An intelligent control method for an intelligent temperature control system

Abstract

The present invention relates to an intelligent control method for an intelligent temperature control system, belonging to the technical field of intelligent temperature control. The present invention tracks and identifies the real-time heat generation characteristic data of each sub-region in the target region, obtains the sub-regions to be cooled, obtains the cooling requirements of the sub-regions to be cooled, thereby obtains the cooling performance data of the temperature intelligent control system for each sub-region, and conducts a feasibility analysis based on the cooling performance data of the temperature intelligent control system for each sub-region and the cooling requirements of the sub-regions to be cooled, obtains the feasibility analysis result, and finally cools the sub-regions to be cooled according to the feasibility analysis result or generates relevant warning information. The present invention can formulate a more accurate temperature control process by evaluating the effectiveness according to the cooling performance data of the temperature intelligent control system and the heat generation situation of the regions that need to be cooled, so as to achieve power consumption reduction and precise temperature control.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature control, and in particular, to an intelligent control method for an intelligent temperature control system. Background Art

[0002] An intelligent temperature control system is an intelligent system that can perform dynamic control according to the temperature characteristics of a target object or a target area. The intelligent temperature control system includes refrigeration equipment or heating equipment such as air conditioners, fans, heaters, etc. Nowadays, after the relevant equipment of the intelligent temperature control system has been in service for a certain number of years, the refrigeration or heating performance will decline to a certain extent, and it may not meet the temperature control requirements. The prior art does not consider this situation at all, resulting in a decrease in the control accuracy of the intelligent temperature control system and the failure to meet the control requirements of temperature control. Summary of the Invention

[0003] The present invention overcomes the deficiencies of the prior art and provides an intelligent control method for an intelligent temperature control system.

[0004] To achieve the above object, the technical solution adopted by the present invention is as follows:

[0005] The first aspect of the present invention provides an intelligent control method for an intelligent temperature control system, including the following steps:

[0006] Obtain the environmental characteristic data of the target area, construct a temperature characteristic model according to the environmental characteristic data of the target area, and construct a temperature tracking model based on a deep neural network;

[0007] Track and identify the real-time heat generation characteristic data of each sub-area in the target area according to the temperature tracking model and the temperature characteristic model, obtain the sub-areas to be refrigerated, and obtain the refrigeration requirements of the sub-areas to be refrigerated;

[0008] Obtain the refrigeration performance data of the temperature intelligent control system of each sub-area, and perform a feasibility analysis according to the refrigeration performance data of each sub-area and the refrigeration requirements of the sub-areas to be refrigerated, and obtain a feasibility analysis result;

[0009] Refrigerate the sub-areas to be refrigerated according to the feasibility analysis result or generate relevant warning information.

[0010] Further, in this method, obtaining the environmental characteristic data of the target area and constructing a temperature characteristic model according to the environmental characteristic data of the target area is specifically:

[0011] Obtain the layout diagram data in the target area, and construct a 3D model diagram of the target area through 3D modeling software based on the layout diagram data in the target area. Set sensors in each sub-area in the target area;

[0012] Obtain the environmental characteristic data of the target area through the sensors, set the temperature gradient data map, and display the temperature characteristics of each sub-area in the target area based on the temperature gradient data map and the environmental characteristic data of the target area. Construct a temperature characteristic model for the current timestamp based on the 3D model diagram of the target area;

[0013] Obtain the temperature characteristic models for each timestamp, combine the temperature characteristic models for each timestamp, and display them in a preset manner to form a dynamic temperature characteristic model, which is used as the final temperature characteristic model and output.

[0014] Furthermore, in this method, a temperature tracking model is constructed based on a deep neural network, specifically:

[0015] Construct a temperature tracking model based on a deep neural network, initialize the learning rate of the temperature tracking model and the mean square error of the stop condition, obtain the dynamic temperature characteristic model, and extract the model change characteristics of the dynamic temperature characteristic model;

[0016] Take the model change characteristics of each dynamic temperature characteristic model as a state vector, calculate the transition probability value of the state vector transferring to another state vector, and set the transition probability threshold;

[0017] When the transition probability value of the state vector transferring to another state vector is greater than the transition probability threshold, update the state vector to another state vector and update the model change characteristics of the dynamic temperature characteristic model;

[0018] When the transition probability value of the state vector transferring to another state vector is not greater than the transition probability threshold, keep the current state vector unchanged, input the model change characteristics of the dynamic temperature characteristic model into the temperature tracking model for learning based on the learning. When the stop condition of the model is less than the mean square error of the stop condition, the temperature tracking model training is completed.

[0019] Furthermore, in this method, track and identify the real-time heat generation characteristic data of each sub-area in the target area according to the temperature tracking model and the temperature characteristic model, and obtain the sub-areas to be refrigerated, specifically:

[0020] Obtain the temperature characteristic models within a preset time, and input the temperature characteristic models within the preset time into the temperature tracking model for identification and state update;

[0021] Through identification and status update, obtain the temperature feature model after status update, and obtain the real-time heat generation feature data of each sub-region in the target region according to the temperature feature model after the status update;

[0022] Set a threshold for the heat generation feature data, and determine whether the real-time heat generation feature data of the sub-region is greater than the threshold for the heat generation feature data. If it is less, then regard the corresponding region as a normal heat generation region;

[0023] When the real-time heat generation feature data of the sub-region is greater than the threshold for the heat generation feature data, then regard the corresponding region as a sub-region to be refrigerated.

[0024] Further, in this method, obtain the refrigeration performance data of the temperature intelligent control system for each sub-region, and perform a feasibility analysis based on the refrigeration performance data of the temperature intelligent control system for each sub-region and the refrigeration demand of the sub-region to be refrigerated, and obtain the result of the feasibility analysis. Specifically:

[0025] Obtain the refrigeration performance data of the temperature intelligent control system for each sub-region, and obtain the maximum refrigeration performance data of the temperature intelligent control system for each sub-region according to the refrigeration performance data of the temperature intelligent control system for each sub-region;

[0026] Determine whether the maximum refrigeration performance data of the temperature intelligent control system is greater than the refrigeration demand of the sub-region to be refrigerated;

[0027] When the maximum refrigeration performance data of the temperature intelligent control system is greater than the refrigeration demand of the sub-region to be refrigerated, then regard the situation where the maximum refrigeration performance data is greater than the refrigeration demand of the sub-region to be refrigerated as an adjustable region;

[0028] When the maximum refrigeration performance data of the temperature intelligent control system is not greater than the refrigeration demand of the sub-region to be refrigerated, then regard the situation where the maximum refrigeration performance data is not greater than the refrigeration demand of the sub-region to be refrigerated as a non-adjustable region;

[0029] Construct a feasibility analysis result based on the adjustable region and the non-adjustable region, and output the feasibility analysis result.

[0030] Further, in this method, refrigerate the sub-region to be refrigerated according to the result of the feasibility analysis or generate relevant warning information. Specifically:

[0031] When the result of the feasibility analysis is a non-adjustable region, then obtain the location of the temperature intelligent control system corresponding to the sub-region where it is located, and generate relevant warning information according to the location of the temperature intelligent control system corresponding to the sub-region where it is located;

[0032] When the result of the feasibility analysis is an adjustable area, initialize the refrigeration working parameters of the temperature intelligent control system, issue instructions to each sub-area based on the refrigeration working parameters of the temperature intelligent control system, and obtain the cooling characteristic data of the target area;

[0033] Set a threshold for the cooling characteristic data. When the cooling characteristic data of the target area is greater than the threshold for the cooling characteristic data, output the refrigeration working parameters of the temperature intelligent control system, and perform temperature regulation according to the refrigeration working parameters of the temperature intelligent control system;

[0034] When the cooling characteristic data of the target area is not greater than the threshold for the cooling characteristic data, readjust the refrigeration working parameters of the temperature intelligent control system until the cooling characteristic data of the target area is greater than the threshold for the cooling characteristic data.

[0035] The second aspect of the present invention provides an intelligent control device for a temperature intelligent control system, including a memory and a processor. The memory includes an intelligent control method program for the temperature intelligent control system. When the intelligent control method program for the temperature intelligent control system is executed by the processor, the steps of any one of the intelligent control methods for the temperature intelligent control system are implemented.

[0036] The third aspect of the present invention provides a temperature intelligent control terminal, including:

[0037] A temperature tracking model construction module, responsible for obtaining the environmental characteristic data of the target area, constructing a temperature characteristic model based on the environmental characteristic data of the target area, and constructing a temperature tracking model based on a deep neural network;

[0038] A refrigeration analysis module, responsible for tracking and identifying the real-time heat generation characteristic data of each sub-area in the target area according to the temperature tracking model and the temperature characteristic model, obtaining the sub-areas to be refrigerated, and obtaining the refrigeration requirements of the sub-areas to be refrigerated;

[0039] A feasibility analysis module, responsible for obtaining the refrigeration performance data of the temperature intelligent control system for each sub-area, and performing a feasibility analysis according to the refrigeration performance data of the temperature intelligent control system for each sub-area and the refrigeration requirements of the sub-areas to be refrigerated, to obtain a feasibility analysis result;

[0040] A control analysis module, responsible for refrigerating the sub-areas to be refrigerated according to the feasibility analysis result or generating relevant warning information.

[0041] A fourth aspect of the present invention provides a computer-readable storage medium, including an intelligent control method program for a temperature intelligent control system. When the intelligent control method program of the temperature intelligent control system is executed by a processor, the steps of any of the intelligent control methods of the temperature intelligent control system are implemented.

[0042] The present invention solves the defects existing in the background technology and has the following beneficial effects:

[0043] The present invention obtains environmental characteristic data of a target area, constructs a temperature characteristic model according to the environmental characteristic data of the target area, constructs a temperature tracking model based on a deep neural network, and then tracks and identifies real-time heat generation characteristic data of each sub-area in the target area according to the temperature tracking model and the temperature characteristic model to obtain sub-areas to be refrigerated, obtains the refrigeration requirements of the sub-areas to be refrigerated, thereby obtaining the refrigeration performance data of the temperature intelligent control system of each sub-area, and conducts a feasibility analysis according to the refrigeration performance data of the temperature intelligent control system of each sub-area and the refrigeration requirements of the sub-areas to be refrigerated to obtain a feasibility analysis result. Finally, refrigeration is performed on the sub-areas to be refrigerated according to the feasibility analysis result or relevant warning information is generated. The present invention can formulate a more accurate temperature control process by evaluating the refrigeration performance data of the temperature intelligent control system and the heat generation situation of the area to be refrigerated, thereby achieving power consumption reduction and precise temperature control. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or in the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0045] Figure 1 Shows the overall flowchart of the intelligent control method of the temperature intelligent control system;

[0046] Figure 2 Shows the partial method flowchart of the intelligent control method of the temperature intelligent control system;

[0047] Figure 3 Shows the schematic diagram of the intelligent control device of the temperature intelligent control system;

[0048] Figure 4 Shows the schematic diagram of the temperature intelligent control terminal. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] To better understand the above objects, features, and advantages of the present invention, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0050] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention may be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited by the specific embodiments disclosed below.

[0051] As Figure 1 shown, in the first aspect of the present invention, an intelligent control method for a temperature intelligent control system is provided, including the following steps:

[0052] S102: Obtain the environmental characteristic data of the target area, construct a temperature characteristic model according to the environmental characteristic data of the target area, and construct a temperature tracking model based on a deep neural network;

[0053] S104: Track and identify the real-time heat generation characteristic data of each sub-area in the target area according to the temperature tracking model and the temperature characteristic model, obtain the sub-areas to be refrigerated, and obtain the refrigeration requirements of the sub-areas to be refrigerated;

[0054] S106: Obtain the refrigeration performance data of the temperature intelligent control system for each sub-area, and perform a feasibility analysis according to the refrigeration performance data of the temperature intelligent control system for each sub-area and the refrigeration requirements of the sub-areas to be refrigerated, and obtain the feasibility analysis result;

[0055] S108: Refrigerate the sub-areas to be refrigerated according to the feasibility analysis result or generate relevant warning information.

[0056] It should be noted that the present invention can evaluate the effectiveness according to the refrigeration performance data of the temperature intelligent control system and the heat generation situation of the area to be refrigerated, so as to be able to formulate a more accurate temperature control process, reduce power consumption, and achieve precise temperature control.

[0057] Further, in this method, obtaining the environmental characteristic data of the target area and constructing a temperature characteristic model according to the environmental characteristic data of the target area are specifically as follows:

[0058] Obtain the layout plan data of the target area, construct a three-dimensional model diagram of the target area through three-dimensional modeling software according to the layout plan data of the target area, and set sensors in each sub-area of the target area;

[0059] Obtain the environmental feature data of the target area through sensors, set the temperature gradient data map, and display the temperature characteristics of each sub-region in the target area according to the temperature gradient data map and the environmental feature data of the target area. Construct a temperature characteristic model for the current timestamp based on the three-dimensional model map of the target area;

[0060] Obtain the temperature characteristic model for each timestamp, combine the temperature characteristic models for each timestamp, and display them in a preset manner to form a dynamic temperature characteristic model, which is used as the final temperature characteristic model and output.

[0061] It should be noted that the target area can be a building, a device, or an indoor area, etc. The 3D modeling software includes 3ds Max, Maya, Rhino, ZBrush, SketchUp, Blender, C4D software, etc., so as to construct the 3D model map of the target area or the device model map, etc. The temperature gradient data map shows different colors for different temperature gradients. For example, it is green at 25 degrees Celsius and red at 45 degrees Celsius, etc. By rendering in the 3D model map of the target area, the temperature situation in the target area is displayed dynamically and in 3D mode.

[0062] Furthermore, in this method, a temperature tracking model is constructed based on a deep neural network. Specifically:

[0063] Construct a temperature tracking model based on a deep neural network, initialize the learning rate of the temperature tracking model and the mean square error of the stop condition to 0.001, obtain the dynamic temperature characteristic model, and extract the model change characteristics of the dynamic temperature characteristic model;

[0064] Take the model change characteristics of each dynamic temperature characteristic model as a state vector, calculate the transition probability value from one state vector to another state vector, and set the transition probability threshold;

[0065] When the transition probability value from one state vector to another state vector is greater than the transition probability threshold, update the state vector to another state vector and update the model change characteristics of the dynamic temperature characteristic model;

[0066] When the transition probability value from one state vector to another state vector is not greater than the transition probability threshold, keep the current state vector unchanged, input the model change characteristics of the dynamic temperature characteristic model into the temperature tracking model for learning based on learning. When the stop condition of the model is less than the mean square error of the stop condition, the temperature tracking model training is completed.

[0067] It should be noted that the temperature feature model is dynamically learned through a deep neural network and machine learning methods to complete the intelligent tracking of temperature data. The transition probability value of the state vector transferred to another state vector is calculated by a Markov model, and a transition probability threshold is set to update the state in a timely manner, improving the intelligent tracking accuracy of temperature.

[0068] Further, in this method, according to the temperature tracking model and the temperature feature model, the real-time heating feature data of each sub-region in the target area is tracked and identified to obtain the sub-region to be cooled. Specifically:

[0069] Obtain the temperature feature model within a preset time, and input the temperature feature model within the preset time into the temperature tracking model for identification and state update;

[0070] Through identification and state update, obtain the temperature feature model after state update, and obtain the real-time heating feature data of each sub-region in the target area according to the temperature feature model after state update;

[0071] Set a heating feature data threshold, and judge whether the real-time heating feature data of the sub-region is greater than the heating feature data threshold. If it is less, the corresponding region is regarded as a normal heating region;

[0072] When the real-time heating feature data of the sub-region is greater than the heating feature data threshold, the corresponding region is regarded as the sub-region to be cooled.

[0073] It should be noted that through this method, the target area can be evaluated in real time to identify abnormal areas.

[0074] Further, in this method, obtain the refrigeration performance data of each sub-region temperature intelligent control system, and conduct a feasibility analysis based on the refrigeration performance data of each sub-region temperature intelligent control system and the refrigeration demand of the sub-region to be cooled to obtain a feasibility analysis result. Specifically:

[0075] Obtain the refrigeration performance data of each sub-region temperature intelligent control system, and obtain the maximum refrigeration performance data of each sub-region temperature intelligent control system according to the refrigeration performance data of each sub-region temperature intelligent control system;

[0076] Judge whether the maximum refrigeration performance data of the temperature intelligent control system is greater than the refrigeration demand of the sub-region to be cooled;

[0077] When the maximum refrigeration performance data of the temperature intelligent control system is greater than the refrigeration demand of the sub-region to be cooled, the area where the maximum refrigeration performance data is greater than the refrigeration demand of the sub-region to be cooled is regarded as an adjustable region;

[0078] When the maximum refrigeration performance data of the temperature intelligent control system is not greater than the refrigeration demand of the sub-region to be refrigerated, the area where the maximum refrigeration performance data is not greater than the refrigeration demand of the sub-region to be refrigerated is regarded as an uncontrollable area;

[0079] Construct a feasibility analysis result based on the controllable area and the uncontrollable area, and output the feasibility analysis result.

[0080] It should be noted that the refrigeration performance of each device can be predicted or directly obtained. The refrigeration performance data includes data such as the temperature drop amount per unit time, the heat drop amount per unit time, and the refrigeration temperature per unit time. The refrigeration demand of the sub-region to be refrigerated includes the refrigeration temperature required per unit time and the temperature drop amount per unit time. In fact, when some areas generate more heat, a higher refrigeration demand is required at this time, otherwise it is impossible to keep the temperature environment within the predetermined area range. When the maximum refrigeration performance data of the temperature intelligent control system is not greater than the refrigeration demand of the sub-region to be refrigerated, it means that the refrigeration does not meet the requirements. On the contrary, if it meets the requirements, the abnormal area can be analyzed through this method.

[0081] As Figure 2 shown, further, in this method, according to the feasibility analysis result, refrigeration is carried out on the sub-region to be refrigerated or relevant warning information is generated. Specifically:

[0082] S202: When the feasibility analysis result is an uncontrollable area, obtain the location of the temperature intelligent control system corresponding to the sub-region where it is located, and generate relevant warning information according to the location of the temperature intelligent control system corresponding to the sub-region where it is located;

[0083] S204: When the feasibility analysis result is a controllable area, initialize the refrigeration working parameters of the temperature intelligent control system, issue instructions to each sub-region based on the refrigeration working parameters of the temperature intelligent control system, and obtain the cooling characteristic data of the target area;

[0084] S206: Set a cooling characteristic data threshold. When the cooling characteristic data of the target area is greater than the cooling characteristic data threshold, output the refrigeration working parameters of the temperature intelligent control system, and perform temperature control according to the refrigeration working parameters of the temperature intelligent control system;

[0085] S208: When the cooling characteristic data of the target area is not greater than the cooling characteristic data threshold, readjust the refrigeration working parameters of the temperature intelligent control system until the cooling characteristic data of the target area is greater than the cooling characteristic data threshold.

[0086] It should be noted that the refrigeration working parameters of the temperature intelligent control system include the cold air supply volume per unit time, the chilled water flow volume per unit time, etc. Through this method, the refrigeration working parameters can be dynamically adjusted to make the refrigeration working parameters meet the predetermined requirements and improve the rationality of the temperature control system.

[0087] In addition, this method specifically further includes:

[0088] Obtain the historical refrigeration performance change data of the temperature intelligent control system, construct time stamps, sort the refrigeration performance change data based on the chronological order of the time stamps, and obtain the historical refrigeration performance change data based on the time series;

[0089] Construct a refrigeration performance feature prediction model based on a deep neural network, input the refrigeration performance change into the refrigeration performance feature prediction model for training, and obtain the trained refrigeration performance feature prediction model;

[0090] Obtain the refrigeration performance change data of each temperature intelligent control system within a preset time, and input the refrigeration performance change data of the temperature intelligent control system within the preset time into the trained refrigeration performance feature prediction model for prediction;

[0091] Obtain the refrigeration performance requirements of each region, through prediction, calculate the time nodes when the refrigeration performance of each temperature intelligent control system is lower than the refrigeration performance requirements, and give an early warning according to the time nodes when the refrigeration performance of the temperature intelligent control system is lower than the refrigeration performance requirements, and display it in a preset manner.

[0092] It should be noted that through this method, the refrigeration performance data of each region can be known in advance, so as to prevent in advance the time nodes when the refrigeration performance is lower than the refrigeration performance requirements, and carry out early replacement or analysis of the temperature intelligent control system.

[0093] In addition, this method further includes:

[0094] Obtain the temperature characteristic data of each sub-region in the target region at the current time stamp, obtain the temperature demand information of the user, introduce a genetic algorithm, and set the number of genetic generations based on the genetic algorithm;

[0095] Obtain the driving position required by the user, and initialize the recommended driving route of the user according to the temperature characteristic data of each sub-region in the target region at the current time stamp and the driving position required by the user;

[0096] Obtain the temperature characteristic data of the recommended driving route of each user, and judge whether the temperature characteristic data of the recommended driving route of the user meets the temperature demand information of the user;

[0097] When the temperature characteristic data of the recommended driving route of the user conforms to the user's temperature requirement information, the recommended driving route of the user is output and displayed in a preset manner;

[0098] When the temperature characteristic data of the recommended driving route of the user does not conform to the user's temperature requirement information, genetic operations are performed based on the number of generations, and the recommended driving route of the user is re-planned until it conforms to the user's temperature requirement information and is displayed in a preset manner.

[0099] It should be noted that when the target area is some public places and the user needs a cool route, at this time, when the temperature in some areas is not suitable, a driving route suitable for the user is planned through the genetic algorithm to improve the user experience in public places.

[0100] As Figure 3 shown, the second aspect of the present invention provides an intelligent control device 4 of a temperature intelligent control system, including a memory 41 and a processor 42. The memory 41 includes an intelligent control method program of the temperature intelligent control system. When the intelligent control method program of the temperature intelligent control system is executed by the processor 42, the steps of any one of the intelligent control methods of the temperature intelligent control system are realized.

[0101] As Figure 4 shown, the third aspect of the present invention provides a temperature intelligent control terminal, including:

[0102] A temperature tracking model construction module 10, which is responsible for obtaining the environmental characteristic data of the target area, constructing a temperature characteristic model according to the environmental characteristic data of the target area, and constructing a temperature tracking model based on a deep neural network;

[0103] A refrigeration analysis module 20, which is responsible for tracking and identifying the real-time heat generation characteristic data of each sub-area in the target area according to the temperature tracking model and the temperature characteristic model, obtaining the sub-areas to be refrigerated, and obtaining the refrigeration requirements of the sub-areas to be refrigerated;

[0104] A feasibility analysis module 30, which is responsible for obtaining the refrigeration performance data of the temperature intelligent control system of each sub-area, and performing feasibility analysis according to the refrigeration performance data of the temperature intelligent control system of each sub-area and the refrigeration requirements of the sub-areas to be refrigerated, and obtaining a feasibility analysis result;

[0105] A control analysis module 40, which is responsible for refrigerating the sub-areas to be refrigerated according to the feasibility analysis result or generating relevant warning information.

[0106] Further, in this device, obtaining the environmental characteristic data of the target area and constructing a temperature characteristic model according to the environmental characteristic data of the target area is specifically:

[0107] Obtain the layout diagram data in the target area, and construct a 3D model diagram of the target area through 3D modeling software based on the layout diagram data in the target area. Set sensors in each sub-area in the target area;

[0108] Obtain the environmental characteristic data of the target area through sensors, set the temperature gradient data diagram, and display the temperature characteristics of each sub-area in the target area according to the temperature gradient data diagram and the environmental characteristic data of the target area, and construct the temperature characteristic model of the current timestamp;

[0109] Obtain the temperature characteristic models of each timestamp, combine the temperature characteristic models of each timestamp, and display them in a preset manner to form a dynamic temperature characteristic model, which is used as the final temperature characteristic model and output.

[0110] Furthermore, in this device, a temperature tracking model is constructed based on a deep neural network. Specifically:

[0111] Construct a temperature tracking model based on a deep neural network, initialize the learning rate of the temperature tracking model and the mean square error of the stop condition, obtain the dynamic temperature characteristic model, and extract the model change characteristics of the dynamic temperature characteristic model;

[0112] Take the model change characteristics of each dynamic temperature characteristic model as a state vector, calculate the transition probability value of the state vector transferring to another state vector, and set the transition probability threshold;

[0113] When the transition probability value of the state vector transferring to another state vector is greater than the transition probability threshold, update the state vector to another state vector and update the model change characteristics of the dynamic temperature characteristic model;

[0114] When the transition probability value of the state vector transferring to another state vector is not greater than the transition probability threshold, keep the current state vector unchanged, input the model change characteristics of the dynamic temperature characteristic model into the temperature tracking model for learning based on learning. When the stop condition of the model is less than the mean square error of the stop condition, the temperature tracking model training is completed.

[0115] Furthermore, in this device, track and identify the real-time heat generation characteristic data of each sub-area in the target area according to the temperature tracking model and the temperature characteristic model, and obtain the sub-areas to be refrigerated. Specifically:

[0116] Obtain the temperature characteristic models within a preset time, and input the temperature characteristic models within the preset time into the temperature tracking model for identification and state update;

[0117] Through identification and status update, obtain the temperature feature model after status update, and based on the temperature feature model after status update, obtain the real-time heat generation feature data of each sub-region in the target area;

[0118] Set a threshold for the heat generation feature data, and determine whether the real-time heat generation feature data of the sub-region is greater than the threshold for the heat generation feature data. If it is less, then regard the corresponding region as a normal heat generation region;

[0119] When the real-time heat generation feature data of the sub-region is greater than the threshold for the heat generation feature data, then regard the corresponding region as a sub-region to be cooled.

[0120] Furthermore, in this device, obtain the refrigeration performance data of the temperature intelligent control system for each sub-region, and conduct a feasibility analysis based on the refrigeration performance data of the temperature intelligent control system for each sub-region and the refrigeration demand of the sub-region to be cooled, and obtain the result of the feasibility analysis. Specifically:

[0121] Obtain the refrigeration performance data of the temperature intelligent control system for each sub-region, and based on the refrigeration performance data of the temperature intelligent control system for each sub-region, obtain the maximum refrigeration performance data of the temperature intelligent control system for each sub-region;

[0122] Determine whether the maximum refrigeration performance data of the temperature intelligent control system is greater than the refrigeration demand of the sub-region to be cooled;

[0123] When the maximum refrigeration performance data of the temperature intelligent control system is greater than the refrigeration demand of the sub-region to be cooled, then regard the situation where the maximum refrigeration performance data is greater than the refrigeration demand of the sub-region to be cooled as an adjustable region;

[0124] When the maximum refrigeration performance data of the temperature intelligent control system is not greater than the refrigeration demand of the sub-region to be cooled, then regard the situation where the maximum refrigeration performance data is not greater than the refrigeration demand of the sub-region to be cooled as a non-adjustable region;

[0125] Construct the result of the feasibility analysis based on the adjustable region and the non-adjustable region, and output the result of the feasibility analysis.

[0126] Furthermore, in this device, cool the sub-region to be cooled according to the result of the feasibility analysis or generate relevant warning information. Specifically:

[0127] When the result of the feasibility analysis is a non-adjustable region, then obtain the location of the temperature intelligent control system corresponding to the sub-region where it is located, and generate relevant warning information based on the location of the temperature intelligent control system corresponding to the sub-region where it is located;

[0128] When the result of the feasibility analysis is an adjustable region, the refrigeration working parameters of the temperature intelligent control system are initialized, and each sub-region is commanded based on the refrigeration working parameters of the temperature intelligent control system to obtain the cooling characteristic data of the target region;

[0129] Set the cooling characteristic data threshold. When the cooling characteristic data of the target region is greater than the cooling characteristic data threshold, the refrigeration working parameters of the temperature intelligent control system are output, and temperature regulation is performed according to the refrigeration working parameters of the temperature intelligent control system;

[0130] When the cooling characteristic data of the target region is not greater than the cooling characteristic data threshold, the refrigeration working parameters of the temperature intelligent control system are readjusted until the cooling characteristic data of the target region is greater than the cooling characteristic data threshold.

[0131] The fourth aspect of the present invention provides a computer-readable storage medium, including the intelligent control method program of the temperature intelligent control system. When the intelligent control method program of the temperature intelligent control system is executed by a processor, the steps of the intelligent control method of the temperature intelligent control system in any one of the above are realized.

[0132] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed with each other can be through some interfaces. The indirect coupling or communication connection of the devices or units can be electrical, mechanical, or other forms.

[0133] The units described as separate components above may or may not be physically separated. The components shown as units may or may not be physical units; they can be located in one place or distributed to multiple network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0134] In addition, each functional unit in the embodiments of the present invention can be all integrated in one processing unit, or each unit can be separately used as one unit, or two or more units can be integrated in one unit; the above integrated units can be implemented in the form of hardware, or in the form of a combination of hardware and software functional units.

[0135] Those of ordinary skill in the art can understand that all or part of the steps to implement the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps including the above method embodiments; and the foregoing storage medium includes: various media such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0136] Alternatively, if the above integrated unit is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present invention, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of the various embodiments of the present invention. And the foregoing storage medium includes: various media such as mobile storage devices, ROM, RAM, magnetic disks, or optical discs that can store program codes.

[0137] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. An intelligent control method for an intelligent temperature control system, characterized in that, The method includes the following steps: Obtain the environmental characteristic data of the target area, construct a temperature characteristic model according to the environmental characteristic data of the target area, and construct a temperature tracking model based on a deep neural network; Track and identify the real-time heat generation characteristic data of each sub-area in the target area according to the temperature tracking model and the temperature characteristic model, obtain the sub-areas to be refrigerated, and obtain the refrigeration requirements of the sub-areas to be refrigerated; Obtain the refrigeration performance data of the temperature intelligent control system of each sub-area, and perform a feasibility analysis according to the refrigeration performance data of the temperature intelligent control system of each sub-area and the refrigeration requirements of the sub-areas to be refrigerated, and obtain the feasibility analysis result; Refrigerate the sub-areas to be refrigerated according to the feasibility analysis result or generate relevant warning information; Constructing a temperature tracking model based on a deep neural network specifically includes: Construct a temperature tracking model based on a deep neural network, initialize the learning rate of the temperature tracking model and the mean square error of the stop condition, obtain a dynamic temperature characteristic model, and extract the model change characteristics of the dynamic temperature characteristic model; Take the model change characteristics of each dynamic temperature characteristic model as a state vector, calculate the transition probability value of the state vector transferring to another state vector, and set the transition probability threshold; When the transition probability value of the state vector transferring to another state vector is greater than the transition probability threshold, update the state vector to another state vector and update the model change characteristics of the dynamic temperature characteristic model; When the transition probability value of the state vector transferring to another state vector is not greater than the transition probability threshold, keep the current state vector unchanged, input the model change characteristics of the dynamic temperature characteristic model into the temperature tracking model for learning based on the learning. When the stop condition of the model is less than the mean square error of the stop condition, the temperature tracking model training is completed; This method further includes: Obtain the temperature characteristic data of each sub-area in the target area at the current time stamp, obtain the temperature requirement information of the user, introduce a genetic algorithm, and set the number of genetic generations based on the genetic algorithm; Obtain the driving position required by the user, and initialize the recommended driving route of the user according to the temperature characteristic data of each sub-area in the target area at the current time stamp and the driving position required by the user; Obtain the temperature characteristic data of the recommended driving route of each user, and determine whether the temperature characteristic data of the recommended driving route of the user meets the temperature requirement information of the user; When the temperature characteristic data of the recommended driving route of the user meets the temperature requirement information of the user, output the recommended driving route of the user and display it in a preset manner; When the temperature characteristic data of the recommended driving route of the user does not meet the temperature requirement information of the user, perform genetic based on the number of genetic generations, re-plan the recommended driving route of the user until it meets the temperature requirement information of the user, and display it in a preset manner; This method further includes: Obtain the historical refrigeration performance change data of the temperature intelligent control system, construct time stamps, sort the refrigeration performance change data based on the chronological order of the time stamps, and obtain the historical refrigeration performance change data based on the time series; Construct a refrigeration performance feature prediction model based on a deep neural network, input the refrigeration performance change into the refrigeration performance feature prediction model for training, and obtain the trained refrigeration performance feature prediction model; Obtain the refrigeration performance change data of each temperature intelligent control system within a preset time, and input the refrigeration performance change data of the temperature intelligent control system within the preset time into the trained refrigeration performance feature prediction model for prediction; Obtain the refrigeration performance requirements of each region, through prediction, calculate the time nodes when the refrigeration performance of each temperature intelligent control system is lower than the refrigeration performance requirements, and give an alarm according to the time nodes when the refrigeration performance of the temperature intelligent control system is lower than the refrigeration performance requirements, and display it in a preset manner.

2. The intelligent control method of an intelligent temperature control system according to claim 1, characterized in that, Obtain the environmental characteristic data of the target region, and construct a temperature characteristic model according to the environmental characteristic data of the target region, specifically: Obtain the layout map data of the target region, and construct a three-dimensional model diagram of the target region through three-dimensional modeling software according to the layout map data of the target region, and set sensors in each sub-region of the target region; Obtain the environmental characteristic data of the target region through the sensors, set a temperature gradient data map, and display the temperature characteristics of each sub-region in the target region according to the temperature gradient data map and the environmental characteristic data of the target region, and construct a temperature characteristic model of the current time stamp based on the three-dimensional model diagram of the target region; Obtain the temperature characteristic models of each time stamp, combine the temperature characteristic models of each time stamp, and display them in a preset manner to form a dynamic temperature characteristic model, which is used as the final temperature characteristic model and output.

3. The intelligent control method of an intelligent temperature control system according to claim 1, characterized in that Track and identify the real-time heat generation characteristic data of each sub-region in the target region according to the temperature tracking model and the temperature characteristic model, and obtain the sub-regions to be refrigerated, specifically: Obtain the temperature characteristic models within a preset time, and input the temperature characteristic models within the preset time into the temperature tracking model for identification and status update; Through identification and status update, obtain the temperature characteristic model after status update, and obtain the real-time heat generation characteristic data of each sub-region in the target region according to the temperature characteristic model after status update; Set a heat generation characteristic data threshold, and judge whether the real-time heat generation characteristic data of the sub-region is greater than the heat generation characteristic data threshold. If it is less, the corresponding region is regarded as a normal heat generation region; When the real-time heat generation characteristic data of the sub-region is greater than the heat generation characteristic data threshold, the corresponding region is regarded as a sub-region to be refrigerated.

4. The intelligent control method of an intelligent temperature control system according to claim 1, characterized in that Obtain the refrigeration performance data of the temperature intelligent control system of each sub-region, and conduct a feasibility analysis according to the refrigeration performance data of the temperature intelligent control system of each sub-region and the refrigeration requirements of the sub-region to be refrigerated, and obtain the feasibility analysis result, specifically: Obtain the refrigeration performance data of each sub-region temperature intelligent control system, and obtain the maximum refrigeration performance data of each sub-region temperature intelligent control system according to the refrigeration performance data of each sub-region temperature intelligent control system; Judge whether the maximum refrigeration performance data of the temperature intelligent control system is greater than the refrigeration demand of the sub-region to be refrigerated; When the maximum refrigeration performance data of the temperature intelligent control system is greater than the refrigeration demand of the sub-region to be refrigerated, then regard the maximum refrigeration performance data greater than the refrigeration demand of the sub-region to be refrigerated as the adjustable region; When the maximum refrigeration performance data of the temperature intelligent control system is not greater than the refrigeration demand of the sub-region to be refrigerated, then regard the maximum refrigeration performance data not greater than the refrigeration demand of the sub-region to be refrigerated as the non-adjustable region; Construct a feasibility analysis result based on the adjustable region and the non-adjustable region, and output the feasibility analysis result.

5. The intelligent control method of an intelligent temperature control system according to claim 1, characterized in that, Refrigerate the sub-region to be refrigerated or generate relevant warning information according to the feasibility analysis result, specifically: When the feasibility analysis result is a non-adjustable region, obtain the location of the temperature intelligent control system corresponding to the sub-region where it is located, and generate relevant warning information according to the location of the temperature intelligent control system corresponding to the sub-region where it is located; When the feasibility analysis result is an adjustable region, initialize the refrigeration working parameters of the temperature intelligent control system, issue commands to each sub-region based on the refrigeration working parameters of the temperature intelligent control system, and obtain the cooling characteristic data of the target region; Set a cooling characteristic data threshold. When the cooling characteristic data of the target region is greater than the cooling characteristic data threshold, output the refrigeration working parameters of the temperature intelligent control system, and perform temperature regulation according to the refrigeration working parameters of the temperature intelligent control system; When the cooling characteristic data of the target region is not greater than the cooling characteristic data threshold, readjust the refrigeration working parameters of the temperature intelligent control system until the cooling characteristic data of the target region is greater than the cooling characteristic data threshold.

6. An intelligent control device for an intelligent temperature control system, characterized in that, It includes a memory and a processor. The memory includes an intelligent control method program for the temperature intelligent control system. When the intelligent control method program for the temperature intelligent control system is executed by the processor, the steps of the intelligent control method for the temperature intelligent control system as described in any one of claims 1-5 are implemented.

7. An intelligent temperature control terminal, characterized in that, It includes: A temperature tracking model construction module, responsible for obtaining the environmental characteristic data of the target region, constructing a temperature characteristic model according to the environmental characteristic data of the target region, and constructing a temperature tracking model based on a deep neural network; A refrigeration analysis module, responsible for tracking and identifying the real-time heat generation characteristic data of each sub-region in the target region according to the temperature tracking model and the temperature characteristic model, obtaining the sub-region to be refrigerated, and obtaining the refrigeration demand of the sub-region to be refrigerated; A feasibility analysis module, responsible for obtaining the refrigeration performance data of each sub-region temperature intelligent control system, and conducting a feasibility analysis based on the refrigeration performance data of each sub-region temperature intelligent control system and the refrigeration demand of the sub-region to be refrigerated, so as to obtain the feasibility analysis result; A control analysis module, responsible for refrigerating the sub-region to be refrigerated according to the feasibility analysis result or generating relevant warning information; Construct a temperature tracking model based on a deep neural network, specifically: Construct a temperature tracking model based on a deep neural network, and initialize the learning rate of the temperature tracking model and the mean square error of the stopping condition to obtain a dynamic temperature feature model, and extract the model change features of the dynamic temperature feature model; Take the model change features of each dynamic temperature feature model as a state vector, calculate the transition probability value of the state vector transferring to another state vector, and set the transition probability threshold; When the transition probability value of the state vector transferring to another state vector is greater than the transition probability threshold, update the state vector to another state vector and update the model change features of the dynamic temperature feature model; When the transition probability value of the state vector transferring to another state vector is not greater than the transition probability threshold, keep the current state vector unchanged, input the model change features of the dynamic temperature feature model into the temperature tracking model for learning based on the learning. When the stopping condition of the model is less than the mean square error of the stopping condition, the temperature tracking model training is completed; This method further includes: Obtain the temperature feature data of each sub-region in the target region at the current timestamp, and obtain the temperature demand information of the user. Introduce a genetic algorithm and set the number of genetic generations based on the genetic algorithm; Obtain the driving position required by the user, and initialize the recommended driving route of the user according to the temperature feature data of each sub-region in the target region at the current timestamp and the driving position required by the user; Obtain the temperature feature data of the recommended driving route of each user, and judge whether the temperature feature data of the recommended driving route of the user meets the temperature demand information of the user; When the temperature feature data of the recommended driving route of the user meets the temperature demand information of the user, output the recommended driving route of the user and display it in a preset manner; When the temperature feature data of the recommended driving route of the user does not meet the temperature demand information of the user, conduct genetic based on the number of genetic generations, re-plan the recommended driving route of the user until it meets the temperature demand information of the user, and display it in a preset manner; This method further includes: Obtain the historical refrigeration performance change data of the temperature intelligent control system, and construct timestamps. Sort the refrigeration performance change data according to the chronological order of the timestamps to obtain the historical refrigeration performance change data based on the time series; Construct a refrigeration performance feature prediction model based on a deep neural network, input the refrigeration performance change into the refrigeration performance feature prediction model for training, and obtain the trained refrigeration performance feature prediction model; Obtain the cooling performance change data of each temperature intelligent control system within the preset time, and input the cooling performance change data of the temperature intelligent control system within the preset time into the trained cooling performance feature prediction model for prediction; Obtain the cooling performance requirements of each area, through prediction, calculate the time nodes when the cooling performance of each temperature intelligent control system is lower than the cooling performance requirements, and give early warnings according to the time nodes when the cooling performance of the temperature intelligent control system is lower than the cooling performance requirements, and display them in a preset manner.

8. A computer-readable storage medium, characterized in that, It includes an intelligent control method program of the temperature intelligent control system. When the intelligent control method program of the temperature intelligent control system is executed by a processor, the steps of the intelligent control method of the temperature intelligent control system as described in any one of claims 1-5 are implemented.

Images