Washing machine control method and washing machine

Abstract

The invention provides a washing machine control method and a washing machine, and the washing machine comprises a roller which provides a processing space for to-be-processed clothes; a shell of the box body is constructed for the washing machine, an installation space is provided for a roller, and the induction device is arranged on the inner surface of the roller and used for collecting friction signals generated when the induction device makes contact with to-be-treated clothes; the control method of the washing machine comprises the steps that feature extraction is conducted on friction signals collected when the roller rotates at the set rotating speed, and signal features are obtained; determining a clothing material type corresponding to the signal feature according to the signal feature; and counting clothes material types corresponding to the signal features, determining a corresponding processing mode in a preset mode comparison table, and processing the to-be-processed clothes. Therefore, the washing machine can automatically identify the material of the to-be-processed clothes and automatically match the corresponding clothes processing mode.

Description

Technical Field

[0001] The present application relates to the technical field of washing machines, and in particular to a control method for a washing machine and a washing machine. Background Art

[0002] In order to better meet users' clothing processing needs, some washing machines on the market cannot automatically identify the properties of clothing materials. Manual selection of clothing material properties is required to match the corresponding clothing processing mode, which greatly reduces the user experience. Sometimes users cannot accurately identify the properties of clothing materials, which may cause damage to clothing.

[0003] Therefore, how to enable the washing machine to automatically identify the material of the clothes to be processed and automatically match the corresponding clothes processing mode is a problem that urgently needs to be solved. Summary of the Invention

[0004] The present application aims to solve the technical problem of how to enable a steam generator used in a washing machine to spray only steam during operation.

[0005] In a first aspect, the present application provides a control method for a washing machine, the washing machine comprising: a drum providing a processing space for clothes to be processed; a housing forming an outer shell of the washing machine and providing a mounting space for the drum; a sensing device mounted on an inner surface of the drum and configured to collect a friction signal generated when the sensing device contacts the clothes to be processed, the friction signal representing a vibration frequency, a vibration amplitude, and a static pressure generated when the sensing device contacts the clothes to be processed;

[0006] The control method of the washing machine includes:

[0007] Feature extraction is performed on each friction signal collected when the drum rotates at a set speed to obtain signal features; based on the signal features, the type of clothing material corresponding to the signal features is determined; the type of clothing material corresponding to each signal feature is counted, and the corresponding processing mode is determined in a preset mode comparison table to process the clothing to be processed.

[0008] In an embodiment of the present application, in view of the fact that current washing machines are unable to accurately identify the type of material of the clothes to be processed, based on the principle that the vibration frequency, vibration amplitude and static pressure generated by the sensing device when it comes into contact with clothes of different materials are different, according to the friction signal generated when the sensing device comes into contact with the clothes, it is determined what material the clothes that the sensing device comes into contact with are, and then the processing mode is determined according to the material of the clothes to be processed to prevent damage to the clothes.

[0009] In one embodiment of the present application, before extracting features from each friction signal collected when the drum rotates at a set speed to obtain signal features, the method further includes: obtaining a continuous friction signal through the sensing device when the drum rotates at a set speed; taking time as the axis, determining the time node in the continuous friction signal where the fluctuation range is greater than a set threshold as a segmentation point, segmenting the continuous friction signal, and obtaining each friction signal.

[0010] In this embodiment, the drum is rotated at a set speed. Since the friction signals collected by the sensing device are generated at different speeds, the friction signals generated by the sensing device are different. Therefore, rotating the drum at the set speed ensures the accuracy and uniqueness of the friction signals corresponding to various clothing materials. Furthermore, since the sensing device may be in constant contact with different clothing materials during the drum's rotation, the friction signals corresponding to different clothing materials form a continuous friction signal with time as the axis. This continuous friction signal corresponds to multiple clothing materials, with different portions of the continuous friction signal corresponding to different clothing materials. The friction signal corresponds to a single clothing material. Based on the principle that the vibration frequency, vibration amplitude, and static pressure generated by the sensing device differ when contacting clothing materials of different materials, the friction signal will inevitably fluctuate significantly when the sensing device switches from contacting one clothing material to contacting another. Therefore, the time points at which the friction signal fluctuates significantly correspond to the moments when the sensing device contacts different clothing materials. These points serve as segmentation points, allowing the continuous friction signal to be segmented into friction signals corresponding to different types of clothing materials.

[0011] In one embodiment of the present application, the friction signals collected when the drum rotates at a set speed are subjected to feature extraction to obtain signal characteristics, including: performing an inner product operation on the friction signal and a set function to obtain a characteristic coefficient, wherein the characteristic coefficient represents the amplitude change and phase information of the friction signal at different frequencies; and obtaining the signal characteristics of the friction signal by analyzing the amplitude change and phase information of the friction signal.

[0012] If the friction signal is not converted by a set function as a time domain signal, the friction signal is a relatively messy waveform, and the phase spectrum and amplitude spectrum of the friction signal cannot be clearly obtained at this time. This is because the time domain signal only shows the size of the signal amplitude corresponding to different time nodes, but when the signals are superimposed, it is difficult to separate the signals. The friction signal is converted by a set function to obtain characteristic coefficients representing the relevant characteristics of the friction signal. The friction signal converted into a time domain signal is a sine wave. The characteristic coefficients can be used to obtain clear phase spectrum and amplitude spectrum to represent the signal characteristics of the friction signal. Therefore, when performing signal analysis, converting the time domain signal into a frequency domain signal can more accurately understand the "structure" of the signal and more conveniently extract the signal characteristics of the friction signal.

[0013] Therefore, the friction coefficient is obtained by performing an inner product operation between the friction signal and the set function. The friction coefficient represents the amplitude change and phase information of the friction signal at different frequencies. By analyzing the amplitude change and phase information of the friction coefficient, the signal characteristics of the friction signal can be obtained more clearly and accurately.

[0014] In one embodiment of the present application, determining the type of clothing material corresponding to the signal feature based on the signal feature includes: determining the properties of the clothing material corresponding to the signal feature based on the signal feature, the clothing material properties including material stiffness, texture height, and texture spacing; determining the type of clothing material corresponding to the signal feature based on the properties of the clothing material corresponding to the signal feature.

[0015] In this embodiment, the sensing device generates different vibration frequencies, amplitudes, and static pressures when in contact with different clothing materials. Consequently, different clothing materials generate different friction signals. By analyzing these friction signals, signal features representing the corresponding vibration frequencies, amplitudes, and static pressures can be extracted. The specific values of the vibration frequencies, amplitudes, and static pressures can be affected by the properties of the clothing material. Therefore, the properties of the clothing material can be determined based on the signal features, and then the type of clothing material can be determined based on the properties. This approach allows for accurate determination of the type of clothing material corresponding to the friction signal.

[0016] In one embodiment of the present application, determining the type of clothing material corresponding to the signal feature based on the signal feature also includes: inputting the signal feature into multiple classification decision trees respectively to obtain the initial clothing material type output by each classification decision tree; and determining the initial clothing material type that appears the most times as the clothing material type corresponding to the signal feature.

[0017] In this embodiment, in order to determine the type of clothing material corresponding to a signal feature based on the properties of the clothing material corresponding to the signal feature, a signal feature is input into multiple classification decision trees respectively. Each classification decision tree is trained using different sample data, and the parameters included in each classification decision tree are also different. Based on the output results of each classification decision tree, the output result with the largest number of occurrences is counted as the final clothing material type. The type of clothing material corresponding to the signal feature is verified through multiple different classification decision trees, thereby ensuring the accuracy of determining the type of clothing material corresponding to each signal feature.

[0018] In one embodiment of the present application, before inputting the signal features into multiple classification decision trees respectively to obtain the initial clothing material types output by each classification decision tree, the method further includes: repeatedly randomly selecting samples with the same number as the total number of samples from the sample set multiple times to obtain several sub-sample sets, wherein the samples include signal feature samples and clothing material types corresponding to the signal feature samples; and training a decision tree using each of the sub-sample sets to obtain a classification decision tree corresponding to each sub-sample set.

[0019] In this embodiment, multiple subsample sets are generated by repeatedly randomly selecting the same number of samples from the sample set as the total number of samples. This ensures that each subsample set is diverse, which in turn leads to differences between the trained classification decision trees. This ensures that each classification decision tree can more accurately determine the clothing material type corresponding to the signal feature. Furthermore, training the classification decision trees simultaneously using multiple subsample sets significantly reduces training time.

[0020] In one embodiment of the present application, the types of clothing materials corresponding to each of the signal features are counted, and the corresponding processing mode is determined in a preset mode comparison table to process the clothing to be processed, including: among the counted clothing material types, the clothing material type with the highest priority is used as the target clothing material type; and the processing mode matching the target clothing material type is determined in the comparison table to process the clothing to be processed.

[0021] In this embodiment, since some types of clothing materials can accept multiple processing modes, but some types of clothing materials can only accept a certain processing mode, in this case, the types of clothing materials that can only accept specific processing modes are set to a higher priority, and the clothing materials with higher priority are used as the basis for processing to avoid damage to some precious clothing materials.

[0022] In a second aspect, an embodiment of the present application provides a washing machine, comprising: a drum, providing a processing space for clothes to be processed; a housing, constructing an outer shell for the washing machine and providing an installation space for the drum; a sensing device, installed on the inner surface of the drum, for collecting a friction signal generated when the sensing device contacts the clothes to be processed, the friction signal representing the vibration frequency, vibration amplitude, and static pressure generated when the sensing device contacts the clothes to be processed; a controller, configured as: an acquisition unit, for performing feature extraction on each friction signal collected when the drum rotates at a set speed to obtain a signal feature; a determination unit, for determining, based on the signal feature, the type of clothing material corresponding to the signal feature; a processing unit, for counting the type of clothing material corresponding to each signal feature, determining the corresponding processing mode in a preset mode comparison table, and processing the clothes to be processed.

[0023] In an embodiment of the present application, in view of the fact that current washing machines are unable to accurately identify the type of material of the clothes to be processed, based on the principle that the vibration frequency, vibration amplitude and static pressure generated by the sensing device when it comes into contact with clothes of different materials are different, according to the friction signal generated when the sensing device comes into contact with the clothes, it is determined what material the clothes that the sensing device comes into contact with are, and then the processing mode is determined according to the material of the clothes to be processed to prevent damage to the clothes.

[0024] In one embodiment of the present application, the controller is further configured as: an acquisition unit, used to acquire a continuous friction signal through the sensing device when the drum rotates at a set speed; a segmentation unit, used to determine the time node in the continuous friction signal where the fluctuation range is greater than a set threshold as a segmentation point based on time, and segment the continuous friction signal to obtain each friction signal.

[0025] In this embodiment, the drum is rotated at a set speed. Since the friction signals collected by the sensing device are generated at different speeds, the friction signals generated by the sensing device are different. Therefore, rotating the drum at the set speed ensures the accuracy and uniqueness of the friction signals corresponding to various clothing materials. Furthermore, since the sensing device may be in constant contact with different clothing materials during the drum's rotation, the friction signals corresponding to different clothing materials form a continuous friction signal with time as the axis. This continuous friction signal corresponds to multiple clothing materials, with different portions of the continuous friction signal corresponding to different clothing materials. The friction signal corresponds to a single clothing material. Based on the principle that the vibration frequency, vibration amplitude, and static pressure generated by the sensing device differ when contacting clothing materials of different materials, the friction signal will inevitably fluctuate significantly when the sensing device switches from contacting one clothing material to contacting another. Therefore, the time points at which the friction signal fluctuates significantly correspond to the moments when the sensing device contacts different clothing materials. These points serve as segmentation points, allowing the continuous friction signal to be segmented into friction signals corresponding to different types of clothing materials.

[0026] In one embodiment of the present application, a lifting rib is installed on the inner surface of the drum, and the sensing device is installed on a side of the lifting rib close to the central axis of the drum.

[0027] In this embodiment, lifting ribs are provided on the inner surface of the drum, and the sensing device is installed on the side of the lifting ribs close to the central axis of the drum, so that the sensing device can fully contact the clothes to be processed, thereby avoiding incomplete detection of the type of clothing materials.

[0028] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by practice of the present application.

[0029] It should be understood that the foregoing general description and the following detailed description are merely illustrative and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The above and other objects, features and advantages of the present application will become more apparent by describing in detail example embodiments thereof with reference to the attached drawings.

[0031] Figure 1 A structural schematic diagram of a washing machine according to an embodiment of the present application is shown.

[0032] Figure 2 A flow chart of a method for controlling a washing machine according to an embodiment of the present application is shown.

[0033] Figure 3 A flow chart of dividing a continuous friction signal to obtain a friction signal according to one embodiment of the present application is shown.

[0034] Figure 4 A flow chart is shown for extracting features from friction signals collected when the drum rotates at a set speed to obtain signal features according to an embodiment of the present application.

[0035] Figure 5 A flow chart of determining the type of clothing material corresponding to a signal feature based on the signal feature according to an embodiment of the present application is shown.

[0036] Figure 6 A flow chart of determining the type of clothing material corresponding to a signal feature based on the signal feature according to an embodiment of the present application is shown.

[0037] Figure 7 A flowchart of training a classification decision tree according to an embodiment of the present application is shown.

[0038] Figure 8 A flowchart is shown for counting the types of clothing materials corresponding to each signal feature, determining the corresponding processing mode in a preset mode comparison table, and processing the clothing to be processed according to an embodiment of the present application. DETAILED DESCRIPTION

[0039] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of this application will be more comprehensive and complete and will fully convey the concepts of the example embodiments to those skilled in the art. The accompanying drawings are merely schematic illustrations of the present application and are not necessarily drawn to scale. Identical reference numerals in the figures indicate identical or similar parts, and thus repeated descriptions thereof will be omitted.

[0040] In addition, the described features, structures or characteristics may be combined in one or more example embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the example embodiments of the present application. However, those skilled in the art will appreciate that the technical solutions of the present application may be practiced while omitting one or more of the specific details, or other methods, components, steps, etc. may be adopted. In other cases, known structures, methods, implementations or operations are not shown or described in detail to avoid obscuring the main content and making various aspects of the present application vague.

[0041] Some of the blocks shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0042] The present application provides a washing machine, comprising a housing, an outer tub, a drum, and a sensing device. Figure 1 , Figure 1 A structural schematic diagram of a washing machine according to an embodiment of the present application is shown.

[0043] The housing typically has a hollow rectangular structure and serves as the outer shell of the washing machine. The housing may also have other shapes and can be designed as needed, without limitation. The interior of the housing provides mounting space for components such as the outer drum and the roller. The outer drum is located within the mounting space within the housing and is relatively fixed within the housing. A sensing device is mounted on the inner surface of the roller and is used to collect friction signals generated when the sensing device contacts the laundry to be processed. The friction signals represent the vibration frequency, vibration amplitude, and static pressure generated when the sensing device contacts the laundry to be processed.

[0044] See also Figure 2 , Figure 2 A flow chart of a method for controlling a washing machine according to an embodiment of the present application is shown. The present application provides a method for controlling a washing machine, including the following steps:

[0045] Step S210, performing feature extraction on each friction signal collected when the drum rotates at a set speed to obtain signal features;

[0046] Step S220, determining the type of clothing material corresponding to the signal feature based on the signal feature;

[0047] Step S230 , counting the types of clothing materials corresponding to the signal features, determining the corresponding processing mode in a preset mode comparison table, and processing the clothing to be processed.

[0048] The above three steps are described in detail below.

[0049] See also Figure 3 , Figure 3 A flow chart of segmenting a continuous friction signal to obtain a friction signal according to an embodiment of the present application is shown. The embodiment of the present application provides steps of segmenting a continuous friction signal to obtain a friction signal, including:

[0050] Step S301, when the drum rotates at a set speed, a continuous friction signal is obtained through a sensing device;

[0051] In step S302 , taking time as an axis, the time nodes in the continuous friction signal where the fluctuation range is greater than a set threshold are determined as segmentation points, and the continuous friction signal is segmented to obtain individual friction signals.

[0052] The above two steps are described in detail below.

[0053] In step S301, since the sensing device may always be in contact with different clothing materials, the friction signals corresponding to different clothing materials will form a continuous friction signal with time as the axis. The continuous friction signal corresponds to multiple clothing materials. According to the corresponding clothing material type, the continuous friction signal contains multiple friction signals corresponding to one clothing material type, and each friction signal corresponds to one clothing material.

[0054] In step S302, based on the principle that the vibration frequency, vibration amplitude and static pressure generated by the sensing device are different when it contacts clothing made of different materials, the friction signal will inevitably produce relatively large fluctuations when the sensing device contacts one clothing material to another clothing material. Therefore, the time node when the friction signal fluctuates greatly is the moment when the sensing device contacts different clothing materials. Based on this, the continuous friction signal can be divided into friction signals corresponding to different clothing materials.

[0055] In step S210, the friction signals generated by the sensing device vary due to friction between the sensing device and the laundry being processed at different speeds. This means that even for the same laundry material, the friction signals generated by the sensing device vary, resulting in different vibration frequencies, amplitudes, and static pressures sensed by the sensing device. Therefore, the drum is rotated at a set speed to maintain a stable range of vibration frequencies, amplitudes, and static pressures when the sensing device rubs against the laundry. This ensures that each type of laundry material corresponds to a fixed friction signal.

[0056] The collection of friction signals is based on time, so the friction signals change with time. When the sensing device only rubs against one type of clothing material, the changes in the friction signals show regular changes.

[0057] In one embodiment of the present application, the friction signal records the vibration amplitude of the sensing device over time. The vibration frequency of the sensing device can be determined by the change in the vibration amplitude. For example, the number of times the vibration amplitude reaches a peak value in 1 second is the vibration frequency of the sensing device. The friction signal also records the change in the static pressure experienced by the sensing device. In other words, the friction signal consists of two components: the vibration amplitude sensed by the sensing device and the static pressure sensed by the sensing device. The vibration frequency of the sensing device can be determined by changes in the friction signal.

[0058] The texture height and material stiffness of the clothing material affect the amplitude of the vibration. At the same time, the texture spacing of the clothing material affects the vibration frequency of the clothing sensing device. The material stiffness and texture spacing of the clothing material affect the static pressure borne by the sensing device. It should be clarified that static pressure refers to a pressure that overcomes frictional resistance.

[0059] The friction between the sensing device and each type of clothing material causes the friction signal to exhibit a corresponding pattern of change. Therefore, by extracting the signal features of the friction signal, we can represent the pattern of change in the friction signal and its correspondence with the type of clothing material. Each type of clothing material corresponds to a friction signal with a corresponding pattern of change and characteristics, that is, a signal feature. It should be understood that a signal feature does not simply refer to a single signal feature; a signal feature can also be a set of multiple features, with different components of this signal feature set describing different aspects of the friction signal.

[0060] See also Figure 4 , Figure 4 A flowchart of extracting features from each friction signal collected when the drum rotates at a set speed to obtain signal features according to one embodiment of the present application is shown. The embodiment of the present application provides a step S210 of extracting features from each friction signal collected when the drum rotates at a set speed to obtain signal features, including:

[0061] Step S211: performing an inner product operation on the friction signal and a set function to obtain a characteristic coefficient, which represents the amplitude change and phase information of the friction signal at different frequencies;

[0062] Step S212: Analyze the amplitude change and phase information of the friction signal to obtain the signal characteristics of the friction signal.

[0063] The above two steps are described in detail below.

[0064] In step S211, the friction signal is a time-domain signal, which allows for intuitive observation of the signal's shape. However, since the time-domain signal is affected by various factors during acquisition, the signal characteristics cannot be accurately described using the limited time-domain signal. Therefore, in steps S221 and S212, the time-domain signal is converted into a frequency-domain signal to obtain the frequency-domain characteristics of the friction signal.

[0065] This is because time-domain signals are often complex waveforms that make it difficult to extract good features. However, the frequency-domain signal's spectrum is a sinusoidal wave, which allows for better extraction of the friction signal's characteristics. The characteristics contained in the frequency-domain signal are also called time-frequency characteristics, which describe the friction signal's vibration amplitude, vibration frequency, static pressure variation, and numerical characteristics. Variation characteristics refer to the characteristics exhibited when the friction signal changes, such as the speed of change and the interval between peaks and valleys. Numerical characteristics refer to the numerical range, peaks, or valleys, within which the friction signal's numerical content lies.

[0066] Specifically, the first step is to select an appropriate setting function, which can be chosen from wavelet functions. The selection of this setting function is crucial for time-frequency feature extraction. Commonly used setting functions include Haar wavelets, Daubechies wavelets, and Morlet wavelets. This setting function decomposes the friction signal into a series of characteristic coefficients. These characteristic coefficients represent the characteristics of the friction signal at different frequencies and time points. Specifically, the friction signal is recursively decomposed into two components: a low-frequency approximation (Approximation) and a high-frequency detail (Detail). The low-frequency approximation represents the general shape of the signal, while the high-frequency detail captures rapid changes or noise in the signal. The number of decomposition levels is determined: Each decomposition level further decomposes the low-frequency approximation of the previous level into a new low-frequency approximation and high-frequency detail. The greater the number of decomposition levels, the higher the frequency resolution, but the lower the time resolution, achieving a conversion from the time domain to the frequency domain.

[0067] The converted friction signal can be used to obtain its spectrum. The spectrum represents the signal in the frequency domain, describing the amplitude and phase information of the friction signal at various frequencies. This spectrum can be used to extract the vibration frequency and amplitude characteristics of the sensing device. The amplitude spectrum and phase spectrum of the friction signal can be obtained from the spectrum. The amplitude spectrum represents the vibration amplitude and static pressure of the friction signal, while the phase spectrum represents the vibration frequency of the friction signal.

[0068] Similarly, if the friction signal is not transformed as a time-domain signal by a set function, the friction signal will be a relatively chaotic waveform, and the phase and amplitude spectra of the friction signal cannot be clearly obtained. If the friction signal is transformed by a set function to obtain characteristic coefficients representing the relevant characteristics of the friction signal, the friction signal converted into a time-domain signal will be a sine wave. The characteristic coefficients can be used to obtain clear phase and amplitude spectra to represent the signal characteristics of the friction signal.

[0069] In step S212, feature analysis is performed based on the amplitude spectrum and the phase spectrum to obtain signal features in the friction signal that are used to represent the vibration frequency, vibration amplitude, and static pressure of the sensing device.

[0070] In step S220, since each type of clothing material corresponds to a friction signal with corresponding change rules and characteristics, that is, corresponds to a signal feature, the corresponding clothing material type can be determined based on the signal feature.

[0071] In another embodiment of the present application, based on the signal characteristics of the friction signal, the material properties of the clothing material that causes the sensing device to generate the friction signal can be known, and then the type of clothing material can be determined.

[0072] This is because the texture and stiffness of the clothing material affect the vibration amplitude. The spacing between the textures also affects the vibration frequency of the clothing sensor. Furthermore, the stiffness and spacing between the textures affect the static pressure applied to the sensor. Therefore, the characteristics of the friction signal reflect the material properties of the clothing material. All characteristics of the friction signal can be used to identify the material properties of the corresponding clothing material. Clothing materials have specific properties, so the material type can be further determined based on these properties.

[0073] See also Figure 5 , Figure 5 A flowchart of determining the type of clothing material corresponding to the signal feature according to an embodiment of the present application is shown. The embodiment of the present application provides a step S220 of determining the type of clothing material corresponding to the signal feature according to the signal feature, including:

[0074] Step S221a, determining the clothing material properties corresponding to the signal features based on the signal features, where the clothing material properties include material stiffness, texture height, and texture spacing;

[0075] Step S222a: determining the type of clothing material corresponding to the signal feature based on the properties of the clothing material corresponding to the signal feature.

[0076] Specifically, in step S221a, the texture height and material stiffness of the clothing material are determined based on the variation patterns and characteristics of the sensing device's vibration amplitude as described by the signal characteristics. The texture spacing of the clothing material is determined based on the variation patterns and characteristics of the sensing device's vibration frequency as described by the signal characteristics. The texture height, texture spacing, and material stiffness of the clothing material are determined based on the variation patterns and characteristics of the static pressure to which the sensing device is subjected as described by the signal characteristics. Different components of the signal characteristics can collectively determine certain material properties, and the determined material properties can be mutually verified. By comprehensively analyzing multiple signal characteristics, material properties can be more accurately determined.

[0077] It should be made clear that the signal characteristics are the changing patterns of the friction signal, which reflect the changing patterns of the amplitude and some characteristics, such as peak values and valley values; they reflect the changing patterns and characteristics of the vibration frequency; and they also reflect the changing patterns and characteristics of the static pressure.

[0078] In another embodiment of the present application, the properties of the clothing material corresponding to the signal characteristics can be determined through experimental data obtained in advance. For example, the drum is rotated at a set speed, a piece of clothing material is placed in the drum, and the friction signal generated by the friction between the sensing device and the clothing material is obtained. The signal characteristics of the friction signal are extracted based on the friction signal. Since the texture height, texture interval, and material stiffness of the clothing material are known, the content of each part of the signal characteristics represents the known texture height, texture interval, and material stiffness of the clothing material. For example, the vibration amplitude corresponds to a certain texture height and material stiffness in a certain numerical range; the vibration frequency corresponds to a certain texture interval in a certain numerical range; and the static pressure corresponds to a certain texture height, material stiffness, and texture interval in a certain numerical range.

[0079] By collecting data from various clothing materials, the properties of the clothing materials corresponding to various signal characteristics at a set speed can be determined.

[0080] It's important to note that since the friction signals generated by different sensing devices rubbing against clothing materials can be highly similar, simply judging the material type based on the friction signal can lead to errors. Therefore, by extracting features from the friction signal and then determining the material type based on the material properties indicated by the signal features, we provide a more detailed analysis of the friction signal, ensuring accurate material identification.

[0081] In step S222a, since the material properties of various clothing materials are known, such as the texture spacing, texture height, and material stiffness of various clothing materials, after obtaining the material properties corresponding to the signal feature, the clothing material type corresponding to the signal feature can be determined.

[0082] See also Figure 6 , Figure 6 A flowchart of determining the type of clothing material corresponding to the signal feature according to an embodiment of the present application is shown. The embodiment of the present application provides a step S220 of determining the type of clothing material corresponding to the signal feature according to the signal feature, including:

[0083] Step S221b: inputting the signal features into a plurality of classification decision trees respectively to obtain the initial clothing material types output by each classification decision tree;

[0084] Step S222b: determining the initial clothing material type that appears the most times as the clothing material type corresponding to the signal feature.

[0085] In step S221b, the signal features are simultaneously input into multiple classification decision trees trained using different subsample sets. The classification decision trees are used to determine the initial clothing material category corresponding to the signal features based on the signal features. Each classification decision tree outputs an initial clothing material category based on the same input signal features.

[0086] In step S222b, to increase the error tolerance of each classification decision tree and improve the accuracy of clothing material classification, multiple classification decision trees are used to determine the clothing material category corresponding to the signal features based on the same signal features. This initial clothing material category is used as the final clothing material category corresponding to the signal features. In this way, even if some classification decision trees contain errors, the accuracy of the output result will not be affected, thereby greatly improving the accuracy of clothing material classification.

[0087] See also Figure 7 , Figure 7 A flow chart of training a classification decision tree according to an embodiment of the present application is shown. The embodiment of the present application provides steps for training a classification decision tree, including:

[0088] Step S401, repeatedly randomly selecting samples equal to the total number of samples from the sample set to obtain a plurality of sub-sample sets, wherein the samples include signal feature samples and clothing material types corresponding to the signal feature samples;

[0089] Step S402 : training a decision tree using each sub-sample set to obtain a classification decision tree corresponding to each sub-sample set.

[0090] The above two steps are described in detail below.

[0091] In step S401, a sample set is created. The sample set contains a set number of samples. Each sample includes a signal feature sample and the type of clothing material corresponding to the signal feature sample. A sample is randomly extracted and placed into a subsample set. This sample is then returned to the sample set, ensuring that it is likely to be selected the next time sampling is performed. In this way, after several random sampling operations, a subsample set containing the set number of samples is obtained. Some samples in the subsample set will appear multiple times, while others will never appear. Approximately 63.2% of the samples in the initial training set appear in the incoming sample set. At least two subsample sets are obtained in this way.

[0092] In step S402, each initial decision tree is trained in the form of one subsample set corresponding to one initial decision tree, to obtain the same number of classification decision trees as the subsample sets.

[0093] By using different sub-sample sets to train classification decision trees, each classification decision tree is also different, which has greater fault tolerance and accuracy when using each classification decision tree to make decisions at the same time. Even if an incorrect classification decision tree appears among many classification decision trees, when determining the type of clothing material by voting, it will not affect the final correct result and the correct type of clothing material will be obtained.

[0094] In step S230, after determining the material type of the laundry to be processed, the processing mode for the laundry to be processed is determined from a preset mode comparison table, and the laundry to be processed is then processed according to the determined processing mode. The mode comparison table records the processing modes corresponding to different types of laundry material, or the processing modes corresponding to different single types of laundry material.

[0095] One friction signal identifies one material type, while multiple friction signals identify multiple material types. If there is only one material type, the processing mode for the garment to be processed is determined directly from the mode comparison table. If there are multiple material types, the processing mode corresponding to the material type composition is determined from the mode comparison table based on the composition of the material types.

[0096] The processing mode includes but is not limited to the speed, water volume, and time for washing and rinsing clothes; the temperature and time for drying clothes; and the temperature, method, and time for sterilizing or ironing clothes.

[0097] It should be noted that the mode comparison table can exist in any form. For example, in one embodiment of the present application, the mode comparison table exhibits a tree-like structure. The mode comparison table identifies the upper-level processing mode compatible with each type of clothing material. This means finding a processing mode that can handle all the clothing materials contained in the clothing to be processed, and then processing the clothing to be processed. At the bottom level of the mode comparison table, the primary processing mode corresponding to each clothing material type is identified—the processing mode that is perfectly suited for that clothing material type. Above the primary processing mode are secondary processing modes, which indicate at least two clothing material types that can be processed within that mode. In other words, the secondary processing mode indicates which clothing material types can be processed simultaneously. Similarly, there are three or even N levels of processing modes, indicating which clothing material types can be processed under the corresponding processing mode. Of course, as the level of the processing mode increases, a more balanced approach will be adopted when processing multiple clothing materials, ensuring that the clothing is treated with maximum efficiency without compromising the various clothing material types.

[0098] Therefore, after determining the type of clothes to be processed, the processing mode that is compatible with all clothes to be processed is determined according to the mode comparison table. This method can ensure that the clothes to be processed are processed in the most suitable clothing processing mode to the greatest extent.

[0099] It should be noted that in one embodiment of the present application, when the processing modes corresponding to clothing material types conflict, the user is reminded of the clothing material type conflict. For example, if clothing material type A requires processing mode A, and clothing material type B requires processing mode B, and mode A and mode B are incompatible, the user is reminded that clothing containing clothing material type A and clothing containing clothing material type B cannot be washed at the same time. The user is asked to remove clothing containing clothing material type A or clothing material type B, and then the clothing material type is identified again. After confirming that there is no conflict in processing mode, the clothing to be processed is processed.

[0100] In another embodiment of the present application, since some types of clothing materials can accept multiple processing modes, but some types of clothing materials can only accept a certain processing mode, in this case, the types of clothing materials that can only accept specific processing modes are set to a higher priority, and the clothing material types with a higher priority are used as the basis for processing to avoid damage to some clothes.

[0101] See also Figure 8 , Figure 8A flowchart is shown for counting the types of clothing materials corresponding to each signal feature, determining the corresponding processing mode in a preset mode comparison table, and processing the clothing to be processed according to one embodiment of the present application. The present embodiment provides step S230 of counting the types of clothing materials corresponding to each signal feature, determining the corresponding processing mode in a preset mode comparison table, and processing the clothing to be processed, including:

[0102] Step S231, among the counted clothing material types, taking the clothing material type with the highest priority as the target clothing material type;

[0103] Step S232: determining a processing mode that matches the target clothing material type in the comparison table, and processing the clothing to be processed.

[0104] The above two steps are described in detail below.

[0105] In step S231, the clothing is prioritized based on the processing conditions required by the clothing material type. The higher the priority, the more complex the corresponding processing mode. The highest priority clothing material type among the counted clothing material types is determined as the target clothing material type.

[0106] In step S232, the clothing processing mode corresponding to the target clothing is determined in the mode comparison table, and it is judged whether the processing mode of the target clothing type can process the clothing material types contained in other clothing to be processed. If so, all clothing to be processed are processed with the processing mode corresponding to the target clothing type. If not, the user is reminded of which clothing material type conflicts with the target clothing material type, prompting the user to resolve the problem as soon as possible.

[0107] In another embodiment of the present application, since each friction signal corresponds to a signal characteristic, and each signal characteristic corresponds to a type of clothing material, each friction signal corresponds to a type of clothing material. Therefore, the proportion of each type of clothing material in the clothing to be processed can be determined based on the clothing material type corresponding to each signal characteristic. Finally, based on the proportion of each type of clothing material, a treatment mode for the clothing to be processed is determined. By using different treatment modes for different proportions of clothing material types, the treatment effect on the clothing to be processed can be maximized.

[0108] Similarly, in combination with the method for determining the processing mode used in the previous embodiment, when determining the clothing material type with the highest priority, the clothing material type with the largest proportion is used as the target clothing material type to determine the processing mode of the clothing to be processed.

[0109] In one embodiment of the present application, the present application also discloses a washing machine, comprising: a drum, providing a processing space for clothes to be processed; a housing, forming an outer shell for the washing machine and providing an installation space for the drum; a sensing device, the sensing device being installed on the inner surface of the drum, for collecting a friction signal generated when the sensing device contacts the clothes to be processed, the friction signal representing the vibration frequency, vibration amplitude, and static pressure generated when the sensing device contacts the clothes to be processed.

[0110] The controller is configured as follows: an acquisition unit for extracting features of each friction signal collected when the drum rotates at a set speed to obtain signal features; a determination unit for determining the type of clothing material corresponding to the signal feature based on the signal feature; and a processing unit for counting the type of clothing material corresponding to each signal feature, determining the corresponding processing mode in a preset mode comparison table, and processing the clothes to be processed.

[0111] In an embodiment of the present application, the controller is also configured as an acquisition unit, which is used to obtain a continuous friction signal segmentation unit through the sensing device when the drum rotates at a set speed. The unit is used to use time as the axis to determine the time node in the continuous friction signal where the fluctuation range is greater than the set threshold as a segmentation point, segment the continuous friction signal, and obtain each friction signal.

[0112] In one embodiment of the present application, the inner surface of the drum is provided with lifting ribs, and the sensing device is installed on the side of the lifting ribs close to the central axis of the drum. This allows the sensing device to fully contact the clothes to be processed, thereby avoiding incomplete detection of the types of clothes.

[0113] The washing machine and the control method for the washing machine provided in the above embodiments are aimed at the situation that the current washing machine cannot accurately identify the type of clothing material of the clothes to be processed. Based on the principle that the vibration frequency, vibration amplitude and static pressure generated by the sensing device when it comes into contact with clothes of different materials are different, the friction signal generated when the sensing device comes into contact with the clothes is used to determine the material of the clothes that the sensing device comes into contact with, and then determine the processing mode according to the material of the clothes to be processed to prevent damage to the clothes.

[0114] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described here can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, USB flash drive, mobile hard disk, etc.) or on a network, and includes several instructions to enable a washing machine to execute the method according to the embodiments of the present application.

[0115] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiment of the application, the features and functions of two or more modules or units described above can be concretized in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be concretized.

[0116] Furthermore, although the steps of the method of the present application are described in a particular order in the accompanying drawings, this does not require or imply that the steps must be performed in this particular order, or that all steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0117] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered merely as exemplary, and the true scope and spirit of the present application are indicated by the appended claims.

Claims

1. A method for controlling a washing machine, characterized in that: The washing machine comprises: The drum provides a processing space for the clothes to be processed; A housing is provided for the outer shell of the washing machine and provides a mounting space for the drum; a sensing device, the sensing device being mounted on the inner surface of the drum and being used to collect a friction signal generated when the sensing device contacts the laundry to be processed, the friction signal representing the vibration frequency, vibration amplitude, and static pressure generated when the sensing device contacts the laundry to be processed; The control method of the washing machine includes: Extracting features of the friction signals collected when the drum rotates at a set speed to obtain signal features; determining, based on the signal feature, a type of clothing material corresponding to the signal feature; The types of clothing materials corresponding to the signal features are counted, the corresponding processing modes are determined in a preset mode comparison table, and the clothing to be processed is processed.

2. The method according to claim 1, characterized in that Before extracting features of the friction signals collected when the drum rotates at a set speed to obtain signal features, the method further includes: When the drum rotates at a set speed, a continuous friction signal is obtained through the sensing device; Taking time as an axis, the time nodes in the continuous friction signal where the fluctuation range is greater than a set threshold are determined as segmentation points, and the continuous friction signal is segmented to obtain individual friction signals.

3. The method according to claim 1, characterized in that The feature extraction is performed on each friction signal collected when the drum rotates at a set speed to obtain signal features, including: Performing an inner product operation on the friction signal and a set function to obtain a characteristic coefficient, wherein the characteristic coefficient represents the amplitude change and phase information of the friction signal at different frequencies; By analyzing the amplitude change and phase information of the friction signal, the signal characteristics of the friction signal are obtained.

4. The method according to claim 1, wherein The determining, based on the signal feature, the type of clothing material corresponding to the signal feature includes: determining, based on the signal features, clothing material properties corresponding to the signal features, the clothing material properties including material stiffness, texture height, and texture spacing; The type of clothing material corresponding to the signal feature is determined according to the property of the clothing material corresponding to the signal feature.

5. The method according to claim 1, wherein The determining, based on the signal feature, the type of clothing material corresponding to the signal feature further includes: Inputting the signal features into a plurality of classification decision trees respectively to obtain the initial clothing material type output by each classification decision tree; The initial clothing material type that appears the most times is determined as the clothing material type corresponding to the signal feature.

6. The method according to claim 1, characterized in that Before inputting the signal features into a plurality of classification decision trees to obtain the initial clothing material types output by each classification decision tree, the method further includes: Repeatably randomly selecting samples of the same number as the total number of samples from the sample set multiple times to obtain a plurality of sub-sample sets, wherein the samples include signal feature samples and clothing material types corresponding to the signal feature samples; Decision trees are trained respectively through each of the sub-sample sets to obtain classification decision trees corresponding to each sub-sample set.

7. The method according to claim 1, characterized in that The counting of the types of clothing materials corresponding to the signal features, determining the corresponding processing mode in a preset mode comparison table, and processing the clothing to be processed includes: Among the clothing material types counted, the clothing material type with the highest priority is used as the target clothing material type; A processing mode matching the target clothing material type is determined in the comparison table, and the clothing to be processed is processed.

8. A washing machine, characterized in that: The washing machine comprises: The drum provides a processing space for the clothes to be processed; A housing is provided for the outer shell of the washing machine and provides a mounting space for the drum; a sensing device, the sensing device being mounted on the inner surface of the drum and being used to collect a friction signal generated when the sensing device contacts the laundry to be processed, the friction signal representing the vibration frequency, vibration amplitude, and static pressure generated when the sensing device contacts the laundry to be processed; A controller configured to: an acquisition unit, configured to extract features of the friction signals acquired when the drum rotates at a set speed, to obtain signal features; a determining unit, configured to determine, based on the signal feature, a type of clothing material corresponding to the signal feature; The processing unit is used to count the types of clothing materials corresponding to the signal characteristics, determine the corresponding processing mode in a preset mode comparison table, and process the clothing to be processed.

9. The washing machine according to claim 8, characterized in that The controller is further configured to: an acquisition unit, configured to acquire a continuous friction signal through the sensing device when the drum rotates at a set speed; The segmentation unit is used to determine the time nodes in the continuous friction signal where the fluctuation range is greater than a set threshold as segmentation points based on time, and segment the continuous friction signal to obtain individual friction signals.

10. The washing machine according to claim 8, characterized in that The inner surface of the drum is provided with lifting ribs, and the sensing device is provided on a side of the lifting ribs close to the central axis of the drum.

Images