Centralized management system and centralized management method

Abstract

A centralized management system (SYS) comprising a data processor (101) that collects information regarding at least one electric motor (5) and a management device (200) that communicates with the data processor (101) via a communication network (400). The data processor (101) stores current data which corresponds to a certain period of time and is obtained by measuring a current (Iuv) flowing through the electric motor in a time-division manner and transmits current data (Iu_lim[n]) in a data amount divided in correspondence to the current frequency of the electric motor to the management device (200) via the communication network (400). The data processor (101) transmits deterioration estimation information (West[n]) to the management device together with the current data, the deterioration estimation information (West[n]) being used for identifying a cause of an abnormality in the electric motor.

Description

Technical Field

[0005] ,

[0001] The present disclosure relates to a centralized management system, a learning device, and a centralized management method.

Background Art

[0002] When driving a compressor equipped with an electric motor having a bearing, many failures are caused by deterioration of the bearing of the electric motor or damage to the bearing. If the compressor is used in a state where the bearing of the electric motor is worn and deteriorated, the electric motor stops due to the deterioration, resulting in a large downtime (stop time) in the operation of the compressor and a decrease in the operation rate of the compressor. Therefore, it is preferable to detect the deterioration of the bearing of the electric motor before the electric motor stops due to the wear of the bearing and take appropriate measures such as repairing the deteriorated bearing of the electric motor. By doing so, the downtime of the compressor can be reduced or shortened, and the operation rate of the compressor can be improved.

[0003] International Publication No. 2022 / 030516 (Patent Document 1) discloses an abnormality determination device including an abnormality determination unit that determines an abnormality of a mechanical element of a compressor based on an electrical characteristic quantity of the compressor driven by an electric motor. Here, the electrical characteristic quantity is a specific frequency component of a signal representing a physical quantity correlated with the current of the electric motor driving the compressor, and the specific frequency component is a component that is a positive integer multiple of the rotation frequency of the compressor. The abnormality determination unit makes a determination regarding an abnormality of a mechanical element of the compressor in consideration of fluctuations in the relationship between the abnormality of the mechanical element and the electrical characteristic quantity of the compressor due to a change in the rotation frequency of the compressor.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] Building owners and other users have a need to centrally monitor whether the motor bearings are deteriorating in multiple properties they manage. However, the technology disclosed in International Publication No. 2022 / 030516 (Patent Document 1) does not envision improving the accuracy of anomaly detection using information from multiple compressors. Therefore, there is a problem in that high-precision analysis is not possible, making it difficult to improve services to users.

[0006] This disclosure provides a centralized management system that solves the above-mentioned problems, with the aim of collecting a large amount of data to perform highly accurate analysis and provide better services to users. [Means for solving the problem]

[0007] This disclosure relates to a centralized management system. The centralized management system comprises a data processor that collects information on at least one electric motor, and a management device that communicates with the data processor via a communication network. The data processor stores current data measured in time division for a certain period of time, divides the current data into amounts corresponding to the current frequency of the motor, and transmits the current data to the management device via the communication network. Along with the current data, the data processor transmits degradation estimation information, which is information used to identify the cause of the abnormality of the electric motor, to the management device. [Effects of the Invention]

[0008] According to the centralized management system described in this disclosure, highly accurate analysis can be performed from a large amount of data, enabling the provision of services to users. [Brief explanation of the drawing]

[0009] [Figure 1] This is a block diagram illustrating an example configuration of the centralized management system according to Embodiment 1. [Figure 2] This is a cross-sectional view showing an example of the internal structure of a compressor. [Figure 3]This is a cross-sectional view of the bearing during normal operation, with the main shaft and main bearing in a lubricated state. [Figure 4] This is a cross-sectional view of a bearing during abnormal operation when the main shaft and main bearing are not in a lubricated state. [Figure 5] This is a control block diagram of the management device according to Embodiment 1. [Figure 6] This is a block diagram illustrating an example of processing in the centralized management system according to Embodiment 1. [Figure 7] This is a flowchart illustrating an example of processing performed by the data processor within the control unit. [Figure 8] This is a diagram illustrating the data processing of current data. [Figure 9] This diagram illustrates an example of degradation allocation processing in the data processor within the control unit. [Figure 10] This is a flowchart to explain the timing of output to the network. [Figure 11] This is a diagram illustrating the data storage status in the management device according to Embodiment 1. [Figure 12] This is a flowchart illustrating an example of processing performed by the control device. [Figure 13] This is a diagram illustrating an example of processing in the control device according to Embodiment 1. [Figure 14] This is a control block diagram of the control device according to Embodiment 2. [Figure 15] This is a diagram illustrating an example of processing in the centralized management system according to Embodiment 3. [Figure 16] This is a diagram illustrating the data storage status in the management device according to Embodiment 3. [Figure 17] This is a flowchart illustrating the output timing to the communication network according to Embodiment 4. [Modes for carrying out the invention]

[0010] Hereinafter, a centralized management system, a learning device, and a centralized management method according to an embodiment will be described with reference to the drawings. Here, in each drawing, components denoted by the same reference numerals are the same or corresponding components, and are assumed to be common components in all the embodiments described below. Also, the forms of the components shown in all the embodiments described below are merely examples, and are not limited to the forms described below. In particular, the combinations of components are not limited to the combinations in each embodiment, and components described in other embodiments can be applied to other embodiments. Furthermore, regarding the high or low of parameters such as pressure and temperature, it is not determined in relation to absolute values in particular, but is determined relatively in the states and operations of devices and the like.

[0011] Embodiment 1. The centralized management system SYS will be described with reference to the drawings. FIG. 1 is a block diagram for explaining a configuration example of the centralized management system according to Embodiment 1. The centralized management system SYS shown in FIG. 1 includes a management device 200 and a data processor 101.

[0012] The object of fault diagnosis of the centralized management system SYS is an electric motor (not shown) included in the compressor 5. A plurality of outdoor units 1000, 2000, 3000... are connected to the management device 200 via a communication network 400. The data processor 101 is mounted on a control device 100 included in each outdoor unit.

[0013] The configuration of the following outdoor unit 1000 will be typically described, but the outdoor units 2000, 3000... have the same configuration.

[0014] The configuration for driving the compressor 5 includes an AC power supply 1, a rectifier circuit 2, an electrolytic capacitor 3, and an inverter 4. The rectifier circuit 2 converts three-phase (UVW phase) AC power from the AC power supply 1 into DC power. The electrolytic capacitor 3 smooths the DC power from the rectifier circuit 2. The inverter 4 converts the DC power from the rectifier circuit 2 into three-phase AC power and outputs the three-phase AC power to the compressor 5. The current sensor 6 is installed in the wiring 7 from the inverter 4 to the compressor 5 and detects the current Iuv (e.g., current Iu and current Iv) of two phases of the three-phase AC power flowing from the inverter 4 to the compressor 5.

[0015] The configuration for driving the compressor 5 further includes a control device 100 that controls the driving of the compressor 5. The control device 100 controls and drives the compressor 5 by outputting a gate pulse GP to the inverter 4 based on the results detected by the current sensor 6 and the bus voltage 8. The management device 200 also collects data from the control devices in multiple outdoor units via the communication network 400. The management device 200 then analyzes the collected data and outputs the maintenance costs required to the notification device 300 via the network 500. The management device 200 is, for example, a server connected to the notification device 300 and the outdoor units 1000 via the communication network 400.

[0016] The control device 100 comprises a data processor 101, a CPU (Central Processing Unit) 102, memory 103 (ROM (Read Only Memory) and RAM (Random Access Memory)), and input / output buffers (not shown), etc. The data processor 101 and CPU 102 load the programs stored in ROM into RAM, etc., and execute them. The programs stored in ROM are programs that describe the processing procedures of the control device 100. The control device 100 controls each piece of equipment in the refrigeration cycle system according to these programs. The control device 100 can be implemented using hardware such as a computer that executes various programs, and for the calculation unit that performs various processes, for example, an FPGA (Field-Programmable Gate Array) can be used instead of the data processor 101 or CPU 102. This control is not limited to software processing, but can also be processed by dedicated hardware (electronic circuits).

[0017] The control device 100 processes signals using its internal data processor 101 and transmits the processed signals to the communication network 400. The management device 200 receives signals from the communication network 400, calculates maintenance costs from those signals, and outputs them to the notification device 300. The notification device 300 notifies the user or maintenance team of the maintenance costs calculated by the management device 200. For example, the notification device 300 is installed on the indoor unit monitor and the maintenance team's management monitor. The communication network 400 is, for example, a LAN, and the network 500 is, for example, the Internet.

[0018] Figure 2 is a cross-sectional view showing an example of the configuration of the compressor 5 in Figure 1. As shown in Figure 2, the compressor 5 includes an intake pipe 51, a main shaft 52, an electric motor 53, an oil pump 55, a sub-bearing 56, a main bearing 57, a compression mechanism 58, and a discharge pipe 59. These are housed in the casing of the compressor 5. Lubricating oil 54 is stored at the bottom of the casing.

[0019] The compressor 5, which is part of the air conditioning system, is connected to other elements by refrigerant piping to form a refrigeration cycle. As will be described later, the refrigerant is drawn in through the suction pipe 51 of the compressor 5 and discharged through the discharge pipe 59.

[0020] The suction pipe 51 is a pipe for drawing low-temperature, low-pressure refrigerant into the compressor 5. Pressure sensors, temperature sensors, humidity sensors, etc., may be attached to the suction pipe 51 to measure the pressure, temperature, humidity, etc., of the refrigerant flowing through the pipe. Alternatively, these sensors may be attached to the piping within the air conditioning equipment to estimate the pressure, temperature, humidity, etc., of the refrigerant flowing through the suction pipe 51.

[0021] The electric motor 53, although not shown in the diagram, is connected to a three-phase AC power line and is driven according to the voltage applied from the inverter 4. The main shaft 52 is connected to the electric motor 53 and transmits rotational energy to the compression mechanism 58. Lubricating oil 54 is stored at the bottom of the compressor 5 housing and is supplied to the sub-bearing 56 and the main shaft 52 by the oil pump 55, lubricating the sub-bearing 56 and the main shaft 52. In order to check the amount of lubricating oil 54, a liquid level sensor capable of detecting the height of the oil level of the lubricating oil 54 may be installed and the amount of lubricating oil 54 may be measured.

[0022] The discharge pipe 59 is a pipe for discharging the high-temperature, high-pressure refrigerant compressed by the compression mechanism 58 to the outside of the compressor 5. Pressure sensors, temperature sensors, humidity sensors, etc., may be attached to the discharge pipe 59 to measure the pressure, temperature, humidity, etc., of the refrigerant flowing through the pipe. Alternatively, these sensors may be attached to the piping inside the air conditioning equipment to estimate the pressure, temperature, humidity, etc., of the refrigerant flowing through the discharge pipe 59.

[0023] Furthermore, the state of the main shaft 52 and main bearing 57 when the compressor 5 is driven will be explained using Figures 3 and 4. Figure 3 is a cross-sectional view of the bearing when the main shaft 52 and main bearing 57 are lubricated and under normal operation. Figure 4 is a cross-sectional view of the bearing when the main shaft 52 and main bearing 57 are not lubricated and under abnormal operation. Note that the main bearing 57 is a sliding bearing as an example.

[0024] As shown in Figure 3, during normal operation, sufficient lubricating oil 54 fills the space between the main shaft 52 and the main bearing 57, allowing the main shaft 52 to rotate smoothly while maintaining a certain clearance from the main bearing 57. On the other hand, as shown in Figure 4, during abnormal operation, the viscosity of the lubricating oil 54 decreases due to the effects of temperature, aging, etc., making it impossible to maintain an oil film between the main shaft 52 and the main bearing 57. As a result, the main shaft 52 and the main bearing 57 come into contact in some areas, and wear occurs on the main bearing 57 at this contact point. If the main shaft 52 continues to rotate while the main bearing 57 is worn, the wear on the main bearing 57 will worsen and deteriorate further. Ultimately, this may cause the compressor 5 to stop (downtime), reducing its operating rate. At the same time, runout occurs with each cycle of the machine angle, which may accelerate deterioration and further reduce the operating rate of the compressor 5.

[0025] Next, the control of the management device 200 will be described. Figure 5 is a control block diagram of the management device according to Embodiment 1. The management device 200 includes a database (DB) 201, a learning unit 202, an inference unit 203, and a maintenance cost calculation unit 204.

[0026] Regarding the database (DB) 201, as detailed in Figure 6, it processes data from the communication network 400 and outputs data DWA linked to degradation to the learning unit 202. As detailed in Figure 12, the learning unit 202 performs machine learning using the data DWA linked to degradation and outputs a pattern generation function PGF to the inference unit 203. The inference unit 203 uses the limit current data Iu_lim[n] from the communication network 400 and the pattern generation function PGF to output the compressor degradation degree West[n] to the maintenance cost calculation unit 204. As will be described later, the maintenance cost calculation unit 204 calculates the maintenance cost from the degradation degree.

[0027] Next, the details of the internal processing of the data processor 101, the communication network 400, and the management device 200 will be explained using Figure 6. Figure 6 is a block diagram illustrating an example of processing in the centralized management system according to Embodiment 1. The data processor 101 is composed of a limit count calculation processing unit 1011, a data limit processing unit 1012, a drive time count processing unit 1013, and a degradation allocation processing unit 1014. The data processor 101 operates as these processing units according to the software that is loaded. The details of the control performed by these processing units will be explained below.

[0028] The limit quantity calculation processing unit 1011 calculates the limit quantity N_lim[n] based on the U-phase current Iu. Details of the limit quantity calculation processing unit 1011 will be explained using Figure 7. Figure 7 is a flowchart illustrating an example of processing in the data processor within the control device. In Figure 7, the data processor 101 executes the process of reading the current Iu in step S1011-1. In Figure 7, the U-phase current Iu is read, but the W-phase current Iw may also be read, or the V-phase current calculated from the U-phase current Iu and the W-phase current Iw may be read. Furthermore, it is preferable to measure the U-phase current and W-phase current during the stable operation of the motor 53. That is, it is preferable to measure the current at a timing when there is little load fluctuation or speed fluctuation.

[0029] For example, if speed control is implemented, measuring the current at a time when speed fluctuations are minimal can be achieved by controlling the motor so that the speed command value remains constant for a certain period. Similarly, if torque control is implemented, measuring the current at a time when load fluctuations are minimal can be achieved by controlling the motor so that the torque command value remains constant for a certain period. By adjusting the timing in this way, it is possible to collect data with minimal current fluctuations during the stable operation of the motor, enabling highly accurate analysis and providing better service to air conditioner users.

[0030] In step S1011-2, the data processor 101 performs a moving average operation on the U-phase current Iu read in step S1011-1 to mitigate the effects of switching noise from the inverter 4. This moving average operation is performed in step S1011-3, described later, to prevent false detection due to chattering when the U-phase current Iu value is near zero.

[0031] In step S1011-3, the data processor 101 detects the timing (zero-crossing timing) when the value of the U-phase current Iu, which has been subjected to moving average processing in step S1011-3, crosses zero. Further explanation is given using Figure 8. Figure 8 is a diagram for explaining the data processing of current data. In Figure 8, the elapsed time is shown on the horizontal axis and the compressor current is shown on the vertical axis. As shown in Figure 8, in this zero-crossing detection process, the times when the elapsed time becomes zero are detected in order from shortest to longest: T[0], T[1], T[2]... Here, this zero-crossing timing is denoted as T[n] (where n is a non-negative integer).

[0032] Returning to Figure 7, in step S1011-4, the data processor 101 calculates the frequency F[n] (where n is a non-negative integer) corresponding to one period of the mechanical angle. For example, the frequency F[n] is calculated using the timing T[n] (where n is a non-negative integer) detected in step S1011-3, as shown in equation (1). Note that P represents the number of pole pairs, and when calculated with P=1, the electrical angle and mechanical angle are the same. However, if the number of pole pairs P is a positive integer other than 1, the frequency F[n] corresponding to the mechanical angle can be calculated. F[n]=1 / (T[2nP+2P]- T[2nP]) ···(1) Next, in step S1011-5, the data processor 101 calculates the limit number N_lim[n] using the frequency F[n] calculated in equation (1) and the sampling time Tsam, as shown in equation (2). This allows for the sequential calculation of the number of data points corresponding to one period of the machine angle. Here, the sampling time Tsam is the reciprocal of the carrier frequency and is a fixed value. N_lim[n]=(1 / F[n]) / Tsam ···(2) According to equation (2), when the rotational speed of the motor is increasing (accelerating), N_lim[n] decreases as n increases, and when the rotational speed of the motor is decreasing (deceleration), N_lim[n] increases as n increases. Also, when the motor is operating at a constant speed, N_lim[n] does not change.

[0033] Returning to Figure 6, the data limiting processing unit 1012 outputs the limiting current Iu_lim[n] to the communication network 400 based on the U-phase current Iu and the limiting number N_lim[n] calculated by the limiting number calculation processing unit 1011.

[0034] Figure 8 illustrates the details of the control of the limit quantity calculation processing unit 1011. At regular intervals, the limit quantity calculation processing unit 1011 extracts data for the limit quantity N_lim[n] from the stored compressor current data and uses it as the limit current Iu_lim[n] data. This allows the amount of data corresponding to one machine angle cycle to be sequentially output to the communication network 400.

[0035] Returning to Figure 6, the drive time counting unit 1013 has internal memory and counts the drive time of the compressor 5 from the U-phase current Iu based on the limited number N_lim[n], and outputs the operating time Twork[n] to the degradation allocation unit 1014. Specifically, the drive time counting unit 1013 starts counting when the compressor 5 is started and the U-phase current Iu is flowing, and stops counting when the compressor 5 stops. Furthermore, when the compressor 5 is started again, the drive time counting unit 1013 starts counting from the value at the time of the previous count stop.

[0036] The degradation assignment processing unit 1014 executes a process to assign a degradation degree West[n] according to the operating time Twork[n] status from the drive time count processing unit 1013. The process executed by the degradation assignment processing unit 1014 will be specifically explained using Figure 9. Figure 9 is a diagram to explain an example of the degradation assignment process in the data processor within the control device. In Figure 9, the horizontal axis represents operating time, and the vertical axis represents the degradation degree.

[0037] For operating time, operating time WT1 and WT2 are set as thresholds in advance. Operating time WT1 is the time it takes for the compressor 5 to transition from normal to minor deterioration (minor deterioration in Figure 9). Operating time WT2 is the time it takes for the compressor 5 to transition from minor deterioration to severe deterioration (severe deterioration in Figure 9). In other words, operating time is divided into a normal operating time interval (WT0 to WT1), a minor deterioration operating time interval (WT1 to WT2), and a severe deterioration operating time interval. time It is set for the interval (WT2 and later).

[0038] Therefore, the degradation assignment processing unit 1014 assigns whether the degradation state of the compressor 5 is normal, slightly degraded, or severely degraded based on the operating time Twork[n], and outputs the degradation degree West[n] to the communication network 400. Regarding thresholds such as WT1 and WT2, the current distortion, kurtosis, and imbalance are calculated for each individual compressor from past current data Iu_lim[n], and thresholds such as WT1 and WT2 are set for each individual compressor based on these values. Furthermore, as will be described later, in order to exclude the influence of initial defects in the compressor 5, an operating time determination value WTS may be set in advance, and the degradation degree West[n] may be output to the communication network 400 using the operating time Twork[n] after this determination value WTS.

[0039] By obtaining the degree of degradation from the current waveform, existing sensor information (current sensor) can be used, thus suppressing the increase in the amount of data and cost compared to obtaining the degree of degradation using a separate sensor.

[0040] Next, the timing of data output to the communication network 400 will be explained using Figure 10. Figure 10 is a flowchart for explaining the timing of output to the network. First, in step S101-1, the data processor 101 calculates the operating time Twork[n] of the compressor 5 as a process of the drive time count processing unit 1013 in Figure 6.

[0041] Next, in step S101-2, the data processor 101 determines whether the operating time Twork[n] calculated in step S101-1 is greater than or equal to the judgment value WTS (see Figure 9). If the operating time Twork[n] is greater than or equal to the judgment value WTS (Yes in S101-2), the process proceeds to steps S101-3 and S101-5. On the other hand, if the operating time Twork[n] is less than the judgment value WTS (No in S101-2), the process returns and steps S101-1 is executed again. As a result, current data and operating time can be linked, enabling highly accurate analysis and providing better service to air conditioner users.

[0042] In step S101-3, the data processor 101, acting as the limit count calculation processing unit 1011 in Figure 6, calculates the limit count N_lim[n] for one mechanical angle period of the U-phase current Iu. Next, in step S101-4, the data processor 101, acting as the data limit processing unit 1012 in Figure 6, uses the limit count N_lim[n] calculated in step S101-3 to divide the buffered U-phase current Iu data (Iu_lim[n]).

[0043] The data processor 101, acting as the degradation allocation processing unit 1014 in Figure 6, executes the processes in steps S101-5 and S101-6.

[0044] In step S101-5, the data processor 101 assigns the degradation degree West[n] according to the operating time Twork[n]. In step S101-6, the data processor 101 synchronizes the timing of the limiting current Iu_lim[n] processed in step S101-4 with the degradation degree West[n] and outputs it to the communication network 400.

[0045] Although steps S101-3 and S101-4 and step S101-5 are intended to be performed concurrently, they may also be executed sequentially. In this case, the order in which steps S101-3 and S101-4 and step S101-5 are executed does not matter.

[0046] Furthermore, although the above explanation describes a single outdoor unit, similar processing can be performed on multiple outdoor units to sequentially output data to the communication network 400.

[0047] Returning to Figure 6, let's explain the processing of the database (DB) 201 within the management device 200. The database (DB) 201 consists of a frequency conversion processing unit 2011 and a normalization processing unit 2012. The database (DB) 201 generates data DWA associated with degradation from the limiting current Iu_lim[n] and degradation degree West[n] from the communication network 400. The frequency conversion processing unit 2011 performs a process to convert the limiting current Iu_lim[n] into the frequency domain and generates a spectrum SPE[n] corresponding to the frequency. Next, the normalization processing unit 2012 performs a normalization process by dividing the spectrum SPE[n] by the fundamental wave component. For example, if the fundamental wave component is first order, the process of dividing the spectrum of each order in the spectrum SPE[n] by the first order spectrum is performed, so the value of the first order component becomes 1, and the values ​​of the other order components become numbers indicating how many times they are compared to the first order spectrum.

[0048] Next, Figure 11 will be used to explain the DWA data associated with degradation. Figure 11 is a diagram illustrating the data storage status in the management device according to Embodiment 1. Figure 11 shows the storage status in the database (DB) 201 of Figure 6. In Figure 11, the horizontal columns represent the order representing the frequency domain, and the vertical rows show the spectral values ​​normalized for each n (where n is a non-negative integer).

[0049] For example, at n=0, the 0th order A0 represents the DC component, the 1st order "1" represents the spectrum of the fundamental wave (1st order), the 2nd order A2 represents the spectrum of the 2nd harmonic, and the 3rd order A3 represents the spectrum of the 3rd harmonic.

[0050] Database (DB) 201 performs normalization using the fundamental wave (first order), so as mentioned above, the value for the first order becomes "1," and values ​​of other orders A2, A3, etc., that are less than 1 are accumulated and stored. Furthermore, for each row [n], database (DB) 201 is constructed by placing the spectrum SPE[n] in the leftmost column and the degradation degree West[n] in the rightmost column. Thus, over time, the spectrum SPE[n] and degradation degree are accumulated and stored in database (DB) 201. Since sliding bearings cannot automatically repair degradation, the longer the operating time, that is, the higher n is, the worse the degradation progresses.

[0051] Next, an example of operation in the management device 200 of this embodiment 1 will be described with reference to the flowchart showing the processing procedure in Figure 12. Figure 12 is a flowchart illustrating an example of processing in the management device. Note that the processing procedure described below is an example of the learning method of this disclosure. Therefore, each process may be modified as much as possible, and depending on the embodiment, processes can be omitted, replaced, and added as appropriate.

[0052] Figure 12 shows, in order, the processes executed by the learning unit 202, inference unit 203, and maintenance cost calculation unit 204 shown in Figure 5.

[0053] First, the learning unit 202 performs machine learning and creates a trained model. The inference unit 203 then performs inference using the trained model created through machine learning. From here on, the processing differs depending on whether machine learning is performed or inference is performed, so we will first explain the processing procedure when machine learning is performed.

[0054] In step S202-1, the learning unit 202 refers to the data DWA associated with degradation and obtains the spectrum SPE[n] from the data DWA as input data. "Data DWA associated with degradation" refers to the table in Figure 11 in one example. Spectrum SPE[n] refers to the data other than the degradation degree (A0, 1, A2, etc.) in the table in Figure 11.

[0055] In step S202-2, the learning unit 202 obtains the degradation degree West[n] as a label from the DWA data associated with degradation.

[0056] In step S202-3, the learning unit 202 acquires the input data obtained in step S202-1 and the labels obtained in step S202-2 as a set of data (referred to as the training data set), and performs training with training data. Based on the above, the learning unit 202 constructs a trained model by performing training with training data based on the training data set. This makes it possible to link the degree of compressor degradation with the order of the current.

[0057] Here, the "trained model" specifically refers to the pattern generation function PGF. The pattern generation function PGF is a function that takes the current spectrum as input and outputs the degree of degradation.

[0058] The machine learning targeting the compressor in this embodiment 1 is supervised learning using a neural network constructed by combining perceptrons. Specifically, the neural network is given a set of supervised data consisting of input data indicating the current state and labels corresponding to the deterioration state of the compressor, and learning is repeated while changing the weights of each perceptron so that the output of the neural network matches the label.

[0059] Learning process Then, by repeatedly performing a process called backpropagation (also known as error backpropagation), the weighting values ​​are adjusted to reduce the error in the output of each perceptron.

[0060] In this way, the learning unit 202 learns the features of the training data set and inductively acquires a trained model to estimate results from the input. That is, as described above, training with training data adjusts the weighting values ​​so that the error between the labels and the output data is eliminated.

[0061] Thus, in supervised learning, a trained model is obtained as a result of the learning process to determine the degree of degradation from the order information of the current. This trained model is then stored as the next-stage pattern generation function PGF.

[0062] Furthermore, the neural network used by the learning unit 202 for training may be made multi-layered, allowing it to perform training using so-called deep learning.

[0063] In step S202-4, the trained model obtained through supervised data training is saved as a pattern generation function PGF. The pattern generation function PGF may be updated by periodically executing the processes from steps S202-1 to S202-4. Alternatively, the pattern generation function PGF may be updated by executing the processes from steps S202-1 to S202-4 whenever the degradation state changes.

[0064] The pattern generation function PGF can be generated by generating the degree of degradation from current information. For example, a trained model obtained from at least one of the current information such as current likelihood, distortion, and harmonics may be generated and stored as the pattern generation function PGF.

[0065] The pattern generation function PGF is output when the inference unit 203, described later, performs its processing. The inference unit 203 then determines the degree of degradation based on the normalized spectrum SPE[n].

[0066] Next, we will explain the processing performed by the inference unit 203 using the trained model after machine learning has been performed as described above. First, in step S203-1, the inference unit 203 obtains the pattern generation function PGF, which is the trained model saved in step S202-4.

[0067] Next, in step S203-2, the inference unit 203 acquires the normalized spectrum SPE[n] from the data DWA associated with degradation as input data. Then, in step S203-3, the inference unit 203 calculates the degree of degradation from the current information that is the target of the degradation diagnosis from multiple outdoor units acquired from the communication network 400.

[0068] Although Figure 9 shows an example with three levels of deterioration, the level of deterioration is determined by the designer based on the level at which maintenance costs are incurred (normal, minor deterioration, severe deterioration), so the level of deterioration does not necessarily have to be three stages.

[0069] The maintenance cost calculation unit 204 calculates the maintenance costs based on the degree of deterioration calculated in step S203-3. The maintenance costs will be explained using Figure 13. Figure 13 is a diagram illustrating an example of processing in the management device according to Embodiment 1. The horizontal axis represents the degree of deterioration, and the vertical axis represents the maintenance costs.

[0070] As shown in Figure 13, the greater the degree of deterioration, the higher the maintenance costs. Maintenance costs include the cost of replacing parts and the cost of service technicians' work. The longer the service technician's work time, the higher the maintenance costs. Therefore, by notifying the user before charging them a high fee, user satisfaction can be improved. In this embodiment, the maintenance costs are notified to the notification device 300, but the degree of deterioration could also be notified to provide useful information for the user's equipment management. In Figure 13, the degree of deterioration increases with operating time, and maintenance costs increase accordingly.

[0071] Based on the above, by performing the processing of the inference unit 203, the management device 200 reads the pattern generation function, which is a learned model, from the current information and determines the degree of deterioration of the compressor installed in the outdoor unit connected to the communication network 400. As a result, a large amount of general-purpose real-world data necessary for deterioration diagnosis is collected, enabling highly accurate analysis and allowing for better service to air conditioner users.

[0072] Embodiment 2. Figure 14 is a control block diagram of the management device 200 according to Embodiment 2. In the management system of Embodiment 2, the processing within the management device 200 differs from that of the management system of Embodiment 1. Specifically, Embodiment 2 is provided with a parts selection unit 205 instead of a maintenance cost calculation unit 204. Other components and processing are the same. This parts selection unit 205 determines the parts or the number of service personnel required for maintenance according to the degree of deterioration from the inference unit 203 and outputs it to the notification device 300.

[0073] Therefore, because the necessary parts and the number of service technicians for maintenance can be determined in advance, it is possible to estimate the time required to procure maintenance parts and personnel, thereby providing better service to air conditioner users.

[0074] Embodiment 3. Figure 15 is a diagram illustrating an example of processing in the centralized management system according to Embodiment 3. In the management system of Embodiment 3, the processing within the management device 200 differs from that of the management system of Embodiment 1. Specifically, in Embodiment 3, the internal processing of the database (DB) 201 within the management device 200 differs from that of Embodiment 1.

[0075] The database (DB) 201 of Embodiment 3 includes an image processing unit 2013 in place of the frequency conversion processing unit 2011 and normalization processing unit 2021 of Embodiment 1. The image processing unit 2013 has the function of processing the data of the limiting current Iu_lim[n] from the communication network 400 into an image. Other components and processing are the same as in Embodiments 1 and 2, so they will not be described again.

[0076] Next, using Figure 16, we will explain the data DWA (data associated with degradation) generated from the database (DB) 201. Figure 16 is a diagram illustrating the data storage state in the management device according to Embodiment 3. In the database (DB) 201, the data processed by the image processing unit 2013 is associated with the degradation degree West[n]. Specifically, as shown in Figure 16, images and degradation degrees are accumulated and stored according to the number n. In Figure 16, for example, if the number of pole pairs of the electric motor is 3, the mechanical angle has a period three times that of the electrical angle, so images are stored every three periods of the electrical angle. In addition, the degradation degree West[n] is associated and stored in accordance with these images. Note that these processes may also be applied to multiple outdoor units.

[0077] Figure 16 shows the change where the system remained normal for a while, then experienced mild degradation for two cycles, followed by severe degradation. For explanatory purposes, the mild degradation is described as lasting only two cycles, but the period of mild degradation does not necessarily have to be two cycles.

[0078] As shown in Figure 16, the accumulated and stored database undergoes the learning and inference processing described in Embodiment 1, and finally notifies the notification device 300 of the maintenance costs. In this case, the input data for steps S202-1 and S203-2 described in Figure 12 becomes image data. By applying machine learning to this image data, it becomes possible to estimate degradation from the waveform shape of the current, enabling highly accurate analysis and providing better service to air conditioner users.

[0079] Embodiment 4. In the management system of Embodiment 4, the timing of output to the communication network 400 differs from that of the management system of Embodiment 1. Figure 17 is a flowchart illustrating the timing of output to the communication network 400 according to Embodiment 4. Specifically, in Embodiment 4, compared to the flowchart of Figure 10 described in Embodiment 1, a new step S101-7 process is added before the process of step S101-1, and the process of step S101-8 is executed instead of the process of step S101-2.

[0080] In step S101-7, the data processor 101 obtains time information for each outdoor unit. In step S101-8, the data processor 101 determines whether the time obtained in step S101-7 is the set time. If it is the set time (YES in step S101-8), the data processor 101 proceeds to steps S101-3 and S101-5. On the other hand, if it is not the set time (NO in step S101-8), the data processor 101 returns to step S101-7.

[0081] For example, by setting a specific time, such as 3 AM once a day, data can be collected regularly, enabling highly accurate analysis and allowing for better service to air conditioner users. Alternatively, depending on the user's usage frequency, collection could be done once a week.

[0082] (summary) Finally, we will summarize this embodiment by referring to the diagram again.

[0083] (Section 1) This disclosure relates to a centralized management system SYS. The centralized management system SYS shown in Figure 1 comprises a data processor 101 that collects information on at least one electric motor 53, and a management device 200 that communicates with the data processor 101 via a communication network 400. The data processor 101 stores current data measured in time division by the current Iuv flowing through the electric motor 53 for a certain period of time, divides the current data (Figure 6: Iu_lim[n]) into data amounts corresponding to the current frequency of the electric motor, and transmits the current data (Figure 6: Iu_lim[n]) to the management device 200 via the communication network 400 (Figure 10: S101-6). Along with the current data, the data processor 101 transmits degradation estimation information (Figure 6: Degradation degree West[n]), which is information used to identify the cause of the electric motor abnormality, to the management device 200.

[0084] (Section 2) In the centralized management system described in Section 1, the amount of data corresponding to the current frequency is the amount of data measured over one cycle of the mechanical angle of the electric motor 53 (Figure 8: T[0]~T[2]).

[0085] (Article 3) In the centralized management system described in Article 1 or Article 2, the degradation estimation information (Figures 6 and 9: Degradation degree West[n]) is the operating time of the motor obtained by integrating the period over which the current flows (Figure 9: Operating time).

[0086] (Section 4) In the centralized management system described in Section 3, the data processor 101 is configured to update current data and send it to the management device 200 as the operating time increases (Figure 10: YES in S101-2, execute S101-6).

[0087] (Article 5) In the centralized management system described in Article 4, the data processor 101 updates the current data at most once a day.

[0088] (Article 6) In the centralized management system described in any one of Articles 1 to 5, the data processor 101 is configured to acquire current data when the electric motor 53 is operating stably.

[0089] (Section 7) In the centralized management system described in any one of Sections 1 to 6, the management device 200 is configured to calculate the degree of deterioration of the motor 53 from the acquired current data and deterioration estimation information, calculate the maintenance cost based on the degree of deterioration (Figures 12:204, 13), and notify the maintenance cost.

[0090] (Section 8) In the centralized management system described in Section 7, as shown in Figure 6, the management device 200 includes a frequency conversion processing unit 2011 that performs a process to convert current data (limiting current Iu_lim[n]) into the frequency domain and generates a spectrum SPE[n] corresponding to the frequency, and a normalization processing unit 2012 that performs a normalization process to divide the spectrum SPE[n] by the fundamental wave component.

[0091] (Section 9) In the centralized management system described in Section 7, the management device 200 is configured to notify whether or not maintenance parts are needed according to the degree of deterioration (Figure 14: 205, 300).

[0092] (Section 10) In the centralized management system described in Section 1, the management device 200 is configured to convert current data into image data (Figure 15: 2013, Figure 16) and link it with degradation estimation information (Figure 15: Degradation degree West [n]).

[0093] (Section 11) In other parts of this disclosure, the present disclosure relates to a learning device (Figure 12:202) for optimizing an estimation model used to predict the degradation of at least one electric motor 53. The learning device comprises a data processor 101 that collects information about the electric motor 53 and a management device 200 that communicates with the data processor 101 via a communication network 400. The management device 200 acquires current data obtained by dividing the current (Iuv) flowing through the electric motor 53 calculated by the data processor 101 into fixed time intervals, and acquires degradation estimation information which is information used to identify the cause of the abnormality of the electric motor 53 (Figure 12:S202-2), and constructs a learning dataset including the current data and the degradation estimation information. The management device 200 inputs the current data extracted from the learning dataset into the estimation model and optimizes the estimation model so that the output estimation result approaches the degradation estimation information labeled in the learning dataset.

[0094] (Section 12) In other aspects, the disclosure relates to a centralized management method that uses a data processor 101 that collects information relating to at least one electric motor 53 and a management device 200 that communicates with the data processor 101 via a communication network 400. The centralized management method comprises the steps of: the data processor 101 storing current data (Iuv) measured in time division by the current flowing through the electric motor 53 for a certain period of time; the data processor 101 dividing the current data (Figures 6 and 8: Iu_lim[n]) into data amounts corresponding to the current frequency of the electric motor 53 and transmitting it to the management device 200 via the communication network (Figure 10: S101-3, S101-4); and the data processor 101 transmitting degradation estimation information (Figure 6: Degradation degree West[n]), which is information used to identify the cause of the abnormality of the electric motor, along with the current data to the management device 200 (Figure 10: S101-6).

[0095] The embodiments disclosed herein should be considered in all respects to be illustrative and not restrictive. The scope of this disclosure is indicated by the claims rather than by the description of the embodiments above, and all modifications within the meaning and scope of the claims are intended to be included. Furthermore, the inventions described in the embodiments and each variation are intended to be carried out individually or in combination as far as possible. [Explanation of Symbols]

[0096] 1 AC power supply, 2 Rectifier circuit, 3 Electrolytic capacitor, 4 Inverter, 5 Compressor, 6 Current sensor, 7 Wiring, 8 Bus voltage, 51 Intake pipe, 52 Main shaft, 53 Electric motor, 54 Lubricating oil, 55 Oil pump, 56 Sub-bearing, 57 Main bearing, 58 Compression mechanism, 59 Discharge pipe, 100 Control device, 101 Data processor, 102 CPU, 103 Memory, 200 Management device, 202 Learning unit, 203 Inference unit, 204 Maintenance cost calculation unit, 205 Parts selection unit, 300 Notification device, 400 Communication network, 500 Network, 1000, 2000, 3000 Outdoor unit, 1011 Limit quantity calculation processing unit, 1012 Data limit processing unit, 1013 Drive time count processing unit, 1014 Degradation allocation processing unit, 2011 Frequency conversion processing unit, 2012, 2021; Normalization processing unit, 2013; Image processing unit; SYS centralized management system.

Claims

1. A data processor that collects information about at least one electric motor, The system includes a management device that communicates with the data processor via a communication network, The data processor is configured to store current data measured from the electric motor for a certain period of time, divide the current data into amounts corresponding to the current frequency of the electric motor, and transmit the current data to the management device via the communication network. The data processor is configured to transmit degradation estimation information, which is information used to identify the cause of the abnormality of the electric motor, along with the current data, to the management device. The amount of data corresponding to the current frequency is the amount of data measured over the time of one cycle of the motor's mechanical angle. The aforementioned degradation estimation information is the operating time of the electric motor, which is obtained by integrating the periods during which the current flows, in a centralized management system.

2. The centralized management system according to claim 1, wherein the data processor is configured to update the current data and send it to the management device as the operating time increases.

3. The centralized management system according to claim 2, wherein the data processor updates the current data at a frequency of at most once a day.

4. The centralized management system according to claim 1, wherein the data processor is configured to acquire the current data when the electric motor is operating stably.

5. The centralized management system according to claim 1, wherein the management device is configured to calculate the degree of deterioration of the electric motor from the acquired current data and the deterioration estimation information, calculate maintenance costs based on the degree of deterioration, and notify the maintenance costs.

6. The aforementioned control device is A frequency conversion processing unit that performs a process to convert the current data into the frequency domain and generates a spectrum corresponding to the frequency, The centralized management system according to claim 5, further comprising a normalization processing unit that performs a normalization process of dividing the spectrum by the fundamental wave component.

7. The centralized management system according to claim 5, wherein the management device is configured to notify whether or not maintenance parts are needed according to the degree of deterioration.

8. The centralized management system according to claim 1, wherein the management device is configured to convert the current data into image data and link it with the degradation estimation information.

9. A centralized management method that uses a data processor that collects information relating to at least one electric motor, and a management device that communicates with the data processor via a communication network, The data processor stores current data, which is the current flowing through the electric motor, for a certain period of time. The data processor divides the current data into data amounts corresponding to the current frequency of the electric motor and transmits the current data to the management device via the communication network. The data processor includes the step of transmitting, along with the current data, degradation estimation information, which is information used to identify the cause of the abnormality of the electric motor, to the management device. The amount of data corresponding to the current frequency is the amount of data measured over the time of one cycle of the motor's mechanical angle. The aforementioned degradation estimation information is the operating time of the electric motor, which is obtained by accumulating the period during which the current flows, in a centralized management method.

Images