Clothes weighing method and device, washing machine control method, washing machine and storage medium

Abstract

The invention discloses a clothes weighing method and device, a washing machine control method, a washing machine and a storage medium, relates to the technical field of clothes weighing in washing machines, and solves the problems that in the prior art, an additional sensor needs to be added for clothes weighing in a washing machine, and a clothes weighing method based on the total output power of a motor is poor in universality. The method comprises the following steps: acquiring a drum rotating speed and a silicon controlled rectifier conduction angle of a drum driving motor, inputting the drum rotating speed and the silicon controlled rectifier conduction angle into a trained neural network model to obtain an estimated value of clothes weight, and adding the estimated value and a calibration value under the current clothes weight condition to obtain a clothes weight value, according to the method, sensors such as a pressure sensor and a load sensor do not need to be arranged in the washing machine, the cost is low, the fault rate is low, the method is also suitable for low-end alternating-current series excited motors used by part of household washing machines, and therefore the universality of the weighing method is greatly improved.

Description

Technical Field

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

[0002] In order to optimize the washing effect, save water and electricity, reduce wear and tear on household drum washing machines and extend their lifespan, it is generally necessary to judge the weight of the clothes in the washing machine during washing and adjust the washing program based on the weight.

[0003] Common weighing methods in the prior art include:

[0004] 1. Pressure sensor method: Place a pressure sensor directly under the washing machine drum to measure the weight of the clothes.

[0005] (1) Advantages: the measurement is most accurate;

[0006] (2) The disadvantage is that it is necessary to add a pressure sensor, which increases the cost and has a certain impact on the mechanical design of the washing machine.

[0007] 2. Load sensor method: Measure the torque and speed of the washing machine drum and calculate the load on the drum.

[0008] (1) Advantages: relatively stable, with high measurement accuracy under certain conditions;

[0009] (2) Disadvantages: Easy to wear: Mechanical parts are easy to wear and the accuracy decreases after long-term use.

[0010] 3. Current measurement method: Calculate the weight of clothes through the relationship between motor current and drum speed.

[0011] (1) Advantages: no mechanical parts, reducing the probability of failure, extending equipment life and reducing costs.

[0012] (2) The disadvantages are: the relationship between motor current and clothing weight is complex, difficult to calculate, large error, and easily affected by environmental interference.

[0013] For example: Wuxi Little Swan Company's Chinese invention patent CN103266449A proposes a weighing method, which places a gravity sensor at a corner of the washing machine drum to measure the weight of the washing machine drum, and takes the average value of multiple measurements.

[0014] Haier's Chinese invention patent CN101575793B proposes a weighing method: first accelerate the washing machine to a first speed and record the motor-driven load power at this time. Then accelerate to a second speed, measure the rising power in this process, and then compare it with the load power and load weight relationship curve to obtain the load weight.

[0015] Sichuan Changhong Company's Chinese invention patent CN106757974A proposes a weighing method to measure the total power of the washing machine drum rotating at a stable speed for a fixed time, regress the total power and the weight of the clothes, and use the obtained regression formula to calculate the weight of the clothes.

[0016] It can be seen that the weighing method in the prior art still has the following disadvantages: 1. Adding new pressure sensors or load sensors in the prior art will undoubtedly increase the cost of manufacturers producing washing machines; 2. Some household washing machines use low-end AC series-excited motors, and therefore cannot measure the motor output power value or the motor current value. Only the conduction angle of the thyristor that controls the motor can be measured, resulting in the clothing weighing method based on the total motor output power being difficult to implement in the washing machine using the low-end AC series-excited motor. Summary of the invention

[0017] The purpose of the present application is to overcome the problem in the prior art that washing machines need to add additional sensors to weigh clothes and that the clothing weighing method based on the total power output of the motor has poor universality, and to provide a clothing weighing method, device, washing machine control method, washing machine and storage medium.

[0018] In a first aspect, a method for weighing clothes is provided, comprising:

[0019] Reading the rotation speed of the washing machine drum and the thyristor conduction angle of the drum drive motor in the first process at a preset frequency;

[0020] Inputting the read rotating speed of the washing machine drum and the thyristor conduction angle of the drum drive motor into the trained neural network model to obtain an estimated value of the laundry weight;

[0021] Get the calibration value under the current clothing weight condition;

[0022] The estimated value and the calibrated value are added together to obtain the laundry weight value.

[0023] In some possible implementations, the first process is a process in which the washing machine rotates a drum containing clothes without adding water for washing, so that the drum accelerates from a stationary state to a preset speed and maintains the preset speed stably for a preset time before stopping.

[0024] In some possible implementations, the training method of the neural network model includes:

[0025] S201, reading the rotation speed of the drum of the washing machine and the thyristor conduction angle of the drum drive motor in the second process at a preset frequency, wherein the second process is a process in which the washing machine rotates a drum with a built-in counterweight block of a standard weight, so that the drum accelerates from rest to a preset speed and keeps the preset speed stably for a preset time before stopping;

[0026] S202, changing the weight of the counterweight block, and repeating step S201 to obtain a first data set;

[0027] S203, normalizing the first data set to obtain a second data set;

[0028] S204, dividing the second data set into a training set and a test set according to a preset ratio;

[0029] S205: Use the training set and the test set to train and test the neural network model to obtain a trained neural network model.

[0030] In some possible implementations, the neural network model uses a time series network as the basic network and uses a stochastic gradient descent algorithm to train the model. During the test, if the mean square error of the predicted value of the neural network model is less than a first preset error value, the neural network model training is considered to be completed.

[0031] In some possible implementations, the training method of the neural network model further includes:

[0032] S206, reading the rotation speed of the drum of the washing machine and the thyristor conduction angle of the drum driving motor in the third process at a preset frequency, wherein the third process is a process in which the washing machine rotates a drum containing clothes of known weight without adding water for washing, so that the drum accelerates from rest to a preset speed and keeps the preset speed stably for a preset time before stopping;

[0033] S207, normalizing the rotation speed of the washing machine drum and the thyristor conduction angle of the drum drive motor in the third process and inputting them into the trained neural network model to obtain an estimated value of the laundry weight;

[0034] S208, comparing the estimated value obtained in step S207 with the actual weight of the clothes, if the error is less than a second preset error value, the calibration value under the current clothes weight condition is zero, otherwise the calibration value under the current clothes weight condition is calculated;

[0035] S209. Repeat steps S206 to S208 to obtain calibration values ​​under different clothing weight conditions.

[0036] In some possible implementations, the method for calculating the calibration value includes:

[0037] Recording the actual laundry weight value under the current laundry weight condition, and repeating steps S206 to S207 to obtain multiple estimated values ​​of laundry weight under the current laundry weight condition;

[0038] An average difference between an actual laundry weight value under a current laundry weight condition and a plurality of estimated laundry weight values ​​is calculated, and the average difference is used as a calibration value under the current laundry weight condition.

[0039] In a second aspect, a clothing weighing device is provided, comprising:

[0040] A data acquisition module, used for reading the rotation speed of the washing machine drum and the thyristor conduction angle of the drum drive motor in the first process at a preset frequency;

[0041] A model prediction module, used for inputting the read rotating speed of the washing machine drum and the thyristor conduction angle of the drum drive motor into a trained neural network model to obtain an estimated value of the laundry weight;

[0042] A calibration value acquisition module, used to obtain a calibration value under the current clothing weight condition;

[0043] A calculation module is used to add the estimated value and the calibration value to obtain a laundry weight value.

[0044] In a third aspect, a washing machine control method is provided, including the method in any one of the implementations of the first aspect, and further including: regulating operating parameters of the washing machine according to the weight value of the clothes.

[0045] In a fourth aspect, a washing machine is provided, comprising a device as in any one of the implementations of the second aspect, wherein the washing machine can weigh the clothes in a drum by means of the device as in any one of the implementations of the second aspect.

[0046] In a fifth aspect, a computer-readable storage medium is provided, wherein the computer-readable medium stores a program code for execution by a device, wherein the program code includes steps for executing the method in any one of the implementations of the first aspect described above.

[0047] This application has the following beneficial effects:

[0048] 1. The weighing method proposed in this application does not need to install pressure sensors, load sensors and other sensors in the washing machine, which not only reduces the mechanical complexity and cost of the washing machine, simplifies the structure of the washing machine, but also avoids the probability of malfunction of the washing machine caused by adding sensors;

[0049] 2. This application uses an algorithm to replace the load sensor. It does not need to directly measure the motor-driven load electric energy and the motor's output power. Instead, it measures the driving thyristor conduction angle and uses an artificial neural network to fit the complex nonlinear relationship between the thyristor conduction angle and the motor output power. By introducing artificial neural network technology into the field of washing machine weighing, it can significantly improve the accuracy of washing machine weighing and reduce the error in traditional methods. For some household washing machines that use low-end AC series-excited motors, it is also possible to measure the thyristor conduction angle of the motor, thereby greatly improving the universality of the weighing method of this application. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application.

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0052] Figure 1 is a flow chart of a clothing weighing method according to Embodiment 1 of the present application;

[0053] Figure 2 is a structural block diagram of a clothing weighing device according to Embodiment 2 of the present application;

[0054] Figure 3 It is a schematic diagram of the washing machine of embodiment 4 of the present application.

[0055] Reference numerals:

[0056] 100. Data acquisition module; 200. Model prediction module; 300. Calibration value acquisition module; 400. Calculation module; 500. Clothing weighing device. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] Example 1

[0059] like Figure 1As shown, a clothing weighing method according to Embodiment 1 of the present application includes:

[0060] S100. Reading the rotation speed of the washing machine drum and the thyristor conduction angle of the drum drive motor in the first process at a preset frequency, wherein the first process is a process in which the washing machine rotates the drum with clothes inside without adding water for washing, so that the drum accelerates from rest to a preset speed and keeps stably rotating at the preset speed for a preset time before stopping.

[0061] Specifically, after the user uses the washing machine and puts the laundry into the drum of the washing machine and closes the drum cover, the washing machine does not perform operations such as adding water and washing, but only rotates the drum, so that the drum starts from rest, accelerates to a certain speed (for example, 800 rpm), and then rotates steadily for 5 seconds, and then gradually decelerates and stops rotating. In this process, the washing machine control program reads and records the rotation speed of the washing machine drum and the conduction angle of the thyristor controlling the motor, wherein the record is made every 20 milliseconds, and 50 records are generated per second, and the recorded content includes the rotation speed of the washing machine drum and the conduction angle of the thyristor controlling the motor.

[0062] S200, inputting the read rotating speed of the washing machine drum and the thyristor conduction angle of the drum drive motor into a trained neural network model to obtain an estimated value of the laundry weight;

[0063] It should be noted that before using the trained neural network model to estimate the weight of clothing, the neural network model needs to be trained first. The training process is as follows:

[0064] S201. First, place a standard weight counterweight in the drum of the washing machine. The standard weight of the counterweight is known. The counterweight can be any object that can be weighed and will not damage the inner wall of the drum, such as a rubber block, a rubber sheet, a piece of clothing, a rag doll, etc. That is to say, the counterweight is not necessarily a block, but can be any shape. Then control the speed of the washing machine drum, accelerate from rest, until the speed reaches the set speed, for example: 800 rpm. Then run stably for 5 seconds, then decelerate and stop rotating. The drum speed and the duration of stable operation can be customized according to needs.

[0065] During the whole process of the washing machine drum accelerating, rotating steadily, slowing down and stopping, the speed of the washing machine drum and the conduction angle of the thyristor controlling the motor are continuously recorded. For example, the record is made every 20 milliseconds, and 50 records are generated per second. The frequency of recording the speed of the washing machine drum and the conduction angle of the thyristor controlling the motor can also be customized according to the needs.

[0066] S202, changing the weight of the counterweight, repeating the measurement, and collecting multiple sets of data. The number of repetitions can be customized according to needs, and the weight distribution of the counterweight should evenly cover the working weight range of the washing machine, for example: 0.2 kg, 0.4 kg, ... 1 kg, 2 kg, etc., until the maximum working weight of the washing machine, such as 6 kg.

[0067] In the operation record of the washing machine, at each time point, the two values ​​of the drum speed and the thyristor conduction angle are taken as the eigenvalue vector. The eigenvalue vectors of 50 consecutive time points (i.e. 1 second) are combined into a sequence as the input of the neural network model. The weight of the counterweight is the output of the neural network. Each input and the corresponding output constitute a piece of data.

[0068] From the collected operation records of washing machines under different weight conditions, a large amount of data is generated according to the above method. All these data constitute the training data set of the neural network model.

[0069] S203, preprocess the training data set and normalize the data to [0,1]. The preprocessing adopts the min-max method, that is, linear transformation of the data. The method is:

[0070]

[0071] In the formula, X normalized is the normalized data, X is the data to be normalized, X max is the maximum value of the same type of data in the training data set as the data to be normalized, X min It is the minimum value of the same type of data in the training data set as the data to be normalized.

[0072] S204, dividing the normalized training data set into a training set and a test set in a ratio of 7:3, wherein the ratio of the training set to the test set can be customized according to the requirements, and can also be set to a ratio of 8:2, 6:4, etc.

[0073] S205. Use the training set and the test set to train and test the neural network model to obtain a trained neural network model. Specifically, first design an artificial neural network according to the neural network input and output defined in the above step S202.

[0074] In this embodiment, the neural network model uses the time series network (TSN) as the basic network. The time series network is a neural network model used to process sequence data with time dependence. This type of network can capture the dynamic characteristics of data changing over time and is widely used in natural language processing, financial forecasting, video analysis and other fields.

[0075] The loss function of the neural network model uses the mean square error (MSE). It evaluates the accuracy of the model by calculating the average of the squares of the differences between the predicted values ​​and the actual values. The calculation formula of MSE is

[0076]

[0077] In the formula, MSE stands for mean square error, n is the number of samples, and Y i is the actual value of the i-th sample, is the estimated value of the ith sample.

[0078] The stochastic gradient descent (SGD) algorithm is used to train the neural network model. The core idea of ​​stochastic gradient descent is to gradually reduce the value of the loss function by continuously adjusting the model parameters. It improves computational efficiency by randomly selecting a sample in each iteration to calculate the gradient and update the model parameters.

[0079] Use the training set data to train the neural network model, and then use the test set data to evaluate the neural network model. If the mean square error (MSE) of the model prediction value of the test set data is less than 0.01, the model is considered to have been trained. Otherwise, the model hyperparameters need to be adjusted and the neural network model needs to be retrained.

[0080] S206. After the neural network model training is completed, data calibration is required to further improve the accuracy of clothing weighing. Weigh the clothes first and then put them into the washing machine. Control the speed of the washing machine drum and accelerate from a standstill until the speed reaches the set speed, for example: 800 rpm. Then run stably for 5 seconds, then decelerate and stop rotating.

[0081] During the above operation of the washing machine, the speed of the washing machine drum and the conduction angle of the thyristor controlling the motor are continuously recorded. For example, the record is recorded every 20 milliseconds, and 50 records are generated per second.

[0082] S207, using the neural network model trained in step S205, and the washing machine operation record obtained in step S206 (including the washing machine drum speed and the thyristor conduction angle of the control motor) to obtain an estimated value of the laundry weight output by the neural network model.

[0083] S208, compare the estimated value of the clothing weight obtained in step S207 with the actual clothing weight. If the error is less than the second preset error value, the calibration value under the current clothing weight condition is zero, otherwise the calibration value under the current clothing weight condition is calculated, wherein the error can be the difference between the estimated value of the clothing weight and the actual clothing weight, the error can also be the mean square error between the estimated value of the clothing weight and the actual clothing weight, of course, the error can also be the mean square error between the estimated value of the clothing weight and the actual clothing weight after normalization, etc., and the error can be defined according to user needs. For example: the user needs to have a normalized mean square error of less than 0.01, then if the mean square error between the estimated value of the clothing weight and the actual clothing weight is less than 0.01 after normalization, it indicates that the neural network model has met the user's needs, that is, under the clothing weight condition, the estimated value of the neural network model can already meet the user's needs, and the calibration value is recorded as 0, otherwise it means that the error is large and does not meet the user's needs, and the calibration value needs to be calculated.

[0084] If the error is large, the neural network model needs to be calibrated using the calibration value. The specific method is: record the difference between the actual clothing weight and the estimated value output by the neural network model. After repeated experiments, an average difference is obtained. This average difference is the calibration value under the current clothing weight condition. For example: the actual clothing weight is 4.10 kg, and the average weight calculated using the neural network model through multiple experiments is 4.40 kg. Then the calibration value under the current clothing weight (4.40 kg) condition is: 4.10 kg - 4.40 kg = -0.30 kg.

[0085] S209, repeating steps S206 to S208, and repeating the above steps repeatedly under different clothing weight conditions to obtain calibration values ​​under different clothing weight conditions.

[0086] S300, obtaining a calibration value under the current clothing weight condition, wherein the current clothing weight condition refers to an estimated value predicted and output by the neural network model, for example, if the clothing weight output by the neural network model is 4.4 kg, then it is necessary to obtain a calibration value under the current clothing weight condition (4.40 kg), for example, the calibration value under the current clothing weight condition (4.40 kg) is -0.30 kg. It should be noted that, in general, the calibration value is pre-calculated and can be stored locally or in the cloud. In actual use, it is only necessary to obtain the calibration value under the current clothing weight condition by query, thereby improving the efficiency of clothing weighing;

[0087] S400. Add the estimated value and the calibration value to obtain the weight value of the clothes. For example, the estimated value output by the neural network model prediction in step S200 is 4.40 kg, and the calibration value under the current clothing weight (4.40 kg) obtained in step S300 is -0.30 kg. Then, the estimated value and the calibration value are added to obtain the clothing weight value: 4.40 kg + (-0.30 kg) = 4.10 kg.

[0088] Through the above implementation, this application provides an efficient and accurate method for weighing clothes in a washing machine drum, which significantly improves the performance and user experience of the washing machine by using neural network technology and real-time data processing. This method is not only applicable to household washing machines, but can also be extended to commercial laundry equipment, bringing a higher level of intelligence to the laundry industry.

[0089] Secondly, since the weighing method proposed in this application does not require the installation of pressure sensors, load sensors and other sensors in the washing machine, it not only reduces the mechanical complexity and cost of the washing machine and simplifies the structure of the washing machine, but also avoids the probability of malfunction of the washing machine due to the addition of sensors.

[0090] In order to improve the universality of the weighing method, the present application uses an artificial neural network to fit the complex nonlinear relationship between the thyristor conduction angle and the motor output power. By introducing artificial neural network technology into the field of washing machine weighing, the accuracy of washing machine weighing can be significantly improved, and the errors in traditional methods can be reduced. For some household washing machines using low-end AC series-excited motors, although the motor output power value and the motor current value cannot be measured, the thyristor conduction angle that controls the motor can be measured. Therefore, the weighing method of the present application is also applicable to some household washing machines using low-end AC series-excited motors.

[0091] Example 2

[0092] like Figure 2 As shown, a clothing weighing device according to Embodiment 2 of the present application includes:

[0093] The data acquisition module 100 is used to read the rotation speed of the drum of the washing machine and the thyristor conduction angle of the drum drive motor in the first process at a preset frequency;

[0094] A model prediction module 200, for inputting the read rotating speed of the washing machine drum and the thyristor conduction angle of the drum drive motor into a trained neural network model to obtain an estimated value of the laundry weight;

[0095] The calibration value acquisition module 300 is used to obtain the calibration value under the current clothing weight condition;

[0096] The calculation module 400 is used to add the estimated value and the calibration value to obtain the laundry weight value.

[0097] It should be noted that other specific implementations of the clothing weighing device in this embodiment can refer to the specific implementations of the above-mentioned clothing weighing method, and will not be described again here to avoid redundancy.

[0098] Example 3

[0099] A washing machine control method involved in Example 3 of the present application includes a method as in any one of the implementations in the above-mentioned Example 1, and also includes: regulating the operating parameters, operating programs, etc. of the washing machine according to the weight value of the clothes to achieve the purpose of optimizing the washing effect and saving water and electricity.

[0100] Example 4

[0101] like Figure 3 As shown, a washing machine involved in this embodiment 4 includes a clothing weighing device 500 as in any one of the embodiments in the above embodiment 2. The washing machine can rely on the clothing weighing device 500 as in any one of the embodiments in the above embodiment 2 to weigh the clothing in the drum, so that the subsequent operating parameters, operating programs, etc. of the washing machine can be adjusted according to the weight value of the clothing, so as to achieve the purpose of optimizing the washing effect and saving water and electricity.

[0102] Example 5

[0103] A computer-readable storage medium involved in Embodiment 5 of the present application, wherein the computer-readable storage medium stores a program code for execution by a device, wherein the program code includes steps for executing a method in any one of the implementations in Embodiment 1 of the present application;

[0104] Among them, the computer-readable storage medium can be a read-only memory (ROM), a static storage device, a dynamic storage device or a random access memory (RAM); the computer-readable storage medium can store program code, and when the program stored in the computer-readable storage medium is executed by the processor, the processor is used to execute the steps of the method in any one of the implementation methods in Example 1 of the present application.

[0105] The above are only preferred specific implementations of the present application; however, the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical solution and its improved ideas of the present application within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for weighing clothing, characterized in that: include: Reading the rotation speed of the washing machine drum and the thyristor conduction angle of the drum drive motor in the first process at a preset frequency; Inputting the read rotating speed of the washing machine drum and the thyristor conduction angle of the drum drive motor into the trained neural network model to obtain an estimated value of the laundry weight; Get the calibration value under the current clothing weight condition; The estimated value and the calibrated value are added together to obtain the laundry weight value.

2. The clothing weighing method according to claim 1, characterized in that: The first process is a process in which the washing machine rotates a drum containing clothes without adding water for washing, so that the drum accelerates from a stationary state to a preset speed and keeps rotating at the preset speed for a preset time before stopping.

3. The clothing weighing method according to claim 1, characterized in that: The training method of the neural network model includes: S201, reading the rotation speed of the drum of the washing machine and the thyristor conduction angle of the drum drive motor in the second process at a preset frequency, wherein the second process is a process in which the washing machine rotates a drum with a built-in counterweight block of a standard weight, so that the drum accelerates from rest to a preset speed and keeps the preset speed stably for a preset time before stopping; S202, changing the weight of the counterweight block, and repeating step S201 to obtain a first data set; S203, normalizing the first data set to obtain a second data set; S204, dividing the second data set into a training set and a test set according to a preset ratio; S205: Use the training set and the test set to train and test the neural network model to obtain a trained neural network model.

4. The clothing weighing method according to claim 3, characterized in that: The neural network model uses a time series network as the basic network and adopts a stochastic gradient descent algorithm to train the model. During the test, if the mean square error of the predicted value of the neural network model is less than a first preset error value, the neural network model training is considered to be completed.

5. The clothing weighing method according to claim 3 or 4, characterized in that: The training method of the neural network model also includes: S206, reading the rotation speed of the drum of the washing machine and the thyristor conduction angle of the drum driving motor in the third process at a preset frequency, wherein the third process is a process in which the washing machine rotates a drum containing clothes of known weight without adding water for washing, so that the drum accelerates from rest to a preset speed and keeps the preset speed stably for a preset time before stopping; S207, normalizing the rotation speed of the washing machine drum and the thyristor conduction angle of the drum drive motor in the third process and inputting them into the trained neural network model to obtain an estimated value of the laundry weight; S208, comparing the estimated value obtained in step S207 with the actual weight of the clothes, if the error is less than a second preset error value, the calibration value under the current clothes weight condition is zero, otherwise the calibration value under the current clothes weight condition is calculated; S209. Repeat steps S206 to S208 to obtain calibration values ​​under different clothing weight conditions.

6. The clothing weighing method according to claim 5, characterized in that: The calculation method of the calibration value includes: Recording the actual laundry weight value under the current laundry weight condition, and repeating steps S206 to S207 to obtain multiple estimated values ​​of laundry weight under the current laundry weight condition; An average difference between an actual laundry weight value under a current laundry weight condition and a plurality of estimated laundry weight values ​​is calculated, and the average difference is used as a calibration value under the current laundry weight condition.

7. A clothing weighing device, characterized in that: include: A data acquisition module, used for reading the rotation speed of the washing machine drum and the thyristor conduction angle of the drum drive motor in the first process at a preset frequency; A model prediction module, used for inputting the read rotating speed of the washing machine drum and the thyristor conduction angle of the drum drive motor into a trained neural network model to obtain an estimated value of the laundry weight; A calibration value acquisition module, used to obtain a calibration value under the current clothing weight condition; A calculation module is used to add the estimated value and the calibration value to obtain a laundry weight value.

8. A washing machine control method, characterized in that: The method comprises the method as described in any one of claims 1 to 6, further comprising: regulating the operating parameters of the washing machine according to the weight value of the clothes.

9. A washing machine, characterized in that: Comprising the clothing weighing device as claimed in claim 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program code for execution by a device, wherein the program code includes steps for executing the method according to any one of claims 1 to 6.

Images