Method for constructing energy efficiency and water efficiency optimization model of washing machine

Abstract

The invention discloses a method for constructing an energy efficiency and water efficiency optimization model of a washing machine. The method comprises the steps of obtaining load data, a cleaning image, an environment temperature, washing parameters and consumption data of the washing machine; inputting the load data into a preset stain identification model to obtain stain data, and inputting the cleaning image into the preset stain identification model to obtain cleaning data; clustering the stain data and the load data to obtain washing difficulty data, and obtaining a washing parameter threshold according to the washing difficulty data and the washing parameters; constructing an energy efficiency function according to the environment temperature, the washing parameters and the consumption data, and constructing a water efficiency function according to the load data, the washing parameters and the washing difficulty data; and establishing a washing machine energy efficiency and water efficiency optimization model according to the washing parameter threshold, the energy efficiency function and the water efficiency function, inputting the to-be-optimized data into the washing machine energy efficiency and water efficiency optimization model, and outputting an optimization result. The method improves the precision of energy efficiency and water efficiency optimization of the washing machine, and can be directly applied to an energy efficiency and water efficiency optimization system of the washing machine.

Description

Technical Field

[0001] The present invention relates to the field of energy efficiency and water efficiency optimization of washing machines, and in particular to a method for constructing an energy efficiency and water efficiency optimization model of a washing machine. Background Art

[0002] At present, most washing machines on the market use fixed washing programs, and it is impossible to set personalized washing parameters according to the actual degree of stains, materials and weight of clothes. This one-size-fits-all washing method not only reduces the washing effect, but also may cause damage to clothes. In addition, with the increase in environmental awareness and the shortage of water resources, consumers have put forward higher requirements for the energy efficiency and water efficiency of washing machines. Therefore, it is particularly important to develop an optimization model that can dynamically adjust washing parameters according to actual washing needs.

[0003] In recent years, with the development of artificial intelligence and big data technology, the intelligence level of washing machines has gradually improved. Some new washing machines have begun to introduce sensors and image recognition technology, which can monitor the stains and material characteristics of clothes in real time, so as to adjust the washing program. However, the existing technology still has shortcomings in stain recognition, washing parameter optimization, and energy efficiency and water efficiency modeling, and has not yet formed a systematic and operational optimization model. Therefore, studying a washing machine energy efficiency and water efficiency optimization model based on multidimensional data analysis can not only improve the energy efficiency and water efficiency of washing machines, but also provide consumers with a better washing experience, which has important practical significance and application value. Summary of the invention

[0004] The purpose of the present invention is to provide a method for constructing an energy efficiency and water efficiency optimization model for a washing machine.

[0005] To achieve the above object, the present invention is implemented according to the following technical solutions:

[0006] The present invention comprises the following steps:

[0007] Obtain washing machine load data, cleaning images, ambient temperature, washing parameters and consumption data;

[0008] Inputting the load data into a preset stain recognition model to obtain stain data, and inputting the cleaning image into a preset stain recognition model to obtain cleaning data;

[0009] Clustering the stain data and the load data to obtain washing difficulty data, and obtaining a washing parameter threshold value according to the washing difficulty data and the washing parameter;

[0010] constructing an energy efficiency function according to the ambient temperature, the washing parameters and the consumption data, and constructing a water efficiency function according to the load data, the washing parameters and the washing difficulty data;

[0011] A washing machine energy efficiency and water efficiency optimization model is established according to the washing parameter threshold, the energy efficiency function and the water efficiency function, the data to be optimized is input into the washing machine energy efficiency and water efficiency optimization model, and the optimization result is output.

[0012] Furthermore, the method for obtaining load data, cleaning images, ambient temperature, washing parameters and consumption data of a washing machine includes:

[0013] The load data includes images and basic data of clothes before washing, the cleaning images are images of clothes after washing, the washing parameters include the set water temperature, set water level, inner drum speed and washing time for each washing of the washing machine, and the consumption data includes the power consumption and water consumption of the washing machine for each washing.

[0014] Furthermore, the method of inputting the load data into a preset stain recognition model to obtain stain data, and inputting the cleaning image into a preset stain recognition model to obtain cleaning data comprises:

[0015] The preset stain recognition model uses the YOLOv5 algorithm to learn and identify the types of stains in clothing images based on the clothing stain image dataset. The stain ratio of different types of stains and the total stain ratio are obtained according to the proportion of stain pixels in the clothing. The clothing stain image dataset contains the labels of the stain types of pixels.

[0016] The images of clothes before and after washing are input into the stain recognition model, and the obtained stain types, stain proportions of different stain types and total stain proportions are used as stain data and cleaning data respectively.

[0017] Furthermore, the method of clustering the stain data and the load data to obtain washing difficulty data includes:

[0018] Calculate the ratio of the stain ratio of the stain type in the cleaning data and the stain data to get the stain residual ratio, calculate the average stain residual ratio of each stain type, encode the material of the clothes, use the basic data of the clothes, the average stain residual ratio of the stain type of the clothes, the stain ratio and the total stain ratio to establish data points, fill the vacant values ​​in the data points with 0, and the offset vector of the data points:

[0019]

[0020] Among them, M h( x ) is the offset vector, x represents the data point, G(·) is the kernel function, h is the sliding window size, is the i-th data point x i The weight of , e is the base of the natural logarithm, ε is the bandwidth of the local weighting, n is the number of data points,

[0021] Probability density function:

[0022]

[0023] Where d is the dimension, K(·) is the kernel density estimation function,

[0024] Kernel density gradient estimation:

[0025]

[0026] in, f ( x ) The gradient of g (x) is the kernel function The probability density function of

[0027] In the clustering results, the ratio of the total stain ratio in the clean data and the stain data of the data point is taken as the total stain residual ratio of the data point, the average value of the total stain residual ratio in each cluster is calculated as the cluster stain residual ratio of the cluster, and the cluster stain residual ratio is taken as the washing difficulty data of the cluster.

[0028] Furthermore, the method for obtaining a washing parameter threshold value according to the washing difficulty data and the washing parameter comprises:

[0029] The washing parameters whose stain residue ratio is less than the cleaning threshold are removed according to the preset cleaning threshold, and the maximum and minimum values ​​of the washing parameters of the clothes in the washing difficulty data are used as the washing parameter thresholds of the washing difficulty data.

[0030] Furthermore, the method of constructing an energy efficiency function according to the ambient temperature, the washing parameters and the consumption data, and constructing a water efficiency function according to the load data, the washing parameters and the washing difficulty data includes:

[0031] Ambient temperature and washing parameters are the independent variables of the energy efficiency function, and the basic data of clothing, washing parameters and washing difficulty data are the independent variables of the water efficiency function. The energy efficiency data and water efficiency data are calculated according to the consumption data as the target values ​​of the energy efficiency function and the water efficiency function, and a regression model is established to fit the independent variables and target values ​​of the energy efficiency function and the water efficiency function respectively:

[0032] The decision function of the regression model is:

[0033] f(x)=ω T τ(x)+b,b∈R

[0034] Among them, f(x) is the linear regression function, x is the independent variable, τ(·) is the mapping function, ω T is the transpose of ω, ω and b are the weight vector and bias to be determined, R represents a real number,

[0035] Lagrangian objective function of the regression model:

[0036]

[0037] Where L is the Lagrangian objective function and the Lagrangian multiplier μ i , α i , μ i and is the slack multiplier associated with the slack variable, C is the regularization parameter, α i and x i The corresponding Lagrange multipliers for the upper and lower boundaries, f(x i ) is based on x i The obtained i The predicted value, y i For x i The corresponding target value, ε is the tolerance error, and the minimum value of the Lagrangian function is solved to obtain the optimal optimization multiplier. The weight vector and bias are obtained according to the optimal optimization multiplier. The energy efficiency function and water efficiency function obtained according to the regression model are:

[0038] y nx =f nx ( x nx ) =ω nx T τ ( x nx ) +b nx

[0039] y sx =f sx (x sx ) =ω sx T τ(x sx ) +b sx

[0040] where f nx( · ) and f sx( · ) are energy efficiency function and water efficiency function respectively, x nx and x sx are the independent variables of energy efficiency function and water efficiency function, y nx and sx are energy efficiency data and water efficiency data respectively, ω nx and ω sxare the weight vectors of energy efficiency function and water efficiency function, b nx and b sx are the biases of the energy efficiency function and the water efficiency function respectively.

[0041] Furthermore, a method for establishing a washing machine energy efficiency and water efficiency optimization model according to the washing parameter threshold, the energy efficiency function and the water efficiency function, inputting the data to be optimized into the washing machine energy efficiency and water efficiency optimization model, and outputting the optimization result includes:

[0042] The initial population is randomly generated, each individual represents a solution to a set of washing parameters, and the individual searches in the search space composed of washing parameter thresholds. The individual's target optimization vector is:

[0043] F max =(f nx ( c ) , f sx ( c ) )

[0044] Among them, F max is the target optimization vector of the individual, c is the position of the individual in the search space, (f nx( c ) , f sx( c ) ) is the vector of energy efficiency data and water efficiency data corresponding to individual c,

[0045] Perform non-dominated sorting on individuals, divide the population into different non-dominated frontiers, use crossover and mutation to update the positions of individuals, select the best non-dominated frontier as the optimal solution set after the position update, and calculate the crossover rate:

[0046]

[0047] Among them, p c is the crossover rate, δ ( · ) is the indicator function, p cavg 、p cmax and p cmin They are p c The average value, maximum value and minimum value of the t is the current iteration number, T is the preset maximum iteration number, d ( i ) is the crowding degree of the ith individual, d avg ( i ) is the average crowding degree of the non-dominated frontier where the i-th individual is located, and the mutation rate is calculated as:

[0048]

[0049] Among them, p m is the mutation rate, p magv 、p mmax and p mmin They are p m The average, maximum and minimum values ​​of

[0050] When the maximum number of iterations is reached, the optimal solution set is output. According to the weights of energy efficiency data and water efficiency data, the weighted Euclidean length of the target optimization vector in the optimal solution set is calculated as the individual fitness value, and the solution with the largest fitness value in the optimal solution set is taken as the optimal solution.

[0051] The ambient temperature of the data to be optimized, the basic data of the clothes and the washing difficulty data are used as fixed values ​​of the energy efficiency function and the water efficiency function, and are input into the washing machine energy efficiency and water efficiency optimization model to obtain the optimal washing parameters as the optimization result.

[0052] In a second aspect, an embodiment of the present application further provides an electronic device, including:

[0053] A processor; and a memory arranged to store computer executable instructions, which when executed cause the processor to perform the method steps described in the first aspect.

[0054] In a third aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple applications, the electronic device executes the method steps described in the first aspect.

[0055] The beneficial effects of the present invention are:

[0056] The present invention is a method for constructing an energy efficiency and water efficiency optimization model for a washing machine. Compared with the prior art, the present invention has the following technical effects:

[0057] The present invention realizes dynamic optimization of washing parameters of washing machines by constructing a washing machine energy efficiency and water efficiency optimization model. The model can intelligently adjust washing parameters according to stain recognition results and washing difficulty assessment to achieve optimal energy efficiency and water efficiency. Compared with the prior art, the present invention not only improves the energy efficiency and water efficiency of washing machines, but also enhances the controllability of washing effects, providing users with a more energy-saving and environmentally friendly washing solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 A flowchart of the steps of a method for constructing an energy efficiency and water efficiency optimization model for a washing machine according to the present invention;

[0059] Figure 2 It is a schematic diagram of the structure of an electronic device in an embodiment of this specification. DETAILED DESCRIPTION

[0060] The present invention is further described below by means of specific embodiments. The illustrative embodiments and descriptions of the present invention are used to explain the present invention but are not intended to limit the present invention.

[0061] A method for constructing a washing machine energy efficiency and water efficiency optimization model of the present invention comprises the following steps:

[0062] like Figure 1 As shown, in this embodiment, the following steps are included:

[0063] Obtain washing machine load data, cleaning images, ambient temperature, washing parameters and consumption data;

[0064] In the actual evaluation, the washing machine selected was a pulsator washing machine. During washing, detergent was added in proportion to the weight of the clothes. The data obtained included image data before and after the clothes were cleaned and the following data:

[0065]

[0066]

[0067] Inputting the load data into a preset stain recognition model to obtain stain data, and inputting the cleaning image into a preset stain recognition model to obtain cleaning data;

[0068] In the actual evaluation, the stain data and cleaning data of the samples are:

[0069] sample Type of stain before washing Percentage of stains before washing Type of stain after washing Percentage of stains after washing 1 Stain A 0.3 Stain A 0.1 2 Stain B 0.2 Stain B 0.05 3 Stain A 0.25 Stain A 0.15 4 Stain C 0.15 Stain C 0.05 5 Stains D 0.4 Stains D 0.2 ;

[0070] Clustering the stain data and the load data to obtain washing difficulty data, and obtaining a washing parameter threshold value according to the washing difficulty data and the washing parameter;

[0071] In the actual evaluation, the washing difficulty data of samples 1 and 3 is 0.46, the washing difficulty data of samples 2 and 4 is 0.29, and the washing difficulty data of sample 5 is 0.5. The washing parameter thresholds are: the clothes with washing difficulty data of 0.46 are the maximum and minimum values ​​of the washing parameters of samples 1 and 3, the clothes with washing difficulty data of 0.29 are the maximum and minimum values ​​of the washing parameters of samples 2 and 4, and the clothes with washing difficulty data of 0.5 are the washing parameters of sample 5 as the minimum value;

[0072] constructing an energy efficiency function according to the ambient temperature, the washing parameters and the consumption data, and constructing a water efficiency function according to the load data, the washing parameters and the washing difficulty data;

[0073] Establishing a washing machine energy efficiency and water efficiency optimization model according to the washing parameter threshold, the energy efficiency function and the water efficiency function, inputting the data to be optimized into the washing machine energy efficiency and water efficiency optimization model, and outputting the optimization result;

[0074] In the actual evaluation, the data to be optimized is sample 1, and the optimized washing parameters are:

[0075] Water temperature: 35℃, water level: 48L, speed: 750rpm, washing time: 55 minutes.

[0076] In this embodiment, the method for obtaining load data, cleaning images, ambient temperature, washing parameters and consumption data of a washing machine includes:

[0077] The load data includes images and basic data of clothes before washing, the cleaning images are images of clothes after washing, the washing parameters include the set water temperature, set water level, inner drum speed and washing time for each washing of the washing machine, and the consumption data includes the power consumption and water consumption of the washing machine for each washing.

[0078] In this embodiment, the method of inputting the load data into a preset stain recognition model to obtain stain data, and inputting the cleaning image into a preset stain recognition model to obtain cleaning data includes:

[0079] The preset stain recognition model uses the YOLOv5 algorithm to learn and identify the types of stains in clothing images based on the clothing stain image dataset. The stain ratio of different types of stains and the total stain ratio are obtained according to the proportion of stain pixels in the clothing. The clothing stain image dataset contains the labels of the stain types of pixels.

[0080] The images of clothes before and after washing are input into the stain recognition model, and the obtained stain types, stain proportions of different stain types and total stain proportions are used as stain data and cleaning data respectively.

[0081] In this embodiment, the method of clustering the stain data and the load data to obtain the washing difficulty data includes:

[0082] Calculate the ratio of the stain ratio of the stain type in the cleaning data and the stain data to get the stain residual ratio, calculate the average stain residual ratio of each stain type, encode the material of the clothes, use the basic data of the clothes, the average stain residual ratio of the stain type of the clothes, the stain ratio and the total stain ratio to establish data points, fill the vacant values ​​in the data points with 0, and the offset vector of the data points:

[0083]

[0084] Among them, M h( x )is the offset vector, x represents the data point, G(·) is the kernel function, h is the sliding window size, is the i-th data point x i The weight of , e is the base of the natural logarithm, ε is the bandwidth of the local weighting, n is the number of data points,

[0085] Probability density function:

[0086]

[0087] Where d is the dimension, K(·) is the kernel density estimation function,

[0088] Kernel density gradient estimation:

[0089]

[0090] in, f ( x ) The gradient of g (x) is the kernel function The probability density function of

[0091] In the clustering results, the ratio of the total stain ratio in the clean data and the stain data of the data point is taken as the total stain residual ratio of the data point, the average value of the total stain residual ratio in each cluster is calculated as the cluster stain residual ratio of the cluster, and the cluster stain residual ratio is taken as the washing difficulty data of the cluster.

[0092] In this embodiment, the method for obtaining the washing parameter threshold value according to the washing difficulty data and the washing parameter includes:

[0093] The washing parameters whose stain residue ratio is less than the cleaning threshold are removed according to the preset cleaning threshold, and the maximum and minimum values ​​of the washing parameters of the clothes in the washing difficulty data are used as the washing parameter thresholds of the washing difficulty data.

[0094] In this embodiment, the method of constructing an energy efficiency function according to the ambient temperature, the washing parameters and the consumption data, and constructing a water efficiency function according to the load data, the washing parameters and the washing difficulty data includes:

[0095] Ambient temperature and washing parameters are the independent variables of the energy efficiency function, and the basic data of clothing, washing parameters and washing difficulty data are the independent variables of the water efficiency function. The energy efficiency data and water efficiency data are calculated according to the consumption data as the target values ​​of the energy efficiency function and the water efficiency function, and a regression model is established to fit the independent variables and target values ​​of the energy efficiency function and the water efficiency function respectively:

[0096] The decision function of the regression model is:

[0097] f(x)=ωT τ(x)+b,b∈R

[0098] Among them, f(x) is the linear regression function, x is the independent variable, τ(·) is the mapping function, ω T is the transpose of ω, ω and b are the weight vector and bias to be determined, R represents a real number,

[0099] Lagrangian objective function of the regression model:

[0100]

[0101]

[0102] Where L is the Lagrangian objective function and the Lagrangian multiplier μ i , α i , μ i and is the slack multiplier associated with the slack variable, C is the regularization parameter, α i and x i The corresponding Lagrange multipliers for the upper and lower boundaries, f(x i ) is based on x i The obtained i The predicted value, y i For x i The corresponding target value, ε is the tolerance error, and the minimum value of the Lagrangian function is solved to obtain the optimal optimization multiplier. The weight vector and bias are obtained according to the optimal optimization multiplier. The energy efficiency function and water efficiency function obtained according to the regression model are:

[0103] y nx =f nx ( x nx ) =ω nx T τ ( x nx ) +b nx

[0104] y sx =f sx (x sx ) =ω sx T τ(x sx ) +b sx

[0105] where f nx( ·) and f sx( · ) are energy efficiency function and water efficiency function respectively, x nx and x sx are the independent variables of energy efficiency function and water efficiency function, y nx and sx are energy efficiency data and water efficiency data respectively, ω nx and ω sx are the weight vectors of energy efficiency function and water efficiency function, b nx and b sx are the biases of the energy efficiency function and the water efficiency function respectively.

[0106] In this embodiment, a method for establishing a washing machine energy efficiency and water efficiency optimization model according to the washing parameter threshold, the energy efficiency function and the water efficiency function, inputting the data to be optimized into the washing machine energy efficiency and water efficiency optimization model, and outputting the optimization result includes:

[0107] The initial population is randomly generated, each individual represents a solution to a set of washing parameters, and the individual searches in the search space composed of washing parameter thresholds. The individual's target optimization vector is:

[0108] F max =(f nx ( c ) , f sx ( c ) )

[0109] Among them, F max is the target optimization vector of the individual, c is the position of the individual in the search space, (f nx( c ) , f sx( c ) ) is the vector of energy efficiency data and water efficiency data corresponding to individual c,

[0110] Perform non-dominated sorting on individuals, divide the population into different non-dominated frontiers, use crossover and mutation to update the positions of individuals, select the best non-dominated frontier as the optimal solution set after the position update, and calculate the crossover rate:

[0111]

[0112] Among them, p c is the crossover rate, δ ( · ) is an indicator function. It takes the value 1 when the condition in the brackets is met, otherwise it takes the value 0. cavg 、p cmax and p cmin They are p cThe average value, maximum value and minimum value of the t is the current iteration number, T is the preset maximum iteration number, d ( i ) is the crowding degree of the ith individual, d avg ( i ) is the average crowding degree of the non-dominated frontier where the i-th individual is located, and the mutation rate is calculated as:

[0113]

[0114] Among them, p m is the mutation rate, p magv 、p mmax and p mmin They are p m The average, maximum and minimum values ​​of

[0115] When the maximum number of iterations is reached, the optimal solution set is output. According to the weights of energy efficiency data and water efficiency data, the weighted Euclidean length of the target optimization vector in the optimal solution set is calculated as the individual fitness value, and the solution with the largest fitness value in the optimal solution set is taken as the optimal solution.

[0116] The ambient temperature of the data to be optimized, the basic data of the clothes and the washing difficulty data are used as fixed values ​​of the energy efficiency function and the water efficiency function, and are input into the washing machine energy efficiency and water efficiency optimization model to obtain the optimal washing parameters as the optimization result.

[0117] Figure 2 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 2 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.

[0118] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0119] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.

[0120] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a device for constructing a washing machine energy efficiency and water efficiency optimization model at the logical level. The processor executes the program stored in the memory and is specifically used to execute any of the aforementioned methods for constructing a washing machine energy efficiency and water efficiency optimization model.

[0121] The above application Figure 1 The method for constructing a washing machine energy efficiency and water efficiency optimization model disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or instructions in the form of software. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in a decoding processor. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0122] The electronic device may also perform Figure 1 A method for constructing a washing machine energy efficiency and water efficiency optimization model is proposed, and the Figure 1 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0123] An embodiment of the present application also proposes a computer-readable storage medium, which stores one or more programs, and the one or more programs include instructions. When the instructions are executed by an electronic device including multiple applications, they execute any of the aforementioned methods for constructing a washing machine energy efficiency and water efficiency optimization model.

[0124] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0125] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0126] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0127] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0128] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0129] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0130] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0131] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0132] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0133] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for constructing a washing machine energy efficiency and water efficiency optimization model, characterized in that: The following steps are involved: Obtain washing machine load data, cleaning images, ambient temperature, washing parameters and consumption data; Inputting the load data into a preset stain recognition model to obtain stain data, and inputting the cleaning image into a preset stain recognition model to obtain cleaning data; Clustering the stain data and the load data to obtain washing difficulty data, and obtaining a washing parameter threshold value according to the washing difficulty data and the washing parameter; constructing an energy efficiency function according to the ambient temperature, the washing parameters and the consumption data, and constructing a water efficiency function according to the load data, the washing parameters and the washing difficulty data; A washing machine energy efficiency and water efficiency optimization model is established according to the washing parameter threshold, the energy efficiency function and the water efficiency function, the data to be optimized is input into the washing machine energy efficiency and water efficiency optimization model, and the optimization result is output.

2. The method for constructing a washing machine energy efficiency and water efficiency optimization model according to claim 1, characterized in that: A method for obtaining load data, cleaning images, ambient temperature, washing parameters, and consumption data of a washing machine, comprising: The load data includes images and basic data of clothes before washing, the cleaning images are images of clothes after washing, the washing parameters include the set water temperature, set water level, inner drum speed and washing time for each washing of the washing machine, and the consumption data includes the power consumption and water consumption of the washing machine for each washing.

3. The method for constructing a washing machine energy efficiency and water efficiency optimization model according to claim 1, characterized in that: The method of inputting the load data into a preset stain recognition model to obtain stain data, and inputting the cleaning image into a preset stain recognition model to obtain cleaning data comprises: The preset stain recognition model uses the YOLOv5 algorithm to learn and identify the types of stains in clothing images based on the clothing stain image dataset. The stain ratio of different types of stains and the total stain ratio are obtained according to the proportion of stain pixels in the clothing. The clothing stain image dataset contains the labels of the stain types of pixels. The images of clothes before and after washing are input into the stain recognition model, and the obtained stain types, stain proportions of different stain types and total stain proportions are used as stain data and cleaning data respectively.

4. The method for constructing a washing machine energy efficiency and water efficiency optimization model according to claim 1, characterized in that: The method for clustering the stain data and the load data to obtain washing difficulty data comprises: Calculate the ratio of the stain ratio of the stain type in the cleaning data and the stain data to get the stain residual ratio, calculate the average stain residual ratio of each stain type, encode the material of the clothes, use the basic data of the clothes, the average stain residual ratio of the stain type of the clothes, the stain ratio and the total stain ratio to establish data points, fill the vacant values ​​in the data points with 0, and the offset vector of the data points: Among them, M h( x ) is the offset vector, x represents the data point, G(·) is the kernel function, h is the sliding window size, is the i-th data point x i The weight of , e is the base of the natural logarithm, ε is the bandwidth of the local weighting, n is the number of data points, Probability density function: Where d is the dimension, K(·) is the kernel density estimation function, Kernel density gradient estimation: in, f ( x ) The gradient of g (x) is the kernel function The probability density function of In the clustering results, the ratio of the total stain ratio in the clean data and the stain data of the data point is taken as the total stain residual ratio of the data point, the average value of the total stain residual ratio in each cluster is calculated as the cluster stain residual ratio of the cluster, and the cluster stain residual ratio is taken as the washing difficulty data of the cluster.

5. The method for constructing a washing machine energy efficiency and water efficiency optimization model according to claim 1, characterized in that: The method for obtaining a washing parameter threshold value according to the washing difficulty data and the washing parameter comprises: The washing parameters whose stain residue ratio is less than the cleaning threshold are removed according to the preset cleaning threshold, and the maximum and minimum values ​​of the washing parameters of the clothes in the washing difficulty data are used as the washing parameter thresholds of the washing difficulty data.

6. The method for constructing a washing machine energy efficiency and water efficiency optimization model according to claim 1, characterized in that: The method of constructing an energy efficiency function according to the ambient temperature, the washing parameters and the consumption data, and constructing a water efficiency function according to the load data, the washing parameters and the washing difficulty data, comprises: Ambient temperature and washing parameters are the independent variables of the energy efficiency function, and the basic data of clothing, washing parameters and washing difficulty data are the independent variables of the water efficiency function. The energy efficiency data and water efficiency data are calculated according to the consumption data as the target values ​​of the energy efficiency function and the water efficiency function, and a regression model is established to fit the independent variables and target values ​​of the energy efficiency function and the water efficiency function respectively: The decision function of the regression model is: f ( x ) =ω T t ( x ) +b,b∈R Among them, f ( x ) is the linear regression function, x is the independent variable, τ ( · ) is the mapping function, ω T is the transpose of ω, ω and b are the weight vector and bias to be determined, R represents a real number, Lagrangian objective function of the regression model: Among them, L is the Lagrangian objective function, and the Lagrangian multiplier μ i and is the slack multiplier associated with the slack variable, C is the regularization parameter, α i and x i The corresponding Lagrange multipliers for the upper and lower boundaries, f(x i ) is based on x i The obtained i The predicted value, y i For x i The corresponding target value, ε is the tolerance error, and the minimum value of the Lagrangian function is solved to obtain the optimal optimization multiplier. The weight vector and bias are obtained according to the optimal optimization multiplier. The energy efficiency function and water efficiency function obtained according to the regression model are: y nx =f nx (x nx )=ω nx T τ(x nx )+b nx y sx =f sx (x sx )=ω sx T τ(x sx )+b sx where f nx( · ) and f sx( · ) are energy efficiency function and water efficiency function respectively, x nx and x sx are the independent variables of energy efficiency function and water efficiency function, y nx and sx are energy efficiency data and water efficiency data respectively, ω nx and ω sx are the weight vectors of energy efficiency function and water efficiency function, b nx and b sx are the biases of the energy efficiency function and the water efficiency function respectively.

7. The method for constructing a washing machine energy efficiency and water efficiency optimization model according to claim 1, characterized in that: The method of establishing a washing machine energy efficiency and water efficiency optimization model according to the washing parameter threshold, the energy efficiency function and the water efficiency function, inputting the data to be optimized into the washing machine energy efficiency and water efficiency optimization model, and outputting the optimization result comprises: The initial population is randomly generated, each individual represents a solution to a set of washing parameters, and the individual searches in the search space composed of washing parameter thresholds. The individual's target optimization vector is: F max =(f nx ( c ) ,f sx ( c ) ) Among them, F max is the target optimization vector of the individual, c is the position of the individual in the search space, (f nx( c ) , f sx( c ) ) is the vector of energy efficiency data and water efficiency data corresponding to individual c, Perform non-dominated sorting on individuals, divide the population into different non-dominated frontiers, use crossover and mutation to update the positions of individuals, select the best non-dominated frontier as the optimal solution set after the position update, and calculate the crossover rate: Among them, p c is the crossover rate, δ ( · ) is the indicator function, p cavg 、p cmax and p cmin They are p c The average value, maximum value and minimum value of the t is the current iteration number, T is the preset maximum iteration number, d ( i ) is the crowding degree of the ith individual, d avg ( i ) is the average crowding degree of the non-dominated frontier where the i-th individual is located, and the mutation rate is calculated as: Among them, p m is the mutation rate, p magv 、p mmax and p mmin They are p m The average, maximum and minimum values ​​of When the maximum number of iterations is reached, the optimal solution set is output. According to the weights of energy efficiency data and water efficiency data, the weighted Euclidean length of the target optimization vector in the optimal solution set is calculated as the individual fitness value, and the solution with the largest fitness value in the optimal solution set is taken as the optimal solution. The ambient temperature of the data to be optimized, the basic data of the clothes and the washing difficulty data are used as fixed values ​​of the energy efficiency function and the water efficiency function, and are input into the washing machine energy efficiency and water efficiency optimization model to obtain the optimal washing parameters as the optimization result.

8. An electronic device comprising: processor; as well as A memory arranged to store computer executable instructions, which when executed cause the processor to perform the method according to any one of claims 1 to 7.

9. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, enables the electronic device to execute the method according to any one of claims 1 to 7.

Images