Clothing identification method, device and washing machine

Abstract

The application discloses a clothes material identification method and device and a washing machine, and relates to the field of household appliances. Based on the principle that different clothes materials have different suspension amounts on a drum washing machine, the torque of a motor is different, and then the Q-axis current of the motor has different characteristics. The weight of clothes, a first characteristic parameter of the Q-axis current of the motor of the drum washing machine when the clothes are dried, and a second characteristic parameter of the Q-axis current of the motor when the clothes are saturated and absorb water are input into a pre-trained machine learning model for analysis, so as to determine the clothes material of the clothes. The application does not need additional equipment, saves cost, and does not need the user to manually input the clothes material of the clothes put in, thereby improving the user experience.

Description

Technical Field

[0001] This invention relates to the field of household appliances, and in particular to a method, device and washing machine for identifying fabric. Background Technology

[0002] Because different fabrics require different washing needs, the washing programs used in washing machines vary significantly depending on the fabric. Specifically, different fabrics require different number of rinses, washing times, spin speeds, and detergent amounts. An inappropriate washing program can lead to wear and tear on clothes or poor washing results. To select the appropriate program, the fabric type must first be identified. Current technology identifies fabrics by collecting their infrared spectra, requiring an additional infrared spectrometer inside the washing machine, which is costly. Alternatively, requiring users to manually input the fabric type of the clothes to be put into the washing machine is inefficient and provides a poor user experience. Summary of the Invention

[0003] The purpose of this invention is to provide a fabric identification method, device, and washing machine that does not require additional equipment, thus saving costs, and eliminates the need for users to manually input the fabric type of the clothes placed inside, thereby improving the user experience.

[0004] To solve the above-mentioned technical problems, the present invention provides a fabric identification method, applied to a drum washing machine, comprising:

[0005] Determine the weight of the clothes inside the drum of the washing machine when drying;

[0006] Determine a first characteristic parameter of the Q-axis current of the motor of the drum washing machine when the clothes are drying;

[0007] Determine the second characteristic parameter of the Q-axis current of the motor when the clothing is saturated with water;

[0008] The weight, the first feature parameter, and the second feature parameter are input into a pre-trained machine learning model to determine the fabric of the garment.

[0009] Preferably, determining the first characteristic parameter of the Q-axis current of the motor when the clothing is drying includes:

[0010] When the clothes are drying, the motor is controlled to drive the drum to rotate at a first speed for a first preset time, and the first average value of the Q-axis current of the motor during the first preset time is determined, and the first average value is used as the first characteristic parameter.

[0011] Preferably, determining the second characteristic parameter of the Q-axis current of the motor when the clothing is saturated with water includes:

[0012] Control the clothing to saturate with water;

[0013] When the clothes are saturated with water, the motor is controlled to drive the drum to rotate at a second speed for a second preset time, and the second average value of the Q-axis current of the motor during the second preset time is determined, and the second average value is used as the second characteristic parameter.

[0014] Preferably, controlling the saturation of the clothing for water absorption includes:

[0015] The water inlet valve of the drum washing machine is controlled to allow water to enter, and the motor is controlled to drive the drum to rotate at a third speed until the water level inside the drum rises steadily.

[0016] Preferably, determining the second characteristic parameter of the Q-axis current of the motor when the clothing is saturated with water further includes:

[0017] Determine the standard deviation of the Q-axis current of the motor during the second preset time period;

[0018] Using the second average value as the second feature parameter includes:

[0019] The second average value and the standard deviation are used as the second characteristic parameters.

[0020] Preferably, the machine learning model is a support vector machine classification model.

[0021] Preferably, after inputting the weight, the first feature parameter, and the second feature parameter into a pre-trained machine learning model to determine the fabric of the garment, the method further includes:

[0022] Select the washing program corresponding to the fabric.

[0023] Preferably, the washing program corresponding to the fabric includes:

[0024] The number of rinses and / or washing time and / or spin speed and / or detergent dosage corresponding to the fabric.

[0025] The present invention also provides a fabric identification device, comprising:

[0026] Memory, used to store computer programs;

[0027] A processor is used to implement the steps of the fabric recognition method described above when executing the computer program.

[0028] The present invention also provides a washing machine, including a washing machine body and a fabric recognition device as described above.

[0029] This invention provides a method, device, and washing machine for identifying fabric. Based on the principle that different weights of fabrics hang differently on a drum washing machine, resulting in varying motor torque and consequently different Q-axis current characteristics, the method inputs the weight of the fabric, a first characteristic parameter of the Q-axis current of the washing machine motor when the fabric is dry, and a second characteristic parameter of the Q-axis current of the washing machine motor when the fabric is saturated with water into a pre-trained machine learning model for analysis to determine the fabric type. This method eliminates the need for additional equipment, saving costs, and also eliminates the need for users to manually input the fabric type of the fabric, improving the user experience. Attached Figure Description

[0030] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the prior art and embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0031] Figure 1 A flowchart of a fabric identification method provided by the present invention;

[0032] Figure 2 A schematic diagram comparing the magnitudes of the Q-axis current when clothes of different fabrics are dried;

[0033] Figure 3 A schematic diagram comparing the magnitudes of the Q-axis current when clothing of different fabrics is saturated with water;

[0034] Figure 4 A schematic diagram comparing the standard deviation of the Q-axis current of different fabrics when they are saturated with water;

[0035] Figure 5 This invention provides a schematic diagram of the structure of a washing machine;

[0036] Figure 6 This is a schematic diagram of the structure of a fabric recognition device provided by the present invention. Detailed Implementation

[0037] The core of this invention is to provide a fabric identification method, device, and washing machine that does not require additional equipment, thus saving costs, and eliminates the need for users to manually input the fabric type of the clothes being placed in the machine, thereby improving the user experience.

[0038] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0039] Please refer to Figure 1 , Figure 1 A flowchart of a fabric identification method provided by the present invention.

[0040] A fabric identification method, applied to a drum washing machine, includes:

[0041] S1: Determine the weight of the clothes inside the drum of the front-loading washing machine when drying;

[0042] Even for the same type of fabric, different weights of clothing affect the torque required by the washing machine motor. For example, if 1kg and 2kg of cotton clothing are placed in the drum of a washing machine and the motor is controlled to rotate the drum at the same speed, the 2kg cotton clothing requires more motor torque than the 1kg cotton clothing, resulting in different Q-axis currents. Conversely, when the weight of the clothing is the same and the drum rotates at the same speed, the Q-axis current of the washing machine motor will differ depending on the fabric. Therefore, analyzing the fabric composition using the washing machine motor's Q-axis current requires first determining the weight of the clothing at the time of drying.

[0043] Specifically, when determining the weight of clothes when they are dry, one can measure the weight of the clothes by installing a weight sensor inside the washing machine, or by rotating the washing machine drum at a fixed speed and determining the weight by using a preset torque or the correlation between the motor's Q-axis current and the weight.

[0044] S2: The first characteristic parameter for determining the Q-axis current of the motor of the drum washing machine when clothes are drying;

[0045] Please refer to the details. Figure 2 , Figure 2 This diagram illustrates the comparison of the Q-axis current values ​​for different fabrics during drying.

[0046] Considering that when clothes are drying, soft fabrics such as silk have weaker cohesion and are more dispersed within the washing machine drum, while heavy fabrics such as cotton and terry cloth have stronger cohesion and are more concentrated, when the washing machine motor rotates at a certain speed, for the same weight of soft and heavy fabrics, the soft fabrics will hang more on the lifting ribs within the drum, resulting in higher motor torque and a larger Q-axis current at that speed. Conversely, the heavy fabrics will hang less on the lifting ribs, resulting in lower motor torque and a smaller Q-axis current at the same speed. Therefore, in this embodiment, a first characteristic parameter of the washing machine motor's Q-axis current during drying is determined for subsequent analysis to identify the fabric type. The first characteristic parameter of the motor's Q-axis current here may include, but is not limited to, the magnitude and fluctuation of the motor's Q-axis current.

[0047] S3: Determine the second characteristic parameter of the motor's Q-axis current when the clothing is saturated with water;

[0048] Please refer to Figure 3 , Figure 3 This diagram illustrates the comparison of the Q-axis current values ​​for different fabrics when they are saturated with water.

[0049] Considering that thick fabrics such as towels have a higher water absorption rate, while soft fabrics such as silk have a lower water absorption rate, for two fabrics of the same weight when dry, after saturation, the thicker fabric absorbs more water and becomes heavier due to its higher absorption rate, while the softer fabric absorbs less water and gains less weight. Therefore, if the washing machine motor is controlled to rotate at a certain speed, lifting the heavier fabric with more water will require higher motor torque, resulting in a higher Q-axis current. Conversely, lifting the softer fabric with less water will require higher motor torque, resulting in a lower Q-axis current. Therefore, in this embodiment, a second characteristic parameter of the motor's Q-axis current when the fabric is saturated with water is determined for subsequent analysis to identify the fabric type. This second characteristic parameter of the motor's Q-axis current may include, but is not limited to, the magnitude and fluctuation of the motor's Q-axis current.

[0050] The weight, first feature parameter, and second feature parameter are input into a pre-trained machine learning model to determine the fabric of the garment.

[0051] To determine the fabric of clothing based on its weight when dry and the first and second characteristic parameters of the motor's Q-axis current, this embodiment inputs the weight, the first characteristic parameter, and the second characteristic parameter into a pre-trained machine learning model to determine the fabric. This machine learning model is pre-trained using multiple sample datasets. Each sample dataset corresponds to one or more fabric types, such as cotton, soft fabric, terry cloth, and blended fabrics. Each sample dataset includes sample data of the first and second characteristic parameters of the Q-axis current for different weights of the fabric corresponding to that sample dataset.

[0052] In summary, this embodiment utilizes the principle that different weights of clothing hang differently on the drum washing machine, resulting in varying motor torque and consequently different Q-axis current characteristics. The weight of the clothing, the first characteristic parameter of the drum washing machine's Q-axis current during drying, and the second characteristic parameter of the motor's Q-axis current when the clothing is saturated with water are input into a pre-trained machine learning model for analysis to determine the type of clothing. This eliminates the need for additional equipment, saving costs, and also eliminates the need for users to manually input the type of clothing, improving the user experience.

[0053] Based on the above embodiments:

[0054] As a preferred embodiment, determining a first characteristic parameter of the Q-axis current of the motor when the clothes are drying includes:

[0055] When clothes are drying, the motor drives the drum to rotate at a first speed for a first preset time and determines the first average value of the Q-axis current of the motor within the first preset time, and uses the first average value as the first characteristic parameter.

[0056] Considering that during the drying process, soft fabrics such as silk have weaker cohesion and are more dispersed within the washing machine drum, while heavier fabrics such as cotton and terry cloth have stronger cohesion and are more concentrated, when the washing machine motor rotates at a certain speed, for the same weight of soft and heavy fabrics, the soft fabrics will hang more on the lifting ribs within the drum, resulting in higher motor torque and a larger Q-axis current. Conversely, the heavy fabrics will hang less on the lifting ribs, resulting in lower motor torque and a smaller Q-axis current. Therefore, in this embodiment, during the drying process, the motor drives the drum to rotate at a first speed for a first preset time. During this first preset time, the Q-axis current of the motor is sampled, and the first average value of all sampled Q-axis current values ​​within the first preset time is calculated. This first average value is used as the first characteristic parameter. The first preset time here is set by the technicians based on the sampling frequency. As long as the number of samplings of the Q-axis current of the motor is sufficient within the first preset time, the first average value calculated based on all the sampling values ​​of the Q-axis current within the first preset time can represent the characteristics of the Q-axis current of the clothing when it is drying.

[0057] It should also be noted that this application does not specify a particular first rotation speed, as long as it allows soft fabric clothing to hang on the lifting ribs of the roller.

[0058] In summary, in this embodiment, by controlling the motor to drive the drum to rotate at a first speed for a first preset time during the drying process of the clothes, and determining the first average value of the Q-axis current of the motor within the first preset time, the first average value is used as the first characteristic parameter. Utilizing the average value reduces the impact of random errors in the Q-axis current on the fabric judgment.

[0059] As a preferred embodiment, determining a second characteristic parameter of the motor's Q-axis current when the clothing is saturated with water includes:

[0060] Control the saturation of water absorption in clothing;

[0061] When the clothes are saturated with water, the motor drives the drum to rotate at a second speed for a second preset time, and the second average value of the Q-axis current of the motor is determined within the second preset time. The second average value is used as the second characteristic parameter.

[0062] Considering that thick fabrics such as towels have a higher water absorption rate, while soft fabrics such as silk have a lower water absorption rate, for two garments of the same weight when dry, the thicker fabric, due to its higher absorption rate, absorbs more water and becomes heavier after saturation, while the softer fabric, due to its lower absorption rate, absorbs less water and gains less weight. Therefore, if the washing machine motor is controlled to rotate at a certain speed, lifting the heavier fabric with more water absorption requires higher motor torque, resulting in a higher Q-axis current. Conversely, lifting the softer fabric with less water absorption requires higher motor torque, resulting in a lower Q-axis current. Therefore, in this embodiment, the washing machine is controlled to absorb water to saturation. After saturation, the motor drives the drum to rotate at a second speed for a second preset time. During this second preset time, the Q-axis current of the motor is sampled, and the second average value of all sampled Q-axis current values ​​within the second preset time is calculated. This second average value is used as a second characteristic parameter. The second preset time here is set by the technicians based on the sampling frequency. As long as the number of samplings of the motor's Q-axis current within the second preset time is sufficient, the second average value calculated based on all the sampling values ​​of the Q-axis current within the second preset time can represent the characteristics of the Q-axis current of the clothing after it has absorbed water to a saturation.

[0063] It should also be noted that this application does not specifically limit the second rotation speed, as long as it can lift the clothes after they have been saturated with water.

[0064] In summary, in this embodiment, after the garment has absorbed saturated water, the motor drives the drum to rotate at a second speed for a second preset time, and the second average value of the Q-axis current of the motor within the second preset time is determined. This second average value is then used as the second characteristic parameter. Utilizing the average value reduces the impact of random errors in the Q-axis current on the garment's condition.

[0065] As a preferred embodiment, controlling the saturation of clothing with water absorption includes:

[0066] Control the water inlet valve of the drum washing machine to allow water to enter and control the motor to drive the drum to rotate at the third speed until the water level inside the drum rises steadily.

[0067] To allow clothes to absorb water more quickly, in this embodiment, the motor drives the drum to rotate at a third speed, ensuring sufficient contact between the clothes and water to achieve saturation more rapidly. This application does not specify a particular third speed, as long as it ensures sufficient contact between the clothes and the water in the drum for adequate water absorption. Without considering water absorption, the water inlet speed is constant, resulting in a constant rise in the water level inside the washing machine drum. However, considering water absorption, if the clothes are not saturated, the rise in water level will fluctuate due to absorption; if the clothes are saturated, the water level will rise steadily, either uniformly or linearly. Therefore, in this embodiment, the motor drives the drum to rotate at the third speed until the water level inside the drum stabilizes. When the water level stabilizes, it indicates that the clothes inside the drum are saturated.

[0068] It should also be noted that when controlling the water inlet valve of a drum washing machine, priority can be given to controlling the water inlet valve that can directly supply water to the surface of the clothes, so that the clothes can absorb water better.

[0069] As a preferred embodiment, determining the second characteristic parameter of the motor's Q-axis current when the clothing is saturated with water also includes:

[0070] Determine the standard deviation of the Q-axis current of the motor within a second preset time period;

[0071] Using the second average value as the second characteristic parameter, including:

[0072] The second mean and standard deviation are used as the second characteristic parameters.

[0073] Please refer to Figure 4 , Figure 4 Made of soft fabric Figure 4 This diagram illustrates the comparison of the standard deviations of the Q-axis current when clothing of different fabrics is saturated with water.

[0074] Considering that delicate fabrics are less prone to clumping after absorbing water, when the motor drives the drum, the fabric moves by being lifted and then dropped, resulting in greater fluctuations in motor torque and consequently, greater fluctuations in the Q-axis current. Conversely, for heavy fabrics, which are also prone to clumping after absorbing water, the fabric moves by rolling inside the drum, resulting in less fluctuation in motor torque and consequently, less fluctuation in the Q-axis current. Therefore, in this embodiment, after sampling the motor's Q-axis current within a second preset time period, the standard deviation of all sampled Q-axis current values ​​within that time period is calculated. The second average value and standard deviation of all sampled Q-axis current values ​​within the second preset time period are used as the second characteristic parameter. The standard deviation reflects the degree of fluctuation in the Q-axis current within the second preset time period, allowing for the identification of the fabric type and further improving the accuracy of fabric identification.

[0075] As a preferred embodiment, the machine learning model is a support vector machine classification model.

[0076] Support Vector Machine (SVM) classification models achieve significantly better results than other algorithms on small training sets. The optimization objective of SVM is to minimize structured risk, rather than empirical risk, thus avoiding overfitting. By obtaining a structured description of the data distribution, it reduces the requirements for data size and distribution, and exhibits excellent generalization ability. Since the final result is determined by a small number of support vectors, SVM not only helps us identify key samples and eliminate a large number of redundant samples, but also ensures that the method is not only simple but also has good robustness.

[0077] In a preferred embodiment, after inputting the weight, the first feature parameter, and the second feature parameter into a pre-trained machine learning model to determine the fabric of the garment, the method further includes:

[0078] Choose the washing program that corresponds to the fabric.

[0079] Considering that different fabrics have different washing requirements, the washing machine uses different programs for different fabrics. Inappropriate program selection can lead to wear and tear on the clothes or poor washing results. Therefore, in this embodiment, the weight, first feature parameter, and second feature parameter are input into a pre-trained machine learning model to determine the fabric type. Then, a suitable washing mode is selected based on the fabric's material. The washing program corresponding to the fabric includes the washing time, spin speed, and water temperature, etc., which are not specifically limited in this embodiment.

[0080] As a preferred embodiment, the washing program corresponding to the fabric includes:

[0081] The number of rinses and / or washing time and / or spin speed and / or detergent dosage corresponding to the fabric.

[0082] Considering that for easily damaged or deformed clothing, such as sweaters and silk, the number of rinses should not be too many, the washing time should not be too long, and the spin speed should not be too high. However, for clothing that is less prone to damage or deformation, to achieve higher cleaning power, the number of rinses can be appropriately increased, the washing time extended, and the spin speed increased. For clothing prone to color fading, the amount of detergent added should not be excessive. This is because, in this embodiment, the washing program corresponding to the fabric includes the number of rinses and / or washing time and / or spin speed and / or detergent dosage corresponding to the fabric, in order to provide more targeted washing for different fabrics.

[0083] Please refer to Figure 6 , Figure 6 This is a schematic diagram of the structure of a fabric recognition device provided by the present invention.

[0084] The present invention also provides a fabric identification device, comprising:

[0085] Memory 41 is used to store computer programs;

[0086] The processor 42 is used to implement the steps of the fabric recognition method described above when executing a computer program.

[0087] For details regarding the fabric recognition device, please refer to the above embodiments; further elaboration will not be repeated here.

[0088] The present invention also provides a washing machine, including a washing machine body and a fabric recognition device as described above.

[0089] Please refer to Figure 5 , Figure 5 This is a schematic diagram of the structure of a washing machine provided by the present invention. Figure 5 In the washing machine, the processor 42 is an MCU, and the washing machine body is also equipped with a panel that can display and determine the fabric of the clothes in the drum.

[0090] For details regarding the washing machine, please refer to the above embodiments; further details will not be repeated here.

[0091] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to the method section.

[0092] It should also be noted that, in this specification, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0093] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for identifying fabric, characterized in that, Applied to drum washing machines, including: Determine the weight of the clothes inside the drum of the washing machine when drying; A first characteristic parameter is determined for the Q-axis current of the motor of the drum washing machine when the clothes are drying. The first characteristic parameter is the first average value of the Q-axis current of the motor during the first preset time when the clothes are drying, which controls the motor to drive the drum to rotate at a first speed for a first preset time. The first speed enables soft fabric clothes to hang on the lifting ribs of the drum. A second characteristic parameter is determined for the Q-axis current of the motor when the garment is saturated with water. The second characteristic parameter includes the second average value of the Q-axis current of the motor and the standard deviation of the Q-axis current of the motor during the second preset time when the garment is saturated with water, and the standard deviation characterizes the degree of fluctuation of the Q-axis current during the second preset time. The weight, the first feature parameter, and the second feature parameter are input into a pre-trained machine learning model to determine the fabric of the garment.

2. The fabric identification method as described in claim 1, characterized in that, The second characteristic parameter for determining the Q-axis current of the motor when the clothing is saturated with water includes: Control the clothing to saturate with water; When the clothes are saturated with water, the motor is controlled to drive the drum to rotate at a second speed for a second preset time, and the second average value of the Q-axis current of the motor during the second preset time is determined, and the second average value is used as the second characteristic parameter.

3. The fabric identification method as described in claim 2, characterized in that, Controlling the saturation of the clothing for water absorption includes: The water inlet valve of the drum washing machine is controlled to allow water to enter, and the motor is controlled to drive the drum to rotate at a third speed until the water level inside the drum rises steadily.

4. The fabric identification method as described in claim 2, characterized in that, Determining the second characteristic parameter of the Q-axis current of the motor when the clothing is saturated with water also includes: Determine the standard deviation of the Q-axis current of the motor during the second preset time period; Using the second average value as the second feature parameter includes: The second average value and the standard deviation are used as the second characteristic parameters.

5. The fabric identification method as described in claim 1, characterized in that, The machine learning model is a support vector machine classification model.

6. The fabric identification method according to any one of claims 1 to 5, characterized in that, After inputting the weight, the first feature parameter, and the second feature parameter into a pre-trained machine learning model to determine the fabric of the garment, the process further includes: Select the washing program corresponding to the fabric.

7. The fabric identification method as described in claim 6, characterized in that, The washing program corresponding to the fabric includes: The number of rinses and / or washing time and / or spin speed and / or detergent dosage corresponding to the fabric.

8. A fabric identification device, characterized in that, include: Memory, used to store computer programs; A processor, configured to implement the steps of the fabric recognition method as described in any one of claims 1 to 7 when executing the computer program.

9. A washing machine, characterized in that, It includes the washing machine body and the fabric recognition device as described in claim 8.

Images