Air conditioner

Abstract

An air conditioner (100) includes: a converter (3) that rectifies an AC voltage; a smoothing capacitor (4) that smooths the voltage after rectification; a bus voltage detecting unit (5) that detects a bus voltage after smoothing; a bus-voltage pulsation detecting unit (6) that detects a pulsating voltage of the bus voltage; an inverter (7) that generates a driving voltage from the bus voltage and supplies the driving voltage to a motor (11); a drive control unit (8) that performs pulse width modulation control on the inverter; and a notification unit (9) that gives a notification of the control state of the inverter controlled by the drive control unit. The drive control unit performs control to suppress an output frequency of the inverter when the pulsating voltage is equal to or larger than a defined threshold. The notification unit gives a notification that the output frequency is being suppressed, when the drive control unit performs control to suppress the output frequency of the inverter.

Description

air conditioner

[0001] The present disclosure relates to an air conditioner that uses an inverter device that controls the speed of an electric motor.

[0002] Conventional air conditioners include one equipped with a motor drive power supply unit that performs control to reduce the inverter output frequency when the pulsating voltage of the bus voltage exceeds a predetermined value, in order to achieve both a reduction in the capacity and an extended life of the smoothing capacitor that smooths the pulsating components contained in the output of the rectifier that converts AC to DC (see Patent Document 1).

[0003] Japanese Patent Application Laid-Open No. 2007-259629

[0004] The air conditioner described in Patent Document 1 does not notify the user that the inverter output frequency is being intentionally reduced, even when the air conditioner is operating with the inverter output frequency reduced to reduce the capacitance of the smoothing capacitor and ensure its lifespan. As a result, there is a problem in that the user cannot know whether the air conditioner is intentionally suppressing output through normal control operation, or whether the output has been reduced due to a malfunction.

[0005] The present disclosure has been made in view of the above, and has an object to provide an air conditioner that can notify a user of the cause of a decrease in output.

[0006] In order to solve the above-mentioned problems and achieve the object, an air conditioner according to the present disclosure includes a converter that rectifies AC voltage, a smoothing capacitor that smooths the rectified voltage, a bus voltage detection unit that detects the smoothed bus voltage, a bus voltage pulsation detection unit that detects the pulsating voltage of the bus voltage, an inverter that generates a drive voltage from the bus voltage and supplies it to a motor, a drive control unit that performs pulse width modulation control of the inverter, and a notification unit that notifies the control state of the inverter by the drive control unit. The drive control unit suppresses the output frequency of the inverter when the pulsating voltage is equal to or greater than a predetermined threshold, and the notification unit notifies that the output frequency is being suppressed when the drive control unit is controlling the inverter to suppress the output frequency.

[0007] The air conditioner according to the present disclosure has the effect of being able to notify the user of the cause of the decrease in output.

[0008] FIG. 10 is a block diagram showing an example of the configuration of an air conditioner according to a first embodiment; FIG. 11 is a flowchart showing an example of the operation of protecting a smoothing capacitor of the air conditioner according to the first embodiment; FIG. 12 is a diagram showing an example of a method of notifying during suppression of the output frequency of the air conditioner according to the first embodiment; FIG. 13 is a block diagram showing an example of the configuration of an air conditioner according to a second embodiment; FIG. 14 is a block diagram showing an example of the configuration of an air conditioner according to a third embodiment; FIG. 15 is a diagram showing an example of the configuration of a learning device provided in the air conditioner according to the third embodiment;

[0009] Hereinafter, an air conditioner according to an embodiment of the present disclosure will be described in detail with reference to the drawings.

[0010] 1 is a block diagram showing an example of the configuration of an air conditioner 100 according to embodiment 1. The air conditioner 100 is connected to an AC power supply 1, and receives power from the AC power supply 1 to perform air conditioning.

[0011] The air conditioner 100 includes a power conversion unit 50 configured with a reactor 2, a converter 3, a smoothing capacitor 4, and an inverter 7, a bus voltage detection unit 5, a bus voltage pulsation detection unit 6, a drive control unit 8, a notification unit 9, and a compressor 10. The compressor 10 includes a motor 11. The motor 11 is connected to the inverter 7. In this embodiment, the current flowing from the converter 3 to the smoothing capacitor 4 is referred to as current I1, the current flowing from the smoothing capacitor 4 to the inverter 7 is referred to as current I2, and the current flowing into the smoothing capacitor 4 is referred to as current I3.

[0012] The power conversion unit 50 converts the AC power supplied from the AC power supply 1 into motor driving power, which is AC power for driving the motor 11 of the compressor 10 .

[0013] The bus voltage detector 5 detects the voltage across the smoothing capacitor 4 as the bus voltage. The bus voltage pulsation detector 6 detects the pulsation of the bus voltage detected by the bus voltage detector 5.

[0014] The drive control unit 8 calculates the output voltage, phase, and frequency to be applied to the motor 11 of the compressor 10 using known mathematical formulas based on the bus voltage pulsation detected by the bus voltage pulsation detection unit 6 and signals from an inverter output current detection unit (not shown) and an inverter output frequency setting unit (not shown). The drive control unit 8 performs pulse width modulation (PWM) control of the inverter 7 based on the calculated output voltage, phase, and frequency. Specifically, the drive control unit 8 generates a PWM signal to drive the inverter 7 so as to generate the required air conditioning capacity of the air conditioner 100 and the required drive torque when driving the compressor 10, and outputs the PWM signal to the inverter 7. Here, the inverter output current detection unit detects the current flowing from the inverter 7 to the motor 11 and outputs a signal indicating the detection result to the drive control unit 8. The inverter output frequency setting unit outputs a signal indicating the setting result of the output frequency of the compressor 10 to the drive control unit 8. The output frequency of the compressor 10 is set based on the target temperature of the space to be air-conditioned by the air conditioner 10. The target temperature is specified by, for example, the user of the air conditioner 100 .

[0015] The PWM control of the inverter 7 by the drive control unit 8 is similar to the PWM control in the air conditioner described in Patent Document 1, and therefore a detailed description thereof will be omitted.

[0016] The notification unit 9 notifies the outside of the control state of the inverter 7 by the drive control unit 8. For example, the notification unit 9 notifies when the drive control unit 8 is performing control to suppress the output of the inverter 7. The notification by the notification unit 9 is not limited to the control state of the inverter 7. For example, the notification unit 9 may notify the content of an operational abnormality that has occurred in the air conditioner 100, or may notify the air conditioner 100 of a malfunction that has occurred.

[0017] The arrangement of the components of the power conversion unit 50 shown in Fig. 1 is an example, and the arrangement of the components is not limited to the example shown in Fig. 1. For example, the reactor 2 may be arranged in a stage subsequent to the converter 3. The reactor 2 may also have a function of boosting the bus voltage. The converter 3 may also have a function of boosting the bus voltage.

[0018] The smoothing capacitor 4 that constitutes the power conversion unit 50 must be used under conditions where the temperature and voltage across it are within a specified range, and if the specified ranges are exceeded, deterioration will progress and the lifespan will be shortened. For convenience, in the following explanation, the above specified ranges will be referred to as the guaranteed operating range.

[0019] One cause of deterioration of the smoothing capacitor 4 is a temperature rise due to the equivalent series resistance (ESR) of the smoothing capacitor 4 when a ripple current I3 flows through the smoothing capacitor 4. In order to suppress deterioration of the smoothing capacitor 4 due to ESR, the drive control unit 8 controls the inverter 7 so that the input current I1 from the converter 3 to the smoothing capacitor 4 and the output current I2 from the smoothing capacitor 4 to the inverter 7 are equal. By controlling in this manner, the ripple current I3 can be reduced, suppressing deterioration of the smoothing capacitor 4. However, because a ripple component caused by PWM control is superimposed on the output current I2, the drive control unit 8 must control the inverter 7 taking this ripple component into account.

[0020] For this reason, in the air conditioner 100, the drive control unit 8 suppresses deterioration of the smoothing capacitor 4 by performing control in accordance with the flowchart shown in Fig. 2. Furthermore, when an operation for suppressing deterioration of the smoothing capacitor 4 (hereinafter sometimes referred to as a deterioration suppression operation) is being performed, the user is notified that the deterioration suppression operation is in progress. Note that Fig. 2 is a flowchart showing an example of an operation for protecting the smoothing capacitor 4 of the air conditioner 100 according to the first embodiment.

[0021] In the air conditioner 100, first, the bus voltage detector 5 detects the bus voltage (step S1), and the bus voltage pulsation detector 6 detects the bus voltage pulsation (step S2). Hereinafter, the result of the detection of the bus voltage pulsation by the bus voltage pulsation detector 6 will be referred to as a pulsating voltage value ΔV.

[0022] Next, the drive control unit 8 checks whether the pulsating voltage value ΔV is equal to or greater than a predetermined threshold value (step S3). The threshold value used in step S3 is set based on the relationships among the pulsating voltage value ΔV, the ripple current I3, and the degree of deterioration of the smoothing capacitor 4, which are determined, for example, by simulation or the like. The threshold value is set to a value that keeps the temperature of the smoothing capacitor 4 within the guaranteed operating range. In other words, the threshold value is set to a value that does not cause the temperature of the smoothing capacitor 4 to exceed the upper limit of the guaranteed operating range.

[0023] If the pulsating voltage value ΔV is equal to or greater than the threshold value (step S3: Yes), the drive control unit 8 starts suppressing the output frequency of the inverter 7 so that the pulsating voltage value ΔV is less than the threshold value (step S4). This suppresses the ripple current I3 and brings it within the guaranteed operating range, enabling operation while suppressing deterioration of the smoothing capacitor 4. On the other hand, if the pulsating voltage value ΔV is less than the threshold value (step S3: No), the drive control unit 8 ends suppression of the output frequency of the inverter 7 (step S6).

[0024] As for the threshold value used in the judgment process of step S3, a dead zone is provided between the threshold value for starting output frequency suppression and the threshold value for ending output frequency suppression, so that the output frequency suppression is controlled so as not to react too sensitively.

[0025] After starting suppression of the output frequency of the inverter 7 in step S4, the drive control unit 8 starts notifying the user that the output frequency is being suppressed (step S5). That is, while the output frequency of the inverter 7 is being suppressed, the drive control unit 8 outputs a signal to the notification unit 9 to notify the user that the output frequency of the inverter 7 is being suppressed due to an overcurrent in the smoothing capacitor 4.

[0026] After ending the suppression of the output frequency of the inverter 7 in step S6, the drive control unit 8 ends the notification that the output frequency is being suppressed (step S7).

[0027] Possible notification methods by the notification unit 9 include, for example, lighting or blinking an LED 91 provided on the remote control 90 of the air conditioner 100, or displaying a message on an LCD screen 92, as shown in FIG. 3 . FIG. 3 is a diagram showing an example of a notification method for the air conditioner 100 according to the first embodiment when the output frequency is being suppressed. The notification when the output frequency is being suppressed may be performed by voice. The notification may also be performed by a combination of a visual and a visual. As shown in FIG. 3 , the display on the LCD screen 92 is performed by, for example, text 93. The text 93 display need only indicate that the output frequency is being suppressed, and does not have to directly indicate the suppression of the output frequency of the inverter 7. Alternatively, an icon 94 may be displayed instead of text. A symbol indicating that the output frequency is being suppressed may also be displayed. Notification by displaying text or the like may be performed on the main body of the air conditioner 100.

[0028] If the device has a function for detecting a failure in the smoothing capacitor 4, the notification unit 9 may notify the failure when it detects the failure in the smoothing capacitor 4, but the content of the notification will be different.

[0029] As described above, in order to suppress deterioration of the smoothing capacitor 4, the air conditioner 100 according to the first embodiment determines whether or not it is necessary to suppress the output frequency of the inverter 7 based on the pulsation of the bus voltage, which is the voltage across the smoothing capacitor 4, and if it is necessary to suppress the output frequency, it suppresses the output frequency and notifies the user that the output frequency is being suppressed. According to the air conditioner 100, when the output frequency of the inverter 7 is in a suppressed state, the user can know whether the suppression of the output frequency is due to a malfunction of the air conditioner 100 or whether the suppression of the output frequency is due to a protective operation of the device.

[0030] In this embodiment, the protective operation of suppressing the output frequency of the inverter 7 to prevent deterioration of the smoothing capacitor 4 and the notification operation to the user when the output is being suppressed are described as being applied to an air conditioner, but it goes without saying that the above protective operation and notification operation can also be applied to other devices that have a configuration in which a motor is driven by an inverter.

[0031] Second Embodiment Next, an air conditioner according to a second embodiment will be described. Explanations of the configuration and operation common to the first embodiment will be omitted, and only differences will be described.

[0032] 4 is a block diagram showing a configuration example of an air conditioner 100a according to a second embodiment. The air conditioner 100a has a configuration in which a recording unit 12 is added to the air conditioner 100 according to the first embodiment shown in FIG. 1. The recording unit 12 is realized, for example, by a volatile or non-volatile semiconductor memory such as a flash memory built into a microprocessor or an EEPROM (registered trademark) (Electrically Erasable Programmable Read-Only Memory). The recording unit 12 may also be realized by using a recording device available in a cloud service on the Internet.

[0033] In the air conditioner 100a, the recording unit 12 records a control log, which is a log of the control operation of the inverter 7 by the drive control unit 8. The control log includes, for example, the voltage of the AC power supply 1, the pulsating voltage value ΔV detected by the bus voltage pulsation detection unit 6, the output current and output frequency of the inverter 7, the time and duration of the notification by the notification unit 9 that the output frequency is being suppressed, and environmental information. The notification duration is the length of time the notification unit 9 has issued the notification. The control log may include the end time of the notification instead of the notification duration. The environmental information may be, for example, at least one of weather conditions, indoor temperature, and outdoor temperature. This makes it possible to investigate and analyze at a later date the circumstances under which the output frequency of the inverter 7 was suppressed.

[0034] 4, the air conditioner 100a has means for externally checking the control log recorded in the recording unit 12, for example, an interface for connecting a communication cable. The air conditioner 100a may have a wireless communication function, and the control log may be externally checked using the wireless communication function.

[0035] Third Embodiment Next, an air conditioner according to a third embodiment will be described. Explanations of the configuration and operation common to the first embodiment will be omitted, and only differences will be described.

[0036] FIG. 5 is a block diagram showing a configuration example of an air conditioner 100b according to a third embodiment. The air conditioner 100b has a configuration in which a temperature detection unit 13, a learning device 20, a trained model storage unit 30, and an inference device 40 are added to the air conditioner 100 according to the first embodiment shown in FIG. 1. The temperature detection unit 13 is realized, for example, by a temperature sensor. The temperature detection unit 13 may be composed of multiple temperature sensors installed in different locations. In other words, the temperature detection unit 13 may be configured to be able to detect temperatures at multiple locations. Furthermore, the air conditioner 100b has a function of connecting to an external network, and the drive control unit 8 is configured to be able to communicate with an external server 60 via the network.

[0037] In the air conditioner 100b, the drive control unit 8 changes the threshold value used when determining whether to suppress the output frequency of the inverter 7 according to the usage environment of the air conditioner 100b. This threshold value is generated by the learning device 20, and is determined by the inference device 40 using the learned model stored in the learned model storage unit 30.

[0038] That is, the learning device 20 generates a trained model for inferring a threshold value used when the drive control unit 8 determines whether or not to suppress the output frequency of the inverter 7. The trained model storage unit 30 acquires and stores the trained model generated by the learning device 20. The inference device 40 uses the trained model stored in the trained model storage unit 30 to infer a threshold value used in the control operation of the inverter 7 by the drive control unit 8.

[0039] In this embodiment, an example is described in which the learning device 20, the trained model storage unit 30, and the inference device 40 are provided inside the air conditioner 100b, but some or all of these may be provided outside the air conditioner 100b and connected to the air conditioner 100b via a network, etc. Some or all of the learning device 20, the trained model storage unit 30, and the inference device 40 may reside on a cloud server.

[0040] Below, the operation of the air conditioner 100b will be explained by dividing it into a learning phase in which the learning device 20 generates a trained model and an utilization phase in which the inference device 40 infers a threshold value using the trained model.

[0041] 6 is a diagram illustrating an example of the configuration of the learning device 20 included in the air conditioner 100b according to embodiment 3. The learning device 20 includes a data acquisition unit 21 and a model generation unit 22. The model generation unit 22 includes a reward calculation unit 23 and a function update unit 24.

[0042] The data acquisition unit 21 acquires, as learning data, temperature data and threshold values ​​held in the drive control unit 8 and used in the output frequency suppression control of the inverter 7. The temperature data refers to one or more of the following data: the room temperature of the room in which the air conditioner 100b is installed, the outside temperature, and weather conditions. The weather conditions refer to predicted values ​​such as the weather, maximum temperature, and minimum temperature in the location in which the air conditioner 100b is installed. The data acquisition unit 21 acquires the room temperature and outside temperature from the temperature detection unit 13, and acquires the weather conditions from the external server 60.

[0043] The model generation unit 22 learns thresholds under each temperature condition based on the thresholds and temperature data acquired as learning data by the data acquisition unit 21. In other words, the model generation unit 22 generates a learned model for inferring, from the temperature data of the air conditioner 100b, the thresholds used by the drive control unit 8 in the output frequency suppression control of the inverter 7. In the following description, the thresholds used by the drive control unit 8 in the output frequency suppression control of the inverter 7 may be referred to as the "output suppression determination thresholds."

[0044] The learning algorithm used by the model generation unit 22 may be a known algorithm such as supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning. As an example, a case where reinforcement learning is applied to the learning algorithm used by the model generation unit 22 will be described. In reinforcement learning, an agent (acting subject) in a certain environment observes the current state (environmental parameters) and determines the action to be taken. The environment changes dynamically depending on the agent's actions, and the agent is given a reward according to the environmental changes. The agent repeats this process and learns the action course that will obtain the most reward through a series of actions. Typical reinforcement learning methods include Q-learning and TD-learning. For example, in the case of Q-learning, a general update formula for the action value function Q(s, a) is expressed as the following formula (1):

[0045]

[0046] In formula (1), s t represents the state of the environment at time t, and a t represents the action at time t. t Therefore, the state is s t+1 It changes to r t+1 represents the reward that can be obtained depending on the change in state, γ represents the discount rate, and α represents the learning coefficient. Note that γ is in the range of 0<γ≦1, and α is in the range of 0<α≦1. In the model generation unit 22 of the learning device 20 according to this embodiment, the output suppression determination threshold is set to 0<γ≦1. t and temperature data such as weather conditions, room temperature, and outside temperature are stored in state s t The model generation unit 22 generates the state s t Best action in a t Learn.

[0047] The update formula expressed by the above formula (1) increases the action value Q if the action value Q of the action a with the highest Q value at time t+1 is greater than the action value Q of the action a executed at time t, and decreases the action value Q in the opposite case. In other words, the action value function Q(s, a) is updated so that the action value Q of the action a at time t approaches the best action value at time t+1. As a result, the best action value in a certain environment is propagated sequentially to the action values ​​in previous environments.

[0048] The reward calculation unit 23 calculates the reward based on the output suppression determination threshold and temperature data acquired by the data acquisition unit 21 as learning data. Specifically, the reward calculation unit 23 calculates the reward r based on whether or not the user operates the air conditioner 100b during the period in which the drive control unit 8 suppresses the output frequency of the inverter 7. For example, the reward calculation unit 23 increases the reward r (e.g., provides a reward of "1") if there is no user operation during the period, and decreases the reward r (e.g., provides a reward of "-1") if there is a user operation. The user operation used to calculate the reward r is an operation to change the set temperature. In other words, the reward calculation unit 23 decreases the reward r when an operation to change the set temperature is performed, and increases the reward r when an operation other than an operation to change the set temperature is performed or when no operation is performed.

[0049] The function update unit 24 updates the function for determining the output suppression determination threshold in accordance with the reward calculated by the reward calculation unit 23. The function update unit 24 outputs the trained model created by updating the function to the trained model storage unit 30. For example, when the learning algorithm is Q-learning, the action value function Q(s t , a t ) is used as a function for determining the output suppression determination threshold.

[0050] The learning process is repeated as described above. The learned model storage unit 30 stores the action value function Q(s) updated by the function update unit 24. t , a t ), i.e., stores the trained model.

[0051] 7 is a flowchart showing the processing procedure of the learning device 20 shown in FIG. 6. Referring to the flowchart of FIG. 7, the learning device 20 calculates the action value function (s t , a t ) will be explained.

[0052] First, the data acquisition unit 21 acquires the output suppression determination threshold and temperature data as learning data (step S11).

[0053] Next, the drive control unit 8 determines that the pulsation of the bus voltage is equal to or greater than the threshold value, and starts suppressing the output frequency of the inverter 7 (step S12).

[0054] In steps S13 to S16, the model generation unit 22 calculates an action value function (s t , a t ) to update.

[0055] Specifically, the model generation unit 22 checks whether or not there is a user operation (step S13). For example, the model generation unit 22 checks whether or not a user operation has been received until the drive control unit 8 finishes suppressing the output frequency of the inverter 7. The model generation unit 22 may check whether or not a user operation has been received until a predetermined time has elapsed since the drive control unit 8 started suppressing the output frequency of the inverter 7.

[0056] If there is no user operation (step S13: No), the reward calculation unit 23 increases the reward (step S14). If there is a user operation (step S13: Yes), the reward calculation unit 23 decreases the reward (step S15).

[0057] Following step S14 or step S15, the function update unit 24 updates the action value function Q(s) stored in the trained model storage unit 30 based on the reward after the reward calculation unit 23 has increased or decreased the reward. t , a t ) is updated (step S16). The updated action value function Q(s t , a t ) is stored as a learned model in the learned model storage unit 30.

[0058] The learning device 20 repeatedly executes the above steps S11 to S16 to obtain the action value function Q(s t , a t ) will be updated.

[0059] <Utilization Phase> Next, the utilization phase in which the inference device 40 infers the output suppression determination threshold value using the trained model will be described.

[0060] 8 is a diagram showing an example of the configuration of the inference device 40 provided in the air conditioner 100b according to the third embodiment. The inference device 40 includes a data acquisition unit 41 and an inference unit 42.

[0061] The data acquisition unit 41 acquires the above-mentioned temperature data, i.e., temperature data consisting of one or more data of the room temperature, the outside temperature, and the weather conditions. Like the data acquisition unit 21 of the above-mentioned learning device 20, the data acquisition unit 41 acquires the room temperature and the outside temperature from the temperature detection unit 13, and acquires the weather conditions from the external server 60.

[0062] The inference unit 42 uses the trained model stored in the trained model storage unit 30 to infer an output suppression determination threshold appropriate for the usage environment of the air conditioner 100b indicated by the temperature data acquired by the data acquisition unit 41. That is, by inputting the temperature data into this trained model, the inference unit 42 infers a threshold for determining whether or not the drive control unit 8 will suppress the output frequency of the inverter 7 when the air conditioner 100b is used in the usage environment indicated by the temperature data.

[0063] In this embodiment, the output suppression judgment threshold is described as being inferred using a learned model generated by the model generation unit 22 of the air conditioner 100b, but it is also possible to obtain a learned model generated by the model generation unit of a learning device provided in another air conditioner from this learning device, and infer the output suppression judgment threshold using the obtained learned model.

[0064] Fig. 9 is a flowchart showing the processing procedure of the inference device 40 shown in Fig. 8. The operation of the inference device 40 for inferring the output suppression determination threshold will be described with reference to the flowchart of Fig. 9.

[0065] First, the data acquisition unit 41 acquires temperature data from one or both of the temperature detection unit 13 and the external server 60 (step S21).

[0066] Next, the inference unit 42 inputs the temperature data acquired by the data acquisition unit 41 into the trained model stored in the trained model storage unit 30, and obtains the corresponding output from the trained model, thereby inferring an output suppression determination threshold (step S22). That is, the trained model stored in the trained model storage unit 30 infers an output suppression determination threshold appropriate for the usage environment of the air conditioner 100b based on the input temperature data.

[0067] When the inference unit 42 has finished inferring the output suppression determination threshold, it outputs the inferred output suppression determination threshold to the drive control unit 8 (step S23).

[0068] The drive control unit 8 updates the threshold value used in the suppression control of the output frequency of the inverter 7 based on the output suppression determination threshold value output from the inference unit 42 of the inference device 40 (step S24). That is, the drive control unit 8 sets the output suppression determination threshold value output from the inference unit 42 as the threshold value used in the suppression control of the output frequency of the inverter 7.

[0069] This allows the output frequency of the inverter 7 to be suppressed within a range in which the user will not operate the air conditioner 100b, i.e., within a range in which the user will not feel uncomfortable with the room temperature, and deterioration of the smoothing capacitor 4 can be suppressed.

[0070] As described above, in the air conditioner 100b of this embodiment, the threshold value used by the drive control unit 8 in the process of determining whether or not to suppress the output frequency of the inverter 7 is adjusted to suit the environment in which the air conditioner is used, thereby preventing the comfort of the user using the air conditioner 100b from being impaired while suppressing deterioration of the smoothing capacitor 4.

[0071] In the present embodiment, the learning device 20 generates a trained model using training data obtained from a single air conditioner 100b. However, this is not limiting. The data acquisition unit 21 of the learning device 20 may acquire training data from multiple air conditioners, and the model generation unit 22 may learn the output suppression determination threshold. In this case, the data acquisition unit 21 may acquire training data from multiple air conditioners used in the same area, or from multiple air conditioners operating independently in different areas. That is, the model generation unit 22 may learn the relationship between temperature data and the output suppression determination threshold using training data acquired from multiple air conditioners used in the same area to generate a trained model, or may learn the relationship between temperature data and the output suppression determination threshold using training data acquired from multiple air conditioners operating independently in different areas to generate a trained model. The learning device 20 may also add or remove air conditioners from which training data is collected during the process. Furthermore, a learning device that has learned the relationship between temperature data and the output suppression judgment threshold for a certain air conditioner may be applied to another air conditioner, and the relationship between temperature data and the output suppression judgment threshold for the other air conditioner may be re-learned to update the learned model.

[0072] Furthermore, in the present embodiment, an example has been described in which the temperature detection unit 13, learning device 20, learned model storage unit 30, and inference device 40 are added to the air conditioner 100 according to embodiment 1, but the temperature detection unit 13, learning device 20, learned model storage unit 30, and inference device 40 may also be added to the air conditioner 100a according to embodiment 2. In this case, the learning device 20 may perform machine learning using the control log recorded by the recording unit 12 to generate the learned model.

[0073] Fourth Embodiment Next, an air conditioner according to a fourth embodiment will be described. Explanations of the configuration and operation common to the first embodiment will be omitted, and only differences will be described.

[0074] Fig. 10 is a block diagram showing a configuration example of an air conditioner 100c according to embodiment 4. The air conditioner 100c has a configuration in which an operation unit 15 is added to the air conditioner 100 according to embodiment 1 shown in Fig. 1 .

[0075] The operation unit 15 of the air conditioner 100c accepts an operation to forcibly terminate the output suppression of the inverter 7. For example, the operation unit 15 includes a button that allows the user to perform this operation.

[0076] In the air conditioner 100c, when the operation unit 15 receives an operation to forcibly terminate output suppression of the inverter 7 while the drive control unit 8 is performing control to suppress the output frequency of the inverter 7, the drive control unit 8 terminates suppression of the output frequency of the inverter 7 and starts normal control, that is, control that does not suppress the output frequency of the inverter 7 even if the pulsation of the bus voltage is equal to or greater than a specified threshold. This allows the user to prioritize the output of the air conditioner 100c over the life of the smoothing capacitor 4. The display of the button used by the operation unit 15 to receive an operation does not need to directly suggest the forced termination of output suppression, and may display, for example, "power mode."

[0077] In this embodiment, an operation unit 15 is added to the air conditioner 100 according to embodiment 1, allowing the user to forcibly terminate the output suppression of the inverter 7; however, an operation unit 15 may also be added to the air conditioner 100a according to embodiment 2 or the air conditioner 100b according to embodiment 3, allowing the user to forcibly terminate the output suppression of the inverter 7.

[0078] Fifth Embodiment Next, an air conditioner according to a fifth embodiment will be described. Explanations of the configuration and operation common to the first embodiment will be omitted, and only differences will be described. The configuration of the air conditioner according to this embodiment is the same as that of the fourth embodiment (see FIG. 10).

[0079] In the air conditioner 100 according to the first embodiment, the notification unit 9 notifies the user when suppression of the output frequency of the inverter 7 begins. In contrast, in the air conditioner 100c according to the present embodiment, the notification unit 9 does not issue a notification simply when suppression of the output frequency of the inverter 7 begins, but rather starts to issue a notification when the operation unit 15 receives a specific operation while the output frequency of the inverter 7 is being suppressed. An example of a specific operation is the long press of two or more different buttons. As a result, the notification is not issued to normal users, but can be issued to service personnel or the like who know the specific operation method only during, for example, inspection or repair.

[0080] The notification unit 9 may be configured to notify different contents before and after the specific operation is performed. For example, from the time when the drive control unit 8 starts suppressing the output frequency of the inverter 7 until the operation unit 15 accepts the specific operation, the notification unit 9 may notify the contents for the user described in the first embodiment using Fig. 3, and after the operation unit 15 accepts the specific operation, the notification unit 9 may start notifying information required for inspection and repair.

[0081] Furthermore, the air conditioners 100a and 100b described in the second and third embodiments may be provided with an operation unit 15, and may be configured to initiate an alert when a specific operation is performed while the output frequency of the inverter 7 is suppressed.

[0082] Next, we will explain the hardware configuration of each part that performs operations related to the control of the inverter 7 in the air conditioner described in each embodiment, specifically the hardware configuration of the bus voltage detection part 5, bus voltage pulsation detection part 6, drive control part 8, notification part 9, recording part 12, temperature detection part 13, operation part 15, learning device 20, learned model storage part 30 and inference device 40.

[0083] Of the above-mentioned units, the bus voltage pulsation detection unit 6, the drive control unit 8, the notification unit 9, and the recording unit 12 are realized, for example, by the hardware shown in Fig. 11. Fig. 11 is a diagram showing an example of hardware that realizes the units that perform operations related to the control of the inverter 7 of the air conditioner.

[0084] That is, the bus voltage ripple detection unit 6, drive control unit 8, notification unit 9, and recording unit 12 can be realized by a processor 101, memory 102, display device 103, and communication device 104 shown in FIG. 11 . An example of the processor 101 is a CPU (Central Processing Unit, also referred to as a central processing unit, processing device, arithmetic unit, microprocessor, microcomputer, or DSP (Digital Signal Processor)) or a system LSI (Large Scale Integration). An example of the memory 102 is a non-volatile or volatile semiconductor memory such as a RAM (Random Access Memory), a ROM (Read Only Memory), or a flash memory, a magnetic disk, etc. An example of the display device 103 is a liquid crystal monitor, a display, etc. An example of the communication device 104 is a wireless LAN (Local Area Network) adapter, etc.

[0085] The bus voltage ripple detector 6 and the drive controller 8 are realized by the processor 101 executing a program for operating these units. The program for operating the bus voltage ripple detector 6 and the drive controller 8 is stored in advance in the memory 102. The processor 101 operates as the bus voltage ripple detector 6 and the drive controller 8 by reading and executing this program from the memory 102.

[0086] The notification unit 9 is realized by the display device 103. The recording unit 12 is realized by the memory 102. As described in the first embodiment, the notification unit 9 may be realized by an LED, an audio output device, or the like instead of the display device 103.

[0087] The communication device 104 is used when the drive control unit 8 communicates with the external server 60 shown in FIG.

[0088] Of the above components, the bus voltage detector 5 is implemented by a voltage sensor, etc. The temperature detector 13 is implemented by a temperature sensor, etc. The operation unit 15 is implemented by a keypad, etc.

[0089] Among the above-mentioned units, the learning device 20 and the inference device 40 are respectively realized by a processor and a memory similar to the processor 101 and the memory 102 shown in Fig. 11. The trained model storage unit 30 is realized by a non-volatile or volatile semiconductor memory such as RAM, ROM, or flash memory, a magnetic disk, or the like.

[0090] The configurations shown in the above embodiments are merely examples, and may be combined with other known technologies, or the embodiments may be combined with each other, or part of the configuration may be omitted or modified within the scope of the gist.

[0091] REFERENCE SIGNS LIST 1 AC power supply, 2 Reactor, 3 Converter, 4 Smoothing capacitor, 5 Bus voltage detection unit, 6 Bus voltage pulsation detection unit, 7 Inverter, 8 Drive control unit, 9 Notification unit, 10 Compressor, 11 Motor, 12 Recording unit, 13 Temperature detection unit, 15 Operation unit, 20 Learning device, 21, 41 Data acquisition unit, 22 Model generation unit, 23 Reward calculation unit, 24 Function update unit, 30 Learned model storage unit, 40 Inference device, 42 Inference unit, 50 Power conversion unit, 60 External server, 90 Remote control, 91 LED, 92 LCD screen, 93 Characters, 94 Icon, 100, 100a, 100b, 100c Air conditioner.

Claims

1. A converter that rectifies the AC voltage; A smoothing capacitor that smoothes the rectified voltage; A bus voltage detection unit that detects the smoothed bus voltage; a bus voltage ripple detection unit for detecting a ripple voltage of the bus voltage; an inverter that generates a drive voltage from the bus voltage and supplies the drive voltage to a motor; A drive control unit that performs pulse width modulation control of the inverter; a notification unit that notifies a control state of the inverter by the drive control unit; Equipped with The drive control unit performs control to suppress an output frequency of the inverter when the pulsating voltage is equal to or greater than a predetermined threshold value, The notification unit notifies that a deterioration suppression operation is being performed when the drive control unit is performing control to suppress the output frequency of the inverter. Air conditioner.

2. a recording unit that records a log of the control operation of the inverter by the drive control unit; The air conditioner according to claim 1 .

3. A temperature detection unit; An inference device that infers the threshold value using a learned model generated by learning a relationship between the threshold value used by the drive control unit in the inverter output frequency suppression control and the usage environment of the air conditioner; Equipped with The inference device infers the threshold value based on temperature data including the temperature detected by the temperature detection unit and the trained model. The air conditioner according to claim 1.

4. a learning device that learns a relationship between the threshold value being used by the drive control unit in the output frequency suppression control of the inverter and temperature data including a temperature detected by the temperature detection unit while the drive control unit is controlling the inverter, and generates the learned model; The air conditioner according to claim 3 .

5. The temperature detection unit detects at least one of a room temperature in a room in which the air conditioner is installed and an outside temperature. The air conditioner according to claim 3.

6. The temperature data further includes weather conditions acquired from an external source via a network. The air conditioner according to claim 3.

7. an operation unit capable of accepting, from a user, an operation for forcibly terminating the suppression of the output frequency of the inverter in a state in which the drive control unit is suppressing the output frequency of the inverter; Equipped with When the operation unit receives the operation, the drive control unit ends the suppression of the output frequency of the inverter. The air conditioner according to claim 1.

8. The notification unit notifies that the output frequency is being suppressed when the drive control unit performs control to suppress the output frequency of the inverter and a predetermined specific operation is performed.

8. An air conditioner according to any one of claims 1 to 7.