Eccentricity detection method and device for washing machine, electronic equipment and washing equipment

Abstract

The application discloses a washing machine eccentricity detection method and device, electronic equipment and washing equipment, and belongs to the technical field of washing machine control. The washing machine eccentricity detection method comprises the following steps: after entering the eccentricity detection stage, real-time acquisition of multi-modal data in the running process of the washing machine, at least including any two of vibration modal data, current modal data and rotating speed modal data; multi-modal feature extraction according to the multi-modal data; weighted fusion of the multi-modal features to generate a fusion feature, and real-time prediction of the eccentricity state of the washing machine based on the fusion feature. The application solves the single sensor sensing blind area problem, improves the accuracy and dynamic response capability of eccentricity detection, provides a directional guide for balance adjustment, reduces the collision of parts and the bearing wear rate, thereby prolonging the service life of mechanical parts.

Description

Technical Field

[0001] The present application relates to the technical field of washing machine control, and in particular to a method and device for detecting eccentricity of a washing machine, an electronic device, and a laundry appliance. Background Art

[0002] As people's living standards and economic and social development levels continue to improve, the functionality and intelligence of washing machines are also constantly improving. During the operation of a washing machine, eccentricity detection is a key step in ensuring smooth operation during the spin cycle. Currently, washing machine eccentricity detection relies on single sensor data (such as vibration or current) combined with a threshold judgment method. Traditional vibration detection is susceptible to uneven load distribution or noise interference during the low-speed spin cycle, resulting in a high misjudgment rate. The current analysis method has limited ability to distinguish normal load changes from eccentricity when the motor speed fluctuates. In particular, there is a risk of failure in variable frequency drive scenarios, resulting in low detection accuracy and limited dynamic adjustment efficiency. Summary of the Invention

[0003] The embodiments of the present application provide a method, device, electronic device and laundry appliance for detecting eccentricity of a washing machine, so as to at least solve the technical problems in the related art of low eccentricity detection sensitivity, high false alarm rate, lack of direction perception and poor dynamic adaptability.

[0004] According to a first aspect of an embodiment of the present application, a method for detecting eccentricity of a washing machine is provided, comprising:

[0005] After entering the eccentricity detection phase, multimodal data of the washing machine during operation is acquired in real time, wherein the multimodal data includes at least any two of vibration modal data, current modal data, and speed modal data;

[0006] Extracting multimodal features based on multimodal data;

[0007] The multimodal features are weightedly fused to generate fused features, and the eccentricity state of the washing machine is predicted in real time based on the fused features.

[0008] In conjunction with the first aspect, in an optional implementation of the embodiment of the present application, after entering the eccentricity detection phase, multimodal data during the operation of the washing machine is acquired in real time, including:

[0009] generating a pulse signal;

[0010] After entering the eccentricity detection phase, multimodal data is acquired in real time based on the pulse signal so that the acquisition start time of each data in the multimodal data is the same;

[0011] Perform difference alignment on each data in the multimodal data based on the pulse signal.

[0012] In conjunction with the first aspect, in an optional implementation of the embodiment of the present application, extracting multimodal features based on multimodal data includes:

[0013] When the multimodal data includes vibration modal data, extracting vibration modal features using the vibration modal data;

[0014] When the multimodal data includes current modal data, current modal features are extracted using the current modal data;

[0015] When the multimodal data includes rotational speed modal data, the rotational speed modal data is used to extract rotational speed modal features.

[0016] In conjunction with the first aspect, in an optional implementation of the embodiment of the present application, multimodal features are weightedly fused to generate fused features, and the eccentricity state of the washing machine is predicted in real time based on the fused features, including:

[0017] The multimodal features are spliced ​​according to the pre-set dimension information to obtain the fusion features;

[0018] The fused features are input into the deep learning model, and the deep learning model is used to predict the eccentricity state of the washing machine in real time.

[0019] In conjunction with the first aspect, in an optional implementation of the embodiment of the present application, before splicing the multimodal features according to pre-set dimensional information to obtain the fused features, the method further includes:

[0020] The weight of each feature in the multimodal feature is adjusted according to the working condition characteristics.

[0021] In conjunction with the first aspect, in an optional implementation of the embodiment of the present application, the deep learning model is a one-dimensional convolutional neural network combined with a transformer model, and the fusion features are input into the deep learning model, and the deep learning model is used to predict the eccentricity state of the washing machine in real time, including:

[0022] Inference is performed on the one-dimensional convolutional neural network and the transformer combined with the model input fusion features to obtain the inference results;

[0023] Extract local features through one-dimensional convolutional neural network to capture the nonlinear coupling relationship in fusion features;

[0024] Capture the long-range correlation between fused features by modeling global dependencies through transformers;

[0025] Based on the inference results, nonlinear coupling relationships, and long-range correlations, the eccentricity state of the washing machine is output.

[0026] In conjunction with the first aspect, in an optional implementation of the embodiment of the present application, the method further includes:

[0027] Adjust the control parameters of the washing machine motor according to the eccentricity state.

[0028] In combination with the first aspect, in an optional implementation of the embodiment of the present application, the eccentricity state includes the eccentricity amount and the eccentricity angle, and adjusting the control parameters of the washing machine motor according to the eccentricity state includes:

[0029] Calculate the speed adjustment amount and the steering adjustment amount according to the eccentricity and the eccentricity angle;

[0030] The washing machine motor is adjusted based on the speed adjustment amount and the direction adjustment amount, and the adjusted eccentricity state is monitored in real time after the adjustment until the eccentricity state reaches a preset eccentricity requirement.

[0031] In the washing machine eccentricity detection method provided by an embodiment of the present invention, after entering the eccentricity detection phase, multimodal data from the washing machine's operation is first acquired in real time. Multimodal features are then extracted from this multimodal data. These features are then weighted and fused to generate fused features. Based on these fused features, the eccentricity state of the washing machine is predicted in real time. Finally, the control parameters of the washing machine's motor are adjusted based on the eccentricity state. This solution overcomes the blind spot problem of a single sensor, improves the accuracy and dynamic response of eccentricity detection, provides guidance for balancing adjustments, and reduces component collisions and bearing wear, thereby extending the life of mechanical components.

[0032] According to a second aspect of an embodiment of the present application, there is provided an eccentricity detection device for a washing machine, comprising:

[0033] an acquisition unit, configured to acquire, in real time, multimodal data during the operation of the washing machine after entering the eccentricity detection phase, wherein the multimodal data includes at least any two of vibration modal data, current modal data, and speed modal data;

[0034] an extraction unit, configured to extract multimodal features based on the multimodal data;

[0035] A prediction unit is used to perform weighted fusion on the multimodal data to generate a fusion feature, and predict the eccentricity state of the washing machine in real time based on the fusion feature.

[0036] According to the third aspect of the embodiments of the present application, the present invention provides an electronic device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, computer instructions being stored in the memory, and the processor executing the computer instructions to thereby execute the eccentricity detection method for a washing machine of the above-mentioned first aspect or any corresponding embodiment thereof.

[0037] According to the fourth aspect of the embodiments of the present application, the embodiments of this specification provide a computer-readable storage medium, on which computer instructions are stored. When the computer instructions are executed by a processor, the eccentricity detection method of the washing machine as described in any one of the above items is implemented.

[0038] According to the fifth aspect of the embodiments of the present application, the embodiments of this specification provide a computer program product or computer program, wherein the computer program product includes a computer program, and the computer program is stored in a computer-readable storage medium; the processor of the computer device reads the computer program from the computer-readable storage medium, and when the processor executes the computer program, it implements the eccentricity detection method of the washing machine as described in any one of the above items.

[0039] The technical effects obtained in the above-mentioned second to fifth aspects are similar to the technical effects obtained by the corresponding technical means in the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 1 is a flow chart of a method for detecting eccentricity of a washing machine provided in an embodiment of the present application;

[0041] Figure 2 1 is a schematic diagram of a specific flow chart of a method for detecting eccentricity of a washing machine provided in an embodiment of the present application;

[0042] Figure 3 This is a schematic diagram of the process of simultaneous extraction of different detection units provided in an embodiment of the present application;

[0043] Figure 4 This is a flow chart of collaborative multimodal data processing provided by an embodiment of the present application;

[0044] Figure 5 2 is a schematic structural diagram of an eccentricity detection device for a washing machine provided in an embodiment of the present application;

[0045] Figure 6 It is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] 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.

[0047] It should be understood that the "plurality" mentioned herein refers to two or more. In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in this article is merely a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in order to facilitate a clear description of the technical solutions of the embodiments of the present application, in the embodiments of the present application, words such as "first" and "second" are used to distinguish between identical or similar items with substantially the same functions and effects. Those skilled in the art will understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit them to be different.

[0048] In addition, the terms "comprises" and "having" and any variations thereof are intended to cover a non-exclusive inclusion. For example, a process, method, system, product or apparatus that includes a series of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, product or apparatus.

[0049] As mentioned in the background technology, with the continuous improvement of people's living standards and the level of economic and social development, the functionality and intelligence of washing machines are also constantly improving. During the operation of the washing machine, eccentricity detection is an important link to ensure smooth operation during the dehydration stage. At present, the eccentricity detection of washing machines relies on a single sensor data (such as vibration or current) combined with a threshold judgment method. Traditional vibration detection is susceptible to uneven load distribution or noise interference during the low-speed dehydration stage, resulting in a high misjudgment rate; the current analysis method has limited ability to distinguish between normal load changes and eccentricity when the motor speed fluctuates, especially in the variable frequency drive scenario, there is a risk of failure. In summary, the current eccentricity detection has the following problems:

[0050] Low sensitivity: may cause sudden imbalance in the dehydration stage;

[0051] High false alarm rate: external interference can easily trigger alarms;

[0052] No direction perception: Unable to locate the eccentric angle, and the efficiency of balance adjustment is limited;

[0053] Insufficient dynamic adaptability: Load changes after clothing absorbs water may render traditional thresholds ineffective.

[0054] In summary, the related art fails to effectively fuse multi-source time series data and lacks the ability to deeply model nonlinear coupling characteristics, resulting in low detection accuracy and limited dynamic adjustment efficiency. Based on this, the embodiment of the present application provides a method for detecting eccentricity of a washing machine, referring to Figure 1The flowchart of the eccentricity detection method of the washing machine shown in FIG. 1 includes the following processing steps.

[0055] S101: After entering the eccentricity detection phase, multimodal data during the operation of the washing machine is obtained in real time.

[0056] In specific implementation, after the washing machine enters the eccentricity detection stage, multimodal data is acquired in real time through sensors, wherein the multimodal data includes at least any two of vibration modal data, current modal data and speed modal data, and of course may also include more other modal data, so as to improve the data source of the multimodal data and make the prediction of the subsequent eccentricity state more accurate.

[0057] S102: Extracting multimodal features based on the multimodal data.

[0058] In a specific implementation, feature extraction is performed using the multimodal data obtained in step S101 to obtain multimodal features corresponding to the multimodal data.

[0059] S103: Perform weighted fusion on the multimodal features to generate fusion features, and predict the eccentricity state of the washing machine in real time based on the fusion features.

[0060] In specific implementation, multimodal features are weightedly fused to obtain fused features, which are then used to predict the eccentricity state of the washing machine in real time. The prediction can be made using a neural network model, or calculated using other forms or algorithms, which is not limited in this embodiment of the present disclosure.

[0061] In this step, the control parameters of the washing machine motor may also be adjusted according to the eccentricity state.

[0062] This embodiment, after entering the eccentricity detection phase, first acquires multimodal data from the washing machine's operation in real time. Multimodal features are extracted from this multimodal data, and then weighted fusion is performed to generate a fused feature. Based on this fused feature, the eccentricity state of the washing machine is predicted in real time. Finally, the control parameters of the washing machine's motor are adjusted based on the eccentricity state. This solution overcomes the blind spot problem of a single sensor, improves the accuracy and dynamic response of eccentricity detection, provides guidance for balancing adjustments, and reduces component collisions and bearing wear, thereby extending the life of mechanical components.

[0063] In the above embodiments of the present application, the descriptions of the various embodiments have their own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The steps shown in the relevant flow charts can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flow charts, in some cases, the steps shown or described can be executed in an order different from that shown here. In other words, the order of steps described in the foregoing embodiments is only an example, and reasonable adjustment of the order of steps based on the content of the embodiments of the present application is also within the scope of protection of the embodiments of the present application.

[0064] like Figure 2 As shown, the eccentricity detection method of the washing machine specifically includes the following processing steps:

[0065] S201: After entering the eccentricity detection phase, multimodal data during the operation of the washing machine is acquired in real time.

[0066] In specific implementation, after the washing machine enters the eccentricity detection stage, multimodal data of the washing machine during operation is obtained in real time, wherein the multimodal data includes at least any two of vibration modal data, current modal data and speed modal data. In this embodiment, taking the multimodal data including vibration modal data, current modal data and speed modal data as an example, it is necessary to set a vibration detection unit, a current detection unit and a speed detection unit respectively to obtain vibration modal data, current modal data and speed modal data respectively.

[0067] The vibration detection unit is installed at key stress points in the washing machine's inner drum (such as the bearing seat) to capture axial and radial vibrations. In one example, to ensure high-precision acquisition of vibration signals, the vibration detection unit uses a high-sensitivity MEMS accelerometer with a sampling frequency set to 10kHz to meet the requirements of capturing high-frequency vibration signals.

[0068] The current sensing unit is integrated into the motor power circuit and collects multiphase current signals. This multiphase current signal collection is achieved through Hall-effect current sensors, which can monitor the current changes in each phase of the motor in real time. In one example, the current sensing unit is installed close to the motor driver circuit board to directly obtain the raw, unfiltered current signal. To improve the accuracy of current signal acquisition, the current sensing unit uses a 24-bit ADC with a sampling frequency of 10kHz to match the sampling rate of the vibration sensing unit.

[0069] The speed detection unit is installed on the motor rotor shaft to monitor the speed and angular acceleration. This unit uses an incremental photoelectric encoder, which outputs a pulse signal by detecting the number of grooves on the grating disk on the rotor shaft. The grating disk outputs a fixed number of pulse signals per rotation, and the current speed value is obtained by calculating the number of pulses per unit time. In one example, to further improve the accuracy of speed measurement, the speed detection unit uses a high-resolution encoder with a resolution of 1024 pulses per revolution. Furthermore, the edge end needs to be equipped with a high-speed communication interface to ensure real-time communication.

[0070] When acquiring multimodal data, time domain alignment of the data can also be performed based on the pulse signal. Specifically, Figure 3 As shown, a periodic synchronization pulse signal is first generated and distributed to each sensor via a dedicated signal line to ensure consistent sampling start times. For example, if the time deviation is less than 0.1ms, the sampling start times are considered identical. A sliding time window is then applied to each sensor data stream. Within the window, data points are interpolated and aligned based on timestamps or pulse counts to ensure complete temporal consistency of the three modal data. A buffer is used to manage the data flow and prevent data accumulation or loss. This solves the problem of time sequence misalignment in heterogeneous data from multiple sources, providing a high-quality data foundation for subsequent feature extraction and fusion.

[0071] S202: Extracting multimodal features based on the multimodal data.

[0072] In specific implementation, when the multimodal data includes vibration modal data, the vibration modal features are extracted using the vibration modal data; when the multimodal data includes current modal data, the current modal features are extracted using the current modal data; when the multimodal data includes speed modal data, the speed modal features are extracted using the speed modal data, and the vibration modal features, current modal features and speed modal features are determined as multimodal features. In practical applications, such as Figure 4As shown, frequency domain analysis is used to extract vibration modal features. Fast Fourier transform (FFT) is performed on the vibration signal to extract the target frequency band. Time domain analysis is also used to calculate the effective value and peak value of the signal to characterize vibration intensity and transient impact. The target frequency band is selected based on the common vibration frequency range during washing machine operation. For example, the low-frequency band of 0-50 Hz is used to characterize vibration caused by uneven clothing load distribution, while the high-frequency band of 50-500 Hz is used to characterize vibration caused by wear or looseness of mechanical components. In time domain analysis, the effective value and peak value of the vibration signal are calculated to characterize vibration intensity and transient impact. The effective value is obtained by taking the square root of the average square of the vibration signal, while the peak value is obtained by finding the maximum absolute value of the vibration signal. The vibration modal features are ultimately represented as energy distribution, effective value, and peak value. When extracting current modal features, torque is used to calculate a vector based on the multiphase current. Harmonic analysis is then performed to characterize current waveform anomalies. The specific steps for vector calculation include converting the three-phase current signal into a current vector in a two-phase stationary coordinate system and then converting the two-phase stationary current vector into a two-phase rotating coordinate system. The motor's output torque information can be obtained by calculating the amplitude of the current vector in the rotating coordinate system. In harmonic analysis, the harmonic components of the current signal are extracted through fast Fourier transform, focusing on the amplitude ratio of the fundamental and harmonic waves. The current modal characteristics are ultimately characterized primarily by torque information and harmonic components. When extracting the speed modal characteristics, the real-time angular acceleration is calculated by differentially measuring the encoder pulse interval. Specifically, the current speed value is obtained by calculating the time interval between two adjacent pulses, and the angular acceleration value is then obtained by calculating the difference between the two adjacent speed values. The angular acceleration value reflects the severity of the speed change and can be used to characterize the dynamic characteristics of the washing machine during operation. The speed modal characteristics are ultimately characterized primarily by angular acceleration.

[0073] S203: The multimodal features are spliced ​​according to the preset dimension information to obtain fusion features.

[0074] In specific implementations, regarding the implementation of multimodal feature fusion, vibration modal features, current modal features, and speed modal features are concatenated into a high-dimensional vector according to preset dimensions. The preset dimensions are selected based on the representational capabilities of each modal feature. For example, the dimension of the vibration modal feature is set to 10, the dimension of the current modal feature is set to 5, and the dimension of the speed modal feature is set to 3. To highlight the impact of important features, the weight of each modal feature is adjusted according to the operating conditions. For example, during the high-speed spin cycle, the weight of the vibration modal feature is increased; during the low-speed wash cycle, the weight of the current modal feature is increased. If a sensor fails (such as a loss of current signal), its weight is forced to 0, and the remaining weights are proportionally amplified according to their current ratios to maintain an overall weight of 1. The resulting fused feature is represented as a weighted high-dimensional vector. Finally, the fused feature can be Z-score normalized to ensure a consistent distribution of values ​​and adapt to subsequent model inputs. Of course, other algorithms such as Min-Max, Robust Scaling, or Log Transform can also be used for normalization, but this is not limited in the present embodiment.

[0075] S204: Input the fused features into a deep learning model, and use the deep learning model to predict the eccentricity state of the washing machine in real time.

[0076] During specific implementation, a lightweight deep learning model combining a one-dimensional convolutional neural network and a transformer, i.e., a 1D-CNN+Transformer structure, can be used as the deep learning model in this embodiment. 1D-CNN is responsible for extracting local features and capturing the nonlinear coupling relationship in vibration, current, and speed modal characteristics, such as the correlation between high-frequency components in the vibration signal and abnormal current waveforms; Transformer is responsible for modeling global dependencies and capturing long-range correlations between multimodal features, such as the delay effect between speed changes and vibration energy distribution. The model outputs the predicted eccentricity state. In this way, millisecond-level prediction of the eccentricity state is achieved, breaking through the response delay bottleneck of traditional open-loop control.

[0077] In this step, other models may also be used, such as GRU, LSTM, Transformer encoder-only model or TCN, which is not limited in the embodiments of the present disclosure.

[0078] S205: Adjusting control parameters of the washing machine motor according to the eccentricity state.

[0079] During specific implementation, the speed adjustment and steering adjustment are first calculated based on the eccentricity and eccentricity angle. The washing machine motor is then adjusted based on the speed adjustment and steering adjustment. After the adjustment, the adjusted eccentricity is monitored in real time until the eccentricity meets the preset eccentricity requirement. This solution calculates the motor speed adjustment and steering adjustment based on the eccentricity and eccentricity angle. The motor speed and steering are adjusted via the motor controller to reduce the eccentricity. For example, when the eccentricity angle is on the left side of the washing machine drum, the left motor speed is reduced and the right motor speed is increased, shifting the clothing load to the right and reducing the eccentricity. The adjusted eccentricity is monitored in real time. If the eccentricity does not reach the preset threshold, the above adjustment process is repeated until the eccentricity meets the requirement. Through the above closed-loop control strategy, dynamic adjustment of the eccentricity is achieved, improving the smoothness and safety of the washing machine operation.

[0080] In this step, the accuracy of eccentricity detection can also be evaluated by obtaining user feedback information. Specifically, user feedback information is input through a mobile phone APP or the washing machine operation panel, including indicators such as the number of eccentricity alarms and the effect of eccentricity adjustment. If there is a deviation between the detection result and the user feedback information, the cause of the deviation is analyzed. For example, certain key modal features are ignored during the feature extraction process or the long-range dependencies are not fully captured during the model inference process. The feature extraction and model inference processes are optimized based on the cause of the deviation. The model parameters are updated through the online learning mechanism to improve the user experience. For example, when the user reports that the washing machine frequently alarms under specific load conditions, the model will automatically adjust the alarm threshold to reduce the false alarm rate.

[0081] The above is an illustration of the method embodiment according to the present application. The embodiment of the present invention further provides a method and device for detecting eccentricity of a washing machine. Figure 5 Schematic diagram of a method and device for detecting eccentricity of a washing machine according to an embodiment of the present invention. Figure 5 , the eccentricity detection device 700 of the washing machine includes the following modules.

[0082] An acquisition unit 701 is configured to acquire multimodal data during the operation of the washing machine in real time after entering the eccentricity detection phase, wherein the multimodal data includes at least any two of vibration modal data, current modal data, and speed modal data;

[0083] An extraction unit 702 is configured to extract multimodal features based on the multimodal data;

[0084] The prediction unit 703 is configured to perform weighted fusion on the multimodal data to generate fusion features, and predict the eccentricity state of the washing machine in real time based on the fusion features.

[0085] In one possible implementation, the acquiring unit 701 is specifically configured to:

[0086] generating a pulse signal;

[0087] After entering the eccentricity detection phase, multimodal data is acquired in real time based on the pulse signal so that the acquisition start time of each data in the multimodal data is the same;

[0088] Perform difference alignment on each data in the multimodal data based on the pulse signal.

[0089] In one possible implementation, the extraction unit 702 is specifically configured to:

[0090] When the multimodal data includes vibration modal data, extracting vibration modal features using the vibration modal data;

[0091] When the multimodal data includes current modal data, current modal features are extracted using the current modal data;

[0092] When the multimodal data includes rotational speed modal data, the rotational speed modal data is used to extract rotational speed modal features.

[0093] In one possible implementation, the prediction unit 703 is specifically configured to:

[0094] The multimodal features are spliced ​​according to the pre-set dimension information to obtain the fusion features;

[0095] The fused features are input into the deep learning model, and the deep learning model is used to predict the eccentricity state of the washing machine in real time.

[0096] In one possible implementation, the prediction unit 703 is further configured to:

[0097] The weight of each feature in the multimodal feature is adjusted according to the working condition characteristics.

[0098] In one possible implementation, the deep learning model is a one-dimensional convolutional neural network combined with a transformer model, and the prediction unit 703 is further configured to:

[0099] Inference is performed on the one-dimensional convolutional neural network and the transformer combined with the model input fusion features to obtain the inference results;

[0100] Extract local features through one-dimensional convolutional neural network to capture the nonlinear coupling relationship in fusion features;

[0101] Capture the long-range correlation between fused features by modeling global dependencies through transformers;

[0102] Based on the inference results, nonlinear coupling relationships, and long-range correlations, the eccentricity state of the washing machine is output.

[0103] In one possible implementation, the device further includes:

[0104] The adjustment unit 704 is configured to adjust the control parameters of the washing machine motor according to the eccentricity state.

[0105] In a possible implementation, the eccentricity state includes an eccentricity amount and an eccentricity angle, and the adjustment unit 704 is specifically configured to:

[0106] Calculate the speed adjustment amount and the steering adjustment amount according to the eccentricity and the eccentricity angle;

[0107] The washing machine motor is adjusted based on the speed adjustment amount and the direction adjustment amount, and the adjusted eccentricity state is monitored in real time after the adjustment until the eccentricity state reaches a preset eccentricity requirement.

[0108] The above describes the device embodiments of the present application. For detailed descriptions of the specific execution processes of data, terms, nouns, steps, technical issues and effects, alternative methods and combinations, please refer to the descriptions in the method embodiments, which will not be repeated here.

[0109] An embodiment of the present application also provides a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the eccentricity detection method for a washing machine according to various embodiments of the present specification described in the above "Exemplary Method" section of the present specification.

[0110] The computer program product can be written in any combination of one or more programming languages ​​to write program codes for executing the operations of the embodiments of this specification, and the programming languages ​​include object-oriented programming languages ​​such as Java, C++, etc., and also include conventional procedural programming languages ​​such as "C" language or similar programming languages.

[0111] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon, and the computer program is executed by a processor to execute the steps of the eccentricity detection method for a washing machine according to various embodiments of the present specification as described in the above “Exemplary Method” section of the present specification.

[0112] An embodiment of the present application also provides an electronic device, including a memory and a processor, wherein the memory stores a method for detecting eccentricity of a washing machine, and the processor is configured to adopt the above-described method for detecting eccentricity of a washing machine when executing the method.

[0113] Specifically, such as Figure 6As shown, the electronic device includes a processor 100, at least one communication bus 200, a user interface 300, at least one external communication interface 400, and a memory 500. The communication bus 200 is configured to enable communication between these components. The user interface 300 may include a display screen, and the external communication interface 400 may include a standard wired interface and a wireless interface. The memory 500 stores a method for detecting eccentricity of a washing machine. The processor 100 is configured to employ the above method when executing the method for detecting eccentricity of a washing machine stored in the memory 500.

[0114] The descriptions of the computer program product, computer-readable storage medium, and electronic device described above are similar to the descriptions of the method embodiments described above and have similar beneficial effects as the method embodiments. For technical details not disclosed in the computer program product, computer-readable storage medium, and electronic device of this application, please refer to the descriptions of the method embodiments of this application for understanding.

[0115] The sequence of the serial numbers or introduction of the embodiments of this application is for description only and does not represent the superiority or inferiority of the embodiments.

[0116] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0117] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0118] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0119] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that includes one or more available media integrated therein. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, or a magnetic tape), an optical medium (e.g., a digital versatile disc (DVD)), or a semiconductor medium (e.g., a solid state disk (SSD)). It is worth noting that the computer-readable storage medium mentioned in the embodiments of the present application may be a non-volatile storage medium, in other words, a non-transient storage medium.

[0120] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in the embodiments of this application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions. For example, the scene data of the current frame in the three-dimensional virtual scene, the client's device information, and the scene interaction information involved in the embodiments of this application are all obtained with full authorization.

[0121] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for detecting eccentricity of a washing machine, characterized in that: The method comprises: After entering the eccentricity detection phase, multimodal data of the washing machine during operation is acquired in real time, wherein the multimodal data includes at least any two of vibration modal data, current modal data, and speed modal data; extracting multimodal features based on the multimodal data; The multimodal features are weightedly fused to generate fusion features, and the eccentricity state of the washing machine is predicted in real time based on the fusion features. The step of performing weighted fusion on the multimodal features to generate a fusion feature, and predicting the eccentricity state of the washing machine in real time based on the fusion feature, includes: Adjusting the weight of each feature in the multimodal feature according to the working condition characteristics; splicing the multimodal features according to pre-set dimensional information to obtain the fused features; The fused features are input into a deep learning model, and the deep learning model is used to predict the eccentricity state of the washing machine in real time.

2. The method according to claim 1, characterized in that After entering the eccentricity detection phase, multimodal data during the operation of the washing machine is obtained in real time, including: generating a pulse signal; After entering the eccentricity detection phase, the multimodal data is acquired in real time based on the pulse signal, so that the acquisition start time of each data in the multimodal data is the same; Perform difference alignment on each data in the multimodal data based on the pulse signal.

3. The method according to claim 1, characterized in that The extracting multimodal features according to the multimodal data includes: When the multimodal data includes the vibration modal data, extracting vibration modal features using the vibration modal data; When the multimodal data includes the current modal data, extracting current modal features using the current modal data; When the multimodal data includes the rotational speed modal data, the rotational speed modal data is used to extract rotational speed modal features.

4. The method according to claim 1, wherein The deep learning model is a one-dimensional convolutional neural network combined with a transformer model, and the fusion features are input into the deep learning model, and the eccentricity state of the washing machine is predicted in real time using the deep learning model, including: Performing reasoning on the one-dimensional convolutional neural network and the transformer combined model by inputting the fusion features to obtain a reasoning result; Extracting local features through a one-dimensional convolutional neural network to capture the nonlinear coupling relationship in the fusion features; Capturing the long-range correlation between the fused features by modeling global dependencies through transformers; Based on the inference result, the nonlinear coupling relationship, and the long-range correlation, the eccentricity state of the washing machine is output.

5. The method according to claim 1, characterized in that The method further comprises: The control parameters of the washing machine motor are adjusted according to the eccentricity state.

6. The method according to claim 5, characterized in that The eccentricity state includes an eccentricity amount and an eccentricity angle, and the step of adjusting the control parameters of the washing machine motor according to the eccentricity state includes: Calculating a speed adjustment amount and a steering adjustment amount according to the eccentricity amount and the eccentricity angle; The washing machine motor is adjusted based on the speed adjustment amount and the direction adjustment amount, and the adjusted eccentricity state is monitored in real time after the adjustment until the eccentricity state reaches a preset eccentricity requirement.

7. The method according to claim 3, characterized in that The adjusting the weight of each feature in the multimodal feature according to the operating condition characteristics includes: The weight of the vibration modal feature, the weight of the current modal feature, and the weight of the speed modal feature are adjusted according to the operating condition feature.

8. The method according to claim 1, characterized in that After entering the eccentricity detection phase, multimodal data during the operation of the washing machine is obtained in real time, including: Acquiring the vibration modal data according to a vibration detection unit installed at a key stress point of the washing machine inner drum; Acquiring the current modal data according to a current detection unit integrated in a click power supply circuit; The speed modal data is obtained according to a speed detection unit installed on the motor rotor shaft.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the eccentricity detection method for a washing machine according to any one of claims 1 to 8 by executing the computer instructions.

10. A laundry device, characterized in that: It adopts the eccentricity detection method of the washing machine described in any one of claims 1 to 8, or has the electronic device described in claim 9.

Images