Ice detection method, ice maker, and program product

Abstract

The application discloses a method for detecting stuck ice, an ice maker and a program product. The method comprises the following steps: after the ice maker starts to make ice, acquiring a sound signal collected in the ice maker, acquiring torque data collected from a target driving mechanism, and acquiring a falling ice detection signal collected in the ice maker; the target driving mechanism is used for driving ice cubes made in an ice making cavity of the ice maker; performing stuck ice identification according to the sound signal and the torque data to obtain a first identification result; performing stuck ice identification according to the falling ice detection signal to obtain a second identification result; and if at least one of the first identification result and the second identification result indicates that there is a stuck ice condition, it is determined that there is a stuck ice condition in the ice maker. The application can effectively detect whether stuck ice occurs in the ice maker in a timely manner, and effectively solves the hysteresis of stuck ice detection.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of detection, and more particularly, to an ice jam detection method, an ice maker, and a program product. BACKGROUND

[0002] During use of the ice maker, ice jam may occur in the ice maker, that is, the ice blocks produced are jammed in the ice maker, for example, in the ice making cavity of the ice maker, so that the ice maker cannot normally produce ice. In the related art, a falling ice detection sensor is usually installed in the ice maker to detect whether ice blocks fall from the ice making cavity of the ice maker. If the ice blocks do not fall from the ice making cavity of the ice maker for a long time, it is determined that there is an ice jam in the ice maker. However, this way of identifying whether there is an ice jam in the ice maker has a lag, which causes the ice jam in the ice maker to be unable to be detected in time. SUMMARY

[0003] In view of the above problems, the embodiments of the present application provide an ice jam detection method, an ice maker, and a program product to solve the problem of lag in the way of detecting the ice jam in the ice maker in the related art.

[0004] In a first aspect, an ice jam detection method is provided, comprising:

[0005] After the ice maker starts to produce ice, a sound signal collected in the ice maker is obtained, torque data collected from a target driving mechanism is obtained, and a falling ice detection signal collected in the ice maker is obtained. The target driving mechanism is used to drive the ice blocks produced in the ice making cavity of the ice maker to be output.

[0006] An ice jam identification is performed according to the sound signal and the torque data, and a first identification result is obtained.

[0007] An ice jam identification is performed according to the falling ice detection signal, and a second identification result is obtained.

[0008] If at least one of the first identification result and the second identification result indicates that there is an ice jam, it is determined that there is an ice jam in the ice maker.

[0009] In a second aspect, a stuck ice detection apparatus is provided, comprising: an acquisition module configured to acquire a sound signal collected inside an ice maker after the ice maker starts making ice, acquire torque data collected from a target driving mechanism configured to drive ice cubes made in an ice making cavity of the ice maker, and acquire a falling ice detection signal collected in the ice maker; a first identification module configured to identify stuck ice based on the sound signal and the torque data to obtain a first identification result; a second identification module configured to identify stuck ice based on the falling ice detection signal to obtain a second identification result; and a stuck ice determination module configured to determine that there is stuck ice in the ice maker if at least one of the first identification result and the second identification result indicates that there is stuck ice.

[0010] In a third aspect, an ice maker is provided, comprising: a processor; and a memory having computer readable instructions stored thereon, the computer readable instructions, when executed by the processor, implement the stuck ice detection method as described above.

[0011] In a fourth aspect, a computer readable storage medium is provided, having computer readable instructions stored thereon, the computer readable instructions, when executed by a processor, implement the stuck ice detection method as described above.

[0012] In a fifth aspect, a computer program product is provided, comprising computer readable instructions, the computer readable instructions, when executed by a processor, implement the stuck ice detection method as described above.

[0013] In the present application, in addition to identifying stuck ice based on the collected falling ice detection signal to obtain a second identification result, stuck ice is further identified based on the sound signal collected inside the ice maker and the torque data of the target driving mechanism to obtain a first identification result, and it is determined that there is stuck ice in the ice maker if at least one of the first identification result and the second identification result indicates that there is stuck ice. In this way, the characteristics that the sound inside the ice maker is larger and the torque output by the target driving mechanism is larger when stuck ice occurs in the ice maker are fully utilized, which can ensure the accuracy of the first identification result obtained by identifying stuck ice based on the sound signal and the torque data of the target driving mechanism. Moreover, in the early stage of stuck ice occurring in the ice maker, ice will still fall in the ice maker, but due to the abnormal sound in the ice maker relative to the normal ice making condition, the sound signal collected inside the ice maker and the torque data of the target driving mechanism can effectively identify that stuck ice occurs in the ice maker. Therefore, it can ensure that stuck ice is identified in a timely and accurate manner in the early stage of stuck ice, rather than identifying stuck ice only when ice cannot fall in the ice maker. In this way, the problem of hysteresis in the related art method of detecting stuck ice in the ice maker is effectively solved. BRIEF DESCRIPTION OF DRAWINGS

[0014] The accompanying drawings, which are incorporated herein and constitute part of the specification, illustrate embodiments consistent with the application and, together with the description, further serve to explain the principles of the application. It is to be expressly understood that the drawings are only exemplary and are provided to further facilitate an understanding of the application. In the drawings, the same or like reference characters are used to denote like or similar elements throughout the several views.

[0015] Figure 1 is a flowchart of a method for detecting stuck ice according to an embodiment of the application.

[0016] Figure 2 is a flowchart of detecting falling ice and determining a second identification result according to an embodiment of the application.

[0017] Figure 3 is a flowchart of step 120 according to an embodiment of the application.

[0018] Figure 4 is a flowchart of collecting a sound signal and performing abnormal sound identification according to an embodiment of the application.

[0019] Figure 5 is a flowchart of step 320 according to an embodiment of the application.

[0020] Figure 6 is a flowchart of collecting a torque value and identifying an abnormal torque according to an embodiment of the application.

[0021] Figure 7 is a flowchart of steps before step 310 according to an embodiment of the application.

[0022] Figure 8 is a schematic diagram of detecting stuck ice according to an embodiment of the application.

[0023] Figure 9 is a block diagram of a stuck ice detection device according to an embodiment of the application.

[0024] Figure 10 is a block diagram of an ice maker according to an embodiment of the application. DETAILED DESCRIPTION

[0025] Embodiments of the application are described in detail below with reference to the attached drawing figures, wherein the same or like reference numerals are used throughout the several views to designate the same or like components. The embodiments described below are merely examples for the principles of the present application and, therefore, are not to be taken in a limiting sense, as the present application can be embodied in numerous other forms.

[0026] In the following description, the terms "first", "second", etc. are merely used to distinguish similar objects, and do not represent a specific order or sequence for the objects. It can be understood that the "first" and "second" can be interchanged in a specific order or sequence as allowed, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein.

[0027] "Multiple" as mentioned herein refers to two or more. "And / or" describes the association relationship of associated objects, which means that there can be three relationships, for example, A and / or B can represent three cases: A exists alone, A and B exist together, and B exists alone. The character " / " generally represents an "or" relationship between the front and rear associated objects. In the following description, "some embodiments" or "some embodiments" are described, which are a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subset of all possible embodiments, and can be combined with each other without conflict.

[0028] Figure 1 is a flowchart of a card ice detection method according to an embodiment of the present application. The method can be executed by an electronic device, which can be a device (such as a smart terminal) in communication connection with an ice maker, or an ice maker, which is not specifically limited here. As shown in Figure 1 , the method includes at least steps 110 to 140, which are described in detail as follows:

[0029] Step 110: After the ice maker starts to make ice, the sound signal collected inside the ice maker is obtained, the torque data collected from the target driving mechanism is obtained, and the ice falling detection signal collected in the ice maker is obtained. The target driving mechanism is used to drive the ice blocks made in the ice making cavity of the ice maker.

[0030] The ice maker includes an ice making cavity, which is a refrigeration space for forming ice blocks in the ice maker. The ice making cavity is provided with a liquid inlet and an ice outlet. The liquid flowing into the ice making cavity from the liquid inlet is cooled by the evaporator to form ice blocks, and then the formed ice blocks are output to the outside of the ice making cavity, for example, to the ice basket in the ice maker. In the present application, a sound collecting device (such as a microphone) is provided in the ice maker, which is used to collect the sound signal inside the ice maker. In some embodiments, the sound collecting device can be installed at any position inside the ice maker, for example, near the ice making cavity inside the ice maker, so that the sound signal inside the ice maker is collected by the sound collecting device to approximate the sound signal inside the ice making cavity. In some other embodiments, the sound collecting device can be installed on the outer wall of the ice making cavity of the ice maker, so that the sound collecting device faces the inside of the ice making cavity to collect the sound signal, so as to ensure that the collected sound signal mainly comes from the inside of the ice making cavity.

[0031] In the present application, a torque sensor can be installed on the target driving mechanism to collect the torque value output by the target driving mechanism. In some embodiments, the ice maker also has an ice ejector, which is at least partially located inside the ice making cavity. The ice ejector is used to eject or push the ice formed in the ice making cavity to the outside of the ice making cavity. For example, the ice ejector can be a spiral scraper, which includes a rod body and a spiral blade fixedly arranged on the rod body along the central axis of the rod body. The spiral blade can be used to scrape the ice formed in the ice making cavity. The rod body of the spiral scraper is installed at the ice outlet of the ice making cavity, and the spiral blade is located inside the ice making cavity. In this case, the torque output end of the target driving mechanism can be connected to the ice ejector, so that the target driving mechanism drives the ice ejector to output the ice formed in the ice making cavity to the outside of the ice making cavity. The target driving mechanism is located at the end of the ice ejector away from the ice making cavity. In some embodiments, the target driving mechanism can be an electric motor, such as a direct current motor.

[0032] In the present application, the ice maker also has a falling ice detection sensor, which is used to detect whether ice falls from the ice outlet of the ice making cavity. The falling ice detection sensor is fixedly arranged outside the ice making cavity and close to the ice outlet of the ice making cavity. In some embodiments, the falling ice detection sensor can be an infrared sensor, which includes a signal emitter and a signal receiver. The signal emitter can emit infrared signals in a direction perpendicular to the falling direction of the ice. In the case of ice falling from the ice outlet, the falling ice will block the infrared signals emitted by the signal emitter, thereby causing the signal receiver to be unable to receive the infrared signals or to receive weak infrared signals. Conversely, in the case of no ice falling from the ice outlet, the infrared signals emitted by the signal emitter will be substantially received by the signal receiver. Thus, whether ice falls from the ice outlet can be identified according to the infrared signals emitted by the signal emitter and the signals received by the signal receiver. The falling ice detection signal is used to indicate whether ice falls from the ice outlet of the ice making cavity.

[0033] The start of ice making by the ice maker means that the ice maker starts to make ice and enters the ice making mode. In the case where the ice maker does not enter the ice making mode, the ice making process has not started, and the refrigeration cavity in the ice maker is not being cooled. Correspondingly, there is no ice formation in the refrigeration cavity. Therefore, in some embodiments, the torque data of the target driving mechanism can be collected and the falling ice detection can be performed (i.e., the falling ice detection sensor is activated) in response to the ice maker entering the ice making mode. If the ice maker is in a standby state (i.e., the ice maker is turned on but not in the ice making mode) or in a defrosting mode, the torque data of the target driving mechanism does not need to be collected, and the falling ice detection does not need to be performed.

[0034] In some embodiments, considering the case that the ice maker just enters the ice making mode, there can be abnormal sound (for example, interference sound generated by the start of other components in the ice maker, such as the start of the water pump, the fan, etc.) caused by the start of the machine. Therefore, to avoid the sound signal collected when the ice maker just enters the ice making mode affecting the accuracy of the ice block identification, the sound signal inside the ice maker can be started to be collected in response to the time length of the ice maker entering the ice making mode reaching a third target time length. In this way, during the time period when the time length of the ice maker entering the ice making mode does not reach the third target time length, the sound signal collected towards the ice making cavity does not need to be collected. The third target time length can be determined according to the duration of the interference sound generated after the ice maker starts. In some embodiments, the third target time length can be set to 1 minute, 3 minutes, 4 minutes, 5 minutes, 6 minutes, etc.

[0035] Step 120, identifying the ice block according to the sound signal and the torque data to obtain a first identification result.

[0036] The ice block identification refers to identifying whether the ice block situation occurs in the ice maker. The first identification result is used to indicate whether the ice block situation exists in the ice maker.

[0037] In the case of the ice block situation in the ice maker, because new ice blocks are continuously formed and the generated ice blocks cannot be output to the outside of the ice making cavity in time, more and more ice blocks will gradually accumulate in the ice making cavity. In this way, the mutual contact and collision between the ice blocks become more and more frequent, and the mutual contact and collision between the ice blocks and other components become more and more frequent, thereby causing the sound inside the ice making cavity to be significantly different from the sound inside the ice making cavity in the case of no ice block. In other words, the sound inside the ice making cavity in the case of the ice block is an abnormal sound relative to the sound inside the ice making cavity in the case of no ice block. Therefore, based on the difference between the sound inside the ice making cavity in the case of the ice block and the sound inside the ice making cavity in the case of no ice block, the ice block situation inside the ice making cavity can be identified through the collected sound signal inside the ice making cavity.

[0038] In the case of the ice block situation in the ice maker, because more and more ice blocks will gradually accumulate in the ice making cavity, the resistance (for example, the resistance of the ice blocks acting on the ice extruder) caused by the ice blocks becomes larger and larger. Therefore, it will cause the torque output by the target driving mechanism to be larger in the case of the ice block than in the case of no ice block. Therefore, based on the difference between the torque value output by the target driving mechanism in the case of no ice block and the torque value output by the target driving mechanism in the case of the ice block, the ice block situation in the ice maker can be identified according to the collected torque data of the target driving mechanism.

[0039] In addition, considering that the sound collection device in the ice maker can collect environmental sound in the environment where the ice maker is located, if there are other objects in the environment where the ice maker is located that produce irregular sound, it is possible that the collected environmental sound is identified as abnormal sound, and then misidentified as ice jam in the ice maker. In addition, considering that the torque of the target driving mechanism increases, in addition to being caused by ice jam, it can also be caused by abnormalities in the target driving mechanism itself or other reasons. Therefore, relying solely on the torque data of the target driving mechanism to identify ice jam can also result in low accuracy of ice jam identification.

[0040] Based on the above reasons, in the application, the ice jam identification is performed by combining the sound signal and the torque data. In this way, the accuracy of the obtained first identification result is ensured, and the probability of misidentification is reduced.

[0041] Step 130: Perform ice jam identification according to the ice falling detection signal to obtain a second identification result.

[0042] The second identification result is used to indicate whether there is an ice jam in the ice maker. It can be understood that in steps 120 and 130, different data is used for ice jam identification, so the two identification results (i.e. the first identification result and the second identification result) obtained by using different data for ice jam identification can be different or the same.

[0043] In the process of normal ice making of the ice maker, if no ice jam occurs in the ice making cavity, ice blocks will continuously fall from the ice outlet of the ice making cavity, so the ice falling detection sensor will continuously detect that ice blocks fall from the ice outlet. On the contrary, if ice jam occurs in the ice making cavity, the ice falling sensor can continuously detect that no ice blocks fall from the ice outlet of the ice making cavity for a long time. Therefore, based on this principle, the ice falling detection signal obtained by the ice falling detection sensor can be used to identify whether ice blocks fall from the ice outlet of the ice making cavity, and then identify whether there is an ice jam in the ice maker (which can also be understood as in the ice making cavity of the ice maker).

[0044] In some embodiments, step 130 includes: if it is determined according to the ice falling detection signal that the time interval from the last time ice falling is detected reaches a first target time interval, determining that the second identification result is an identification result indicating that there is an ice jam; if it is determined according to the ice falling detection signal that the continuous time interval during which no ice falling is detected after first entering the ice making mode reaches a second target time interval, determining that the second identification result is an identification result indicating that there is an ice jam; and the second target time interval is greater than the first target time interval.

[0045] That is, the first case is: after the ice maker starts to make ice, after detecting the ice drop for the first time, if it is determined according to the subsequent ice drop detection signal that the interval time from the last time of detecting the ice drop exceeds the first target time, it indicates that a long time has passed since the last time of detecting the ice drop without detecting the ice drop again, and therefore, it can be determined that the ice jam occurs in the ice maker under this condition.

[0046] The second case is: after the ice maker starts to make ice, the ice drop is not detected all the time, that is, the continuous time of not detecting the ice drop after entering the ice making mode for the first time reaches the second target time, which indicates that the ice jam occurs in the ice maker before the ice drop for the first time.

[0047] Since the ice maker needs a certain time to form ice from starting to make ice, the second target time can be slightly longer than the shortest time from starting to make ice to forming ice. The first target time can be slightly longer than the shortest time of the adjacent two ice drops. Generally, in the process of normal ice making, the interval time of the adjacent two ice drops is relatively short, which is less than the shortest time from starting to make ice to forming ice, and therefore, the second target time can be set to be greater than the first target time. In some embodiments, the first target time can be set to 5 minutes, and the second target time can be 30 minutes, and in other embodiments, other time lengths can also be set, which are not limited here. In some embodiments, step 130 further includes: if it is determined according to the ice drop detection signal that the time from the last time of detecting the ice drop does not reach the first target time, or if it is determined according to the ice drop detection signal that the interval time from entering the ice making mode to detecting the ice drop for the first time does not exceed the second target time, determining that the second identification result indicates the identification result of the non-existence of the ice jam condition.

[0048] Figure 2 is a flowchart for detecting the ice drop and determining the second identification result according to an embodiment of the present application. The infrared sensor is used to detect the ice drop of the ice outlet of the ice making cavity of the ice maker. After the ice maker enters the ice making mode, ① the ice drop detection times and the timing time length of the ice drop detection are cleared, then ② the infrared sensor collects the ice drop detection signal, ③ whether the ice drop is detected is determined according to the ice drop detection signal, if the ice drop is detected, ④ whether the ice drop is not detected for the first target time is determined according to the ice drop detection signal collected by the infrared sensor at the subsequent time (that is, whether the time from the last time of detecting the ice drop reaches the first target time is determined, for example, the first target time is 5 minutes), and if it is determined that the ice drop is not detected for the first target time, it is determined that the second identification result is the result indicating that the ice jam condition exists in the ice maker.

[0049] In ③, if the falling ice is detected, ⑤ continues to determine whether the timing length of the falling ice detection reaches a second target length (i.e., determine whether the continuous time length of the falling ice detection after entering the ice making mode reaches the second target length, for example, the second target length is 30 minutes) according to the accumulated falling ice detection timing length; if it is determined that the timing length of the falling ice detection reaches the second target length, it is determined that the second identification result is a result indicating that there is a stuck ice condition in the ice maker.

[0050] In step 140, if at least one of the first identification result and the second identification result indicates that there is a stuck ice condition, it is determined that there is a stuck ice condition in the ice maker.

[0051] That is, as long as at least one of the first identification result and the second identification result indicates that the stuck ice is identified, it is determined that there is a stuck ice condition in the ice maker. On the contrary, if both the first identification result and the second identification result indicate that the stuck ice is not identified, it is determined that there is no stuck ice condition in the ice maker.

[0052] The inventors of the present application found through experiments on the ice maker that the ice maker may experience the following four stages in the process of ice making, in the order from first to last: ① early ice making stage, no abnormal sound is generated inside the ice maker, and the ice outlet of the ice making cavity can fall ice; ② middle ice making stage, a small abnormal sound is generated inside the ice maker, and the ice outlet of the ice making cavity can fall ice; ③ middle-late ice making stage, no abnormal sound is generated inside the ice maker, and the ice outlet of the ice making cavity cannot fall ice; ④ late ice making stage, a large abnormal sound is generated inside the ice maker, and the ice outlet of the ice making cavity cannot fall ice.

[0053] It should be noted that the above-mentioned four stages are not necessarily experienced in every ice making process, but the inventors of the present application found through actual experiments that the above-mentioned four stages exist, and the order of the above-mentioned four stages is from ① to ④, and in actual ice making process, only two or three stages may be experienced from the beginning of ice making to the occurrence of the stuck ice condition. For the above-mentioned third stage “middle-late ice making stage”, it is found in actual experiments that some ice makers may have ice blocks in the ice making cavity completely frozen, without abnormal sound and ice falling.

[0054] In the second stage, i.e. the ice-making middle stage, ice has actually been stuck in the ice maker, but the ice in the ice-making cavity has not been completely frozen, so the ice outlet of the ice-making cavity can still drop ice. In this case, if the ice drop detection signal detected by the ice drop detection sensor in the related art is used to identify whether ice is stuck, the situation where ice is not stuck in the ice maker at this time will be misidentified, and there will be a missed identification. Using the ice drop detection sensor in the related art to identify the ice sticking situation can at least identify the existence of ice sticking in the ice-making middle stage and the ice-making late stage, but in practice, ice has actually been stuck in the ice-making middle stage, so the method of using the ice drop detection sensor in the related art to identify the ice sticking situation has a lag.

[0055] If the method of the present application is used, if the ice-making middle stage occurs, the ice sticking situation can be identified through the collected sound signal and the torque data of the target driving mechanism; if the ice-making middle-late stage occurs, the ice sticking situation can be identified through the ice drop detection signal collected by the ice drop detection sensor; if the ice-making late stage occurs, the ice sticking situation can be identified through the collected sound signal and the torque data of the target driving mechanism, or through the ice drop detection signal. It can be seen that, in the present application, on the basis of using the ice drop detection signal to identify ice sticking and obtaining a second identification result, the sound signal collected in the ice maker and the torque data of the target driving mechanism are also used to identify ice sticking to obtain a first identification result, and at least one of the first identification result and the second identification result indicates that there is an ice sticking situation, and it is determined that there is an ice sticking situation in the ice maker. This can effectively solve the problem of missed identification and lag in the related art of using only the ice drop detection sensor to identify ice sticking. Using the method of the present application, the ice sticking situation in the ice maker can be identified in a timely and effective manner, and measures can be taken in a timely manner to deal with the ice sticking situation.

[0056] In this application, in addition to using the collected ice-fall detection signal to identify ice jam and obtain a second identification result, it further uses the sound signal collected inside the ice maker and the torque data of the target drive mechanism to identify ice jam and obtain a first identification result. If at least one of the first and second identification results indicates that ice jam exists, it is determined that ice jam exists in the ice maker. In this way, by making full use of the characteristics that the sound inside the ice maker is relatively loud and the torque output of the target drive mechanism is relatively large when ice jam occurs, the accuracy of the first identification result obtained by identifying ice jam based on the sound signal and the torque data of the target drive mechanism can be guaranteed. Furthermore, even in the early stages of ice jamming, ice will still fall into the ice maker. However, abnormal sounds will be heard from the ice maker compared to normal ice-making conditions. By collecting sound signals from inside the ice maker and torque data from the target drive mechanism, the ice jam can be effectively identified. This ensures that the ice jam is identified promptly and accurately in its early stages, rather than only when ice cannot fall into the ice maker. This effectively solves the problem of lag in the methods of detecting ice jamming in ice makers in related technologies.

[0057] Moreover, the sound signal collected inside the ice maker and the torque data of the target drive mechanism are used to identify ice jams and obtain the first identification result, rather than using only the sound signal or only the torque data of the target drive mechanism to determine the first identification result. The sound signal and torque data can corroborate each other to ensure the accuracy of the first identification result.

[0058] In some embodiments, such as Figure 3 As shown, step 120 includes the following steps 310-330:

[0059] Step 310: Perform abnormal sound recognition on the sound signal to obtain the abnormal sound recognition result.

[0060] In some embodiments, the sound signal inside the ice-making cavity collected when the ice maker is in normal ice-making state can be acquired as a normal sample sound signal. Then, the similarity between the newly acquired sound signal and the normal sample sound signal is calculated. If the similarity between the two is greater than the similarity threshold, the abnormal sound recognition result is determined to be a result indicating that the currently acquired sound signal is not an abnormal sound; otherwise, if the similarity between the two is not greater than the similarity threshold, the abnormal sound recognition result is determined to be a result indicating that the currently acquired sound signal is an abnormal sound.

[0061] In some embodiments, in order to avoid the situation that a sudden abnormal sound (e.g. noise in the surrounding environment or a short and sharp sound generated by a component inside the ice making machine) is identified as an abnormal sound generated in the ice making cavity, and thus the subsequent first identification result is inaccurate, if the sound signals collected for K consecutive times are subjected to abnormal sound identification, and it is determined that the K abnormal sound identification results all indicate that the corresponding sound signals are abnormal sounds, and the average of the confidence levels in the K abnormal sound identification results is greater than a confidence level threshold, it is determined that the K abnormal sound identification results are reliable, i.e. indicating that an abnormal sound is generated in the ice making cavity. On the contrary, if there is at least one of the K abnormal sound identification results indicating that the corresponding sound signal is a normal sound, or, in the case that the K abnormal sound identification results all indicate that the corresponding sound signals are abnormal sounds, the average of the confidence levels in the K abnormal sound identification results is not greater than the confidence level threshold, it is determined that the K abnormal sound identification results are unreliable, and thus it is determined that no abnormal sound is generated in the ice making cavity. K is an integer greater than 1.

[0062] In some embodiments, in order to avoid the situation that a sudden abnormal sound (e.g. noise in the surrounding environment or a short and sharp sound generated by a component inside the ice making machine) is identified as an abnormal sound generated in the ice making cavity, and thus the subsequent first identification result is inaccurate, if the sound signals collected for K consecutive times are subjected to abnormal sound identification, and it is determined that the K abnormal sound identification results all indicate that the corresponding sound signals are abnormal sounds, and the average of the confidence levels in the K abnormal sound identification results is greater than a confidence level threshold, it is determined that the K abnormal sound identification results are reliable, i.e. indicating that an abnormal sound is generated in the ice making cavity. On the contrary, if there is at least one of the K abnormal sound identification results indicating that the corresponding sound signal is a normal sound, or, in the case that the K abnormal sound identification results all indicate that the corresponding sound signals are abnormal sounds, the average of the confidence levels in the K abnormal sound identification results is not greater than the confidence level threshold, it is determined that the K abnormal sound identification results are unreliable, and thus it is determined that no abnormal sound is generated in the ice making cavity. K is an integer greater than 1.

[0063] Figure 4 is a flowchart of collecting a sound signal and performing abnormal sound identification according to an embodiment of the present application, as shown in Figure 4 the ice making duration is accumulated from the start of entering the ice making mode, if the ice making duration does not reach a third target duration, the ice making duration is continuously accumulated, if the ice making duration reaches the third target duration, the microphone starts collecting a sound signal (i.e. collecting a sound signal inside the ice making cavity), then the Fbank feature of the sound signal is extracted (the Fbank feature can be obtained by sequentially performing pre-emphasis, framing, windowing, short-time Fourier transform and Mel filtering on the sound signal), then the Fbank feature is subjected to abnormal sound classification to obtain an abnormal sound identification result, if K consecutive abnormal sound identification results all indicate abnormal sounds, and the average of the confidence levels in the K consecutive abnormal sound identification results is greater than a confidence level threshold, it is determined that an abnormal sound is generated in the ice making cavity. If a 1s sound signal is collected once, and K = 10, it is equivalent to collecting a 1s sound signal for 10 consecutive times. Of course, the length of the sound signal collected each time can be set according to actual needs, and K can also be set according to actual needs, which is not specifically limited here.

[0064] At step 320, the abnormal torque is identified according to the torque data, and an abnormal torque identification result is obtained.

[0065] In some embodiments, the torque data includes torque values at a plurality of time points; as Figure 5 As shown in FIG. 5, step 320 includes steps 510-540 as follows:

[0066] At step 510, a first reference torque value is determined according to torque values at last N time points in the torque data; the first reference torque value is used to reflect the torque condition at the last N time points.

[0067] In some embodiments, after the ice maker enters the ice making mode (starts ice making), the torque values of the target driving mechanism can be collected at a preset collection interval, and the collected torque values are stored in a cache. On this basis, all the torque values stored in the cache are taken as the torque data. It can be understood that the torque values at last N time points in the torque data are the latest N torque values collected. N can be set according to actual needs, for example, N is 10, 20, 100, 150, 200, etc., which is not limited here.

[0068] In some embodiments, the torque values at last N time points in the torque data can be calculated by mean value, and the obtained average torque value is taken as the first reference torque value. In other embodiments, a torque value at a specified percentile can be determined from the torque values at last N time points in the torque data, and taken as the first reference torque value. The specified percentile is, for example, 50%, 60%, 80%, etc.

[0069] At step 520, a second reference torque value is obtained; the second reference torque value is used to reflect the torque condition of the target driving mechanism of the ice maker under normal ice making condition.

[0070] In some embodiments, the output torque range of the target driving mechanism of the ice maker under normal ice making condition (in the ice making process and no ice jamming condition) can be stored in advance, and then a torque value is selected from the output torque range as the second reference torque value, or the middle torque value in the output torque range is taken as the second reference torque value, or the maximum torque value in the output torque range is taken as the second reference torque value.

[0071] In some embodiments, in the case that the number of torque values in the torque data is greater than N, the torque values at the first P time points before the first time point of the last N time points in the torque data can be averaged, and the obtained average torque value can be taken as the second reference torque value. Similarly, the torque value at a specified percentile among the torque values at the first P time points before the first time point of the last N time points in the torque data can also be determined as the second reference torque value.

[0072] In step 530, if the difference between the first reference torque value and the second reference torque value is greater than a target threshold, it is determined that the abnormal torque identification result is an identification result indicating that there is a torque abnormality in the last N time points.

[0073] If the difference between the first reference torque value and the second reference torque value is greater than the target threshold, it indicates that the first reference torque value is relatively large relative to the second reference torque value, and thus, it indicates that the torque value output by the target driving mechanism in the time period in which the N time points from which the first reference torque value is derived is located is relatively large, and it is thus determined that the abnormal torque identification result is an identification result indicating that there is a torque abnormality. The target threshold can be set according to actual needs, for example, the difference between the maximum output torque of the target driving mechanism in the ice jamming state and the minimum output torque of the target driving mechanism in the normal ice making state can be taken as the target threshold.

[0074] In step 540, if the difference between the first reference torque value and the second reference torque value is not greater than the target threshold, it is determined that the torque identification result is an identification result indicating that there is no torque abnormality in the last N time points; wherein N is an integer greater than 1, and the target threshold is greater than zero.

[0075] If the difference between the first reference torque value and the second reference torque value is not greater than the target threshold, it indicates that the difference between the first reference torque value and the second reference torque value is relatively small, and it is thus determined that the torque identification result is an identification result indicating that there is no torque abnormality in the last N time points.

[0076] Figure 6 is a flowchart of collecting torque values and identifying abnormal torque according to an embodiment of the present application, as shown in Figure 6As shown, the method comprises: after the ice maker enters the ice making mode, emptying the torque data in the cache, then collecting the torque value of the target driving mechanism according to the collection interval, and storing it in the cache, the collection interval can be set as needed, for example, the collection interval is 2s, 3s, 5s, etc.; then, it is judged whether the number of torque values in the cache reaches M, if not, the torque value is continuously collected; if the number of torque values in the cache reaches M, the latest N torque values in the M torque values in the cache are calculated by the mean value, to obtain the first reference torque value, and the earliest P torque values in the M torque values in the cache are calculated by the mean value, to obtain the second reference torque value, M=P+N; for example, if M=240, N=200, P=40, the mean value of the first 200 torque values in the 240 torque values can be taken as the first reference torque value, and the last 40 torque values can be taken as the second reference torque value; then, if the difference between the first reference torque value and the second reference torque value is greater than the target threshold value, it is determined that there is a torque abnormality in the ice maker. The target threshold value can be set according to actual needs, for example, the target threshold value is 350.

[0077] In some embodiments, in the process of collecting the torque value of the target driving mechanism in real time, after the number of torque values in the cache reaches M, if a torque value is newly collected, the torque value collected earliest is deleted from the cache, and the newly collected torque value is stored in the cache, so that the torque values stored in the cache are the M torque values collected most recently.

[0078] Step 330, determining the first identification result according to the abnormal sound identification result and the abnormal torque identification result.

[0079] In some embodiments, step 330 comprises: if the abnormal sound identification result indicates that the sound is abnormal, and the abnormal torque identification result indicates that the torque is abnormal, determining that the first identification result indicates that there is an ice jam in the ice maker; if the abnormal sound identification result indicates that the sound is normal, and / or, the abnormal torque identification result indicates that the torque is normal, determining that the first identification result indicates that there is no ice jam in the ice maker.

[0080] In the above embodiments, the sound signal and the torque data are used to jointly identify the ice jam, which can ensure the accuracy of the obtained first identification result and avoid the problem of misidentification when only the sound signal or only the torque data is used to identify the ice jam.

[0081] In some embodiments, the abnormal sound identification of the sound signal is performed by the abnormal sound classification model; for example, the abnormal sound classification model is a sound signal classification model trained by a sound signal training set, and the sound signal training set comprises a plurality of sound signal samples, each sound signal sample comprises a plurality of sound signal segments, and each sound signal segment is labeled with a sound type. Figure 7 As shown, before step 310, the method further comprises:

[0082] At step 710, a plurality of sample sound signals and sound labels corresponding to the sample sound signals are obtained, the plurality of sample sound signals including a sample sound signal collected in an interior of a sample ice maker when the sample ice maker is in an ice jamming state and a sample sound signal collected in the interior of the sample ice maker when the sample ice maker is in a normal ice making state, and the sound labels are used to indicate whether the sample ice maker from which the sample sound signal is derived is in the ice jamming state when the sample sound signal is collected.

[0083] At step 720, a sound feature of the sample sound signal is extracted by the abnormal sound classification model, and an abnormal sound classification is performed according to the sound feature, to obtain an abnormal sound classification result.

[0084] The abnormal sound classification model can be a machine learning model or a neural network model constructed by a neural network, which is not specifically limited herein. The extracted sound feature can be the Fbank feature or a vectorized representation of the sample sound signal.

[0085] The abnormal sound classification result is used to indicate whether the sample sound signal belongs to an abnormal sound. If it is predicted that the sample sound signal belongs to the abnormal sound, it indicates that it is recognized that the sample ice maker from which the sample sound signal is derived is in the ice jamming state or is in the ice jamming state during the process of collecting the sample sound signal. If it is predicted that the sample sound signal does not belong to the abnormal sound, it indicates that it is recognized that the sample ice maker from which the sample sound signal is derived is in the normal ice making state during the process of collecting the sample sound signal.

[0086] At step 730, a sound recognition loss is calculated according to the abnormal sound classification result and the sound label corresponding to the sample sound signal.

[0087] The sound recognition loss is used to reflect the difference between the state of the sample ice maker (the ice jamming state or the normal ice making state) reflected by the abnormal sound classification result and the state of the sample ice maker indicated by the sound label corresponding to the sample sound signal. In some embodiments, the difference between the abnormal sound classification result and the sound label corresponding to the sample sound signal can be calculated by a loss function to obtain the sound recognition loss, and the loss function can be an absolute value loss function, a mean square error loss function, etc., which is not specifically limited herein.

[0088] At step 740, parameters of the abnormal sound classification model are adjusted according to the sound recognition loss until a training end condition is reached.

[0089] The training end condition can be that the number of iterations of the abnormal sound classification model reaches a number threshold, and / or the sound recognition loss converges.

[0090] Through the training process as above, the abnormal sound classification model can effectively learn the features of the sample sound signals collected in the interior of the sample ice maker in the case of ice jamming of the sample ice maker and the features of the sample sound signals collected in the interior of the sample ice maker in the normal ice making state of the sample ice maker, so that the trained abnormal sound classification model can accurately use the sound signals to identify whether the sound signals are collected in the ice maker in the ice jamming state, that is, accurately identify whether the sound signals are abnormal sound.

[0091] In some embodiments, after step 140, the method further comprises: controlling the ice maker to enter a defrosting mode. In the defrosting mode, the ice layer formed in the ice making cavity is melted by the high-temperature refrigerant in the ice maker, so that a micro-fusion layer is formed between the ice layer and the inner wall of the ice making cavity, thereby eliminating the ice jamming state in the ice making cavity. In this way, continuous refrigeration in the case of ice jamming of the ice maker is avoided, so that the ice making efficiency is not affected.

[0092] In some embodiments, the processing performed by the ice maker in the defrosting mode includes: first, opening the electromagnetic valve to guide the high-temperature and high-pressure gaseous refrigerant discharged by the compressor into the evaporator to melt the ice blocks in the ice making cavity; then, closing the electromagnetic valve and controlling the compressor to stop, and then opening the water pump to make the liquid flow into the ice making cavity for water flushing; finally, closing the water pump and closing the motor, and the defrosting process ends. After the defrosting ends, the ice maker can be controlled to resume ice making.

[0093] In some embodiments, after detecting that the ice jamming condition exists in the ice maker, on the one hand, the ice maker is controlled to enter the defrosting mode to perform defrosting work to eliminate the ice jamming, and on the other hand, during the defrosting work, the state of the ice maker is marked as a frozen cylinder state (which can also be referred to as an ice jamming state), and during the state of the ice maker is marked as the frozen cylinder state, no ice jamming detection is performed (i.e., no ice jamming detection is performed according to the embodiment shown in Figure 1 In some embodiments, the ice maker is controlled to enter the defrosting mode to perform defrosting work to eliminate the ice jamming, and on the other hand, during the defrosting work, the state of the ice maker is marked as a frozen cylinder state (which can also be referred to as an ice jamming state), and during the state of the ice maker is marked as the frozen cylinder state, no ice jamming detection is performed (i.e., no ice jamming detection is performed according to the embodiment shown in Figure 1 In some embodiments, the duration of the defrosting work of the ice maker can be 10 minutes, but is not limited thereto.

[0094] Figure 8 is a schematic diagram of ice jamming detection according to an embodiment of the present application, as shown in Figure 8The ice jam detection device shown in the figure is used for ice jam identification on the ice falling detection signal, abnormal sound identification on the collected sound signal, and abnormal torque identification on the torque data. When ice jam is identified based on the ice falling detection signal, the ice maker is controlled to enter the defrosting mode to remove the ice jam. In addition, when abnormal sound is identified based on the sound signal and abnormal torque is identified based on the torque data, it is determined that there is ice jam in the ice maker. Then, the ice maker is controlled to enter the defrosting mode to remove the ice jam.

[0095] In the embodiment, the ice jam is identified based on the collected sound signal and the torque data of the target driving mechanism on the basis of the second identification result obtained by the ice jam identification on the ice falling detection signal to obtain the first identification result. When either the first identification result or the second identification result indicates that there is ice jam, it is determined that there is ice jam in the ice maker. In this way, the ice jam in the ice maker can be quickly detected. After the ice jam in the ice maker is detected, the ice maker enters the defrosting mode to automatically remove the ice jam state of the ice maker to restore the normal ice making state, thereby minimizing the impact of the ice jam in the ice maker.

[0096] In some embodiments, the method further includes: collecting a sound signal inside the ice maker when the ice maker is in a standby state; performing abnormal sound identification on the sound signal collected when the ice maker is in the standby state to obtain a third identification result; and generating external sound interference prompt information if the third identification result indicates that the sound is abnormal.

[0097] The standby state of the ice maker refers to a state in which the ice maker is turned on but does not perform specific operations (such as starting ice making). Since the ice maker is not started to make ice when the ice maker is in the standby state, the abnormal sound identified by the collected sound signal indicates that the abnormal sound in the sound signal is from the environment in which the ice maker is located. At this time, it is considered to be external interference, and therefore, external sound interference prompt information is generated to indicate that there is external abnormal sound in the external environment of the ice maker that affects ice jam identification.

[0098] In some embodiments, if it is detected that the sound collection device in the ice maker is abnormal (such as short circuit or open circuit), the sound collection device is marked as abnormal, and in the subsequent process, the sound signal is not collected by the sound collection device and the abnormal sound is not identified.

[0099] The device embodiments of the present application are described below, which can be used to execute the methods in the above embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the above method embodiments of the present application.

[0100] Figure 9 is a block diagram of an ice jam detection device according to an embodiment of the present application, as shown in Figure 9As shown, the ice jam detection apparatus comprises: an acquisition module 910 configured to acquire a sound signal collected inside the ice maker after the ice maker starts making ice, acquire torque data collected from a target driving mechanism, and acquire a falling ice detection signal collected in the ice maker; the target driving mechanism is configured to drive ice cubes made in an ice making cavity of the ice maker; a first identification module 920 configured to perform ice jam identification based on the sound signal and the torque data to obtain a first identification result; a second identification module 930 configured to perform ice jam identification based on the falling ice detection signal to obtain a second identification result; and an ice jam determination module 940 configured to determine that there is an ice jam in the ice maker if at least one of the first identification result and the second identification result indicates that there is an ice jam.

[0101] In some embodiments, the first identification module 920 comprises: an abnormal sound identification unit configured to perform abnormal sound identification on the sound signal to obtain an abnormal sound identification result; an abnormal torque identification unit configured to perform abnormal torque identification on the torque data to obtain an abnormal torque identification result; and a first identification result determination unit configured to determine the first identification result based on the abnormal sound identification result and the abnormal torque identification result.

[0102] In some embodiments, the abnormal sound identification on the sound signal comprises: performing abnormal sound identification on the sound signal by an abnormal sound identification model; and the ice jam detection apparatus further comprises:

[0103] a sample acquisition module configured to acquire a plurality of sample sound signals and sound labels corresponding to the sample sound signals, the plurality of sample sound signals comprising sample sound signals collected inside a sample ice maker when the sample ice maker has an ice jam and sample sound signals collected inside the sample ice maker when the sample ice maker is in a normal ice making state; and the sound label is configured to indicate whether the sample ice maker from which the sample sound signal is derived has an ice jam when the corresponding sample sound signal is collected;

[0104] a classification module configured to extract a sound feature of the sample sound signal by the abnormal sound identification model, and perform abnormal sound classification based on the sound feature to obtain an abnormal sound classification result;

[0105] a loss calculation module configured to calculate a sound identification loss based on the abnormal sound classification result and the sound label corresponding to the sample sound signal;

[0106] a parameter adjustment module configured to adjust parameters of the abnormal sound identification model based on the sound identification loss until a training end condition is reached.

[0107] In some embodiments, the torque data includes torque values at a plurality of time points; the abnormal torque identification unit is configured to: determine a first reference torque value according to torque values at last N time points in the torque data; the first reference torque value is used to reflect torque conditions of the last N time points; obtain a second reference torque value; the second reference torque value is used to reflect torque conditions of the target driving mechanism under normal ice making conditions of the ice maker; if a difference between the first reference torque value and the second reference torque value is greater than a target threshold, determine that the abnormal torque identification result is an identification result indicating that there is a torque abnormality at the last N time points; if the difference between the first reference torque value and the second reference torque value is not greater than the target threshold, determine that the torque identification result is an identification result indicating that there is no torque abnormality at the last N time points; N is an integer greater than 1; the target threshold is greater than zero.

[0108] In some embodiments, the first identification result determination unit is configured to: if the abnormal sound identification result indicates a sound abnormality, and the abnormal torque identification result indicates a torque abnormality, determine that the first identification result indicates that there is an ice jam situation in the ice maker; if the abnormal sound identification result indicates a sound normality, and / or, the abnormal torque identification result indicates a torque normality, determine that the first identification result indicates that there is no ice jam situation in the ice maker.

[0109] In some embodiments, the second identification module 930 is configured to: if it is determined according to the ice drop detection signal that a time length from a last time when ice drop is detected reaches a first target time length, determine that the second identification result is an identification result indicating that there is an ice jam situation; if it is determined according to the ice drop detection signal that a continuous time length during which no ice drop is detected after the ice maker first enters the ice making mode reaches a second target time length, determine that the second identification result is an identification result indicating that there is an ice jam situation; the second target time length is greater than the first target time length.

[0110] In some embodiments, the ice jam detection device further includes: a defrosting module configured to control the ice maker to enter a defrosting working mode.

[0111] In some embodiments, the ice jam detection device further includes: a first acquisition module configured to start to acquire torque data of the target driving mechanism and start to perform ice drop detection in response to the ice maker entering the ice making mode; and a second acquisition module configured to start to acquire sound signals inside the ice maker in response to a time length during which the ice maker enters the ice making mode reaching a third target time length.

[0112] In some embodiments, the ice jam detection device further includes: a third acquisition module configured to acquire sound signals inside the ice maker when the ice maker is in a standby state; a third identification module configured to perform abnormal sound identification on the sound signals acquired when the ice maker is in the standby state to obtain a third identification result; and a prompt module configured to generate external sound interference prompt information if the third identification result indicates a sound abnormality.

[0113] Figure 10 is a block diagram of an ice maker according to an embodiment of the present application. The ice maker can include a processor 1010 and a memory 1020, the memory 1020 storing computer readable instructions, the computer readable instructions being executed by the processor 1010 to implement the method in any of the above method embodiments. In addition, the ice maker further includes a target driving mechanism and an ice making cavity, a sound collecting device and an ice drop detection sensor, Figure 10 are not shown in the present application.

[0114] The processor 1010 can include one or more processing cores. The processor 1010 connects various parts in the entire ice maker through various interfaces and lines, and performs various functions of the ice maker and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 1020, and calling data stored in the memory 1020. Alternatively, the processor 1010 can be implemented in at least one of a hardware form of a digital signal processing (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA). The processor 1010 can be integrated with a combination of one or more of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU is mainly used to process operating systems, user interfaces and application programs, etc.; the GPU is used to render and draw display content; and the modem is used to process wireless communication. It can be understood that the above-mentioned modem can also not be integrated into the processor 1010, but can be realized by a separate communication chip.

[0115] The memory 1020 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 1020 can include a storage program area and a storage data area, wherein the storage program area can store instructions for implementing an operating system, instructions for implementing at least one function, instructions for implementing each of the above method embodiments, etc. The storage data area can also store data generated by the ice maker during use, etc.

[0116] The present application also provides a computer readable storage medium having computer readable instructions stored thereon, the computer readable instructions being executed by a processor to implement the method in any of the above method embodiments.

[0117] The computer-readable storage medium can be an electronic, magnetic, optical, or other physical storage device that stores executable computer program instructions. Examples of computer-readable storage media include, but are not limited to, a Random Access Memory (RAM), a flash memory, and others. The computer-readable storage medium can optionally comprise a non-transitory computer-readable medium. The computer-readable storage medium has a storage space to store computer-readable instructions to perform any of the method steps described above. The computer-readable instructions can be read or written to the computer program product by one or more computer program products. The computer-readable instructions can be compressed or packaged in a suitable form.

[0118] According to an aspect of the embodiments of the present application, a computer program product is provided, which comprises computer readable instructions stored in a computer readable storage medium. A processor of a computer device reads the computer readable instructions from the computer readable storage medium, and the processor executes the computer readable instructions to cause the computer device to perform the method in any of the embodiments described above.

[0119] It should be noted that although several modules or units of devices for action execution are mentioned in the foregoing detailed description, such division is not mandatory. In fact, according to the embodiments of the present application, features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, features and functions of one module or unit described above can be further divided into a plurality of modules or units.

[0120] From the above description of the embodiments, those skilled in the art will readily appreciate that the example embodiments described herein can be implemented by software and / or by hardware and / or by a combination of software and hardware. The embodiments of the present application as described above can be embodied in a software product that includes instructions to make a computer device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) perform the methods according to the embodiments of the present application. The software product can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB, a mobile hard disk, etc.) or on a network, and includes a plurality of instructions to make a computer device perform the methods according to the embodiments of the present application.

[0121] Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the embodiments disclosed herein. It is intended that the present application cover any and all variations of the present application comprising features of the application broadly falling within the scope of the general inventive concept. Such variations can include but are not limited to those specifically recited in the claims prepared by and on behalf of the inventors.

[0122] It is to be understood that the application is not limited to the precise construction already described above and shown in the drawings, and that various modifications and changes can be made by those skilled in the art without departing from the scope of the application. The scope of the application should only be limited by the claims appended hereto.

Claims

1. A method for detecting carbohydrate, characterized in that, include: After the ice maker starts making ice, the system acquires sound signals collected inside the ice maker, torque data collected from the target drive mechanism, and ice falling detection signals collected inside the ice maker. The target drive mechanism is used to drive and output the ice blocks made in the ice-making chamber of the ice maker. The sound signals collected inside the ice maker are the sound signals inside the ice-making chamber of the ice maker. The process of identifying ice jams in the ice maker based on the sound signal and the torque data to obtain a first identification result includes: identifying abnormal sounds in the sound signal to obtain an abnormal sound identification result; identifying abnormal torques in the torque data to obtain an abnormal torque identification result; if the abnormal sound identification result indicates an abnormal sound and the abnormal torque identification result indicates an abnormal torque, then the first identification result indicates that there is an ice jam in the ice maker; if the abnormal sound identification result indicates a normal sound and / or the abnormal torque identification result indicates a normal torque, then the first identification result indicates that there is no ice jam in the ice maker. Based on the ice-fall detection signal, ice jam identification is performed to obtain a second identification result; If at least one of the first and second identification results indicates that there is ice jam, it is determined that there is ice jam in the ice maker.

2. The method according to claim 1, characterized in that, The step of identifying abnormal sounds in the sound signal includes: identifying abnormal sounds in the sound signal using an abnormal sound classification model; Before performing abnormal sound recognition on the sound signal to obtain the abnormal sound recognition result, the method further includes: Multiple sample sound signals and corresponding sound tags for each sample sound signal are acquired. The multiple sample sound signals include sample sound signals collected inside the sample ice maker when ice jamming occurs, and sample sound signals collected inside the sample ice maker when the sample ice maker is in normal ice-making mode. The sound tags are used to indicate whether ice jamming occurs in the sample ice maker from which the corresponding sample sound signal originates when the sample sound signal is collected. The abnormal sound classification model extracts the sound features of the sample sound signal, and performs abnormal sound classification based on the sound features to obtain the abnormal sound classification result; Calculate the sound recognition loss based on the abnormal sound classification results and the sound labels corresponding to the sample sound signals; The parameters of the abnormal sound classification model are adjusted based on the sound recognition loss until the training termination condition is met.

3. The method according to claim 1, characterized in that, The torque data includes torque values ​​at multiple time points; The step of identifying abnormal torque based on the torque data to obtain abnormal torque identification results includes: A first reference torque value is determined based on the torque values ​​at the last N time points in the torque data; the first reference torque value is used to reflect the torque situation at the last N time points. Obtain a second reference torque value; the second reference torque value is used to reflect the torque of the target drive mechanism of the ice maker under normal ice-making conditions; If the difference between the first reference torque value and the second reference torque value is greater than the target threshold, the abnormal torque identification result is determined to be an identification result indicating that there is an abnormal torque at the last N time points; If the difference between the first reference torque value and the second reference torque value is not greater than the target threshold, the torque identification result is determined to be an identification result indicating that there is no torque abnormality at the last N time points; Where N is an integer greater than 1, and the target threshold is greater than zero.

4. The method according to claim 1, characterized in that, The step of identifying ice-stuck points based on the ice-falling detection signal to obtain a second identification result includes: If the ice-fall detection signal determines that the time elapsed since the last ice-fall detection has reached the first target time, then the second identification result is determined to be an identification result indicating that there is ice jamming. If, based on the ice-falling detection signal, it is determined that the duration for which no ice falls are detected after the first entry into the ice-making mode reaches the second target duration, the second identification result is determined to be an identification result indicating that there is ice jamming; the second target duration is longer than the first target duration.

5. The method according to any one of claims 1 to 4, characterized in that, If at least one of the first and second identification results indicates that ice is stuck in the ice maker, after determining that ice is stuck in the ice maker, the method further includes: Control the ice maker to enter defrosting mode.

6. The method according to any one of claims 1 to 4, characterized in that, The method further includes: In response to the ice maker entering the ice-making mode, the torque data of the target drive mechanism is collected and the ice-fall detection is started. In response to the ice maker entering ice-making mode for a duration that reaches the third target duration, the sound signal inside the ice maker is collected.

7. The method according to any one of claims 1 to 4, characterized in that, The method further includes: When the ice maker is in standby mode, the sound signal inside the ice maker is collected; Abnormal sound recognition is performed on the sound signals collected when the ice maker is in standby mode to obtain a third recognition result; If the third recognition result indicates an abnormal sound, an external sound interference warning message is generated.

8. An ice maker, characterized in that, include: processor; A memory storing computer-readable instructions that, when executed by the processor, implement the method as described in any one of claims 1-7.

9. A computer program product, characterized in that, It includes computer-readable instructions that, when executed by a processor, implement the method as described in any one of claims 1-7.

Images