is close to saturation. In the embodiment of the present application, the ratio of indoor temperature to indoor humidity can be directly used as the wet-bulb temperature to measure the relationship between indoor temperature and humidity. The difference between indoor temperature and outdoor temperature is used as the indoor and outdoor temperature difference; the difference between evaporation temperature and maintenance temperature is used as the cold storage temperature difference.
[0066] The machine learning model can predict the predicted indoor temperature of the target place at the target time based on the indoor temperature, outdoor temperature, wet-bulb temperature, indoor-outdoor temperature difference and cold storage temperature difference. The indoor temperature, outdoor temperature, wet-bulb temperature, indoor-outdoor temperature difference and cold storage temperature difference can be processed by conventional encoding methods and then spliced, and then the machine learning model determines the predicted indoor temperature based on the spliced features.
[0067] In some embodiments, the control module 303 is also configured to obtain the predicted indoor temperatures when multiple refrigeration devices are turned off within the preset cycle; calculate the difference between each predicted indoor temperature and the temperature threshold, and calculate the average of all the differences; optimize the preset time length based on the average to achieve dynamic adjustment of the preset time length.
[0068] Assuming that the preset cycle is one week, then every week: obtain the predicted indoor temperatures when the refrigeration equipment is turned off seven times in a week (the refrigeration equipment is turned off once a day); calculate the difference between the seven predicted indoor temperatures and the temperature threshold, and calculate the average of the seven differences; optimize the preset duration based on the average to achieve dynamic adjustment of the preset duration.
[0069] In some embodiments, the control module 303 is also configured to optimize the preset duration according to the following method: if the mean is greater than the first preset mean, the preset duration is reduced; if the mean is less than the second preset mean, the preset duration is increased, and the first preset mean is greater than the second preset mean.
[0070] In some embodiments, the control module 303 is also configured to collect environmental parameters of the target place at the current moment; calculate multiple temperature parameters based on the environmental parameters, wherein the multiple temperature parameters include: wet-bulb temperature, indoor and outdoor temperature difference, and cold storage temperature difference; determine the predicted indoor temperature of the target place at the target moment using a machine learning model based on the environmental parameters and the multiple temperature parameters; if the predicted indoor temperature is less than the temperature threshold, turn off the refrigeration equipment; if the predicted indoor temperature is greater than or equal to the temperature threshold, execute the following loop: collect the environmental parameters of the target place at the i-th moment, wherein i is the sequence number of the moment; predict the predicted indoor temperature of the target place at the target moment using a machine learning model based on the environmental parameters at the i-th moment; determine whether the predicted indoor temperature is less than the temperature threshold; if it is less than, turn off the refrigeration equipment and end the loop; if it is not less than, update i by adding 1.
[0071] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean 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 the present application.
[0072] Figure 4 Schematic diagram of an electronic device 4 provided in an embodiment of the present application. Figure 4 As shown, the electronic device 4 of this embodiment includes: a processor 401, a memory 402, and a computer program 403 stored in the memory 402 and executable on the processor 401. When the processor 401 executes the computer program 403, the steps in the above-mentioned method embodiments are implemented. Alternatively, when the processor 401 executes the computer program 403, the functions of the modules / units in the above-mentioned device embodiments are implemented.
[0073] The electronic device 4 may be a desktop computer, a notebook, a PDA, a cloud server, or other electronic device. The electronic device 4 may include, but is not limited to, a processor 401 and a memory 402. Those skilled in the art will appreciate that Figure 4 The electronic device 4 is merely an example and does not limit the electronic device 4 , and may include more or less components than those shown in the figure, or different components.
[0074] The processor 401 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
[0075] The memory 402 may be an internal storage unit of the electronic device 4, for example, a hard disk or memory of the electronic device 4. The memory 402 may also be an external storage device of the electronic device 4, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 4. The memory 402 may also include both an internal storage unit and an external storage device of the electronic device 4. The memory 402 is used to store computer programs and other programs and data required by the electronic device.
[0076] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units.
[0077] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. The computer program may include computer program code, and the computer program code may be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.
[0078] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.
Claims
1. A method for determining the shutdown time of a refrigeration device, characterized in that: include: Collecting environmental parameters of the target location at the current moment, wherein the environmental parameters include: indoor temperature, indoor humidity and outdoor temperature; Determining the predicted indoor temperature of the target place at the target time using a machine learning model based on the environmental parameters, wherein the machine learning model has been trained to predict the indoor temperature of the place at a subsequent time after the current time based on the environmental parameters of the place at the current time; If the predicted indoor temperature is less than the temperature threshold, shutting down the refrigeration equipment; Otherwise, the environmental parameters are collected again at preset time intervals, and the predicted indoor temperature is re-predicted based on the re-collected environmental parameters until the predicted indoor temperature is less than the temperature threshold, and the refrigeration device is turned off.
2. The method according to claim 1, characterized in that If the predicted indoor temperature is greater than or equal to the temperature threshold, execute the following loop: Collect the environmental parameters of the target location at the i-th moment, where i is the sequence number of the moment; According to the environmental parameters at the i-th moment, using the machine learning model to predict the predicted indoor temperature of the target place at the target moment; Determining whether the predicted indoor temperature is less than the temperature threshold; If it is less than, shut down the refrigeration equipment and end the cycle; If it is not less than, update i by adding 1.
3. The method according to claim 1, characterized in that The method further comprises: Collecting the actual indoor temperature of the target place at the target time; determining a feedback reward based on the predicted indoor temperature and the actual indoor temperature; Model parameters of the machine learning model are optimized based on the feedback reward.
4. The method according to claim 1, characterized in that: Before determining the predicted indoor temperature of the target place at the target time using the machine learning model based on the environmental parameters, the method further includes: Obtaining environmental parameters of multiple places at different times and the actual indoor temperature of each place at a target time subsequent to the time; Based on the environmental parameters of each place at different times, the machine learning model is used to determine the predicted indoor temperature of each place at a target time subsequent to the time; The loss function is used to calculate the loss value between the predicted indoor temperature and the actual indoor temperature of each place at different times; Optimize the model parameters of the machine learning model according to the loss value to complete the training of the machine learning model.
5. The method according to claim 1, characterized in that Determining the predicted indoor temperature of the target place at the target time using a machine learning model based on the environmental parameters includes: Calculating a plurality of temperature parameters based on the environmental parameters, wherein the plurality of temperature parameters include: wet bulb temperature and indoor and outdoor temperature difference; Based on the environmental parameters and multiple temperature parameters, the machine learning model is used to determine the predicted indoor temperature of the target place at the target time.
6. The method according to claim 5, characterized in that Calculating a plurality of temperature parameters based on the environmental parameters, including: calculating the wet-bulb temperature based on the indoor temperature and the indoor humidity; The indoor and outdoor temperature difference is calculated based on the indoor temperature and the outdoor temperature.
7. The method according to claim 1, characterized in that The method further comprises: The following method is executed every preset period: Obtain the predicted indoor temperature when the refrigeration device is turned off for a plurality of times within the preset period; Calculate the difference between each predicted indoor temperature and the temperature threshold, and calculate the average of all the differences; The preset duration is optimized based on the mean value to achieve dynamic adjustment of the preset duration.
8. A device for determining the shutdown time of a refrigeration device, characterized in that: include: The collection module is configured to collect environmental parameters of the target location at the current moment, wherein the environmental parameters include: indoor temperature, indoor humidity, and outdoor temperature; A prediction module is configured to determine the predicted indoor temperature of the target place at the target time using a machine learning model based on the environmental parameters, wherein the machine learning model has been trained to predict the indoor temperature of the place at a subsequent time after the current time based on the environmental parameters of the place at the current time; a control module configured to shut down the refrigeration device if the predicted indoor temperature is less than a temperature threshold; The control module is further configured to re-collect the environmental parameters at preset time intervals, and re-predict the predicted indoor temperature based on the re-collected environmental parameters until the predicted indoor temperature is less than the temperature threshold, and then turn off the refrigeration equipment.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.
Citation Information
Patent Citations
Control method, control system, computer readable storage medium and movable air conditioner
CN107642868A
Control method, control system, computer readable storage medium and mobile air conditioner
CN107883544A
Control method, control system, computer readable storage medium and mobile air conditioner
CN107883545A
Machine room temperature regulation method and system
CN112050397A
Machine room temperature regulation and control method based on time sequence prediction
CN116627190A
