Control method, device and system for anti-collision barrel of washing machine

Abstract

The invention provides a control method, device and system for an anti-collision barrel of a washing machine. Under the condition that the current washing process of the washing machine is in the dewatering process, obtaining posture data, collected by a posture sensor, of a rotating drum of the washing machine at the current moment to obtain current posture data, gradually increasing the rotating speed of the rotating drum, and processing the current posture data by adopting a neural network model technology to obtain a prediction result; the washing machine is controlled to stop working or the rotating speed of the rotating drum is reduced at least according to the prediction result, the purpose of detecting whether the risk of drum collision exists in real time is achieved, compared with an existing scheme, the accuracy of predicting and detecting the eccentric value through drum collision prevention is improved, meanwhile, the eccentricity detection process time is shortened, and the efficiency is improved. Therefore, the problems that in the prior art, in the dewatering process, the accuracy of the anti-collision barrel predicted and detected eccentric value is low, and meanwhile the time of the eccentric detection process is long are solved.

Description

Technical Field

[0001] The present application relates to the technical field of anti-collision barrels of washing machines, and in particular to a control method, device and system for anti-collision barrels of washing machines. Background Art

[0002] At present, drum washing machines often have uneven distribution of laundry during the washing, drying and dehydration processes due to the different materials, sizes and water absorption levels of the clothes. The uneven distribution of clothes will not only reduce the washing effect of the clothes, but also cause the drum to be eccentric during rotation and hit the outer barrel, causing huge noise. In severe cases, the washing machine may move or jump, causing damage.

[0003] Patent application number CN110872760A discloses a method for detecting eccentricity of a washing machine. When the dehydration process starts, when the acceleration sensor detects that the eccentricity value of the outer drum at the current speed is greater than the limit eccentricity value, the eccentricity value at the current speed and the eccentricity value of the barrel are further judged. If it is greater than the eccentricity value of the barrel, a judgment is made as to whether to perform eccentricity correction; if it is less than the eccentricity value of the barrel, a judgment is made as to whether to continue dehydration. However, during the washing process, the acceleration sensor outputs acceleration, while the eccentricity value of the outer drum is a displacement. There is no necessary connection between the two, and the limit eccentricity value is difficult to determine, so the current eccentricity cannot be detected well.

[0004] That is, the existing solution has a low accuracy in predicting and detecting the eccentricity value of the anti-collision barrel during the dehydration process, and the eccentricity detection process takes a long time. Summary of the invention

[0005] The main purpose of the present application is to provide a control method, device and system for the anti-collision drum of a washing machine, so as to at least solve the problem that the accuracy of the eccentricity value predicted and detected by the anti-collision drum during the dehydration process is low and the eccentricity detection process time is long in the existing solution.

[0006] In order to achieve the above object, according to one aspect of the present application, a method for controlling an anti-collision drum of a washing machine is provided, the method comprising:

[0007] When the current washing process of the washing machine is in the dehydration process, the posture data of the rotating drum of the washing machine at the current moment collected by the posture sensor is obtained, the current posture data is obtained, and the rotation speed of the rotating drum is gradually increased, and the current posture data includes the acceleration and angular velocity of the rotating drum in each direction of the coordinate axis;

[0008] The current posture data is processed using a neural network model technology to obtain a prediction result, wherein the prediction result indicates that the rotating barrel will collide with the barrel or the rotating barrel will not collide with the barrel;

[0009] At least according to the prediction result, the washing machine is controlled to stop working, or the rotation speed of the rotating tub is reduced.

[0010] Optionally, at least the prediction result controls the washing machine to stop working, or reduces the rotation speed of the drum, including:

[0011] When the prediction result indicates that the rotating tub will not collide with the tub and the dehydration work is completed, controlling the washing machine to stop working;

[0012] When the prediction result indicates that the rotating barrel is about to collide with the barrel, the rotation speed of the rotating barrel is reduced by a preset step length;

[0013] When the rotation speed of the rotating tub is greater than or equal to a preset maximum rotation speed, the washing machine is controlled to stop working.

[0014] Optionally, at least the prediction result controls the washing machine to stop working, including:

[0015] When the prediction result indicates that the rotating barrel is about to collide with the barrel, the rotation speed of the rotating barrel is reduced by a preset step size, and the current prediction count result is updated to n+1, where n≥0 and n is a positive integer;

[0016] When the current predicted counting result is the preset maximum number of times, the washing machine is controlled to stop working.

[0017] Optionally, before using the neural network model technology to process the current posture data to obtain the prediction result, the method further includes:

[0018] Acquire historical posture data of the rotating barrel when eccentric blocks of different weights are set, wherein the historical posture data represents the acceleration and angular velocity of the rotating barrel in each direction of the coordinate axis collected at a preset collection frequency within a preset time period;

[0019] All of the historical posture data are used to train the neural network model to obtain the final neural network model.

[0020] Optionally, all of the historical posture data are used to train the neural network model to obtain a final neural network model, including:

[0021] according to

[0022] Determine the accuracy of the neural network model, where MSE is the accuracy of the neural network model, N is the number of samples, C is the number of categories, and yi j is the true label of the i-th sample of the j-th category, is the predicted probability of the i-th sample of the j-th category;

[0023] When the accuracy of the neural network model is greater than or equal to the accuracy threshold, the current neural network model is determined to be the final neural network model.

[0024] Optionally, the current posture data is processed using a neural network model technology to obtain a prediction result, including:

[0025] Performing Fourier transform on the current posture data to obtain a Fourier transform value;

[0026] The Fourier transform quantity is processed by using a neural network model technology to obtain the prediction result.

[0027] Optionally, in the process of using all the historical posture data to train the neural network model to obtain the final neural network model, the method further includes:

[0028] When the barrel rotation displacement corresponding to the Fourier transform amount is greater than the displacement threshold, determining that the current posture data corresponding to the Fourier transform amount is barrel collision data;

[0029] When the barrel rotation displacement corresponding to the Fourier transform amount is less than or equal to the displacement threshold, it is determined that the current posture data corresponding to the Fourier transform amount is non-barrel collision data.

[0030] Optionally, the input layer of the neural network model in the neural network model technology includes 6 neurons, corresponding to the Fourier transform quantities of 3 linear accelerations and angular acceleration in the current posture data respectively. The neural network model also includes 2 hidden layers, namely the first hidden layer and the second hidden layer. The first hidden layer includes 64 neurons, and the second hidden layer includes 32 neurons. The output layer of the neural network model is 1 neuron, which is used to output the prediction result.

[0031] According to another aspect of the present application, a control device for a washing machine anti-collision drum is provided, the device comprising:

[0032] a first acquisition unit, configured to acquire, when the current washing process of the washing machine is in the dehydration process, the posture data of the rotary drum of the washing machine collected by the posture sensor at the current moment, obtain the current posture data, and gradually increase the rotation speed of the rotary drum, wherein the current posture data includes the acceleration and angular velocity of the rotary drum in each direction of the coordinate axis;

[0033] A first processing unit is used to process the current posture data using a neural network model technology to obtain a prediction result, wherein the prediction result indicates that the rotating barrel will collide with the barrel or that the rotating barrel will not collide with the barrel;

[0034] The second processing unit is used to control the washing machine to stop working or reduce the rotation speed of the rotating tub at least according to the prediction result.

[0035] According to another aspect of the present application, a washing machine anti-collision barrel system is provided, the system comprising: 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 methods for executing any one of the described methods.

[0036] By applying the technical solution of the present application, when the current washing process of the washing machine is in the dehydration process, the posture data of the rotating drum of the washing machine collected by the posture sensor at the current moment is obtained, the current posture data is obtained, and the rotation speed of the rotating drum is gradually increased. The current posture data is processed by using a neural network model technology to obtain a prediction result. At least according to the prediction result, the washing machine is controlled to stop working, or the rotation speed of the rotating drum is reduced, thereby achieving the purpose of real-time detection of whether there is a risk of collision with the drum. Compared with the existing scheme, the accuracy of the eccentricity value of the anti-collision drum prediction detection is improved, and the eccentricity detection process time is reduced, thereby solving the problem that the accuracy of the eccentricity value of the anti-collision drum prediction detection during the dehydration process is low and the eccentricity detection process time is long in the existing scheme. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The drawings constituting part of the present application are used to provide a further understanding of the present application. The exemplary embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0038] Figure 1 A schematic flow chart of a method for controlling an anti-collision drum of a washing machine provided in accordance with an embodiment of the present application is shown;

[0039] Figure 2 A front view and a top view are shown of the installation position of a posture sensor provided in an embodiment of the present application in a drum washing machine;

[0040] Figure 3 The data collection and training process of the posture sensor provided in the embodiment of the present application is shown;

[0041] Figure 4 A schematic flow chart of another method for controlling an anti-collision drum of a washing machine provided in accordance with an embodiment of the present application is shown;

[0042] Figure 5 A structural block diagram of a control device for an anti-collision drum of a washing machine provided according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0043] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0044] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0045] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0046] For the convenience of description, some nouns or terms involved in the embodiments of the present application are explained below:

[0047] Fourier Transform is a mathematical technique used to represent a function as the sum of a series of sine and cosine functions. Fourier Transform has a wide range of applications in signal processing, image processing, communications and other fields.

[0048] FFT (Fast Fourier Transform) is an algorithm for efficiently calculating Fourier transform. The FFT algorithm can significantly reduce the computational complexity, especially for sequences whose length is a power of 2, the computational efficiency of the FFT algorithm is very high. FFT is widely used in digital signal processing, image processing, spectrum analysis and other fields.

[0049] As introduced in the background technology, patent application number CN110872760A discloses a method for detecting eccentricity of a washing machine. When the dehydration program starts, when the acceleration sensor detects that the eccentricity value of the outer drum at the current speed is greater than the limit eccentricity value, the eccentricity value at the current speed and the eccentricity value of the collision barrel are further judged. If it is greater than the eccentricity value of the collision barrel, a judgment is made as to whether to perform eccentricity correction; if it is less than the eccentricity value of the collision barrel, a judgment is made as to whether to continue dehydration. However, during the washing process, the acceleration sensor outputs acceleration, while the eccentricity value of the outer drum is a displacement. There is no necessary connection between the two, and the limit eccentricity value is difficult to determine, and the current eccentricity cannot be well detected. In order to solve the problem that the existing solution has a low accuracy in predicting and detecting the eccentricity value of the anti-collision barrel during the dehydration process and a long eccentricity detection process, the embodiments of the present application provide a control method, device and system for the anti-collision barrel of a washing machine.

[0050] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0051] In this embodiment, a method for controlling an anti-collision drum of a washing machine is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0052] Figure 1 It is a flow chart of a method for controlling an anti-collision drum of a washing machine provided according to an embodiment of the present application.

[0053] like Figure 1 As shown, the method comprises the following steps:

[0054] Step S101, when the current washing process of the washing machine is in the dehydration process, the posture data of the rotating drum of the washing machine at the current moment collected by the posture sensor is obtained, the current posture data is obtained, and the rotation speed of the rotating drum is gradually increased, and the current posture data includes the acceleration and angular velocity of the rotating drum in each direction of the coordinate axis;

[0055] The rotation speed of the rotating barrel can be gradually increased by taking 50 revolutions as a step length to increase the rotation speed of the rotating barrel.

[0056] Specifically, the acceleration (ax, ay, az) and angular velocity (rx, ry, rz) output by the attitude sensor are first subjected to a fast Fourier transform to extract the frequency domain features of the current attitude data, and then the frequency domain features of the current attitude data are used as the input of the neural network model.

[0057] like Figure 2As shown, the installation position of the posture sensor in the drum washing machine is shown (i.e., it is shown through the front view and the top view). In order to better extract the posture of the washing machine during the washing process, the posture sensor is installed on the outer barrel and kept in the middle of the top of the inner barrel. The outer barrel will shake to varying degrees during the washing process. The intensity of the shaking is related to the rotation speed and the eccentricity value of the clothes. The posture sensor installed on the outer barrel can reflect the vibration of the rotating barrel during the washing process.

[0058] Step S102, using a neural network model technology to process the current posture data to obtain a prediction result, wherein the prediction result indicates that the rotating barrel will collide with the barrel, or the rotating barrel will not collide with the barrel;

[0059] Step S102, i.e. using a neural network model technology to process the above current posture data to obtain a prediction result, includes:

[0060] Performing Fourier transform on the above current posture data to obtain Fourier transform amount;

[0061] The above-mentioned Fourier transform quantity is processed by using neural network model technology to obtain the above-mentioned prediction result.

[0062] Specifically, according to Determine the Fourier transform quantity;

[0063] Among them, X[k] is the kth Fourier transform quantity in the collected signal sample, x [ n ] is the nth collected signal sample, N is the total length of the signal, i is the imaginary unit, k is the frequency index, and the range is 0 to N-1. Through Fourier transform, the time domain signal can be transformed into a frequency signal.

[0064] In one embodiment of the present application, before using the neural network model technology to process the current posture data to obtain the prediction result, the method further includes:

[0065] Acquire historical posture data of the rotating barrel when eccentric blocks of different weights are set, wherein the historical posture data represents the acceleration and angular velocity of the rotating barrel in each direction of the coordinate axis collected at a preset collection frequency within a preset time period;

[0066] All the above historical posture data are used to train the neural network model to obtain the final neural network model.

[0067] When determining whether to hit the barrel, the neural network model needs to be trained. Since the installation position of the attitude sensor varies, it is more sensitive to the current position and attitude. In order to obtain more consistent data, the attitude sensor is calibrated before training to eliminate the error of each installation.

[0068] like Figure 3 As shown in the figure, the data collection and training process of the attitude sensor is demonstrated. The barrel collision process mainly occurs during the dehydration period with heavy weight and high speed. In order to reduce the amount of data, only the barrel posture during the dehydration process is collected. In order to cope with the different speeds and eccentricity values ​​of the washing machine during the washing process, eccentric blocks of different weights (100g, 200g, 500g, 700g, 1000g, 1500g) are placed during the data collection process, and the dehydration speed is increased by a gradient of 50 revolutions. Five data samples are collected at each speed gradient, and the sampling rate is 1Khz, that is, 1000 data samples are collected per second, and it is judged whether a barrel collision will occur or has occurred at the current speed gradient.

[0069] Replace the eccentric blocks with different weights and conduct experimental training again to observe whether the loss function on the training set is reduced to a stable level, or reaches an acceptable small value and no longer decreases significantly. This indicates that the network has completed the training requirements for the training data. You can also input a part of the verification data into the training set to verify the training results. If the accuracy rate can reach 98%, it means that the network has been trained.

[0070] In one embodiment of the present application, all of the above historical posture data are used to train the neural network model to obtain a final neural network model, including:

[0071] according to

[0072] Determine the accuracy of the above neural network model, where MSE is the accuracy of the above neural network model, N is the number of samples, C is the number of categories, yij is the true label of the i-th sample of the j-th category, is the predicted probability of the i-th sample of the j-th category;

[0073] When the accuracy of the neural network model is greater than or equal to the accuracy threshold, the current neural network model is determined to be the final neural network model.

[0074] In one embodiment of the present application, in the process of using all the above historical posture data to train the neural network model to obtain the final neural network model, the method further includes:

[0075] When the barrel rotation displacement corresponding to the Fourier transform amount is greater than the displacement threshold, determining the current posture data corresponding to the Fourier transform amount as barrel collision data;

[0076] When the barrel rotation displacement corresponding to the Fourier transform amount is less than or equal to the displacement threshold, the current posture data corresponding to the Fourier transform amount is determined to be non-barrel collision data.

[0077] Specifically, the standard for barrel collision is to measure whether the left and right displacement d of the barrel during the dehydration process exceeds the maximum set displacement D. If d>D, these 5 data samples are marked as barrel collision data, otherwise they are marked as non-barrel collision data. If a barrel collision has occurred or the current speed has reached the maximum value, the data collection in the current cycle is terminated, otherwise the speed continues to increase to collect data until a barrel collision occurs or the speed reaches the set maximum speed.

[0078] In one embodiment of the present application, the input layer of the neural network model in the above-mentioned neural network model technology includes 6 neurons, which respectively correspond to the Fourier transform quantities of the three linear accelerations and angular acceleration in the above-mentioned current posture data. The above-mentioned neural network model also includes 2 hidden layers, namely the first hidden layer and the second hidden layer. The above-mentioned first hidden layer includes 64 neurons, and the above-mentioned second hidden layer includes 32 neurons. The output layer of the above-mentioned neural network model is 1 neuron, which is used to output the above-mentioned prediction results.

[0079] As shown in Table 1, the acceleration data in the X-axis direction at 300 revolutions under different eccentricity values ​​are transformed by FFT to obtain the frequency value and barrel collision situation. It can be seen that whether there is barrel collision is positively correlated with the frequency of vibration. Generally, the greater the vibration, the more likely it is to cause barrel collision. However, using a single frequency data to predict barrel collision is prone to deviation, and the data under a single working condition cannot cover all situations. All data collected under different eccentricity blocks and different rotation speeds are imported into the neural network model for prediction.

[0080] Table 1

[0081] Eccentric mass Maximum frequency Whether to hit the barrel 200g 11Hz no 500g 23Hz no 700g 59Hz no 1000g 179Hz yes 1500g 249Hz yes

[0082] After the neural network is trained, real-time barrel collision prediction is performed in the actual processing process. Generally, barrel collision occurs during the dehydration process. When entering the dehydration speed increase, the posture sensor is calibrated and the speed is increased. The sampling frequency is 1khz and the sampling period is 1s. During the acceleration process, the posture sensor data is sampled in real time and imported into the neural network for prediction. When the neural network predicts a barrel collision, it immediately decelerates and performs anti-collision barrel operations on the clothes. The number of anti-collision barrels n is recorded. When the number of anti-collision barrels reaches a certain number (n>N), it indicates that the clothes cannot be prevented from hitting the barrel by the anti-collision barrel operation, and the dehydration process is ended in advance and waits for the user to handle it. When the neural network does not predict a barrel collision or the anti-collision barrel operation is successful, the speed is increased until the dehydration is completed.

[0083] Step S103, at least based on the prediction result, controlling the washing machine to stop working or reducing the rotation speed of the rotating tub.

[0084] In the above steps, when the current washing process of the washing machine is in the dehydration process, the posture data of the rotating drum of the washing machine at the current moment collected by the posture sensor is obtained to obtain the current posture data, and the rotation speed of the above rotating drum is gradually increased. The neural network model technology is used to process the above current posture data to obtain a prediction result. At least according to the above prediction result, the above washing machine is controlled to stop working, or the rotation speed of the above rotating drum is reduced, thereby achieving the purpose of real-time detection of whether there is a risk of collision with the barrel. Compared with the existing scheme, the accuracy of the eccentricity value of the anti-collision barrel prediction detection is improved, and the eccentricity detection process time is reduced, thereby solving the problem that the accuracy of the eccentricity value of the anti-collision barrel prediction detection during the dehydration process is low and the eccentricity detection process time is long in the existing scheme.

[0085] In one embodiment of the present application, at least the prediction result controls the washing machine to stop working, or reduces the rotation speed of the drum, including:

[0086] If the prediction result indicates that the rotating tub will not collide with the tub and the dehydration work is completed, the washing machine is controlled to stop working;

[0087] When the prediction result indicates that the rotating barrel is about to collide with the rotating barrel, the rotating speed of the rotating barrel is reduced by a preset step length;

[0088] When the rotation speed of the rotating tub is greater than or equal to a preset maximum rotation speed, the washing machine is controlled to stop working.

[0089] The maximum speed is set during the washing process. It is stipulated that the maximum speed during the dehydration process of clothes cannot exceed the set speed. If the maximum speed is reached during the dehydration process, the dehydration work is completed. If not reached, the speed will continue to increase. The best effect is to reach the maximum set speed.

[0090] Specifically, when the prediction result indicates that the drum will not collide with the drum, and the dehydration work is completed, it is determined that there is no need to adjust the speed of the drum again, and the washing machine is directly controlled to stop working. When the speed of the drum is greater than or equal to the preset maximum speed, it is determined that the speed cannot be increased further, and the washing machine is controlled to stop working. When the prediction result indicates that the drum will collide with the drum, it is determined that the drum collision can be avoided by reducing the speed, and the speed of the drum is reduced by a preset step size. The value of the preset maximum speed depends on the model of the washing machine.

[0091] In one embodiment of the present application, at least the above prediction result controls the above washing machine to stop working, including:

[0092] When the prediction result indicates that the rotating barrel is about to collide with the barrel, the rotation speed of the rotating barrel is reduced by a preset step size, and the current prediction count result is updated to n+1, where n≥0 and n is a positive integer;

[0093] When the current predicted counting result is the preset maximum number of times, the washing machine is controlled to stop working.

[0094] Specifically, for example, the preset maximum number of times is set to 10, then when the current predicted count result is 10, the washing machine is controlled to stop working. When the predicted result indicates that the rotating drum is about to collide with the drum, the rotation speed of the rotating drum is reduced by 50 revolutions as a preset step to prevent the drum from collide with the drum.

[0095] In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation process of the control method of the anti-collision drum of the washing machine of the present application will be described in detail below in combination with specific embodiments.

[0096] This embodiment relates to a specific method for controlling the anti-collision drum of a washing machine. Figure 4 As shown, including:

[0097] Obtain historical posture data of the rotating barrel when eccentric blocks of different weights are set, the historical posture data representing the acceleration and angular velocity of the rotating barrel in each direction of the coordinate axis collected at a preset collection frequency within a preset time period; use all the historical posture data to train the neural network model to obtain the final neural network model;

[0098] When the current washing process of the washing machine is in the dehydration process, the posture data of the rotating drum of the washing machine collected by the posture sensor at the current moment is obtained, the current posture data is obtained, and the rotation speed of the rotating drum is gradually increased, and the current posture data includes the acceleration and angular velocity of the rotating drum in each direction of the coordinate axis;

[0099] Perform Fourier transform on the current posture data to obtain the Fourier transform quantity; use the neural network model technology to process the Fourier transform quantity to obtain the prediction result, which indicates that the rotating barrel will collide with the barrel or will not collide with the barrel;

[0100] When the prediction result indicates that the drum will not collide with the drum and the dehydration work is completed, the washing machine is controlled to stop working;

[0101] When the prediction result indicates that the rotating barrel is about to collide with the barrel, the rotating speed of the rotating barrel is reduced by a preset step size, and the current prediction count result is updated to n+1, n≥0, and n is a positive integer;

[0102] When the rotating speed of the drum is greater than or equal to the preset maximum rotating speed, the washing machine is controlled to stop working;

[0103] When the current predicted counting result is the preset maximum number of times, the washing machine is controlled to stop working.

[0104] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0105] The embodiment of the present application also provides a control device for the anti-collision barrel of a washing machine. It should be noted that the control device for the anti-collision barrel of the washing machine in the embodiment of the present application can be used to execute the control method for the anti-collision barrel of the washing machine provided in the embodiment of the present application. The device is used to implement the above-mentioned embodiments and preferred implementation modes, and those that have been explained will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0106] The following is an introduction to the control device of the anti-collision drum of the washing machine provided in an embodiment of the present application.

[0107] Figure 5 1 is a structural block diagram of a control device for a washing machine anti-collision drum according to an embodiment of the present application. Figure 5 As shown, the device comprises:

[0108] The first acquisition unit 51 is used to acquire the posture data of the rotating drum of the washing machine collected by the posture sensor at the current moment when the current washing process of the washing machine is in the dehydration process, obtain the current posture data, and gradually increase the rotation speed of the rotating drum, wherein the current posture data includes the acceleration and angular velocity of the rotating drum in each direction of the coordinate axis;

[0109] The first processing unit 52 is used to process the current posture data using a neural network model technology to obtain a prediction result, wherein the prediction result indicates that the rotating barrel will collide with the barrel or the rotating barrel will not collide with the barrel;

[0110] The second processing unit 53 is used to control the washing machine to stop working or reduce the rotation speed of the rotating tub at least according to the prediction result.

[0111] In the above-mentioned device, when the current washing process of the washing machine is in the dehydration process, the posture data of the rotating drum of the washing machine at the current moment collected by the posture sensor is obtained to obtain the current posture data, and the rotation speed of the above-mentioned rotating drum is gradually increased. The above-mentioned current posture data is processed by using the neural network model technology to obtain a prediction result. At least according to the above-mentioned prediction result, the above-mentioned washing machine is controlled to stop working, or the rotation speed of the above-mentioned rotating drum is reduced, thereby achieving the purpose of real-time detection of whether there is a risk of collision with the barrel. Compared with the existing scheme, the accuracy of the eccentricity value of the anti-collision barrel prediction detection is improved, and the eccentricity detection process time is reduced, thereby solving the problem that the accuracy of the eccentricity value of the anti-collision barrel prediction detection during the dehydration process of the existing scheme is low and the eccentricity detection process time is long.

[0112] In one embodiment of the present application, the second processing unit includes a first processing module, a second processing module and a third processing module.

[0113] The first processing module is used for controlling the washing machine to stop working when the prediction result indicates that the rotating tub will not collide with the tub and the dehydration work is completed;

[0114] The second processing module is used for reducing the rotation speed of the rotating barrel by a preset step length when the prediction result indicates that the rotating barrel is about to collide with the barrel;

[0115] The third processing module is used to control the washing machine to stop working when the rotation speed of the rotating tub is greater than or equal to a preset maximum rotation speed.

[0116] In one embodiment of the present application, the second processing unit includes a fourth processing module and a fifth processing module.

[0117] The fourth processing module is used for reducing the rotation speed of the rotating barrel by a preset step length when the prediction result indicates that the rotating barrel is about to collide with the barrel, and updating the current prediction count result to n+1, n≥0, and n is a positive integer;

[0118] The fifth processing module is used to control the washing machine to stop working when the current predicted counting result is a preset maximum number of times.

[0119] In one embodiment of the present application, the above-mentioned device further includes a second acquisition unit and a second processing unit.

[0120] The second acquisition unit is used to process the current posture data using the neural network model technology to obtain the historical posture data of the rotating barrel when the eccentric blocks of different weights are set before obtaining the prediction result, wherein the historical posture data represents the acceleration and angular velocity of the rotating barrel in each direction of the coordinate axis collected at a preset collection frequency within a preset time period;

[0121] The second processing unit is used to train the neural network model using all the above historical posture data to obtain the final neural network model.

[0122] In one embodiment of the present application, the second processing unit includes a first determining module and a second determining module.

[0123] The first determining module is used to

[0124] Determine the accuracy of the above neural network model, where MSE is the accuracy of the above neural network model, N is the number of samples, C is the number of categories, and yi j is the true label of the i-th sample of the j-th category, is the predicted probability of the i-th sample of the j-th category;

[0125] The second determination module is used to determine that the current neural network model is the final neural network model when the accuracy of the neural network model is greater than or equal to the accuracy threshold.

[0126] In one embodiment of the present application, the first processing unit includes a sixth processing module and a seventh processing module.

[0127] The sixth processing module is used to perform Fourier transform on the above current posture data to obtain Fourier transform value;

[0128] The seventh processing module is used to process the above-mentioned Fourier transform quantity using a neural network model technology to obtain the above-mentioned prediction result.

[0129] In one embodiment of the present application, the second processing unit includes a third determining module and a fourth determining module.

[0130] The third determination module is used to determine that the current posture data corresponding to the Fourier transform amount is the barrel collision data when the barrel rotation displacement corresponding to the Fourier transform amount is greater than the displacement threshold value in the process of training the neural network model using all the above-mentioned historical posture data to obtain the final neural network model;

[0131] The fourth determination module is used to determine that the current posture data corresponding to the Fourier transform amount is non-barrel collision data when the barrel rotation displacement corresponding to the Fourier transform amount is less than or equal to the displacement threshold.

[0132] In one embodiment of the present application, the input layer of the neural network model in the above-mentioned neural network model technology includes 6 neurons, which respectively correspond to the Fourier transform quantities of the three linear accelerations and angular acceleration in the above-mentioned current posture data. The above-mentioned neural network model also includes 2 hidden layers, namely the first hidden layer and the second hidden layer. The above-mentioned first hidden layer includes 64 neurons, and the above-mentioned second hidden layer includes 32 neurons. The output layer of the above-mentioned neural network model is 1 neuron, which is used to output the above-mentioned prediction results.

[0133] The control device for the anti-collision drum of the washing machine includes a processor and a memory. The first acquisition unit, the first processing unit, the second processing unit, etc. are all stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions. The modules are all located in the same processor; or, the modules are located in different processors in any combination.

[0134] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the kernel parameters can be adjusted to solve the problem that the accuracy of the eccentricity value predicted by the anti-collision barrel during the dehydration process is low and the eccentricity detection process takes a long time.

[0135] 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.

[0136] An embodiment of the present invention provides a computer-readable storage medium, which includes a stored program, wherein when the program is running, the device where the computer-readable storage medium is located is controlled to execute the control method of the anti-collision drum of the washing machine.

[0137] An embodiment of the present invention provides a processor, and the processor is used to run a program, wherein the control method of the anti-collision drum of the washing machine is executed when the program is run.

[0138] The embodiment of the present invention provides a device, which includes a processor, a memory, and a program stored in the memory and can be run on the processor. When the processor executes the program, at least the following steps are implemented: when the current washing process of the washing machine is in the dehydration process, the posture data of the rotary drum of the washing machine collected by the posture sensor at the current moment is obtained, the current posture data is obtained, and the rotation speed of the rotary drum is gradually increased, and the current posture data includes the acceleration and angular velocity of the rotary drum in each direction in the coordinate axis; the current posture data is processed by a neural network model technology to obtain a prediction result, and the prediction result indicates that the rotary drum will collide with the barrel, or the rotary drum will not collide with the barrel; at least according to the prediction result, the washing machine is controlled to stop working, or the rotation speed of the rotary drum is reduced. The device in this article can be a server, a PC, a PAD, a mobile phone, etc.

[0139] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that is initialized with at least the following method steps: when the current washing process of the washing machine is in the dehydration process, obtaining the posture data of the rotating drum of the washing machine collected by the posture sensor at the current moment, obtaining the current posture data, and gradually increasing the rotation speed of the above-mentioned rotating drum, the above-mentioned current posture data includes the acceleration and angular velocity of the above-mentioned rotating drum in various directions in the coordinate axis; using a neural network model technology to process the above-mentioned current posture data to obtain a prediction result, the above-mentioned prediction result indicates that the above-mentioned rotating drum will have a barrel collision situation, or the above-mentioned rotating barrel will not have a barrel collision situation; at least according to the above-mentioned prediction result, control the above-mentioned washing machine to stop working, or reduce the rotation speed of the above-mentioned rotating drum.

[0140] The present application also provides a washing machine anti-collision barrel system, the system includes: 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 include methods for executing any of the above methods. When the current washing process of the washing machine is in the dehydration process, the posture data of the rotary barrel of the washing machine collected by the posture sensor at the current moment is obtained, the current posture data is obtained, and the rotation speed of the rotary barrel is gradually increased, and the current posture data is processed by a neural network model technology to obtain a prediction result. At least according to the prediction result, the washing machine is controlled to stop working, or the rotation speed of the rotary barrel is reduced, so as to achieve the purpose of real-time detection of whether there is a risk of barrel collision. Compared with the existing scheme, the accuracy of the eccentricity value of the anti-collision barrel prediction detection is improved, and the eccentricity detection process time is reduced, thereby solving the problem that the accuracy of the eccentricity value of the anti-collision barrel prediction detection in the dehydration process is low and the eccentricity detection process time is long in the existing scheme.

[0141] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0142] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0143] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0144] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0145] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0146] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0147] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0148] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be 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 erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0149] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0150] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0151] 1) The control method of the anti-collision barrel of the washing machine of the present application, when the current washing process of the washing machine is in the dehydration process, obtains the posture data of the rotating barrel of the washing machine collected by the posture sensor at the current moment, obtains the current posture data, and gradually increases the rotation speed of the above-mentioned rotating barrel, and uses the neural network model technology to process the above-mentioned current posture data to obtain a prediction result, and at least according to the above-mentioned prediction result, controls the above-mentioned washing machine to stop working, or reduces the rotation speed of the above-mentioned rotating barrel, thereby achieving the purpose of real-time detection of whether there is a risk of collision with the barrel. Compared with the existing scheme, the accuracy of the eccentricity value of the prediction detection of the anti-collision barrel is improved, and the eccentricity detection process time is reduced, thereby solving the problem that the accuracy of the eccentricity value of the prediction detection of the anti-collision barrel in the dehydration process is low and the eccentricity detection process time is long in the existing scheme.

[0152] 2) The control device of the anti-collision drum of the washing machine of the present application obtains the posture data of the rotating drum of the washing machine collected by the posture sensor at the current moment, obtains the current posture data, and gradually increases the rotation speed of the above-mentioned rotating drum, and uses the neural network model technology to process the above-mentioned current posture data to obtain a prediction result. At least according to the above-mentioned prediction result, the above-mentioned washing machine is controlled to stop working, or the rotation speed of the above-mentioned rotating drum is reduced, thereby achieving the purpose of real-time detection of whether there is a risk of collision with the drum. Compared with the existing scheme, the accuracy of the eccentricity value of the prediction detection of the anti-collision drum is improved, and the eccentricity detection process time is reduced, thereby solving the problem that the accuracy of the eccentricity value of the prediction detection of the anti-collision drum in the dehydration process is low and the eccentricity detection process time is long in the existing scheme.

[0153] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, 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 an anti-collision drum of a washing machine, characterized in that: include: When the current washing process of the washing machine is in the dehydration process, the posture data of the rotating drum of the washing machine at the current moment collected by the posture sensor is obtained, the current posture data is obtained, and the rotation speed of the rotating drum is gradually increased, and the current posture data includes the acceleration and angular velocity of the rotating drum in each direction of the coordinate axis; The current posture data is processed using a neural network model technology to obtain a prediction result, wherein the prediction result indicates that the rotating barrel will collide with the barrel or the rotating barrel will not collide with the barrel; At least according to the prediction result, the washing machine is controlled to stop working, or the rotation speed of the rotating tub is reduced.

2. The method according to claim 1, characterized in that At least the prediction result controls the washing machine to stop working, or reduces the rotation speed of the drum, including: When the prediction result indicates that the rotating tub will not collide with the tub and the dehydration work is completed, controlling the washing machine to stop working; When the prediction result indicates that the rotating barrel is about to collide with the barrel, the rotation speed of the rotating barrel is reduced by a preset step length; When the rotation speed of the rotating tub is greater than or equal to a preset maximum rotation speed, the washing machine is controlled to stop working.

3. The method according to claim 1, characterized in that At least the prediction result controls the washing machine to stop working, including: When the prediction result indicates that the rotating barrel is about to collide with the barrel, the rotation speed of the rotating barrel is reduced by a preset step size, and the current prediction count result is updated to n+1, where n≥0 and n is a positive integer; When the current predicted counting result is the preset maximum number of times, the washing machine is controlled to stop working.

4. The method according to claim 1, characterized in that Before using the neural network model technology to process the current posture data to obtain a prediction result, the method further includes: Acquire historical posture data of the rotating barrel when eccentric blocks of different weights are set, wherein the historical posture data represents the acceleration and angular velocity of the rotating barrel in each direction of the coordinate axis collected at a preset collection frequency within a preset time period; All of the historical posture data are used to train the neural network model to obtain the final neural network model.

5. The method according to claim 4, characterized in that All the historical posture data are used to train the neural network model to obtain the final neural network model, including: according to Determine the accuracy of the neural network model, where MSE is the accuracy of the neural network model, N is the number of samples, C is the number of categories, and y ij is the true label of the i-th sample of the j-th category, is the predicted probability of the i-th sample of the j-th category; When the accuracy of the neural network model is greater than or equal to the accuracy threshold, the current neural network model is determined to be the final neural network model.

6. The method according to claim 4, characterized in that The current posture data is processed using a neural network model technology to obtain a prediction result, including: Performing Fourier transform on the current posture data to obtain a Fourier transform value; The Fourier transform quantity is processed by using a neural network model technology to obtain the prediction result.

7. The method according to claim 6, characterized in that In the process of using all the historical posture data to train the neural network model to obtain the final neural network model, the method further includes: When the barrel rotation displacement corresponding to the Fourier transform amount is greater than the displacement threshold, determining that the current posture data corresponding to the Fourier transform amount is barrel collision data; When the barrel rotation displacement corresponding to the Fourier transform amount is less than or equal to the displacement threshold, it is determined that the current posture data corresponding to the Fourier transform amount is non-barrel collision data.

8. The method according to any one of claims 1 to 7, characterized in that: The input layer of the neural network model in the neural network model technology includes 6 neurons, which correspond to the Fourier transform values ​​of the three linear accelerations and angular acceleration in the current posture data respectively. The neural network model also includes 2 hidden layers, namely the first hidden layer and the second hidden layer. The first hidden layer includes 64 neurons, and the second hidden layer includes 32 neurons. The output layer of the neural network model is 1 neuron, which is used to output the prediction result.

9. A control device for a washing machine anti-collision drum, characterized in that: include: a first acquisition unit, configured to acquire, when the current washing process of the washing machine is in the dehydration process, the posture data of the rotary drum of the washing machine collected by the posture sensor at the current moment, obtain the current posture data, and gradually increase the rotation speed of the rotary drum, wherein the current posture data includes the acceleration and angular velocity of the rotary drum in each direction of the coordinate axis; A first processing unit is used to process the current posture data using a neural network model technology to obtain a prediction result, wherein the prediction result indicates that the rotating barrel will collide with the barrel or that the rotating barrel will not collide with the barrel; The second processing unit is used to control the washing machine to stop working or reduce the rotation speed of the rotating tub at least according to the prediction result.

10. A washing machine anti-collision barrel system, 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 methods for executing any one of claims 1 to 8.

Images