Control method, device and washing machine for laundry dehydration

Abstract

The application provides a clothes dehydration control method and device and electronic equipment. The method comprises: obtaining posture data of a washing machine, wherein the posture data at least comprises acceleration and angular velocity; analyzing the posture data through a target neural network model to obtain an eccentricity value, wherein the eccentricity value represents a degree of deviation from the center, the target neural network model is obtained by training a plurality of sets of data, and each set of data in the plurality of sets of data comprises historical posture data and a historical eccentricity value; and in a case where the eccentricity value is greater than or equal to a preset eccentricity value, controlling the washing machine to enter an untangling process, wherein the untangling process represents a process of untangling clothes of the washing machine. Through the application, the problem that the eccentricity value of the washing machine is not accurately measured, resulting in a large number of clothes untangling times and poor user experience, is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of laundry dehydration control of a washing machine, in particular to a laundry dehydration control method and device, a computer readable storage medium and a washing machine. BACKGROUND

[0002] Currently, in the washing process of a drum washing machine, the distribution of washing objects is uneven in the washing, drying and dehydration processes due to different materials, sizes and water absorption levels of the laundry. The uneven distribution of the laundry not only reduces the washing effect, but also causes excessive vibration of the washing machine, increases noise and reduces the service life of the washing machine in the high-speed dehydration process. Generally, in the dehydration process, too much or too much entangled laundry will cause excessive eccentricity, at which time the entanglement needs to be disentangled. The traditional disentanglement treatment is to perform a cycle of forward rotation and reverse rotation, and then start the speed increase again. When the eccentricity is too large, the disentanglement operation is started again, and the process is repeated until the eccentricity is reduced to the speed increase.

[0003] In order to reduce the vibration and improve the service life of the washing machine, the maximum speed at which the laundry can be raised is determined by measuring the eccentricity of the laundry in advance in the washing process. The measurement of the eccentricity is particularly important in the dehydration process of the washing machine. The accuracy of the eccentricity detection often affects the dehydration performance and vibration of the washing machine.

[0004] The prior art discloses a dehydration processing method, device, equipment and storage medium based on load distribution. After obtaining the parameter information of the laundry processing equipment in the low-speed dehydration stage, the parameter information is input into the load distribution identification network model, and when it is determined that the output result of the load distribution identification network model is the uniform distribution state, the laundry processing equipment is controlled to enter the high-speed dehydration stage. However, this method may not be able to successfully enter the high speed for a long time due to the non-uniform distribution of the laundry. Another prior art discloses a laundry processing equipment and its control method, and a washing machine dehydration stage is provided with a dehydration speed increasing stage. In the dehydration speed increasing stage, the motor adjustment parameter is determined based on the vibration value and the eccentricity value of the laundry processing equipment; and whether the running condition of the motor needs to be adjusted is determined according to the motor adjustment parameter. However, the accuracy of the laundry eccentricity detection in the above-mentioned prior art is low, the number of laundry disentanglement is large, and the user experience is poor. SUMMARY

[0005] The main purpose of the present application is to provide a laundry dehydration control method and device, a computer readable storage medium and a washing machine to at least solve the problem of inaccurate measurement of the eccentricity of the washing machine in the prior art, which causes a large number of laundry disentanglement and poor user experience.

[0006] To achieve the above object, according to one aspect of the present application, a control method for clothes dehydration is provided, comprising: obtaining posture data of a washing machine, wherein the posture data at least includes acceleration and angular velocity of a washing tub; analyzing the posture data by a target neural network model to obtain an eccentricity value, wherein the eccentricity value represents a degree of deviation from the center, the target neural network model is obtained by training a plurality of sets of data, each set of data in the plurality of sets of data includes historical posture data and a historical eccentricity value; in a case where the eccentricity value is greater than or equal to a preset eccentricity value, controlling the washing machine to enter an untangling process, wherein the untangling process represents a process of untangling clothes in the washing machine.

[0007] Optionally, before analyzing the posture data by the target neural network model, the method further comprises: obtaining the historical posture data corresponding to eccentricity detection modules of a plurality of preset weights, and obtaining the historical eccentricity value corresponding to each of the eccentricity detection modules of the plurality of preset weights; establishing an initial target neural network model, training the initial target neural network model by the historical posture data and the historical eccentricity value until the loss function of the initial target neural network model is an optimal value, to obtain the target neural network model.

[0008] Optionally, obtaining the historical posture data corresponding to eccentricity detection modules of a plurality of preset weights comprises: in a case where the washing machine starts dehydration, obtaining a current rotation speed; in a case where the current rotation speed is greater than a rotation speed threshold, obtaining the historical posture data corresponding to eccentricity detection modules of a plurality of preset weights, wherein the rotation speed threshold is a minimum rotation speed at which the clothes are close to the tub wall.

[0009] Optionally, controlling the washing machine to enter the untangling process comprises: controlling the washing machine tub to rotate forward by a preset angle; controlling the washing machine tub to rotate reversely by the preset angle.

[0010] Optionally, after controlling the washing machine to enter the untangling process, the method further comprises one of the following: in a case where an untangling time is greater than or equal to a preset time, controlling the washing machine to enter a dehydration process, wherein the untangling time represents a running time of the untangling process; obtaining a current eccentricity value, and in a case where the current eccentricity value is less than the preset eccentricity value, controlling the washing machine to enter the dehydration process.

[0011] Optionally, controlling the washing machine to enter the dehydration process comprises: determining an optimal rotation speed corresponding to the current eccentricity value, and controlling the washing machine to enter the dehydration process at the optimal rotation speed.

[0012] Optionally, determining the optimal rotating speed corresponding to the current eccentricity value comprises: obtaining a one-to-one mapping relationship between eccentricity values and optimal rotating speeds; and determining the optimal rotating speed corresponding to the current eccentricity value according to the one-to-one mapping relationship between eccentricity values and optimal rotating speeds.

[0013] According to another aspect of the present application, a control device for clothes dehydration is provided, comprising: a first obtaining unit configured to obtain attitude data of a washing machine, wherein the attitude data comprises at least acceleration and angular velocity of a washing tub; an analyzing unit configured to analyze the attitude data by a target neural network model to obtain an eccentricity value, wherein the eccentricity value represents a degree of deviation from the center, and the target neural network model is obtained by training a plurality of sets of data, each set of data comprising historical attitude data and a historical eccentricity value; and a first control unit configured to control the washing machine to enter an untangling process if the eccentricity value is greater than or equal to a preset eccentricity value, wherein the untangling process represents a process of untangling clothes in the washing machine.

[0014] According to still another aspect of the present application, a computer readable storage medium is provided, comprising a stored program, wherein the program, when executed, controls a device in which the computer readable storage medium is located to perform any of the control methods for clothes dehydration.

[0015] According to yet another aspect of the present application, a washing machine is provided, comprising one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs comprise a program for performing any of the control methods for clothes dehydration.

[0016] By applying the technical solution of the present application, the attitude data of the washing machine is obtained, wherein the attitude data comprises at least acceleration and angular velocity; the attitude data is analyzed by a target neural network model to obtain an eccentricity value, wherein the eccentricity value represents a degree of deviation from the center, and the target neural network model is obtained by training a plurality of sets of data, each set of data comprising historical attitude data and a historical eccentricity value; and the washing machine is controlled to enter an untangling process if the eccentricity value is greater than or equal to a preset eccentricity value, wherein the untangling process represents a process of untangling clothes in the washing machine. Compared with the prior art, in which the eccentricity value of the washing machine is not accurate, resulting in a large number of times of clothes untangling and poor user experience, the present application predicts the eccentricity value by the attitude data of the washing machine, and controls the washing machine to untangle according to the predicted eccentricity value, thereby avoiding the problem of too many times of untangling and improving the user experience. Therefore, the problem of poor user experience caused by too many times of clothes untangling in the prior art can be solved, and the user experience is improved. BRIEF DESCRIPTION OF DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the application and, together with the description, serve to explain the application. In the drawings:

[0018] Figure 1 A flowchart of a control method for clothes dehydration is shown;

[0019] Figure 2 An installation position of a posture sensor in a drum washing machine is shown;

[0020] Figure 3 A data collection and training flowchart of a posture sensor is shown;

[0021] Figure 4 A specific control method for clothes dehydration is shown;

[0022] Figure 5 A structure block diagram of a control device for clothes dehydration is shown. DETAILED DESCRIPTION

[0023] It should be noted that the embodiments and features of the embodiments in the present application can be combined with each other without conflict. The embodiments of the present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0024] In order to enable persons skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by persons skilled in the art without creative labor should fall within the scope of protection of the present application.

[0025] 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 do not necessarily mean a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not necessarily limit to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0026] As introduced in the background, the eccentricity value of the washing machine in the prior art is not accurate, resulting in more clothes detangling times and poor user experience. To solve the problem of poor user experience, embodiments of the present application provide a clothes dewatering control method, device, computer readable storage medium and washing machine.

[0027] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.

[0028] In the present embodiment, a clothes dewatering control method running on a mobile terminal, a computer terminal or a similar computing device is provided. It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that here.

[0029] Figure 1 is a flowchart of the clothes dewatering control method according to the embodiments of the present application. As shown in Figure 1 , the method comprises the following steps:

[0030] Step S201, obtaining attitude data of the washing machine, wherein the attitude data at least includes acceleration and angular velocity of the washing tub;

[0031] Specifically, the present application uses an attitude sensor to obtain the attitude data of the clothes during the dewatering process. The attitude reflects the vibration of the clothes in the washing tub. The attitude data, such as acceleration (a x ,a y ,a z ) and angular velocity (r x ,r y ,r z ). Figure 2 The figure shows the installation position of the attitude sensor in the drum washing machine. In order to better extract the attitude of the washing machine during washing, it is installed on the outer drum and its position is kept in the middle position of the top of the inner barrel. The outer drum will have different degrees of shaking during washing, and the degree of shaking is related to the speed and the size of the clothes eccentricity. The attitude sensor installed on the outer drum can reflect the vibration of the barrel during washing.

[0032] Step S202, analyzing the attitude data through a target neural network model to obtain an eccentricity value, wherein the eccentricity value represents the degree of deviation from the center, and the target neural network model is obtained by training a plurality of sets of data, each set of data in the plurality of sets of data comprising historical attitude data and historical eccentricity value;

[0033] Specifically, the above-mentioned posture data is input into a neural network prediction model to accurately predict the eccentricity value of the clothes, and the clothes are unwound according to the eccentricity value and the speed of the motor is adjusted according to the eccentricity value, thereby improving the accuracy of the clothes eccentricity detection, reducing the number of clothes unwinding, and saving the dehydration time.

[0034] In step S203, in the case that the eccentricity value is greater than or equal to a preset eccentricity value, the washing machine is controlled to enter an unwinding process, wherein the unwinding process represents unwinding the clothes of the washing machine.

[0035] Specifically, the clothes are unwound according to the eccentricity value and the speed of the motor is adjusted according to the eccentricity value, that is, when the eccentricity value is greater than or equal to a preset eccentricity value, the clothes are unwound.

[0036] Through the embodiment, the posture data of the washing machine is obtained, wherein the posture data at least includes acceleration and angular velocity; the posture data is analyzed by a target neural network model to obtain an eccentricity value, wherein the eccentricity value represents the degree of deviation from the center, the target neural network model is obtained by training a plurality of sets of data, each set of data in the plurality of sets of data includes historical posture data and historical eccentricity value; in the case that the eccentricity value is greater than or equal to a preset eccentricity value, the washing machine is controlled to enter an unwinding process, wherein the unwinding process represents unwinding the clothes of the washing machine. Compared with the prior art, in which the eccentricity value of the washing machine is not accurate, resulting in a large number of clothes unwinding and poor user experience, the present application predicts the eccentricity value through the posture data of the washing machine, and controls the washing machine to unwind according to the predicted eccentricity value, thereby avoiding the problem of too many unwinding times and improving the user experience. Therefore, the problem of poor user experience caused by too many clothes unwinding times in the prior art can be solved, and the user experience is improved.

[0037] In the specific implementation process, before the posture data is analyzed by the target neural network model, the method further includes the following steps: step S204: obtaining the historical posture data corresponding to the eccentricity detection module of a plurality of preset weights, and obtaining the historical eccentricity value corresponding to each eccentricity detection module of the preset weight; step S205: establishing an initial target neural network model, training the initial target neural network model through the historical posture data and the historical eccentricity value until the loss function of the initial target neural network model is the optimal value, and obtaining the target neural network model. The method trains the neural network model through the above steps to obtain a target neural network model suitable for eccentricity value prediction, and accurately predicts the eccentricity value.

[0038] Specifically, the input layer of the initial target neural network model contains 6 neurons corresponding to the normalization of 3 linear accelerations and angular accelerations, and contains 2 hidden layers, the first hidden layer contains 64 neurons, the second layer contains 32 neurons, and the output layer is 1 neuron for outputting the predicted value. Each neuron is fully connected to the neurons of the next layer. When determining whether to hit the bucket, the neural network model needs to be trained. Due to the difference in the installation position of the attitude sensor, the current position and attitude are more sensitive. In order to obtain more consistent data, the attitude sensor is calibrated before training to eliminate the error of each installation. The historical attitude data of the inner cylinder under the rotation speed of the eccentricity detection module (100g, 200g, 500g, 700g, 1000g) of different preset weights is collected and input into the neural network; and when the rotation speed reaches the value of the clothes close to the cylinder wall, the eccentricity value is measured, and the eccentricity detection module is generally an eccentric block.

[0039] The collected acceleration sensor is input to the neural network for training. First, the output of each neuron is calculated in turn from the input layer to the output layer. For the i-th neuron in the l-th layer, its output a i (l) is

[0040]

[0041] where n(l-1) represents the number of neurons in the l-1-th layer; w ij (l) is the weight connecting the j-th neuron in the l-1-th layer and the i-th neuron in the l-th layer; a j (l-1) is the output of the j-th neuron in the l-1-th layer; f is an activation function, f(x) = max(0, x); b i (l) is the bias of the i-th neuron in the l-th layer.

[0042] For this neural network, the input vector of the input layer is X, the weight matrix from the input layer to the hidden layer is W1, and the bias vector is b1. The output of the first hidden layer is:

[0043] z1 = XW1 + b1

[0044] a1 = f(z1)

[0045] Similarly, the output of the second hidden layer is:

[0046] z2 = XW2 + b2

[0047] a2 = f(z2)

[0048] For the last layer, the node calculation value Z is directly output.

[0049] However, the output prediction value Z is inaccurate for the untrained neural network, which requires continuous iteration of the neural network, calculation of the loss function MSE, that is, the mean square error, on the training set, and calculation of the gradient of the loss function with respect to each parameter, where N is the number of samples, yi is the actual value, is the predicted value.

[0050]

[0051] The gradient of the loss function is reduced each time the iteration is performed, so the gradient is updated each time the iteration is performed:

[0052]

[0053] where a is the learning rate, and the values of W and b are iteratively trained until a set value is met or the maximum number of iterations is reached. The collected eccentricity value and the posture data at the current maximum speed are trained, and the neural network is continuously updated until the loss function MSE reaches a relatively ideal value. The trained neural network can then be used to predict the eccentricity value.

[0054] In some optional embodiments, the step S204 acquires the historical posture data corresponding to the eccentricity detection module of the plurality of preset weights, which can be achieved by the following steps: in the case that the washing machine starts to dehydrate, the current speed is acquired; in the case that the current speed is greater than the speed threshold, the historical posture data corresponding to the eccentricity detection module of the plurality of preset weights is acquired, wherein the speed threshold is the minimum speed at which the clothes are tightly attached to the barrel wall. The historical posture data is acquired by the above steps, which can ensure that the historical posture data is acquired under the condition of meeting the conditions, so as to further ensure accurate prediction of the eccentricity value.

[0055] In the specific implementation process, Figure 3 for the data acquisition and training process of the posture sensor, the eccentric block pre-weight is set as shown above, and when the washing machine performs the dehydration action, the speed starts to rise, and when the speed reaches the speed threshold at which the clothes are tightly attached to the barrel wall, that is, the speed threshold is the critical speed at which the clothes are tightly attached to the barrel wall, the eccentricity value is measured to obtain the eccentricity value under the current eccentric block weight.

[0056] In other optional embodiments, the step S203 controls the washing machine to enter the untwining process, which can be achieved by the following steps: step S2031: control the washing machine barrel to rotate forward by a preset angle; step S2032: control the washing machine barrel to rotate in reverse by the preset angle. The above steps are used to untwine, which can avoid the clothes from being entangled.

[0057] Specifically, the preset angle is 180 degrees, the unwinding is performed by constantly reversing 180 degrees, and the neural network is called to determine the eccentricity during the unwinding. When the eccentricity is less than D or the maximum unwinding time is reached, the speed is increased, and one dehydration is completed. The cycle is repeated until the dehydration is completed.

[0058] In the specific implementation process, after the washing machine enters the unwinding process, the method further includes one of the following: in the case that the unwinding time is greater than or equal to a preset time, controlling the washing machine to enter a dehydration process, wherein the unwinding time represents the running time of the unwinding process; obtaining a current eccentricity value, and in the case that the current eccentricity value is less than the preset eccentricity value, controlling the washing machine to enter the dehydration process. The method exits the unwinding process and enters the dehydration process through the above steps, which can make the clothes washing more uniform and clean.

[0059] Specifically, after entering the unwinding process, in the case that a set unwinding time is reached or the eccentricity value is less than the maximum eccentricity value at a set speed, dehydration is performed at an optimal speed n, and it is further determined whether n is greater than a set speed or the maximum unwinding number K is reached. In the case of yes, it is ended, and in the case of no, it continues to enter the dehydration process.

[0060] In some optional embodiments, controlling the washing machine to enter the dehydration process includes the following steps: determining an optimal speed corresponding to the current eccentricity value, and controlling the washing machine to enter the dehydration process according to the optimal speed. The method determines the optimal speed corresponding to the current eccentricity value through the above steps, which can make the clothes dehydrate at the most suitable speed, achieving the optimal dehydration effect.

[0061] In the specific implementation process, the optimal speed of the washing machine in the dehydration process is determined by using the eccentricity value predicted by the neural network, so that the dehydration effect can be optimized and the noise can be controlled within an acceptable range.

[0062] In some optional embodiments, the above step of determining the optimal speed corresponding to the current eccentricity value can be implemented by the following steps: obtaining a one-to-one mapping relationship between the eccentricity value and the optimal speed; and determining the optimal speed corresponding to the current eccentricity value according to the one-to-one mapping relationship between the eccentricity value and the optimal speed. The method determines the optimal speed through the one-to-one mapping relationship, which can ensure that the clothes dehydrate at the optimal speed, achieving the best dehydration effect.

[0063] Specifically, Table 1-1 is the optimal speed under different eccentricity values obtained by experiments.

[0064] Table 1-1 Optimal speed under different eccentricity values

[0065] eccentric mass maximum rotational speed 100g 1320 rad / min 200g 1320 rad / min 500g 837 rad / min 700g 525 rad / min 1000g 249 rad / min 1500g 126 rad / min

[0066] The binomial is used to fit this curve to get the relationship between the eccentricity value and the rotation speed as shown in the following formula: y = 0.000623x 2 -1.925x + 1593.213, x represents the eccentricity value, and y represents the optimal rotation speed.

[0067] In order for those skilled in the art to more clearly understand the technical solutions of the present application, the implementation process of the laundry dehydration control method of the present application will be described in detail below in conjunction with specific embodiments.

[0068] The present embodiment relates to a specific laundry dehydration control method, as shown in the following steps: Figure 4

[0069] Step S1: dehydration starts;

[0070] Step S2: posture sensor calibration;

[0071] Step S3: start to speed up, when the rotation speed reaches a value that allows the laundry to tightly adhere to the barrel wall, the neural network predicts the eccentricity value;

[0072] Step S4: the eccentricity value is greater than the maximum eccentricity value at the set rotation speed;

[0073] Step S5: untangle forward rotation by 180 degrees and then reverse rotation by 180 degrees, and predict the eccentricity value;

[0074] Step S6: determine whether the set untangling time is reached or the eccentricity value is less than the eccentricity value at the set rotation speed;

[0075] Step S7: if yes, proceed with dehydration at the optimal rotation speed n;

[0076] Step S8: determine whether n is greater than the set rotation speed or the maximum untangling number K is reached, if no, continue to execute the above steps, if yes, end.

[0077] The present application also provides a laundry dehydration control device. It should be noted that the laundry dehydration control device of the present application can be used to execute the laundry dehydration control method provided by the present application. The device is used to implement the above embodiments and preferred embodiments, and those that have been described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware can also be implemented and conceived.

[0078] The laundry dehydration control device provided by the present application will be described below.

[0079] Figure 5 ​is a schematic view of a control device for laundry dehydration according to an embodiment of the present application. As shown in Figure 5 the device comprises:

[0080] a first acquisition unit 10 configured to acquire posture data of a washing machine, wherein the posture data comprises at least acceleration and angular velocity of a washing tub;

[0081] Specifically, the present application uses a posture sensor to acquire posture data of laundry during dehydration, the posture reflects the vibration of laundry in the washing tub, and the posture data is, for example, acceleration (a x , a y , a z ) and angular velocity (r x , r y , r z ). Figure 2 The installation position of the posture sensor in the drum washing machine is on the outer cylinder, and its position is kept in the middle position of the top of the inner barrel. The outer cylinder will shake to different degrees during washing, and the degree of shaking is related to the speed and the size of the laundry eccentricity. The posture sensor installed on the outer cylinder can reflect the vibration of the barrel during washing.

[0082] an analysis unit 20 configured to analyze the posture data through a target neural network model to obtain an eccentricity value, wherein the eccentricity value represents the degree of deviation from the center, and the target neural network model is obtained by training a plurality of sets of data, each set of data comprising historical posture data and a historical eccentricity value;

[0083] Specifically, the above posture data is input into a neural network prediction model to accurately predict the eccentricity value of the laundry, and the laundry is unwound according to the eccentricity value and the speed of the motor is adjusted according to the eccentricity value, which improves the accuracy of the laundry eccentricity detection, reduces the number of laundry unwinding, and saves the dehydration time.

[0084] a first control unit 30 configured to control the washing machine to enter an unwinding process when the eccentricity value is greater than or equal to a preset eccentricity value, wherein the unwinding process represents unwinding the laundry of the washing machine.

[0085] Specifically, the laundry is unwound according to the eccentricity value and the speed of the motor is adjusted according to the eccentricity value, i.e. when the eccentricity value is greater than or equal to the preset eccentricity value, the laundry is unwound.

[0086] By the embodiment, posture data of the washing machine is acquired, wherein the posture data at least includes acceleration and angular velocity; the posture data is analyzed by a target neural network model to obtain an eccentricity value, wherein the eccentricity value represents a degree of deviation from the center, the target neural network model is obtained by training a plurality of sets of data, each set of data in the plurality of sets of data includes historical posture data and a historical eccentricity value; in a case where the eccentricity value is greater than or equal to a preset eccentricity value, the washing machine is controlled to enter an untangling process, wherein the untangling process represents a process of untangling clothes of the washing machine. Compared with the prior art, in which the eccentricity value of the washing machine is not accurate, resulting in a large number of clothes untangling times and poor user experience, the present application predicts the eccentricity value through the posture data of the washing machine, and controls the washing machine to untangle according to the predicted eccentricity value, thereby avoiding the problem of too many untangling times and improving the user experience. Therefore, the problem of poor user experience caused by too many clothes untangling times in the prior art can be solved, and the user experience is improved.

[0087] In a specific implementation process, before the posture data is analyzed by the target neural network model, the device further includes a second acquisition unit and a training unit. The second acquisition unit is configured to acquire the historical posture data corresponding to the eccentricity detection module of a plurality of preset weights, and to acquire the historical eccentricity value corresponding to the eccentricity detection module of each preset weight. The training unit is configured to establish an initial target neural network model, train the initial target neural network model by using the historical posture data and the historical eccentricity value, until the loss function of the initial target neural network model is an optimal value, and obtain the target neural network model. The device trains the neural network model through the above steps to obtain a target neural network model suitable for eccentricity value prediction, and accurately predicts the eccentricity value.

[0088] Specifically, the input layer of the initial target neural network model includes 6 neurons corresponding to the normalization of 3 linear accelerations and angular accelerations, and includes 2 hidden layers. The first hidden layer includes 64 neurons, the second layer includes 32 neurons, and the output layer includes 1 neuron for outputting a predicted value. Each neuron is fully connected to the neurons of the next layer. When determining whether to hit the bucket, the neural network model needs to be trained. Due to the difference in the installation position of the posture sensor, the current position and posture are sensitive. In order to obtain more consistent data, the posture sensor is calibrated before training to eliminate the error of each installation. The historical posture data of the inner cylinder under the speed of the eccentricity detection module (100g, 200g, 500g, 700g, 1000g) of different preset weights is collected and input into the neural network; and the eccentricity value is measured when the speed reaches the point at which the clothes are close to the cylinder wall. The eccentricity detection module is generally an eccentric block.

[0089] The collected acceleration sensor input is input to the neural network for training. First, the output of each neuron is calculated from the input layer to the output layer in turn. For the i-th neuron in the l-th layer, its output a i (l) For

[0090]

[0091] where n(l-1) represents the number of neurons in the l-1-th layer; w ij (l) is the weight connecting the j-th neuron in the l-1-th layer and the i-th neuron in the l-th layer; a j (l-1) is the output of the j-th neuron in the l-1-th layer; f is an activation function, f(x) = max(0, x); b i (l) is the bias of the i-th neuron in the l-th layer.

[0092] For this neural network, the input vector of the input layer is X, the weight matrix from the input layer to the hidden layer is W1, and the bias vector is b1. The output of the first hidden layer is:

[0093] z1 = XW1 + b1

[0094] a1 = f(z1)

[0095] Similarly, the output of the second hidden layer is:

[0096] z2 = XW2 + b2

[0097] a2 = f(z2)

[0098] For the last layer, the output node calculates the value Z directly.

[0099] However, for a neural network that has not been trained, the predicted value Z of the output is not accurate, which requires continuous iteration of the neural network, calculation of the loss function MSE, that is, the mean square error, and calculation of the gradient of the loss function with respect to each parameter, where N is the number of samples, yi is the actual value, is the predicted value.

[0100]

[0101] The gradient of the loss function is reduced each time the iteration is performed, so the gradient is updated each time the iteration is performed:

[0102]

[0103]

[0104] wherein a is the learning rate, and the values of W and b are iteratively trained until a set value is satisfied or a maximum number of iterations is reached. The collected eccentricity values and posture data at the current maximum rotational speed are trained, and the neural network is constantly updated until the damage function MSE reaches a relatively ideal value. The trained neural network can then be used to predict the eccentricity value.

[0105] In some optional embodiments, the second acquisition unit includes a first acquisition module and a second acquisition module. The first acquisition module is configured to acquire the current rotational speed when the washing machine starts the dehydration process. The second acquisition module is configured to acquire the historical posture data corresponding to the eccentricity detection module of the plurality of preset weights when the current rotational speed is greater than a rotational speed threshold. The rotational speed threshold is the minimum rotational speed at which the clothes adhere to the barrel wall. The device acquires the historical posture data through the above steps, which ensures that the historical posture data is acquired under the condition of meeting the conditions, thereby further ensuring accurate prediction of the eccentricity value.

[0106] In the specific implementation process, Figure 3 For the data acquisition and training process of the posture sensor, when the washing machine performs the dehydration operation, the speed starts to increase. When the rotational speed reaches the rotational speed threshold, which is the critical rotational speed at which the clothes adhere to the barrel wall, the eccentricity value is measured to obtain the eccentricity value under the current eccentric block weight.

[0107] In some other optional embodiments, the first control unit includes a first control module and a second control module. The first control module is configured to control the forward rotation of the washing machine barrel by a preset angle. The second control module is configured to control the reverse rotation of the washing machine barrel by the preset angle. The device performs the untwisting through the above steps, which can avoid the clothes from being tangled.

[0108] Specifically, the preset angle is 180 degrees, and the untwisting adopts the continuous forward and reverse rotation of 180 untwisting operations. The neural network is constantly called to determine the eccentricity value during the untwisting process. When the eccentricity value is less than D or the maximum untwisting time is reached, the speed starts to increase, and one dehydration is completed. The cycle is repeated until the dehydration is completed.

[0109] In the specific implementation process, after controlling the washing machine to enter the untwisting process, the device further includes a second control unit and a third control unit. The second control unit is configured to control the washing machine to enter the dehydration process when the untwisting time is greater than or equal to a preset time. The untwisting time represents the running time of the untwisting process. The third control unit is configured to acquire the current eccentricity value and control the washing machine to enter the dehydration process when the current eccentricity value is less than the preset eccentricity value. The device exits the untwisting process and enters the dehydration process through the above steps, which can make the clothes cleaning more uniform and clean.

[0110] Specifically, after entering the untangling process, if a set untangling time is reached or the eccentricity value is less than the maximum eccentricity value at the set rotation speed, dehydration is performed at the optimal rotation speed n, and it is further determined whether n is greater than the set rotation speed or the maximum number of untangling times K is reached, and if yes, the process is ended, and if no, the dehydration process is continued.

[0111] In some optional embodiments, the third control unit comprises a third control module configured to determine the optimal rotation speed corresponding to the current eccentricity value and control the washing machine to enter the dehydration process at the optimal rotation speed. The device determines the optimal rotation speed corresponding to the current eccentricity value through the above steps, so that the clothes can be dehydrated at the most suitable rotation speed, achieving the optimal dehydration effect.

[0112] In the implementation process, the optimal rotation speed of the washing machine in the dehydration process is determined by using the eccentricity value predicted by the neural network, so that the dehydration effect can be optimized and the noise can be controlled within an acceptable range.

[0113] In some optional embodiments, the third control module comprises an acquisition submodule and a determination submodule, the acquisition submodule is configured to acquire a one-to-one mapping relationship between the eccentricity value and the optimal rotation speed, and the determination submodule is configured to determine the optimal rotation speed corresponding to the current eccentricity value according to the one-to-one mapping relationship between the eccentricity value and the optimal rotation speed. The device determines the optimal rotation speed through the one-to-one mapping relationship, so that the clothes can be dehydrated at the optimal rotation speed, achieving the best dehydration effect.

[0114] Specifically, Table 1-1 is the optimal rotation speed at different eccentricity values obtained by experiments.

[0115] Table 1-1 Optimal rotation speed at different eccentricity values

[0116] eccentric mass maximum rotational speed 100g 1320 rad / min 200g 1320 rad / min 500g 837 rad / min 700g 525 rad / min 1000g 249 rad / min 1500g 126 rad / min

[0117] The binomial is used to fit this curve to obtain the relationship between the eccentricity value and the rotation speed as shown in the following formula: y = 0.000623x 2 -1.925x + 1593.213, x represents the eccentricity value, and y represents the optimal rotation speed.

[0118] The control device for the dehydration of the clothes comprises a processor and a memory, and the above-mentioned first acquisition unit, analysis unit and first control unit are stored in the memory as program units, and the corresponding functions are realized by the processor executing the program units stored in the memory. The above-mentioned modules are located in the same processor; or the above-mentioned modules are located in different processors in any combination.

[0119] The processor contains a kernel, which retrieves the corresponding program unit from memory. One or more kernels can be configured. By adjusting kernel parameters, the system can address the issue of inaccurate eccentricity measurement in washing machines, resulting in frequent untangling of clothing and a poor user experience.

[0120] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0121] An embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the control method for dehydrating clothes.

[0122] Specifically, the control method for dehydrating clothes includes:

[0123] Step S201, obtaining posture data of the washing machine, wherein the posture data at least includes the acceleration and angular velocity of the washing tub;

[0124] Specifically, the present invention uses a posture sensor to obtain the posture data of the clothes during the dehydration process. The posture reflects the vibration of the clothes in the washing tub. The posture data, such as acceleration (a x ,a y ,a z ) and angular velocity (r x ,r y ,r z ). Figure 2 The position sensor in a drum washing machine is located on the outer drum to better detect the machine's position during the wash cycle. It is positioned in the center of the inner drum. The outer drum vibrates to varying degrees during the wash cycle, with the intensity of the vibration related to the rotational speed and the eccentricity of the clothing. The position sensor installed on the outer drum can reflect the vibration of the drum during the wash cycle.

[0125] Step S202: Analyzing the posture data using a target neural network model to obtain an eccentricity value, wherein the eccentricity value indicates a degree of deviation from the center, and the target neural network model is obtained by training multiple sets of data, each set of data including: historical posture data and historical eccentricity values;

[0126] Specifically, the above-mentioned posture data is input into a neural network prediction model to accurately predict the eccentricity value of the clothes, and the clothes are unwound according to the eccentricity value, and the speed of the motor is adjusted according to the eccentricity value, thereby improving the accuracy of the clothes eccentricity detection, reducing the number of clothes unwinding, and saving the dehydration time.

[0127] Step S203, in the case that the eccentricity value is greater than or equal to a preset eccentricity value, the washing machine is controlled to enter an unwinding process, wherein the unwinding process represents unwinding the clothes in the washing machine.

[0128] Specifically, the clothes are unwound according to the eccentricity value, and the speed of the motor is adjusted according to the eccentricity value, that is, when the eccentricity value is greater than or equal to a preset eccentricity value, the clothes are unwound.

[0129] The embodiment of the present application provides a washing machine, which comprises a processor, a memory, and a program stored in the memory and executable on the processor, and at least the following steps are realized when the processor executes the program:

[0130] Step S201, acquiring posture data of the washing machine, wherein the posture data at least comprises acceleration and angular velocity of the washing tub;

[0131] Specifically, the posture sensor is used to acquire the posture data of the clothes in the dehydration process, and the posture reflects the vibration condition of the clothes in the washing tub. The posture data is, for example, acceleration (a x ,a y ,a z ) and angular velocity (r x ,r y ,r z ). Figure 2 The installation position of the posture sensor in the drum washing machine is that the posture sensor is installed on the outer drum and kept at the middle position of the top of the inner tub, so as to better extract the posture of the washing machine in the washing process. The outer drum will shake to different degrees in the washing process, and the shaking intensity is related to the rotation speed and the size of the clothes eccentricity. The posture sensor installed on the outer drum can reflect the vibration condition of the washing tub in the washing process.

[0132] Step S202, analyzing the posture data through a target neural network model to obtain an eccentricity value, wherein the eccentricity value represents the degree of deviation from the center, and the target neural network model is obtained by training a plurality of groups of data, and each group of data in the plurality of groups of data comprises historical posture data and a historical eccentricity value;

[0133] Specifically, the above-mentioned posture data is input into a neural network prediction model to accurately predict the eccentricity value of the clothes, and the clothes are unwound according to the eccentricity value, and the rotating speed of the motor is adjusted according to the eccentricity value, thereby improving the accuracy of the clothes eccentricity detection, reducing the number of clothes unwinding, and saving the dehydration time.

[0134] In step S203, when the eccentricity value is greater than or equal to a preset eccentricity value, the washing machine is controlled to enter an unwinding process, wherein the unwinding process represents unwinding the clothes in the washing machine.

[0135] Specifically, the clothes are unwound according to the eccentricity value, and the rotating speed of the motor is adjusted according to the eccentricity value, that is, when the eccentricity value is greater than or equal to a preset eccentricity value, the clothes are unwound.

[0136] The device herein can be a server, a PC, a PAD, a mobile phone, etc.

[0137] The application also provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the method described in various embodiments of the application:

[0138] In step S201, posture data of a washing machine is acquired, wherein the posture data at least includes acceleration and angular velocity of a washing tub.

[0139] Specifically, the posture sensor is used to acquire the posture data of the clothes in the dehydration process, and the posture reflects the vibration of the clothes in the washing tub. The posture data is, for example, acceleration (ax, ay, az) and angular velocity (rx, ry, rz). Figure 2 The posture sensor is installed on the outer drum and kept at the middle position of the top of the inner tub in order to better extract the posture of the washing machine in the washing process. The outer drum will shake to different degrees in the washing process, and the shaking intensity is related to the rotating speed and the size of the clothes eccentricity. The posture sensor installed on the outer drum can reflect the vibration of the tub in the washing process.

[0140] In step S202, the posture data is analyzed by a target neural network model to obtain an eccentricity value, wherein the eccentricity value represents the degree of deviation from the center, and the target neural network model is obtained by training a plurality of sets of data, each set of data in the plurality of sets of data including historical posture data and a historical eccentricity value.

[0141] Specifically, the above-mentioned attitude data is input into a neural network prediction model to accurately predict the eccentricity value of the clothes, and the clothes are unwound according to the eccentricity value, and the speed of the motor is adjusted according to the eccentricity value, thereby improving the accuracy of the clothes eccentricity detection, reducing the number of clothes unwinding, and saving the dehydration time.

[0142] In step S203, in the case that the eccentricity value is greater than or equal to the preset eccentricity value, the washing machine is controlled to enter an unwinding process, wherein the unwinding process represents unwinding the clothes of the washing machine.

[0143] Specifically, the clothes are unwound according to the eccentricity value, and the speed of the motor is adjusted according to the eccentricity value, that is, when the eccentricity value is greater than or equal to the preset eccentricity value, the clothes are unwound.

[0144] Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the present application can be realized by a general computing device, which can be concentrated on a single computing device or distributed on a network composed of multiple computing devices, which can be realized by program codes executable by a computing device, so that they can be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described can be executed in different order, or they can be manufactured into individual integrated circuit modules, or multiple modules or steps can be manufactured into a single integrated circuit module. Thus, the present application is not limited to any specific hardware and software combination.

[0145] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt a computer program product implemented on one or more computer usable storage media containing computer usable program codes (including but not limited to disk storage, CD-ROM, optical storage, etc.).

[0146] The embodiments of the present application are described with reference to flowcharts and / or block diagrams according to the methods, devices (systems), and computer program products of the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks, can be realized by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the computer or other programmable data processing devices produce a device for implementing the functions described in the flowcharts and / or block diagrams. Figure 1 Each flow or multiple flows and / or blocks Figure 1an apparatus to perform each function

[0147] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a Figure 1 one or more processes and / or blocks Figure 1 an apparatus to perform each function

[0148] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions that are executed on the computer or other programmable apparatus provide steps for implementing processes Figure 1 one or more processes and / or blocks Figure 1 an apparatus to perform each function

[0149] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0150] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) about which the processor can execute instructions. The memory can also include non-volatile memory, such as read only memory (ROM), electrically programmable read only memory (EPROM), electrically erasable programmable read only memory (EEPROM), flash memory, or other memory technologies, about which the processor can execute instructions. The memory is an example of computer readable media.

[0151] Computer readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), electrically programmable read only memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital versatile disc (DVD), or other optical storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer readable media does not include transitory media, such as modulated data signals and carrier waves.

[0152] It is also to be noted that the terms "comprising", "comprises" or any other variation thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises a... " does not, without more constraints, exclude the presence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0153] From the above description, it can be seen that the above-mentioned embodiments of the present application achieve the following technical effects:

[0154] 1) In the laundry dehydration control method of the present application, the attitude data of the washing machine is obtained, wherein the attitude data at least includes acceleration and angular velocity; the attitude data is analyzed by a target neural network model to obtain an eccentricity value, wherein the eccentricity value represents the degree of deviation from the center, the target neural network model is obtained by training a plurality of sets of data, each set of data in the plurality of sets of data includes historical attitude data and historical eccentricity value; in the case where the eccentricity value is greater than or equal to a preset eccentricity value, the washing machine is controlled to enter an untwisting process, wherein the untwisting process represents the untwisting state of the laundry of the washing machine. Compared with the prior art, the eccentricity value of the washing machine is not accurate, resulting in a large number of laundry untwisting times, and the user experience is poor. In the present application, the eccentricity value is predicted by the attitude data of the washing machine, and the washing machine is controlled to untwist according to the predicted eccentricity value, avoiding the problem of too many untwisting times, and improving the user experience. Therefore, the problem of poor user experience caused by too many laundry untwisting times in the prior art can be solved, and the user experience is improved.

[0155] 2) In the laundry dehydration control device of the present application, the attitude data of the washing machine is obtained, wherein the attitude data at least includes acceleration and angular velocity; the attitude data is analyzed by a target neural network model to obtain an eccentricity value, wherein the eccentricity value represents the degree of deviation from the center, the target neural network model is obtained by training a plurality of sets of data, each set of data in the plurality of sets of data includes historical attitude data and historical eccentricity value; in the case where the eccentricity value is greater than or equal to a preset eccentricity value, the washing machine is controlled to enter an untwisting process, wherein the untwisting process represents the untwisting state of the laundry of the washing machine. Compared with the prior art, the eccentricity value of the washing machine is not accurate, resulting in a large number of laundry untwisting times, and the user experience is poor. In the present application, the eccentricity value is predicted by the attitude data of the washing machine, and the washing machine is controlled to untwist according to the predicted eccentricity value, avoiding the problem of too many untwisting times, and improving the user experience. Therefore, the problem of poor user experience caused by too many laundry untwisting times in the prior art can be solved, and the user experience is improved.

[0156] The above descriptions are only the preferred embodiments of the present application, and are not intended to limit the present application. The present application can have various modifications and changes for those skilled in the art. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for controlling dehydration of clothes, characterized in that: include: Acquiring posture data of the washing machine, wherein the posture data includes at least acceleration and angular velocity of the washing tub; Analyzing the posture data using a target neural network model to obtain an eccentricity value, wherein the eccentricity value indicates a degree of deviation from the center, the target neural network model is obtained by training multiple sets of data, each set of data in the multiple sets of data including: historical posture data and historical eccentricity values; When the eccentricity value is greater than or equal to a preset eccentricity value, controlling the washing machine to enter an untangling process, wherein the untangling process means untangling the clothes in the washing machine; Before analyzing the posture data using the target neural network model, the method further includes: Obtaining the historical posture data corresponding to the eccentricity detection modules of multiple preset weights, and obtaining the historical eccentricity value corresponding to the eccentricity detection module of each preset weight; An initial target neural network model is established, and the initial target neural network model is trained using the historical posture data and the historical eccentricity values ​​until the loss function of the initial target neural network model reaches an optimal value, thereby obtaining the target neural network model.

2. The method for controlling dehydration of clothes according to claim 1, characterized in that: Obtaining the historical posture data corresponding to the eccentricity detection modules of multiple preset weights includes: When the washing machine starts to spin, obtaining a current rotation speed; When the current rotation speed is greater than a rotation speed threshold, the historical posture data corresponding to the eccentricity detection modules of multiple preset weights are obtained, wherein the rotation speed threshold is the minimum rotation speed that makes the clothes stick to the barrel wall.

3. The method for controlling dehydration of clothes according to claim 1, characterized in that: Controlling the washing machine to enter the untangling process, comprising: Control the washing machine drum to rotate forward to a preset angle; The washing machine tub is controlled to rotate in the reverse direction by the preset angle.

4. The method for controlling dehydration of clothes according to claim 1, characterized in that: After controlling the washing machine to enter the untangling process, the method further includes one of the following: When the untangling time is greater than or equal to a preset time, controlling the washing machine to enter a dehydration process, wherein the untangling time represents the running time of the untangling process; A current eccentricity value is obtained, and when the current eccentricity value is less than the preset eccentricity value, the washing machine is controlled to enter the dehydration process.

5. The method for controlling dehydration of clothes according to claim 4, characterized in that: Controlling the washing machine to enter the dehydration process includes: An optimal rotation speed corresponding to the current eccentricity value is determined, and the washing machine is controlled to enter the dehydration process according to the optimal rotation speed.

6. The method for controlling dehydration of clothes according to claim 5, characterized in that: Determining the optimal speed corresponding to the current eccentricity value includes: Obtain a one-to-one mapping relationship between eccentricity value and optimal speed; The optimal speed corresponding to the current eccentricity value is determined according to a one-to-one mapping relationship between the eccentricity value and the optimal speed.

7. A control device for dehydrating clothes, characterized in that: include: a first acquiring unit, configured to acquire posture data of the washing machine, wherein the posture data includes at least acceleration and angular velocity of the washing tub; an analyzing unit, configured to analyze the posture data using a target neural network model to obtain an eccentricity value, wherein the eccentricity value indicates a degree of deviation from the center, the target neural network model being obtained by training multiple sets of data, each set of data including: historical posture data and historical eccentricity values; a first control unit, configured to control the washing machine to enter an untangling process when the eccentricity value is greater than or equal to a preset eccentricity value, wherein the untangling process refers to untangling the clothes in the washing machine; The device further comprises: a second acquiring unit, configured to acquire the historical posture data corresponding to the eccentricity detection modules of multiple preset weights and acquire the historical eccentricity values ​​corresponding to the eccentricity detection modules of each preset weight before analyzing the posture data through the target neural network model; A training unit is used to establish an initial target neural network model, and train the initial target neural network model through the historical posture data and the historical eccentricity values ​​until the loss function of the initial target neural network model is optimal, thereby obtaining the target neural network model.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method for controlling dehydration of clothes according to any one of claims 1 to 6.

9. An electronic device, characterized in that: include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for executing the laundry dehydration control method according to any one of claims 1 to 6.

Images