Method and device for controlling operation of fabric treatment appliance

By collecting parameters of liquid water drainage characteristics during the drying process of clothes dryers and using machine learning models, the problem of non-adjustable drying time was solved, achieving precise control and improved user experience.

CN118996812APending Publication Date: 2024-11-22BSH ELECTRICAL APPLIANCES (JIANGSU) CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310559239.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-17
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

The drying time settings of existing dryers cannot be changed and cannot be adjusted according to the actual situation of the clothes, resulting in inaccurate measurements and affecting the user experience.

Method used

By collecting parameters of liquid water drainage characteristics during the drying process of fabric processors, such as mass flow rate, volumetric flow rate, and flow velocity, and using pressure sensors to measure water pressure information, combined with machine learning models to predict drying time, precise control can be achieved.

Benefits of technology

It improves the accuracy of drying time estimation, allows for flexible adjustment of the drying process, and enhances user experience and energy efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118996812A_ABST
    Figure CN118996812A_ABST
Patent Text Reader

Abstract

An embodiment of the present invention provides a method for controlling operation of a fabric treatment appliance, the method comprising the steps of: collecting drainage characteristic parameters of the fabric treatment appliance during a drying operation of the fabric treatment appliance, the drainage characteristic parameters corresponding to liquid water separated from fabric in the fabric treatment appliance by the drying operation; obtaining time information for enabling the fabric in the fabric treatment appliance to reach a preset drying degree according to the drainage characteristic parameters; the operation of the fabric treatment appliance is controlled on the basis of the determined timing information. The invention also provides a device for controlling the operation of a fabric treatment appliance, a fabric treatment appliance and a machine-readable storage medium. According to some embodiments of the invention, by analyzing the moisture separated from the fabric in the form of liquid water, the drying state of the fabric can be mastered without being influenced by the stacking form and humidity distribution of the fabric, and the estimation accuracy of the clothes drying time can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of household appliances, and in particular to a method for controlling the operation of a fabric processing appliance, a device for controlling the operation of a fabric processing appliance, a fabric processing appliance and a machine-readable storage medium. Background Art

[0002] With the improvement of science and technology, fabric processing appliances with drying function have become one of the indispensable products in modern families, which provides great convenience for people's daily life. At present, the drying time is generally set in advance before the dryer leaves the factory, and it cannot be changed. It has poor flexibility and cannot be adjusted according to the actual situation of the clothes. Usually, there is a large deviation between the preset drying time and the actual drying time required for the clothes, which reduces the user experience.

[0003] In order to solve the above problems, some dryers that can automatically adjust the drying time have appeared on the market. These machines use humidity sensors placed in the drum to monitor the changes in the moisture content of the clothes in real time, and then predict the drying time. This solution mainly relies on the contact between the measuring electrode of the humidity sensor and the fabric to measure the humidity. However, since the sensor cannot be placed directly on the fabric, the internal humidity of the stacked fabric is difficult to measure. In addition, if the fabric itself contains metal conductive materials (such as zippers) or if the amount of fabric is too small, the reading of the humidity sensor will be biased. Therefore, the sensor measurement results cannot correctly reflect the actual humidity level of the fabric, resulting in the calculated drying time being inaccurate.

[0004] In this context, it is desirable to provide an improved fabric processing appliance control solution so as to more accurately control the drying processing time of the fabric processing appliance. Summary of the invention

[0005] An object of embodiments of the present invention is to provide a method for controlling the operation of a fabric processing appliance, a device for controlling the operation of a fabric processing appliance, a fabric processing appliance and a machine-readable storage medium, so as to at least solve some of the problems in the prior art.

[0006] According to a first aspect of the present invention, there is provided a method for controlling the operation of a fabric processing appliance, wherein the fabric processing appliance is configured to perform a drying operation on fabric, the method comprising the following steps:

[0007] collecting a drainage characteristic parameter of the fabric treating appliance during a drying operation of the fabric treating appliance, the drainage characteristic parameter corresponding to liquid water separated from fabric in the fabric treating appliance by the drying operation;

[0008] Obtaining timing information for making the fabrics in the fabric processing device reach a predetermined drying degree from the drainage characteristic parameters; and

[0009] The operation of the fabric processing device is controlled based on the obtained timing information.

[0010] The present invention particularly includes the following technical concepts: It is currently recognized that due to the limitations of the sensor installation position and the contact detection principle, it is difficult to accurately reflect the actual humidity level of the fabric through the detected humidity information of the drum environment. In the present invention, by analyzing the moisture separated from the fabric in the form of liquid water, the drying state of the fabric can be grasped without being affected by the stacking form and humidity distribution of the fabric, which is conducive to improving the accuracy of the drying time estimation, and can accurately control the drying process according to the actual use situation, thereby improving the user experience.

[0011] Optionally, the drainage characteristic parameters include: the mass flow rate, volume flow rate, flow rate and / or time variation characteristics of the liquid water separated from the fabric in the fabric processing device in the drainage pipeline of the fabric processing device. By understanding these drainage characteristic parameters, not only can the drying degree of the fabric be more accurately grasped, but also the variation of the drying rate over time can be explored. This helps to more flexibly determine the drying treatment time and specific parameters of the drying program.

[0012] Optionally, the water pressure information at a certain position in the drainage pipeline of the fabric processing device is measured by means of a pressure sensor, and the drainage characteristic parameters of the fabric processing device are obtained based on the water pressure information. Thus, a low-cost pressure sensor can be used to replace an expensive flow meter to measure the drainage characteristic parameters, saving hardware costs, and ensuring measurement accuracy even when the amount of precipitated water is small or the flow rate is slow.

[0013] Optionally, the drainage characteristic parameters are collected in a vertically extending section of the drainage pipeline of the fabric treatment device, which helps to convert the separated liquid water into pressure or height for measurement, thereby ensuring measurement accuracy even when the amount of separated water is small or the drainage flow rate is slow.

[0014] Optionally, during the collection of drainage characteristic parameters, the drainage pump of the fabric treatment device is controlled to remain closed so that the liquid water separated from the fabric is accumulated in the drainage pipeline of the fabric treatment device; and / or, when the amount of liquid water separated from the fabric accumulated in the drainage pipeline of the fabric treatment device reaches a preset limit, the drainage pump is controlled to be turned on to pump the water in the drainage pipeline to the external environment. This helps to prevent the liquid water from being directly discharged, resulting in a lack of time to perform measurement on it. This accumulation process can also avoid insufficient measurement accuracy caused by too little water.

[0015] Optionally, the time for collecting the drainage characteristic parameters is controlled so that the drainage characteristic parameters are collected only at the stage where the drainage characteristic parameters show a downward trend over time; and / or only the part of the collected drainage characteristic parameters that show a downward trend over time is used for obtaining the timing information. The downward stage intuitively reflects the influence of the drying time on the dryness of the fabric, thereby facilitating the establishment of a corresponding relationship between the drainage characteristic parameters and the drying time.

[0016] Optionally, the timing information for making the fabric reach a predetermined drying degree is obtained by: estimating the initial fabric weight in a dry state according to the drainage characteristic parameter; and estimating the timing information for making the fabric reach a predetermined drying degree according to the initial fabric weight. Considering that fabrics of the same weight mostly follow the same humidity change trend, the control law of the drying process can be more accurately estimated by taking the initial fabric weight as an intermediate result.

[0017] Optionally, the timing information for making the fabric reach a predetermined drying degree is obtained by: inputting the collected drainage characteristic parameters into a trained machine learning model; obtaining the timing information for making the fabric reach a predetermined drying degree according to the output result of the machine learning model, wherein the output result is in the form of an estimated drying time required for the fabric to reach a preset humidity level, and / or the output result is in the form of an estimated drainage characteristic parameter corresponding to when the fabric reaches a preset humidity level. By introducing the directional analysis of the machine learning model, the drying information can be inferred more reliably.

[0018] Optionally, the machine learning model is trained in the following manner: collecting sample data during a drying operation performed by a fabric processing device in a historical time period, the sample data including drainage characteristic parameters corresponding to different initial fabric weights; labeling the sample data in terms of timing information for making the fabric reach a predetermined drying degree; and establishing and adjusting the input-output mapping relationship of the machine learning model based on the labeled sample data until the performance evaluation index of the machine learning model meets a preset condition and / or until a preset number of training steps is reached. In this way, a large amount of accumulated prior knowledge can be fully utilized to enable the model to self-learn the relationship between the fabric moisture level and the timing of the end of the drying program, thereby improving the training efficiency and optimizing the model generalization ability.

[0019] Optionally, a linear regression model is used as a machine learning model at least for the step of estimating the initial fabric weight according to the drainage characteristic parameters, wherein the linear regression model is established in the following manner: the drainage characteristic parameters are used as independent variables and the initial fabric weight is used as the dependent variable to establish the linear regression model, and the parameters of the linear regression model are solved by the least square method to minimize the fitting error of the linear regression model to the sample data. Through the linear regression model, a correlation can be quickly established between the fabric weight and the drainage characteristic parameters, so as to more accurately summarize the drainage characteristic rules that fabrics of different weights conform to.

[0020] Optionally, the method further includes the following steps: obtaining the user's positive feedback behavior and / or negative feedback behavior on the timing information obtained by means of the trained machine learning model; and retraining the machine learning model based on the positive feedback behavior and / or negative feedback behavior. Thus, on the basis of the basic model framework established based on experience or experimental data, the initial model can be further optimized according to the user's specific operating habits and drying degree preferences, thereby speeding up the convergence process of the training algorithm while ensuring that personalized user needs are met.

[0021] Optionally, controlling the operation of the fabric processing device based on the timing information includes: controlling the fabric processing device to automatically end the drying operation when the timing information is met; and / or controlling the fabric processing device to display the estimated drying time and / or remaining drying time required for the fabric to reach a predetermined drying degree. Thus, the drying process can be dynamically adjusted according to the change in fabric moisture during the drying operation, thereby improving energy efficiency, and also facilitating users to know the drying progress by displaying the time, thereby improving user satisfaction.

[0022] According to a second aspect of the present invention, there is provided a device for controlling the operation of a fabric processing appliance, the device being configured to be able to perform the method according to the first aspect of the present invention, the device comprising:

[0023] A collecting module configured to collect drainage characteristic parameters of the fabric treating appliance during the fabric treating appliance performing a drying operation, wherein the drainage characteristic parameters correspond to liquid water separated from fabrics in the fabric treating appliance through the drying operation;

[0024] an obtaining module configured to obtain timing information for making the fabrics in the fabric processing device reach a predetermined drying degree from the drainage characteristic parameters; and

[0025] An execution module is configured to control the operation of the fabric processing tool based on the obtained timing information.

[0026] According to a third aspect of the present invention, there is provided a fabric processing device, the fabric processing device comprising:

[0027] a drain line for directing liquid water separated from the fabric in the fabric treating appliance to the external environment; and

[0028] The device according to the second aspect of the present invention.

[0029] Optionally, the drainage pipeline includes at least a section extending in the vertical direction, wherein the collection module of the device is configured to collect drainage characteristic parameters in the section of the drainage pipeline extending in the vertical direction.

[0030] Optionally, the fabric processing tool further includes: a pressure sensor, which is arranged in the drainage pipeline of the fabric processing tool and is used to measure water pressure information at a certain position in the drainage pipeline; wherein the collection module of the device is configured to obtain the drainage characteristic parameters of the fabric processing tool based on the water pressure information.

[0031] Optionally, the fabric processing device further comprises: a drainage pump, which is used to pump water in the drainage pipe of the fabric processing device to the external environment when in an on state; wherein the device is further configured to: control the drainage pump to remain closed during the collection of drainage characteristic parameters so that liquid water separated from the fabric in the fabric processing device accumulates in the drainage pipe, and / or, when the amount of liquid water separated from the fabric accumulated in the drainage pipe reaches a preset limit, control the drainage pump to turn on so as to pump the water in the drainage pipe to the external environment.

[0032] According to a fourth aspect of the present invention, there is provided a machine-readable storage medium, on which a computer program is stored, wherein the computer program is used to execute the method according to the first aspect of the present invention when executed on a computer. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The present invention will be described in more detail below with reference to the accompanying drawings, so that the principles, features and advantages of the present invention can be better understood. The accompanying drawings include:

[0034] Figure 1 A schematic diagram showing a fabric processing device according to an exemplary embodiment of the present invention is shown;

[0035] Figure 2 shows a flow chart of a method for controlling the operation of a fabric processing appliance according to an exemplary embodiment of the present invention;

[0036] Figure 3 Shows Figure 2 A flow chart of one method step of the method shown;

[0037] Figure 4 A schematic diagram showing the principle of obtaining information on the timing of making the fabric reach a predetermined drying degree by means of a machine learning model;

[0038] Figure 5 Shows Figure 2 A flow chart of another method step of the method shown; and

[0039] Figure 6 The time curve diagram of drainage characteristic parameters corresponding to different initial fabric weights is shown. DETAILED DESCRIPTION

[0040] In order to make the technical problems, technical solutions and beneficial technical effects to be solved by the present invention more clearly understood, the present invention will be further described in detail below in conjunction with the accompanying drawings and multiple exemplary embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the scope of protection of the present invention.

[0041] Figure 1 A schematic diagram of a fabric treating appliance according to an exemplary embodiment of the present invention is shown.

[0042] Figure 1 The fabric treatment device 1 shown can be, for example, a clothes dryer with a simple drying function or a spin drying function, or can also be a washer-dryer. The fabric treatment device 1 includes a drum 2 for accommodating a load, a motor 4, a heat pump system 6, an air duct 5 for guiding circulating air, and a fan unit 3 for causing the circulating air to flow in a directional manner in the air duct 5. In addition, the fabric treatment device 1 also includes a drainage pipeline 9 for guiding liquid water separated from the fabric in the drum 2, a drainage pump 10, and a pressure sensor 11.

[0043] exist Figure 1 In the illustrated embodiment, the drum 2 and the fan unit 3 are coaxially driven by a motor 4. During the drying process of the fabric processing device 1, the drum 2 is driven by the motor 4 to perform a spin drying operation, and the fan unit 3 is driven by the motor 4 to provide flow power for the circulating air, so that the dry air in the air duct 5 can enter the drum 2, and the humid air exhausted from the drum 2 is sent into the air duct 5 again.

[0044] Figure 1 The heat pump system 6 shown, for example, includes an evaporator 7, a heat pump compressor 12, a condenser 8, and an expansion valve 13 connected in sequence. In the heat pump system 6, the refrigerant (cold medium) is compressed from a low-pressure / low-temperature gas state to a high-pressure / high-temperature gas state by the heat pump compressor 12. Under this high pressure, the refrigerant is condensed into a liquid in the condenser 8 when it is equal to or close to the boiling point of the refrigerant at this pressure to release heat to the air flow of the surrounding environment. Then, the refrigerant reaches the expansion valve 13 and expands to a low pressure level there, thereby reaching a two-phase state. Finally, the refrigerant evaporates in the evaporator 7 in a cycle, thereby absorbing heat from the air flow and reaching a gas state again.

[0045] During the drying operation, the warm and moist air enters the evaporator 7 under the guidance of the air duct 5, where it is cooled and separated into dry cold air. The dry cold air enters the condenser 8 and is heated into dry hot air. Then, it is blown into the drum 2 under the action of the fan unit 3 and absorbs moisture when passing through the wet fabric load, becoming warm and moist air, and finally entering the evaporator 7 again. Thus, the fabric is dried. In addition, the fabric processing device 1 further includes a water collector 91, which is, for example, arranged below the evaporator 7. Figure 1 As shown, the condensed water converted by condensation at the evaporator 7 enters the water collector 91 arranged below it in the form of water droplets and is collected there. The water collector 91 is, for example, a part of the drainage pipeline 9 for guiding the condensed water and extends in the horizontal direction. The water collector 91 is connected to one end of the drainage pump 10 through the section 92 extending in the vertical direction of the drainage pipeline 9. The drainage pump 10 can be, for example, a vane-type electrically driven pumping device. The other end of the drainage pump 10 is connected to the inlet side of the sewer, so that under the action of the drainage pump 10, the condensed water collected in the drainage pipeline 9 can be regularly discharged to the external environment.

[0046] A pressure sensor 11 is provided in the section 92 extending in the vertical direction of the drainage pipe 9, and the water pressure information at a certain position in the drainage pipe 9 can be measured by means of the pressure sensor 11. Here, the "certain position" may refer to, for example, the bottom of the section 92 extending in the vertical direction of the drainage pipe, but may also refer to a plurality of positions arranged at intervals along the vertical section 92. Optionally, it is also conceivable to provide other sensors (not explicitly shown) such as a velocity meter, a flow meter and a liquid level sensor in the drainage pipe 9 to regularly detect the flow velocity, flow rate and liquid level value of the liquid water separated from the fabric.

[0047] In order to control the operation of the textile processing device 1 , the textile processing device 1 further comprises a device 20 , which comprises a collecting module 21 , a determining module 22 and an executing module 23 , which are connected to each other by means of communication technology.

[0048] The collecting module 21 is used to collect drainage characteristic parameters of the fabric treatment device 1 during the drying operation of the fabric treatment device 1, and the drainage characteristic parameters correspond to the liquid water separated from the fabric in the fabric treatment device 1 through the drying operation. To this end, the collecting module 21 is connected to the pressure sensor 11, for example, to determine the flow information of the liquid water separated from the fabric in the drainage pipeline 9 according to the water pressure information. Optionally, the collecting module 21 can also be connected to a velocity meter or a flow meter arranged in the drainage pipeline 9, so as to directly determine the drainage characteristic parameters based on the flow velocity information or flow information of the detected liquid water. Optionally, the collecting module 11 can also be connected to the drainage pump 10 and the liquid level sensor arranged in the drainage pipeline 9, so that the drainage pump 10 can be regularly controlled to open in combination with the liquid level value to pump the water accumulated in the drainage pipeline 9 to the external environment, and the drainage pump 90 can be kept closed during the collection of the drainage characteristic parameters.

[0049] The obtaining module 22 receives the drainage characteristic parameter from the collecting module 21, and obtains the timing information for making the fabric in the fabric processing device 1 reach a predetermined drying degree from the drainage characteristic parameter. In one embodiment, a machine learning model is stored in the device 20, and the machine learning model can predict the timing information for making the fabric reach a predetermined drying degree based on the drainage characteristic parameter. In another embodiment, a lookup table of drainage characteristic parameters and their corresponding recommended shutdown times is stored in the device 20. When receiving the drainage characteristic parameter measured in real time from the collecting module 21, the obtaining module 22 can directly read the recommended shutdown time of the fabric processing device from the lookup table, and provide it to the execution module 23 as the timing information.

[0050] The execution module 23 is used to control the operation of the fabric processing device 1 based on the obtained timing information. For example, the execution module 23 is connected to the motor 4 so that it can output instructions on starting and stopping the motor 4 to the motor 4. Thus, when it has been determined based on the drainage characteristic parameters that the fabric in the drum 2 has reached a predetermined drying degree, the execution module 23 can stop the motor 4. In another embodiment, the execution module 23 can also be connected to a display of the fabric processing device 1 so that the display displays the estimated drying time and / or the remaining drying time of the fabric processing device 1.

[0051] It should be noted that although the reference Figure 1 Only one pressure sensor 11 is shown at the bottom of the vertical section 92 of the drain pipe 9, but it is also conceivable that one or more pressure sensors are arranged at other positions in the drain pipe 9, and the type, number and installation position of the pressure sensor are not intended to be limited here.

[0052] It should also be noted that although Figure 1The drying process of the fabric processing device is introduced by taking the heat pump drying principle as an example, but the fabric processing device of the present invention can also complete the drying operation with the help of the condensation drying principle or other possible heat exchange methods. The implementation of the operation control scheme involved in the context is not limited to a specific type of drying principle.

[0053] Figure 2 A flow chart of a method for controlling the operation of a fabric processing device according to an exemplary embodiment of the present invention is shown. The method exemplarily comprises steps S1-S3 and can be used, for example, in a Figure 1 The device 20 is shown as being implemented in the context of.

[0054] In step S1 , drainage characteristic parameters of the fabric treating appliance are collected during a drying operation of the fabric treating appliance, wherein the drainage characteristic parameters correspond to liquid water separated from fabrics in the fabric treating appliance through the drying operation.

[0055] In this context, the drainage characteristic parameter "corresponds to" the liquid water separated from the fabric in the fabric treatment apparatus by the drying operation is understood as follows: "drainage characteristic" does not generally refer to the discharge characteristics of the liquid guided by the drainage pipeline when the fabric treatment apparatus performs washing, rinsing or other fabric treatment operations, nor does it involve the flow characteristics of the coolant in the coolant circulation circuit of the fabric treatment apparatus, but only has a clear correspondence with the discharge of liquid water separated from the fabric during the drying stage. To a certain extent, this drainage characteristic parameter can reflect the amount of wet load carried by the fabric to be dried and its change over time.

[0056] Here, the drainage characteristic parameters may exist in various forms, for example, and may include, for example, mass flow, volume flow, flow rate and / or time variation characteristics of the liquid water separated from the fabric in the drainage pipeline of the fabric treatment device.

[0057] In one embodiment, the flow characteristics of the liquid water separated from the fabric can be directly measured using sensors such as flow meters and flow rate meters arranged in the drainage pipeline, and used as drainage characteristic parameters.

[0058] In another embodiment, considering that the drying process of the fabric is a relatively slow process, the moisture precipitated from the fabric generally drips into the water collector in the form of water droplets. Therefore, even if the water collector is designed to have a certain slope to promote the flow of liquid, the liquid collected there usually flows only at a very slow rate. Only very expensive low-flow flow meters or flow meters can achieve the accuracy of this measurement rate. Therefore, it is particularly advantageous to wait until the liquid water enters the vertically extending section of the drainage pipeline before measuring the drainage characteristic parameters. In this way, the flow characteristics of the liquid water are converted into pressure characteristics, and then the water pressure information at a certain position in the drainage pipeline can be measured with the help of a low-cost pressure sensor, and then the drainage characteristic parameters are obtained based on the water pressure information.

[0059] In step S2, the timing information for making the fabrics in the fabric processing device reach a predetermined drying degree is obtained from the drainage characteristic parameters.

[0060] Here, the "predetermined drying degree" can be characterized by the moisture content or humidity level of the fabric. In addition, the "predetermined drying degree" can also be indirectly characterized by the drainage characteristic parameter. For example, for a fabric with an initial fabric weight of 1 kg in a dry state, the predetermined drying degree is the drying degree corresponding to when the drainage flow rate of the fabric is reduced to 10 g / min.

[0061] In one embodiment, the "predetermined drying degree" can be pre-calibrated and set to be fixed. For example, the drying degree corresponding to the zero moisture point of the fabric can be defined as the predetermined drying degree. In the preliminary experiment or calibration process, the initial fabric weight in the dry state of the fabric can be measured, and then the fabric in the drum is taken out regularly during the drying operation to weigh it and detect its drying state. When it is found that the weight obtained by weighing is consistent with the initial fabric weight of the fabric in the dry state, it is considered that the zero moisture point of the fabric is reached, or the predetermined drying degree is reached.

[0062] In another embodiment, the "predetermined drying degree" can also be personalized according to user preferences. For example, the user can be allowed to specify the desired drying degree through the parameter setting process, which can be presented to the user in the form of a moisture content percentage or a graded level (e.g., completely dry, basically dry, basically wet) for the user to select.

[0063] Here, the "timing information" may include, for example, the time required for the fabric treatment appliance to reach a predetermined drying degree. In addition, the "timing information" may not represent a period of time, but a certain moment or a condition corresponding to the moment. When the moment is reached or the condition corresponding to the moment is satisfied, it means that the drying process should be terminated.

[0064] In one embodiment, the functional relationship between the drainage characteristic parameters of the fabric and the expected drying time can be summarized through a large amount of experimental data or based on experience. Through repeated parameter fitting and manual parameter adjustment processes, a physical or mathematical model for describing this functional relationship can be obtained. Then, for the drainage characteristic parameters collected in actual operation, the corresponding expected drying time can be calculated using the established physical or mathematical model.

[0065] In another embodiment, the drainage characteristic parameters of the fabric obtained by the experiment may be bound to the expected drying time and stored in a lookup table. Then, the corresponding expected drying time may be read from the lookup table according to the drainage characteristic parameters detected during the actual drying process.

[0066] In another embodiment, the machine learning model can also be used to determine the timing information for the fabric to reach a predetermined drying degree from the collected drainage characteristic parameters. Figure 4 and Figure 5 Further elaboration.

[0067] In step S3, the operation of the fabric processing device is controlled based on the obtained timing information.

[0068] In one embodiment, the fabric processing device can be controlled to automatically end the drying operation when the timing information is met. For example, the drainage flow of the fabric processing device is continuously monitored, and when the drainage flow drops below a preset flow threshold, a shutdown instruction is sent to the fabric processing device to stop the operation. Optionally, a "drying completed" message can also be sent to the user's mobile terminal when the timing information is met to remind the user to take out the fabric in time.

[0069] In another embodiment, the fabric processing device can also be controlled to display the estimated drying time and / or remaining drying time required for the fabric to reach a predetermined drying degree. For example, the estimated drying time is read from a lookup table according to the detected drainage flow rate, and the read estimated drying time is transmitted to the display. For another example, when the total estimated drying time is obtained, the remaining drying time can also be calculated in combination with the currently performed drying process, and the remaining drying time can be displayed to the user in real time.

[0070] Figure 3 Shows Figure 2 A flow chart of the method steps of the method shown. Figure 3 In the embodiment shown, Figure 2 Step S1 in the process includes sub-steps S101-S108.

[0071] First, in step S101, it is determined whether the preheating stage of the fabric processing device is over. In the preheating stage, the heat pump system is turned on and the operating parameters of the components of the heat pump system are gradually stabilized. In order to make the collected drainage characteristic parameters more intuitively reflect the progress of the formal drying stage, the drainage characteristic parameters are not collected in the preheating stage, or the drainage characteristic parameters collected in the preheating stage are not used for the subsequent predetermined drying degree analysis.

[0072] If it is determined in step S101 that the warm-up phase has not yet ended, such determination is continued in step S101 .

[0073] If it is determined in step S101 that the preheating phase has ended and the formal drying phase has begun, then in the next step S102, water pressure information at a certain position in the drainage pipeline of the fabric processing device is obtained, and the drainage characteristic parameters of the fabric processing device are obtained based on the water pressure information.

[0074] In one embodiment, when the pressure sensor is arranged at the bottom of a section extending in the vertical direction of the drainage pipeline (hereinafter referred to as the vertical section for ease of description), the measured water pressure information can be converted into liquid water flow information according to the following formula:

[0075]

[0076]

[0077] Wherein, q is the drainage flow rate of liquid water separated from the fabric in the vertical section of the drainage pipe (here, for example, the volume flow rate), p is the water pressure at the bottom of the vertical section (here, for example, the difference between the pressure sensor reading and the atmospheric pressure at that point), h is the liquid level height in the vertical section, ρ is the density of the liquid water guided by the drainage pipe, r is the cross-sectional radius of the vertical section, t is the time elapsed from the moment the drainage pump is turned off each time, and g is the acceleration due to gravity.

[0078] In step S103, the amount of water accumulated in the vertical section of the drainage pipe is obtained. For example, the liquid level in the vertical section can be detected by a liquid level sensor, and the liquid level is used as the water amount information. For another example, the water pressure information obtained in the previous step can also be determined as the water amount information.

[0079] In step S104, it is checked whether the amount of water accumulated in the vertical section of the drainage pipe reaches a preset limit. Here, depending on the specific type of sensor that collects the water amount information, the preset limit can also have multiple representation forms. For example, it can be confirmed that the water amount reaches the preset limit when the liquid level in the vertical section of the drainage pipe reaches a preset height threshold and / or when the water pressure at the bottom of the vertical section reaches a preset pressure threshold.

[0080] If it is determined in step S104 that the water volume has not reached the preset limit, the drainage pump is kept off and the drainage characteristic parameter is continued to be determined through the reading of the pressure sensor in step S102.

[0081] If it is determined in step S104 that the water volume has reached the preset limit, the drain pump is controlled to be turned on in step S105 to pump the liquid water accumulated in the vertical section to the external environment. At the same time, in step S106, the pressure sensor is temporarily stopped from recording water pressure information during the period when the drain pump is turned on, and the timer is reset to zero, so as to prevent the detection result during the period when the drain pump is turned on from interfering with the determination of fabric dryness.

[0082] Next, in step S107, it is checked whether the water in the vertical section is completely drained. Assuming that the drainage rate of the drainage pump is constant, it can be checked in this step whether the opening time of the drainage pump reaches a preset time threshold. In addition, this judgment can also be performed based on the detection results of the liquid level sensor and the pressure sensor.

[0083] If it is found that the water has not been drained, the drain pump is kept on and the check is continued in step S107. Once it is found that the water has been drained, the drain pump is turned off in step S108, and the process returns to step S102 to resume the detection of water pressure information, and the timing is restarted from this moment. Thus, a complete water pressure recording cycle is completed. Here, the time period between each time the drain pump is turned off and the next time it is turned on can be defined as a complete water pressure recording cycle.

[0084] In this way, it is possible to ensure that there is sufficient water in the drainage pipeline during the collection of drainage characteristic parameters to improve measurement accuracy, while preventing energy consumption and noise problems caused by the continuous operation of the drainage pump.

[0085] Figure 4 A schematic diagram showing the principle of obtaining the timing information for the fabric to reach a predetermined drying degree with the help of a machine learning model.

[0086] refer to Figure 4 The machine learning model 400 takes the drainage characteristic parameter of the liquid water separated from the fabric as input, and takes the timing information of the fabric reaching the predetermined drying degree as output. Exemplarily, the drainage characteristic parameter can be represented by the drainage flow q in the drainage pipeline. The timing information can be represented by the estimated drying time t required for the fabric to reach the preset humidity level and / or the drainage flow q0 corresponding to the fabric reaching the preset humidity level.

[0087] In this embodiment, the machine learning model 400 uses two links 401 and 402 to obtain the timing information. In the first link 401, the initial fabric weight W in the dry state is estimated according to the drainage characteristic parameter q. In the second link 402, the timing information t and q0 for the fabric to reach a predetermined drying degree are estimated according to the initial fabric weight W. In this process, the initial fabric weight W functions as an implicit factor to affect the working process of the entire machine learning model 400. The implicit factor does not need to be measured and input by the outside world, and is not directly output as a result, but is used as an intermediate result to construct a mapping relationship between the model input and output.

[0088] Combined with the experimental process conducted previously (the experimental results are in Figure 6 For example, it is known or can be assumed that for fabrics with the same initial fabric weight W, the decreasing rate of the drainage flow rate q in the drying stage is linear, and fabrics with the same initial fabric weight W have the same decreasing rate of the drainage flow rate q. Based on this understanding, for example, a linear regression model can be used in the first link 401 to estimate the initial fabric weight W according to the drainage characteristic parameters.

[0089] First, it is necessary to collect sample data during the drying operation performed by the fabric processing device in the historical period, and these sample data include, for example, drainage characteristic parameters corresponding to different initial fabric weights W. Then, the linear regression model will learn the following linear equation through these sample data, and the linear equation takes the drainage characteristic parameter as the independent variable x and the initial fabric weight as the dependent variable y, so that the unknown initial fabric weight W can be estimated.

[0090] y==β0+β1·x (3)

[0091] Where y represents the initial fabric weight, x represents the drainage flow, β0 represents the intercept, and β1 represents the slope. The least squares method can be used to solve the parameters β0 and β1 to minimize the fitting error of the model to the sample data. Specifically, suppose there are n sample data (x1, y1), (x2, y2), ..., (x n ,y n ), where x i is the drainage flow, y i is the initial fabric weight. The goal of the least squares method is to find the sum of squared errors between the predicted value and the true value of each sample data:

[0092]

[0093] Thus, the total fitting error is obtained, and then the parameters β0 and β1 that minimize the total fitting error are solved. In order to perform this least squares estimation, it is necessary to calculate the partial derivatives of S(β0,β1) with respect to β0 and β1 respectively, setting them to 0 respectively, and obtain:

[0094]

[0095]

[0096] The solution is:

[0097]

[0098]

[0099] in, and Represent the average values ​​of x and y, respectively. In this way, by minimizing the fitting error, the optimal solution of the linear regression model in the above formula (3) is obtained, that is, the optimal parameters β0 and β1.

[0100] Therefore, in actual drying operations, the above linear regression model can be used to infer or estimate the unknown initial fabric weight W.

[0101] In the second step 402, it is also necessary to collect sample data during the drying operation performed by the fabric processing device in the historical time period, and the sample data includes, for example, the estimated drying time t corresponding to different initial fabric weights W or the drainage flow q0 when the preset humidity level is reached. Then, various regression models (such as linear regression, decision tree regression, random forest regression, support vector regression, neural network regression, etc.) can also be used to predict the timing information for making the fabric reach the predetermined drying degree based on the obtained initial fabric weight W. The specific selection of the regression model needs to consider multiple factors such as the characteristics of the sample data set, the distribution of the data, the complexity of the model, and the performance of the model.

[0102] In the second step 402, for example, the sample data can be divided into a training set, a validation set, and a test set to train and tune the constructed model. When evaluating the performance of the model, for example, the mean square error (MSE) can be used as an evaluation indicator to measure the error between the model prediction value and the true value, which is defined as:

[0103]

[0104] Where n represents the number of samples, yi represents the true value of the i-th sample, represents the predicted value of the ith sample. The smaller the MSE, the smaller the prediction error of the model and the better the model performance. Finally, the trained and tuned model in the second step 402 can be used to obtain the timing information of the fabric reaching the predetermined drying degree based on the initial fabric weight W.

[0105] Figure 5 Shows Figure 2 A flow chart of another method step of the method shown. Figure 5 In the embodiment shown, Figure 2 Step S2 in the above comprises sub-steps S201-S205. Figure 4 When the first and second links 401 and 402 in the embodiment are considered as a whole, the Figure 5 The training process introduced is to Figure 4 The machine learning model 400 shown is trained.

[0106] In step S201, sample data of a drying operation performed by a fabric processing device in a historical time period is obtained, and the sample data includes drainage characteristic parameters corresponding to different initial fabric weights.

[0107] Here, the collected sample data should have a certain amount and should especially cover different fabric moisture contents, different initial fabric weights, and different drying modes, so as to ensure that the collected sample data can simulate the diversity of actual drying scenarios, so that the machine learning model has good generalization ability. In addition, in the process of collecting samples, for example, fabrics with the same initial fabric weight can be numbered or distinguished by using identifiers or identification codes to prevent similar individuals from recurring multiple times.

[0108] In step S202, the sample data is annotated in terms of the timing information for making the fabric reach a predetermined drying degree. Here, for example, the timing information can be annotated manually. For example, during the experimental measurement process, the drying operation is periodically suspended and the fabric is taken out, and then the current drying level of the fabric is determined by observation or contact operation. When it is determined empirically that the fabric has reached the desired dry state or smoothness, the duration of the drying process so far is manually recorded and annotated as the above timing information.

[0109] Next, in step S203, a training set consisting of sample data with known timing information is used to establish and adjust the input-output mapping relationship of the machine learning model. Specifically, the drainage flow data within a period of time can be used as the input of the machine learning model, and the estimated drying time annotated for the drainage flow data can be used as the output of the machine learning model. Then, the parameters of the model are continuously adjusted using new sample data.

[0110] In step S204, the performance evaluation index of the machine learning model is checked to see if it meets the preset conditions and / or until the preset number of training steps is reached. Figure 4 As has been explained, different performance evaluation indicators can be selected depending on the type of model, including, for example, mean square error (MSE), mean absolute error (MAE), root mean square coefficient (RMSE), determination coefficient (R^2), etc.

[0111] If the preset number of training steps is not reached or if the performance evaluation index reflects that the model regression effect does not meet the requirements, it is necessary to continue training the model and continue to perform this check in step S204.

[0112] If it is found that the preset number of training steps has been reached or if the value of the corresponding performance evaluation index reflects that the prediction effect of the model meets the expected requirements, the drainage characteristic parameters detected in the actual drying process are input into the trained machine learning model in step S205, thereby obtaining the final result of the information on the timing when the fabric reaches the predetermined drying degree.

[0113] In addition, in an embodiment not shown, on the premise that the machine learning model is preliminarily trained based on steps S201-S204, the user's positive feedback and / or negative feedback on the model output results can be obtained during the use of the model. Then, the machine learning model is retrained based on the positive feedback and / or negative feedback.

[0114] Specifically, the mandatory correction event of the user to the timing information determined by the model can be recorded, or the user's behavior of actively ending the drying process or actively shutting down the fabric processing device before the timing information determined by the model is reached can be recorded, and these events can be recorded as negative feedback behaviors. In general, the user's active intervention behavior on the timing information determined by the machine learning model can be classified as negative feedback behavior, and the behavior of not intervening can be classified as positive feedback behavior. By understanding the number and degree of active intervention by the user, it can reflect his satisfaction with the current machine learning model, so that these feedback behaviors can be used as supplementary training data to update the internal parameters of the machine learning model.

[0115] Figure 6 The time curve diagram of drainage characteristic parameters corresponding to different initial fabric weights is shown.

[0116] exist Figure 6 The preheating phase and the drying phase of the fabric processing device are marked along the time axis. For example, the preheating phase is performed before the time t0, and the drying phase begins after the time t0.

[0117] In this embodiment, the drainage characteristic parameter is characterized in the form of the mass flow rate q of the liquid water separated from the fabric treatment device in the drainage pipeline, which is also referred to as "drainage flow rate" for convenience of description below. The drainage flow rate q is obtained by converting the water pressure information detected by the pressure sensor arranged in the drainage pipeline.

[0118] like Figure 6 As shown, in the drying stage, for fabrics with the same initial fabric weight w1, w2, w3, w4, w5, w6, the time variation trend of the drainage flow rate q is roughly the same, and all show a linear downward trend over time. This shows that as the drying process proceeds, the fabric becomes increasingly dry, so the amount and rate of liquid water discharged also gradually decreases. It can also be observed that the time variation trend of the detected drainage flow rate q varies with the initial fabric weight w1, w2, w3, w4, w5, w6. More specifically, the greater the initial fabric weight w1, w2, w3, w4, w5, w6 of the fabric in the dry state, the smoother the time variation of its drainage flow rate q in the drying stage, that is, the lower the rate of decline.

[0119] In addition, Figure 6 In the figure, the "zero humidity point" of the fabric is marked with a square symbol on each drainage flow time curve. At this zero humidity point, the fabric reaches the predetermined drying degree. Correspondingly, the time coordinate of the zero humidity point is the time when the fabric reaches the predetermined drying degree, which can also be understood as the time when the drying operation needs to be ended or the expected drying time. Here, by comparing the time scales and drainage flow q corresponding to the zero humidity points on different curves, it can be found that the time required for fabrics with the same initial fabric weight to reach the predetermined drying degree and the drainage flow corresponding to the predetermined drying degree are roughly the same. It can also be seen that the larger the initial fabric weight w1, w2, w3, w4, w5, w6, the smaller the corresponding drainage flow q when the fabric reaches the predetermined drying degree, which indirectly reflects that there is also a correlation between the initial fabric weight w1, w2, w3, w4, w5, w6 and the timing information of reaching the predetermined drying degree.

[0120] By analyzing the above observation data, a linear regression model can be used to establish a correlation between the drainage flow rate q of the liquid water separated from the fabric and the initial fabric weight w1, w2, w3, w4, w5, w6 of the fabric, and a correlation can also be established between the initial fabric weight w1, w2, w3, w4, w5, w6 of the fabric and the timing information when the fabric reaches a predetermined degree of drying. Furthermore, based on the drainage flow rate information collected in actual applications, the expected drying time can be inferred, and adaptive control of the drying time can be achieved.

[0121] exist Figure 6In the illustrated embodiment, in the time period when the drainage flow rate q gradually decreases over time, the linear relationship between the drainage characteristic parameter of the fabric and the initial fabric weight can be clearly obtained based on the observed data. In practical applications, in order to fully follow this proven law to ensure a more reliable prediction result, only the part of the collected drainage characteristic parameters that shows a downward trend over time can be used to obtain the timing information. Alternatively, the time for collecting the drainage characteristic parameters can be controlled so that the drainage characteristic parameters are collected only in the stage when the drainage characteristic parameters show a downward trend over time.

[0122] According to another embodiment of the present disclosure, a machine-readable storage medium is provided, such as a CD-ROM, which includes a computer program, which, when executed, causes a computer or a processor to perform a method according to each embodiment of the present disclosure. The machine-readable storage medium is, for example, an optical storage medium or a solid-state medium supplied together with other hardware or as part of other hardware.

[0123] If an embodiment includes an “and / or” relationship between a first feature and a second feature, it should be interpreted as follows: according to one embodiment, the embodiment has both the first feature and the second feature, and according to another embodiment, the embodiment has either only the first feature or only the second feature.

[0124] Although specific embodiments have been described above, these embodiments are not intended to limit the scope of the present disclosure, even when only a single embodiment is described with respect to specific features. The feature examples provided in the present disclosure are intended to be illustrative, not limiting, unless otherwise stated. In specific implementations, multiple features may be combined with each other as required and as technically feasible. Various substitutions, changes, and modifications may also be conceived without departing from the spirit and scope of the present invention.

Claims

1. A method for controlling the operation of a fabric treatment device (1), wherein the fabric treatment device (1) is configured to perform a drying operation on fabric, the method comprising the following steps: collecting drainage characteristic parameters of the fabric treatment appliance (1) during a drying operation of the fabric treatment appliance (1), the drainage characteristic parameters corresponding to liquid water separated from fabrics in the fabric treatment appliance (1) by the drying operation; Obtaining information on the timing for making the fabric in the fabric processing device (1) reach a predetermined drying degree from the drainage characteristic parameters; as well as The operation of the fabric processing device (1) is controlled based on the obtained timing information.

2. The method according to claim 1, wherein: The drainage characteristic parameters include: the mass flow, volume flow, flow rate and / or time variation characteristics of the liquid water separated from the fabric in the fabric processing device (1) in the drainage pipeline (9) of the fabric processing device (1).

3. The method according to claim 1 or 2, wherein: Water pressure information at a certain position in a drainage pipeline (9) of a fabric treatment device (1) is measured by means of a pressure sensor (11), and drainage characteristic parameters of the fabric treatment device (1) are obtained based on the water pressure information.

4. The method according to any one of claims 1 to 3, wherein: The drainage characteristic parameters are collected in a section (92) of the drainage pipeline (9) of the textile treatment device (1) extending in the vertical direction.

5. The method according to any one of claims 1 to 4, wherein: During the collection of drainage characteristic parameters, the drainage pump (10) of the fabric treatment device (1) is controlled to remain closed, so that the liquid water separated from the fabric is accumulated in the drainage pipeline (9) of the fabric treatment device (1); and / or When the amount of liquid water separated from the fabric accumulated in the drainage pipeline (9) of the fabric treatment device (1) reaches a preset limit, the drainage pump (10) is controlled to start so as to pump the water in the drainage pipeline (9) to the external environment.

6. The method according to any one of claims 1 to 5, wherein: Controlling the time of collecting the drainage characteristic parameters so that the drainage characteristic parameters are collected only at the stage when the drainage characteristic parameters show a decreasing trend over time; and / or Only the portion of the collected drainage characteristic parameters that shows a decreasing trend over time is used for obtaining the timing information.

7. The method according to any one of claims 1 to 6, wherein: The timing information for making the fabric reach the predetermined drying degree is obtained by: estimating the initial fabric weight in a dry state based on the drainage characteristic parameters; and Estimates the timing of the fabric reaching a predetermined dryness level based on the initial fabric weight.

8. The method according to any one of claims 1 to 7, wherein: The timing information for making the fabric reach the predetermined drying degree is obtained by: Inputting the collected drainage characteristic parameters into a trained machine learning model (400); The timing information for making the fabric reach a predetermined drying degree is obtained based on the output result of the machine learning model (400), wherein the output result is in the form of an estimated drying time required for the fabric to reach a preset humidity level, and / or the output result is in the form of an estimated drainage characteristic parameter corresponding to the fabric reaching a preset humidity level.

9. The method according to claim 8, wherein: The machine learning model (400) is trained in the following manner: Collecting sample data during a drying operation performed by means of a fabric processing device (1) within a historical period, wherein the sample data includes drainage characteristic parameters corresponding to different initial fabric weights; annotating the sample data with respect to timing information for achieving a predetermined degree of dryness of the fabric; as well as Based on the labeled sample data, an input-output mapping relationship of the machine learning model (400) is established and adjusted until the performance evaluation index of the machine learning model (400) meets the preset conditions and / or until a preset number of training steps is reached.

10. The method according to claim 8 or 9, wherein: A linear regression model is used as a machine learning model (400) at least for estimating the initial fabric weight according to the drainage characteristic parameters, wherein the linear regression model is established in the following manner: A linear regression model was established with drainage characteristic parameters as independent variables and initial fabric weight as dependent variable, and the parameters of the linear regression model were solved by least square method to minimize the fitting error of the linear regression model to the sample data.

11. The method according to any one of claims 8 to 10, wherein: The method further comprises the following steps: Obtaining positive feedback behavior and / or negative feedback behavior of the user in response to the timing information obtained by means of the trained machine learning model (400); and The machine learning model (400) is retrained based on the positive feedback behavior and / or negative feedback behavior.

12. The method according to any one of claims 1 to 11, wherein: Controlling the operation of the fabric processing device (1) based on the timing information includes: Controlling the fabric processing device (1) to automatically end the drying operation when the timing information is met; and / or The fabric processing device (1) is controlled to display the estimated drying time and / or the remaining drying time required for the fabric to reach a predetermined drying degree.

13. A device (20) for controlling the operation of a fabric processing appliance (1), the device (20) being configured to be able to perform the method according to any one of claims 1 to 12, the device (20) comprising: A collecting module (21) configured to collect drainage characteristic parameters of the fabric processing appliance (1) during a drying operation of the fabric processing appliance (1), wherein the drainage characteristic parameters correspond to liquid water separated from fabrics in the fabric processing appliance (1) through the drying operation; An obtaining module (22) configured to obtain timing information for making the fabrics in the fabric processing device (1) reach a predetermined drying degree from the drainage characteristic parameters; as well as An execution module (23) is configured to control the operation of the fabric processing device (1) based on the obtained timing information.

14. A fabric treatment device (1), comprising: a drainage line (9) for guiding liquid water separated from the fabric in the fabric treatment device (1) to the external environment; as well as The device (20) according to claim 13.

15. The fabric treating device (1) according to claim 14, wherein: The drainage pipeline (9) comprises at least a section (92) extending in the vertical direction, wherein the collection module (21) of the device (20) is configured to collect drainage characteristic parameters in the section (92) extending in the vertical direction of the drainage pipeline (9).

16. The fabric treating device (1) according to claim 14 or 15, wherein: The fabric processing device (1) further comprises: A pressure sensor (11) is arranged in a drainage pipeline (9) of the fabric processing device (1) and is used to measure water pressure information at a certain position in the drainage pipeline (9); Wherein, the collection module (21) of the device (20) is configured to obtain drainage characteristic parameters of the fabric processing tool (1) based on the water pressure information.

17. The fabric treating device (1) according to any one of claims 14 to 16, wherein: The fabric processing device (1) further comprises: A drainage pump (10) for pumping water in the drainage pipeline (9) of the fabric treatment device (1) to the external environment when in an open state; Wherein, the device (20) is further configured as: During the collection of the drainage characteristic parameters, the drainage pump (10) is controlled to remain closed so that the liquid water separated from the fabrics in the fabric processing device (1) is accumulated in the drainage pipeline (9), and / or When the amount of liquid water separated from the fabric and accumulated in the drainage pipeline (9) reaches a preset limit, the drainage pump (10) is controlled to start, so as to pump the water in the drainage pipeline (9) to the external environment.

18. A machine-readable storage medium having a computer program stored thereon, the computer program being configured to execute the method according to any one of claims 1 to 12 when executed on a computer.