Control method and device of refrigeration equipment and refrigeration equipment

Abstract

The invention discloses a control method and device of refrigeration equipment and the refrigeration equipment, and belongs to the technical field of refrigeration equipment. The control method of the refrigeration equipment comprises the steps that the actual environment temperature, collected by a temperature sensor, of the environment where the refrigeration equipment is located and the actual environment humidity collected by a humidity sensor are obtained, the time module outputs actual solar term information; the positioning module outputs actual geographic position information of the refrigeration equipment; inputting the actual environment temperature, the actual environment humidity, the actual solar term information and the actual geographic position information into a target neural network model, and obtaining target parameter information output by the target neural network model; and based on the target parameter information, the compressor is controlled to operate. According to the control method of the refrigeration equipment, the use experience of a user in different solar term environments is improved, manual intervention of the user is not needed, and the comfort degree and the satisfaction degree of the user are improved.

Description

Technical Field

[0001] The present application belongs to the technical field of refrigeration equipment, and in particular relates to a control method and device for refrigeration equipment, and refrigeration equipment. Background Art

[0002] With the improvement of people's living standards, air conditioners have become essential appliances in homes and offices. Related technologies generally use on-off control based on fixed temperature thresholds or manual switching through preset limited operating modes (such as cooling / heating / dehumidification). The control logic in these technologies is based solely on immediate environmental parameters and lacks a mechanism to link them with other characteristics. Users must manually adjust the mode or rely on simple timing functions to switch between modes, which is cumbersome and provides a poor user experience. Summary of the Invention

[0003] This application aims to solve at least one of the technical problems existing in the related art. To this end, this application proposes a control method, device, and refrigeration device for refrigeration equipment, which improves the user experience in different solar terms without manual user intervention, thereby improving user comfort and satisfaction.

[0004] In a first aspect, the present application provides a control method for a refrigeration device, wherein the refrigeration device includes a temperature sensor, a humidity sensor, a time module, a positioning module, and a compressor; the method includes:

[0005] Acquire the actual ambient temperature of the environment in which the refrigeration device is located, as collected by the temperature sensor, the actual ambient humidity, as collected by the humidity sensor, the actual solar term information output by the time module, and the actual geographical location information of the refrigeration device, as output by the positioning module;

[0006] Inputting the actual ambient temperature, the actual ambient humidity, the actual solar term information, and the actual geographical location information into a target neural network model, and obtaining target parameter information output by the target neural network model;

[0007] Based on the target parameter information, the operation of the compressor is controlled.

[0008] According to the control method of the refrigeration equipment provided in the embodiment of the present application, by pre-training the target neural network model, it is possible to output target parameter information based on the real-time monitored temperature, humidity, solar term information and geographical location information, thereby controlling the operation of the compressor based on the target parameter information, and establishing an association mechanism between the target parameter information and the multi-dimensional features. It is possible to automatically adjust the operation of the refrigeration equipment according to the climatic characteristics of the user's location, thereby improving the user's usage experience in different solar term environments without the need for manual intervention by the user, thereby improving the user's comfort and satisfaction.

[0009] In a control method for a refrigeration device according to an embodiment of the present application, the target neural network model is trained based on the following steps:

[0010] Acquire a training data set, wherein the training data set includes a plurality of training samples, each of the training samples includes sample temperature data, sample humidity data, sample solar term information, sample geographic location information, and sample parameter information;

[0011] With the goal of learning the correlation between the sample temperature data, the sample humidity data, the sample solar term information and the sample geographic location information and the sample parameter information, and outputting predicted parameter information, a neural network model is trained based on the training data set to obtain the target neural network model.

[0012] In a control method for a refrigeration device according to an embodiment of the present application, obtaining a training data set includes:

[0013] Obtain sample temperature data, sample humidity data, sample solar term information, sample geographic location information and sample parameter information;

[0014] A clustering algorithm is used to process the sample temperature data, the sample humidity data, the sample solar term information, the sample geographic location information and the sample parameter information to obtain a multi-cluster data set, so as to obtain the training data set based on the multi-cluster data set; each cluster of the data set includes sample temperature data, sample humidity data, sample solar term information and sample geographic location information, and the label of each cluster of the data set is the sample parameter information corresponding to the data set.

[0015] A control method for a refrigeration device according to an embodiment of the present application, for obtaining the sample parameter information, includes:

[0016] Based on the date information and sample parameter information corresponding to adjacent sample solar term information, the sample parameter information corresponding to each date between the adjacent sample solar term information is interpolated to obtain the sample parameter information corresponding to each date between the adjacent sample solar term information.

[0017] In a control method for a refrigeration device according to an embodiment of the present application, obtaining a training data set includes:

[0018] Acquiring user behavior characteristic data, wherein the user behavior characteristic data is historical parameter information set by the user when using the refrigeration device under conditions of historical temperature data, historical humidity data, historical solar term information, and historical geographic location information;

[0019] The training data set is updated based on the historical temperature data, the historical humidity data, the historical solar term information, the historical geographic location information, and the historical parameter information.

[0020] In a control method for a refrigeration device according to an embodiment of the present application, the training of a neural network model based on the training data set to obtain the target neural network model includes:

[0021] Using a particle swarm optimization algorithm to update the initial network parameters of the neural network model;

[0022] Taking the minimum value of the target loss function as the goal, the updated neural network model is trained based on the training data set to obtain the target neural network model.

[0023] In a control method for a refrigeration device according to an embodiment of the present application, controlling the operation of the compressor based on the target parameter information includes:

[0024] Obtain the first parameter information input by the user;

[0025] When the difference information between the target parameter information and the first parameter information is less than a target difference threshold, controlling the operation of the compressor based on the target parameter information;

[0026] When the difference information is greater than or equal to the target difference threshold, the target parameter information is updated based on the first parameter information, and the operation of the compressor is controlled based on the updated target parameter information.

[0027] In a second aspect, the present application provides a control device for a refrigeration device, the refrigeration device including a temperature sensor, a humidity sensor, a time module, a positioning module, and a compressor; the device includes:

[0028] A first processing module is configured to obtain the actual ambient temperature of the environment in which the refrigeration device is located, as collected by the temperature sensor, the actual ambient humidity, as collected by the humidity sensor, the actual solar term information output by the time module, and the actual geographical location information of the refrigeration device, as output by the positioning module;

[0029] a second processing module, configured to input the actual ambient temperature, the actual ambient humidity, the actual solar term information, and the actual geographical location information into a target neural network model, and obtain target parameter information output by the target neural network model;

[0030] A third processing module is configured to control the operation of the compressor based on the target parameter information.

[0031] According to the control device of the refrigeration equipment provided in the embodiment of the present application, through the pre-training of the target neural network model, it is possible to output target parameter information based on the real-time monitored temperature, humidity, solar term information and geographical location information, thereby controlling the operation of the compressor based on the target parameter information, and establishing an association mechanism between the target parameter information and the multi-dimensional features. It is possible to automatically adjust the operation of the refrigeration equipment according to the climatic characteristics of the user's location, thereby improving the user's usage experience in different solar term environments without the need for manual intervention by the user, thereby improving the user's comfort and satisfaction.

[0032] In a third aspect, the present application provides a refrigeration device, comprising:

[0033] indoor subject;

[0034] Outdoor subject;

[0035] A temperature sensor is installed inside the housing of the indoor body;

[0036] A humidity sensor is installed inside the housing of the indoor body;

[0037] A time module is installed inside the housing of the indoor main body;

[0038] A positioning module is installed inside the housing of the indoor main body;

[0039] A compressor installed inside the housing of the outdoor main body;

[0040] The refrigeration device operates based on the control method for the refrigeration device according to the first aspect.

[0041] According to the refrigeration equipment provided in the embodiment of the present application, through the pre-training target neural network model, it is possible to output target parameter information based on the real-time monitored temperature, humidity, solar term information and geographical location information, thereby controlling the operation of the compressor based on the target parameter information, and establishing an association mechanism between the target parameter information and the multi-dimensional features. It is possible to automatically adjust the operation of the refrigeration equipment according to the climatic characteristics of the user's location, thereby improving the user's usage experience in different solar term environments without the need for manual intervention by the user, thereby improving the user's comfort and satisfaction.

[0042] In a fourth aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the control method for the refrigeration equipment as described in the first aspect above is implemented.

[0043] In a fifth aspect, the present application provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the control method for the refrigeration equipment as described in the first aspect above.

[0044] In a sixth aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the control method for the refrigeration equipment as described in the first aspect above.

[0045] The above one or more technical solutions in the embodiments of the present application have at least one of the following technical effects:

[0046] By pre-training the target neural network model, it is possible to output target parameter information based on the real-time monitored temperature, humidity, solar term information and geographic location information, thereby controlling the operation of the compressor based on the target parameter information. A correlation mechanism between the target parameter information and multi-dimensional features is established, which can automatically adjust the operation of the refrigeration equipment according to the climatic characteristics of the user's location, thereby improving the user's usage experience in different solar term environments without the need for manual user intervention, thereby improving the user's comfort and satisfaction.

[0047] Furthermore, clustering analysis of sample data through clustering algorithms can achieve automatic classification of samples and effectively identify sample groups with different control strategies (i.e., sample parameter information) under unsupervised conditions, thereby providing training data sets for training neural network models.

[0048] Furthermore, by interpolating the blank dates between two adjacent solar terms, we can obtain the sample parameter information corresponding to each blank date. Combined with dynamic adjustment rules and special scenario optimization, the flexibility and robustness of the system are enhanced while retaining the solar term control strategy. By interpolating the sample parameter information, the parameter information of each date can be smoothly transitioned, avoiding sudden changes in user perception and improving the user experience.

[0049] Furthermore, by obtaining the user's behavioral characteristic data and obtaining a training data set based on the user's behavioral characteristic data, the database can be updated according to the user's personalized settings and personal preferences, and analysis and prediction can be performed based on a large amount of historical data. The target neural network model can be continuously optimized so that the parameters output by the target neural network model are more in line with the user's personalized needs, thereby improving the accuracy and reliability of the recommended control method and improving the user's usage experience and comfort.

[0050] Furthermore, by updating the initial network parameters of the neural network model through the particle swarm optimization algorithm, the neural network model can be prevented from falling into the local optimal solution during the training process, the generalization ability and convergence speed of the model are improved, and the global search ability and training efficiency of the neural network model are improved. Then, the neural network model is trained with the minimum value of the target loss function as the goal, and the model can be further locally optimized, thereby improving the rationality of the model's control strategy for the generated refrigeration equipment.

[0051] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become obvious from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0053] Figure 1 This is one of the flow charts of the control method of the refrigeration equipment provided in the embodiment of the present application;

[0054] Figure 2 This is a schematic diagram of the principle of the control method of the refrigeration equipment provided in the embodiment of the present application;

[0055] Figure 3 This is the second flow chart of the control method of the refrigeration equipment provided in the embodiment of the present application;

[0056] Figure 4 This is the third flow chart of the control method of the refrigeration equipment provided in the embodiment of the present application;

[0057] Figure 5 This is the fourth flow chart of the control method of the refrigeration equipment provided in the embodiment of the present application;

[0058] Figure 6 is a schematic structural diagram of a control device for a refrigeration device provided in an embodiment of the present application;

[0059] Figure 7 It is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0060] The following will be combined with the accompanying drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of this application.

[0061] The terms "first," "second," and the like in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of this application can be implemented in an order other than that illustrated or described herein, and that the objects distinguished by "first," "second," and the like are generally of the same type, and do not limit the number of objects; for example, the first object can be one or more. In addition, the term "and / or" in the specification and claims refers to at least one of the connected objects, and the character " / " generally indicates that the objects connected are in an "or" relationship.

[0062] The following, in conjunction with the accompanying drawings, describes in detail the control method for refrigeration equipment, the control device for refrigeration equipment, the electronic device, and the readable storage medium provided in the embodiments of the present application through specific embodiments and their application scenarios.

[0063] The control method for the refrigeration equipment may be applied to a terminal, and may be specifically executed by hardware or software in the terminal.

[0064] The terminal includes, but is not limited to, a portable communication device such as a mobile phone or tablet computer having a touch-sensitive surface (e.g., a touch screen display and / or a touch pad). It should also be understood that, in some embodiments, the terminal may not be a portable communication device, but a desktop computer having a touch-sensitive surface (e.g., a touch screen display and / or a touch pad).

[0065] In the following embodiments, a terminal including a display and a touch-sensitive surface is described. However, it should be understood that the terminal may include one or more other physical user interface devices such as a physical keyboard, a mouse, and a joystick.

[0066] The control method for a refrigeration device provided in an embodiment of the present application may be executed by an electronic device or a functional module or functional entity in the electronic device that can implement the control method for the refrigeration device. The electronic devices mentioned in the embodiment of the present application include but are not limited to mobile phones, tablet computers, computers, cameras, and wearable devices. The control method for a refrigeration device provided in an embodiment of the present application is described below using an electronic device as an example of the execution entity.

[0067] like Figure 1 As shown, the control method of the refrigeration equipment includes: step 110, step 120 and step 130.

[0068] Refrigeration equipment can include wall-mounted air conditioners, floor-standing air conditioners, central air conditioners or window air conditioners, etc.

[0069] The refrigeration equipment includes a temperature sensor, a humidity sensor, a time module, a positioning module and a compressor.

[0070] The control system can be connected to the temperature sensor, humidity sensor, time module, positioning module and compressor respectively.

[0071] The temperature sensor, humidity sensor, time module and positioning module can send the data they collect to the control system.

[0072] The control system may include a cloud server.

[0073] Temperature sensors can be used to monitor ambient temperature in real time.

[0074] Humidity sensors can be used to detect the ambient humidity level.

[0075] The time module is used to obtain date information and time information, and the time module may include a real-time clock (RTC).

[0076] The positioning module is used to determine the geographical location of the refrigeration equipment, and the positioning module may include a GPS module.

[0077] The compressor compresses the refrigerant to transfer heat.

[0078] Step 110: Acquire the actual ambient temperature of the environment in which the refrigeration equipment is located as collected by the temperature sensor, the actual ambient humidity as collected by the humidity sensor, the actual solar term information output by the time module, and the actual geographical location information of the refrigeration equipment as output by the positioning module;

[0079] In this step, the actual ambient temperature is the actual temperature of the environment in which the refrigeration equipment is located.

[0080] When the actual ambient temperature is different, the target temperature that the air conditioner needs to set may also be different. For example, when the outside temperature is high, the air conditioner can set a lower indoor target temperature to provide a cooling effect. When the outside temperature is low, the air conditioner may need heating and the target temperature can be set to a higher temperature.

[0081] The actual ambient humidity is the humidity information of the environment where the refrigeration equipment is located.

[0082] When the actual ambient humidity is different, the target humidity that the air conditioner needs to set may also be different. For example, in an environment with high humidity, the air conditioner can turn on the dehumidification function to reduce indoor humidity and improve comfort. In an environment with low humidity, the dehumidification function can be turned off to avoid excessive drying.

[0083] The time module can obtain the date information corresponding to the current collection time to determine the actual solar term information based on the date information.

[0084] For example, the actual solar term information of the current solar term can be determined based on the Gregorian calendar date range of the 24 solar terms (error ±1 day).

[0085] The positioning module can obtain the latitude and longitude information of the location of the refrigeration equipment to output the actual geographical location information of the refrigeration equipment.

[0086] Different regions have different climate characteristics and user habits. For example, the Jianghuai region has a plum rain season, so the air conditioner needs to strengthen the dehumidification function to reduce indoor humidity and avoid problems such as clothing difficult to dry and furniture moldy due to excessive humidity; due to its special terrain, the Sichuan Basin has a significant wet and cold climate in winter, so the air conditioner needs to provide both heating and dehumidification functions to increase the indoor temperature and reduce humidity to create a comfortable indoor environment.

[0087] Step 120: Input the actual ambient temperature, actual ambient humidity, actual solar term information, and actual geographic location information into the target neural network model to obtain target parameter information output by the target neural network model;

[0088] In this step, the target neural network model can be trained based on the sample climate data and the sample labels corresponding to the sample climate data, wherein the sample climate data may include sample ambient temperature, sample ambient humidity, sample solar term information and sample geographic location information.

[0089] The target parameter information is output by the target neural network and is used to control the parameters of the refrigeration equipment operation. The target parameter information may include temperature, humidity, and fresh air parameters.

[0090] Step 130: Control the operation of the compressor based on the target parameter information.

[0091] In this step, when the target parameter information corresponding to the current environment is determined, the operation of the compressor can be controlled based on the target parameter information.

[0092] For example, the set temperature, set humidity, and set fresh air parameters of the refrigeration equipment can be adjusted to target parameter information, so that the compressor operation can be controlled to make the indoor climate data reach the set value.

[0093] According to the control method of the refrigeration equipment provided in the embodiment of the present application, by pre-training the target neural network model, it is possible to output target parameter information based on the real-time monitored temperature, humidity, solar term information and geographical location information, thereby controlling the operation of the compressor based on the target parameter information, and establishing an association mechanism between the target parameter information and the multi-dimensional features. It is possible to automatically adjust the operation of the refrigeration equipment according to the climatic characteristics of the user's location, thereby improving the user's usage experience in different solar term environments without the need for manual intervention by the user, thereby improving the user's comfort and satisfaction.

[0094] like Figure 3 As shown, in some embodiments, the target neural network model can be trained based on the following steps:

[0095] Get the training dataset;

[0096] With the goal of learning the correlation between sample temperature data, sample humidity data, sample solar term information and sample geographic location information and sample parameter information, and outputting predicted parameter information, a neural network model is trained based on the training data set to obtain a target neural network model.

[0097] In this embodiment, the training data set includes multiple training samples.

[0098] Each training sample includes sample temperature data, sample humidity data, sample solar term information, sample geographic location information and sample parameter information.

[0099] The training data set may include sample data input by the user, or may also include a public meteorological data set, which may be selected based on user needs and is not limited in this application.

[0100] The training dataset can be used to characterize the relationship between different climate conditions and parameter information.

[0101] The target neural network model can be learned through a three-layer or multi-layer structure.

[0102] For example, the feature extraction layer can be used to identify the hot, cold, and dry patterns and seasonal geographical laws corresponding to the sample climate data, and then the fusion decision layer can be used to determine which factors are more important in the current scenario (such as humidity priority in the rainy season and temperature priority in the cold winter). Finally, the parameter prediction layer can output the optimal parameter combination based on comprehensive judgment.

[0103] Continue to refer Figure 3 In some embodiments, obtaining a training data set may include:

[0104] Obtain sample temperature data, sample humidity data, sample solar term information, sample geographic location information and sample parameter information;

[0105] A clustering algorithm is used to process sample temperature data, sample humidity data, sample solar term information, sample geographic location information and sample parameter information to obtain a multi-cluster data set, so as to obtain a training data set based on the multi-cluster data set.

[0106] In this embodiment, multiple cluster data sets can be obtained after clustering processing. Each cluster data set includes sample temperature data, sample humidity data, sample solar term information and sample geographic location information. The label of each cluster data set is the sample parameter information corresponding to the data set.

[0107] Clustering algorithms may include K-means, DBSCAN, or hierarchical clustering, etc., which can be selected based on user needs and are not limited in this application.

[0108] By clustering the sample temperature data, sample humidity data, sample solar term information, sample geographic location information and sample parameter information, we can discover the inherent distribution structure of the data. By clustering the climate data of different solar terms and geographic locations, we can achieve automatic classification of samples.

[0109] You can obtain sample temperature data, sample humidity data, sample solar term information, and sample geographic location information, and set different parameter information for different temperatures, humidity, solar terms, and geographic locations.

[0110] In the actual implementation process, the K-means clustering algorithm can be used to process the sample temperature data, sample humidity data, sample solar term information, sample geographic location information and sample parameter information to obtain a multi-cluster data set, and then a training data set can be obtained based on the multi-cluster data set. The core idea of the K-means algorithm is to minimize the square error between the samples within the cluster and the cluster center. Its objective function can be defined as:

[0111]

[0112] Among them, x is the sample data, μ j is the centroid of the jth cluster, C j is the set of samples in the jth cluster. The algorithm first randomly selects K initial centroids, and then uses the Euclidean distance to assign each sample to the cluster with the nearest centroid. The Euclidean distance calculation formula is:

[0113]

[0114] Where n represents the dimension of the sample features. The centroid is updated by calculating the mean of all samples in each cluster, that is:

[0115]

[0116] The steps of sample allocation and centroid update are iterated continuously until the centroid position change is lower than the preset threshold or the maximum number of iterations is reached.

[0117] According to the control method of refrigeration equipment provided in the embodiment of the present application, cluster analysis of sample data is performed through a clustering algorithm, which can realize automatic classification of samples and effectively identify sample groups of different control strategies (i.e., sample parameter information) under unsupervised conditions, thereby providing a training data set for training the neural network model.

[0118] In actual implementation, when the outside temperature is high, the air conditioner needs to set a lower indoor target temperature to provide a cooling effect; when the outside temperature is low, the air conditioner may need to heat and a higher indoor target temperature can be set. The correlation between the sample temperature data and the sample parameter information is shown in Table 1:

[0119] Table 1

[0120]

[0121] When the sample temperature data is below -5°C, the outside temperature is very low and the indoor temperature needs to be kept warm. The sample parameter information (such as the air conditioner set temperature) can be set to 25°C to 26°C.

[0122] When the sample temperature data is -5°C to 0°C, the outside temperature is very low and the indoor temperature needs to be kept relatively warm. The sample parameter information (such as the air conditioner set temperature) can be set to 24°C to 26°C.

[0123] When the sample temperature data is 0℃ to 5℃, it is still cold but slightly warmer than the previous interval. The sample parameter information (such as the air conditioner set temperature) can be set to 23℃ to 25℃.

[0124] When the sample temperature data is 5℃ to 10℃, the outside temperature begins to approach the human comfort zone, but the indoor temperature still needs to be kept warm. The sample parameter information (such as the air conditioner set temperature) can be set to 22℃ to 24℃.

[0125] When the sample temperature data is 10°C to 15°C, which is relatively mild spring or autumn weather, the sample parameter information (such as the air conditioner set temperature) can be set to 21°C to 23°C.

[0126] When the sample temperature data is 15℃ to 20℃, it is close to the human body's comfortable temperature, but slight heating may still be required to keep the indoor temperature stable. The sample parameter information (such as the air conditioner set temperature) can be set to 20℃ to 22℃.

[0127] When the sample temperature data is 20℃ to 25℃, the outdoor temperature is comfortable and the indoor temperature may not require heating or only requires slight cooling. The sample parameter information (such as the air conditioning set temperature) can be set to 20℃ to 22℃.

[0128] When the sample temperature data is 25°C to 30°C, you start to feel hot and need to cool down. You can set the sample parameter information (such as the air conditioner set temperature) to 22°C to 24°C.

[0129] When the sample temperature data is 30°C to 35°C, it is very hot and requires a stronger cooling effect. The sample parameter information (such as the air conditioner set temperature) can be set to 22°C to 23°C.

[0130] When the sample temperature data is above 35°C, which is extremely high temperature and requires maximum cooling effect, the sample parameter information (such as the air conditioner set temperature) can be set to around 22°C.

[0131] In a high humidity environment, the air conditioner needs to turn on the dehumidification function to reduce indoor humidity and improve comfort. In a low humidity environment, the dehumidification function may not need to be turned on to avoid excessive drying. The correlation between the sample humidity data and the sample parameter information is shown in Table 2:

[0132] Table 2

[0133] External humidity (%) 0-30 30-40 40-50 50-60 60-70 70-80 80-100 Target humidity (%) 30-40 40 40-50 50 50-60 ＜60 ＜60

[0134] When the sample humidity data is 0% to 30%, it may cause dry skin, throat discomfort and static electricity problems. The sample parameter information (such as the air conditioner setting humidity) can be set to 30% to 40%.

[0135] When the sample humidity data is 30% to 40%, it is relatively dry but still within a comfortable range. The sample parameter information (such as the air conditioner set humidity) can be set to about 40%.

[0136] When the sample humidity data is between 40% and 50%, it is an ideal humidity range, which helps to maintain the comfort of the indoor environment. The sample parameter information (such as the air conditioner setting humidity) can be set to maintain the current humidity.

[0137] When the sample humidity data is 50% to 60%, it is still comfortable, but close to the upper limit. Care should be taken to prevent mold growth. The sample parameter information (such as the air conditioner set humidity) can be set to around 50%.

[0138] When the sample humidity data is 60% to 70%, the humidity is high and may cause mold growth, odor and discomfort. The sample parameter information (such as the air conditioner set humidity) can be set between 50% and 60%.

[0139] When the sample humidity data is 70% to 80%, it is very humid and requires active dehumidification. The sample parameter information (such as the air conditioner set humidity) can be set to below 60%.

[0140] When the sample humidity data is 80% to 100%, it is extremely humid and may cause serious mold problems and deterioration of the indoor environment. The sample parameter information (such as the air conditioner set humidity) can be set to below 60%.

[0141] Different regions have different climate characteristics and user habits. For example, the Jianghuai region experiences the plum rain season, and air conditioners need to enhance their dehumidification function to reduce indoor humidity and avoid problems such as clothing not drying easily and furniture becoming moldy due to excessive humidity. Due to its unique topography, the Sichuan Basin has a significant wet and cold climate in winter. Air conditioners need to provide both heating and dehumidification functions to increase indoor temperature and reduce humidity to create a comfortable indoor environment. The correlation between sample geographic location information and sample parameter information is shown below:

[0142] The high-humidity climate zones in the south (such as the Yangtze River Basin and areas to the south, including the Sichuan Basin and the southeast coast) have the risk of mold during high temperatures and high humidity in summer and the plum rain and typhoon season. In summer, operation is centered on cooling, and the temperature can be set in the range of 24-26°C. The powerful dehumidification function can be simultaneously activated to control the humidity below 55%, and automatic ventilation can be triggered for 3-5 minutes every hour to enhance air circulation. In winter, heating can be based on 18-22°C, and the humidity threshold is set to 50%. In humid and cold areas such as the Sichuan Basin, the auxiliary dehumidification module can be linked to avoid physical discomfort caused by low temperature and high humidity.

[0143] The northern hot and dry climate zone (such as the Yellow River Basin to the North China Plain) is characterized by hot and dry summers with little rain, and cold and windy winters. The cooling temperature can be maintained at 24-26°C in summer. To avoid excessive dryness, the lower humidity limit is set to 40%, and low-speed air supply is used to balance cooling and humidity retention. At night, the energy-saving mode is automatically switched to and the temperature is relaxed by 1-2°C to reduce energy consumption. The heating temperature is set at 18-24°C in winter (can be adjusted higher in the northeast), and the humidification function is started simultaneously to maintain a humidity of more than 35%. In the morning, when the outdoor temperature is below 0°C, preheating is performed to alleviate the impact of extreme temperature differences.

[0144] Alpine and dry areas (such as the northern part of Northeast China, Northwest China and the Qinghai-Tibet Plateau) are characterized by low temperatures, dryness and thin air throughout the year. In winter, the heating standard can be 20-24°C. The humidification module runs continuously to ensure that the humidity is not lower than 30%. The fresh air oxygenation function is added in areas above 2,000 meters above sea level. During the short cooling period in summer, the temperature is set at 22-26°C. In extremely cold conditions (such as below -15°C), anti-freeze heating protection is automatically activated to avoid equipment damage.

[0145] For special climate zones (such as the Yunnan-Guizhou Plateau, Qinling Mountains and coastal mountainous areas with significant temperature differences between day and night), a dynamic segmentation strategy can be adopted: during the day, the system operates according to the standards of the main climate zone to which it belongs, with a nighttime temperature fluctuation of ±2°C and real-time monitoring of humidity for dynamic compensation of ±5%; in areas near mountains and rivers, GPS data is bound and terrain correction parameters are pre-loaded (such as enhanced dehumidification on windward slopes and humidity compensation on leeward slopes) to adapt to local microclimate fluctuations.

[0146] Based on the climate characteristics of each solar term, independent control logic can be set. The control logic can include sample parameter information under various climate conditions. By integrating the north-south regional differences, extreme climate responses, and equipment protection mechanisms, a three-dimensional adaptive system of "solar term-date-region" can be formed. The relationship between sample solar term information and sample parameter information is shown below:

[0147] The climate characteristics corresponding to the Beginning of Spring (February 3-5) are: the temperature rises initially but fluctuates, and humidity begins to return in the south. The control logic can be set as follows: the daytime temperature is set at 18-20℃ (dehumidification is mainly used in the south, and humidity ≤55%), and intermittent heating is used in the north to compensate for the late spring cold; the heating module is turned off at night, and a low-speed fresh air circulation of 2m / s is started to replace the accumulated cold air.

[0148] The climate characteristics corresponding to the Rain Water solar term (February 18-20) are: increased precipitation and a significant increase in air humidity. The control logic can be set as follows: dehumidification priority mode is activated in the entire southern region (humidity hard limit ≤ 50%), and the cooling temperature is relaxed to 22°C; in the northern dust zone, circulation filtration is triggered within 3 minutes every hour, and the lower limit of humidity is set to 35% for anti-static protection.

[0149] The climate characteristics corresponding to the Jingzhe solar term (March 5-7) are: more thunderstorms and increased insect and mold activity. The control logic can be set as follows: the temperature is maintained at 20-22℃, the dehumidification frequency is increased to 10 minutes per hour, local ventilation is linked to mold-prone spots such as wardrobes and corners, and the humidity fluctuation tolerance is tightened to ±3%.

[0150] The climate characteristics corresponding to the Spring Equinox (March 20-22) are: long days and long nights, and balanced temperature and humidity. The control logic can be set as follows: adopt a "neutral temperature" of 24°C as the benchmark, and a humidity of 40-50%; turn on smart ventilation (introduce fresh air when the outdoor temperature difference is less than 5°C), and start the plant respiration simulation mode at night (CO2 concentration control ≤600ppm).

[0151] The climate characteristics corresponding to the Qingming solar term (April 4-6) are: frequent precipitation and high incidence of willow catkins and dust. The control logic can be set as: cooling temperature 22-24℃, humidity upper limit 55%; the three-level filter interception mode is activated in the north (pressurized filtration when PM10>80), and the rain sensor is linked to pre-dehumidification in the south.

[0152] The climate characteristics corresponding to the Grain Rain (April 19-21) solar term are: warm and humid air currents push northward in an all-round way, and the temperature difference narrows. The control logic can be set as follows: the temperature of the entire area is locked at 22-24℃, and the humidity threshold is 45-55%; the Yangtze River Basin activates the "moisture-proof pre-cooling" mechanism (cooling and dehumidification 30 minutes in advance when the outdoor humidity is >70%).

[0153] The climate characteristics corresponding to the Beginning of Summer (May 5-7) are: the beginning of humidity and heat, and a sharp increase in air conditioning load. The control logic can be set as: cooling temperature 24-26℃, humidity ≤ 60%; adopt step-by-step cooling (0.8℃ per hour), and bind the tide table in coastal areas to strengthen the dehumidification intensity during high tide periods.

[0154] The climate characteristics corresponding to the Grain Full solar term (May 20-22) are: the feeling of stuffiness intensifies, and the evaporation of crops increases humidity. The control logic can be set as follows: the temperature is lowered to 23-25℃, and the humidity is strictly limited to ≤55%; the "anti-evaporation mode" is activated for houses around farmland (the dehumidification capacity is increased by 20% from 11-15 o'clock every day).

[0155] The climate characteristics corresponding to the Grain in Ear solar term (June 5-7) are: the beginning of the plum rain season and continued high humidity. The control logic can be set as follows: the "Plum Rain Agreement" is activated in the south - temperature 25℃ + humidity ≤ 50% forced linkage, and directional dehumidification is additionally added in the wardrobe / study area; the dry and hot areas in the north maintain a humidity lower limit of 40%.

[0156] The climate characteristics corresponding to the summer solstice (June 21-22) are: the longest sunshine of the year and the risk of extreme high temperatures. The control logic can be set as follows: enable "anti-extreme heat mode" - the cooling in public places can be temporarily lowered to 22°C, and residential areas maintain 24-26°C; the compressor runs at off-peak (80% frequency limit at noon), and the humidity threshold is tightened to 50%.

[0157] The climate characteristics corresponding to the Lesser Heat solar term (July 6-8) are: the initial heat wave, the body feels scorching hot, and the control logic can be set as follows: set the temperature to 24-26℃, start the "hurricane cycle" (wind speed 4-6m / s); enable rapid cooling compensation from 2-4 pm every day (the temperature drops by 1℃ instantly for 15 minutes), and compensate the humidity in desert areas to 40% at night.

[0158] The climate characteristics corresponding to the Great Heat solar term (July 22-24) are: the hottest period of the year, with typhoons and summer droughts coexisting. The control logic can be set as follows: the temperature is allowed to exceed 22-26°C, and the humidity is strictly limited to ≤55%; typhoon warning areas close the external circulation and increase the dehumidification frequency, and in inland drought areas, midnight humidification (humidity ≥45%) is activated.

[0159] The climate characteristics corresponding to the Beginning of Autumn (August 7-9) are: the "autumn tiger" is raging, and the temperature difference between day and night increases. The control logic can be set as: cooling at 25-26℃ during the day, switching to ventilation + low-wind dehumidification (wind speed ≤ 2m / s) at sunset, and slight humidification (30-35%) in the morning in the north.

[0160] The climate characteristics corresponding to the solar term of End of Heat (August 22-24) are: hot and humid rebound, frequent thunderstorms in the afternoon. The control logic can be set as: temperature 24-26℃, humidity ≤ 60%, pre-cooling 1℃ 1 hour before thunderstorm, and humidity fluctuation tolerance +5%.

[0161] The climate characteristics corresponding to the White Dew solar term (September 7-9) are: increased morning dew and high incidence of respiratory sensitivity. The control logic can be set to: temperature 22-24℃, humidity 50-60%, "feel-free air supply" in the bedroom at night (wind speed ≤1m / s), and allergen filtering mode turned on.

[0162] The climate characteristics corresponding to the Autumnal Equinox (September 22-24) are: dry and cold air moves south and the humidity drops sharply. The control logic can be set as follows: temperature 20-22℃, humidity ≥ 40%, delayed start of the heating module, and priority for fresh air preheating (when the outside temperature is > 12℃).

[0163] The climate characteristics corresponding to the Cold Dew solar term (October 8-9) are: late autumn turns cooler and the first frost appears in the north. The control logic can be set as follows: North: heating 18-20℃ + humidification (≥35%); South: temperature 20-22℃, humidity ≤55%.

[0164] The climate characteristics corresponding to the Frost Descent solar term (October 23-24) are: the beginning of frost and increased risk of static electricity. The control logic can be set as follows: humidity ≥ 45%, humidification and dust prevention are activated in advance in the northwest, and static electricity is suppressed in the bookcase / carpet area and air is supplied (ion function is activated).

[0165] The climate characteristics corresponding to the Beginning of Winter (November 7-8) are: the first cold wave hits, and the dry and wet conditions in the north and south are differentiated. The control logic can be set as follows: North: heating 18-22℃ + continuous humidification; South: heating 20-24℃ + dehumidification linkage (humidity ≤ 50%).

[0166] The climate characteristics corresponding to the Xiaoxue solar term (November 22-23) are: frequent first snowfall and risk of frost on the outdoor unit. The control logic can be set as follows: the automatic defrost cycle of the outdoor unit is shortened to 2 hours / time, the humidity threshold is ≥30% in the north and ≤50% in the south, and the heating wind speed limit is ≤2m / s.

[0167] The climate characteristics corresponding to the Heavy Snow solar term (December 6-8) are: increased snowfall and urgent need for heat storage. The control logic can be set as follows: cold wave warning 3 hours in advance to increase temperature and store heat, humidification intensity in the north +15%, and automatic start of outdoor electric auxiliary heating.

[0168] The climate characteristics corresponding to the winter solstice (December 21-23) are: the coldest in the whole year, with the air dryest. The control logic can be set as follows: heating is locked at 20-24℃ + humidification ≥ 30% in the north, heating is set at 16-20℃ + dehumidification ≤ 45% in the wet and cold southern areas, and the entire area is silent and protected against direct blowing late at night.

[0169] The climate characteristics corresponding to the Lesser Cold solar term (January 5-7) are: continuous dry cold, static electricity and risk of equipment freezing damage. The control logic can be set to: humidity ≥ 35%, ionized air supply to carpet / fabric areas, and outdoor unit anti-freeze mode (the heating wire continues to work below -10℃).

[0170] The climate characteristics corresponding to the Great Cold (January 20-21) solar term are: extremely low temperature, equipment operating at its limit, and the control logic can be set as follows: the heating temperature is allowed to exceed 26°C, the compressor load is limited to 80%, the humidifier runs around the clock (humidity ≥ 30%), and the outdoor unit is de-iced for 10 minutes every hour.

[0171] In some embodiments, obtaining sample parameter information may include:

[0172] Based on the date information and sample parameter information corresponding to adjacent sample solar term information, the sample parameter information corresponding to each date between adjacent sample solar term information is interpolated to obtain the sample parameter information corresponding to each date between adjacent sample solar term information.

[0173] In this embodiment, the sample parameter information includes parameter information corresponding to various climate conditions. The sample parameter information may include parameter information corresponding to each date, and parameter information corresponding to samples obtained by combining the date with different climate data.

[0174] For any two adjacent sample solar term information, the blank date between them can be interpolated.

[0175] The date information corresponding to the sample solar term information may include the date range of the current solar term information. For example, the date information corresponding to the Beginning of Spring solar term may be February 3-5, and the date information corresponding to the Rain Water solar term may be February 18-20.

[0176] After obtaining each sample solar term information and the sample parameter information corresponding to each sample solar term information, the sample parameter information corresponding to each date between adjacent sample solar term information may be interpolated to obtain the sample parameter information corresponding to each date.

[0177] In the actual implementation process, for the parameter information of blank dates between adjacent solar terms (such as non-solar day between the end of Lichun and the beginning of Yushui), a linear interpolation algorithm can be used to fine-tune the parameters daily (for example, the temperature fluctuates by 0.3°C daily, and the humidity is ±1%). Through mathematical uniform distribution, seamless connection of parameters can be achieved during the solar term transition period.

[0178] For example, you can calculate the number of blank days between two adjacent solar terms (solar term A and solar term B):

[0179] N=DB -D A -1

[0180] Among them, D B is the starting date of solar term B, D A is the end date of solar term A, and N is the number of blank days between solar term A and solar term B.

[0181] The daily parameter adjustment corresponding to the blank date between solar terms A and B is:

[0182]

[0183] Among them, ΔP is the daily parameter adjustment corresponding to the blank day between solar terms A and B, P B is the sample parameter information of solar term B, P A is the sample parameter information of solar term A, and N is the number of blank days between solar term A and solar term B.

[0184] The sample parameter information corresponding to each blank date between solar term A and solar term B is:

[0185]

[0186] in, is the sample parameter information corresponding to each blank date between solar term A and solar term B, P A is the sample parameter information of solar term A, ΔP is the daily parameter adjustment corresponding to the blank date between solar terms A and B, and i is the index of the blank date between solar terms A and B.

[0187] The parameter information can be automatically updated at 0:00 every day during the transition period between two adjacent solar terms.

[0188] According to the control method of the refrigeration equipment provided in the embodiment of the present application, the blank dates between two adjacent solar terms are interpolated to obtain sample parameter information corresponding to each blank date. Combined with dynamic adjustment rules and special scenario optimization, the flexibility and robustness of the system are enhanced while retaining the solar term control strategy. Moreover, by interpolating the sample parameter information, the parameter information of each date can be smoothly transitioned, avoiding sudden changes in user physical sensation and improving the user experience.

[0189] In some embodiments, for leap years, the sample parameter information of February 29 can be set to be consistent with the sample parameter information corresponding to the Rain Water solar term, thereby avoiding a gap in the sample parameter information and ensuring the continuity of the sample parameter information corresponding to the date.

[0190] In some embodiments, the date offset can be dynamically corrected based on actual meteorological data. For example, when the beginning of spring in South China is advanced to February 1, the sample parameter information corresponding to the beginning of spring solar term can be automatically matched.

[0191] In some embodiments, data cleaning may be performed on sample temperature data, sample humidity data, sample solar term information, sample geographic location information, and sample parameter information to eliminate samples with many missing values or significant anomalies.

[0192] For missing data, mean filling or interpolation can be used to fill it based on its characteristic distribution, thereby reducing the impact of data incompleteness on the model training process.

[0193] In some embodiments, the sample temperature data, the sample humidity data, and the sample parameter information may be normalized to obtain new sample temperature data, sample humidity data, and sample parameter information.

[0194] In this embodiment, for numerical variables, a minimum-maximum normalization method can be used for normalization processing so that its value range is mapped to [0, 1]:

[0195]

[0196] Among them, X norm is the sample data after normalization, X is the sample data before normalization, X min is the minimum value of the sample data before normalization, X max is the maximum value of the sample data before normalization.

[0197] In this application, by normalizing the sample data, the problem of dimensional inconsistency between different features can be eliminated, thereby enhancing the stability and convergence of the model.

[0198] like Figure 4 As shown, in some embodiments, obtaining a training data set may include:

[0199] Obtain user behavior feature data;

[0200] The training data set is updated based on historical temperature data, historical humidity data, historical solar term information, historical geographic location information, and historical parameter information.

[0201] In this embodiment, the user behavior characteristic data is historical parameter information set by the user when using the refrigeration equipment under the conditions of historical temperature data, historical humidity data, historical solar term information, and historical geographical location information.

[0202] Historical temperature data, historical humidity data, historical solar term information, historical geographic location information, and historical parameter information can be determined as a training sample.

[0203] Multiple training samples can be clustered to obtain a training data set.

[0204] According to the control method for refrigeration equipment provided in the embodiment of the present application, by acquiring the user's behavioral characteristic data, a training data set is obtained based on the user's behavioral characteristic data, and the database can be updated according to the user's personalized settings and personal preferences. Analysis and prediction are performed based on a large amount of historical data, and the target neural network model can be continuously optimized so that the parameters output by the target neural network model are more in line with the user's personalized needs, thereby improving the accuracy and reliability of the recommended control method and improving the user's usage experience and comfort.

[0205] In some embodiments, training a neural network model based on a training data set to obtain a target neural network model may include:

[0206] Use particle swarm optimization algorithm to update the initial network parameters of the neural network model;

[0207] Taking the minimum value of the target loss function as the goal, the updated neural network model is trained based on the training data set to obtain the target neural network model.

[0208] In this embodiment, the neural network model may be a BP neural network model (Back Propagation Neural Network, back propagation neural network), such as Figure 2 The BP neural network model structure diagram provided in the embodiment of the present application is illustrated, or it can be other types of neural network models, which can be selected based on user needs and are not limited in the present application.

[0209] A neural network model can include an input layer, a hidden layer, and an output layer.

[0210] In the input layer, hidden layer and output layer, the neurons between adjacent layers are fully connected, and there is no connection between the neurons in each layer.

[0211] The S function can be selected as the activation function of the hidden layer, and the hidden layer can be expressed as:

[0212]

[0213] Among them, x i is the input unit, including temperature, humidity, solar terms and geographical location information; h j is the hidden unit, y k is the output unit, from the input unit x i To the hidden unit h j The connection weight is w ij , from the hidden unit h jTo the output unit y k The connection weight is w ik , ω=(W,w) represents all connection weights.

[0214] The gradient descent method can be used to update the connection weights and bias values in the network. The update formula for the connection weights between the output layer and the hidden layer and the output layer neuron bias values is:

[0215]

[0216] b (3) =b (3) +Δb (3)

[0217]

[0218] Among them, b is the bias value of the output layer neuron, w j1 is the connection weight between the output layer and the hidden layer, η is the learning rate, and E is the error function.

[0219] The update formula for the connection weights between the hidden layer and the input layer and the bias of each neuron in the hidden layer is:

[0220]

[0221] Among them, w ij For input unit x i To the hidden unit h j The connection weight, b j is the bias value of the hidden layer neuron, η is the learning rate, E is the error function, y is the output unit, h j is a hidden unit, x i For the input unit.

[0222] The initial network parameters of the neural network model may include initial weights and thresholds.

[0223] Particle Swarm Optimization (PSO) is a swarm optimization algorithm that can find the optimal solution by simulating the iterative update process of ions in the search space.

[0224] The target loss function can include mean square error loss, mean absolute error loss, cross entropy loss, and absolute value loss, etc., which can be selected based on user needs. For example, mean square error can be used as the loss function: Among them, y k is the true value in the training sample, The predicted value output by the neural network model.

[0225] like Figure 4 As shown, the particle swarm optimization algorithm can be introduced to optimize the initial weights and thresholds of the neural network model. Each particle corresponds to a weight parameter combination of the neural network model. The position and speed update of the particle swarm optimization algorithm in the search space are based on the following formula:

[0226] v i,d (t+1)=ωv i,d (t)+c1r1[p i,d (t)-x i,d (t)]+c2r2[g d (t)-x i,d (t)]

[0227] x i,d (t+1)=x i,d (t)+v i,d (t+1)

[0228] Among them, x i,d and v i,d Represents the current position and velocity of the i-th particle in the d-th dimension, p i,d (t) is the individual optimal position of the particle, g d (t) is the global optimal position, ω is the inertia weight, c1 and c2 are learning factors, r1 and r2 are random numbers in the range [0,1].

[0229] By continuously iteratively adjusting the positions of particles, the particle swarm optimization algorithm can search for the optimal initial network parameters of the neural network model in a global range, and use the parameters optimized by the particle swarm optimization algorithm as the initial network parameters of the neural network model.

[0230] Then, the error back propagation algorithm can be used for local optimization. For example, the error can be back propagated through the gradient descent method to continuously adjust the weights and thresholds of the network model. This process is repeated until the global error of the network tends to a given minimum value, that is, the learning process is completed.

[0231] According to the control method for refrigeration equipment provided in the embodiment of the present application, the initial network parameters of the neural network model are updated by the particle swarm optimization algorithm, which can prevent the neural network model from falling into the local optimal solution during the training process, improve the generalization ability and convergence speed of the model, and improve the global search ability and training efficiency of the neural network model. Then, the neural network model is trained with the minimum value of the target loss function as the goal, and the model can be further locally optimized, thereby improving the rationality of the control strategy of the model for the generated refrigeration equipment.

[0232] In some embodiments, step 130 may include:

[0233] Obtain the first parameter information input by the user;

[0234] When the difference information between the target parameter information and the first parameter information is less than the target difference threshold, controlling the operation of the compressor based on the target parameter information;

[0235] When the difference information is greater than or equal to the target difference threshold, the target parameter information is updated based on the first parameter information, and the operation of the compressor is controlled based on the updated target parameter information.

[0236] In this embodiment, Figure 4 As shown, users can manually set the parameter information of the refrigeration equipment.

[0237] The first parameter information is parameter information manually set by the user, and the first parameter information may include a set temperature, set humidity, and set fresh air parameters of the refrigeration equipment.

[0238] The target parameter information is the parameters generated by the target neural network model based on real-time climate data.

[0239] The difference information between the target parameter information and the first parameter information can be obtained, and then the size relationship between the difference information and the target difference threshold can be compared, wherein the value of the target difference threshold can be customized based on the user, for example, the target difference threshold can be set to 10%, or it can also be set to other values, which is not limited in this application.

[0240] When it is determined that the difference information is less than the target difference threshold, the operation of the compressor may be controlled based on the target parameter information output by the target neural network model.

[0241] When it is determined that the difference information is greater than or equal to the target difference threshold, the first parameter information may be updated to new target parameter information, and the operation of the compressor may be controlled based on the updated target parameter information.

[0242] In some embodiments, when the target parameter information is updated based on the first parameter information, the climate data currently input to the target neural network model and the first parameter information can be added to the training data set as training samples to continuously optimize the model parameters of the target neural network model.

[0243] The control device of the refrigeration equipment provided in the present application is described below. The control device of the refrigeration equipment described below and the control method of the refrigeration equipment described above can be referenced to each other.

[0244] The control method for refrigeration equipment provided in the embodiment of the present application can be executed by a control device of the refrigeration equipment. In the embodiment of the present application, the control device of the refrigeration equipment executing the control method for refrigeration equipment is used as an example to illustrate the control device of the refrigeration equipment provided in the embodiment of the present application.

[0245] An embodiment of the present application also provides a control device for refrigeration equipment.

[0246] like Figure 6 As shown, the control device of the refrigeration equipment includes a temperature sensor, a humidity sensor, a time module, a positioning module and a compressor; the device includes: a first processing module 610, a second processing module 620 and a third processing module 630.

[0247] The first processing module 610 is configured to obtain the actual ambient temperature of the refrigeration device collected by the temperature sensor, the actual ambient humidity collected by the humidity sensor, the actual solar term information output by the time module, and the actual geographical location information of the refrigeration device output by the positioning module;

[0248] The second processing module 620 is used to input the actual ambient temperature, the actual ambient humidity, the actual solar term information and the actual geographical location information into the target neural network model to obtain target parameter information output by the target neural network model;

[0249] The third processing module 630 is configured to control the operation of the compressor based on the target parameter information.

[0250] According to the control device of the refrigeration equipment provided in the embodiment of the present application, through the pre-training of the target neural network model, it is possible to output target parameter information based on the real-time monitored temperature, humidity, solar term information and geographical location information, thereby controlling the operation of the compressor based on the target parameter information, and establishing an association mechanism between the target parameter information and the multi-dimensional features. It is possible to automatically adjust the operation of the refrigeration equipment according to the climatic characteristics of the user's location, thereby improving the user's usage experience in different solar term environments without the need for manual intervention by the user, thereby improving the user's comfort and satisfaction.

[0251] In some embodiments, the control device of the refrigeration equipment further includes a fourth processing module, configured to obtain a target neural network model through training based on the following steps:

[0252] Obtain a training data set, the training data set including multiple training samples, each training sample including sample temperature data, sample humidity data, sample solar term information, sample geographic location information and sample parameter information;

[0253] With the goal of learning the correlation between sample temperature data, sample humidity data, sample solar term information and sample geographic location information and sample parameter information, and outputting predicted parameter information, a neural network model is trained based on the training data set to obtain a target neural network model.

[0254] In some embodiments, the fourth processing module may further be configured to:

[0255] Obtain sample temperature data, sample humidity data, sample solar term information, sample geographic location information and sample parameter information;

[0256] A clustering algorithm is used to process sample temperature data, sample humidity data, sample solar term information, sample geographic location information and sample parameter information to obtain a multi-cluster data set, so as to obtain a training data set based on the multi-cluster data set; each cluster data set includes sample temperature data, sample humidity data, sample solar term information and sample geographic location information, and the label of each cluster data set is the sample parameter information corresponding to the data set.

[0257] In some embodiments, the fourth processing module may further be configured to:

[0258] Based on the date information and sample parameter information corresponding to adjacent sample solar term information, the sample parameter information corresponding to each date between adjacent sample solar term information is interpolated to obtain the sample parameter information corresponding to each date between adjacent sample solar term information.

[0259] In some embodiments, the fourth processing module may further be configured to:

[0260] Obtaining user behavior characteristic data, which is historical parameter information set by the user when using the refrigeration equipment under conditions of historical temperature data, historical humidity data, historical solar term information, and historical geographic location information;

[0261] The training data set is updated based on historical temperature data, historical humidity data, historical solar term information, historical geographic location information, and historical parameter information.

[0262] In some embodiments, the fourth processing module may further be configured to:

[0263] Use particle swarm optimization algorithm to update the initial network parameters of the neural network model;

[0264] Taking the minimum value of the target loss function as the goal, the updated neural network model is trained based on the training data set to obtain the target neural network model.

[0265] In some embodiments, the third processing module 630 may also be configured to:

[0266] Obtain the first parameter information input by the user;

[0267] When the difference information between the target parameter information and the first parameter information is less than the target difference threshold, controlling the operation of the compressor based on the target parameter information;

[0268] When the difference information is greater than or equal to the target difference threshold, the target parameter information is updated based on the first parameter information, and the operation of the compressor is controlled based on the updated target parameter information.

[0269] The control device of the refrigeration equipment in the embodiment of the present application can be an electronic device or a component in the electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal or other devices other than a terminal. For example, the electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a mobile Internet device (MID), an augmented reality (AR) / virtual reality (VR) device, a robot, a wearable device, an ultra-mobile personal computer (UMPC), a netbook or a personal digital assistant (PDA), etc. It can also be a server, a network attached storage (NAS), a personal computer (PC), a television (TV), a teller machine or a self-service machine, etc., and the embodiment of the present application does not specifically limit it.

[0270] The control device of the refrigeration equipment in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0271] The control device of the refrigeration equipment provided in the embodiment of the present application can achieve Figures 1 to 5 To avoid repetition, the various processes implemented in the method embodiment are not described here.

[0272] In some embodiments, as Figure 7 As shown, an embodiment of the present application also provides an electronic device 700, including a processor 701, a memory 702, and a computer program stored in the memory 702 and executable on the processor 701. When the program is executed by the processor 701, each process of the control method embodiment of the above-mentioned refrigeration equipment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0273] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0274] like Figure 5 As shown, in some embodiments, the present application also provides a control system for refrigeration equipment, including: a data collection module, a data preprocessing module, a model building module and a data update module.

[0275] In this embodiment, the data collection module can be used to obtain actual ambient temperature, actual ambient humidity, actual solar term information, and actual geographical location information.

[0276] The data preprocessing module can be used to check the validity of data during the data preprocessing process, including processing erroneous data and empty data, verifying and correcting erroneous data, replacing empty data with historical mean values, and correcting invalid data.

[0277] The unsupervised clustering module can use the K-means clustering algorithm to perform cluster analysis on climate data of different solar terms and geographical locations to achieve automatic classification of samples.

[0278] The model building module is used to build a neural network model. The neural network model can be trained according to the training data set, the S-type transfer function is selected to process the sample data, the mean square error is selected as the loss function, and the network weights and thresholds of the loss function are iteratively calculated and optimized through the back propagation error of the neural network. The PSO algorithm is used to search for the optimal initial network parameters of the neural network model in a global scope to achieve the minimum value of the error function and finally establish the target neural network model.

[0279] The data update module can update the database according to the user's personalized settings and personal preferences, and continuously optimize the network weights and thresholds, so that the parameter information output by the target neural network model is more in line with the user's personalized needs, thereby improving the user's usage experience and comfort.

[0280] In some embodiments, the embodiments of the present application further provide a refrigeration device, including: an indoor main body, an outdoor main body, a temperature sensor, a humidity sensor, a time module, a positioning module and a compressor.

[0281] In this embodiment, the temperature sensor is installed inside the shell of the indoor main body. The temperature sensor can be used to monitor the ambient temperature in real time and obtain the actual ambient temperature.

[0282] The humidity sensor is installed inside the housing of the indoor main body. The humidity sensor can be used to detect the ambient humidity level and obtain the actual ambient humidity.

[0283] The time module is installed inside the shell of the indoor main body and is used to obtain actual solar term information.

[0284] The positioning module is installed inside the shell of the indoor main body and is used to obtain actual geographical location information.

[0285] The compressor is installed inside the casing of the outdoor main body.

[0286] The refrigeration device operates based on the control method for the refrigeration device as described in any of the above embodiments.

[0287] According to the refrigeration equipment provided in the embodiment of the present application, through the pre-training target neural network model, it is possible to output target parameter information based on the real-time monitored temperature, humidity, solar term information and geographical location information, thereby controlling the operation of the compressor based on the target parameter information, and establishing an association mechanism between the target parameter information and the multi-dimensional features. It is possible to automatically adjust the operation of the refrigeration equipment according to the climatic characteristics of the user's location, thereby improving the user's usage experience in different solar term environments without the need for manual intervention by the user, thereby improving the user's comfort and satisfaction.

[0288] On the other hand, the present application also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the various processes of the above-mentioned control method embodiment of the refrigeration equipment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0289] On the other hand, the present application also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it is implemented to perform the various processes of the above-mentioned control method embodiment of the refrigeration equipment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0290] On the other hand, an embodiment of the present application further provides a chip, which includes a processor and a communication interface, the communication interface and the processor are coupled, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned control method embodiment of the refrigeration equipment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0291] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0292] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0293] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the above technical solution, in essence, or the part that contributes to the relevant technology, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0294] Finally, it should be noted that 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. However, 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.

Claims

1. A method for controlling a refrigeration device, characterized in that: The refrigeration equipment includes a temperature sensor, a humidity sensor, a time module, a positioning module and a compressor; the method includes: Acquire the actual ambient temperature of the environment in which the refrigeration device is located, as collected by the temperature sensor, the actual ambient humidity, as collected by the humidity sensor, the actual solar term information output by the time module, and the actual geographical location information of the refrigeration device, as output by the positioning module; Inputting the actual ambient temperature, the actual ambient humidity, the actual solar term information, and the actual geographical location information into a target neural network model, and obtaining target parameter information output by the target neural network model; Based on the target parameter information, the operation of the compressor is controlled.

2. The control method for refrigeration equipment according to claim 1, characterized in that: The target neural network model is trained based on the following steps: Acquire a training data set, wherein the training data set includes a plurality of training samples, each of the training samples includes sample temperature data, sample humidity data, sample solar term information, sample geographic location information, and sample parameter information; With the goal of learning the correlation between the sample temperature data, the sample humidity data, the sample solar term information and the sample geographic location information and the sample parameter information, and outputting predicted parameter information, a neural network model is trained based on the training data set to obtain the target neural network model.

3. The control method for refrigeration equipment according to claim 2, characterized in that: The obtaining of the training data set includes: Obtain sample temperature data, sample humidity data, sample solar term information, sample geographic location information and sample parameter information; A clustering algorithm is used to process the sample temperature data, the sample humidity data, the sample solar term information, the sample geographic location information and the sample parameter information to obtain a multi-cluster data set, so as to obtain the training data set based on the multi-cluster data set; each cluster of the data set includes sample temperature data, sample humidity data, sample solar term information and sample geographic location information, and the label of each cluster of the data set is the sample parameter information corresponding to the data set.

4. The control method for refrigeration equipment according to claim 3, characterized in that: Obtaining the sample parameter information includes: Based on the date information and sample parameter information corresponding to adjacent sample solar term information, the sample parameter information corresponding to each date between the adjacent sample solar term information is interpolated to obtain the sample parameter information corresponding to each date between the adjacent sample solar term information.

5. The control method for refrigeration equipment according to claim 2, characterized in that: The obtaining of the training data set includes: Acquiring user behavior characteristic data, wherein the user behavior characteristic data is historical parameter information set by the user when using the refrigeration device under conditions of historical temperature data, historical humidity data, historical solar term information, and historical geographic location information; The training data set is updated based on the historical temperature data, the historical humidity data, the historical solar term information, the historical geographic location information, and the historical parameter information.

6. The control method for refrigeration equipment according to claim 2, characterized in that: The step of training a neural network model based on the training data set to obtain the target neural network model includes: Using a particle swarm optimization algorithm to update the initial network parameters of the neural network model; Taking the minimum value of the target loss function as the goal, the updated neural network model is trained based on the training data set to obtain the target neural network model.

7. The control method for refrigeration equipment according to any one of claims 1 to 6, characterized in that: The controlling the operation of the compressor based on the target parameter information includes: Obtain the first parameter information input by the user; When the difference information between the target parameter information and the first parameter information is less than a target difference threshold, controlling the operation of the compressor based on the target parameter information; When the difference information is greater than or equal to the target difference threshold, the target parameter information is updated based on the first parameter information, and the operation of the compressor is controlled based on the updated target parameter information.

8. A control device for refrigeration equipment, characterized in that: The refrigeration equipment includes a temperature sensor, a humidity sensor, a time module, a positioning module and a compressor; the device includes: A first processing module is configured to obtain the actual ambient temperature of the environment in which the refrigeration device is located, as collected by the temperature sensor, the actual ambient humidity, as collected by the humidity sensor, the actual solar term information output by the time module, and the actual geographical location information of the refrigeration device, as output by the positioning module; a second processing module, configured to input the actual ambient temperature, the actual ambient humidity, the actual solar term information, and the actual geographical location information into a target neural network model, and obtain target parameter information output by the target neural network model; A third processing module is configured to control the operation of the compressor based on the target parameter information.

9. A refrigeration device, characterized in that: include: indoor subject; Outdoor subject; A temperature sensor is installed inside the housing of the indoor body; A humidity sensor is installed inside the housing of the indoor body; A time module is installed inside the housing of the indoor main body; A positioning module is installed inside the housing of the indoor main body; A compressor installed inside the housing of the outdoor main body; The refrigeration device operates based on the control method for refrigeration device according to any one of claims 1 to 7.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the control method for the refrigeration equipment according to any one of claims 1 to 7 is implemented.

Images