JPWO2019116471A1 - Power converter and air conditioner - Google Patents

Abstract

A power conversion device (500) that converts DC power into AC power and applies AC power to the electric motor mounted on the compressor (1). An inverter (3) that converts DC power to AC power, and compression. A failure degree calculation unit for calculating a failure degree indicating the degree of failure of the compressor (1) based on a measurement result of a physical quantity indicating the state of the machine (1) is provided.

Description

The present invention relates to a power converter that applies electric power to an electric motor that drives a compressor, and an air conditioner including the electric power converter.

There is a technology for diagnosing failures in refrigeration cycle equipment and the like. For example, in Patent Document 1, an abnormality detection device that detects an abnormality of a device based on a first state value of a device when the drive unit is stopped and a second state value of the device when the drive unit is started. Is disclosed.

International Publication No. 2016/035187

In the compressor, different measures may be desired depending on the degree of failure. For example, depending on the degree of failure, different measures such as stopping the compressor electric motor or changing the operating frequency of the compressor electric motor may be desired. However, the abnormality detection device described in Patent Document 1 performs abnormality determination based on the difference between the specific physical quantity when the drive unit is started and the specific physical quantity when the drive unit is stopped. Therefore, there is a problem that it can only determine the presence or absence of a failure.

The present invention has been made in view of the above, and an object of the present invention is to obtain a power conversion device capable of determining the degree of failure.

In order to solve the above-mentioned problems and achieve the object, the power conversion device according to the present invention is a power conversion device that converts DC power into AC power and applies AC power to an electric motor mounted on a compressor. It is equipped with an inverter that converts DC power to AC power. Further, this power conversion device includes a failure degree calculation unit that calculates a failure degree indicating the degree of failure of the compressor based on the measurement result of a physical quantity indicating the state of the compressor.

The power conversion device according to the present invention has an effect that the degree of failure can be determined.

The figure which shows the configuration example of the power conversion apparatus which concerns on Embodiment 1. The figure which shows the structural example of the compressor of Embodiment 1. The figure which shows the structural example of the inverter of Embodiment 1. The figure which shows the structural example of the arithmetic unit of Embodiment 1. The figure which shows the structural example of the control circuit of Embodiment 1. The figure which shows the configuration example of the power conversion apparatus which uses the measurement result of the vibration state of the compressor of Embodiment 1. FIG. 6 shows a configuration example of a compressor to which AC power is supplied from the power conversion device shown in FIG. 6 of the first embodiment. The figure which shows the structural example of the arithmetic unit of the power conversion apparatus shown in FIG. 6 of Embodiment 1. The figure which shows an example of the vibration level detected by the vibration detection part when the compressor of Embodiment 1 is normal. The figure which shows an example of the vibration level detected by the vibration detection part in the state which the frictional resistance is increased from the normal state by the damage of the specific part of the drive shaft of the compressor of Embodiment 1. The figure which shows the functional structure example of the failure degree calculation part of Embodiment 1. Schematic diagram showing the signal transmission of the neuromodel included in the intermediate portion of the first embodiment. Schematic diagram showing the degree of failure set as a teacher signal when the state of failure is artificially generated according to the first embodiment. The figure which shows the operation example of the power conversion apparatus at the time of taking measures according to the failure degree of Embodiment 1. The figure which shows the structural example of the air conditioner of Embodiment 2.

The power conversion device and the air conditioner according to the embodiment of the present invention will be described in detail below with reference to the drawings. The present invention is not limited to this embodiment.

Embodiment 1.
FIG. 1 is a diagram showing a configuration example of a power conversion device according to a first embodiment of the present invention. The power conversion device 500 of the present embodiment converts the DC power supplied from the DC power source 6 into AC power, and applies the AC power to the compressor 1, specifically, the electric motor described later in the compressor 1. The compressor 1 and the power conversion device 500 of the present embodiment are used in a refrigerant cycle device that uses a refrigeration cycle, such as an air conditioner and a refrigerator. In FIG. 1, the DC power supply 6 and the compressor 1 are also shown together with the power converter 500. As shown in FIG. 1, the power conversion device 500 includes an inverter 3, a voltage detection unit 7, current detection elements 8a and 8b, current detection units 9a and 9b, and a calculation unit 21.

The voltage detection unit 7 measures the DC voltage Vdc, which is the voltage of the DC power applied from the DC power supply 6 to the inverter 3, and outputs the measured DC voltage Vdc to the calculation unit 21. The current detection elements 8a and 8b detect the motor current, which is the current of the AC power applied from the inverter 3 to the compressor 1, and output the detected results to the current detection units 9a and 9b, respectively. The current detection units 9a and 9b amplify the results detected by the current detection elements 8a and 8b, respectively, and output the amplified results to the calculation unit 21 as motor currents Iu and Iw corresponding to the U phase and the W phase, respectively.

Although an example in which the electric motor 2 is a three-phase electric motor will be described here, the number of phases of the electric motor 2 is not limited to this. Further, here, an example will be described in which the motor currents of two of the three phases of the motor 2 are detected and the currents of the remaining phases are obtained by calculation by utilizing the fact that the motor currents are three-phase balanced. The two three-phase motor currents may be detected respectively. Further, when detecting a two-phase motor current by utilizing the fact that the motor current is in three-phase equilibrium, the phase for detecting the motor current is not limited to the above-mentioned U phase and W phase, and among the three phases. It may be two-phase.

FIG. 2 is a diagram showing a configuration example of the compressor 1. As shown in FIG. 2, the compressor 1 includes an electric motor 2, a temperature detection unit 13, and an oil level measurement unit 14. The electric motor 2 includes a U-phase winding 2a, a V-phase winding 2b, and a W-phase winding 2c. The U-phase winding 2a, the V-phase winding 2b, and the W-phase winding 2c are connected to a U-phase terminal, a V-phase terminal, and a W-phase terminal (not shown, respectively).

The temperature detection unit 13 detects the temperature of the compressor 1 and outputs the detected temperature as the temperature Th to the calculation unit 21. The oil level measuring unit 14 measures the height of the oil level of the refrigerating machine oil, which is the lubricating oil in the compressor 1. The oil level measurement unit 14 outputs the detection result, that is, the oil level height Oi in the compressor 1, to the calculation unit 21.

The inverter 3 converts the DC power supplied from the DC power source 6 into AC power, and applies the AC power to the electric motor 2 of the compressor 1. FIG. 3 is a diagram showing a configuration example of the inverter 3. As shown in FIG. 3, the inverter 3 includes switching elements 4a and 4d which are a pair of switching elements, switching elements 4b and 4e which are a pair of switching elements, and switching elements 4c and 4f which are a pair of switching elements. The two switching elements that make up the switching element pair are connected in series. Reflux diodes 5a to 5f are connected in antiparallel to the switching elements 4a to 4f, respectively.

Each switching element pair of the switching element 4a and the switching element 4d, the switching element 4b and the switching element 4e, the switching element 4c and the switching element 4f is referred to as an arm. Each arm is connected in parallel. The midpoint of each arm of the inverter 3 is connected to the phase terminal of the corresponding phase of the motor 2. The midpoint between the switching element 4a and the switching element 4d is connected to the U-phase terminal of the motor 2, and the midpoint between the switching element 4b and the switching element 4e is connected to the V-phase terminal of the motor 2. The midpoint between the 4c and the switching element 4f is connected to the W-phase terminal of the motor 2.

In each switching element pair, the switching element 4a, the switching element 4b, and the switching element 4c, which are the switching elements connected to the positive terminal of the DC power supply 6, are also referred to as the switching element of the upper arm. In each switching element pair, the switching element 4d, the switching element 4e, and the switching element 4f, which are switching elements connected to the negative terminal of the DC power supply 6, are also referred to as lower arm switching elements.

FIG. 4 is a diagram showing a configuration example of the calculation unit 21. As shown in FIG. 4, the calculation unit 21 includes a drive signal generation unit 10, a feature amount calculation unit 11, and a failure degree calculation unit 12. The drive signal generation unit 10 generates a drive signal for controlling the inverter 3 by using the DC voltage Vdc input from the voltage detection unit 7 and the motor currents Iu and Iw input from the current detection units 9a and 9b. Then, the drive signal is output to the inverter 3. Specifically, the drive signal is a PWM signal for controlling PWM (Pulse Width Modulation) of the switching elements 4a to 4f of the inverter 3. Any method may be used for the drive signal generation unit 10 to generate a drive signal, and a general method for generating a PWM signal using a DC voltage Vdc and a motor current can be used.

The drive signal generation unit 10 generates six PWM signals Up, Vp, Wp, Un, Vn, and Wn corresponding to each switching element and outputs them to the inverter 3. The PWM signal Up for the switching element of the upper arm of the U phase is input to the switching element 4a, the PWM signal Vp for the switching element of the upper arm of the V phase is input to the switching element 4b, and the PWM signal Vp for the switching element of the upper arm of the V phase is input to the switching element 4c. Is input with the PWM signal Wp for the switching element of the upper arm of the W phase. The PWM signal Un for the switching element of the lower arm of the U phase is input to the switching element 4d, the PWM signal Vn for the switching element of the lower arm of the V phase is input to the switching element 4e, and the PWM signal Vn for the switching element of the lower arm of the V phase is input to the switching element 4f. Is input with the PWM signal Wn for the switching element of the lower arm of the W phase.

The feature amount calculation unit 11 calculates the feature amount Ia of the motor currents Iu and Iw using the motor currents Iu and Iw. The feature amount will be described later. The failure degree calculation unit 12 calculates the failure degree Jud, which is information indicating the degree of malfunction or failure of the compressor 1, from the temperature Th, the oil level height Oi, and the like.

The hardware configuration of the arithmetic unit 21 will be described. The calculation unit 21 is realized by a processing circuit. This processing circuit may be a processing circuit that is dedicated hardware, or may be a control circuit including a processor. Further, it may be composed of a plurality of processing circuits. In the case of dedicated hardware, the processing circuit may be, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or these. Is a combination of.

When the processing circuit that realizes the arithmetic unit 21 is realized by a control circuit including a processor, this control circuit is, for example, the control circuit 100 having the configuration shown in FIG. FIG. 5 is a diagram showing a configuration example of the control circuit 100 of the present embodiment. The control circuit 100 includes a processor 101 and a memory 102. The processor 101 is a CPU (Central Processing Unit, Central Processing Unit, Processing Device, Arithmetic Logic Unit, Microprocessor, Microcomputer, Processor, also referred to as DSP (Digital Signal Processor)) or the like. The memory 102 corresponds to, for example, a non-volatile or volatile semiconductor memory such as a RAM (Random Access Memory), a ROM (Read Only Memory), or a flash memory.

When the processing circuit that realizes the arithmetic unit 21 is the control circuit 100 including the processor 101, the processor 101 reads and executes the program in which the processing of the arithmetic unit 21 is described stored in the memory 102, thereby executing the arithmetic unit. 21 is realized. The memory 102 is also used as a temporary memory in each process performed by the processor 101.

Next, the operation of this embodiment will be described. In the compressor 1, depending on the connection status of other devices to the device equipped with the compressor 1 and the environmental conditions of the device equipped with the compressor 1, the liquefied refrigerant dissolves in the refrigerating machine oil and accumulates at the time of starting the compressor 1. A state of being depressed, so-called stagnation of the refrigerant, may occur. When the liquefied refrigerant dissolves in the refrigerating machine oil, the viscosity of the refrigerating machine oil decreases, which causes poor lubrication of the compressor 1. In addition, when the refrigerant falls asleep in the path of the refrigerant, the refrigerating machine oil also accumulates together with the refrigerant, so that the refrigerating machine oil may be insufficient. Therefore, the calculation unit 21 can determine that the oil level measured by the oil level measurement unit 14 is in an abnormal state when the height of the oil level deviates from the appropriate range. The state in which the refrigerating machine oil is insufficient and the state in which the viscosity of the refrigerating machine oil is lowered are collectively referred to as poor lubrication.

When the compressor 1 is started in a state where the refrigerating machine oil is insufficient or the viscosity of the refrigerating machine oil is lowered, the sliding portion of the drive shaft of the compressor 1 is slightly scratched. When the operation is performed while maintaining this state, the normal operation is continued for a while, but the damage to the sliding portion is deepened and the load applied to the drive shaft of the compressor 1 increases as the mechanical friction increases. As a result, the compressor 1 may malfunction or malfunction.

In the present embodiment, an index indicating the malfunction or the degree of failure of the compressor 1 is referred to as a failure degree. For example, when the degree of failure is indicated by 5 levels from L (level: Level) 1 to L5, the normal state, that is, the state without failure is defined as L1, and L2 to L5 are defined as the states with malfunction or failure. It is assumed that the degree of failure increases as the value behind it increases. That is, the degree of failure is calculated so that the value becomes the smallest when the compressor 1 is normal, and the value increases as the degree of failure of the compressor 1 increases. The number of failure levels is not limited to this example. The number of levels of the degree of failure may be, for example, two stages of L0 indicating normality and L1 indicating abnormality. That is, the failure degree calculation unit 12 may at least determine whether or not it is normal, that is, whether or not there is a failure.

For example, when the sliding portion of the compressor 1 is damaged in a part of the drive shaft, the frictional resistance of the drive shaft becomes large, so that the load applied to the electric motor 2 becomes large. Specifically, for example, the load increases in a specific section in the time domain, and as a result of the increase in load, the current flowing through the compressor 1 increases. Under the same driving conditions and the same load magnitude applied to the compressor 1, the current flowing through the compressor 1, that is, the motor current is substantially the same. On the other hand, when the motor current increases in a specific section in the time domain, that is, when the motor current exceeds the threshold value, there is a high possibility that a part of the drive shaft is damaged. As the motor current used for determining the presence or absence of damage, for example, one of the motor current Iu and the motor current Iw, or the sum of the motor current Iu and the motor current Iw is used.

In particular, damage to a specific portion of the drive shaft of the compressor 1 appears as a periodic fluctuation in the motor current. That is, by extracting the primary component of the rotation frequency of the compressor 1 or the specific order component of the rotation frequency, that is, the frequency component data of the specific frequency from the motor current, the normal state and the specific part of the drive shaft of the compressor 1 can be obtained. It is possible to distinguish it from an abnormal condition in which damage is present. Therefore, in the present embodiment, the feature amount calculation unit 11 extracts, for example, the primary component of the rotation frequency of the compressor 1 or the specific order component of the rotation frequency as the feature amount from the motor current, and sends it to the failure degree calculation unit 12. Output. The failure degree calculation unit 12 calculates the failure degree based on the feature amount input from the feature amount calculation unit 11. The method of calculating the degree of failure will be described later.

In the above example, an example of determining an abnormality in which a specific portion of the drive shaft of the compressor 1 is damaged is described using the motor current, but when the drive signal generation unit 10 generates a drive signal by vector control. The above-mentioned feature amount and failure degree may be calculated by using the current of the dq-axis component after coordinate conversion used in vector control instead of the motor current. In this case, the influence of higher-order noise components can be removed.

Further, when the refrigerant falls asleep, the refrigerating machine oil stays together with the refrigerant, so that the height of the oil level measured by the oil level measuring unit 14 may deviate from the appropriate range. Therefore, the failure degree calculation unit 12 calculates the failure degree of the compressor 1 based on whether or not the oil level height Oi measured by the oil level measurement unit 14 is within a predetermined appropriate range. It is also possible. When the frictional resistance increases from the normal state due to damage to a specific portion of the drive shaft of the compressor 1, the temperature of the compressor 1 rises from the normal state. Therefore, it is also possible for the failure degree calculation unit 12 to calculate the failure degree based on whether or not the temperature of the compressor 1 exceeds the threshold value based on the temperature Th measured by the temperature detection unit 13.

Further, when the frictional resistance increases from the normal state due to damage to a specific portion of the drive shaft of the compressor 1, the exciting force of the compressor 1 increases from the normal state. Therefore, the calculation unit 21 can also determine the damage of a specific portion of the drive shaft of the compressor 1 by using the vibration state of the compressor 1, particularly the component in the rotation direction, instead of the motor current described above.

FIG. 6 is a diagram showing a configuration example of a power conversion device using the measurement result of the vibration state of the compressor 1. The power conversion device 500a shown in FIG. 6 is the same as the power conversion device 500 of the first embodiment except that the calculation unit 21 of the power conversion device 500 shown in FIG. 1 is replaced with the calculation unit 21a. The power converter 500a applies AC power to the compressor 1a.

FIG. 7 is a diagram showing a configuration example of a compressor 1a to which AC power is supplied from the power conversion device 500a shown in FIG. The compressor 1a is the same as the compressor 1 shown in FIG. 2 except that the vibration detection unit 15 is added to the compressor 1 shown in FIG.

The vibration detection unit 15 detects the vibration of the compressor 1a. The vibration detection unit 15 is a sensor that detects physical quantities related to vibration, specifically physical quantities such as acceleration, velocity, and displacement. The vibration detection unit 15 outputs the detection result, that is, a physical quantity indicating the vibration state of the compressor 1a, as vibration information Vib to the calculation unit 21a. Examples of the vibration detection unit 15 include a sensor using a piezoelectric element and a sensor using a laser, but the vibration detection unit 15 is not limited to these, and any sensor may be used.

FIG. 8 is a diagram showing a configuration example of the calculation unit 21a of the power conversion device 500a shown in FIG. The calculation unit 21a is the same as the calculation unit 21 shown in FIG. 4, except that the failure degree calculation unit 12a is provided instead of the failure degree calculation unit 12. The hardware configuration of the calculation unit 21a is the same as that of the calculation unit 21. The failure degree calculation unit 12a of the present embodiment has the same function as the failure degree calculation unit 12 shown in FIG. 4, and further, the primary component of the rotation frequency from the vibration information Vib input from the vibration detection unit 15. Alternatively, a feature amount such as a specific order component of the rotation frequency is calculated, and the degree of failure is calculated based on the feature amount. In the power converter 500a shown in FIG. 6, the drive shaft of the compressor 1a is based on the vibration information Vib input from the vibration detection unit 15 instead of the motor current or in addition to the failure determination using the motor current. Detects anomalies in which frictional resistance increases from normal due to damage to a specific part of the.

FIG. 9 is a diagram showing an example of the vibration level detected by the vibration detection unit 15 when the compressor 1 is normal. FIG. 10 is a diagram showing an example of a vibration level detected by the vibration detection unit 15 in a state where the frictional resistance is increased from the normal state due to damage to a specific portion of the drive shaft of the compressor 1a. In FIGS. 9 and 10, the vertical axis represents the vibration level and the horizontal axis represents time. The vibration level is, for example, acceleration. When the mechanical angle of the electric motor 2 is 360 degrees as one cycle, in the example shown in FIG. 10, vibration is increased in a specific section within one cycle as compared with the example shown in FIG. The position of the section 200 in FIG. 9 is the same as that of the section 201 shown in FIG. 10, and when the section 200 and the section 201 are compared, it can be seen that the section 201 has a larger vibration level.

In this way, whether or not the vibration level is periodically increased is determined by Fourier transforming the vibration level, that is, the acceleration included in the vibration information Vib, and the frequency corresponding to one cycle of the mechanical angle of the electric motor 2, that is, the rotation frequency. It can be determined by whether or not the primary component or the specific order component of the rotation frequency exceeds the threshold value.

As described above, the failure degree calculation unit 12 shown in FIG. 1 calculates the failure degree based on parameters such as the motor currents Iu and Iw, the temperature Th, and the oil level height Oi. Further, the failure degree calculation unit 12a shown in FIG. 6 calculates the failure degree based on parameters such as motor currents Iu and Iw, temperature Th, oil level height Oi, and vibration information Vib. That is, the failure degree calculation unit 12 and the failure degree calculation unit 12a are failure detection units that detect failures based on parameters such as motor currents Iu and Iw, temperature Th, vibration information Vib, and oil level height Oi. The parameter used by the fault degree calculation unit 12 for fault detection is one or more of the motor currents Iu and Iw, the temperature Th, the oil level height Oi, and the like. The parameters used by the fault degree calculation unit 12a for fault detection are one or more of the motor currents Iu, Iw, temperature Th, vibration information Vib, oil level height Oi, and the like. When the measurement results of a plurality of different types of physical quantities, that is, two or more parameters are used, erroneous detection can be suppressed even when the difference between the specific physical quantities at the time of failure and the normal time is small. For example, the failure degree calculation unit 12 makes a failure determination using each of the two parameters, and if it is determined to be a failure in the failure determination using at least one of the two parameters, it is determined to be a failure. .. The parameters used by the failure degree calculation unit 12 and the failure degree calculation unit 12a to detect the failure may be parameters other than the motor currents Iu, Iw, temperature Th, vibration information Vib, and oil level height Oi. .. For example, the DC voltage Vdc may be included as a parameter. These parameters may be appropriately selected according to the requirements for the device provided with the compressor 1, the installation conditions of the device provided with the compressor 1, and the like.

Next, the degree of failure of the present embodiment will be described. A plurality of failure degrees may be determined for one parameter, or a failure degree may be determined according to the number of parameters determined to be failures in the failure determination using each parameter. In the former case, for example, a threshold value is set for the feature amount in a plurality of stages, and the feature amount input from the feature amount calculation unit 11 is compared with the threshold value in each of the plurality of stages to calculate the degree of failure. For example, the failure degree calculation unit 12 sets L1 when the above-mentioned feature amount obtained by Fourier transforming the motor current exceeds the first threshold value and is equal to or less than the second threshold value. The failure degree calculation unit 12 sets L2 when the above-mentioned feature amount obtained by Fourier transforming the motor current exceeds the second threshold value.

In the latter case, that is, when the degree of failure is determined according to the number of parameters determined to be failure, when the number of parameters determined to be failure in the failure determination using each parameter is one, L2 is set and each parameter is set. Each level is defined such that when the number of parameters determined to be a failure in the failure determination used is two, it is set to L3. Alternatively, the level may be defined by weighting each parameter. For example, the degree of failure calculated by the degree of failure calculation unit 12a is set to level (L) N, the number of level increases is predetermined for each parameter, and ΔL _i is set to the number of level increases of the i-th parameter. The number of levels to be increased is the number of levels to be increased when a failure is determined by the failure determination using the parameter. In this case, N represents, the sum of [Delta] L _i related parameters determined a failure in the failure determination using the parameters. The value of [Delta] L _i of each parameter will correspond to the weight. The weight is determined according to the importance of the parameter.

Further, when a plurality of parameters are used, the failure degree calculation unit 12 determines, for example, a weighting coefficient for each parameter, and calculates the sum of the values obtained by multiplying the deviation amount from the appropriate range of each parameter by the weighting coefficient. The degree of failure may be calculated accordingly.

In the present embodiment, the failure degree calculation units 12 and 12a calculate the failure degree indicating the degree of failure of the compressor 1 based on the measurement result of the physical quantity indicating the state of the compressors 1 and 1a. The measurement results of the physical quantity indicating the state of the compressor 1 are the motor currents Iu and Iw which are the currents flowing through the electric motor 2, the temperature Th of the compressor 1, the vibration information Vib indicating the state of vibration in the compressor 1, and the height of the oil level. Includes parameters such as Oi. The data input to the failure degree calculation unit 12 may be time-series data of physical quantities such as motor currents Iu, Iw, temperature Th, vibration information Vib, and oil level height Oi, or the time-series data may be Fourier-converted. It may be the frequency component data of a specific frequency obtained by the above.

As described above, if the degree of failure is determined and the operation to be performed by the power conversion device 500 is determined for each level indicating the degree of failure, it is possible to perform appropriate processing for the failure. For example, when it is determined to be L2, the power conversion device 500 displays information notifying the abnormality on the internal or external display unit of the power conversion device 500 (not shown in FIG. 1). When it is determined that the value is L3 or higher, the power conversion device 500 displays information notifying the abnormality on the internal or external display unit of the power conversion device 500 (not shown in FIG. 1) and stops the inverter 3. The operation of the power conversion device 500a according to the degree of failure is the same as that of the power conversion device 500.

On the other hand, as described above, when the failure is determined by using a plurality of parameters, the determination using the threshold value is performed for each parameter, and the setting of the threshold value, that is, the rule making of the failure determination becomes complicated. It is also necessary to set the importance, that is, the weight for each parameter.

Therefore, in the present embodiment, the failure degree calculation unit 12 and the failure degree calculation unit 12a calculate the failure degree by using the machine learning system. In the following, an example in which the failure degree calculation unit 12 and the failure degree calculation unit 12a calculate the failure degree by using machine learning will be described, but the failure degree calculation method in the failure degree calculation unit 12 and the failure degree calculation unit 12a Is not limited to this example. Further, in the following, a configuration example will be described by taking the failure degree calculation unit 12a as an example, but the configuration and operation of the failure degree calculation unit 12 are the same as those of the failure degree calculation unit 12a except for the number of input signals. is there.

FIG. 11 is a diagram showing a functional configuration example of the failure degree calculation unit 12a. The failure degree calculation unit 12a has a function as a machine learning system, which is also called a neural network, and has an input unit 23, an intermediate unit 24, and an output unit 25 in the machine learning system. The input unit 23, the intermediate unit 24, and the output unit 25 correspond to the input layer, the intermediate layer, and the output layer in the so-called neuro model, respectively.

When the feature amount Ia of the motor current, the vibration information Vib, the oil level height Oi, and the temperature Th are input, the input unit 23 outputs the input signals to each neuron of the intermediate unit 24, respectively. The middle part 24 has a plurality of neurons. Although the vibration information Vib is directly input to the failure degree calculation unit 12a here, even if the feature amount calculated from the vibration information is input to the failure degree calculation unit 12a in the same manner as the motor current. Good.

FIG. 12 is a schematic view showing the signal transmission of the neuro model included in the intermediate portion 24. The number of input signals input to the intermediate section 24 is n, when the i-th input signal as x _{i (i} = 1 to n), a weighting coefficient is w _i for each input signal, is inputted to each neuron The total sum of the input signals can be expressed by the following equation (1).

Here, each neuron outputs 1 to the subsequent neurons when y shown in the following equation (2) becomes 1, that is, when the sum of the input signals exceeds the threshold value θ. Note that f _h (x) in equation (2) is a step function as shown in equation (3). As f _h (x), a sigmoid function or the like may be used instead of the step function.

When the intermediate portion 24 has one layer, the output from each neuron of the intermediate portion 24 is input to the output unit 25. When the intermediate portion 24 has two or more layers, the output signal from each neuron in the intermediate portion 24 is input to each neuron in the next layer, and the same operation is performed by the neurons in each layer. Then, an output signal is output from the final layer of the intermediate unit 24 to the output unit 25. The output unit 25 uses the output signal output from the intermediate unit 24 as an input signal, and calculates the output signal according to the equation (2) in the same manner as each neuron in the intermediate unit 24. However, in the output unit 25, a sigmoid function or the like is used as f _h (x). The result output from the output unit 25 is the failure degree Jud.

Weight coefficient w _i for each neuron may be calculated by the backpropagation method using the teacher signal. That is, supervised learning is used as the machine learning used by the failure degree calculation unit 12a. The teacher signal is set so as to perform the operation in a normal state and the operation in an abnormal state under various conditions, respectively, and obtain a desired degree of failure in this state. Thus, the weight coefficient _{w i} is determined. For example, L1 corresponds to the output value 0.1 of the output unit 25, L2 corresponds to the output value 0.2 of the output unit 25, L3 corresponds to the output value 0.4 of the output unit 25, and L4 is output. Corresponds to the output value of 0.6 of the output unit 25, and corresponds to the output value of 0.9 of the output unit 25 of L5. Then, similarly, when operating in a normal state, the teacher signal is set so as to correspond to the output value 0.1 of the output unit 25, and the state of L5 corresponds to the output value 0.9 of the output unit 25. Set the teacher signal, such as set the teacher signal to. The output value of the output unit 25 corresponding to each level is not limited to this example.

FIG. 13 is a schematic diagram showing the degree of failure set as a teacher signal when a failure state is artificially generated. In the example shown in FIG. 13, three parameters used for calculating the degree of failure are the feature amount of the motor current, the temperature of the compressor 1, and the oil level height. The failure state is artificially simulated by adjusting the operating conditions. Since the failure state changes with time, each parameter also changes according to the failure state.

The operation is started from time T0, and the compressor 1 is normal at this point. Therefore, the teacher signal corresponding to the time T0 is set to 0 corresponding to L0.

At time T1, the feature amount of the motor current is I1, the temperature of the compressor 1 indicated by the temperature information is Th1, and the oil level height is Oi1. At time T1, it is in a normal state. Therefore, the teacher signal corresponding to the time T1 is set to 0.1 corresponding to L1.

After time T2, the drive shaft of the compressor 1 is gradually damaged. At time T3, the characteristic amount of the motor current deviates from the normal range, and some measures are required. The teacher signal corresponding to the time T3 is set to 0.4 corresponding to L3. At time T4, the feature amount of the motor current and the temperature of the compressor 1 deviate from the normal range. The teacher signal corresponding to the time T4 is set to 0.6 corresponding to L4.

At time T5, the feature amount of the motor current, the temperature of the compressor 1 and the oil level height all deviate from the normal range. The teacher signal corresponding to the time T5 is set to 0.9 corresponding to L5, which is the maximum failure degree. As described above, the teacher signals for each condition are set for each of the environmental conditions and the operating conditions, and the machine learning system of the failure degree calculation unit 12a is made to learn. As a result, the weighting factor is set.

When the weighting coefficient is set, the failure degree calculation unit 12a can perform the failure diagnosis in the actual operation by using the set weighting coefficient. As an example of the operation of the power conversion device 500a after the failure degree is calculated by the failure degree calculation unit 12a, for example, when the failure degree exceeds the threshold value, the operation frequency of the electric motor 2 that stops the operation of the inverter 3 is set. Lower than normal. Specifically, the drive signal generation unit 10 which is a control unit controls the inverter 3 based on the degree of failure. Alternatively, the power converter 500a may notify the user that a failure of the compressor 1 has been detected according to the degree of failure. The method of notifying the user may be a method of notifying by voice such as a buzzer, or a method of notifying by displaying on a display unit (not shown).

For example, the drive signal generation unit 10 lowers the operating frequency of the electric motor 2 from the normal operating frequency when the degree of failure exceeds the first threshold value, and sets a second threshold value in which the degree of failure is greater than the first threshold value. The inverter 3 is controlled so as to stop the electric motor 2 when the frequency exceeds the limit. Further, the power conversion device 500a notifies the user that the failure of the compressor 1a has been detected when the degree of failure exceeds the first threshold value or when the degree of failure exceeds the second threshold value.

FIG. 14 is a diagram showing an operation example of the power conversion device 500a when a countermeasure is taken according to the degree of failure. In the example shown in FIG. 14, the power converter 500a lowers the operating frequency of the electric motor 2 from the normal operating frequency fm1 when the degree of failure is L3 or higher, and when the degree of failure is L4 or higher, the operating frequency is lowered. The operation of the inverter 3 is stopped, that is, the output of the PWM signal from the inverter 3 is prohibited. Specifically, for example, the failure degree output from the failure degree calculation unit 12a is input to the drive signal generation unit 10, and when the failure degree is L3 or more, the drive signal generation unit 10 sets the operating frequency of the electric motor 2. A drive signal is generated so as to decrease from the normal operating frequency fm1. Further, when the degree of failure is L4 or higher, the drive signal generation unit 10 does not output the drive signal to the inverter 3. The operation corresponding to the degree of failure in the power conversion device 500 is the same as the operation corresponding to the degree of failure in the power conversion device 500a.

As described above, in the power conversion devices 500, 500a of the present embodiment, the degree of failure is quantified as the degree of failure, so that information such as whether the failure has a high degree of urgency or a minor malfunction can be obtained. It is also possible to present it to the user. Further, by determining the countermeasures according to the degree of failure, it is possible to promptly take measures such as stopping the inverter 3 when the degree of failure is high.

Further, in the present embodiment, a plurality of parameters are used for the failure diagnosis of the compressor 1. Therefore, if there is a parameter in which the difference in the specific physical quantity is small between the time of failure and the normal time, even if the failure cannot be detected by the parameter, it can be determined as the failure by other parameters, so that the false diagnosis can be suppressed. Can be done. Therefore, stable control that suppresses erroneous diagnosis can be realized, and the quality of the product can be improved.

Further, in the power conversion device 500, 500a of the present embodiment, by performing the failure diagnosis using the machine learning system, the setting of the threshold value and the like for the failure diagnosis using a plurality of parameters is not complicated. Therefore, it is possible to carry out the failure diagnosis while suppressing the labor of the work for setting the threshold value and the like.

Embodiment 2.
FIG. 15 is a diagram showing a configuration example of the air conditioner according to the second embodiment of the present invention. The air conditioner 501 of the present embodiment includes the compressor 1 and the power conversion device 500 described in the first embodiment. In the air conditioner 501 of the present embodiment, the compressor 1, the four-way valve 82, the outdoor heat exchanger 83, the expansion valve 84, and the indoor heat exchanger 85 equipped with the electric motor 2 described in the first embodiment are the refrigerant pipes 86. It has a refrigeration cycle, that is, a refrigeration cycle device, which is attached via a separate air conditioner to form a separate air conditioner. AC power is supplied to the electric motor 2 from the power converter 500.

A compression mechanism 87 that compresses the refrigerant and an electric motor 2 that operates the compressor 1 are provided inside the compressor 1, and the refrigerant circulates between the compressor 1 and the outdoor heat exchanger 83 and the indoor heat exchanger 85 to perform heating and cooling. The refrigeration cycle to be performed is configured. The configuration shown in FIG. 15 can be applied not only to an air conditioner but also to a device having a refrigerating cycle such as a refrigerator and a freezer.

Further, in the above-described embodiment, the example in which the air conditioner 501 includes the compressor 1 and the power converter 500 has been described, but the air conditioner 501 uses the compressor 1a and the power converter 500a instead of these. You may prepare. As described above, the power conversion devices 500, 500a of the first embodiment can be mounted on an apparatus such as an air conditioner.

The configuration shown in the above-described embodiment shows an example of the content of the present invention, can be combined with another known technique, and is one of the configurations without departing from the gist of the present invention. It is also possible to omit or change the part.

1,1a Compressor, 2 Electric motor, 3 Inverter, 6 DC power supply, 7 Voltage detector, 8a, 8b Current detector, 9a, 9b Current detector, 10 Drive signal generator, 11 Feature calculation unit, 12, 12a Failure degree calculation unit, 13 temperature detection unit, 14 oil level measurement unit, 21,21a calculation unit, 23 input unit, 24 intermediate unit, 25 output unit, 500,500a power conversion device.

In order to solve the above-mentioned problems and achieve the object, the power conversion device according to the present invention is a power conversion device that converts DC power into AC power and applies AC power to an electric motor mounted on a compressor. It is equipped with an inverter that converts DC power to AC power. Further, this power conversion device includes a failure degree calculation unit that calculates a failure degree indicating the degree of failure of the compressor based on frequency component data of a specific frequency of a physical quantity indicating the state of the compressor.

Claims (10)

A power conversion device that converts DC power into AC power and applies the AC power to the electric motor mounted on the compressor.
An inverter that converts the DC power into the AC power,
A failure degree calculation unit that calculates the failure degree indicating the degree of failure of the compressor based on the measurement result of the physical quantity indicating the state of the compressor, and
A power converter equipped with. A control unit that controls the inverter based on the degree of failure,
The power conversion device according to claim 1. The degree of failure is calculated so that the value becomes the smallest when the compressor is normal, and the value increases as the degree of failure of the compressor increases.
When the degree of failure exceeds the first threshold value, the control unit lowers the operating frequency of the electric motor from the normal operating frequency, and the degree of failure exceeds a second threshold value larger than the first threshold value. The power conversion device according to claim 2, wherein the inverter is controlled so as to stop the electric motor in such a case. A claim that the power conversion device notifies the user that a failure of the compressor has been detected when the failure degree exceeds the first threshold value or when the failure degree exceeds the second threshold value. The power conversion device according to 3. The measurement result of the physical quantity indicating the state of the compressor is at least one of the current flowing through the electric motor, the temperature of the compressor, the state of vibration in the compressor, and the height of the oil level of the lubricating oil in the compressor. The power conversion device according to any one of claims 1 to 4, which includes one. The power conversion device according to any one of claims 1 to 5, wherein the measurement result of the physical quantity indicating the state of the compressor is the measurement result of a plurality of different types of physical quantities. The power conversion device according to any one of claims 1 to 6, wherein the failure degree calculation unit calculates the failure degree by using machine learning. The power conversion device according to claim 7, wherein the machine learning is supervised learning. The power conversion device according to claim 7 or 8, wherein the input data to the machine learning is time series data or frequency component data of a specific frequency. A compressor equipped with an electric motor and
The power conversion device according to any one of claims 1 to 9, which applies AC power to the electric motor.
Air conditioner equipped with.

Images