Drying control method and apparatus

Abstract

The present disclosure relates to a drying control method and device, comprising: obtaining multi-stage characteristic data in a drying process, wherein the multi-stage characteristic data comprises first multi-dimensional characteristic data corresponding to a first drying characteristic interval and second multi-dimensional characteristic data corresponding to a second drying characteristic interval; inputting the first multi-dimensional characteristic data and the second multi-dimensional characteristic data into a preset cascade prediction model to obtain a predicted drying time; and sending the predicted drying time to a drying device, so that the drying device performs drying completion determination according to the predicted drying time and initial weight information of clothes to be dried, and stops the drying operation when the drying is completed. Based on the method provided in the present example, the drying time suitable for different clothes weights can be obtained, the accuracy of the drying completion determination can be improved, and the problems of insufficient drying or excessive drying can be reduced.

Description

Technical Field

[0001] This disclosure relates to the field of household appliances, and in particular to drying control methods and apparatus. Background Technology

[0002] Currently, most household dryers employ hot air control strategies based on fixed time or simple temperature control logic. They typically rely on preset timers or set temperature thresholds, determining that drying is complete once the outlet air temperature reaches a certain fixed value and is maintained for a certain period. Fixed time or temperature thresholds cannot adapt to different clothing load characteristics, resulting in low accuracy in determining the dryness of clothes and frequent problems of under-drying or over-drying. Summary of the Invention

[0003] To overcome the problems existing in related technologies, this disclosure provides a drying control method and apparatus.

[0004] According to a first aspect of the present disclosure, a drying control method is provided, comprising:

[0005] Acquire multi-stage feature data during the drying process, wherein the multi-stage feature data includes first multi-dimensional feature data corresponding to the first drying feature interval and second multi-dimensional feature data corresponding to the second drying feature interval;

[0006] The first and second multidimensional feature data are input into a preset cascaded prediction model to obtain the predicted drying time.

[0007] The predicted drying time is sent to the drying device so that the drying device can determine the completion of drying based on the predicted drying time and the initial weight information of the clothes to be dried, and stop the drying operation when drying is complete.

[0008] The beneficial effects are: by using multi-stage characteristic data and clothing weight information during the drying process, the appropriate drying time for different clothing weights can be obtained, which can improve the accuracy of drying completion determination and reduce the problems of under-drying or over-drying.

[0009] In one embodiment of this disclosure, acquiring multi-stage characteristic data during the drying process includes:

[0010] Real-time acquisition of operating data during the drying process, including the temperature of the air vents in the drying tunnel;

[0011] The process from the start of the drying process to the temperature at the air outlet of the drying tunnel reaching the first preset temperature is defined as the first drying characteristic range.

[0012] Multi-dimensional feature extraction is performed on the operating data within the first drying characteristic range to obtain the first multi-dimensional feature data;

[0013] The process from the start of the drying process to the temperature at the air outlet of the drying tunnel reaching the second preset temperature is defined as the second drying characteristic range, wherein the second preset temperature is greater than the first preset temperature.

[0014] Multidimensional feature extraction is performed on the operating data within the second drying characteristic range to obtain the second multidimensional feature data.

[0015] The beneficial effects are as follows: by introducing two time intervals corresponding to two different preset temperatures, multidimensional feature data of two different time intervals are obtained. Furthermore, since the first multidimensional feature data and the second multidimensional feature data reflect information of different drying stages respectively, the prediction results can be more consistent with the actual drying process and the accuracy of drying judgment can be improved.

[0016] In one embodiment of this disclosure, the preset cascaded prediction model includes a first-level prediction model and a second-level prediction model;

[0017] The first and second multidimensional feature data are input into a preset cascaded prediction model to obtain the predicted drying time, including:

[0018] The first multidimensional feature data is input into the first-level prediction model to obtain the first prediction duration;

[0019] The first prediction duration and the second multidimensional feature data are input into the second-level prediction model to obtain the second prediction duration;

[0020] The second prediction duration is determined as the prediction drying duration.

[0021] The beneficial effects are as follows: The cascaded prediction mechanism in this example analyzes the initial multidimensional feature data from the first stage of the prediction model to obtain a preliminary first prediction duration. Then, it uses the first multidimensional feature data and the first prediction duration to derive the final predicted drying duration, so that the output reflects the changing patterns of both the early and later stages of drying. Since the second-stage prediction model performs secondary corrections based on the prediction results from the first stage, the final predicted drying duration can more fully reflect the actual changes in the current clothing load and operating conditions.

[0022] In one embodiment of this disclosure, the drying process includes multiple drying stages, and the preset cascaded prediction model includes a first-level prediction model and multiple second-level prediction models, with each of the multiple second-level prediction models corresponding to one of the multiple drying stages.

[0023] The first and second multidimensional feature data are input into a preset cascaded prediction model to obtain the predicted drying time, including:

[0024] The first multidimensional feature data is input into the first-level prediction model to obtain the first prediction duration and the current drying stage;

[0025] The target second-level prediction model is determined based on the current drying stage. The target second-level prediction model is the second-level prediction model that corresponds to the current drying stage among multiple second-level prediction models.

[0026] The first prediction duration, the current drying stage, and the second multidimensional feature data are input into the target second-level prediction model to obtain the second prediction duration;

[0027] The second prediction duration is determined as the prediction drying duration.

[0028] The beneficial effects are as follows: In this example, the first-level prediction model first completes the stage identification, and then the second-level prediction model corresponding to the current drying stage performs targeted duration prediction, so that the prediction results match the stage changes of the drying process.

[0029] In one embodiment of this disclosure, it further includes:

[0030] Obtain the first cumulative drying time, wherein the first cumulative drying time starts to accumulate from the time the drying device is started;

[0031] When the first cumulative drying time reaches the first preset time, if the temperature at the air outlet of the drying tunnel still has not reached the first preset temperature, a shutdown command is sent to the drying device.

[0032] Obtain the second cumulative drying time, wherein the second cumulative drying time starts to accumulate when the temperature at the air outlet of the drying tunnel reaches the first preset temperature;

[0033] When the second cumulative drying time reaches the second preset time, if the temperature at the air outlet of the drying tunnel still has not reached the second preset temperature, then the first predicted time will be determined as the predicted drying time.

[0034] The beneficial effects are: this example can terminate the drying operation in time when the temperature rises abnormally, and determine the predicted drying time in the subsequent stage by using the first predicted time as a fallback, thereby improving the stability and adaptability of the drying completion determination.

[0035] In one embodiment of this disclosure, before inputting the first multidimensional feature data and the second multidimensional feature data into a preset cascaded prediction model, the method further includes:

[0036] Acquire historical drying data of the drying device, wherein the historical drying data includes first historical drying data corresponding to the first drying characteristic interval, second historical drying data corresponding to the second drying characteristic interval, and historical drying time;

[0037] The first historical drying data and historical drying time are input into the first initial level prediction model, and the first initial level prediction model is iteratively trained based on the preset loss function until the difference between the predicted time output by the first initial level prediction model and the historical drying time is less than or equal to the preset difference. Then the training of the first initial level prediction model ends, so as to obtain the first level prediction model.

[0038] The second historical drying data and historical drying time are input into the second initial level prediction model, and the second initial level prediction model is iteratively trained based on the loss function until the difference between the predicted time output by the second initial level prediction model and the historical drying time is less than or equal to the preset difference. Then the training of the second initial level prediction model ends to obtain the second level prediction model.

[0039] The first-level prediction model and the second-level prediction model are combined to form a pre-defined cascaded prediction model.

[0040] The beneficial effects are as follows: Since the two prediction models are trained on data from different stages, after the actual multidimensional feature data is input, the models can output the predicted drying time in a cascade manner, thereby improving the consistency and adaptability of the drying time prediction.

[0041] According to a second aspect of the present disclosure, a drying control method is provided, applied to a drying apparatus, comprising:

[0042] The initial weight information of the clothes to be dried and the multi-stage feature data during the drying process are obtained. The multi-stage feature data includes the first multi-dimensional feature data corresponding to the first drying feature interval and the second multi-dimensional feature data corresponding to the second drying feature interval.

[0043] Multi-stage feature data is sent to the cloud server so that the cloud server can input the first multi-dimensional feature data and the second multi-dimensional feature data into the preset cascaded prediction model to obtain the predicted drying time.

[0044] Receive the predicted drying time sent by the cloud server;

[0045] The system determines whether drying is complete based on the predicted drying time and the initial weight of the clothes, and stops the drying operation when drying is complete.

[0046] The beneficial effects are as follows: by acquiring the initial load and phased operation characteristics on the drying device side, and using a preset cascaded prediction model on the cloud server side to jointly process the first multidimensional feature data and the second multidimensional feature data, and then returning the obtained predicted drying time to the drying device to perform local drying completion determination, the drying end time is changed from fixed parameter control to the actual drying process based on different loading, different initial moisture content and environmental changes, thereby achieving precise control of the drying device.

[0047] In one embodiment of this disclosure, the drying completion determination is performed based on the predicted drying time and the initial weight information of the clothes, including:

[0048] Determine the target weight level based on the initial weight information of the clothing;

[0049] Based on the preset mapping relationship between weight levels and boundary values, the target boundary value corresponding to the target weight level is determined;

[0050] The target drying interval is determined based on the predicted drying time and the target boundary value;

[0051] The drying process is completed based on the target drying range.

[0052] The beneficial effects are: it can adapt the timing of drying to different garment weights, and it can make the predicted drying time work in synergy with the actual garment load, thereby improving the consistency and matching degree of drying completion judgment.

[0053] In one embodiment of this disclosure, the drying completion determination is performed based on the target drying interval, including:

[0054] Within the target interference resolution interval, at least one interference resolution start time is determined;

[0055] Based on the temporal order of all the stem initiation times, the first stem initiation time is taken as the target stem initiation time.

[0056] Starting from the initial time of the target drying process, the temperature of the drying tunnel air outlet is continuously monitored within a preset time window to obtain the temperature fluctuation value of the drying tunnel air outlet corresponding to the initial time of the target drying process.

[0057] If the temperature fluctuation value of the drying tunnel air outlet at the start time of the target drying is lower than the preset fluctuation value, the drying is determined to be complete.

[0058] If the temperature fluctuation value of the drying tunnel vent corresponding to the target drying start time is greater than or equal to the preset fluctuation value, then based on the time sequence between all drying start times, the next drying start time is determined as the target drying start time, and the process returns to the step of continuously detecting the temperature of the drying tunnel vent within the preset time window from the target drying start time to obtain the temperature fluctuation value of the drying tunnel vent corresponding to the target drying start time, until the temperature fluctuation value of the drying tunnel vent corresponding to the target drying start time is lower than the preset fluctuation value, then the drying is determined to be complete.

[0059] The beneficial effects are as follows: by sequentially selecting the start time of drying within the target drying interval and comparing the temperature fluctuations at multiple time points, the determination of drying completion is based on the stable changes in the temperature of the drying tunnel air outlet. This allows the timing of stopping drying to be closer to the actual drying state and reduces premature shutdown or over-drying caused by misjudgment at a single moment.

[0060] In one embodiment of this disclosure, it further includes:

[0061] If the temperature fluctuation value of the air outlet in the drying tunnel corresponding to the start time of all drying judgments is not lower than the preset fluctuation value, the drying device will be forcibly stopped from drying.

[0062] The beneficial effect is that this example enables the drying device to enter a forced shutdown state when the conditions that meet the dryness criteria are not met for a long time, thereby reducing the over-drying caused by continuous heating.

[0063] In one embodiment of this disclosure, it further includes:

[0064] The drying progress is determined based on the predicted drying time;

[0065] The drying progress is sent to the user terminal, and the user terminal is controlled to display the drying progress.

[0066] The benefits include: users can directly know the current drying completion status, thereby improving process awareness and ease of interaction.

[0067] According to a third aspect of the present disclosure, a drying control device is provided, comprising:

[0068] The first acquisition module is used to acquire multi-stage feature data during the drying process, wherein the multi-stage feature data includes first multi-dimensional feature data corresponding to the first drying feature interval and second multi-dimensional feature data corresponding to the second drying feature interval.

[0069] The input module is used to input the first multidimensional feature data and the second multidimensional feature data into the preset cascaded prediction model to obtain the predicted drying time;

[0070] The first sending module is used to send the predicted drying time to the drying device, so that the drying device can determine the completion of drying based on the predicted drying time and the initial weight information of the clothes to be dried, and stop the drying operation when the drying is completed.

[0071] According to a fourth aspect of the present disclosure, a drying control device is provided, applied to a drying apparatus, comprising:

[0072] The second acquisition module is used to acquire the initial weight information of the clothes to be dried and the multi-stage feature data during the drying process. The multi-stage feature data includes the first multi-dimensional feature data corresponding to the first drying feature interval and the second multi-dimensional feature data corresponding to the second drying feature interval.

[0073] The second sending module is used to send multi-stage feature data to the cloud server, so that the cloud server can input the first multi-dimensional feature data and the second multi-dimensional feature data into the preset cascaded prediction model to obtain the predicted drying time.

[0074] The receiving module is used to receive the predicted drying time sent by the cloud server;

[0075] The processing module is used to determine the completion of drying based on the predicted drying time and the initial weight of the clothes, and to stop the drying operation when drying is complete.

[0076] The technical solutions provided by the embodiments of this disclosure can include the following beneficial effects: The cloud server of this disclosure collects multi-dimensional feature information at different stages during the drying process, combines data from at least two drying feature intervals, estimates the required drying time for the clothes using a preset cascaded prediction model, and sends the prediction results to the drying equipment. The drying equipment then combines the initial weight of the clothes to determine whether drying is complete and controls the machine to stop. This disclosure, through multi-stage feature data during the drying process and the weight information of the clothes, can obtain drying times suitable for different clothing weights, improving the accuracy of drying completion determination and thus reducing the problems of under-drying or over-drying.

[0077] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0078] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0079] Figure 1 This is a schematic diagram of the scenario involved in this disclosure;

[0080] Figure 2 This is a schematic flowchart of a drying control method disclosed herein. Figure 1 ;

[0081] Figure 3 This is a schematic flowchart of a drying control method disclosed herein. Figure 2 ;

[0082] Figure 4 This is a schematic flowchart of a drying control method disclosed herein. Figure 3 ;

[0083] Figure 5 This is a schematic flowchart of a drying control method disclosed herein. Figure 4 ;

[0084] Figure 6 This is a schematic flowchart of a drying control method disclosed herein. Figure 5 ;

[0085] Figure 7 This is a schematic flowchart of a drying control method disclosed herein. Figure 6 ;

[0086] Figure 8 This is a schematic flowchart of a drying control method disclosed herein. Figure 7 ;

[0087] Figure 9 This is a schematic flowchart of a drying control method disclosed herein. Figure 8 ;

[0088] Figure 10 This is a schematic flowchart of a drying control method disclosed herein. Figure 9 ;

[0089] Figure 11 This is a schematic flowchart of a drying control method disclosed herein. Figure 10 ;

[0090] Figure 12 It is the overall process of drying control;

[0091] Figure 13 This is a schematic diagram of the structure of a drying control device disclosed herein. Figure 1 ;

[0092] Figure 14 This is a schematic diagram of the structure of a drying control device disclosed herein. Figure 2 . Detailed Implementation

[0093] Some embodiments of this disclosure will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. Various changes, modifications, and equivalents of the methods, apparatus, and / or systems described herein will become apparent upon understanding this disclosure. For example, the order of operations described herein is merely illustrative and is not limited to those orders set forth herein, but can be changed as will become apparent upon understanding this disclosure, except for operations that must be performed in a particular order. Furthermore, for clarity and brevity, descriptions of features known in the art may be omitted.

[0094] First, the application scenarios of this disclosure will be explained. This disclosure relates to the field of household appliances. For household dryers, a hot air control strategy based on fixed time or simple temperature control logic is generally adopted. It usually relies on a preset timer or a set temperature threshold. When the outlet air temperature reaches a certain fixed value and is maintained for a certain period of time, the drying is considered complete. Fixed time or temperature threshold cannot adapt to different clothing load characteristics, resulting in low accuracy in judging the dryness of clothes, leading to frequent problems of under-drying or over-drying.

[0095] To address the aforementioned problems, this disclosure provides a drying control method and apparatus. A schematic diagram of the scenario involved in this disclosure is shown below. Figure 1 As shown, the drying device disclosed herein can be a small drum-type drying device integrated into a drum-type partitioned washer-dryer. The user places wet clothes to be dried into the small drum of the drum-type partitioned washer-dryer, closes the drum door, and starts the small drum drying program. The drying device then collects multi-stage feature data and initial weight information of the clothes during the drying process, and uploads the multi-stage feature data to a cloud server. The cloud server extracts features from the multi-stage feature data to obtain first multi-dimensional feature data corresponding to the first drying feature interval and second multi-dimensional feature data corresponding to the second drying feature interval. The first and second multi-dimensional feature data are then input into a preset cascaded prediction model. A first prediction duration is determined using the first multi-dimensional feature data, and a second prediction duration is obtained using the second multi-dimensional feature data and the first prediction duration. The second prediction duration is then determined as the final predicted drying duration. The drying device determines the completion of drying based on the predicted drying duration and the initial weight information of the clothes, and stops the drying operation when drying is complete. This disclosure discloses a cloud server that collects multi-dimensional feature information at different stages during the drying process. Combining data from at least two drying feature intervals, it estimates the required drying time for the clothes using a pre-set cascaded prediction model. The prediction results are then sent to the drying equipment, which, based on the initial weight of the clothes, determines whether drying is complete and controls the machine to stop. By using multi-stage feature data and clothing weight information during the drying process, this disclosure can determine the appropriate drying time for different clothing weights, improving the accuracy of drying completion determination and reducing the problems of under-drying or over-drying.

[0096] The present disclosure will now be described with reference to specific embodiments. The embodiments described in the following examples do not represent all embodiments consistent with the present disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0097] Figure 2 This is a schematic flowchart of a drying control method disclosed herein. Figure 1 ,like Figure 2 As shown, it includes:

[0098] S201. Obtain multi-stage feature data during the drying process, wherein the multi-stage feature data includes first multi-dimensional feature data corresponding to the first drying feature interval and second multi-dimensional feature data corresponding to the second drying feature interval.

[0099] For example, in this example, the drying control method is applied to a cloud server. The cloud server acts as a computing and decision-making center, connected to the drying device via network communication, receiving the operating data of the drying device during the drying process and completing feature calculations. The drying process is a continuous operation in which the clothes to be dried are heated and dried by airflow inside the drum. Multi-stage feature data is used to characterize the operating state of different stages of the drying process, including at least the first multi-dimensional feature data corresponding to the first drying feature interval and the second multi-dimensional feature data corresponding to the second drying feature interval. The first and second multi-dimensional feature data are multi-dimensional feature sets extracted from the operating data within the corresponding intervals, used to describe the operating state and fluctuation state of different stages.

[0100] Example, Figure 3 This is a schematic flowchart of a drying control method disclosed herein. Figure 2 ,like Figure 3 As shown, S201 includes:

[0101] S301. Real-time acquisition of operating data during the drying process, including the temperature of the air vents in the drying tunnel.

[0102] For example, after the drying program is detected to have started, the operating data of the drying device is continuously acquired at a fixed sampling period, with the start of the heating element as the start time of the drying program. For example, the operating data includes: drying temperature, drying duct vent temperature, and drying chamber temperature, wherein the drying duct vent temperature includes the drying duct outlet temperature and the drying duct inlet temperature.

[0103] S302. The process from the start of the drying process to the temperature at the air outlet of the drying tunnel reaching the first preset temperature is defined as the first drying characteristic range.

[0104] For example, the first preset temperature is the temperature that the air outlet temperature of the drying tunnel must reach during the drying stage. The first preset temperature can be defined as T1, and the time from the start of drying to the time when the air outlet temperature of the drying tunnel reaches T1 is determined as the first drying characteristic range.

[0105] S303. Perform multi-dimensional feature extraction on the operating data within the first drying characteristic range to obtain the first multi-dimensional feature data.

[0106] For example, after extracting features from the operating data belonging to the first drying characteristic interval, the first multidimensional feature data within the first drying characteristic interval can be obtained. The first multidimensional feature data includes: the first temperature rise time, the change in temperature at the outlet of the first drying tunnel, the average temperature at the outlet of the first drying tunnel, the change in temperature at the inlet of the first drying tunnel, the average temperature at the inlet of the first drying tunnel, the rate of change in temperature at the outlet of the first drying tunnel, the rate of change in temperature at the inlet of the first drying tunnel, the total temperature fluctuation at the outlet of the first drying tunnel, the total temperature fluctuation at the inlet of the first drying tunnel, the change in the first water temperature, and the initial value at the inlet of the drying tunnel. Wherein, the first temperature rise time is the duration of the first drying characteristic interval, that is, the time difference from the start of the drying program to the temperature at the air inlet of the drying tunnel reaching T1; the change in the temperature at the air outlet of the first drying tunnel is the change in the temperature at the air outlet of the drying tunnel within the first drying characteristic interval; the average temperature at the air outlet of the first drying tunnel is the average temperature at the air outlet of the drying tunnel within the first drying characteristic interval; the change in the temperature at the air inlet of the first drying tunnel is the change in the temperature at the air inlet of the drying tunnel within the first drying characteristic interval; the average temperature at the air inlet of the first drying tunnel is the average temperature at the air inlet of the drying tunnel within the first drying characteristic interval; and the rate of change of the temperature at the air outlet of the first drying tunnel is the change in the temperature at the air inlet of the drying tunnel within the first drying characteristic interval. The ratio between the change in air outlet temperature and the first temperature rise time; the rate of change in the air inlet temperature of the first drying tunnel is the ratio between the change in the air inlet temperature of the drying tunnel within the first drying characteristic interval and the first temperature rise time; the sum of the temperature fluctuations at the air outlet of the first drying tunnel is the sum of the first-order differences of the air outlet temperature at the drying tunnel during continuous sampling within the first drying characteristic interval; the sum of the temperature fluctuations at the air inlet of the first drying tunnel is the sum of the first-order differences of the air inlet temperature at the drying tunnel during continuous sampling within the first drying characteristic interval; the first water temperature change is the change in the temperature of the drying chamber within the first drying characteristic interval; the initial value of the air inlet temperature of the drying tunnel is the initial temperature value of the air inlet of the drying tunnel after the drying program is started.

[0107] S304. The process from the start of the drying process to the temperature at the air outlet of the drying tunnel reaching the second preset temperature is defined as the second drying characteristic range, wherein the second preset temperature is greater than the first preset temperature.

[0108] For example, the second preset temperature can be determined through big data filtering, identifying the temperature reached when the total drying time under the corresponding standard conditions does not exceed 50% as the second preset temperature, which is the temperature achievable in the first half of the drying process. This second preset temperature can be defined as T2, and the period from the start of drying to the moment the air vent temperature reaches T2 is defined as the second drying characteristic interval. Since T2 < T1, the first drying characteristic interval is completely encompassed by the second drying characteristic interval. Both share the same starting point and are in the rising phase of the drying temperature increase, corresponding to different technical characterization dimensions: the first drying characteristic interval characterizes the dryness and wetness of the clothes and the system's operating characteristics during the middle of the temperature rise, while the second drying characteristic interval characterizes the system's temperature rise characteristics and the basic drying trend of the clothes throughout the entire temperature rise cycle.

[0109] S305. Perform multidimensional feature extraction on the operating data within the second drying characteristic interval to obtain the second multidimensional feature data.

[0110] For example, following the same processing logic as S303, after extracting features from the operating data belonging to the second drying characteristic interval, the second multi-dimensional feature data within the second drying characteristic interval can be obtained. The second multi-dimensional feature data includes: the second temperature rise time, the change in temperature at the outlet of the second drying tunnel, the average temperature at the outlet of the second drying tunnel, the change in temperature at the inlet of the second drying tunnel, the average temperature at the inlet of the second drying tunnel, the rate of change in temperature at the outlet of the second drying tunnel, the rate of change in temperature at the inlet of the second drying tunnel, the total temperature fluctuation at the outlet of the second drying tunnel, the total temperature fluctuation at the inlet of the second drying tunnel, the change in second water temperature, and the initial value at the inlet of the drying tunnel. Wherein, the second temperature rise time is the duration of the second drying characteristic interval, that is, the time difference from the start of the drying program to the air inlet temperature of the drying tunnel reaching T2; the second drying tunnel outlet temperature change is the change in the drying tunnel outlet temperature within the second drying characteristic interval; the second drying tunnel outlet temperature average is the average temperature of the drying tunnel outlet within the second drying characteristic interval; the second drying tunnel inlet temperature change is the change in the drying tunnel inlet temperature within the second drying characteristic interval; the second drying tunnel inlet temperature average is the average temperature of the drying tunnel inlet within the second drying characteristic interval; the second drying tunnel outlet temperature change rate is the rate of change of the second drying tunnel outlet temperature within the second drying characteristic interval. The ratio between the change in air outlet temperature and the second temperature rise time; the rate of change in the air inlet temperature of the second drying tunnel is the ratio between the change in the air inlet temperature of the drying tunnel and the second temperature rise time within the second drying characteristic interval; the sum of the temperature fluctuations at the air outlet of the second drying tunnel is the sum of the first-order differences of the air outlet temperature at the drying tunnel during continuous sampling within the second drying characteristic interval; the sum of the temperature fluctuations at the air inlet of the second drying tunnel is the sum of the first-order differences of the air inlet temperature at the drying tunnel during continuous sampling within the second drying characteristic interval; the change in the second water temperature is the change in the temperature of the drying chamber within the second drying characteristic interval; the initial value of the air inlet temperature of the drying tunnel is the initial temperature value of the air inlet of the drying tunnel after the drying program is started. Among them, the initial value of the air inlet of the drying tunnel is the environmental correction dimension of the preset cascade prediction model: For the small drum drying scenario, if the initial value of the air inlet of the drying tunnel is greater than the preset temperature threshold, it can be determined that the drying equipment has performed other drying tasks before this drying and the machine body is in a hot start state; Under hot conditions, the overall temperature rise rate of the drying tunnel is significantly increased, which will directly shorten the arrival time of the first and second drying characteristic intervals. If this feature is not introduced for hot correction, the drying time prediction accuracy of the preset cascade prediction model will decrease. Therefore, this feature is used to eliminate the interference of the initial hot state of the machine body on the prediction results.

[0111] Based on the method provided in this example, by introducing two time intervals corresponding to two different preset temperatures, multidimensional feature data of two different time intervals are obtained. Furthermore, since the first multidimensional feature data and the second multidimensional feature data reflect information of different drying stages respectively, the prediction results can be made to better fit the actual drying process and improve the accuracy of drying determination.

[0112] S202. Input the first multidimensional feature data and the second multidimensional feature data into the preset cascaded prediction model to obtain the predicted drying time.

[0113] For example, a pre-defined cascaded prediction model is used to predict drying time based on multi-stage feature data. This model is deployed on a cloud server and processes the data upon receiving the first and second multi-dimensional feature data. The predicted drying time is the total time required for the clothes to be dried from the start of drying to the completion of drying; this prediction is subsequently used as the basis for the drying device to determine the drying completion time.

[0114] Optionally, the preset cascaded prediction model includes a first-level prediction model and a second-level prediction model; Figure 4 This is a schematic flowchart of a drying control method disclosed herein. Figure 3 ,like Figure 4 As shown, S202 includes:

[0115] The first and second multidimensional feature data are input into a preset cascaded prediction model to obtain the predicted drying time, including:

[0116] S401. Input the first multidimensional feature data into the first-level prediction model to obtain the first prediction duration.

[0117] For example, the preset cascaded prediction model includes a first-level prediction model and a second-level prediction model, which can be extreme gradient boosting models. The first-level prediction model outputs a preliminary preset duration based on the aforementioned 11-dimensional first multi-dimensional feature data, and the preliminary prediction duration output by the first-level prediction model is defined as the first prediction duration.

[0118] S402. Input the first prediction duration and the second multidimensional feature data into the second-level prediction model to obtain the second prediction duration.

[0119] For example, the second-level prediction model analyzes and predicts the first prediction duration and the aforementioned 11-dimensional second multi-dimensional feature data, which can realize the re-determination and deviation correction of the first prediction duration and output the second prediction duration.

[0120] S403. The second prediction time is determined as the prediction drying time.

[0121] For example, the second predicted duration output by the second-level prediction model can be determined as the final predicted drying duration.

[0122] The cascaded prediction mechanism in this example analyzes the initial multidimensional feature data from the first stage of the prediction model to obtain a preliminary first prediction duration. Then, it uses the first multidimensional feature data and the first prediction duration to derive the final predicted drying time, ensuring that the output reflects the changing patterns of both the early and later stages of the drying process. Since the second-stage prediction model performs secondary corrections based on the results of the first stage, the final predicted drying time more closely matches the actual changes in the current clothing load and operating conditions.

[0123] Optionally, the drying process includes multiple drying stages, and the preset cascaded prediction model includes a first-level prediction model and multiple second-level prediction models, with each of the multiple second-level prediction models corresponding to one of the multiple drying stages. Figure 5 This is a schematic flowchart of a drying control method disclosed herein. Figure 4 ,like Figure 5 As shown, S202 includes:

[0124] S501. Input the first multidimensional feature data into the first-level prediction model to obtain the first prediction duration and the current drying stage.

[0125] For example, the preset cascaded prediction model can also include multiple second-level prediction models. Multiple drying stages can be preset during the drying process, and a corresponding second-level prediction model can be configured for each drying stage. Unlike S401, the first multidimensional feature data, in addition to obtaining the initial preset duration, can also predict the current drying stage. The drying stages include: preheating stage, main evaporation stage, and tail-drying stage.

[0126] S502. Determine the target second-level prediction model based on the current drying stage, wherein the target second-level prediction model is the second-level prediction model corresponding to the current drying stage among multiple second-level prediction models.

[0127] For example, based on the current drying stage predicted by S501, the second-level prediction model corresponding to the current drying stage is determined as the target second-level prediction model for subsequent formal use.

[0128] S503. Input the first prediction duration, the current drying stage, and the second multidimensional feature data into the target second-level prediction model to obtain the second prediction duration.

[0129] For example, the target second-level prediction model analyzes and predicts the first prediction duration, the current drying stage, and the aforementioned 11-dimensional second multi-dimensional feature data, which can realize the re-determination and deviation correction of the first prediction duration and output the second prediction duration.

[0130] S504. The second predicted duration is determined as the predicted drying duration.

[0131] For example, the second predicted duration output by the second-level prediction model can be determined as the final predicted drying duration. In this example, the first-level prediction model first completes the stage identification, and then the target second-level prediction model corresponding to the current drying stage performs targeted duration prediction, so that the prediction results match the stage changes of the drying process.

[0132] S203. The predicted drying time is sent to the drying device so that the drying device can determine the completion of drying based on the predicted drying time and the initial weight information of the clothes to be dried, and stop the drying operation when the drying is completed.

[0133] For example, after receiving the predicted drying time, the cloud server sends the predicted drying time to the drying device via the communication link corresponding to the drying device. After receiving the predicted drying time, the drying device determines whether the clothes to be dried have been dried by combining the initial weight information of the clothes to be dried, and stops the drying operation after determining that the clothes to be dried have been dried.

[0134] In this example, the cloud server collects multi-dimensional feature information at different stages during the drying process. Combining data from at least two drying feature intervals, it estimates the required drying time for the clothes using a pre-set cascaded prediction model. The prediction results are then sent to the drying equipment, which, based on the initial weight of the clothes, determines whether drying is complete and controls the machine to stop. This disclosure, by using multi-stage feature data and clothing weight information during the drying process, can obtain drying times suitable for different clothing weights, improving the accuracy of drying completion determination and reducing the problems of under-drying or over-drying.

[0135] Optional, Figure 6 This is a schematic flowchart of a drying control method disclosed herein. Figure 5 ,like Figure 6 As shown, it also includes:

[0136] S601. Obtain the first cumulative drying time, wherein the first cumulative drying time starts to accumulate from the start of the drying device.

[0137] For example, the moment the drying device starts is also the moment the heating element starts. Timing begins after the heating element starts, and the duration from the moment the heating element starts to the current moment is determined as the first cumulative drying time.

[0138] S602. When the first cumulative drying time reaches the first preset time, if the temperature of the air outlet of the drying tunnel still has not reached the first preset temperature, a shutdown command is sent to the drying device.

[0139] For example, the first preset time can be determined according to the actual situation. Under normal drying conditions, the temperature of the air outlet in the drying tunnel can reach the first preset temperature T1 within the first preset time. Therefore, if the temperature of the air outlet in the drying tunnel still does not reach T1 after the cumulative drying time reaches the first preset time, it can be determined that the drying condition is abnormal. At this time, the abnormal alarm and safety shutdown logic can be triggered simultaneously, and the drying device can be stopped by sending a shutdown command to the drying device.

[0140] S603. Obtain the second cumulative drying time, wherein the second cumulative drying time starts to accumulate when the temperature of the drying tunnel air outlet reaches the first preset temperature.

[0141] For example, after the temperature at the air outlet of the drying tunnel reaches the first preset temperature T1, the timer is reset to zero and then restarted. The duration of the second timer is then determined as the second cumulative drying time.

[0142] S604. When the second cumulative drying time reaches the second preset time, if the temperature of the drying tunnel air outlet has not yet reached the second preset temperature, the first predicted time is determined as the predicted drying time.

[0143] For example, the second preset duration can be a preset waiting verification window, which can be determined according to the actual situation. If the temperature at the drying tunnel vent reaches the second preset temperature T2 within the waiting verification window, the above-mentioned steps of multi-dimensional feature extraction of the operating data within the second drying feature interval and subsequent steps are executed normally. However, if the temperature at the drying tunnel vent does not reach the second preset temperature T2 within the waiting verification window, the feature extraction of the second drying feature interval and the drying time prediction of the second-level prediction model are terminated, and the first predicted duration output by the first-level prediction model is directly used as the final predicted drying duration.

[0144] Based on the method provided in this example, the drying operation can be terminated in a timely manner when the temperature rises abnormally, and the predicted drying time can be determined in subsequent stages by using the first predicted time as a fallback, thereby improving the stability and adaptability of the drying completion determination.

[0145] Optional, Figure 7 This is a schematic flowchart of a drying control method disclosed herein. Figure 6 ,like Figure 7 As shown, before S202, it also includes:

[0146] S701. Obtain historical drying data of the drying device, wherein the historical drying data includes first historical drying data corresponding to the first drying characteristic interval, second historical drying data corresponding to the second drying characteristic interval, and historical drying duration.

[0147] For example, historical drying data during the operation of the drying device is collected in real time or offline. Similarly, the time from the start of drying to the moment when the temperature at the air vent of the drying tunnel reaches T1 is defined as the first drying characteristic interval, and the time from the start of drying to the moment when the temperature at the air vent of the drying tunnel reaches T2 is defined as the second drying characteristic interval. Historical drying data within the first drying characteristic interval is defined as first historical drying data, and historical drying data within the second drying characteristic interval is defined as second historical drying data. Additionally, the historical drying time for the drying device to complete drying the clothes is also recorded. The historical drying time can be determined by calculating the fluctuation value of the air vent temperature based on a preset time sliding window. When the fluctuation value is first less than or equal to a preset temperature threshold, it is determined as the endpoint where the drying process tends to stabilize. The time from the start of heating to this endpoint is defined as the historical drying time. Both the first and second historical drying data include the aforementioned 11-dimensional data.

[0148] S702. Input the first historical drying data and historical drying time into the first initial level prediction model, and iteratively train the first initial level prediction model based on the preset loss function until the difference between the predicted time output by the first initial level prediction model and the historical drying time is less than or equal to the preset difference, then end the training of the first initial level prediction model to obtain the first level prediction model.

[0149] For example, a cascaded prediction architecture consisting of a two-level extreme gradient boosting regression model is constructed, including a first initial-level prediction model and a second initial-level prediction model. The first initial-level prediction model is trained using first historical drying data and historical drying time to obtain the first-level prediction model. Specifically, the first-level prediction model is the base learner, and its core is used to learn the process characteristics of the middle stage of drying temperature rise, achieving a deep representation and pattern capture of the intermediate state of drying. The first historical drying data can be input into the first initial-level prediction model, and then a preset loss function is used to calculate the deviation between the historical drying time and the first predicted drying time output by the first initial-level prediction model and iteratively train until the deviation is less than or equal to a preset difference to obtain the first-level prediction model.

[0150] S703. Input the second historical drying data and historical drying time into the second initial-level prediction model, and iteratively train the second initial-level prediction model based on the loss function until the difference between the predicted time output by the second initial-level prediction model and the historical drying time is less than or equal to the preset difference, then end the training of the second initial-level prediction model to obtain the second-level prediction model.

[0151] For example, the second initial-level prediction model is trained using second historical drying data and historical drying duration to obtain the second-level prediction model. The second-level prediction model is a meta-learner that, based on global features throughout the entire temperature rise cycle, integrates the first drying prediction duration to achieve global trend capture and prediction accuracy optimization for the entire drying process, realizing a deep integration of intermediate process understanding and global trend prediction. The second historical drying data can be input into the second initial-level prediction model, and then a preset loss function can be used to calculate the deviation between the historical drying duration and the second drying prediction duration output by the second initial-level prediction model, and iterative training can be performed until the deviation is less than or equal to a preset difference to obtain the second-level prediction model.

[0152] Furthermore, defining the first initial-level prediction model as the function mapping F(x) and the second initial-level prediction model as the function mapping G(x), the formulaic description of the two-stage prediction can be expressed as:

[0153]

[0154]

[0155] Where t1 is the first predicted drying time and t2 is the second predicted drying time. This is the first historical drying data. This is the second historical drying data.

[0156] The extreme gradient boosting model used in both the first and second initial-level prediction models is an advanced machine learning algorithm, an optimized implementation of Gradient Boosting Decision Tree (GBDT). Its core idea lies in integrating multiple weak learners (i.e., decision trees) and progressively optimizing them in an additive manner to ultimately form a powerful and accurate prediction model. Its key technical principles are as follows:

[0157] The extreme gradient boosting model follows the basic framework of gradient boosting, building the model iteratively. Each iteration introduces a new decision tree to learn the residual between the current model prediction and the true label. Specifically, starting with an initial constant prediction, the model prediction after the t-th iteration is:

[0158]

[0159] in, It is the predicted value of the i-th sample after t iterations. These are the predictions from the model in the first t-1 rounds. It is a decision tree newly added in round t, whose goal is to fit the negative gradient (i.e., residual) of the model in the previous round.

[0160] Unlike traditional GBDT, which only optimizes the loss function, the Limiting Gradient Boosting model explicitly adds a regularization term to the loss function. This is crucial for preventing overfitting and improving the model's generalization ability. The loss function is defined as follows:

[0161]

[0162] Where L is the loss function (such as mean squared error) for the difference between the predicted value and the true value. It is a regularization term that controls the complexity of the model. Regularization term Defined as:

[0163]

[0164] Where T is the number of leaf nodes in the tree. γ represents the score (weight) of the leaf node, while γ and λ are hyperparameters that control the strength of regularization. This regularization term effectively penalizes complex tree structures (too many leaf nodes) and excessively large leaf node weights, thereby forcing the model to be simpler and more general. This is one of the core mechanisms by which the model of this invention performs robustly on the test set and overcomes the tendency to overfit.

[0165] To efficiently optimize the loss function, the extreme gradient boosting model uses a second-order Taylor expansion to approximate it as a quadratic function of ft(xi). By defining the first derivative gi and the second derivative hi, the loss function can be simplified to:

[0166]

[0167] This second-order derivative information provides more information about the curvature of the loss function, making the optimization process faster and more accurate. Based on this, the extreme gradient boosting model precisely calculates the "gain" of each possible split when constructing the tree structure and finding the optimal split point:

[0168]

[0169] in, and These are the sample sets of the left and right child nodes after the split, respectively, and I is the set of all training samples contained in the current parent node to be split. This gain formula simultaneously considers the degree of descent of the objective function of the left and right subtrees after the split, as well as the complexity penalty (−γ) caused by introducing new leaf nodes, thus automatically achieving precise pruning, avoiding the generation of unnecessary tree structures, and ensuring the efficiency of the model. Furthermore, the extreme gradient boosting model integrates several optimization techniques, making it particularly suitable for the application scenarios of this invention, specifically including: handling missing values: the algorithm can automatically learn the optimal splitting direction for missing data, ensuring the robustness of this invention when encountering temporary missing or abnormal sensor data; weighted quantile optimization: it can efficiently find the optimal splitting point of the feature distribution, greatly accelerating the model training process on a large amount of feature data; parallel processing: although the iteration is serial during boosting, the calculation during node splitting can be performed in parallel, improving the model training efficiency.

[0170] S704. Construct the first-level prediction model and the second-level prediction model into a preset cascaded prediction model.

[0171] For example, the first-level prediction model and the second-level prediction model are organized in a cascaded order, so that the output of the first-level prediction model is used as one of the input conditions of the second-level prediction model, thereby forming a preset cascaded prediction model for predicting drying time.

[0172] In this example, since the two prediction models are trained on data from different stages, after the actual multidimensional feature data is input, the models can output the predicted drying time in a cascaded manner, thereby improving the consistency and adaptability of the drying time prediction.

[0173] Figure 8 This is a schematic flowchart of a drying control method disclosed herein. Figure 7 It is used in drying equipment, such as Figure 8 As shown, it includes:

[0174] S801. Obtain the initial weight information of the clothes to be dried and the multi-stage feature data during the drying process, wherein the multi-stage feature data includes the first multi-dimensional feature data corresponding to the first drying feature interval and the second multi-dimensional feature data corresponding to the second drying feature interval.

[0175] In this example, the drying control method is applied to a drying device, which can be a washer-dryer combo, a standalone dryer, or other equipment with drum drying function, performing heating, air supply, drum tumbling, data acquisition, and shutdown control. Initial weight information of the clothing is used to characterize the initial load state of the clothing at the start of drying and can be obtained by the detection unit of the drying device. Multi-stage feature data is used to characterize the operating state at different stages of the drying process. The first drying feature interval and the second drying feature interval are used to define the feature acquisition range for different stages. The first multi-dimensional feature data and the second multi-dimensional feature data are sets of multi-dimensional operating features extracted within their respective intervals, used to characterize the operating state at different stages. As mentioned above, the first drying feature interval is from the start of drying to the moment the air vent temperature in the drying tunnel reaches T1. Multi-dimensional feature extraction is performed on the operating data belonging to the first drying feature interval to obtain the first multi-dimensional feature data. The second drying feature interval is from the start of drying to the moment the air vent temperature in the drying tunnel reaches T2. Multi-dimensional feature extraction is performed on the operating data belonging to the second drying feature interval to obtain the second multi-dimensional feature data.

[0176] S802. Send the multi-stage feature data to the cloud server so that the cloud server can input the first multi-dimensional feature data and the second multi-dimensional feature data into the preset cascaded prediction model to obtain the predicted drying time.

[0177] For example, the preset cascaded prediction model includes a first-level prediction model and a second-level prediction model. The cloud server inputs the first multidimensional feature data into the first-level prediction model, which outputs a first prediction duration based on the aforementioned 11-dimensional first multidimensional feature data. The first prediction duration and the second multidimensional feature data are then input into the second-level prediction model, which analyzes and predicts the first prediction duration and the aforementioned 11-dimensional second multidimensional feature data to obtain the predicted drying duration.

[0178] S803 receives the predicted drying time sent by the cloud server.

[0179] For example, after the cloud server obtains the predicted drying time through a preset cascaded prediction model, it returns the predicted drying time to the drying device, which then uses the predicted drying time to determine the completion of the drying process.

[0180] S804. Based on the predicted drying time and the initial weight of the clothes, determine whether drying is complete and stop the drying operation when drying is complete.

[0181] For example, by combining the predicted drying time and the initial weight of the clothes, it is determined whether the current drying task has met the drying completion conditions; when drying is determined to be complete, a drying completion signal is output and the drying operation is stopped. The predicted drying time reflects the estimated time required for the clothes to be dried under the actual working conditions, and the initial weight of the clothes reflects the initial load state. Combining the two allows the shutdown timing to correspond to the current task state, thus forming a drying control based on the current drying task.

[0182] The method provided in this example obtains the initial load and phased operation characteristics on the drying device side, and uses a preset cascaded prediction model on the cloud server side to jointly process the first multidimensional feature data and the second multidimensional feature data. Then, the obtained predicted drying time is returned to the drying device to perform local drying completion determination. This changes the control of the drying end from fixed parameters to the actual drying process based on different loading amounts, different initial moisture contents and environmental changes, thereby achieving precise control of the drying device.

[0183] Optional, Figure 9 This is a schematic flowchart of a drying control method disclosed herein. Figure 8 ,like Figure 9 As shown, S804 includes:

[0184] S901. Determine the target weight level based on the initial weight information of the clothing.

[0185] For example, multiple weight levels can be preset, each corresponding to a weight range. This determines the weight range within which the initial weight of the clothing falls, and thus the target weight level. For instance, if the initial weight of the clothing is less than 100g, the target weight level is set to level 1; if the initial weight is greater than or equal to 100g but less than 200g, the target weight level is set to level 2; and if the initial weight is greater than or equal to 200g, the target weight level is set to level 3.

[0186] S902. Determine the target boundary value corresponding to the target weight level based on the preset mapping relationship between the weight level and the boundary value.

[0187] For example, each target weight gear has a corresponding boundary value. The boundary value of gear 1 is less than the boundary value of gear 2, and the boundary value of gear 2 is less than the boundary value of gear 3. The boundary value corresponding to the target weight gear is determined as the target boundary value.

[0188] S903. Determine the target drying interval based on the predicted drying time and target boundary value.

[0189] For example, the predicted drying time can be defined as "t", and the target boundary value can be defined as "a", so the target drying interval can be [ta, t+a].

[0190] S904. Perform a drying completion determination based on the target drying range.

[0191] For example, when the drying time enters the target drying range, the clothes are judged to be dry, and drying is considered complete once the clothes are determined to be dry. If the drying time does not enter the target drying range, the drying process continues. This example adapts the timing of the drying judgment to different clothing weights, allowing the predicted drying time to work in conjunction with the actual clothing load, thereby improving the consistency and accuracy of the drying completion determination.

[0192] Optional, Figure 10 This is a schematic flowchart of a drying control method disclosed herein. Figure 9 ,like Figure 10 As shown, S904 includes:

[0193] S1001. Within the target interference interval, determine at least one interference start time.

[0194] For example, Table 1 shows the start time of the judgment for each gear position.

[0195] Table 1

[0196]

[0197] Among them, a1 <a2<a3<a。

[0198] According to Table 1, if the target weight setting is setting 1, the interference start times are t-a1, t, and t+a1 in sequence. If the target weight setting is setting 2, the interference start times are t-a2, t-a1, t, t+a1, and t+a2 in sequence. If the target weight setting is setting 3, the interference start times are t-a3, t-a2, t-a1, t, t+a1, t+a2, and t+a3 in sequence.

[0199] S1002. Based on the time sequence between all the stem initiation times, the first stem initiation time is taken as the target stem initiation time.

[0200] For example, taking the target weight setting as setting 1, the target drying start time is the time corresponding to t-a1, which is the time when the drying time reaches t-a1.

[0201] S1003. Starting from the initial time of the target drying process, continuously monitor the temperature of the drying tunnel vent within a preset time window to obtain the temperature fluctuation value of the drying tunnel vent corresponding to the initial time of the target drying process.

[0202] For example, when the drying time reaches t-a1, the temperature of the drying tunnel vent within the preset time window is detected, taking the time corresponding to t-a1 as the start time, and the temperature fluctuation value of the drying tunnel vent within the preset time window is obtained.

[0203] S1004. If the temperature fluctuation value of the drying tunnel air outlet corresponding to the start time of the target drying is lower than the preset fluctuation value, then the drying is determined to be completed.

[0204] For example, if the temperature fluctuation value of the drying tunnel vent within the preset time window is less than the preset fluctuation value, then it is determined that the clothes have been dried and the drying process is complete.

[0205] S1005. If the temperature fluctuation value of the drying tunnel vent corresponding to the target drying start time is greater than or equal to the preset fluctuation value, then based on the time sequence between all drying start times, the next drying start time is determined as the target drying start time, and the process returns to the step of continuously detecting the temperature of the drying tunnel vent within the preset time window from the target drying start time to obtain the temperature fluctuation value of the drying tunnel vent corresponding to the target drying start time, until the temperature fluctuation value of the drying tunnel vent corresponding to the target drying start time is lower than the preset fluctuation value, then the drying is determined to be complete.

[0206] For example, if the temperature fluctuation value of the drying tunnel vent within the preset time window is greater than or equal to the preset fluctuation value, it is determined that the clothes have not been dried. Then, when the drying time reaches t, the time corresponding to t is taken as the starting time, and the same detection logic is used to detect the temperature of the drying tunnel vent within the preset time window to obtain the temperature fluctuation value of the drying tunnel vent within the preset time window. Similarly, if the temperature fluctuation value of the drying tunnel vent within the preset time window is still greater than or equal to the preset fluctuation value, the drying determination continues based on the next target drying start time until the temperature fluctuation value of the drying tunnel vent is lower than the preset fluctuation value, at which point the drying is determined to be complete.

[0207] This example selects the start time of drying sequentially within the target drying interval and compares the temperature fluctuations at multiple time points. This allows the determination of drying completion to be based on the stable temperature changes at the air outlet of the drying tunnel. This makes the timing of stopping drying closer to the actual drying state and reduces premature shutdown or over-drying caused by misjudgment at a single moment.

[0208] Optionally, it also includes: if the temperature fluctuation value of the drying tunnel air outlet corresponding to the start time of all drying judgments is not lower than the preset fluctuation value, then the drying device is forcibly controlled to stop the drying operation.

[0209] For example, taking the target weight setting as setting 1, if the drying time reaches t+a1, the starting time is set to the time corresponding to t+a1. Using the same detection logic, the temperature of the air vents in the drying tunnel within the preset time window is detected, and the temperature fluctuation value of the air vents in the drying tunnel within the preset time window is obtained. If the temperature fluctuation value of the air vents in the drying tunnel within the preset time window is still greater than or equal to the preset fluctuation value, since there are no other subsequent dryness start times, the drying device can be directly controlled to stop drying. This example enables the drying device to enter a forced shutdown state if it does not meet the dryness judgment characteristics for a long time, thereby reducing the over-drying caused by continuous heating.

[0210] Optional, Figure 11 This is a schematic flowchart of a drying control method disclosed herein. Figure 10 ,like Figure 11 As shown,

[0211] S1101. Determine the drying progress based on the predicted drying time.

[0212] For example, after receiving the predicted drying time from the cloud server, the drying device can determine the drying progress based on the ratio between the current running time and the predicted drying time, and convert the drying progress into a percentage value.

[0213] S1102. Send the drying progress to the user terminal and control the user terminal to display the drying progress.

[0214] For example, the drying progress can be sent to the user terminal via a wireless communication link. After receiving the data, the user terminal will display the drying progress on its display interface in the form of numbers, icons, or progress bars.

[0215] Based on this example, users can directly know the current drying progress, thereby improving process awareness and ease of interaction.

[0216] Figure 12 It is the overall process of drying control, such as Figure 12As shown, after the drying process begins, the wet clothes are weighed to obtain the initial weight information of the clothes to be dried. Based on this initial weight information, parameters are matched to determine the target weight level. Then, during the drying process, the operating data for the first temperature rise stage and the second drying characteristic interval are recorded. The first multi-dimensional feature data corresponding to the first drying characteristic interval and the second multi-dimensional feature data corresponding to the second drying characteristic interval are uploaded to the cloud server. The cloud server determines the predicted drying time using a preset cascaded prediction model and sends the predicted drying time to the local drying control device. The control device turns on the heating element and accumulates the drying time. When the drying time reaches the initial dryness judgment point (the dryness judgment start time shown in the example in Table 1), the drying is judged based on the temperature fluctuation value of the drying tunnel vents. If the dryness judgment condition is met, the heating element is turned off to stop drying. If the dryness judgment condition is not met, and there is a next dryness judgment start time, the process continues until the next dryness judgment start time, and the drying judgment is repeated based on the temperature fluctuation value of the drying tunnel vents. If there is no next drying start time, the drying operation will be forcibly stopped.

[0217] Figure 13 This is a schematic diagram of the structure of a drying control device disclosed herein. Figure 1 ,like Figure 13 As shown, it includes:

[0218] The first acquisition module 131 is used to acquire multi-stage feature data during the drying process, wherein the multi-stage feature data includes first multi-dimensional feature data corresponding to the first drying feature interval and second multi-dimensional feature data corresponding to the second drying feature interval.

[0219] The input module 132 is used to input the first multidimensional feature data and the second multidimensional feature data into the preset cascaded prediction model to obtain the predicted drying time;

[0220] The first sending module 133 is used to send the predicted drying time to the drying device so that the drying device can perform a drying completion determination based on the predicted drying time and the initial weight information of the clothes to be dried, and stop the drying operation when the drying is completed.

[0221] The drying control device provided in this embodiment can execute the drying control method provided in the first aspect of the method embodiment above. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0222] Figure 14 This is a schematic diagram of the structure of a drying control device disclosed herein. Figure 2 It is used in drying equipment, such as Figure 14 As shown, it includes:

[0223] The second acquisition module 141 is used to acquire the initial weight information of the clothes to be dried and the multi-stage feature data during the drying process. The multi-stage feature data includes the first multi-dimensional feature data corresponding to the first drying feature interval and the second multi-dimensional feature data corresponding to the second drying feature interval.

[0224] The second sending module 142 is used to send multi-stage feature data to the cloud server so that the cloud server can input the first multi-dimensional feature data and the second multi-dimensional feature data into the preset cascaded prediction model to obtain the predicted drying time.

[0225] Receiver module 143 is used to receive the predicted drying time sent by the cloud server;

[0226] The processing module 144 is used to determine the completion of drying based on the predicted drying time and the initial weight of the clothes, and to stop the drying operation when drying is complete.

[0227] The drying control device provided in this embodiment can execute the drying control method provided in the second aspect of the above-described method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0228] Those skilled in the art will also understand that the various illustrative logic blocks and steps listed in the embodiments of this disclosure can be implemented by electronic hardware, computer software, or a combination of both. Whether such functionality is implemented in hardware or software depends on the specific application and the overall system design requirements. Those skilled in the art can implement the functionality using various methods for each specific application, but such implementation should not be construed as exceeding the scope of protection of the embodiments of this disclosure.

[0229] In the above detailed description, reference has been made to the accompanying drawings, which illustrate specific aspects of this disclosure by way of illustration. In this regard, terms indicating direction or positional relationship, such as “center,” “longitudinal,” “lateral,” “length,” “width,” “thickness,” “upper,” “lower,” “front,” “rear,” “left,” “right,” “vertical,” “horizontal,” “top,” “bottom,” “inner,” “outer,” “clockwise,” “counterclockwise,” “axial,” “radial,” and “circumferential,” are used with reference to the orientation of the described figures. Since components of the described device can be positioned in multiple different orientations, directional terms are used for illustrative purposes and not for limitation. It should be understood that other aspects can be utilized and structural or logical changes can be made without departing from the concept of this disclosure. Therefore, the following detailed description should not be considered limiting.

[0230] It should be understood that, unless otherwise specifically indicated, features of various embodiments of this disclosure described herein can be combined with each other. As used herein, the term "and / or" includes any one of the relevant listed items and any combination of any two or more.

[0231] It should be understood that, unless otherwise expressly specified and limited, the terms "joining," "attaching," "installing," "connecting," "linking," "fixing," etc., used in the embodiments of this disclosure should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection, an electrical connection, or a connection that allows communication between them; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise expressly limited. Those skilled in the art can understand the specific meaning of the above terms herein based on the specific circumstances.

[0232] Furthermore, the term "above" as used herein with respect to components, elements, or material layers formed or located "above" a surface may be used to indicate that the component, element, or material layer is "indirectly" positioned (e.g., placed, formed, deposited, etc.) on the surface such that one or more additional components, elements, or layers are arranged between the surface and the component, element, or material layer. However, the term "above" as used with respect to components, elements, or material layers formed or located "above" a surface may also optionally have a specific meaning: that the component, element, or material layer is "directly" positioned (e.g., placed, formed, deposited, etc.) on the surface, for example, in direct contact with the surface.

[0233] Although terms such as “first,” “second,” and “third” may be used herein to describe various components, parts, regions, layers, or sections, these components, parts, regions, layers, or sections are not limited to these terms. Rather, these terms are used only to distinguish one component, part, region, layer, or section from another. Therefore, without departing from the teachings of the examples described herein, the first component, part, region, layer, or section mentioned in the examples may also be referred to as the second component, part, region, layer, or section. Furthermore, the terms “first” and “second” are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as “first” or “second” may explicitly or implicitly include at least one of that feature. In the description herein, “a plurality” means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0234] It should be understood that spatial relative terms, such as “above,” “upper,” “below,” and “lower,” are used herein to describe the relationship between one element and another shown in the figures. In addition to the orientation depicted in the figures, these spatial relative terms are also intended to encompass different orientations of the device in use or operation. For example, if the device in the figures is flipped, an element described as “above” or “upper” relative to another element would be “below” or “lower” relative to that other element. Thus, depending on the spatial orientation of the device, the term “above” encompasses both above and below orientations. Devices may have other orientations (e.g., rotated 90 degrees or in other orientations), and the spatial relative terms used herein should be interpreted accordingly.

[0235] Furthermore, the term “exemplary” is used herein to mean serving as an example, instance, or illustration. Any aspect or design described herein as “exemplary” is not necessarily to be construed as advantageous compared to other aspects or designs. Rather, the use of the term “exemplary” is intended to present the concept in a concrete manner. As used herein, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or.” That is, unless otherwise specified or clear from the context, “X applies A or B” is intended to mean any of the natural inclusive arrangements. That is, “X applies A or B” satisfies any of the foregoing instances if X applies A; X applies B; or both X applies A and B. Additionally, unless otherwise specified or clear from the context to refer to the singular form, the articles “a” and “an” as used in this disclosure and the appended claims are generally understood to mean “one or more.”

[0236] Similarly, although this disclosure has been shown and described with respect to one or more implementations, equivalent variations and modifications will occur to those skilled in the art upon reading and understanding this specification and the accompanying drawings. This disclosure includes all such modifications and variations and is limited only by the scope of the claims. In particular, with respect to the various functions performed by the components described above (e.g., elements, resources, etc.), unless otherwise indicated, the terminology used to describe such components is intended to correspond to any component (functionally equivalent) that performs the specific function of the described component, even if structurally not equivalent to the disclosed structure. Furthermore, although specific features of this disclosure may have been disclosed with respect to only one of several implementations, such features may be combined with one or more other features of other implementations, as may be desired and advantageous to any given or particular application. Moreover, with regard to the terms “comprising,” “owning,” “having,” “having,” or variations thereof as used in the detailed description or claims, such terms are intended to be inclusive in a manner similar to the term “including.”

[0237] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0238] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A drying control method, characterized in that, include: Acquire multi-stage feature data during the drying process, wherein the multi-stage feature data includes first multi-dimensional feature data corresponding to a first drying feature interval and second multi-dimensional feature data corresponding to a second drying feature interval; The first multidimensional feature data and the second multidimensional feature data are input into a preset cascaded prediction model to obtain the predicted drying time; The predicted drying time is sent to the drying device so that the drying device can determine the completion of drying based on the predicted drying time and the initial weight information of the clothes to be dried, and stop the drying operation when drying is complete.

2. The method according to claim 1, characterized in that, The acquisition of multi-stage feature data during the drying process includes: Real-time acquisition of operating data during the drying process, wherein the operating data includes the temperature of the air vents in the drying tunnel; The process from the start of the drying process to the temperature of the air outlet of the drying tunnel reaching the first preset temperature is defined as the first drying characteristic range. Multi-dimensional feature extraction is performed on the operating data within the first drying feature interval to obtain the first multi-dimensional feature data; The process from the start of the drying process to the temperature at the air outlet of the drying tunnel reaching the second preset temperature is defined as the second drying characteristic range, wherein the second preset temperature is greater than the first preset temperature; Multidimensional feature extraction is performed on the operating data within the second drying feature range to obtain the second multidimensional feature data.

3. The method according to claim 2, characterized in that, The preset cascaded prediction model includes a first-level prediction model and a second-level prediction model; The step of inputting the first multidimensional feature data and the second multidimensional feature data into a preset cascaded prediction model to obtain the predicted drying time includes: The first multidimensional feature data is input into the first-level prediction model to obtain the first prediction duration; The first prediction duration and the second multidimensional feature data are input into the second-level prediction model to obtain the second prediction duration; The second predicted duration is determined as the predicted drying duration.

4. The method according to claim 2, characterized in that, The drying process includes multiple drying stages, and the preset cascaded prediction model includes a first-level prediction model and multiple second-level prediction models, with each of the multiple second-level prediction models corresponding to one of the multiple drying stages. The step of inputting the first multidimensional feature data and the second multidimensional feature data into a preset cascaded prediction model to obtain the predicted drying time includes: The first multidimensional feature data is input into the first-level prediction model to obtain the first prediction duration and the current drying stage; A target second-level prediction model is determined based on the current drying stage, wherein the target second-level prediction model is the second-level prediction model corresponding to the current drying stage among a plurality of second-level prediction models; The first prediction duration, the current drying stage, and the second multidimensional feature data are input into the target second-level prediction model to obtain the second prediction duration; The second predicted duration is determined as the predicted drying duration.

5. The method according to claim 3 or 4, characterized in that, Also includes: Obtain the first cumulative drying time, wherein the first cumulative drying time starts to accumulate from the time the drying device is started; When the first cumulative drying time reaches the first preset time, if the temperature of the air outlet of the drying tunnel still has not reached the first preset temperature, a stop command is sent to the drying device. Obtain the second cumulative drying time, wherein the second cumulative drying time begins to accumulate when the temperature at the air outlet of the drying tunnel reaches the first preset temperature; When the second cumulative drying time reaches the second preset time, if the temperature of the drying tunnel air outlet still has not reached the second preset temperature, then the first predicted time is determined as the predicted drying time.

6. The method according to claim 3, characterized in that, Before inputting the first multidimensional feature data and the second multidimensional feature data into the preset cascaded prediction model, the method further includes: Obtain historical drying data of the drying device, wherein the historical drying data includes first historical drying data corresponding to the first drying feature interval, second historical drying data corresponding to the second drying feature interval, and historical drying time; The first historical drying data and the historical drying time are input into the first initial level prediction model, and the first initial level prediction model is iteratively trained based on a preset loss function until the difference between the predicted time output by the first initial level prediction model and the historical drying time is less than or equal to a preset difference. Then the training of the first initial level prediction model ends, so as to obtain the first level prediction model. The second historical drying data and the historical drying time are input into the second initial-level prediction model, and the second initial-level prediction model is iteratively trained based on the loss function until the difference between the predicted time output by the second initial-level prediction model and the historical drying time is less than or equal to the preset difference. Then the training of the second initial-level prediction model ends, so as to obtain the second-level prediction model. The first-level prediction model and the second-level prediction model are combined to form the preset cascaded prediction model.

7. A drying control method, applied to a drying device, characterized in that, include: The initial weight information of the clothes to be dried and the multi-stage feature data during the drying process are obtained. The multi-stage feature data includes first multi-dimensional feature data corresponding to the first drying feature interval and second multi-dimensional feature data corresponding to the second drying feature interval. The multi-stage feature data is sent to the cloud server, so that the cloud server inputs the first multi-dimensional feature data and the second multi-dimensional feature data into a preset cascaded prediction model to obtain the predicted drying time. Receive the predicted drying time sent by the cloud server; The drying completion determination is performed based on the predicted drying time and the initial weight information of the clothing, and the drying operation is stopped when drying is complete.

8. The method according to claim 7, characterized in that, The step of determining whether drying is complete based on the predicted drying time and the initial weight of the clothing includes: Determine the target weight level based on the initial weight information of the clothing; The target boundary value corresponding to the target weight level is determined based on the preset mapping relationship between the weight level and the boundary value. The target drying interval is determined based on the predicted drying time and the target boundary value; The drying completion determination is performed based on the target drying range.

9. The method according to claim 8, characterized in that, The step of determining the completion of drying based on the target drying range includes: Within the target interference interval, at least one interference start time is determined; Based on the temporal order of all the aforementioned initiation times, the first initiation time of the initiation time is taken as the target initiation time of the initiation time. Starting from the target drying start time, the drying tunnel air outlet temperature is continuously monitored within a preset time window to obtain the drying tunnel air outlet temperature fluctuation value corresponding to the target drying start time. If the temperature fluctuation value of the drying tunnel air outlet corresponding to the start time of the target drying is lower than the preset fluctuation value, then the drying is determined to be complete. If the temperature fluctuation value of the drying tunnel vent corresponding to the target drying start time is greater than or equal to the preset fluctuation value, then based on the time sequence between all the drying start times, the next drying start time is determined as the target drying start time, and the process returns to the step of continuously detecting the temperature of the drying tunnel vent within a preset time window from the target drying start time to obtain the temperature fluctuation value of the drying tunnel vent corresponding to the target drying start time, until the temperature fluctuation value of the drying tunnel vent corresponding to the target drying start time is lower than the preset fluctuation value, then drying is determined to be complete.

10. The method according to claim 9, characterized in that, Also includes: If the temperature fluctuation value of the drying tunnel air outlet corresponding to all the aforementioned drying start times is not lower than the preset fluctuation value, then the drying device will be forcibly stopped from drying.

11. The method according to any one of claims 7-10, characterized in that, Also includes: The drying progress is determined based on the predicted drying time; The drying progress is sent to the user terminal, and the user terminal is controlled to display the drying progress.

12. A drying control device, characterized in that, include: The first acquisition module is used to acquire multi-stage feature data during the drying process, wherein the multi-stage feature data includes first multi-dimensional feature data corresponding to a first drying feature interval and second multi-dimensional feature data corresponding to a second drying feature interval. The input module is used to input the first multidimensional feature data and the second multidimensional feature data into a preset cascaded prediction model to obtain the predicted drying time; The first sending module is used to send the predicted drying time to the drying device, so that the drying device can perform a drying completion determination based on the predicted drying time and the initial weight information of the clothes to be dried, and stop the drying operation when the drying is completed.

13. A drying control device, applied to a drying apparatus, characterized in that, include: The second acquisition module is used to acquire the initial weight information of the clothes to be dried and the multi-stage feature data during the drying process. The multi-stage feature data includes the first multi-dimensional feature data corresponding to the first drying feature interval and the second multi-dimensional feature data corresponding to the second drying feature interval. The second sending module is used to send the multi-stage feature data to the cloud server, so that the cloud server inputs the first multi-dimensional feature data and the second multi-dimensional feature data into a preset cascaded prediction model to obtain the predicted drying time; The receiving module is used to receive the predicted drying time sent by the cloud server; The processing module is used to determine the completion of drying based on the predicted drying time and the initial weight information of the clothing, and to stop the drying operation when drying is complete.

Images