CN114108232A - Foam amount prediction method and device, storage medium and washing equipment - Google Patents

Foam amount prediction method and device, storage medium and washing equipment Download PDF

Info

Publication number
CN114108232A
CN114108232A CN202111463309.0A CN202111463309A CN114108232A CN 114108232 A CN114108232 A CN 114108232A CN 202111463309 A CN202111463309 A CN 202111463309A CN 114108232 A CN114108232 A CN 114108232A
Authority
CN
China
Prior art keywords
washing
foam
parameter
correlation
amount
Prior art date
Legal status (The legal status 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 status listed.)
Granted
Application number
CN202111463309.0A
Other languages
Chinese (zh)
Other versions
CN114108232B (en
Inventor
董贵平
蔡莎莎
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
TCL Home Appliances Hefei Co Ltd
Original Assignee
TCL Home Appliances Hefei Co Ltd
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 TCL Home Appliances Hefei Co Ltd filed Critical TCL Home Appliances Hefei Co Ltd
Priority to CN202111463309.0A priority Critical patent/CN114108232B/en
Publication of CN114108232A publication Critical patent/CN114108232A/en
Application granted granted Critical
Publication of CN114108232B publication Critical patent/CN114108232B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • D—TEXTILES; PAPER
    • D06—TREATMENT OF TEXTILES OR THE LIKE; LAUNDERING; FLEXIBLE MATERIALS NOT OTHERWISE PROVIDED FOR
    • D06F—LAUNDERING, DRYING, IRONING, PRESSING OR FOLDING TEXTILE ARTICLES
    • D06F33/00—Control of operations performed in washing machines or washer-dryers 
    • D06F33/30—Control of washing machines characterised by the purpose or target of the control 
    • D06F33/32—Control of operational steps, e.g. optimisation or improvement of operational steps depending on the condition of the laundry
    • D—TEXTILES; PAPER
    • D06—TREATMENT OF TEXTILES OR THE LIKE; LAUNDERING; FLEXIBLE MATERIALS NOT OTHERWISE PROVIDED FOR
    • D06F—LAUNDERING, DRYING, IRONING, PRESSING OR FOLDING TEXTILE ARTICLES
    • D06F34/00—Details of control systems for washing machines, washer-dryers or laundry dryers
    • D06F34/04—Signal transfer or data transmission arrangements
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Abstract

The application provides a foam amount prediction method, a device, a storage medium and washing equipment, wherein the foam amount prediction method comprises the following steps: acquiring a plurality of washing parameters of the washing equipment; calculating the correlation of each washing parameter with the amount of foam; determining a target washing parameter with correlation meeting a preset condition from the plurality of washing parameters; and predicting the foam amount in the washing process of the washing equipment according to the target washing parameters and a foam prediction model. According to the method, the correlation between each washing parameter and the foam quantity is calculated, and the foam quantity generated in the washing process of the washing equipment is predicted through the foam prediction model according to the target washing parameter with the correlation meeting the preset condition. The accuracy of foam quantity prediction of the washing equipment is improved.

Description

Foam amount prediction method and device, storage medium and washing equipment
Technical Field
The application belongs to the technical field of washing equipment, and particularly relates to a foam quantity prediction method and device and washing equipment.
Background
During the washing process, foam is generated due to friction between the detergent and the laundry, and the amount of the foam may become an important factor affecting the washing effect. If the foam amount is too much, the pressure of the inner drum of the washing machine is increased, and the filled foam makes the motor of the washing machine rotate laboriously, so that the service life of the washing machine is influenced. Therefore, the prediction of the amount of foam is very important, and the accuracy of the prediction of the amount of foam is low at present.
Disclosure of Invention
The embodiment of the application provides a foam quantity prediction method and device, a storage medium and washing equipment, and can improve the accuracy of predicting the foam quantity generated in the washing process of the washing equipment.
The embodiment of the application provides a foam quantity prediction method, which comprises the following steps:
acquiring a plurality of washing parameters of the washing equipment;
calculating the correlation of each washing parameter with the amount of foam;
determining a target washing parameter with correlation meeting a preset condition from the plurality of washing parameters;
and predicting the foam amount in the washing process of the washing equipment according to the target washing parameters and a foam prediction model.
Optionally, the calculating the correlation between each washing parameter and the amount of foam comprises:
calculating a correlation value between each washing parameter and the amount of foam by normalizing the mutual information;
the determining of the target washing parameter of which the correlation satisfies the preset condition from the plurality of washing parameters includes:
and determining a target washing parameter with the correlation value larger than the correlation threshold value from the plurality of washing parameters.
Optionally, the determining, from the plurality of washing parameters, a target washing parameter with a correlation value greater than a correlation threshold value includes:
calculating a correlation mean value according to the correlation value of each washing parameter;
and determining a target washing parameter with a correlation value larger than the correlation mean value from the plurality of washing parameters.
Optionally, the calculating a correlation value between each washing parameter and the amount of foam by normalizing mutual information includes:
calculating the entropy of each washing parameter and the entropy of the foam amount;
calculating the joint entropy of each washing parameter and foam amount;
calculating mutual information of the entropy and the joint entropy;
and normalizing the mutual information to obtain a correlation value between each washing parameter and the foam quantity.
Optionally, the method further includes:
by the formula
Figure BDA0003390119020000021
Calculating the entropy of each washing parameter by formula
Figure BDA0003390119020000022
Calculating the entropy of the amount of foam, wherein p (x)k) Is xkProbability density of p (y)l) Is ylThe probability density of (d);
by the formula
Figure BDA0003390119020000023
Calculating the joint entropy of each washing parameter and foam amount, wherein p (x)k,yl) Is xkAnd ylA joint probability density function of (a);
calculating mutual information of the entropy and the joint entropy by formula I (X, Y) ═ H (X) + H (Y) -H (X, Y);
by the formula
Figure BDA0003390119020000024
A correlation value between each washing parameter and the amount of foam was obtained.
Optionally, the method further includes:
acquiring a plurality of historical washing parameters of the washing equipment;
calculating the correlation between each historical washing parameter and the historical foam amount;
determining a target historical washing parameter with correlation meeting a preset condition from the plurality of historical washing parameters;
and constructing the foam prediction model according to the target historical washing parameters and a support vector regression model.
Optionally, the constructing the foam prediction model according to the target historical washing parameter and a support vector regression model includes:
by the formula
Figure BDA0003390119020000025
Constructing the foam prediction model, wherein
Figure BDA0003390119020000026
Is Lagrange multiplier, b is bias variable, k (x)i,xj) Is a kernel function, the target historical washing parameter is used as an input parameter of the kernel function, and f (x) is output as a predicted foam amount.
An embodiment of the present application further provides a foam amount prediction device, where the device includes:
the acquisition module is used for acquiring a plurality of washing parameters of the washing equipment;
a calculation module for calculating the correlation of each washing parameter with the amount of foam;
the determining module is used for determining a target washing parameter of which the correlation meets a preset condition from the plurality of washing parameters;
and the prediction module is used for predicting the foam amount in the washing process of the washing equipment according to the target washing parameters and the foam prediction model.
Embodiments of the present application also provide a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the steps of the foam quantity prediction method as described above.
Embodiments of the present application also provide a washing device, which includes a processor, a memory, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the foam amount prediction method as described above when executing the program.
According to the foam quantity prediction method provided by the embodiment of the application, the correlation between each washing parameter and the foam quantity is calculated, and the foam quantity generated in the washing process of the washing equipment is predicted through the foam prediction model according to the target washing parameter with the correlation meeting the preset condition. The accuracy of foam quantity prediction of the washing equipment can be improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings used in the description of the embodiments will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the application, and that other drawings can be derived from these drawings by a person skilled in the art without inventive effort.
For a more complete understanding of the present application and its advantages, reference is now made to the following descriptions taken in conjunction with the accompanying drawings. Wherein like reference numerals refer to like parts in the following description.
Fig. 1 is a first flowchart of a foam quantity prediction method according to an embodiment of the present disclosure.
Fig. 2 is a second flow chart of a foam quantity prediction method provided in an embodiment of the present application.
Fig. 3 is a schematic structural diagram of a foam quantity prediction apparatus provided in an embodiment of the present application.
Fig. 4 is a schematic structural diagram of a washing apparatus according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. It is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, fig. 1 is a first flow chart of a foam quantity prediction method according to an embodiment of the present disclosure. The washing machine is applied to washing equipment, and the washing equipment can be a pulsator washing machine, a drum washing machine, an agitator washing machine, a jet washing machine and the like. The foam quantity prediction method comprises the following steps:
101, a plurality of washing parameters of a washing device are acquired.
The washing parameter of the washing apparatus may be a parameter generated by the washing apparatus during the washing process, for example, the washing parameter of the washing apparatus may be a water temperature parameter, a detergent amount parameter, a water inflow parameter, a washing pattern parameter, a load weight parameter, a capacity parameter of the washing tub, a type parameter of the washing apparatus, a water inflow speed parameter of the washing apparatus, and the like. It should be noted that the washing parameters may also include other parameters, and all the washing parameters generated in the washing process belong to the washing parameters.
102, calculating the correlation of each washing parameter with the amount of foam.
The correlation between the temperature of the washing water and the amount of the generated bubbles, the correlation between the amount of the inputted water and the amount of the generated bubbles, the correlation between the kind of the washing pattern and the amount of the generated bubbles, the correlation between the amount of the load weight and the amount of the generated bubbles, the correlation between the amount of the washing tub and the amount of the generated bubbles, the correlation between the type of the washing apparatus and the amount of the generated bubbles, the correlation between the speed of the inputted water and the amount of the generated bubbles, etc. are calculated, respectively, the correlation between each washing parameter and the amount of the bubbles, the correlation between the inputted water parameter and the amount of the bubbles, the correlation between the washing pattern parameter and the amount of the bubbles, the correlation between the load weight parameter and the amount of the bubbles, etc, A correlation between a capacity parameter of the washing tub and a bubble amount, a correlation between a type parameter of the washing apparatus and a bubble amount, a correlation between a water inlet speed parameter of the washing apparatus and a bubble amount, etc.
And 103, determining a target washing parameter with correlation meeting a preset condition from the plurality of washing parameters.
And determining a correlation parameter meeting a preset condition from the correlations of the washing parameters and the foam amount, and determining a target washing parameter according to the correlation parameter meeting the preset condition. It is understood that the washing parameter strongly correlated with the amount of foam generation is labeled as the target washing parameter.
And 104, predicting the foam amount in the washing process of the washing equipment according to the target washing parameters and the foam prediction model.
According to the foam quantity prediction method provided by the embodiment of the application, the correlation between each washing parameter and the foam quantity is calculated, the target washing parameter with the correlation meeting the preset condition is used as the input parameter of the foam prediction model, the foam prediction model outputs the foam quantity, and compared with the method that all the washing parameters are used as the input parameters of the foam prediction model, the washing parameters with the correlation meeting the preset condition are screened in advance, and the accuracy of foam quantity prediction of the washing equipment can be improved.
Referring to fig. 2, fig. 2 is a second flow chart of the foam quantity prediction method according to the embodiment of the present disclosure. The foam quantity prediction method comprises the following steps:
a plurality of washing parameters of a washing apparatus are obtained 201.
The washing parameter of the washing apparatus may be a parameter generated by the washing apparatus during the washing process, for example, the washing parameter of the washing apparatus may be a water temperature parameter, a detergent amount parameter, a water inflow parameter, a washing pattern parameter, a load weight parameter, a capacity parameter of the washing tub, a type parameter of the washing apparatus, a water inflow speed parameter of the washing apparatus, and the like. It should be noted that the washing parameters may also include other parameters, and all the washing parameters generated in the washing process belong to the washing parameters.
The water temperature parameter of the washing equipment can be acquired through the temperature sensor, the detergent quantity parameter is acquired through the detergent liquid level sensor, the water inflow parameter is acquired through the water level sensor, the washing mode parameter selected by a user is acquired through the main control board, the load weight parameter is acquired through the weight sensor of the washing barrel, the capacity parameter of the washing barrel and the type parameter of the washing equipment are acquired through the preset specification parameters of the washing equipment, and the water inflow speed parameter and the like are acquired through the sensor of the water inlet valve. It should be noted that the method for obtaining the washing parameters is only exemplary, and the washing parameters can also be obtained by other manners.
A correlation value between each washing parameter and the amount of foam is calculated by normalizing the mutual information 202.
Calculating a correlation value between each washing parameter and the amount of foam by normalizing the mutual information may include:
calculating the entropy of each washing parameter and the entropy of the foam amount;
calculating the joint entropy of each washing parameter and foam amount;
calculating mutual information of the entropy and the joint entropy;
and normalizing the mutual information to obtain a correlation value between each washing parameter and the foam quantity.
Further, it can be represented by the formula
Figure BDA0003390119020000051
Calculating the entropy of each washing parameter by formula
Figure BDA0003390119020000052
Calculating the entropy of the amount of foam, wherein p (x)k) Is xkProbability density of p (y)l) Is ylThe probability density of (c).
Can be represented by formula
Figure BDA0003390119020000061
Calculating the joint entropy of each washing parameter and foam amount, wherein p (x)x,yl) Is xkAnd ylThe joint probability density function of (a).
Mutual information of the entropy and the joint entropy may be calculated by formula I (X, Y) ═ H (X) + H (Y) -H (X, Y);
can be represented by formula
Figure BDA0003390119020000062
A correlation value between each washing parameter and the amount of foam was obtained.
The normalized mutual information NMI is obtained by scaling the mutual information between [0 and 1], so that the influence of different dimensions and value ranges is counteracted, the relation existing among original samples is kept, the correlation between each washing parameter and the generated foam quantity can be obtained by normalizing the mutual information, and the larger the correlation value is, the stronger the relation between the washing parameter and the foam quantity corresponding to the correlation value is.
And 203, calculating a correlation mean value according to the correlation value of each washing parameter.
Adding the correlation mean values corresponding to each washing parameter, dividing by the number of the washing parameters to obtain the correlation mean value, and using the correlation mean value as a correlation threshold value which can be calculated by a formula
Figure BDA0003390119020000063
Calculating the mean value of the correlation, NMIiFor each washing parameter corresponding correlation value, NMIdIs the correlation mean.
And 204, determining a target washing parameter with the correlation value larger than the correlation mean value from the plurality of washing parameters.
And selecting the washing parameter with the correlation value larger than the correlation mean value as the target washing parameter.
And 205, predicting the foam amount in the washing process of the washing equipment according to the target washing parameters and the foam prediction model.
The foam prediction model can be obtained by training in the following way:
a plurality of historical washing parameters of the washing equipment are acquired, wherein the historical washing parameters can be historical washing parameters generated in the historical washing process by the washing equipment. The historical wash parameter of the washing appliance may be a parameter generated by the washing appliance during a historical wash process, for example, the historical wash parameter may be a historical water temperature parameter, a historical detergent amount parameter, a historical water inflow parameter, a historical wash pattern parameter, a historical load weight parameter, a capacity parameter of the washing tub, a type parameter of the washing appliance, a water inflow speed parameter of the historical washing appliance, and the like. It should be noted that the historical washing parameters may also include other parameters, and all the washing parameters generated in the washing process belong to the washing parameters. The historical water temperature parameter of the washing equipment can be acquired through the temperature sensor, the historical detergent quantity parameter is acquired through the detergent liquid level sensor, the historical water inflow parameter is acquired through the water level sensor, the historical washing mode parameter selected by a user is acquired through the main control board, the historical load weight parameter is acquired through the weight sensor of the washing barrel, the capacity parameter of the washing barrel and the type parameter of the washing equipment are acquired through the preset specification parameter of the washing equipment, and the historical water inflow speed parameter and the like are acquired through the sensor of the water inlet valve. It should be noted that the method for obtaining the washing parameters is only exemplary, and the washing parameters can also be obtained by other manners.
And calculating the correlation between each historical washing parameter and the historical foam amount, wherein the correlation value between each washing parameter and the historical foam amount can be calculated by normalizing mutual information. Wherein, the entropy of each historical washing parameter and the entropy of the historical foam amount can be calculated; calculating the joint entropy of each historical washing parameter and historical foam amount; calculating mutual information of the entropy and the joint entropy; and normalizing the mutual information to obtain a correlation value between each historical washing parameter and the historical foam amount.
A target history washing parameter having a correlation satisfying a preset condition is determined from the plurality of history washing parameters, and a washing parameter having a correlation value greater than a correlation threshold value may be marked as the target history washing parameter.
And constructing a foam prediction model according to the target historical washing parameters and the support vector regression model. The Support Vector Regression (SVR) is an application of an SVM (Support Vector machine) to a Regression problem, well solves the construction problem of a high-dimensional model with a limited number of samples, and the constructed model has good prediction performance.
Constructing the foam prediction model from the target historical wash parameters and the support vector regression model may include:
by the formula
Figure BDA0003390119020000071
Constructing an untrained foam prediction model, wherein
Figure BDA0003390119020000072
Is Lagrange multiplier, b is bias variable, k (x)i,xj) Is a kernel function with a target historical wash parameter as an input parameter to the kernel function, and f (x) is output asPredicted amount of foam. The kernel function may be a gaussian function, but in some embodiments, the kernel function may also be another function.
And retraining the model on the training set by the obtained untrained foam prediction model, finally constructing to obtain a foam prediction model value, and finally constructing the obtained foam prediction model to be the trained foam prediction model.
In some embodiments, the foam prediction model may not be built and trained within the washing apparatus, and may be built and trained on a server or other electronic device, such as on the pc (personal computer) side of the support vector regression calculation software.
The embodiment of the application provides a foam quantity prediction method. Compared with the problem that the foam quantity generated in the washing process cannot be accurately predicted and the washing quality is influenced due to the randomness of manually selecting washing parameters to predict the foam quantity or the generality of taking all washing parameters as model input parameters through a neural network model, the method selects the parameters with high correlation with the foam quantity as the input variables of the support vector regression model through the normalized mutual information to predict the foam quantity, selects the parameters with high correlation with the foam quantity as the model input and accurately predicts the foam quantity under the condition of limited data.
In some embodiments, after obtaining the predicted amount of foam, the following steps may also be performed:
calculating the defoaming duration according to the foam quantity;
updating the displayed washing time length according to the defoaming time length, wherein the updating the displayed washing time length according to the defoaming time length comprises the following steps:
determining a load for executing a defoaming action and an execution time length when the load executes the defoaming action according to the foam quantity;
and determining the defoaming duration according to the execution duration.
In some embodiments, after obtaining the predicted amount of foam, the following steps may also be performed:
determining a corresponding defoaming program according to the foam quantity;
if the foam amount is within a first preset range, defoaming through a first defoaming procedure;
if the foam amount is within a second preset range, defoaming through a second defoaming procedure;
if the foam amount is within a third preset range, defoaming through a third defoaming procedure;
the minimum value of the first preset range is larger than the maximum value of the second preset range, the minimum value of the second preset range is larger than the maximum value of the third preset range, the defoaming time of the first defoaming program is larger than the defoaming time of the second defoaming program, and the defoaming time of the second defoaming program is larger than the defoaming time of the third defoaming program.
Referring to fig. 3, fig. 3 is a schematic structural diagram of a foam quantity predicting device according to an embodiment of the present disclosure. The embodiment of the present application further provides a foam amount prediction device, and the foam amount prediction device includes:
the acquisition module is used for acquiring a plurality of washing parameters of the washing equipment;
a calculation module for calculating the correlation of each washing parameter with the amount of foam;
the determining module is used for determining a target washing parameter of which the correlation meets a preset condition from the plurality of washing parameters;
and the prediction module is used for predicting the foam amount in the washing process of the washing equipment according to the target washing parameters and the foam prediction model.
In some embodiments, the computing module is further to: calculating a correlation value between each washing parameter and the amount of foam by normalizing the mutual information;
the determination module is further configured to: and determining a target washing parameter with the correlation value larger than the correlation threshold value from the plurality of washing parameters.
In some embodiments, the determining module is further configured to:
calculating a correlation mean value according to the correlation value of each washing parameter;
and determining a target washing parameter with a correlation value larger than the correlation mean value from the plurality of washing parameters.
In some embodiments, the computing module is further to:
calculating the entropy of each washing parameter and the entropy of the foam amount;
calculating the joint entropy of each washing parameter and foam amount;
calculating mutual information of the entropy and the joint entropy;
and normalizing the mutual information to obtain a correlation value between each washing parameter and the foam quantity.
In some embodiments, the computing module is further to:
by the formula
Figure BDA0003390119020000091
Calculating the entropy of each washing parameter by formula
Figure BDA0003390119020000092
Calculating the entropy of the amount of foam, wherein p (x)k) Is xkProbability density of p (y)l) Is ylThe probability density of (c).
By the formula
Figure BDA0003390119020000093
Calculating the joint entropy of each washing parameter and foam amount, wherein p (x)k,yl) Is xkAnd ylThe joint probability density function of (a).
Calculating mutual information of the entropy and the joint entropy by formula I (X, Y) ═ H (X) + H (Y) -H (X, Y);
by the formula
Figure BDA0003390119020000094
A correlation value between each washing parameter and the amount of foam was obtained.
In some embodiments, the foam amount prediction apparatus further comprises:
a historical washing parameter obtaining module for obtaining a plurality of historical washing parameters of the washing equipment;
a historical correlation calculation module for calculating the correlation between each historical washing parameter and the historical foam amount;
the target historical washing parameter determining module is used for determining a target historical washing parameter of which the correlation meets a preset condition from the plurality of historical washing parameters;
and the construction module is used for constructing the foam prediction model according to the target historical washing parameters and a support vector regression model.
In some embodiments, the build module is further configured to:
by the formula
Figure BDA0003390119020000101
Constructing the foam prediction model, wherein
Figure BDA0003390119020000102
Is Lagrange multiplier, b is bias variable, k (x)i,xj) Is a kernel function, the target historical washing parameter is used as an input parameter of the kernel function, and f (x) is output as a predicted foam amount.
Referring to fig. 4, fig. 4 is a schematic structural diagram of a washing apparatus provided in an embodiment of the present application, and an embodiment of the present application further provides a washing apparatus, which includes a processor, a memory, and a computer program stored in the memory and operable on the processor, where the processor in a circuit of the washing apparatus may be configured to perform:
acquiring a plurality of washing parameters of the washing equipment;
calculating the correlation of each washing parameter with the amount of foam;
determining a target washing parameter with correlation meeting a preset condition from the plurality of washing parameters;
and predicting the foam amount in the washing process of the washing equipment according to the target washing parameters and a foam prediction model.
In some embodiments, in the calculating the correlation of each wash parameter to the amount of foam, the processor is further configured to:
calculating a correlation value between each washing parameter and the amount of foam by normalizing the mutual information;
the determining of the target washing parameter of which the correlation satisfies the preset condition from the plurality of washing parameters includes:
and determining a target washing parameter with the correlation value larger than the correlation threshold value from the plurality of washing parameters.
In some embodiments, when said determining the target washing parameter from the plurality of washing parameters that has a correlation value greater than the correlation threshold value, the process is further configured to perform:
calculating a correlation mean value according to the correlation value of each washing parameter;
and determining a target washing parameter with a correlation value larger than the correlation mean value from the plurality of washing parameters.
In some embodiments, in the calculating the correlation value between each wash parameter and the amount of foam by normalizing the mutual information, the processor is further configured to perform:
calculating the entropy of each washing parameter and the entropy of the foam amount;
calculating the joint entropy of each washing parameter and foam amount;
calculating mutual information of the entropy and the joint entropy;
and normalizing the mutual information to obtain a correlation value between each washing parameter and the foam quantity.
In some embodiments, the processor is further configured to perform:
by the formula
Figure BDA0003390119020000111
Calculating the entropy of each washing parameter by formula
Figure BDA0003390119020000112
Calculating the entropy of the amount of foam, wherein p (x)k) Is xkProbability density of p (y)l) Is ylThe probability density of (c).
By the formula
Figure BDA0003390119020000113
Calculating the joint entropy of each washing parameter and foam amount, wherein p (x)k,yl) Is xkAnd ylThe joint probability density function of (a).
Calculating mutual information of the entropy and the joint entropy by formula I (X, Y) ═ H (X) + H (Y) -H (X, Y);
by the formula
Figure BDA0003390119020000114
A correlation value between each washing parameter and the amount of foam was obtained.
In some embodiments, the processor is further configured to perform:
acquiring a plurality of historical washing parameters of the washing equipment;
calculating the correlation between each historical washing parameter and the historical foam amount;
determining a target historical washing parameter with correlation meeting a preset condition from the plurality of historical washing parameters;
and constructing the foam prediction model according to the target historical washing parameters and a support vector regression model.
In some embodiments, in the building the foam prediction model from the target historical washing parameters and a support vector regression model, the processor is further configured to perform:
by the formula
Figure BDA0003390119020000115
Constructing the foam prediction model, wherein
Figure BDA0003390119020000116
Is Lagrange multiplier, b is bias variable, k (x)i,xj) Is a kernel function, the target historical washing parameter is used as an input parameter of the kernel function, and f (x) is output as a predicted foam amount.
It will be appreciated that in some embodiments, the foam prediction model may not be built and trained within the washing apparatus, and may be built and trained on a server or other electronic device, such as on the pc (personal computer) side of the support vector regression calculation software.
In some embodiments, the washing apparatus may further include a drying device, a driving device, an intelligent module, and the like, the drying device may dry the dehydrated laundry, and the intelligent module may be linked with the driving device, the water inlet and drain device, the heating device, the drying device, and the like, and drive the driving device, the water inlet and drain device, the heating device, and the drying device according to a user's requirement, wherein the intelligent module may further include a voice module, and each function device of the washing machine may be operated through a voice signal.
Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be performed by associated hardware as instructed by a computer program, which may be stored on a computer readable storage medium, which may include, but is not limited to: read Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disks, and the like.
In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the description of the present application, the terms "first", "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implying any number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more features.
The method, the device and the washing equipment for predicting the foam amount provided by the embodiments of the present application are described in detail above, and the principle and the implementation manner of the present application are explained by applying specific examples herein, and the description of the above embodiments is only used to help understanding the method and the core idea of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims (10)

1. A foam amount prediction method applied to a washing device is characterized by comprising the following steps:
acquiring a plurality of washing parameters of the washing equipment;
calculating the correlation of each washing parameter with the amount of foam;
determining a target washing parameter with correlation meeting a preset condition from the plurality of washing parameters;
and predicting the foam amount in the washing process of the washing equipment according to the target washing parameters and a foam prediction model.
2. The foam amount prediction method according to claim 1, wherein the calculating of the correlation of each washing parameter with the foam amount comprises:
calculating a correlation value between each washing parameter and the amount of foam by normalizing the mutual information;
the determining of the target washing parameter of which the correlation satisfies the preset condition from the plurality of washing parameters includes:
and determining a target washing parameter with the correlation value larger than the correlation threshold value from the plurality of washing parameters.
3. The foam quantity prediction method according to claim 2, wherein the determining a target washing parameter from the plurality of washing parameters, the correlation value of which is greater than the correlation threshold value, comprises:
calculating a correlation mean value according to the correlation value of each washing parameter;
and determining a target washing parameter with a correlation value larger than the correlation mean value from the plurality of washing parameters.
4. The foam quantity prediction method according to claim 2, wherein the calculating of the correlation value between each washing parameter and the foam quantity by normalizing mutual information includes:
calculating the entropy of each washing parameter and the entropy of the foam amount;
calculating the joint entropy of each washing parameter and foam amount;
calculating mutual information of the entropy and the joint entropy;
and normalizing the mutual information to obtain a correlation value between each washing parameter and the foam quantity.
5. The foam amount prediction method according to claim 4, further comprising:
by the formula
Figure FDA0003390119010000011
Calculating the entropy of each washing parameter by formula
Figure FDA0003390119010000012
Calculating the entropy of the amount of foam, wherein p (x)k) Is xkProbability density of p (y)l) Is ylThe probability density of (d);
by the formula
Figure FDA0003390119010000021
Calculating the joint entropy of each washing parameter and foam amount, wherein p (x)k,yl) Is xkAnd ylA joint probability density function of (a);
calculating mutual information of the entropy and the joint entropy by formula I (X, Y) ═ H (X) + H (Y) -H (X, Y);
by the formula
Figure FDA0003390119010000022
A correlation value between each washing parameter and the amount of foam was obtained.
6. The foam amount prediction method according to claim 1, further comprising:
acquiring a plurality of historical washing parameters of the washing equipment;
calculating the correlation between each historical washing parameter and the historical foam amount;
determining a target historical washing parameter with correlation meeting a preset condition from the plurality of historical washing parameters;
and constructing the foam prediction model according to the target historical washing parameters and a support vector regression model.
7. The foam quantity prediction method according to claim 6, wherein the constructing the foam prediction model according to the target historical washing parameters and a support vector regression model comprises:
by the formula
Figure FDA0003390119010000023
Constructing the foam prediction model, wherein
Figure FDA0003390119010000024
Is Lagrange multiplier, b is bias variable, k (x)i,xj) Is a kernel function, the target historical washing parameter is used as an input parameter of the kernel function, and f (x) is output as a predicted foam amount.
8. A foam amount prediction device applied to a washing apparatus, the foam amount prediction device comprising:
the acquisition module is used for acquiring a plurality of washing parameters of the washing equipment;
a calculation module for calculating the correlation of each washing parameter with the amount of foam;
the determining module is used for determining a target washing parameter of which the correlation meets a preset condition from the plurality of washing parameters;
and the prediction module is used for predicting the foam amount in the washing process of the washing equipment according to the target washing parameters and the foam prediction model.
9. A computer storage medium, having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the foam quantity prediction method according to any one of claims 1 to 7.
10. A washing apparatus comprising a processor, a memory and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the foam quantity prediction method according to any one of claims 1 to 7 when executing the program.
CN202111463309.0A 2021-12-02 2021-12-02 Foam amount prediction method, foam amount prediction device, storage medium, and washing apparatus Active CN114108232B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111463309.0A CN114108232B (en) 2021-12-02 2021-12-02 Foam amount prediction method, foam amount prediction device, storage medium, and washing apparatus

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111463309.0A CN114108232B (en) 2021-12-02 2021-12-02 Foam amount prediction method, foam amount prediction device, storage medium, and washing apparatus

Publications (2)

Publication Number Publication Date
CN114108232A true CN114108232A (en) 2022-03-01
CN114108232B CN114108232B (en) 2024-03-12

Family

ID=80366842

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111463309.0A Active CN114108232B (en) 2021-12-02 2021-12-02 Foam amount prediction method, foam amount prediction device, storage medium, and washing apparatus

Country Status (1)

Country Link
CN (1) CN114108232B (en)

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0657576A1 (en) * 1993-12-10 1995-06-14 Bosch-Siemens Hausgeräte GmbH Automatically controlled washing machine
CN1137077A (en) * 1995-05-31 1996-12-04 博施-西门子家用器具有限公司 Autocontrolled washer
JP2001120878A (en) * 1999-10-22 2001-05-08 Toshiba Corp Washing machine
US6269506B1 (en) * 1998-09-30 2001-08-07 Siemens Aktiengesellschaft Method and arrangement for computer-assisted determination of clusters for the recognition of foaming in a washing machine as well as method and arrangement for recognizing foaming in a washing machine
JP2006346255A (en) * 2005-06-17 2006-12-28 Hitachi Appliances Inc Electric washing machine
CN101466884A (en) * 2006-06-12 2009-06-24 Bsh博世和西门子家用器具有限公司 Method of removing scum in a drum washing machine, and drum washing machine suitable for this purpose
KR20090114602A (en) * 2008-04-30 2009-11-04 엘지전자 주식회사 Drum type washing machine and control method thereof
EP2418315A2 (en) * 2010-07-29 2012-02-15 BSH Bosch und Siemens Hausgeräte GmbH Household device with fill level sensor and method for determining a status parameter in a household appliance
EP2609845A1 (en) * 2011-12-30 2013-07-03 Indesit Company S.p.A. Dishwasher and method for detecting malfunctions thereof
JP2014054403A (en) * 2012-09-13 2014-03-27 Panasonic Corp Washing machine
DE202016104343U1 (en) * 2016-08-05 2017-08-08 Edmund Pötsch Analysis device for determining foam
CN112941806A (en) * 2021-01-29 2021-06-11 珠海格力电器股份有限公司 Washing machine, foam quantity prediction method and device thereof and electronic equipment

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0657576A1 (en) * 1993-12-10 1995-06-14 Bosch-Siemens Hausgeräte GmbH Automatically controlled washing machine
CN1137077A (en) * 1995-05-31 1996-12-04 博施-西门子家用器具有限公司 Autocontrolled washer
US6269506B1 (en) * 1998-09-30 2001-08-07 Siemens Aktiengesellschaft Method and arrangement for computer-assisted determination of clusters for the recognition of foaming in a washing machine as well as method and arrangement for recognizing foaming in a washing machine
JP2001120878A (en) * 1999-10-22 2001-05-08 Toshiba Corp Washing machine
JP2006346255A (en) * 2005-06-17 2006-12-28 Hitachi Appliances Inc Electric washing machine
CN101466884A (en) * 2006-06-12 2009-06-24 Bsh博世和西门子家用器具有限公司 Method of removing scum in a drum washing machine, and drum washing machine suitable for this purpose
KR20090114602A (en) * 2008-04-30 2009-11-04 엘지전자 주식회사 Drum type washing machine and control method thereof
EP2418315A2 (en) * 2010-07-29 2012-02-15 BSH Bosch und Siemens Hausgeräte GmbH Household device with fill level sensor and method for determining a status parameter in a household appliance
EP2609845A1 (en) * 2011-12-30 2013-07-03 Indesit Company S.p.A. Dishwasher and method for detecting malfunctions thereof
JP2014054403A (en) * 2012-09-13 2014-03-27 Panasonic Corp Washing machine
DE202016104343U1 (en) * 2016-08-05 2017-08-08 Edmund Pötsch Analysis device for determining foam
CN112941806A (en) * 2021-01-29 2021-06-11 珠海格力电器股份有限公司 Washing machine, foam quantity prediction method and device thereof and electronic equipment

Also Published As

Publication number Publication date
CN114108232B (en) 2024-03-12

Similar Documents

Publication Publication Date Title
JP7003753B2 (en) Search point determination program, search point determination method and search point determination device
JPH10111862A (en) Device for analyzing time sequence based on recurrent neural network and its method
CN111416797A (en) Intrusion detection method for optimizing regularization extreme learning machine by improving longicorn herd algorithm
Brownlee et al. Exploring the accuracy–energy trade-off in machine learning
CN111638958A (en) Cloud host load processing method and device, control equipment and storage medium
JP2021099860A (en) Task calculation amount determining method, device, electronic apparatus and computer program product
CN116090536A (en) Neural network optimization method, device, computer equipment and storage medium
CN115019128A (en) Image generation model training method, image generation method and related device
CN114108232A (en) Foam amount prediction method and device, storage medium and washing equipment
CN116595356B (en) Time sequence signal prediction method and device, electronic equipment and storage medium
CN109707658A (en) Method for determination of performance parameter, device and the electronic equipment of blower
Lee et al. Energy-efficient control of mobile processors based on long short-term memory
De Carvalho et al. Autonomous power management for embedded systems using a non-linear power predictor
CN116562156A (en) Training method, device, equipment and storage medium for control decision model
KR20210064044A (en) Apparatus and method for performing artificial neural network inference in mobile terminal
US20230004870A1 (en) Machine learning model determination system and machine learning model determination method
JP6233432B2 (en) Method and apparatus for selecting mixed model
CN115866687A (en) Service cooperative caching method in vehicle-mounted edge computing
CN115204463A (en) Residual service life uncertainty prediction method based on multi-attention machine mechanism
CN111340276B (en) Method and system for generating prediction data
CN112419098A (en) Power grid safety and stability simulation sample screening and expanding method based on safety information entropy
CN116954088B (en) Online monitoring method and system for mixer
CN116933896B (en) Super-parameter determination and semantic conversion method, device, equipment and medium
US20230244910A1 (en) Method and apparatus with neural network control
CN111368861B (en) Method and device for determining the sequence of sub-components in an image object detection process

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant