WO2020181723A1 - 冰箱间室温度和湿度的生成方法及生成装置 - Google Patents

冰箱间室温度和湿度的生成方法及生成装置 Download PDF

Info

Publication number
WO2020181723A1
WO2020181723A1 PCT/CN2019/100740 CN2019100740W WO2020181723A1 WO 2020181723 A1 WO2020181723 A1 WO 2020181723A1 CN 2019100740 W CN2019100740 W CN 2019100740W WO 2020181723 A1 WO2020181723 A1 WO 2020181723A1
Authority
WO
WIPO (PCT)
Prior art keywords
food
individuals
humidity
population
parent
Prior art date
Application number
PCT/CN2019/100740
Other languages
English (en)
French (fr)
Inventor
李桂玺
党广明
Original Assignee
青岛海尔电冰箱有限公司
海尔智家股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 青岛海尔电冰箱有限公司, 海尔智家股份有限公司 filed Critical 青岛海尔电冰箱有限公司
Priority to EP19918899.6A priority Critical patent/EP3940326A4/en
Publication of WO2020181723A1 publication Critical patent/WO2020181723A1/zh

Links

Images

Classifications

    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
    • F25D—REFRIGERATORS; COLD ROOMS; ICE-BOXES; COOLING OR FREEZING APPARATUS NOT OTHERWISE PROVIDED FOR
    • F25D17/00—Arrangements for circulating cooling fluids; Arrangements for circulating gas, e.g. air, within refrigerated spaces
    • F25D17/04—Arrangements for circulating cooling fluids; Arrangements for circulating gas, e.g. air, within refrigerated spaces for circulating air, e.g. by convection
    • F25D17/042—Air treating means within refrigerated spaces
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
    • F25D—REFRIGERATORS; COLD ROOMS; ICE-BOXES; COOLING OR FREEZING APPARATUS NOT OTHERWISE PROVIDED FOR
    • F25D29/00—Arrangement or mounting of control or safety devices
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/12—Computing arrangements based on biological models using genetic models
    • G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
    • F25D—REFRIGERATORS; COLD ROOMS; ICE-BOXES; COOLING OR FREEZING APPARATUS NOT OTHERWISE PROVIDED FOR
    • F25D2500/00—Problems to be solved
    • F25D2500/06—Stock management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning

Definitions

  • the present invention relates to the technical field of refrigeration equipment, and in particular to a method and a device for generating temperature and humidity in a refrigerator compartment.
  • Refrigerators are commonly used household appliances in people’s daily life. In actual use, users usually store a variety of foods in the storage compartment. It is understandable that each type of food has its most suitable temperature and humidity, so , When setting the temperature and humidity of the storage compartment, each type of food needs to be considered.
  • the purpose of the present invention is to provide a method and a device for generating temperature and humidity in a refrigerator compartment.
  • an embodiment of the present invention provides a method for generating temperature and humidity in a refrigerator compartment, which includes the following steps:
  • the attribute value of each food includes at least: being able to uniquely mark the food
  • the operation specifically includes: generating the fitness of each parent individual in the first population, and select according to the higher the fitness The principle of the greater the probability is to delete several parents from the first population to obtain the second population; select several binary groups from the second population, and each binary group contains two different parents.
  • the two parent individuals in the tuple are coded to cross and produce two offspring individuals, and several individuals in all offspring individuals are mutated to obtain the first population;
  • the temperature and humidity of the storage compartment are respectively set to the best temperature and the best humidity of the parent individual with the highest fitness in the first population.
  • the "encoding each food” specifically includes: encoding each food with a floating point number.
  • the "encoding and crossover of two parent individuals in each two-tuple in a number of two-tuples and generating two offspring individuals” specifically includes: For the two parent individuals in each two-tuple in, exchange the best temperatures of the two parent individuals and/or take some intermediate values between the best temperatures of the two parent individuals and/or combine the two parent individuals The optimal humidity of the individual is exchanged and/or several intermediate values between the optimal humidity of the two parent individuals are taken, thereby generating several offspring individuals.
  • the "mutating several individuals from all offspring individuals to obtain the first population” specifically includes: several target individuals randomly selected from all offspring individuals, The optimal temperature and/or optimal humidity are modified, and the first population consists of all unselected offspring individuals and all modified offspring individuals.
  • the embodiment of the present invention also provides a device for generating temperature and humidity of a refrigerator compartment, which includes the following modules:
  • the initialization module is used to obtain all the food in the storage compartment and the attribute value of each food, and encode the attribute value of each food to obtain the first population, where the attribute value of the food includes at least: Uniquely mark the identifier of the food, the stored time, the best temperature, the best humidity, the frequency of removal, the economic value and the storage time;
  • the iterative module is used to continuously perform the following operations until the fitness of each parent individual in the first population meets a preset condition.
  • the operation specifically includes: generating the fitness of each parent individual in the first population, according to the fitness The higher the degree, the greater the probability of selection. Delete several parents from the first population to get the second population; select several binary groups from the second population, where each binary group contains two different parents , Perform coding crossover for the two parent individuals in each binary group and produce two offspring individuals, and mutate several individuals in all offspring individuals to obtain the first population;
  • the setting module is used to set the temperature and humidity of the storage compartment to the best temperature and the best humidity of the parent individual with the highest adaptability in the first population, respectively.
  • the initialization module is also used to encode each food with floating point numbers.
  • the iteration module is also used to: exchange the optimal temperatures of the two parent individuals for each of the two parent individuals in each of the two parent groups, and/ Or take several intermediate values between the optimal temperatures of the two parent individuals and/or exchange the optimal humidity of the two parent individuals and/or take several intermediate values between the optimal humidity of the two parent individuals, thereby Generate several offspring individuals.
  • the iteration module is also used to: randomly select several target individuals from all offspring individuals, modify the optimal temperature and/or optimal humidity of the several target individuals, and A group consists of all unselected offspring individuals and all modified offspring individuals.
  • the embodiments of the present invention provide a method and a device for generating temperature and humidity in a refrigerator compartment.
  • the method includes the following steps: obtaining all foods in the storage compartment and each The attribute value of each food is encoded, and the attribute value of each food is encoded to obtain the first population; the following operations are continued until the fitness of each parent individual in the first population meets the preset conditions, and the operations specifically include: Generate the fitness of each parent individual in the first population, delete several parent individuals from the first population to obtain the second population; perform coding crossover and mutation from the second population to obtain several offspring individuals, and combine several offspring individuals into the first population Population; the temperature and humidity of the storage compartment are respectively set to the best temperature and the best humidity of the most adaptable parent individual in the first population, so that the temperature and humidity of the storage compartment can be automatically adjusted.
  • FIG. 1 is a schematic flowchart of a method for generating temperature and humidity in a refrigerator compartment in an embodiment of the present invention.
  • the embodiment of the present invention provides a method for generating temperature and humidity in a refrigerator compartment, as shown in FIG. 1, including the following steps:
  • Step 101 Obtain all the foods in the storage compartment and the attribute value of each food, and encode the attribute value of each food to obtain the first population, wherein the attribute value of the food includes at least: a unique label
  • the information of all foods that is, when the user puts food into the storage compartment, get the current time (understandably, the current time is the time when the food is put), and the information and the time of the food It is stored in the database, and when the user takes food from the storage compartment, the information of the food is deleted from the database.
  • the identifier can be a character string, which can uniquely identify a food;
  • the stored time is the time difference between the current time and the time when the food is put in, and the optimal temperature is the temperature most suitable for storing the food.
  • the optimal humidity is the humidity that is most suitable for the storage of the food, and the frequency of removal is the number of times the food is of the same type as the food in a period of time (for example, in the storage compartment, the user may enter the storage compartment multiple times Put in beef, the number of times the user takes out the beef in a period of time can be the frequency of taking out the beef), the economic value is an index reflecting the price of the food (the index is proportional to the price of the food), and it can be stored Time is the time that the food can be stored in the storage compartment.
  • each individual corresponds to a kind of food, that is, the optimal temperature of the individual is equal to the optimal temperature of the corresponding food, and the optimal humidity of the individual is equal to the optimal temperature of the corresponding food humidity.
  • Step 102 Continue to perform the following operations until the fitness of each parent individual in the first population meets a preset condition.
  • the operation specifically includes: generating the fitness of each parent individual in the first population, according to the fitness level. High, the greater the probability of selection, delete several parents from the first population to get the second population; select several binary groups from the second population, and each binary group contains two different parents.
  • the two parent individuals in each two-tuple are coded to cross and produce two offspring individuals. Several individuals in all offspring individuals are mutated to obtain the first population.
  • the first-generation population if the first individual corresponds to the first food, the first food can obtain the best storage effect under the temperature and humidity represented by the first individual, but the rest Food cannot get the best storage effect.
  • the preset condition can be: The fitness difference is lower than a certain value, or the difference between the fitness of the parent individual in the previous iteration and this iteration is relatively small.
  • Step 103 Set the temperature and humidity of the storage compartment to the optimal temperature and optimal humidity of the parent individual with the highest fitness in the first population, respectively.
  • the "encoding each food” specifically includes: encoding each food with a floating point number.
  • the "generating the fitness of each parent individual in the first population” specifically includes:
  • the suitability of each food is different. Therefore, the appropriateness of each food needs to be considered. Suitability.
  • the “encoding and crossover of two parent individuals in each two-tuple in a number of two-tuples and generating two offspring individuals” specifically includes: for each two-tuple in the two-tuples The two parent individuals in, exchange the best temperature of the two parent individuals and/or take some intermediate values between the best temperatures of the two parent individuals and/or exchange the best humidity of the two parent individuals And/or take several intermediate values between the optimal humidity of the two parent individuals to generate several offspring individuals.
  • the ways to generate individual offspring are: (1) Exchange the best temperature of the two parents; (2) Take some intermediate values between the best temperatures of the two parents; (3) Combine the two parents The optimal humidity of the individual is exchanged; (4) Take some intermediate values between the optimal humidity of the two parents of the individual. In addition, it is also possible to choose from these four methods to generate offspring individuals.
  • the “mutating several individuals among all offspring individuals to obtain the first population” specifically includes:
  • the first population consists of all unselected offspring individuals and all modified offspring individuals .
  • the method for generating the temperature and humidity of the refrigerator compartment can also adjust the output result of the algorithm according to the user's interaction habits and value orientation.
  • the optimal number of days is uniformly characterized as a task form, where s represents environmental information, d represents storage days information, and q(s) represents the distribution of environmental information, which represents the transition to the environment by adjusting parameters in the environment.
  • a fitness function is designed based on the food temperature deviation ⁇ T, humidity deviation ⁇ H, economic value E, removal frequency k, stored time d, and storage time D. The weight of this function finds the optimal value through offline experiments, and fine-tunes it according to online users' habits.
  • the embodiment of the present invention also provides a device for generating temperature and humidity in a refrigerator compartment, which includes the following modules:
  • the initialization module is used to obtain all the food in the storage compartment and the attribute value of each food, and encode the attribute value of each food to obtain the first population, where the attribute value of the food includes at least: Uniquely mark the identifier of the food, the stored time, the best temperature, the best humidity, the frequency of removal, the economic value and the storage time;
  • the iterative module is used to continuously perform the following operations until the fitness of each parent individual in the first population meets a preset condition.
  • the operation specifically includes: generating the fitness of each parent individual in the first population, according to the fitness The higher the degree, the greater the probability of selection. Delete several parents from the first population to get the second population; select several binary groups from the second population, where each binary group contains two different parents , Perform coding crossover for the two parent individuals in each binary group and produce two offspring individuals, and mutate several individuals in all offspring individuals to obtain the first population;
  • the setting module is used to set the temperature and humidity of the storage compartment to the best temperature and the best humidity of the parent individual with the highest adaptability in the first population, respectively.
  • the initialization module is also used to: encode each food with a floating point number.
  • the storage time of the food d is the stored time of the food
  • ⁇ T is the difference between the optimal humidity of the parent individual and the optimal humidity of the food
  • E is the economic value of the food .
  • the iterative module is also used to: exchange the optimal temperatures of the two parent individuals and/or take the temperature of the two parent individuals for the two parent individuals in each of the two parent groups. Several intermediate values between the optimal temperature and/or the optimal humidity of the two parent individuals are exchanged and/or several intermediate values between the optimal humidity of the two parent individuals are taken, thereby generating several offspring individuals.
  • the iterative module is also used to: randomly select several target individuals from all offspring individuals, modify the optimal temperature and/or optimal humidity of the several target individuals, and the first population consists of all unselected target individuals.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Combustion & Propulsion (AREA)
  • Mechanical Engineering (AREA)
  • Thermal Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computing Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Genetics & Genomics (AREA)
  • Physiology (AREA)
  • Cold Air Circulating Systems And Constructional Details In Refrigerators (AREA)

Abstract

本发明提供一种冰箱间室温度和湿度的生成方法，包括：基于间室中的所有食物的属性值，编码得到第一种群；生成第一种群中的每个父辈个体的适应度，从第一种群中删除若干父辈个体得到第二种群；从第二种群中进行编码交叉和变异得到若干后代个体，将若干后代个体组成第一种群；将间室的温度和湿度分别设置为第一种群中的适应度最高的父辈个体的最佳温度和最佳湿度。

Description

冰箱间室温度和湿度的生成方法及生成装置
本申请要求了申请日为2019年3月13日，申请号为201910189691.7，发明名称为“用于冰箱的生成存储间室温度和湿度的方法及其装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明涉及制冷设备技术领域，尤其涉及一种冰箱间室温度和湿度的生成方法及生成装置。
背景技术
冰箱是人们日常生活中常用的一种家用电器，在实际使用中，用户通常会在存储间室中存放多种食物，可以理解的是，每种食物都有其最适宜的温度和湿度，因此，在设置存储间室的温度和湿度时，需要兼顾每种食物。
因此，在冰箱中设计一种存储间室的温度和湿度的自动设置方法和装置，就成为一个亟待解决的问题。
发明内容
本发明的目的在于提供一种冰箱间室的温度和湿度的生成方法及生成装置。
为了实现上述发明目的之一，本发明一实施方式提供一种冰箱间室的温度和湿度的生成方法，包括以下步骤：
获取存储间室中的所有食物以及每个食物的属性值，将每个食物的属性值都进行编码，从而得到第一种群，其中，所述食物的属性值至少包括：能够唯一标记所述食物的标识符、已存储时间、最佳温度、最佳湿度、取出频率、经济价值和可存储时间；
持续进行以下操作，直至第一种群中的每个父辈个体的适应度符合预设条件，所述操作具体包括：生成第一种群中的每个父辈个体的适应度，依照适应度越高，选择概率越大的原则，从第一种群中删除若干父辈个体得到第二种群；从第二种群中选择若干二元组，其中每个二元组包含有两个不同的父辈个体，对每个二元组中的两个父辈个体都进行编码交叉并产生两个后代个体，将所有后代个体中若干个体进行变异从而得到第一种群；
将所述存储间室的温度和湿度分别设置为第一种群中的适应度最高的父辈个体的最佳温度和最佳湿度。
作为本发明一实施方式的进一步改进，所述“将每个食物都进行编码”具体包括：将每个食物都进行浮点数编码。
作为本发明一实施方式的进一步改进，所述“生成第一种群中的每个父辈个体的适应度”具体包括，基于以下方式得到每个父辈个体的适宜度：父辈个体的适应度＝每个食物的适宜度之和，所述食物的适宜度＝k(α(ΔT*Δd T)+β(D-d)+γ(ΔH*Δd H)+λE)，其中，ΔT为所述父辈个体的最佳温度与所述食物的最佳温度之间的差值，D为所述食物的可存储时间，d为所述食物的已存储时间，ΔT为所述父辈个体的最佳湿度与所述食物的最佳湿度之间的差值，E为所述食物的经济价值。
作为本发明一实施方式的进一步改进，所述“对若干二元组中的每个二元组中的两个父辈个体都进行编码交叉并产生两个后代个体”具体包括：对若干二元组中的每个二元组中的两个父辈个体，将两个父辈个体的最佳温度进行交换和/或取两个父辈个体的最佳温度之间的若干中间值和/或将两个父辈个体的最佳湿度进行交换和/或取两个父辈个体的最佳湿度之间的若干中间值，从而生成若干后代个体。
作为本发明一实施方式的进一步改进，所述“将所有后代个体中若干个体进行变异从而得到第一种群”具体包括：从所有后代个体中随机选择的若干目标个体，将所述若干目标个体的最佳温度和/或最佳湿度进行修改，第一种群由所有未被选中的后代个体和所有修改之后的后代个体组成。
本发明实施例还提供了一种冰箱间室的温度和湿度的生成装置，包括以下模块：
初始化模块，用于获取存储间室中的所有食物以及每个食物的属性值，将每个食物的属性值都进行编码，从而得到第一种群，其中，所述食物的属性值至少包括：能够唯一标记所述食物的标识符、已存储时间、最佳温度、最佳湿度、取出频率、经济价值和可存储时间；
迭代模块，用于持续进行以下操作，直至第一种群中的每个父辈个体的适应度符合预设条件，所述操作具体包括：生成第一种群中的每个父辈个体的适应度，依照适应度越高，选择概率越大的原则，从第一种群中删除若干父辈个体得到第二种群；从第二种群中选择若干二元组，其中每个二元组包含有两个不同的父辈个体，对每个二元组中的两个父辈个体都进行编码交叉并产生两个后代个体，将所有后代个体中若干个体进行变异从而得到第一种群；
设置模块，用于将所述存储间室的温度和湿度分别设置为第一种群中的适应度最高的父辈个体的最佳温度和最佳湿度。
作为本发明一实施方式的进一步改进，所述初始化模块还用于：将每个食物都进行浮点 数编码。
作为本发明一实施方式的进一步改进，所述迭代模块还用于，基于以下方式得到每个父辈个体的适宜度：父辈个体的适应度＝每个食物的适宜度之和，所述食物的适宜度＝k(α(ΔT*Δd T)+β(D-d)+γ(ΔH*Δd H)+λE)，其中，ΔT为所述父辈个体的最佳温度与所述食物的最佳温度之间的差值，D为所述食物的可存储时间，d为所述食物的已存储时间，ΔT为所述父辈个体的最佳湿度与所述食物的最佳湿度之间的差值，E为所述食物的经济价值。
作为本发明一实施方式的进一步改进，所述迭代模块还用于：对若干二元组中的每个二元组中的两个父辈个体，将两个父辈个体的最佳温度进行交换和/或取两个父辈个体的最佳温度之间的若干中间值和/或将两个父辈个体的最佳湿度进行交换和/或取两个父辈个体的最佳湿度之间的若干中间值，从而生成若干后代个体。
作为本发明一实施方式的进一步改进，所述迭代模块还用于：从所有后代个体中随机选择的若干目标个体，将所述若干目标个体的最佳温度和/或最佳湿度进行修改，第一种群由所有未被选中的后代个体和所有修改之后的后代个体组成。
相对于现有技术，本发明的技术效果在于：本发明实施例提供一种冰箱间室的温度和湿度的生成方法及生成装置，该方法包括以下步骤：获取存储间室中的所有食物以及每个食物的属性值，将每个食物的属性值都进行编码得到第一种群；持续进行以下操作，直至第一种群中的每个父辈个体的适应度符合预设条件，所述操作具体包括：生成第一种群中的每个父辈个体的适应度，从第一种群中删除若干父辈个体得到第二种群；从第二种群中进行编码交叉和变异得到若干后代个体，将若干后代个体组成第一种群；将所述存储间室的温度和湿度分别设置为第一种群中的适应度最高的父辈个体的最佳温度和最佳湿度，从而能够自动的调节存储间室的温度和湿度。
附图说明
图1是本发明实施例中的冰箱间室温度和湿度的生成方法的流程示意图。
具体实施方式
以下将结合附图所示的各实施方式对本发明进行详细描述。但这些实施方式并不限制本发明，本领域的普通技术人员根据这些实施方式所做出的结构、方法、或功能上的变换均包含在本发明的保护范围内。
本发明实施例提供了一种冰箱间室温度和湿度的生成方法，如图1所示，包括以下步骤：
步骤101：获取存储间室中的所有食物以及每个食物的属性值，将每个食物的属性值都进行编码，从而得到第一种群，其中，所述食物的属性值至少包括：能够唯一标记所述食物的标识符、已存储时间、最佳温度、最佳湿度、取出频率、经济价值和可存储时间；这里，该冰箱可以包含有一个数据库，该数据库包含有该存储间室中所存储的所有食物的信息，即当用户向存储间室中放入食物时，获取当前时间(可以理解的是，该当前时间即为该食物的放入时间)，将该食物的信息和放入时间存入该数据库中，当用户从存储间室中取走食物时，从该数据库中删除该食物的信息。这里，标识符可以为一个字符串，该字符串能够唯一的标识一个食物；已存储时间为当前时间与该食物的放入时间之间的时间差，最佳温度为最适宜该食物保存的温度，最佳湿度为最适宜该食物保存的湿度，取出频率为与该食品属于同一类型的食物在一段时间内的取出次数(例如，在该存储间室中，用户可能多次向该存储间室中放入牛肉，则在一段时间内，用户取出牛肉的次数，就可以为牛肉的取出频率)，经济价值是一个反应该食物的价格的指数(该指数与该食物的价格呈正比)，可存储时间即该食物在该存储间室中能够存放的时间。
这里，在第一代种群中，每个个体都对应到一种食物，即该个体的最佳温度等于所对应的食物的最佳温度，该个体的最佳湿度等于所对应的食物的最佳湿度。
步骤102：持续进行以下操作，直至第一种群中的每个父辈个体的适应度符合预设条件，所述操作具体包括：生成第一种群中的每个父辈个体的适应度，依照适应度越高，选择概率越大的原则，从第一种群中删除若干父辈个体得到第二种群；从第二种群中选择若干二元组，其中每个二元组包含有两个不同的父辈个体，对每个二元组中的两个父辈个体都进行编码交叉并产生两个后代个体，将所有后代个体中若干个体进行变异从而得到第一种群。这里，在第一代种群中，如果第一个体与第一食物是对应的，则在第一个体所代表的温度和湿度下，第一食物能够获得最佳的存储效果，但其余的食物就无法获得最佳的存储效果了，因此，在该步骤中会进行多次迭代，直至每个父辈个体的适应度符合预设条件，该预设条件可以：每两个父辈个体之间的适应度的差值低于某个值，或者在上次迭代和本次迭代中，父辈个体的适宜度之间差值比较小。
步骤103：将所述存储间室的温度和湿度分别设置为第一种群中的适应度最高的父辈个体的最佳温度和最佳湿度。
优选的，所述“将每个食物都进行编码”具体包括：将每个食物都进行浮点数编码。
优选的，所述“生成第一种群中的每个父辈个体的适应度”，具体包括，
基于以下方式得到每个父辈个体的适宜度：父辈个体的适应度＝每个食物的适宜度之和， 所述食物的适宜度＝k(α(ΔT*Δd T)+β(D-d)+γ(ΔH*Δd H)+λE)，其中，ΔT为所述父辈个体的最佳温度与所述食物的最佳温度之间的差值，D为所述食物的可存储时间，d为所述食物的已存储时间，ΔT为所述父辈个体的最佳湿度与所述食物的最佳湿度度之间的差值，E为所述食物的经济价值。这里，当存储间室中的温度等于该父辈个体的最佳温度且最佳适度等于该父辈个体的最佳湿度时，每个食物的适宜度是不一样的，因此，需要考虑每个食物的适宜度。
优选的，所述“对若干二元组中的每个二元组中的两个父辈个体都进行编码交叉并产生两个后代个体”具体包括：对若干二元组中的每个二元组中的两个父辈个体，将两个父辈个体的最佳温度进行交换和/或取两个父辈个体的最佳温度之间的若干中间值和/或将两个父辈个体的最佳湿度进行交换和/或取两个父辈个体的最佳湿度之间的若干中间值，从而生成若干后代个体。这里，生成后代个体的方式有：(1)将两个父辈个体的最佳温度进行交换；(2)取两个父辈个体的最佳温度之间的若干中间值；(3)将两个父辈个体的最佳湿度进行交换；(4)取两个父辈个体的最佳湿度之间的若干中间值，此外，也可以从这四种方式中任选集中来生成后代个体。
优选的，所述“将所有后代个体中若干个体进行变异从而得到第一种群”具体包括：
从所有后代个体中随机选择的若干目标个体，将所述若干目标个体的最佳温度和/或最佳湿度进行修改，第一种群由所有未被选中的后代个体和所有修改之后的后代个体组成。
此时，冰箱间室温度和湿度的生成方法还可以可以根据用户交互习惯、价值取向等调整算法输出结果。例如：将最优天数统一表征为任务形式，其中，s代表环境信息，d代表储存天数信息，q(s)代表环境信息分布情况，代表在环境下通过调整参数过度到环境下。基于食物的温度偏差ΔT、湿度偏差ΔH、经济价值E、取出频率k、已存储时间d、可存储时间D设计一种适应度函数。该函数权重通过线下实验寻找到最优值，依据线上用户使用习惯进行微调。
其中，食物的适宜度＝{Days(s 1,d 1,...,s H,d H),q(s 1),q(s t+1|s t,d t),H}，
Figure PCTCN2019100740-appb-000001
本发明实施例还提供了一种冰箱间室温度和湿度的生成装置，包括以下模块：
初始化模块，用于获取存储间室中的所有食物以及每个食物的属性值，将每个食物的属性值都进行编码，从而得到第一种群，其中，所述食物的属性值至少包括：能够唯一标记所述食物的标识符、已存储时间、最佳温度、最佳湿度、取出频率、经济价值和可存储时间；
迭代模块，用于持续进行以下操作，直至第一种群中的每个父辈个体的适应度符合预设条件，所述操作具体包括：生成第一种群中的每个父辈个体的适应度，依照适应度越高，选择概率越大的原则，从第一种群中删除若干父辈个体得到第二种群；从第二种群中选择若干二元组，其中每个二元组包含有两个不同的父辈个体，对每个二元组中的两个父辈个体都进行编码交叉并产生两个后代个体，将所有后代个体中若干个体进行变异从而得到第一种群；
设置模块，用于将所述存储间室的温度和湿度分别设置为第一种群中的适应度最高的父辈个体的最佳温度和最佳湿度。
优选的，所述初始化模块还用于：将每个食物都进行浮点数编码。
优选的，所述迭代模块还用于，基于以下方式得到每个父辈个体的适宜度：父辈个体的适应度＝每个食物的适宜度之和，所述食物的适宜度＝k(α(ΔT*Δd T)+β(D-d)+γ(ΔH*Δd H)+λE)，其中，ΔT为所述父辈个体的最佳温度与所述食物的最佳温度之间的差值，D为所述食物的可存储时间，d为所述食物的已存储时间，ΔT为所述父辈个体的最佳湿度与所述食物的最佳湿度度之间的差值，E为所述食物的经济价值。
优选的，所述迭代模块还用于：对若干二元组中的每个二元组中的两个父辈个体，将两个父辈个体的最佳温度进行交换和/或取两个父辈个体的最佳温度之间的若干中间值和/或将两个父辈个体的最佳湿度进行交换和/或取两个父辈个体的最佳湿度之间的若干中间值，从而生成若干后代个体。
优选的，所述迭代模块还用于：从所有后代个体中随机选择的若干目标个体，将所述若干目标个体的最佳温度和/或最佳湿度进行修改，第一种群由所有未被选中的后代个体和所有修改之后的后代个体组成。
应当理解，虽然本说明书按照实施方式加以描述，但并非每个实施方式仅包含一个独立的技术方案，说明书的这种叙述方式仅仅是为清楚起见，本领域技术人员应当将说明书作为一个整体，各实施方式中的技术方案也可以经适当组合，形成本领域技术人员可以理解的其他实施方式。
上文所列出的一系列的详细说明仅仅是针对本发明的可行性实施方式的具体说明，它们并非用以限制本发明的保护范围，凡未脱离本发明技艺精神所作的等效实施方式或变更均应包含在本发明的保护范围之内。

Claims (10)

  1. 一种冰箱间室温度和湿度的生成方法，其特征在于，包括以下步骤：
    获取存储间室中的所有食物以及每个食物的属性值，将每个食物的属性值都进行编码，从而得到第一种群，其中，所述食物的属性值至少包括：能够唯一标记所述食物的标识符、已存储时间、最佳温度、最佳湿度、取出频率、经济价值和可存储时间；
    持续进行以下操作，直至第一种群中的每个父辈个体的适应度符合预设条件，所述操作具体包括：生成第一种群中的每个父辈个体的适应度，依照适应度越高，选择概率越大的原则，从第一种群中删除若干父辈个体得到第二种群；从第二种群中选择若干二元组，其中每个二元组包含有两个不同的父辈个体，对每个二元组中的两个父辈个体都进行编码交叉并产生两个后代个体，将所有后代个体中若干个体进行变异从而得到第一种群；
    将所述存储间室的温度和湿度分别设置为第一种群中的适应度最高的父辈个体的最佳温度和最佳湿度。
  2. 根据权利要求1中所述的冰箱间室温度和湿度的生成方法，其特征在于，所述“将每个食物的属性值都进行编码”包括：将每个食物都进行浮点数编码。
  3. 根据权利要求1所述的冰箱间室温度和湿度的生成方法，其特征在于，所述“生成第一种群中的每个父辈个体的适应度”包括，
    基于以下方式得到每个父辈个体的适宜度：父辈个体的适应度＝每个食物的适宜度之和，所述食物的适宜度＝k(α(ΔT*Δd T)+β(D-d)+γ(ΔH*Δd H)+λE)，其中，ΔT为所述父辈个体的最佳温度与所述食物的最佳温度之间的差值，D为所述食物的可存储时间，d为所述食物的已存储时间，ΔT为所述父辈个体的最佳湿度与所述食物的最佳湿度度之间的差值，E为所述食物的经济价值。
  4. 根据权利要求1所述的冰箱间室温度和湿度的生成方法，其特征在于，所述“对每个二元组中的两个父辈个体都进行编码交叉并产生两个后代个体”包括：
    对若干二元组中的每个二元组中的两个父辈个体，将两个父辈个体的最佳温度进行交换和/或取两个父辈个体的最佳温度之间的若干中间值和/或将两个父辈个体的最佳湿度进行交换和/或取两个父辈个体的最佳湿度之间的若干中间值，从而生成若干后代个体。
  5. 根据权利要求2所述的冰箱间室温度和湿度的生成方法，其特征在于，所述“将所有后代个体中若干个体进行变异从而得到第一种群”包括：
    从所有后代个体中随机选择的若干目标个体，将所述若干目标个体的最佳温度和/或最 佳湿度进行修改，第一种群由所有未被选中的后代个体和所有修改之后的后代个体组成。
  6. 一种冰箱间室温度和湿度的生成装置，其特征在于，包括以下模块：
    初始化模块，用于获取存储间室中的所有食物以及每个食物的属性值，将每个食物的属性值都进行编码，从而得到第一种群，其中，所述食物的属性值至少包括：能够唯一标记所述食物的标识符、已存储时间、最佳温度、最佳湿度、取出频率、经济价值和可存储时间；
    迭代模块，用于持续进行以下操作，直至第一种群中的每个父辈个体的适应度符合预设条件，所述操作具体包括：生成第一种群中的每个父辈个体的适应度，依照适应度越高，选择概率越大的原则，从第一种群中删除若干父辈个体得到第二种群；从第二种群中选择若干二元组，其中每个二元组包含有两个不同的父辈个体，对每个二元组中的两个父辈个体都进行编码交叉并产生两个后代个体，将所有后代个体中若干个体进行变异从而得到第一种群；
    设置模块，用于将所述存储间室的温度和湿度分别设置为第一种群中的适应度最高的父辈个体的最佳温度和最佳湿度。
  7. 根据权利要求6中所述的冰箱间室温度和湿度的生成装置，其特征在于，所述初始化模块还用于：将每个食物都进行浮点数编码。
  8. 根据权利要求6所述的冰箱间室温度和湿度的生成装置，其特征在于，所述迭代模块还用于，
    基于以下方式得到每个父辈个体的适宜度：父辈个体的适应度＝每个食物的适宜度之和，所述食物的适宜度＝k(α(ΔT*Δd T)+β(D-d)+γ(ΔH*Δd H)+λE)，其中，ΔT为所述父辈个体的最佳温度与所述食物的最佳温度之间的差值，D为所述食物的可存储时间，d为所述食物的已存储时间，ΔT为所述父辈个体的最佳湿度与所述食物的最佳湿度度之间的差值，E为所述食物的经济价值。
  9. 根据权利要求6所述的冰箱间室温度和湿度的生成装置，其特征在于，所述迭代模块还用于：
    对若干二元组中的每个二元组中的两个父辈个体，将两个父辈个体的最佳温度进行交换和/或取两个父辈个体的最佳温度之间的若干中间值和/或将两个父辈个体的最佳湿度进行交换和/或取两个父辈个体的最佳湿度之间的若干中间值，从而生成若干后代个体。
  10. 根据权利要求7所述的冰箱间室温度和湿度的生成装置，其特征在于，所述迭代模块还用于：
    从所有后代个体中随机选择的若干目标个体，将所述若干目标个体的最佳温度和/或最 佳湿度进行修改，第一种群由所有未被选中的后代个体和所有修改之后的后代个体组成。
PCT/CN2019/100740 2019-03-13 2019-08-15 冰箱间室温度和湿度的生成方法及生成装置 WO2020181723A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
EP19918899.6A EP3940326A4 (en) 2019-03-13 2019-08-15 METHOD AND DEVICE FOR PRODUCING REFRIGERATOR COMPARTMENT TEMPERATURE AND HUMIDITY

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910189691.7A CN111692833B (zh) 2019-03-13 2019-03-13 用于冰箱的生成存储间室温度和湿度的方法及其装置
CN201910189691.7 2019-03-13

Publications (1)

Publication Number Publication Date
WO2020181723A1 true WO2020181723A1 (zh) 2020-09-17

Family

ID=72427676

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/100740 WO2020181723A1 (zh) 2019-03-13 2019-08-15 冰箱间室温度和湿度的生成方法及生成装置

Country Status (3)

Country Link
EP (1) EP3940326A4 (zh)
CN (1) CN111692833B (zh)
WO (1) WO2020181723A1 (zh)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0716278A1 (en) * 1994-12-10 1996-06-12 Samsung Electronics Co., Ltd. Refrigerator and process for controlling the temperature of such
KR100188925B1 (ko) * 1994-11-30 1999-06-01 김광호 유전자 알고리즘-퍼지 추론을 이용한 냉장고 온도 제어장치 및 방법
KR100195090B1 (ko) * 1994-11-15 1999-06-15 윤종용 유전자 알고리즘-퍼지 추론을 이용한 냉장고 온도 제어 장치 및 방법
CN105222508A (zh) * 2015-09-29 2016-01-06 青岛海尔智能家电科技有限公司 面向变温室的食品自适应冷藏方法、装置及系统
CN107477972A (zh) * 2017-08-18 2017-12-15 楼旦丹 一种人工智能蔬菜冰箱
CN107606870A (zh) * 2017-08-10 2018-01-19 深圳益创信息科技有限公司 一种智能制冷方法及冰箱
CN109436582A (zh) * 2018-12-25 2019-03-08 广州好高冷科技有限公司 一种基于目标周期的保温箱多模式温控系统及方法

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH09318165A (ja) * 1996-05-29 1997-12-12 Hitachi Ltd 電気冷蔵庫
KR100214659B1 (ko) * 1997-06-12 1999-08-02 구자홍 퍼지추론을 이용한 냉장고 온도제어방법
CN1288409C (zh) * 2003-12-18 2006-12-06 广东科龙电器股份有限公司 一种多冷区冰箱及其食物监控方法
TWI577953B (zh) * 2011-11-30 2017-04-11 強生控制科技公司 用以降低冷凍系統中噪音之系統及方法
KR101260649B1 (ko) * 2012-02-27 2013-05-03 부산대학교 산학협력단 상황인식 기반의 스마트 냉장고 관리 시스템 및 방법
CN204027202U (zh) * 2014-08-13 2014-12-17 合肥美菱股份有限公司 一种冰箱智能生物保鲜系统
US9989266B2 (en) * 2014-12-22 2018-06-05 Battelle Memorial Institute Automatic set point detection for water heaters operating in a demand response
CN106598197B (zh) * 2016-11-28 2019-11-22 东软集团股份有限公司 确定系统中设备功率的方法和装置
CN109140896A (zh) * 2017-06-13 2019-01-04 合肥华凌股份有限公司 控制冰箱储存空间湿度的方法及装置、冰箱、存储介质
CN108444110B (zh) * 2018-04-11 2019-06-25 南通大学 基于bp网络预测的空气源热泵热水系统设计方法

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100195090B1 (ko) * 1994-11-15 1999-06-15 윤종용 유전자 알고리즘-퍼지 추론을 이용한 냉장고 온도 제어 장치 및 방법
KR100188925B1 (ko) * 1994-11-30 1999-06-01 김광호 유전자 알고리즘-퍼지 추론을 이용한 냉장고 온도 제어장치 및 방법
EP0716278A1 (en) * 1994-12-10 1996-06-12 Samsung Electronics Co., Ltd. Refrigerator and process for controlling the temperature of such
CN105222508A (zh) * 2015-09-29 2016-01-06 青岛海尔智能家电科技有限公司 面向变温室的食品自适应冷藏方法、装置及系统
CN107606870A (zh) * 2017-08-10 2018-01-19 深圳益创信息科技有限公司 一种智能制冷方法及冰箱
CN107477972A (zh) * 2017-08-18 2017-12-15 楼旦丹 一种人工智能蔬菜冰箱
CN109436582A (zh) * 2018-12-25 2019-03-08 广州好高冷科技有限公司 一种基于目标周期的保温箱多模式温控系统及方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3940326A4

Also Published As

Publication number Publication date
EP3940326A1 (en) 2022-01-19
CN111692833A (zh) 2020-09-22
CN111692833B (zh) 2021-08-24
EP3940326A4 (en) 2022-08-24

Similar Documents

Publication Publication Date Title
CN110555112B (zh) 一种基于用户正负偏好学习的兴趣点推荐方法
Aljuaid et al. Proper imputation techniques for missing values in data sets
CN104298873B (zh) 一种基于遗传算法和粗糙集的属性约简方法及精神状态评估方法
Lawrence Multiobjective genetic algorithms for materialized view selection in OLAP data warehouses
Yadav et al. An overview of genetic algorithm and modeling
CN107256241B (zh) 基于网格与差异替换改进多目标遗传算法的电影推荐方法
CN106844637A (zh) 基于正交与聚类修剪改进多目标遗传算法的电影推荐方法
CN103824115A (zh) 面向开放网络知识库的实体间关系推断方法及系统
Zou et al. Reinforcement learning to diversify top-n recommendation
CN106997553A (zh) 一种基于多目标优化的商品组合模式的挖掘方法
Dasgupta et al. sGA: A structured genetic algorithm
Bhargavi et al. Soil classification using gatree
WO2020181723A1 (zh) 冰箱间室温度和湿度的生成方法及生成装置
CN110471854B (zh) 一种基于高维数据混合约简的缺陷报告指派方法
CN110134861B (zh) 一种基于项目类别和用户偏好的推荐方法
Kumar et al. A survey on soft computing-based high-utility itemsets mining
CN116186278A (zh) 一种基于超平面投影与关系路径邻域的知识图谱补全方法
Talebian et al. Using genetic algorithm to select materialized views subject to dual constraints
Wang et al. PHUIMUS: a potential high utility itemsets mining algorithm based on stream data with uncertainty
CN110659362A (zh) 一种自动调节候选范围的推荐方法和系统
Zhao et al. A novel krill herd algorithm with orthogonality and its application to data clustering
Abu Nayeem et al. Genetic algorithm to solve the p-centre and p-radius problem on a network
Guntupalli et al. High-Scale Food Recommendation Built on Apache Spark using Alternating Least Squares
CN117272838B (zh) 一种政务大数据平台数据采集优化方法
CN110909238B (zh) 一种考虑竞争模式的关联挖掘算法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19918899

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2019918899

Country of ref document: EP

Effective date: 20211013