Clothes processing equipment, clothes weight determination method and electronic equipment

Abstract

The embodiment of the invention relates to the field of clothes treatment, in particular to clothes treatment equipment, a clothes weight determination method and electronic equipment. The method comprises the steps that motor current data in the staged movement process of a clothes processing barrel is collected, clothes are contained in the clothes processing barrel, and the staged movement process comprises a first movement process enabling the clothes to roll over and a second movement process enabling the clothes and the clothes processing barrel to rotate synchronously; performing feature extraction based on the motor current data to obtain feature data; and determining the weight of the clothes based on the feature data and the corresponding relationship between the feature data and the weight of the clothes. According to the embodiment of the invention, more accurate clothes weight can be obtained.

Description

Technical Field

[0001] The present invention relates to the field of clothing processing, and in particular to a clothing processing device, a clothing weight determination method, and an electronic device. Background Art

[0002] Traditional washing machine weighing technology mainly relies on pressure sensors or motor current integration methods, which have the following technical defects: First, the static weighing method cannot eliminate the torque error caused by the eccentric distribution of clothing, resulting in large fluctuations in measurement accuracy; second, the existing dynamic weighing solution uses a single speed mode, and the detection results deviate greatly from the actual value.

[0003] Therefore, how to provide an accurate method for determining the weight of clothing is a topic of concern in the industry. Summary of the Invention

[0004] In order to solve the problem in the related art that it is difficult to accurately determine the weight of clothes, embodiments of the present invention provide a clothes processing device, a clothes weight determination method, and an electronic device.

[0005] According to a first aspect of an embodiment of the present application, a method for determining the weight of laundry applied to a laundry processing device is provided, the method comprising: collecting motor current data during staged motion of a laundry treatment tub containing laundry, the staged motion comprising a first motion process causing the laundry to tumble and a second motion process causing the laundry to rotate synchronously with the laundry treatment tub; Performing feature extraction based on the motor current data to obtain feature data; The weight of the clothes is determined based on the characteristic data and a corresponding relationship between the characteristic data and the weight of the clothes.

[0006] Optionally, in an implementation of the first aspect of this embodiment, the staged movement process further includes: a deceleration rotation process after the second movement process.

[0007] Optionally, in an implementation of the first aspect of this embodiment, the method includes: controlling the laundry processing tub to increase its speed from an initial speed to a first speed at a first acceleration to achieve the first motion process; controlling the laundry processing tub to increase its speed from the first rotational speed to the second rotational speed at a second acceleration to achieve the second motion process; Alternatively, the method further includes: after the second movement process, controlling the laundry processing tub to decelerate from the second rotation speed to a third rotation speed at a third acceleration.

[0008] Optionally, in an implementation of the first aspect of this embodiment, the clothing processing tub rotates at least one circle when increasing from the first speed to the second speed; the first speed is the critical speed for the clothing and the clothing processing tub to rotate synchronously; the second speed is the critical speed for the clothing processing tub to not collide with the tub.

[0009] Optionally, in an implementation of the first aspect of this embodiment, extracting features based on the motor current data to obtain feature data includes: performing normalization processing on the motor current data to obtain normalized current data; At least one of the feature data in the following dimensions is acquired based on the standardized current data: time domain feature, frequency domain feature, power feature, and friction compensation feature.

[0010] Optionally, in an implementation of the first aspect of this embodiment, the method further includes: Before normalizing the motor current data to obtain the normalized current data, determine whether the motor current data meets the threshold requirement. If so, perform the normalization process; otherwise, perform the clothing shaking process and then re-collect the motor current data.

[0011] Optionally, in an implementation of the first aspect of this embodiment, the normalizing the motor current data includes: performing the standardization process on the motor current data using a reference friction parameter; or, The normalization process is performed on the motor current data using an average value of a stable current phase in the motor current data.

[0012] Optionally, in an implementation of the first aspect of this embodiment, determining the weight of the clothing based on the characteristic data and the correspondence between the characteristic data and the weight of the clothing includes: Inputting the characteristic data into a weight prediction model to obtain the weight of the clothing output by the weight prediction model; The weight prediction model is used to reflect the corresponding relationship between the feature data and the weight of the clothing, and the weight prediction model is trained based on historical feature data and historical clothing weights that have a certain corresponding relationship.

[0013] A second aspect of an embodiment of the present application provides an electronic device, comprising a memory for storing computer instructions; and a processor for calling and executing the computer instructions to implement the method provided in the first aspect of the embodiment of the present application.

[0014] A third aspect of the embodiments of the present application provides a clothing processing device that adopts the method of the first aspect of the embodiments of the present application, or an electronic device that adopts the first aspect of the embodiments of the present application.

[0015] It should be understood that the general description above and the detailed descriptions below are merely exemplary and explanatory and do not limit the present invention. By analyzing and processing motor current data under at least two conditions, namely, tumbling of the laundry and synchronous rotation of the laundry and the laundry treatment tub, the method provided in the present embodiment can determine the laundry weight by integrating the current data under different movement conditions, thereby improving accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0017] Figure 1 is a flow chart of a method for determining the weight of clothes applied to a clothes processing device according to an embodiment of the present application; Figure 2 is a flowchart of a process for determining a standardization process according to an embodiment of the present application; Figure 3 1 is a flow chart of another method for determining the weight of clothes applied to a clothes processing device according to an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0019] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0020] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0021] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of such features. Throughout the description of this application, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0022] According to the inventors' research, washing machine weighing technology primarily relies on pressure sensors or motor current integration methods, which suffer from three technical deficiencies. First, static weighing methods cannot eliminate torque errors caused by eccentric clothing distribution, resulting in large fluctuations in measurement accuracy. Second, existing dynamic weighing solutions use a single speed mode, failing to account for the nonlinear effects of different machines on the friction coefficient. Third, mainstream algorithms use empirical formula fitting, which fails to address generalization issues caused by differences in the mechanical structure of different machines.

[0023] In addition, tests have found that the relevant technology is inaccurate in judging small loads and large eccentricities; the potential differences caused by different clothes under the same load will also lead to inaccurate weight predictions, affecting subsequent washing procedures and user experience.

[0024] Machine learning is a branch of artificial intelligence that enables computers to learn from data and improve their performance without being explicitly programmed. By building mathematical models, machine learning algorithms can extract patterns and regularities from large amounts of data and use these regularities to make predictions or decisions. Common machine learning tasks include classification, regression, clustering, and dimensionality reduction.

[0025] In order to solve at least some of the defects in the related art, the embodiment of the present application provides a method for determining the weight of clothes applied to a clothes processing device. Figure 1 As shown, the laundry weight determination method applied to the laundry treating apparatus includes the following processing procedures.

[0026] 100: Collecting motor current data during the phased movement of the laundry treatment tub, where the laundry treatment tub contains laundry.

[0027] By adopting the method provided in this embodiment, the clothes processing tub is controlled to move in stages, so that the collected current data can more fully reflect the influence of the clothes weight on the current under various movement states.

[0028] The staged motion process includes at least a first motion process for tumbling the clothes and a second motion process for synchronously rotating the clothes and the laundry treatment tub. In this way, the collected current data can comprehensively reflect the state of the clothes tumbling and the clothes rotating synchronously with the laundry treatment tub.

[0029] 102: Extract features based on the motor current data to obtain feature data.

[0030] In this embodiment, feature engineering can be used to obtain feature data. Since the motor current data can be related to various motion states corresponding to the clothing, the extracted feature data also includes features related to the weight of the clothing under different motion states.

[0031] 104: Determine the weight of the clothes based on the characteristic data and the corresponding relationship between the characteristic data and the weight of the clothes. For example, the corresponding relationship can be a mapping relationship, a functional relationship, or a corresponding relationship reflected by a mathematical model (including a neural network model).

[0032] The method provided in this embodiment collects motor current data during the staged movement of the clothing treatment tub, performs feature extraction based on the motor current data, and uses the correspondence between the feature data and the weight of the clothing to obtain the clothing weight. This method integrates the effects of the clothing weight on the motor current under various motion states (for example, the tumbling state of the clothing, the synchronous rotation state of the clothing and the clothing treatment tub), making the obtained clothing weight more accurate.

[0033] Optionally, in one implementation of this embodiment, the staged motion process further includes: a deceleration rotation process after the second motion process. In this way, the collected motor current data covers more stages of motor current data, making the subsequent determination of the laundry weight more accurate.

[0034] Optionally, in one implementation of this embodiment, the first movement process is achieved by controlling the laundry processing tub to increase its speed from an initial speed to a first speed at a first acceleration, and the second movement process is achieved by controlling the laundry processing tub to increase its speed from the first speed to a second speed at a second acceleration. Furthermore, after the second movement process, the laundry processing tub may be controlled to decrease its speed from the second speed to a third speed at a third acceleration.

[0035] This implementation allows current data to be collected under three conditions: speed v1 acceleration, speed v2 acceleration (or stabilization after acceleration), and speed v3 deceleration. Furthermore, friction characteristics are decoupled through dual-gradient accelerations of a1 and a2.

[0036] Illustratively, the first rotational speed is a critical rotational speed for synchronous rotation of the laundry and the laundry treatment tub (e.g., the rotational speed at which the laundry and the laundry treatment tub just rotate synchronously during the gradual acceleration process). The second rotational speed is a critical rotational speed for preventing the laundry treatment tub from colliding (e.g., the rotational speed at which the laundry treatment tub is close to colliding but does not collide during the gradual acceleration process).

[0037] For example, the laundry processing tub does not collide with the tub under both the first acceleration and the second acceleration. Different first and second accelerations facilitate decoupling of friction characteristics and reduce the impact of friction characteristics on the final result.

[0038] For example, when the speed is increased from the first rotation speed to the second rotation speed, the laundry processing tub rotates at least one revolution, which helps to avoid periodic errors from interfering with the accuracy of the final determined weight.

[0039] Illustratively, under the second acceleration, the laundry treatment tub rotates at least one circle, so that a stable current curve of a complete cycle can be used to subsequently determine a reference friction parameter, and periodic errors can be eliminated based on the reference friction parameter.

[0040] Optionally, in an implementation of this embodiment, as Figure 2 As shown, the process 102 may be implemented in the following manner.

[0041] 1020: Performing normalization processing on the motor current data to obtain normalized current data.

[0042] For example, the motor current data can be normalized using a baseline friction parameter, or using the average value of the stable current phase within the motor current data. Such normalized current data can effectively reduce the impact of parameter differences between washing machines of the same model on weight detection results, thereby improving the versatility of the method provided in the embodiments of the present application.

[0043] 1022: Acquire at least one of the following feature data dimensions based on the standardized current data: time domain feature, frequency domain feature, power feature, and friction compensation feature.

[0044] For example, the time domain feature may be a uniform downsampling feature, the frequency domain feature may be a Fourier transform waveform feature, the power feature may be an average power, and the friction compensation feature may be a friction deviation feature of different machines.

[0045] The method provided in this embodiment can make the characteristic data fully reflect the weight of the clothes while reducing the influence of other factors on the weight of the clothes, thereby improving the accuracy of the clothing weight detection and having universality.

[0046] Optionally, in this implementation, before 1020, it is determined whether the motor current data meets the threshold requirements. If so, normalization is performed. Otherwise, the motor current data is recollected after the clothes are shaken out. With this implementation, the maximum value of the collected current data is limited to not exceed a certain threshold, and the minimum value is not lower than a certain threshold. The purpose is to control the stability of the data input to the prediction model. For example, if the load is too heavy and the current is too large, it will affect the model judgment. At this time, it can be directly judged as an overload through the threshold in advance without entering the subsequent model prediction.

[0047] Alternatively, in one implementation of this embodiment, process 104 may be implemented as follows: inputting the feature data into a weight prediction model to obtain the weight of the clothing as output by the weight prediction model. The weight prediction model is used to reflect the correspondence between the feature data and the clothing weight, and the weight prediction model is trained based on historical feature data and historical clothing weights having a predetermined correspondence.

[0048] Exemplarily, the weight prediction model can be a machine learning model, for example, a lightweight model such as LightGBM or linear regression.

[0049] Figure 3 FIG. 1 is a flow chart of a method for determining the weight of clothes applied to a clothes processing device according to an embodiment of the present application. Figure 3 , the method includes the following processing procedures.

[0050] First, the washing program begins, the user opens the washing machine drum door and puts in the clothes.

[0051] After that, the washing machine performs variable initialization processing.

[0052] Afterwards, a shaking process is performed to improve the uniformity of clothing distribution. For example, a forward-reverse alternating strategy (5 direction switches per second) is used to eliminate residual torque errors.

[0053] Afterwards, the barrel is controlled to accelerate to v1 at an acceleration of a1 (for example, from 0 rpm to v1). The entire process can include all program initialization processes. The requirement for selecting v1 is to ensure that the clothes in the barrel do not fall out of the barrel as much as possible and reduce the random errors that occur in the process.

[0054] Afterwards, the bucket is accelerated from v1 to v2 at an acceleration of a2. The requirement for selecting v2 is to minimize the impact of the clothes inside the bucket and reduce random errors during the process. The design of a2 ensures that the entire acceleration process lasts for at least one cycle, which is calculated using the following formula (where t represents the acceleration time):

[0055]

[0056] Assuming v1 is 70 rpm and v2 is 93 rpm, the maximum acceleration required for the acceleration process to last at least one revolution is 31.2 rpm / s.

[0057] Afterwards, the bucket is decelerated from v2 to v3 at an acceleration of a3 to complete current acquisition. The acquired current is then checked to see if it meets the threshold conditions. If not, the process returns to the jittering process and re-acquires the current. a2 and a3 can be the same or different.

[0058] Afterwards, the current is normalized and features such as downsampling, waveform, and eccentricity are extracted.

[0059] After obtaining the standardized current data, feature engineering is used for processing to facilitate feature extraction of subsequent machine learning models. This application can adopt the following feature processing methods. Including: (1) uniform speed downsampling features. Its principle is to reduce the data dimension while retaining key information. By reducing the sampling rate (such as taking the mean, variance, etc.), high-dimensional time series data is compressed into low-dimensional features to capture the dynamic change rules of these stages; (2) Fourier transform waveform features. Its principle is to perform Fourier transform on the signal in the uniform speed stage, extract frequency domain features, and decompose the time domain signal into sinusoidal wave components of different frequencies, which can identify periodic vibration or abnormal frequency components; (3) average power features. Its principle is to calculate the signal energy. The power difference in the speed increase / deceleration stage will reflect the load change; (4) friction deviation features of different machines. Its principle is to describe the inherent characteristics of the equipment through static parameters. The eccentricity value represents the degree of imbalance of the rotating parts and directly affects the vibration amplitude. Friction deviation reflects the friction difference caused by equipment assembly or wear.

[0060] The feature data is then fed into a machine learning model to predict clothing weight. This model can be a lightweight model such as LightGBM or linear regression. The model is trained through extensive experimentation and the collection of numerous features. The model is then directly embedded into the driver.

[0061] The present application also provides an electronic device including a memory and a processor, wherein the memory is used to store computer instructions, and the processor is used to call and execute the computer instructions to implement the laundry weight determination method provided in the present application.

[0062] An embodiment of the present application also provides a clothing processing device, which adopts the clothing weight determination method provided in the previous embodiment of the present application, or has the electronic device provided in the previous embodiment of the present application.

[0063] Any process or method description in the flowcharts of the various embodiments of the present application or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes additional implementations in which functions may be performed in a different order than shown or discussed, including performing functions in a substantially simultaneous manner or in a reverse order depending on the functions involved, which should be understood by a person skilled in the art to which the embodiments of the present application belong.

[0064] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing it in another suitable manner if necessary, and then storing it in a computer memory.

[0065] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0066] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0067] In addition, the functional units in the various embodiments of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into a module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0068] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A method for determining the weight of laundry applied to a laundry processing device, the method comprising: collecting motor current data during staged motion of a laundry treatment tub containing laundry, the staged motion comprising a first motion process causing the laundry to tumble and a second motion process causing the laundry to rotate synchronously with the laundry treatment tub; Performing feature extraction based on the motor current data to obtain feature data; The weight of the clothes is determined based on the characteristic data and a corresponding relationship between the characteristic data and the weight of the clothes.

2. The method according to claim 1, characterized in that The staged motion process further includes: a deceleration rotation process after the second motion process.

3. The method according to claim 1, characterized in that The method comprises: controlling the laundry processing tub to increase its speed from an initial speed to a first speed at a first acceleration to achieve the first motion process; controlling the laundry processing tub to increase its speed from the first rotational speed to the second rotational speed at a second acceleration to achieve the second motion process; Alternatively, the method further includes: after the second movement process, controlling the laundry processing tub to decelerate from the second rotation speed to a third rotation speed at a third acceleration.

4. The method according to claim 3, characterized in that The laundry treatment tub rotates at least one revolution from the first speed to the second speed; The first rotation speed is a critical rotation speed for the clothes and the clothes processing tub to rotate synchronously; The second rotation speed is a critical rotation speed at which the laundry processing tub does not collide with the tub.

5. The method according to claim 1, wherein The extracting features based on the motor current data to obtain feature data includes: performing normalization processing on the motor current data to obtain normalized current data; At least one of the feature data in the following dimensions is acquired based on the standardized current data: time domain feature, frequency domain feature, power feature, and friction compensation feature.

6. The method according to claim 5, characterized in that The method further comprises: Before normalizing the motor current data to obtain the normalized current data, determine whether the motor current data meets the threshold requirement. If so, perform the normalization process; otherwise, perform the clothing shaking process and then re-collect the motor current data.

7. The method according to claim 5, characterized in that The standardizing process of the motor current data includes: performing the standardization process on the motor current data using a reference friction parameter; or, The normalization process is performed on the motor current data using an average value of a stable current phase in the motor current data.

8. The method according to claim 1, characterized in that The determining the weight of the clothes based on the characteristic data and the corresponding relationship between the characteristic data and the weight of the clothes includes: Inputting the characteristic data into a weight prediction model to obtain the weight of the clothing output by the weight prediction model; The weight prediction model is used to reflect the corresponding relationship between the feature data and the weight of the clothing, and the weight prediction model is trained based on historical feature data and historical clothing weights that have a certain corresponding relationship.

9. An electronic device, characterized in that: The electronic device comprises: Memory, for storing computer instructions; A processor, configured to call and execute the computer instructions to implement the method according to any one of claims 1 to 8.

10. A clothes processing device, characterized in that: The laundry processing device comprises the method according to any one of claims 1 to 8, or comprises the electronic device according to claim 9.

Images