Refrigerator diagnostic method and refrigerator

Abstract

A refrigerator and a refrigerator diagnostic method utilizing artificial intelligence (AI) algorithms and / or machine learning algorithms in a 5G environment connected for the Internet of Things are disclosed. The refrigerator diagnostic method determines the installation status of the refrigerator based on the power value of the compressor and the rotational speed of the cooling fan equipped in the refrigerator when the operating time after the initial installation of the refrigerator is below a set value, and determines whether the refrigerator is malfunctioning and its cleaning status based on the power value of the compressor and the rotational speed of the cooling fan when the operating time after the initial installation of the refrigerator exceeds the set value.

Description

Technology Field

[0001] The embodiments relate to a refrigerator diagnostic method and a refrigerator, and more specifically, to a refrigerator diagnostic method and a refrigerator capable of diagnosing operational failure or cleaning failure of a refrigerator. Background Technology

[0002] The content described in this section merely provides background information regarding the embodiments and does not constitute prior art.

[0003] Looking at recent trends in technological development, there is a demand for the development of features that allow refrigerators to independently detect operational or cleaning failures in order to provide more convenient functions to users.

[0004] Korean published patent 10-2016-0094739 discloses a cleaning time notification device for a refrigerator. The cleaning time notification device of the prior art includes a sensor unit that measures the amount of dust accumulated in the machine compartment of the refrigerator, and a control unit that determines the cleaning time based on the amount of dust input from the sensor unit.

[0005] In the case of refrigerators, user convenience is further enhanced if the device can self-diagnose and notify the user of issues such as incorrect installation, malfunctions during long-term use, or poor cleaning. Therefore, technological development in this regard is required. The problem to be solved

[0006] In the embodiment, a method is proposed to determine the cleaning status of a machine room, notify the user of the cleaning time of the machine room, or predict the cleaning time of the machine room.

[0007] In the embodiment, a method is proposed to identify the operating status of the compressor and cooling fan and, based on this, notify the user of a refrigerator malfunction.

[0008] In the embodiment, a refrigerator diagnostic method is proposed that measures the cooling fan rotation speed and compressor power, and determines the installation status of the refrigerator based on these measurements.

[0009] The technical problems that the embodiments aim to solve are not limited to those mentioned above, and other unmentioned technical problems will be clearly understood by those skilled in the art from the description below. means of solving the problem

[0010] To achieve the aforementioned objectives, a refrigerator diagnostic method according to one embodiment can determine the installation status of a refrigerator based on the power value of a compressor equipped in the refrigerator and the rotational speed of a cooling fan equipped in the refrigerator when the operating time after the initial installation of the refrigerator is less than or equal to a set value, and determine whether there is an operational failure and the cleaning status of the refrigerator based on the power value of the compressor and the rotational speed of the cooling fan when the operating time after the initial installation of the refrigerator exceeds a set value.

[0011] The refrigerator further includes a condenser connected to a compressor and cooled by a cooling fan, and a control unit that controls the operation of the compressor, the cooling fan, and the condenser, and the control unit may determine the installation status, operational failure, and cleanliness status of the refrigerator.

[0012] The process of determining the installation status of the refrigerator may include a step of measuring the power of the compressor, a step of checking whether the measured power of the compressor is greater than a first reference value, a step of measuring the rotational speed of the cooling fan when the measured power of the compressor is greater than the first reference value, and a step of checking whether the measured rotational speed of the cooling fan is less than a second reference value.

[0013] The process of determining the installation status of the refrigerator may further include a step of notifying the user of a defect in the installation status of the refrigerator if the measured rotational speed of the cooling fan is less than a second reference value.

[0014] The refrigerator may be equipped with a machine room in which a compressor, a cooling fan, and a condenser are installed.

[0015] The control unit may determine at least one of whether the cooling fan is malfunctioning or the cleanliness of the machine room.

[0016] The process of determining whether the refrigerator is malfunctioning and its cleaning status may include a step of calculating a compressor performance index, a step of checking whether the compressor performance index is greater than a third reference value, a step of measuring the rotational speed of the cooling fan if the compressor performance index is greater than the third reference value, a step of checking whether the measured rotational speed of the cooling fan is greater than a fourth reference value, a step of calculating a cooling fan performance index if the measured rotational speed of the cooling fan is greater than the fourth reference value, and a step of checking whether the cooling fan performance index is less than a fifth reference value.

[0017] The compressor performance indicator may be defined as the current power of the compressor / the power of the compressor at the time of the refrigerator's initial installation.

[0018] The cooling fan performance indicator may be defined as the current rotational speed of the cooling fan divided by the rotational speed of the cooling fan at the time of the refrigerator's initial installation.

[0019] The process of determining whether the refrigerator is malfunctioning and its cleaning status may further include a step of notifying the user of the refrigerator's malfunction if the measured rotational speed of the cooling fan is less than or equal to the fourth reference value.

[0020] The process of determining whether the refrigerator is malfunctioning and its cleaning status may further include a step of notifying the user that the time for cleaning the machine room has been reached when the cooling fan performance indicator is smaller than the fifth reference value.

[0021] The process of determining whether the refrigerator is malfunctioning and its cleaning status may further include a step of predicting the cleaning time of the machine room when the cooling fan performance indicator is greater than or equal to the fifth standard value.

[0022] The predicted value for the cleaning time of the machine room may be derived by learning according to an Artificial Intelligence model based on compressor performance indicators and cooling fan performance indicators.

[0023] The control unit is connected to a processor that derives a predicted value, and the processor may derive a predicted value by receiving compressor performance indicators and cooling fan performance indicators as input, while performing learning according to an artificial intelligence model.

[0024] The predicted value may be a value under different conditions for at least one of the compressor performance indicator or cooling fan performance indicator among the learning modes according to the artificial intelligence model.

[0025] A refrigerator according to one embodiment includes a compressor, a condenser connected to the compressor, a cooling fan for cooling the condenser, and a control unit for controlling the operation of the compressor, the cooling fan, and the condenser. The control unit may determine the installation status of the refrigerator based on the power value of the compressor and the rotational speed of the cooling fan when the operating time after the initial installation of the refrigerator is less than or equal to a set value, and determine whether the refrigerator is malfunctioning and the cleaning status based on the power value of the compressor and the rotational speed of the cooling fan when the operating time after the initial installation of the refrigerator exceeds the set value.

[0026] The refrigerator is equipped with a machine room in which a compressor, a cooling fan, and a condenser are installed, and the control unit may determine at least one of whether the cooling fan is malfunctioning or the cleanliness of the machine room.

[0027] The control unit predicts the cleaning time of the machine room, and the predicted value for the cleaning time of the machine room may be derived by learning according to an artificial intelligence model based on compressor performance indicators and cooling fan performance indicators. Effects of the invention

[0028] In the embodiment, the refrigerator itself detects the installation status of the refrigerator and notifies the user if the installation status is poor, thereby increasing user convenience.

[0029] In the embodiment, user convenience can be enhanced by the refrigerator itself notifying the user of a malfunction.

[0030] In the embodiment, the refrigerator can increase user convenience by determining the cleaning time of the machine room itself or predicting the cleaning time and notifying the user. Brief explanation of the drawing

[0031] FIG. 1 is a drawing for explaining a refrigerator according to one embodiment. FIG. 2 is a schematic diagram illustrating the structure of a refrigerator according to one embodiment. Figure 3 is a graph showing the change in compressor power over time according to one embodiment. Figure 4 is a graph showing the change in the rotational speed of a cooling fan with respect to duty according to one embodiment. FIG. 5 is a graph showing the change in the rotational speed of the cooling fan over the refrigerator installation period according to one embodiment. Figure 6 is a graph showing the change in the rotational speed of the cooling fan over the refrigerator installation period according to another embodiment. Figure 7 is a graph showing the change in compressor power over the refrigerator installation period according to one embodiment. FIG. 8 is a graph showing the change in compressor power over the refrigerator installation period according to another embodiment. FIG. 9 is a flowchart illustrating a refrigerator diagnostic method according to one embodiment. FIG. 10 is a flowchart illustrating a refrigerator diagnostic method according to another embodiment. FIG. 11 is a diagram illustrating an artificial intelligence neural network according to one embodiment. Specific details for implementing the invention

[0032] Hereinafter, embodiments will be described in detail with reference to the attached drawings. Since embodiments may be subject to various modifications and may take various forms, specific embodiments are illustrated in the drawings and described in detail in the text. However, this is not intended to limit the embodiments to the specific disclosed forms, and it should be understood that they include all modifications, equivalents, and substitutions that fall within the spirit and scope of the embodiments.

[0033] Terms such as "first," "second," etc., may be used to describe various components, but said components should not be limited by said terms. These terms are used for the purpose of distinguishing one component from another. Furthermore, terms specifically defined in consideration of the configuration and operation of the embodiments are intended only to describe the embodiments and do not limit the scope of the embodiments.

[0034] In the description of the embodiments, where it is stated that an element is formed "on or under," the terms "on or under" include both cases where two elements are in direct contact with each other and cases where one or more other elements are placed between the two elements to form the element indirectly. Furthermore, when expressed as "on or under," the meaning may include not only the upward direction but also the downward direction relative to a single element.

[0035] Additionally, relational terms such as "upper / upper / above" and "lower / lower / below" used below may be used to distinguish one entity or element from another, without necessarily requiring or implying any physical or logical relationship or order between such entities or elements.

[0036] FIG. 1 is a drawing for explaining a refrigerator according to one embodiment. FIG. 2 is a schematic diagram for explaining the structure of a refrigerator according to one embodiment.

[0037] The refrigerator may be equipped with a compressor (110), a condenser (130), an expansion device (150), an evaporator (160), a cooling fan (120), and a control unit (140). The refrigerator of the embodiment can make the interior, that is, the internal space of the refrigerator where food, etc. is stored, a low temperature state below the ambient temperature by operating a refrigeration cycle. The refrigerator of the embodiment can implement a refrigeration cycle using a refrigerant that undergoes a phase change.

[0038] The compressor (110), condenser (130), expansion device (150), and evaporator (160) are connected to each other by piping, and the refrigerant can flow through the compressor (110), condenser (130), expansion device (150), and evaporator (160) by circulating through the piping.

[0039] The compressor (110) compresses the refrigerant, which is mostly in a gaseous state, and discharges it at high temperature and high pressure. The refrigerant discharged from the compressor (110) can flow into the condenser (130).

[0040] The condenser (130) is connected to the compressor (110) by piping, and the refrigerant flowing into the condenser (130) releases heat to the outside and condenses into a liquid, and the refrigerant can be discharged from the condenser (130) in a state where most of it is liquid.

[0041] The expansion device (150) is connected to the condenser (130) via piping and can expand or throttle the refrigerant flowing in from the condenser (130) to bring it to a saturated state with reduced temperature and pressure.

[0042] The evaporator (160) is connected to the expansion device (150) by piping, and at least a portion of its surface is positioned inside the tank to absorb heat from inside the tank.

[0043] The low-temperature refrigerant discharged from the expansion device (150) absorbs heat in the evaporator (160) and undergoes vaporization, i.e., evaporation, and is discharged from the evaporator (160) in a state where most of it is gas and can be fed back into the compressor (110).

[0044] A cooling fan (120) is positioned to face the condenser (130) and can cool the condenser (130). That is, the cooling fan (120) blows air into the condenser (130) to cool the refrigerant flowing inside the condenser (130), thereby causing the refrigerant to condense into a low-temperature liquid state.

[0045] The control unit (140) is electrically connected to the compressor (110), condenser (130), expansion device (150), evaporator (160), and cooling fan (120) and can control their operation. In particular, the control unit (140) can operate or stop the operation of the compressor (110) and the cooling fan (120).

[0046] Meanwhile, the control unit (140) may be connected to a processor (170). The processor (170) may perform learning according to an artificial intelligence model to derive, for example, a predicted value for the cleaning time of the machine room (10). The artificial intelligence model learning is described in detail below.

[0047] Referring to FIG. 2, the refrigerator may be equipped with a machine room (10). In addition to the evaporator (160) that exchanges heat with the interior, most of the components of the refrigerator described above may be provided in the machine room (10), which is a space separated from the interior.

[0048] For example, the machine room (10) may be equipped with the compressor (110), the cooling fan (120), and the condenser (130). Additionally, depending on the structure of the refrigerator, an expansion device (150) may also be provided in the machine room (10).

[0049] Considering the function and structure of the refrigerator, the machine room (10) may be provided as a space with a relatively small volume. In the machine room (10), the aforementioned devices, the piping connecting these devices, and the wiring for supplying power to these devices or communicating with the control unit (140) may be arranged in a small space.

[0050] As a result, the machine room (10) can have a very complex structure. Also, since the cooling fan (120) is operating, external foreign substances such as dust can be actively introduced into the machine room (10) with a complex structure by the cooling fan (120).

[0051] Foreign substances that have entered can accumulate in large quantities in the machine room (10) with a complex structure. In particular, foreign substances can accumulate in large quantities on the blade surface of the cooling fan (120), the surface of the condenser (130) where cooling fins are formed, and on the surfaces of the pipes and wiring.

[0052] Foreign substances accumulated in the machine room (10) can increase the fire rate and reduce the performance of the refrigerator.

[0053] For example, foreign matter accumulated in the machine room (10) can cause a tracking phenomenon and become the cause of a fire. A tracking phenomenon refers to a situation where current flows along the surface of an electrical product where foreign matter has accumulated, causing an electrical short circuit in that area and resulting in a fire.

[0054] Foreign substances accumulated in the machine room (10) may scatter when the cooling fan (120) operates, increasing air flow resistance, and due to the increase in air flow resistance, the rotational speed of the cooling fan (120), which has constant power consumption, may decrease. Due to the decrease in the rotational speed of the cooling fan (120), the cooling performance of the condenser (130) may decrease.

[0055] In addition, due to the structure in which cooling fins are formed, a large amount of foreign matter accumulates on the surface of the condenser (130), and this foreign matter hinders heat exchange between the condenser (130) and the outside, which may reduce the cooling performance of the condenser (130).

[0056] Due to the reduction in the cooling performance of the condenser (130), the temperature of the refrigerant inside the condenser (130) may increase overall. When the temperature of the refrigerant in the condenser (130) increases, the pressure of the refrigerant also increases.

[0057] As a result, the compressor (110) has to do more work to increase the temperature and pressure of the refrigerant flowing into the condenser (130), and accordingly, the power of the compressor (110), that is, the power consumption of the compressor (110), increases.

[0058] Therefore, in order to prevent fire and to prevent a decrease in the performance of the refrigerator, cleaning of the machine room (10) is required. In the embodiment, a refrigerator diagnostic method is provided that determines the cleaning status of the machine room (10), notifies the user of the cleaning time of the machine room (10), or predicts the cleaning time of the machine room (10).

[0059] In addition, the embodiment provides a refrigerator diagnostic method that identifies the operating status of the compressor (110) and the cooling fan (120) and notifies the user of a refrigerator malfunction based on this.

[0060] The refrigerator can operate normally under proper installation conditions. For example, the machine room (10) of the refrigerator is appropriately installed to have a distance greater than a certain distance from the outer wall, and the manufacturer of the refrigerator can provide the user with a guide on this distance.

[0061] If the distance between the refrigerator and the outer wall is closer than the guide, the performance of the refrigerator may be reduced. For example, if the distance is closer than the guide, heat dissipation failure of the condenser (130) may occur, or the performance of the cooling fan (120) may be degraded. The resulting phenomenon may have a tendency similar to that of foreign matter accumulating in the machine room (10).

[0062] If the above separation distance is closer than the guide, the heat discharged from the condenser (130) cannot be smoothly discharged outside the machine room (10), so heat dissipation failure of the condenser (130) may occur compared to normal operation.

[0063] Due to poor heat dissipation of the condenser (130), as described above, the work of the compressor (110) increases, and accordingly, the power of the compressor (110) increases.

[0064] Additionally, if the above separation distance is closer than the guide, the degree of blockage of the machine room (10) increases, making it difficult to smoothly enter and exit the machine room (10). Consequently, the air flow resistance increases, which can reduce the rotational speed of the cooling fan (120) with constant power consumption. Due to the reduction in the rotational speed of the cooling fan (120), the cooling performance of the condenser (130) may decrease.

[0065] Accordingly, the embodiment provides a refrigerator diagnostic method that measures the rotational speed of the cooling fan (120) and the power of the compressor (110), and determines the installation status of the refrigerator based on this.

[0066] FIG. 3 is a graph showing the change in power of the compressor (110) over time according to one embodiment. FIG. 3 shows the results of testing the change in power of the compressor (110) of a refrigerator that is installed and used for a long period of time.

[0067] In Figure 3, the vertical axis represents the power of the compressor (110) in watts (W), and the horizontal axis represents the usage time of the refrigerator in seconds.

[0068] In the embodiment, to satisfy the cooling capacity set for each refrigerator, the amount of work performed by the compressor (110) may vary over time, and thus the power (power consumption) of the compressor (110) may vary. Additionally, as shown in FIG. 3, the compressor (110) may operate intermittently so that the compressor (110) operates, stops, and then operates again.

[0069] Graph 1 shows the power of the compressor (110) when the cleaning condition of the machine room (10) is good, and Graph 2 shows the power of the compressor (110) when the cleaning condition of the machine room (10) is poor and cleaning is required.

[0070] When the machine room (10) is in poor condition, compared to when the cleaning condition is good, it can be seen that the compressor (110) has a longer operating time and a larger power consumption during the compressor (110) operating time. Therefore, when the machine room (10) is in poor condition, compared to when the cleaning condition is good, the power consumption of the compressor (110) increases overall.

[0071] As described above, if the machine room (10) is not clean, heat dissipation from the condenser (130) is poor, and the temperature and pressure of the refrigerant increase. Consequently, the compressor (110) must perform more work to increase the temperature and pressure of the refrigerant flowing into the condenser (130), and accordingly, the power of the compressor (110), that is, the power consumption of the compressor (110), increases.

[0072] FIG. 4 is a graph showing the change in the rotational speed of the cooling fan (120) according to one embodiment with respect to duty. FIG. 4 shows the results of testing the change in the rotational speed of the cooling fan (120) of a refrigerator that is installed and used for a long period of time.

[0073] In the embodiment, the cooling fan (120) generally has a constant power consumption, i.e., a rated power, and the rotational speed may vary from the rated power.

[0074] In FIG. 4, the vertical axis represents the rotational speed of the cooling fan (120) in RPM units, and the horizontal axis represents the duty of the cooling fan (120) in % units. Since the cooling fan (120) also operates intermittently, the operating time of the cooling fan (120) can be represented as a duty cycle.

[0075] Duty refers to the ratio of the operating time of the cooling fan (120) to the total time. For example, if the cooling fan (120) operates for 30 minutes and stops operating for 30 minutes for a total of 1 hour, the duty of the cooling fan (120) is 50%. As can be seen in FIG. 4, as the duty increases, the rotational speed of the cooling fan (120) can increase.

[0076] Graph 3 shows the rotation speed of the cooling fan (120) when the cleaning condition of the machine room (10) is good, and Graph 2 shows the rotation speed of the cooling fan (120) when the cleaning condition of the machine room (10) is poor and cleaning is required.

[0077] As shown in FIG. 4, when the machine room (10) is in poor condition, compared to when the cleaning condition is good, it can be seen that the cooling fan (120) rotation speed is smaller at the same duty cycle.

[0078] As described above, if the cleaning condition of the machine room (10) is poor, foreign matter accumulated in the machine room (10) may be scattered when the cooling fan (120) is operating, increasing the air flow resistance, and due to the increase in air flow resistance, the rotational speed of the cooling fan (120), which has constant power consumption, may decrease.

[0079] As a result of reviewing with reference to FIGS. 3 and FIGS. 4, it can be seen that if the cleaning condition of the machine room (10) is poor, the power of the compressor (110) increases and the rotational speed of the cooling fan (120) decreases. Therefore, in the embodiment, if the power of the compressor (110) is measured and it is greater than a certain reference value, and the rotational speed of the cooling fan (120) is measured and it is less than a certain reference value, it can be determined that the cleaning of the machine room (10) is poor.

[0080] FIG. 5 is a graph showing the change in the rotational speed of the cooling fan (120) over the refrigerator installation period according to one embodiment. In FIG. 5 and FIG. 6 described below, the vertical axis represents the rotational speed of the cooling fan (120) in RPM units, and the horizontal axis represents the installation period of the refrigerator.

[0081] Referring to FIG. 5, when the refrigerator is operated for a long time, as foreign matter accumulates in the machine room (10), the rotation speed of the cooling fan (120) may decrease as indicated by the arrow.

[0082] That is, it can be seen that the cooling fan (120) operates stably at an initial RPM, but as foreign matter accumulates in the machine room (10), the RPM gradually decreases. At this time, when the RPM at which cooling performance begins to decline and the point at which cooling performance declines are reached, cleaning of the machine room (10) is required.

[0083] FIG. 6 is a graph showing the change in the rotational speed of the cooling fan (120) over the refrigerator installation period according to another embodiment.

[0084] In FIG. 6, it can be seen that when the installation period exceeds the hidden line, the rotational speed of the cooling fan (120) rapidly decreases to near 0 or to 0. This is because the cooling fan (120) has stopped operating due to a broken power cable or other reasons, or the rotational speed has rapidly decreased.

[0085] Therefore, by detecting a sudden decrease in the rotational speed of the cooling fan (120), it is possible to detect operational failures caused by a broken wire of the cooling fan (120).

[0086] As a result of reviewing with reference to FIGS. 5 and FIGS. 6, if the rotational speed of the cooling fan (120) becomes smaller than a certain reference value, it can be determined that the operation of the cooling fan (120) is poor or that the machine room (10) is poorly cleaned.

[0087] FIG. 7 is a graph showing the change in compressor (110) power over the refrigerator installation period according to one embodiment. In FIG. 7 and FIG. 8 described below, the vertical axis represents the compressor (110) power, and the horizontal axis represents the refrigerator installation period.

[0088] Referring to Fig. 7, when the refrigerator is operated for a long time, as foreign matter accumulates in the machine room (10), the power of the compressor (110) may increase as indicated by the arrow.

[0089] That is, the compressor (110) operates stably with initial power, but as foreign matter accumulates in the machine room (10), the power gradually increases. At this time, when the power at which cooling performance begins to decline and the point at which cooling performance declines are reached, cleaning of the machine room (10) is required.

[0090] Meanwhile, it can be seen that the power of the compressor (110) increases, and at some point, the power of the compressor (110) decreases rapidly, as shown by the arrow.

[0091] This indicates a case where the compressor (110) is tripped and the operation of the compressor (110) is stopped in order to protect the motor equipped in the compressor (110) as the power of the compressor (110) continues to increase and the compressor (110) is overloaded.

[0092] FIG. 8 is a graph showing the change in compressor (110) power over the refrigerator installation period according to another embodiment.

[0093] In FIG. 8, it can be seen that when the installation period exceeds the silver wire, the power of the compressor (110) increases rapidly and generally maintains a constant value. This is because the cooling fan (120) stops operating due to a broken power cable or a rapid decrease in rotational speed.

[0094] That is, because the cooling fan (120) does not operate, the temperature and pressure of the condenser (130) increase rapidly, and accordingly, the work of the compressor (110) increases to cope with the increased temperature and pressure of the condenser (130). In other words, due to the poor heat dissipation of the condenser (130), as described above, the work of the compressor (110) increases, and accordingly, the power of the compressor (110) increases.

[0095] As a result of reviewing with reference to FIGS. 7 and FIGS. 8, if the power of the compressor (110) exceeds a certain reference value, it can be determined that the operation of the cooling fan (120) is poor or that the machine room (10) is poorly cleaned.

[0096] Based on the results reviewed above, the refrigerator diagnostic method is explained in detail below.

[0097] In the embodiment, the control unit (140) can determine the installation status, operational failure, and cleaning status of the refrigerator.

[0098] To this end, the control unit (140) can measure the power of the compressor (110) and the rotational speed of the cooling fan (120). For example, the control unit (140) can measure the power of the compressor (110) and the rotational speed of the cooling fan (120) through sensors provided in the compressor (110) and the cooling fan (120). Since this is a technical matter obvious to a person skilled in the art, a detailed explanation is omitted.

[0099] In an embodiment, when the operating time after the initial installation of the refrigerator is less than or equal to a set value, the control unit (140) can determine the installation status of the refrigerator based on the power value of the compressor (110) provided in the refrigerator and the rotational speed of the cooling fan (120) provided in the refrigerator.

[0100] In an embodiment, when the operating time after the initial installation of the refrigerator exceeds a set value, the control unit (140) can determine whether the refrigerator is malfunctioning and the cleaning status based on the power value of the compressor (110) and the rotational speed of the cooling fan (120).

[0101] FIG. 9 is a flowchart illustrating a refrigerator diagnostic method according to one embodiment. FIG. 9 illustrates a method for determining the installation status of a refrigerator.

[0102] If the operating time after the initial installation of the refrigerator is less than or equal to the set value, the control unit (140) can measure the power of the compressor (110) (S110). After the initial installation of the refrigerator, it can first determine whether the refrigerator has been properly installed as guided by the manufacturer.

[0103] At this time, the manufacturer's guide may, for example, be to install the refrigerator's machine room (10) at a distance greater than a predetermined distance from the outer wall. The above setting value may, for example, be 3 days (72 hours) or 4 days (96 hours) after the initial installation of the refrigerator, but is not limited thereto.

[0104] The control unit (140) can check whether the power measurement value of the compressor (110) is greater than the first reference value (S120).

[0105] The above first reference value can serve as a criterion for determining whether the refrigerator is properly installed according to the above guide, for example, whether it is installed with a predetermined distance from the outer wall surface, and can be appropriately obtained and set through experiment.

[0106] If the power measurement is less than or equal to the first reference value, the refrigerator can be determined to have been properly installed in accordance with the above guide. If the power measurement is greater than the first reference value, the refrigerator is considered to have been installed differently from the above guide, and there is a possibility of installation failure.

[0107] When the power measurement value of the compressor (110) is greater than the first reference value, the control unit (140) can measure the rotational speed of the cooling fan (120) (S130).

[0108] The control unit (140) can check whether the measured rotational speed of the cooling fan (120) is smaller than the second reference value (S140).

[0109] The above second reference value can serve as a criterion for determining whether the refrigerator is properly installed according to the above guide, for example, whether it is installed with a predetermined distance from the outer wall surface, and can be appropriately obtained and set through experiment.

[0110] If the measured rotational speed is greater than or equal to the second reference value, it can be determined that the refrigerator is properly installed according to the above guide. If the measured rotational speed is less than the second reference value, it can be determined that the refrigerator is installed differently from the above guide, and the control unit (140) can determine that a refrigerator installation defect has occurred.

[0111] If the measured rotational speed of the cooling fan (120) is less than the second reference value, the control unit (140) can notify the user of the faulty installation status of the refrigerator (S150). The control unit (140) can notify the user of the faulty installation status of the refrigerator using sound, voice, text, etc.

[0112] The refrigerator may be connected to the control unit (140) and may be equipped with means capable of notifying the user of the installation status of the refrigerator, such as a speaker or a display that outputs text.

[0113] The user can receive a notification from the control unit (140) that the installation status of the refrigerator is poor and take necessary measures such as reinstalling the refrigerator.

[0114] FIG. 10 is a flowchart illustrating a refrigerator diagnostic method according to another embodiment. FIG. 10 illustrates a method for determining whether the refrigerator is malfunctioning and the cleaning status. The control unit (140) can determine whether the cooling fan (120) is malfunctioning or at least one of the cleaning status of the machine room (10).

[0115] If the operating time after the initial installation of the refrigerator exceeds the set value, the control unit (140) can calculate the compressor performance index (Lc) (S210). At this time, the set value is as described above.

[0116] The compressor performance indicator (Lc) can be defined as follows.

[0117]

[0118] The compressor performance indicator (Lc) has a similar trend to the power of the compressor (110) described above with reference to FIGS. 3, FIGS. 7, FIGS. 8, etc. The compressor performance indicator (Lc) is a dimensionless value introduced so that it can be used for diagnosing refrigerators even between different models, for example, refrigerators with different refrigeration capacities.

[0119] The control unit (140) can check whether the compressor performance indicator (Lc) is greater than the third reference value (S220).

[0120] The above third standard value can serve as a standard for determining whether the refrigerator operates normally without problems, that is, whether there is no malfunction of the refrigerator and no problem with the cleaning of the machine room (10), and can be appropriately obtained and set through experiment.

[0121] If the measured compressor performance index (Lc) is less than or equal to the third reference value, it can be determined that the refrigerator is operating normally without issues regarding malfunction or poor cleaning of the machine room (10). If the measured compressor performance index (Lc) is greater than the third reference value, it may be a situation where the refrigerator is malfunctioning or poor cleaning of the machine room (10) is an issue.

[0122] When the above compressor performance indicator (Lc) is greater than the third reference value, the control unit (140) can measure the rotational speed of the cooling fan (120) (S230).

[0123] The control unit (140) can check whether the rotational speed measurement of the cooling fan (120) is greater than the fourth reference value (S240).

[0124] The above fourth reference value can serve as a criterion for determining whether a malfunction of the refrigerator has occurred as the refrigerator has been operating for a long period of time, such as the cooling fan (120) stopping operation due to a broken power cable or a sudden decrease in rotational speed, and can be appropriately obtained through experiment.

[0125] Of course, since the fourth reference value is related to the case where the cooling fan (120) stops due to a malfunction or the rotational speed decreases rapidly, it may be relatively smaller than the second reference value set when the cooling fan (120) is not malfunctioning.

[0126] If the measured rotational speed of the cooling fan (120) is less than or equal to the fourth reference value, the control unit (140) can determine that the cooling fan (120) is malfunctioning due to a broken cable or the like, and that the refrigerator is in a state of malfunction.

[0127] If the measured rotational speed of the cooling fan (120) is less than or equal to the fourth reference value, the user may be notified of the refrigerator's malfunction (S270). The control unit (140) may notify the user of the refrigerator's malfunction using sound, voice, text, etc.

[0128] The user receives a notification from the control unit (140) that the refrigerator is malfunctioning and can take necessary measures such as repairing the cooling fan (120).

[0129] When the measured rotational speed of the above cooling fan (120) is greater than the fourth reference value, the control unit (140) can calculate the cooling fan performance index (Lf) (S250).

[0130] The cooling fan performance indicator (Lf) can be defined as follows.

[0131]

[0132] The cooling fan performance index (Lf) has a similar tendency to the rotational speed of the cooling fan (120) described above with reference to FIGS. 4 to 6, etc. The cooling fan performance index (Lf) is a dimensionless value introduced so that it can be used for diagnosing refrigerators even between different models, for example, refrigerators with different freezing capacities.

[0133] The control unit (140) can check whether the cooling fan performance index (Lf) is smaller than the fifth reference value (S260).

[0134] The above-mentioned fifth reference value can serve as a criterion for determining whether the cleaning time of the machine room (10) has been reached. That is, the control unit (140) can determine that the cleaning time of the machine room (10) has been reached if the cooling fan performance index (Lf) is smaller than the fifth reference value, and can predict the cleaning time of the machine room (10) if the cooling fan performance index (Lf) is greater than or equal to the fifth reference value. The above-mentioned fifth reference value can be appropriately obtained and set through experimentation.

[0135] When the above cooling fan performance indicator (Lf) is smaller than the fifth reference value, the control unit (140) can notify the user that the time for cleaning the machine room (10) has been reached (S280). The control unit (140) can notify the user that the time for cleaning the machine room (10) has been reached by sound, voice, text, etc.

[0136] The user receives a notification from the control unit (140) that the time for cleaning the machine room (10) has been reached, and cleans the machine room (10) so that the refrigerator can operate normally.

[0137] When the above cooling fan performance indicator (Lf) is greater than or equal to the fifth reference value, the cleaning time of the machine room (10) can be predicted (S290). The control unit (140) can predict how many hours later the machine room (10) needs to be cleaned based on the current time.

[0138] The control unit (140) can notify the user of the predicted cleaning time of the machine room (10) using sound, voice, text, etc. Based on the notification from the control unit (140), the user can take necessary measures, such as notifying the machine room (10) in advance before the predicted cleaning time is reached.

[0139] The predicted value for the cleaning time of the machine room (10) can be derived by learning according to an artificial intelligence model based on the compressor performance index (Lc) and the cooling fan performance index (Lf). The artificial intelligence model is described below.

[0140] Artificial intelligence (AI) is a field of computer science and information technology that studies methods to enable computers to perform thinking, learning, and self-development capable of human intelligence, and refers to the ability of computers to mimic intelligent human behavior.

[0141] Furthermore, artificial intelligence does not exist in isolation but is closely related, directly and indirectly, to many other fields of computer science. Particularly in the modern era, there are very active attempts to introduce AI elements into various sectors of information technology and utilize them to solve problems within those fields.

[0142] Machine learning is a field of artificial intelligence that enables computers to learn without explicit programming.

[0143] Specifically, machine learning can be defined as a technology that researches and builds systems and algorithms capable of learning, making predictions, and improving their own performance based on empirical data. Rather than executing strictly defined static program commands, machine learning algorithms adopt an approach of constructing specific models to derive predictions or decisions based on input data.

[0144] The term 'machine learning' may be used interchangeably with the term 'machine learning'.

[0145] Many machine learning algorithms have been developed to classify data in machine learning. Representative examples include Decision Trees, Bayesian Networks, Support Vector Machines (SVM), and Artificial Neural Networks (ANN).

[0146] A decision tree is an analytical method that performs classification and prediction by plotting decision rules in a tree structure.

[0147] A Bayesian network is a model that represents the probabilistic relationships (conditional independence) between multiple variables as a graph structure. Bayesian networks are suitable for data mining through unsupervised learning.

[0148] Support Vector Machines are supervised learning models for pattern recognition and data analysis, and are primarily used for classification and regression analysis.

[0149] An artificial neural network models the operating principles of biological neurons and the relationships between them, and is an information processing system in which multiple neurons, called nodes or processing elements, are connected in a layered structure.

[0150] Artificial neural networks are models used in machine learning, and are statistical learning algorithms in machine learning and cognitive science inspired by biological neural networks (particularly the brain within the animal central nervous system).

[0151] Specifically, an artificial neural network can refer to a model in which artificial neurons (nodes) forming a network through the connection of synapses change the strength of the synaptic connections through learning to possess problem-solving capabilities.

[0152] The term artificial neural network may be used interchangeably with the term neural network.

[0153] An artificial neural network may include multiple layers, and each of the layers may include multiple neurons. Additionally, an artificial neural network may include synapses connecting the neurons.

[0154] An artificial neural network can generally be defined by the following three factors: (1) a pattern of connections between neurons in different layers, (2) a learning process that updates the weights of the connections, and (3) an activation function that generates an output value from a weighted sum of inputs received from the previous layer.

[0155] Artificial neural networks may include, but are not limited to, network models such as DNN (Deep Neural Network), RNN (Recurrent Neural Network), BRDNN (Bidirectional Recurrent Deep Neural Network), MLP (Multilayer Perceptron), and CNN (Convolutional Neural Network).

[0156] In this specification, the term 'layer' may be used interchangeably with the term 'hierarchy'.

[0157] Artificial neural networks are classified into single-layer neural networks and multi-layer neural networks depending on the number of layers.

[0158] A typical single-layer neural network consists of an input layer and an output layer.

[0159] In addition, a general multilayer neural network consists of an input layer, one or more hidden layers, and an output layer.

[0160] The input layer is a layer that receives external data, and the number of neurons in the input layer is equal to the number of input variables. The hidden layer is located between the input layer and the output layer, receives signals from the input layer, extracts features, and transmits them to the output layer. The output layer receives signals from the hidden layer and outputs an output value based on the received signals. Input signals between neurons are multiplied by their respective connection strengths (weights) and then summed; if this sum is greater than the neuron's threshold, the neuron is activated and outputs the value obtained through the activation function.

[0161] Meanwhile, a deep neural network that includes multiple hidden layers between the input layer and the output layer can be a representative artificial neural network that implements deep learning, a type of machine learning technology.

[0162] Meanwhile, the term 'deep learning' may be used interchangeably with the term 'deep learning'.

[0163] Artificial neural networks can be trained using training data. Here, training refers to the process of determining the parameters of an artificial neural network using training data to achieve objectives such as classifying, regressing, or clustering input data. Typical examples of artificial neural network parameters include weights assigned to synapses or biases applied to neurons.

[0164] An artificial neural network trained on training data can classify or cluster input data according to the patterns of the input data.

[0165] Meanwhile, an artificial neural network trained using training data may be referred to as a trained model in this specification.

[0166] The following explains the learning method of artificial neural networks.

[0167] The learning methods of artificial neural networks can be broadly classified into supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning.

[0168] Supervised learning is a method of machine learning used to infer a function from training data.

[0169] Among the functions derived in this way, outputting continuous values ​​is called regression, and predicting and outputting the class of an input vector can be called classification.

[0170] In supervised learning, artificial neural networks are trained with labels for the training data.

[0171] Here, a label can refer to the correct answer (or result value) that the artificial neural network must infer when training data is input into it.

[0172] In this specification, the correct answer (or result) that an artificial neural network must infer when training data is input is referred to as a label or labeling data.

[0173] In addition, in this specification, setting labels on training data for the training of an artificial neural network is referred to as labeling the training data.

[0174] In this case, the training data and the labels corresponding to the training data constitute a single training set, and can be input into the artificial neural network in the form of a training set.

[0175] Meanwhile, training data represents multiple features, and labeling the training data can mean that labels are attached to the features represented by the training data. In this case, the training data can represent the features of the input object in the form of a vector.

[0176] Artificial neural networks can infer a function regarding the relationship between training data and labeled data using training data and labeled data. Furthermore, the parameters of the artificial neural network can be determined (optimized) through the evaluation of the function inferred by the network.

[0177] Unsupervised learning is a type of machine learning where training data is not labeled.

[0178] Specifically, unsupervised learning can be a learning method in which an artificial neural network is trained to find and classify patterns within the training data itself, rather than the association between the training data and the labels corresponding to the training data.

[0179] Examples of unsupervised learning include clustering or independent component analysis.

[0180] In this specification, the term 'clustering' may be used interchangeably with the term 'clustering'.

[0181] Examples of artificial neural networks that utilize unsupervised learning include Generative Adversarial Networks (GANs) and Autoencoders (AEs).

[0182] Generative Adversarial Networks are a machine learning method in which two different artificial intelligences, a generator and a discriminator, compete to improve performance.

[0183] In this case, the generator is a model that creates new data and can generate new data based on the original data.

[0184] In addition, the discriminator is a model that recognizes data patterns and can perform the role of distinguishing whether the input data is original data or new data generated by the generator.

[0185] Furthermore, the generator learns by receiving input data that failed to deceive the discriminator, while the discriminator can learn by receiving input data that was deceived by the generator. Accordingly, the generator can evolve to deceive the discriminator as effectively as possible, and the discriminator can evolve to distinguish well between the original data and the data generated by the generator.

[0186] An autoencoder is a neural network that aims to reproduce the input itself as the output.

[0187] An autoencoder includes an input layer, at least one hidden layer, and an output layer.

[0188] In this case, since the number of nodes in the hidden layer is less than the number of nodes in the input layer, the dimensionality of the data is reduced, and accordingly, compression or encoding is performed.

[0189] In addition, data output from the hidden layer enters the output layer. In this case, since the number of nodes in the output layer is greater than the number of nodes in the hidden layer, the dimensionality of the data increases, and accordingly, decompression or decoding is performed.

[0190] Meanwhile, an autoencoder represents input data as hidden layer data by adjusting the connection strengths of neurons through learning. In the hidden layer, information is represented with fewer neurons than in the input layer, and the fact that input data can be reproduced as output implies that the hidden layer has discovered and represented hidden patterns from the input data.

[0191] Semi-supervised learning is a type of machine learning that refers to a learning method using both labeled and unlabeled training data.

[0192] One of the semi-supervised learning techniques involves inferring labels from unlabeled training data and then performing learning using the inferred labels; this technique can be useful when the cost of labeling is high.

[0193] Reinforcement learning is a theory that states that if an agent is given an environment where it can determine what action to take at every moment, it can find the best path through experience without data.

[0194] Reinforcement learning can primarily be performed by Markov Decision Processes (MDPs).

[0195] To explain the Markov decision process, first, an environment is provided containing the information necessary for the agent to take its next action; second, how the agent will act within that environment is defined; third, rewards are given for good performance and penalties for poor performance; and fourth, the optimal policy is derived through repeated experiences until future rewards reach their peak.

[0196] The structure of an artificial neural network is determined by the configuration of the model, activation function, loss function or cost function, learning algorithm, optimization algorithm, etc., and hyperparameters are set in advance before learning, and model parameters are set through learning thereafter, so the content can be determined.

[0197] For example, factors determining the structure of an artificial neural network may include the number of hidden layers, the number of hidden nodes included in each hidden layer, the input feature vector, the target feature vector, etc.

[0198] Hyperparameters include various parameters that must be set initially for training, such as initial values ​​for model parameters. Model parameters, on the other hand, include various parameters intended to be determined through training.

[0199] For example, hyperparameters may include inter-node weight initials, inter-node bias initials, mini-batch size, number of training iterations, and learning rate. Additionally, model parameters may include inter-node weights and inter-node bias.

[0200] The loss function can be used as an indicator (criterion) to determine optimal model parameters during the training process of an artificial neural network. In artificial neural networks, training refers to the process of manipulating model parameters to reduce the loss function, and the objective of training can be viewed as determining the model parameters that minimize the loss function.

[0201] The loss function may primarily use the Mean Squared Error (MSE) or Cross Entropy Error (CEE), but the present invention is not limited thereto.

[0202] Cross-entropy error can be used when the correct label is one-hot encoded. One-hot encoding is an encoding method in which the correct label value is set to 1 only for neurons corresponding to the correct answer, and the correct label value is set to 0 for neurons that are not the correct answer.

[0203] In machine learning or deep learning, learning optimization algorithms can be used to minimize the loss function, and learning optimization algorithms include Gradient Descent (GD), Stochastic Gradient Descent (SGD), Momentum, Nesterov Accelerate Gradient (NAG), Adagrad, AdaDelta, RMSProp, Adam, and Nadam.

[0204] Gradient descent is a technique that adjusts model parameters in a direction that reduces the loss function value by considering the gradient of the loss function from the current state.

[0205] The direction in which model parameters are adjusted is called the step direction, and the size of the adjustment is called the step size.

[0206] In this case, the step size can represent the learning rate.

[0207] Gradient descent obtains the gradient by taking the partial derivative of the loss function with respect to each model parameter, and can update the model parameters by changing them by the learning rate in the direction of the obtained gradient.

[0208] Stochastic Gradient Descent is a technique that divides training data into mini-batches and performs gradient descent on each mini-batch to increase the frequency of gradient descent.

[0209] Adagrad, AdaDelta, and RMSProp are techniques that improve optimization accuracy in SGD by adjusting the step size. In SGD, Momentum and NAG are techniques that improve optimization accuracy by adjusting the step direction. Adam is a technique that improves optimization accuracy by combining Momentum and RMSProp to adjust both the step size and the step direction. Nadam is a technique that improves optimization accuracy by combining NAG and RMSProp to adjust both the step size and the step direction.

[0210] The learning speed and accuracy of artificial neural networks are characterized by being heavily dependent on hyperparameters, as well as the network structure and the type of learning optimization algorithm. Therefore, to obtain a good learning model, it is important to set appropriate hyperparameters in addition to determining a suitable network structure and learning algorithm.

[0211] Typically, hyperparameters are experimentally set to various values ​​while training the artificial neural network, and then set to the optimal value that provides stable training speed and accuracy based on the training results.

[0212] The control unit (140) may be connected to a processor (170) that derives the predicted value. The processor (170) may derive the predicted value by receiving the compressor performance indicator (Lc) and the cooling fan performance indicator (Lf) as inputs, while performing learning according to an artificial intelligence model.

[0213] The process is equipped with an artificial intelligence neural network and can receive input parameters and train an artificial intelligence model based on them to derive a predicted cleaning time value. At this time, the input parameters may include a compressor performance index (Lc) and a cooling fan performance index (Lf).

[0214] The refrigerator further includes a communication unit for communicating with a server, and the control unit (140) can communicate with the server through the communication unit.

[0215] The server can store artificial intelligence models and the data required for training them. Additionally, the server can evaluate the artificial intelligence models and update them for better performance even after evaluation.

[0216] The communication unit may be configured to include at least one of a mobile communication module and a wireless internet module. In addition, the communication unit may additionally include a short-range communication module.

[0217] A mobile communication module transmits and receives wireless signals with at least one of a base station, an external terminal, and a server on a mobile communication network built according to technical standards or communication methods for mobile communication (e.g., GSM (Global System for Mobile communication), CDMA (Code Division Multi Access), CDMA2000 (Code Division Multi Access 2000), EV-DO (Enhanced Voice-Data Optimized or Enhanced Voice-Data Only), WCDMA (Wideband CDMA), HSDPA (High Speed ​​Downlink Packet Access), HSUPA (High Speed ​​Uplink Packet Access), LTE (Long Term Evolution), LTE-A (Long Term Evolution-Advanced), 5G mobile communication, etc.).

[0218] A wireless internet module refers to a module for wireless internet access and can be installed in a refrigerator. The wireless internet module is configured to transmit and receive wireless signals in a communication network based on wireless internet technologies.

[0219] The refrigerator can transmit and receive data with a server and various communication-enabled terminals through a 5G network. In particular, the refrigerator can communicate with a server and terminals using at least one of the following services through a 5G network: Enhanced Mobile Broadband (eMBB), Ultra-reliable and low latency communications (URLC), and Massive Machine-type communications (mMTC).

[0220] eMBB (Enhanced Mobile Broadband) is a mobile broadband service that provides multimedia content and wireless data access. Furthermore, eMBB enables enhanced mobile services, such as hotspots and broadband coverage, to accommodate the explosive growth in mobile traffic. Hotspots allow high-volume traffic to be accommodated in high-density areas with low user mobility. Broadband coverage ensures a wide and stable wireless environment while guaranteeing user mobility.

[0221] URLLC (Ultra-reliable and low-latency communications) services define much stricter requirements than existing LTE in terms of data transmission reliability and transmission delay, and 5G services for industrial production process automation, telemedicine, remote surgery, transportation, and safety fall into this category.

[0222] Massive Machine-Type Communications (mmTC) is a service that is insensitive to transmission delay and requires the transmission of relatively small amounts of data. A much larger number of terminals, such as sensors, can simultaneously connect to a wireless access network via mMTC than with standard mobile phones. In this case, the communication module of the terminal must be inexpensive, and enhanced power efficiency and power-saving technologies are required to enable operation for several years without battery replacement or recharging.

[0223] The processor (170) may be provided in the server. The server receives data regarding the input parameters from the refrigerator, and the processor (170) can derive a predicted value for the required cleaning time by training an artificial intelligence model based on the received data.

[0224] The control unit (140) can receive information regarding the predicted cleaning time value from the server. The control unit (140) can receive information regarding the predicted cleaning time value for each condition, which is derived by the processor (170) learning an artificial intelligence model, from the server.

[0225] Here, each of the above conditions refers to a condition in which at least one of the above input factors, namely the compressor performance indicator (Lc) or the cooling fan performance indicator (Lf), is different from each other.

[0226] In addition, the control unit (140) can specify the predicted value for each of the above conditions based on the received predicted cleaning time value.

[0227] FIG. 11 is a diagram illustrating an artificial intelligence neural network according to one embodiment. The artificial intelligence neural network is provided in a processor (170), and the processor (170) can learn an artificial intelligence model through the artificial intelligence neural network.

[0228] At this time, the artificial intelligence model learning according to the embodiment may be, for example, unsupervised learning, but is not limited thereto.

[0229] The predicted cleaning time value may be a value under different conditions for at least one of the compressor performance indicator (Lc) or the cooling fan performance indicator (Lf) during the learning mode according to the artificial intelligence model.

[0230] If each condition is different, the derived predicted cleaning time may also differ. Different predicted cleaning time values ​​can be derived for each of the above conditions through the training of an artificial intelligence model.

[0231] This artificial intelligence model training can be performed in an artificial intelligence neural network composed of an input layer into which input parameters are input, an output layer that derives a predicted cleaning time value, and multiple hidden layers located between the input layer and the output layer.

[0232] The processor (170) can receive input parameters and, based on them, train an artificial intelligence model to derive a predicted cleaning time value.

[0233] As previously mentioned, the above input factors may include the compressor performance indicator (Lc) and the cooling fan performance indicator (Lf). In addition, factors affecting the predicted cleaning time may additionally serve as the above input factors.

[0234] When input factors with different conditions are input into an artificial neural network, the processor (170) can learn the artificial intelligence model to derive a predicted cleaning time value corresponding to the conditions.

[0235] For example, when using an RNN as an artificial intelligence learning model, input parameters under different conditions are sequentially input into the artificial neural network at different times, and by performing combinations and operations on the input parameters in the hidden layer, predicted cleaning times required for each of the different input parameters can be derived.

[0236] Referring again to FIG. 1, the refrigerator may further include a memory (180) that stores information regarding a cleaning time prediction value. The cleaning time prediction value is a value learned from input factors under different conditions through a processor (170). That is, the cleaning time prediction value derived from the processor (170) can be stored in the memory (180).

[0237] The control unit (140) can select the predicted cleaning time based on information regarding the predicted cleaning time stored in the memory (180). Each predicted cleaning time can be stored in the memory (180) under different conditions for input factors.

[0238] Accordingly, the control unit (140) can use the information stored in the memory (180) to select a predicted cleaning time value corresponding to the current compressor performance index (Lc) and cooling fan performance index (Lf) and notify the user of this.

[0239] In an embodiment, the processor (170) can learn an artificial intelligence model at any time during refrigerator operation, and information regarding input parameters and cleaning time prediction values ​​that have changed according to the learning results can be updated in the memory (180).

[0240] Meanwhile, the aforementioned setting values, the first to fifth reference values, may also be derived by learning according to an artificial intelligence model in a manner similar to deriving a predicted value for the cleaning time of the machine room (10).

[0241] In the embodiment, the refrigerator itself detects the installation status of the refrigerator and notifies the user if the installation status is poor, thereby increasing user convenience.

[0242] In the embodiment, user convenience can be enhanced by the refrigerator itself notifying the user of a malfunction.

[0243] In the embodiment, the refrigerator itself can determine the cleaning time of the machine room (10) or predict the cleaning time and notify the user, thereby increasing user convenience.

[0244] Although only a few examples have been described above in relation to the embodiments, various other forms of implementation are possible. The technical details of the embodiments described above can be combined in various forms, provided they are not mutually incompatible, and can be implemented as new embodiments. Explanation of the symbols

[0245] 10: Machine room 110: Compressor 120: Cooling fan 130: Condenser 140: Control unit 150: Expansion device 160: Evaporator 170: Processor 180: Memory

Claims

Claim 1 A refrigerator diagnostic method comprising a compressor, a cooling fan, a machine room in which a condenser connected to the compressor and cooled by the cooling fan is installed, and a control unit that controls the operation of the compressor, the cooling fan, and the condenser, wherein if the operating time after the initial installation of the refrigerator is less than or equal to a set value, the installation status of the refrigerator is determined based on the power value of the compressor equipped in the refrigerator and the rotational speed of the cooling fan equipped in the refrigerator, and if the operating time after the initial installation of the refrigerator exceeds the set value, the operation failure and cleaning status of the refrigerator are determined based on the power value of the compressor and the rotational speed of the cooling fan, and the process of determining the operation failure and cleaning status of the refrigerator comprises: a step of calculating a compressor performance index; a step of checking whether the compressor performance index is greater than a third reference value; a step of measuring the rotational speed of the cooling fan if the compressor performance index is greater than the third reference value; a step of checking whether the measured rotational speed of the cooling fan is greater than a fourth reference value; and if the measured rotational speed of the cooling fan is less than or equal to the fourth reference value, the refrigerator The method includes a step of determining that the device is in a malfunctioning state; a step of calculating a cooling fan performance index when the measured rotational speed of the cooling fan is greater than a fourth reference value; a step of checking whether the cooling fan performance index is less than a fifth reference value; and a step of determining that the cleaning time of the machine room has been reached when the cooling fan performance index is less than the fifth reference value, wherein the cooling fan performance index (Lf) is A refrigerator diagnostic method defined as. Claim 2 delete Claim 3 A refrigerator diagnostic method according to claim 1, wherein the process of determining the installation status of the refrigerator comprises: a step of measuring the power of the compressor; a step of checking whether the power measurement value of the compressor is greater than a first reference value; a step of measuring the rotational speed of the cooling fan when the power measurement value of the compressor is greater than the first reference value; and a step of checking whether the rotational speed measurement value of the cooling fan is less than a second reference value. Claim 4 A refrigerator diagnostic method according to paragraph 3, wherein the process of determining the installation status of the refrigerator further includes the step of notifying the user of a defective installation status of the refrigerator when the measured rotational speed of the cooling fan is smaller than the second reference value. Claim 5 delete Claim 6 delete Claim 7 delete Claim 8 In paragraph 1, the compressor performance indicator (Lc) is, A refrigerator diagnostic method defined as. Claim 9 delete Claim 10 A refrigerator diagnosis method according to claim 1, wherein the process of determining whether the refrigerator is malfunctioning and the cleaning status further includes the step of notifying the user of the refrigerator's malfunction when the measured rotational speed of the cooling fan is less than or equal to a fourth reference value. Claim 11 A refrigerator diagnostic method according to claim 1, wherein the process of determining whether the refrigerator is malfunctioning and the cleaning status further includes the step of notifying the user that the cleaning time of the machine room has been reached when the cooling fan performance indicator is smaller than the fifth reference value. Claim 12 A refrigerator diagnostic method according to claim 1, wherein the process of determining whether the refrigerator is malfunctioning and the cleaning status further includes the step of predicting the cleaning time of the machine room when the cooling fan performance indicator is greater than or equal to the fifth reference value. Claim 13 A refrigerator diagnostic method according to claim 12, wherein the predicted value for the cleaning time of the machine room is derived by learning according to an Artificial Intelligence model based on the compressor performance indicator and the cooling fan performance indicator. Claim 14 A refrigerator diagnostic method according to claim 13, wherein the control unit is connected to a processor that derives the predicted value, and the processor performs learning according to an artificial intelligence model, and receives the compressor performance indicator and the cooling fan performance indicator as input to derive the predicted value. Claim 15 A refrigerator diagnostic method according to claim 14, wherein the predicted value is a value under different conditions for at least one of the compressor performance indicator or the cooling fan performance indicator in a learning mode according to an artificial intelligence model. Claim 16 In a refrigerator, the refrigerator comprises: a compressor; a condenser connected to the compressor; a cooling fan for cooling the condenser; and a control unit for controlling the operation of the compressor, the cooling fan, and the condenser. The apparatus includes a machine room in which the compressor, the cooling fan, and the condenser are installed, and the control unit determines the installation status of the refrigerator based on the power value of the compressor and the rotational speed of the cooling fan when the operating time after the initial installation of the refrigerator is less than or equal to a set value, and determines whether the refrigerator is malfunctioning and its cleaning status based on the power value of the compressor and the rotational speed of the cooling fan when the operating time after the initial installation of the refrigerator exceeds the set value. In determining whether the refrigerator is malfunctioning and its cleaning status, the control unit calculates a compressor performance index and checks whether the compressor performance index is greater than a third reference value, and if the compressor performance index is greater than the third reference value, measures the rotational speed of the cooling fan and checks whether the measured rotational speed of the cooling fan is greater than a fourth reference value, and if the measured rotational speed of the cooling fan is less than or equal to the fourth reference value, determines that the refrigerator is in a malfunctioning state, and if the measured rotational speed of the cooling fan is greater than the fourth reference value, calculates a cooling fan performance index, and the cooling fan It is checked whether the performance indicator is smaller than the fifth reference value, and if the cooling fan performance indicator is smaller than the fifth reference value, it is determined that the cleaning time of the machine room has been reached, and the cooling fan performance indicator (Lf) is, A refrigerator defined as Claim 17 In claim 16, the refrigerator, wherein the control unit determines at least one of whether the cooling fan is malfunctioning or the cleanliness of the machine room. Claim 18 In claim 17, the control unit predicts the cleaning time of the machine room, and the predicted value for the cleaning time of the machine room is derived by learning according to an artificial intelligence model based on compressor performance indicators and cooling fan performance indicators, a refrigerator.

Images