Estimation device, estimation program, estimation method, motor bearing wear monitoring device, and canned motor pump

Abstract

The amount of work required to adjust the correspondence between the detection value of the detection coil and the amount of wear of the bearing is reduced. [Solution] An estimation device 53, 6 according to the present invention estimates an adjustment value of a motor bearing wear monitoring device 5 that monitors the wear state of bearings 32, 33 supporting a rotating shaft 31, based on detection signals from each of a plurality of detection coils C1-C8. The estimation device includes a memory unit 54, 64 that stores a trained thrust learning model M11, M21 that has been machine-learned to output a thrust adjustment value when thrust input data including the rated current value of the motor 3, the length of the movable range, the number of turns of the detection coil, and the position of the rotor 36 relative to the stator 37 in the thrust direction is input, an acquisition unit 530, 630 that acquires the thrust input data, and an estimation unit 531, 631 that inputs the thrust input data acquired by the acquisition unit into the thrust learning model to estimate the thrust adjustment value.

Description

[Technical field]

[0001] The present invention relates to an estimation device, an estimation program, an estimation method, a motor bearing wear monitoring device, and a canned motor pump. [Background technology]

[0002] A canned motor pump has a structure in which the pump and motor are integrated and there is no leakage of the pumped liquid. Generally, the rotating structural parts of a canned motor pump (rotor, rotating shaft, bearings, and impeller) are sealed in a can that is filled with the pumped liquid. Therefore, the internal structure of a canned motor pump cannot be visually monitored from the outside. Therefore, in order to efficiently operate a canned motor pump having such a structure, a device that monitors the wear condition of the bearings (hereinafter referred to as a "monitoring device") is used (see, for example, Patent Document 1).

[0003] The monitoring device (motor bearing wear monitoring device) disclosed in Patent Document 1 uses detection coils attached to both longitudinal ends of the stator to measure changes in magnetic flux as the rotor rotates, thereby monitoring the radial and thrust displacements of the rotor (rotating shaft) caused by bearing wear. This method requires adjustment of the correspondence between the amount of bearing wear (mechanical displacement of the rotor) and the output value of the detection coil so that the output value (voltage value) of the detection coil indicates the amount of bearing wear.

[0004] Normally, bearings have play. Therefore, for example, in the thrust direction, the rotor can displace a length corresponding to the play of the bearing (hereinafter referred to as the "play length") without the bearing wearing out. When the rotor is displaced by more than the play length, the bearing is worn out. Therefore, the output value of the detection coil when the rotor is displaced by the play length becomes a threshold value indicating a state in which the bearing is not worn out. The output value of the detection coil is approximately proportional to the amount of displacement of the rotor. Therefore, the output value corresponding to the limit value of the amount of wear of the bearing can be calculated from the output value corresponding to the play length. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Application Publication No. 10-080103 Summary of the Invention [Problem to be solved by the invention]

[0006] Here, the monitoring device detects the voltage induced in the detection coil by the rotation of the motor. Therefore, the adjustment is performed while the canned motor pump is operated under the specified operating conditions to pump the pumped liquid (e.g., water). At that time, the operator moves the rotor to the front side and the rear side as far as possible within the range of the play length in the thrust direction to obtain the threshold values ​​(output values) on the front side and the rear side, and also obtains the output value at the intermediate position between the front side and the rear side. In other words, the adjustment requires the movement of the rotor and the pumping of liquid by the canned motor pump multiple times. Thus, the adjustment requires manual and mechanical operation, and the labor required is large.

[0007] The present invention aims to provide an estimation device, an estimation program, an estimation method, a motor bearing wear monitoring device, and a canned motor pump that can reduce the labor required to adjust the correspondence between the output value of a detection coil and the amount of bearing wear. [Means for solving the problem]

[0008] An estimating device in one embodiment of the present invention is an estimating device that estimates an adjustment value of a motor bearing wear monitoring device that monitors a wear state of a bearing supporting a rotating shaft of a rotor based on detection signals of each of a plurality of detection coils that detect magnetic flux changes corresponding to a position change of a rotor relative to a stator of a motor of a canned motor pump, wherein each of the plurality of detection coils is attached to the stator and outputs the detection signal indicative of the magnetic flux change, the plurality of detection coils include a plurality of thrust detection coils that detect the magnetic flux change in a thrust direction of the rotating shaft, the plurality of thrust detection coils include a first thrust detection coil forming a set and a second thrust detection coil forming another set, in the thrust direction, the first thrust detection coil is disposed at an end of the stator on one side, and the second thrust detection coil is disposed at an end of the stator on the other side, the adjustment value includes a thrust adjustment value in the thrust direction, and the thrust adjustment value is a thrust adjustment value calculated by calculating a thrust adjustment value of the first thrust detection coil when the rotor is located at a first position, a second position, and a third position relative to the stator, a voltage value of a first thrust composite signal obtained by combining the detection signals output from each of the second thrust detection coils, and a voltage value of a second thrust composite signal obtained by combining the detection signals output from each of the second thrust detection coils, or a thrust determination criterion for the wear state in the thrust direction that can be calculated based on the voltage value of the first thrust composite signal and the voltage value of the second thrust composite signal, wherein the first position is a position where the rotor has moved to the maximum extent in the one direction relative to the stator within a mechanical movable range of the rotating shaft relative to the bearing in the thrust direction, the second position is a position where the rotor has moved to the maximum extent in the other direction relative to the stator within the movable range, and the third position is an intermediate position between the first position and the second position, and a memory unit that stores a trained thrust learning model that has been machine-learned to output the thrust adjustment value when thrust input data including a rated current value of the motor, a length of the movable range, a number of turns of the detection coil, and a position of the rotor relative to the stator in the thrust direction is input.The thrust input data acquisition system includes an acquisition unit that acquires the thrust input data, and an estimation unit that inputs the thrust input data acquired by the acquisition unit into the thrust learning model to estimate the thrust adjustment value.

[0009] An estimation program in one embodiment of the present invention causes a computer to function as the estimation device according to the above embodiment.

[0010] An estimation method according to one embodiment of the present invention is a method for estimating an adjustment value of a motor bearing wear monitoring device that monitors a wear state of a bearing supporting a rotating shaft of a rotor based on detection signals from a plurality of detection coils that detect magnetic flux changes corresponding to a position change of a rotor relative to a stator of a motor of a canned motor pump, the method being executed by an estimation device that estimates an adjustment value of the motor bearing wear monitoring device that monitors a wear state of a bearing supporting a rotating shaft of the rotor based on detection signals from a plurality of detection coils that detect magnetic flux changes corresponding to a position change of the rotor relative to a stator of the motor, the method being executed by an estimation device that estimates an adjustment value of the motor bearing wear monitoring device based on detection signals from a plurality of detection coils that detect magnetic flux changes corresponding to a position change of the rotor relative to a stator of the motor, the method being executed and a memory unit that stores a trained thrust learning model that has been machine-learned to output a thrust adjustment value when thrust input data including a position of the rotor relative to the stator in the thrust direction is input, the trained thrust learning model includes an acquisition step in which the estimating device acquires the thrust input data, and an estimation step in which the estimating device inputs the thrust input data acquired by the acquisition step into the thrust learning model to estimate the thrust adjustment value, the thrust adjustment value includes a thrust determination criterion for the wear state in the thrust direction that is generated based on a voltage value of a first thrust resultant signal obtained by combining the detection signals output from each of the first thrust detection coils and a voltage value of a second thrust resultant signal obtained by combining the detection signals output from each of the second thrust detection coils, or the voltage value of the first thrust resultant signal and the voltage value of the second thrust resultant signal, when the rotor is located at a first position, a second position, and a third position relative to the stator,The first position is a position where the rotor has moved to the maximum extent in the one direction relative to the stator, the second position is a position where the rotor has moved to the maximum extent in the other direction relative to the stator within the movable range, and the third position is an intermediate position between the first position and the second position.

[0011] In one embodiment of the present invention, a motor bearing wear monitoring device is a motor bearing wear monitoring device that monitors a wear state of a bearing supporting a rotating shaft of a rotor based on detection signals from a plurality of detection coils that detect magnetic flux changes corresponding to a position change of the rotor relative to a stator of a motor of a canned motor pump, wherein each of the plurality of detection coils is attached to the stator and outputs the detection signal indicative of the magnetic flux change, the plurality of detection coils include a plurality of thrust detection coils that detect the magnetic flux change in a thrust direction of the rotating shaft, the plurality of thrust detection coils include a first thrust detection coil forming a set and a second thrust detection coil forming another set, in the thrust direction, the first thrust detection coil is disposed at an end of the stator on one side, and the second thrust detection coil is disposed at an end of the stator on the other side, the adjustment value includes a thrust adjustment value in the thrust direction, and the thrust adjustment value is a forward rotational speed signal output from each of the first thrust detection coils when the rotor is located at a first position, a second position, and a third position relative to the stator, a thrust determination criterion for the wear state in the thrust direction, the thrust determination criterion being generated based on a voltage value of a first thrust composite signal obtained by combining the detection signals and a voltage value of a second thrust composite signal obtained by combining the detection signals output from each of the second thrust detection coils, or based on the voltage value of the first thrust composite signal and the voltage value of the second thrust composite signal, and the first position is a position at which the rotor has moved maximally in the one direction relative to the stator within a mechanical movable range of the rotating shaft relative to the bearing in the thrust direction. a memory unit that stores a trained thrust learning model that has been machine-learned to output the thrust adjustment value when thrust input data including a rated current value of the motor, a length of the movable range, a number of turns of the detection coil, and a position of the rotor relative to the stator in the thrust direction is input, the second position being a position where the rotor has moved to the other direction side relative to the stator within the movable range, and the third position being an intermediate position between the first position and the second position; and an acquisition unit that acquires the thrust input data.and an estimation unit that inputs the thrust input data acquired by the acquisition unit into the thrust learning model to estimate the thrust adjustment value.

[0012] In one embodiment of the present invention, a canned motor pump comprises a rotor, a stator which rotates the rotor, a rotating shaft to which the rotation of the rotor is transmitted, a bearing which rotatably supports the rotating shaft, a plurality of detection coils attached to the stator which detect magnetic flux changes corresponding to changes in the position of the rotor relative to the stator, and a motor bearing wear monitoring device which monitors the wear condition of the bearing based on output signals from the detection coils, wherein the motor bearing wear monitoring device is the motor bearing wear monitoring device described in the above embodiment. Effect of the Invention

[0013] The present invention can reduce the number of steps required to adjust the correspondence between the output value of the detection coil and the amount of wear of the bearing. [Brief description of the drawings]

[0014] [Figure 1] 1 is a side view of a canned motor pump showing an embodiment of the canned motor pump according to the present invention. FIG. [Diagram 2] 2 is a schematic cross-sectional view of a motor unit of the canned motor pump of FIG. 1, showing a vertical cross section of the motor unit. [Diagram 3] 3 is a partially enlarged schematic cross-sectional view showing part A of the motor unit in FIG. 2. [Figure 4] 3 is a partially enlarged schematic cross-sectional view showing part B of the motor unit in FIG. 2. [Diagram 5] 3 is a partially enlarged perspective view showing a portion C of the motor unit in FIG. 2. FIG. [Figure 6] 1 is a functional block diagram showing an embodiment of a motor bearing wear monitoring device according to the present invention; [Figure 7] 7 is a schematic perspective view of a stator core of the canned motor pump of FIG. 1, showing the arrangement of detection coils of the motor bearing wear monitoring device of FIG. 6. [Figure 8]8 is a schematic diagram showing an example of a detection signal of the detection coil in FIG. 7. [Figure 9] 7 is a functional block diagram of an offset processing unit of the motor bearing wear monitoring device of FIG. 6. [Figure 10] 7 is a schematic diagram showing an example of information stored in a storage unit of the motor bearing wear monitoring device of FIG. 6. [Figure 11] 7 is a flowchart showing an example of the operation of the motor bearing wear monitoring device of FIG. 6. [Figure 12] 12 is a flowchart showing an example of a thrust adjustment value estimation process included in the operation of FIG. 11. [Figure 13] 12 is a flowchart showing an example of a radial adjustment value estimation process included in the operation of FIG. 11. [Figure 14] 12 is a flowchart showing an example of a determination criterion setting process included in the operation of FIG. 11. [Figure 15] FIG. 4 is a functional block diagram of an estimation device according to another embodiment of the present invention. [Figure 16] 16 is a schematic diagram showing an example of information stored in a storage unit of the estimation device of FIG. 15. [Figure 17] 16 is a flowchart showing an example of the operation of the estimation device of FIG. 15. [Figure 18] 18 is a flowchart showing an example of a thrust adjustment value estimation process included in the operation of FIG. 17. [Figure 19] 18 is a flowchart showing an example of a radial adjustment value estimation process included in the operation of FIG. 17. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] The present invention estimates an adjustment value used for adjusting a motor bearing wear monitoring device of a canned motor pump by using a trained learning model. Data (big data) accumulated in past adjustments is used for the machine learning of the learning model. As a result, the present invention can estimate an adjustment value and adjust the motor bearing wear monitoring device without manual mechanical operation, for example, during initial adjustment before shipment of the canned motor pump or when changing the driving conditions. Details of each term will be described later.

[0016] The following describes embodiments of a canned motor pump (hereinafter referred to as "the pump") according to the present invention, a motor bearing wear monitoring device (hereinafter referred to as "the device") according to the present invention, an estimation device (hereinafter referred to as "the estimation device") according to the present invention, an estimation method (hereinafter referred to as "the estimation method") according to the present invention, and an estimation program (hereinafter referred to as "the estimation program") according to the present invention. In the following description, the drawings will be referred to as appropriate. In the drawings, the same members and elements are given the same symbols, and duplicated descriptions are omitted. Furthermore, the dimensional ratios of the elements may be exaggerated for convenience of explanation, and are not limited to the ratios shown in the drawings.

[0017] ●Canned motor pump● First, a first embodiment of the present estimation device will be described below, taking as an example a case in which the present device of the present pump is equipped with the present estimation device.

[0018] ●Canned motor pump configuration FIG. 1 is a side view of the pump, showing an embodiment of the pump. For ease of explanation, the figure shows a cross-sectional view of the upper half of the pump 1.

[0019] The pump 1 is a pump having a structure that prevents leakage of the pumped liquid. The pump 1 includes a pump section 2, a motor section 3, an adapter 4, and the device 5.

[0020] Among the configurations of this pump 1, the configurations of the pump section 2, the motor section 3, and the adapter 4 are common to the configurations of a known canned motor pump. Therefore, in the following explanation, the configurations of the pump section 2, the motor section 3, and the adapter 4 will only be outlined, and detailed explanations thereof will be omitted.

[0021] In the following description, the "front direction" is the direction in which the pump section 2 is located relative to the motor section 3, and the "rear direction" is the direction in which the motor section 3 is located relative to the pump section 2. The front direction is an example of one direction in the present invention. The rear direction is an example of the other direction in the present invention.

[0022] The pump section 2 draws in and discharges the pumped liquid. The pump section 2 includes a housing 20, an impeller 21, a pump chamber 22, a suction pipe section 23, and a discharge pipe section 24. The housing 20 defines the pump chamber 22 that houses the impeller 21, the suction pipe section 23 which is a path for the pumped liquid drawn into the pump chamber 22, and the discharge pipe section 24 which is a path for the pumped liquid discharged from the pump chamber 22. The pump chamber 22 is in communication with the suction pipe section 23 and the discharge pipe section 24.

[0023] The motor section 3 is driven under rated conditions (e.g., rated frequency: 60 Hz, rated voltage: 200 V, rated current: 10 A) to rotate the impeller 21 of the pump section 2. The motor section 3 includes a housing 30, a rotating shaft 31, two bearings 32 and 33, two thrust washers 34 and 35, a rotor 36, a stator 37, a can 38, and a terminal 39. The motor section 3 is an example of the motor defined in the present invention.

[0024] FIG. 2 is a schematic cross-sectional view of the motor unit 3, showing a vertical cross section of the motor unit 3. As shown in FIG.

[0025] The housing 30 accommodates the stator 37 and the can 38 in a liquid-tight manner.

[0026] The rotating shaft 31 rotates together with the rotor 36 and transmits rotational power to the impeller 21. The rotating shaft 31 is cylindrical in shape. The rotating shaft 31 is inserted through the rotor 36 and fixed to the rotor 36. The front end of the rotating shaft 31 protrudes into the pump chamber 22 (see FIG. 1), and the impeller 21 is attached to the front end. The rotating shaft 31 is provided with cylindrical sleeves 31a, 31b that protect the front and rear portions of the rotating shaft 31.

[0027] In the following description, the “thrust direction” is the thrust direction of the rotating shaft 31 , the “radial direction” is the radial direction of the rotating shaft 31 , and the “circumferential direction” is the circumferential direction of the rotating shaft 31 .

[0028] The bearing 32 is disposed in the front direction of the rotor 36 and rotatably supports the rotating shaft 31. The bearing 33 is disposed in the rear direction of the rotor 36 and rotatably supports the rotating shaft 31. The bearings 32 and 33 are, for example, plain bearings. The thrust washer 34 is attached to the rotating shaft 31 between the bearing 32 and the rotor 36 and limits the movement of the rotating shaft 31 in the front direction. The thrust washer 35 is attached to the rotating shaft 31 between the bearing 33 and the rotor 36 and limits the movement of the rotating shaft 31 in the rear direction.

[0029] FIG. 3 is a partially enlarged schematic cross-sectional view showing part A of the motor unit 3 in FIG. FIG. 4 is a partially enlarged schematic cross-sectional view showing part B of the motor unit 3 in FIG.

[0030] In the thrust direction, a gap Ss1 of length "Ls1" is formed between the bearing 32 and the thrust washer 34. In the thrust direction, a gap Ss2 of length "Ls2" is formed between the bearing 33 and the thrust washer 35. The lengths "Ls1" and "Ls2" of these gaps Ss1 and Ss2 define the mechanical movable range of the rotating shaft 31 relative to the bearings 32 and 33 in the thrust direction, i.e., the play of the bearings 32 and 33 in the thrust direction. In other words, the length of this movable range (hereinafter referred to as the "thrust play length") is expressed as the sum "Ls1+Ls2" of the length "Ls1" and the length "Ls2".

[0031] When the bearing 32 ideally supports the rotating shaft 31, a gap Sr1 of length "Lr1" is formed between the rotating shaft 31 and the bearing 32 in the radial direction. When the bearing 33 ideally supports the rotating shaft 31, a gap Sr2 of length "Lr2" is formed between the rotating shaft 31 and the bearing 33 in the radial direction. The length "Lr1" is approximately the same as the length "Lr2". These gaps Sr1 and Sr2 define the mechanical movable range of the rotating shaft 31 relative to the bearings 32 and 33 in the radial direction, that is, the play of the bearings 32 and 33 in the radial direction. In other words, when the bearings 32 and 33 ideally support the rotating shaft 31, the length of the movable range (hereinafter referred to as the "radial play length") is expressed by the length "Lr1" or the length "Lr2". Here, when the bearings 32 and 33 ideally support the rotating shaft 31, the rotor 36 is located at the center position in the radial direction. The "center position" is the position where the center of the rotating shaft 31 coincides with the centers of the bearings 32, 33 when viewed in the thrust direction.

[0032] In the following description, reference will be mainly made to FIGS. 1 to 4. FIG. The rotor 36 rotates due to a rotating magnetic field generated in the stator 37. The rotor 36 is cylindrical in shape. The rotor 36 has a plurality of (28 in this embodiment) rod-shaped rotor bars 36a embedded at equal intervals in the outer circumferential edge of the rotor 36 in the circumferential direction. When the bearings 32, 33 are not worn, the rotor 36 is disposed in an initial position with respect to the stator 37. In this embodiment, the "initial position" is a position where the center of the stator 37 and the center of the rotor 36 coincide with each other in the thrust direction and the radial direction.

[0033] In the following description, the "front position" refers to a position where the rotor 36 has moved to the maximum in the front direction in the movable range in the thrust direction. That is, the front position is a position where the rotor 36 has moved to the front direction by a length "Ls1" from the initial position. Also, the "rear position" refers to a position where the rotor 36 has moved to the maximum in the rear direction from the initial position in the movable range in the thrust direction. That is, the rear position is a position where the rotor 36 has moved to the rear direction by a length "Ls2" from the initial position. The "radial position" refers to a position where the rotor 36 has moved to the maximum in the radial direction from the central position in the movable range in the radial direction. That is, the radial position is a position where the rotor 36 has moved to the radial direction by a length "Lr1" or "Lr2" from the central position (initial position). The front position is an example of a first position in the present invention. The rear position is an example of a second position in the present invention. The intermediate position between the front position and the rear position is an example of a third position in the present invention. The radial position is an example of a fourth position in the present invention.

[0034] The stator 37 generates a rotating magnetic field that rotates the rotor 36. The stator 37 has a substantially cylindrical shape. The stator 37 includes a stator core 37a and a plurality of motor windings 37b.

[0035] FIG. 5 is a partial enlarged perspective view showing part C of the motor unit 3 in FIG. In the following description, FIGS. 1 to 4 will be referred to together with FIG. 5 as appropriate.

[0036] The stator core 37a holds the motor windings 37b. The stator core 37a has a cylindrical shape. The stator core 37a has a plurality of teeth 37c, slots 37d, and a plurality of notches 37e.

[0037] The tooth portion 37c forms slots 37d through which the motor winding 37b is inserted. The tooth portion 37c is arranged at equal intervals in the circumferential direction on the inner circumferential surface of the stator core 37a. The motor winding 37b is inserted into the slots 37d and connected to a power supply device (not shown) such as an inverter via a terminal 39. The cutout portions 37e are arranged at equal intervals (90° intervals) in the circumferential direction at both ends of the tooth portion 37c in the thrust direction.

[0038] The can 38 liquid-tightly houses the rotating shaft 31, the bearings 32, 33, the thrust washers 34, 35, and the rotor 36. The can 38 is cylindrical in shape. A part of the handled liquid introduced from the suction pipe section 23 is introduced into the can 38 and used for cooling and lubricating the bearings 32, 33 and the motor section 3, and is discharged to the discharge pipe section 24.

[0039] The adapter 4 is connected to a rear end of the pump unit 2 and a front end of the motor unit 3, and connects the pump unit 2 and the motor unit 3 together.

[0040] This device 5 monitors the amount of wear (wear state) of the bearings 32, 33 by detecting a change in magnetic flux corresponding to a mechanical position change of the rotor 36 relative to the stator 37. A specific configuration of this device 5 will be described later.

[0041] ●Motor bearing wear condition estimation device● Configuration of motor bearing wear state estimation device Next, a configuration of the present device 5 will be described. In the following description of the present device 5, Figs. 1 to 4 will be referred to as appropriate.

[0042] FIG. 6 is a functional block diagram showing an embodiment of the present device 5. As shown in FIG.

[0043] The present device 5 includes eight detection coils C1, C2, C3, C4, C5, C6, C7, and C8, a connection unit 50, signal processing circuits 51a, 51b, 51c, and 51d, an A / D converter 52, a control unit 53, a storage unit 54, a display unit 55, and an offset processing unit 56. The A / D converter 52 and the control unit 53 are configured, for example, by a microcomputer. The control unit 53 and the storage unit 54 are an example of the present estimation device. That is, the present pump 1 and the present device 5 include the present estimation device.

[0044] In the present invention, the motor section 3 may include detection coils C1 to C8.

[0045] FIG. 7 is a schematic perspective view of the stator core 37a, showing the arrangement of the detection coils C1 to C8.

[0046] Each of the detection coils C1 to C8 detects a magnetic flux change corresponding to a position change (displacement) of the rotor 36 relative to the stator 37, generates a detection signal indicating the magnetic flux change, and outputs the detection signal. The rotor 36 displaces in the radial and thrust directions together with the rotating shaft 31 according to the wear amount of the bearings 32 and 33 in the radial and thrust directions. That is, the displacement amount of the rotor 36 can be regarded as the wear amount of the bearings 32 and 33. Therefore, the present device 5 can detect the wear amount of the bearings 32 and 33 by acquiring a detection signal indicating the displacement amount of the rotor 36 using the detection coils C1 to C8. Each of the detection coils C1 to C8 has a flat bobbin shape. Each of the detection coils C1 to C8 is fitted into the corresponding cutout portion 37e.

[0047] In the circumferential direction, the detection coils C1 to C4 are attached at equal intervals (90° intervals) to the front end of the tooth portion 37c. In the circumferential direction, the detection coil C1 is arranged to face the detection coil C3 at a position of "180°", and the detection coil C2 is arranged to face the detection coil C4 at a position of "180°". On the other hand, in the circumferential direction, the detection coils C5 to C8 are attached at equal intervals (90° intervals) to the rear end of the tooth portion 37c. In the circumferential direction, the detection coil C5 is arranged to face the detection coil C7 at a position of "180°", and the detection coil C6 is arranged to face the detection coil C8 at a position of "180°". That is, in the radial direction, the detection coils C1, C2, C5, and C6 are arranged to face the corresponding detection coils C3, C4, C7, and C8.

[0048] In the present invention, the detection coils C1, C2, C5, and C6 only need to be arranged to face the corresponding detection coils C3, C4, C7, and C8, and the positional relationship is not limited to an exact "180°" position. In other words, for example, due to manufacturing errors or the shape of the stator 37, the positional relationship in the circumferential direction may deviate from "180°" by a few degrees (for example, 1° to 5°).

[0049] In the present invention, the angle between the detector coil C1 (detector coil C3) and the detector coil C2 (detector coil C4) in the circumferential direction can be set appropriately between 0° and 180°, and is not limited to 90°. The same arrangement is also applied to the detector coil C5 (detector coil C7) and the detector coil C6 (detector coil C8).

[0050] FIG. 8 is a schematic diagram showing an example of a detection signal.

[0051] In the figure, the horizontal axis indicates the rotation angle of the rotor 36, and the vertical axis indicates the output voltage (signal level) of the detection coils C1 to C8. The detection signals of the detection coils C1 to C8 include a waveform (hereinafter referred to as "fundamental wave component") corresponding to the change in the main magnetic flux of the motor unit 3, and a waveform (hereinafter referred to as "harmonic component") corresponding to the change in the magnetic flux generated by the induced current flowing through the rotor bar 36a of the rotor 36. The fundamental wave component is generated by the drive voltage of the motor unit 3, and its frequency is the same as the drive frequency. The harmonic component is generated by the induced current flowing through the rotor bar 36a, and its frequency is determined by the rotation of the rotor 36 and the number of rotor bars 36a. That is, for example, under the following conditions (drive frequency: 60 Hz, number of rotor bars 36a: 28), each of the detection coils C1 to C8 detects the change in the magnetic flux caused by the rotor bar 36a 28 times during one rotation of the rotor 36. Therefore, the frequency of the harmonic component is 60 Hz x 28 = 1.68 kHz. In this way, the fundamental wave component is determined based on the drive frequency, and the harmonic components are determined based on the rotation of the rotor 36, the drive frequency, and the number of rotor bars 36a.

[0052] Here, the rotation speed of the motor unit 3 can be easily changed by varying the drive frequency by inverter control. In this case, if only the drive frequency is lowered without lowering the drive voltage value, the motor unit 3 will burn out, so generally, the drive frequency and the drive voltage value are changed at the same time. The increase or decrease in the drive frequency and the increase or decrease in the drive voltage value are in a proportional relationship. That is, the drive voltage value decreases in proportion to the decrease in the drive frequency, and increases in proportion to the increase in the drive frequency. As described above, since the fundamental wave component of the detection signal is generated by the drive voltage, the signal level of the fundamental wave component is proportional to the drive frequency and the drive voltage value. Therefore, the signal level of the fundamental wave component increases or decreases in proportion to the increase or decrease in the drive frequency and the drive voltage value. Furthermore, when the output of the motor unit 3 is the same, when the drive voltage value increases, the drive current value decreases. That is, the drive current value increases or decreases in inverse proportion to the increase or decrease in the drive frequency and the drive voltage value. Therefore, the signal level of the fundamental wave component increases or decreases in inverse proportion to the increase or decrease in the drive current value. In this way, the signal level of the fundamental wave component increases or decreases in response to increases or decreases in the drive conditions (drive frequency, drive voltage value, drive current value). The pump 1 is designed to operate under rated conditions (i.e., rated frequency, rated voltage value, rated current value).

[0053] The primary drawing reference in this description is to return to FIG. The detection coils C1, C3, C5, and C7 detect the radial displacement of the rotor 36 (i.e., the radial wear of the bearings 32 and 33) by detecting a change in magnetic flux corresponding to the radial displacement of the rotor 36 caused by the widening of the gaps Sr1 and Sr2. The detection coil C1 is connected to the common path Lc1 and the detection coil C3. The detection coil C3 is connected to the signal processing circuit 51a via the connection part 50. The detection coils C1 and C3 are connected in series so that the difference of the detection signals can be obtained (so that the detection signals cancel each other out). The detection coil C5 is connected to the common path Lc1 and the detection coil C7. The detection coil C7 is connected to the signal processing circuit 51b via the connection part 50. The detection coils C5 and C7 are connected in series so that the difference of the detection signals can be obtained (so that the detection signals cancel each other out). The detection coils C1, C3, C5, and C7 are examples of radial detection coils in the present invention. The detection coils C1 and C3 form a pair of radial detection coils and are an example of a first radial detection coil in the present invention. The detection coils C5 and C7 form another pair of radial detection coils and are an example of a second radial detection coil in the present invention.

[0054] In the present invention, the detection coils C5 and C7 may form one set of radial detection coils, and the detection coils C1 and C3 may form another set of radial detection coils.

[0055] When the rotor 36 is displaced in the radial direction from the initial position, the signal level of the harmonic components increases as the rotor 36 approaches the detection coils C1, C3, C5, and C7, and decreases as the rotor 36 moves away from the detection coils C1, C3, C5, and C7. On the other hand, the signal level of the fundamental wave component does not increase or decrease. Therefore, in the composite signal of the detection signals of the detection coils C1 and C3 (hereinafter referred to as the "composite signal (S13)"), the difference in the signal levels of the harmonic components increases as the amount of displacement increases. Similarly, in the composite signal of the detection signals of the detection coils C5 and C7 (hereinafter referred to as the "composite signal (S57)"), the difference in the signal levels of the harmonic components increases as the amount of displacement increases. These differences indicate the amount of wear in the radial direction of the bearings 32 and 33, and the value of the difference is expressed as a voltage value. Therefore, for example, when there is no radial displacement of the rotor 36, the fundamental wave component and the harmonic components in each composite signal (S13, S57) cancel each other out, and theoretically the voltage value is 0. On the other hand, when there is radial displacement of the rotor 36, the difference between the harmonic components in each composite signal (S13, S57) increases according to the amount of displacement, and the voltage value increases according to this difference.

[0056] The detection coils C2, C4, C6, and C8 detect the amount of displacement of the rotor 36 in the thrust direction (i.e., the amount of wear of the bearings 32 and 33 in the thrust direction) by detecting a change in magnetic flux corresponding to the displacement of the rotor 36 in the thrust direction caused by the widening of the gaps Ss1 and Ss2. The detection coil C2 is connected to the common path Lc2 and the detection coil C4. The detection coil C4 is connected to the signal processing circuit 51c via the connection part 50. The detection coils C2 and C4 are connected so that their detection signals are superimposed to generate a composite signal (S24). The detection coil C6 is connected to the common path Lc2 and the detection coil C8. The detection coil C8 is connected to the signal processing circuit 51d via the connection part 50. The detection coils C6 and C8 are connected so that their detection signals are superimposed to generate a composite signal (S68). The detection coils C2, C4, C6, and C8 are examples of thrust detection coils in the present invention. The detection coils C2 and C4 form a pair of thrust detection coils and are an example of a first thrust detection coil in the present invention. The detection coils C6 and C8 form another pair of thrust detection coils and are an example of a second thrust detection coil in the present invention.

[0057] In the present invention, the detection coils C6 and C8 may form one set of thrust detection coils, and the detection coils C2 and C4 may form another set of thrust detection coils.

[0058] When the rotor 36 is displaced from the initial position to the rear side, the overlap between the detection coils C2 and C4 and the front end (end ring) of the rotor 36 in the thrust direction remains almost the same, but the overlap between the detection coils C6 and C8 and the rear end (end ring) of the rotor 36 decreases. As a result, the signal level of the fundamental wave component of the composite signal (S24) remains almost the same, but the signal level of the fundamental wave component of the composite signal (S68) decreases. Similarly, when the rotor 36 is displaced from the initial position to the front side, the signal level of the fundamental wave component of the composite signal (S68) remains almost the same, but the signal level of the fundamental wave component of the composite signal (S24) decreases. Therefore, the displacement amount of the rotor 36 in the thrust direction can be detected from the difference between the composite signal (S24) and the composite signal (S68). That is, a signal indicating the difference (a difference signal (Sd) described later) indicates the displacement amount of the rotor 36 in the thrust direction, that is, the wear amount of the bearings 32 and 33 in the thrust direction. Therefore, for example, when there is no displacement of the rotor 36 in the thrust direction, the fundamental wave component and the harmonic wave component cancel each other out in the differential signal (Sd), and theoretically the voltage value is "0." On the other hand, when there is displacement of the rotor 36 in the thrust direction, the signal level of the fundamental wave component of the combined signal on one side (e.g., combined signal (S24)) decreases in accordance with the amount of displacement, while the signal level of the fundamental wave component of the combined signal on the other side (e.g., combined signal (S68)) hardly changes. Therefore, the difference value (voltage value) of the fundamental wave component in the differential signal (Sd) increases in accordance with the amount of displacement.

[0059] The connection unit 50 is an interface to which the detection coils C1 to C8 are connected. The common paths Lc1 and Lc2, the detection coils C3, C4, C7, and C8, and the signal processing circuits 51a to 51d are connected to the connection unit 50. The common paths Lc1 and Lc2 are connected to the ground via the connection unit 50.

[0060] The signal processing circuits 51a to 51d are connected to the corresponding sets of detection coils C1 to C8, and perform predetermined signal processing (rectification, AC-DC conversion) on the corresponding composite signals (S13, S57, S24, S68) to convert the composite signals (S13, S57, S24, S68) from AC to DC. The signal processing circuits 51a to 51d include, for example, a filter circuit, a rectifier circuit, and an integrator circuit. The signal processing circuits 51a to 51d are connected to the A / D converter 52. The signal processing circuits 51c and 51d are connected to the A / D converter 52 and the offset processing unit 56.

[0061] The A / D converter 52 converts the analog signals input from the signal processing circuits 51a to 51d, the arithmetic circuit 56c and the absolute difference conversion circuit 56d, which will be described later, into digital signals and outputs them to the control unit 53.

[0062] The control unit 53 controls the operation of the entire device 5. The control unit 53 is composed of, for example, a processor such as a CPU (Central Processing Unit) 53a, a volatile memory such as a RAM (Random Access Memory) 53b that functions as a working area for the CPU 53a, and a non-volatile memory such as a ROM (Read Only Memory) 53c that stores various information such as the estimation program and other control programs. The control unit 53 includes a first acquisition unit 530, an estimation unit 531, a setting unit 532, a second acquisition unit 533, and a wear amount detection unit 534.

[0063] The present estimation program runs in the control unit 53, and cooperates with the hardware resources of the present device 5 to realize the present estimation method described below. By causing a processor (CPU 53a) included in the control unit 53 to execute the present estimation program, the present estimation program can cause the processor to function as a first acquisition unit 530, an estimation unit 531, and a setting unit 532, and can cause the processor to execute the present estimation method. Furthermore, by causing a computer to execute the present estimation program, the present estimation program can cause the computer to function as the present device 5 (the present estimation device).

[0064] In the present invention, the estimation program may be stored in the storage unit 54. Also, the estimation program may be stored in a non-transitory storage medium (e.g., a compact disc (CD), a digital versatile disc (DVD), a universal serial bus (USB) memory, etc.) in an installable file format or an executable file format, and may be provided to the device 5 via a dedicated read-in medium.

[0065] The first acquisition unit 530 acquires thrust input data and radial input data. The thrust input data, the radial input data, and the operation of the first acquisition unit 530 will be described in detail below. The first acquisition unit 530 is an example of an acquisition unit in the present invention.

[0066] The estimation unit 531 inputs the thrust input data acquired by the first acquisition unit 530 to the thrust learning model M11 to estimate a thrust adjustment value. The estimation unit 531 also inputs the radial input data acquired by the first acquisition unit 530 to the radial learning model M12 to estimate a radial adjustment value. Details of the thrust learning model M11, the thrust adjustment value, the radial learning model M12, the radial adjustment value, and the operation of the estimation unit 531 will be described later.

[0067] The setting unit 532 sets a thrust determination criterion based on the thrust adjustment value estimated by the estimation unit 531. The setting unit 532 also sets a radial determination criterion based on the radial adjustment value estimated by the estimation unit 531. The thrust determination criterion, the radial determination criterion, and the operation of the setting unit 532 will be described in detail later.

[0068] The second acquisition unit 533 acquires the composite signal (S13, S57) and the differential signal (Sd). A specific operation of the second acquisition unit 533 will be described later.

[0069] The wear amount detection unit 534 detects the amount of wear in the radial direction of the bearings 32, 33 based on the voltage value of each composite signal (S13, S57). The wear amount detection unit 534 also detects the amount of wear in the thrust direction of the bearings 32, 33 based on the voltage value of the differential signal (Sd). The specific operation of the wear amount detection unit 534 will be described later.

[0070] The storage unit 54 stores information (e.g., offset information, first correspondence information, second correspondence information, thrust learning model M11, and radial learning model M12) necessary for the operation of the device 5. The storage unit 54 is, for example, a non-volatile memory such as an EEPROM (Electrically Erasable Programmable Read-Only Memory) or a flash memory.

[0071] The “offset information” is information (e.g., a voltage value) indicating an offset voltage to be added to or subtracted from the composite signal (S24) in the offset processing described below. The offset information is calculated in advance under rated conditions, for example, and stored in the storage unit 54.

[0072] "Offset processing" refers to processing for adding or subtracting an offset voltage to the composite signal (S24) so ​​that the difference value (voltage value of the difference signal (Sd)) between the composite signal (S24) and the composite signal (S68) correctly indicates the displacement amount of the rotor 36 in the thrust direction (the wear amount of the bearings 32, 33 in the thrust direction) under rated conditions. In this embodiment, the offset voltage is an addition signal. By the offset processing, the magnetic center position of the rotor 36 relative to the stator 37 in the thrust direction is virtually aligned with the mechanical center position of the rotor 36 relative to the stator 37 in the thrust direction (the two center positions coincide).

[0073] The "first correspondence information" is information indicating the correspondence between the position (displacement amount) in the thrust direction of the rotor 36 relative to the stator 37 and the difference value between the composite signal (S24) and the composite signal (S68) under rated conditions. In other words, the first correspondence information indicates the correspondence between the wear amount in the thrust direction of the bearings 32, 33 under rated conditions and the voltage value of the differential signal (Sd). The first correspondence information includes, for example, the voltage value at the front maximum position, the voltage value at the rear maximum position, and the voltage value at the intermediate position. The voltage values ​​at the front maximum position, the rear maximum position, and the intermediate position are examples of thrust determination criteria in the present invention, and are information included in the adjustment value in the present invention.

[0074] The "front maximum position" refers to the position where the rotor 36 moves to the front direction by the maximum extent when the bearing 32 wears to the maximum allowable extent in the thrust direction. The front maximum position is set according to the design of the bearing 32, and is, for example, a position that is "n" times (for example, n=2) the length from the intermediate position to the front position. In other words, the front maximum position is set based on the front position. The ratio of the voltage value of the differential signal (Sd) to the voltage value at the front maximum position corresponds to the distance that the rotor 36 moves in the front direction from the intermediate position (in other words, the amount of wear in the thrust direction of the bearing 32).

[0075] The "rear maximum position" refers to the position at which the rotor 36 moves to the rear direction by the maximum extent when the bearing 33 wears to the maximum allowable extent in the thrust direction. The rear maximum position is set according to the design of the bearing 33, and is, for example, a position that is "n" times the length from the intermediate position to the rear position. In other words, the rear maximum position is set based on the rear position. The ratio of the voltage value of the differential signal (Sd) to the voltage value at the rear maximum position corresponds to the distance that the rotor 36 moves to the rear direction from the intermediate position (in other words, the amount of wear in the thrust direction of the bearing 33).

[0076] The "second correspondence information" is information indicating the correspondence between the radial position (displacement amount) of the rotor 36 relative to the stator 37 and the voltage value of the composite signal (S13, S57) under rated conditions. In other words, the second correspondence information indicates the correspondence between the radial wear amount and voltage value of the bearings 32, 33 under rated conditions. The second correspondence information includes the voltage value at the center position and the voltage value at the radial maximum position. The voltage values ​​at the front maximum position, rear maximum position, and intermediate position are examples of radial determination criteria in the present invention, and are information included in the adjustment value in the present invention.

[0077] The "radial maximum position" refers to the position where the rotor 36 moves the maximum in the radial direction when the bearings 32, 33 have worn to the maximum allowable amount in the radial direction. The radial maximum position is set according to the design of the bearings 32, 33, and is, for example, a position that is "n" times the length from the center position to the radial position. The ratio of the voltage value of the composite signal (S13, S57) to the voltage value at the radial maximum position corresponds to the distance that the rotor 36 has moved in the radial direction from the center position (in other words, the amount of wear in the radial direction of the bearings 32, 33).

[0078] The display unit 55 displays the wear state of the bearings 32 and 33 .

[0079] FIG. 9 is a functional block diagram of the offset processing unit 56.

[0080] The offset processing section 56 executes offset processing based on the offset information, and includes a D / A converter 56a, an offset voltage generating circuit 56b, an arithmetic circuit 56c, and a difference absolute value conversion circuit 56d.

[0081] The D / A converter 56a converts the offset information from a digital signal to an analog signal.

[0082] The offset voltage generating circuit 56b generates an offset voltage to be added to or subtracted from the composite signal (S24) based on the offset information converted into an analog signal.

[0083] The arithmetic circuit 56c performs offset processing on the composite signal (S24) by adding or subtracting an offset voltage to the composite signal (S24), and calculates the difference between the composite signal (S24) after the offset processing and the composite signal (S68).

[0084] The differential absolute value conversion circuit 56d converts the differential value calculated by the arithmetic circuit 56c into an absolute value. A signal indicating this absolute value (hereinafter referred to as the “difference signal (Sd)”) is converted into a digital signal by the A / D converter 52 and input to the control unit 53.

[0085] ● Adjusting correspondence As described above, the detection coils C1 to C8 generate detection signals indicating changes in magnetic flux corresponding to changes in position (displacement) of the rotor 36 relative to the stator 37. The device 5 detects the amount of displacement of the rotor 36 (amount of wear of the bearings 32, 33) based on the detection signals. Therefore, it is necessary to adjust the correspondence (first correspondence information, second correspondence information) between the amount of wear of the bearings 32, 33 (amount of displacement of the rotor 36) and the voltage value of the detection signals so that the detection signals correctly indicate the amount of wear of the bearings 32, 33. Hereinafter, the adjustment of the correspondence will be described taking the adjustment of the correspondence in the thrust direction as an example.

[0086] Even if the rotor 36 moves within the movable range in the thrust direction, the bearings 32 and 33 are not worn. That is, when the rotor 36 is located at the front position, the bearing 32 is not worn. On the other hand, when the rotor 36 is located on the front side of the front position, the bearing 32 is worn. The same is true for the rear side. Therefore, the voltage value of the differential signal (Sd) at the front position and the rear position is a threshold value indicating a state in which the bearings 32 and 33 are not worn. The voltage value of the differential signal (Sd) is approximately proportional to the displacement amount of the rotor 36 (the wear amount of the bearings 32 and 33). Therefore, for example, when the voltage value at the front position is "V1" and the wear amount of the bearing 32 is "Lx1", the voltage value "Vx" in a state in which the rotor 36 has moved a length "Lx (Ls1 + Lx1)" from the center position is expressed as "Vx = (Lx / Ls1) × V1". Therefore, the composite signals (S24, S68) at the front and rear positions are information necessary for adjusting the corresponding relationship in the thrust direction.

[0087] Furthermore, when the rotor 36 is located at the intermediate position, the mechanical center position of the rotor 36 coincides with the mechanical center position of the stator 37 in the thrust direction. At this time, the voltage value of the differential signal (Sd) should be "0", but in reality, the position (magnetic center position) where the voltage value of the differential signal (Sd) is "0" is shifted from the mechanical center position. As described above, information required to coincide the two center positions is offset information. This offset information is calculated based on the voltage value of the composite signal (S24, S68) at the intermediate position. In other words, the voltage value of the composite signal (S24, S68) at the intermediate position is information required to adjust the correspondence in the thrust direction.

[0088] Usually, the voltage values ​​of the composite signal (S24, S68) at each rotor position cannot be obtained unless an operator moves the rotor 36 to each position and pumps the pumped liquid in that state. That is, to obtain these voltage values, the operator must move the rotor 36 multiple times and pump the pumped liquid multiple times. In other words, the adjustment of the above-mentioned correspondence requires multiple manual machine operations by the operator, which requires a lot of man-hours. On the other hand, the present device 5 estimates these voltage values ​​by inputting thrust input data into the thrust learning model M11, as described later. That is, in the present device 5, the operator does not need to operate the machine or pump the liquid to obtain these voltage values, and the man-hours are limited to inputting the input data. Therefore, the present device 5 can reduce the man-hours required for adjustment.

[0089] Learning model Next, the thrust learning model M11 and the radial learning model M12 will be described below. In the following description, FIG. 1 and FIG. 6 will be referred to as appropriate.

[0090] FIG. 10 is a schematic diagram showing an example of information (thrust learning model M11, radial learning model M12) stored in the storage unit 54. As shown in FIG.

[0091] The "thrust learning model M11" is a machine learning algorithm (learning model) that has been trained to output a thrust adjustment value when thrust input data is input. The thrust learning model M11 is generated in advance by, for example, a machine learning device and stored in the storage unit 54.

[0092] The "radial learning model M12" is a learned learning model that has been machine-learned to output a radial adjustment value when radial input data is input. The radial learning model M12 is generated in advance by, for example, a machine learning device and stored in the storage unit 54.

[0093] Machine learning is performed, for example, by subjecting training data to machine learning by a known machine learning algorithm (for example, a neural network having an input layer, multiple intermediate layers, and an output layer). The "training data" includes information that serves as input data (thrust input data, radial input data) for the machine learning algorithm (learning model), and information that serves as output data (teaching data) associated with the input data.

[0094] "Input data" is an explanatory variable in machine learning, and in this embodiment includes thrust input data and radial input data.

[0095] The "output data" is a response variable in machine learning, and in this embodiment includes thrust output data and radial output data.

[0096] "Thrust input data" is data that affects the thrust output data and includes rotor position, thrust play length, motor frame number, and rated frequency.

[0097] "Radial input data" is data that affects the radial output data, and includes rotor position, motor frame number, and rated frequency.

[0098] The "thrust output data" is the voltage value of the composite signal (S24, S68) corresponding to each rotor position before the above-mentioned adjustment of the correspondence relationship. Specifically, the thrust output data is the voltage value "V sff " and the voltage value of the composite signal (S68) "V srf ", the voltage value of the composite signal (S24) at the middle position "V sfc " and the voltage value of the composite signal (S68) "V src " or the voltage value of the composite signal (S24) at the rear position "V sfr " and the voltage value of the composite signal (S68) "V srr ", and these voltage values ​​"V sff " "V srf " "V sfc " "V src" "V sfr " "V srr " is an example of the thrust adjustment value in the present invention, and is information included in the adjustment value in the present invention. That is, in this embodiment, the thrust adjustment value is sff " "V srf " "V sfc " "V src " "V sfr " "V srr " is included.

[0099] The "radial output data" is the voltage value of the composite signal (S13, S57) corresponding to the rotor position in the state before the above-mentioned adjustment of the correspondence. Specifically, the radial output data is the voltage value "V rff " and the voltage value of the composite signal (S57) "V rrf ", the voltage value of the composite signal (S13) at the middle position "V rfc " and the voltage value of the composite signal (S57) "V rrc " or the voltage value of the composite signal (S13) at the rear position "V rfr " and the voltage value of the composite signal (S57) "V rrr ", and these voltage values ​​"V rff " "V rrf " "V rfc " "V rrc " "V rfr " "V rrr " is an example of the radial adjustment value in the present invention, and is information included in the adjustment value in the present invention. That is, in this embodiment, the radial adjustment value is rff " "V rrf " "V rfc " "V rrc " "V rfr " "V rrr " is included.

[0100] The "rotor position" is the position of the rotor 36 relative to the stator 37 in the thrust direction, and is either the front position, the rear position, or the middle position. A numerical value such as "0", "1", or "2" is assigned to each rotor position. Here, the voltage value of the differential signal (Sd) becomes smaller as the rear position moves from the middle position to the rear direction. The voltage value of the differential signal (Sd) becomes smaller as the front position moves from the middle position to the front direction. Therefore, the voltage value of the differential signal (Sd) at the front position and the rear position changes according to the thrust play length. That is, there is a correlation between the voltage value of the differential signal (Sd) at the front position and the rear position and the thrust play length. In other words, there is a correlation between the voltage value of the composite signal (S24, S68) and the thrust play length.

[0101] The "motor frame number" is different from the frame number specified in "JIS C 4210" and is a number set for each model of the motor unit 3, which is associated with not only the size of the motor unit 3 but also the rated output value of the motor unit 3 and the number of turns of the detection coils C1 to C8 (hereinafter simply referred to as "the number of turns"). That is, the motor frame number defines a combination of the size of the motor unit 3, the rated output value of the motor unit 3, and the number of turns. In other words, the motor frame number defines a combination of the size of the motor unit 3, the rated current value of the motor unit 3, the rated voltage value of the motor unit 3, and the number of turns. That is, the motor frame number includes the rated current value of the motor unit 3, the rated voltage value of the motor unit 3, and the number of turns. The voltage value of the composite signal (S13, S57, S24, S68) increases and decreases inversely to the increase or decrease of the rated current value, increases and decreases proportionally to the increase or decrease of the rated voltage value, and increases and decreases proportionally to the increase or decrease of the rated frequency. That is, there is a correlation between the voltage value of the composite signal (S13, S57, S24, S68) and the rated current value, rated voltage value, and rated frequency. Also, the voltage value of the composite signal (S13, S57, S24, S68) increases or decreases according to an increase or decrease in the number of turns of the detection coils C1 to C8. That is, there is a correlation between the voltage value of the composite signal (S13, S57, S24, S68) and the number of turns. In other words, there is a correlation between the voltage value of the composite signal (S13, S57, S24, S68) and the motor frame number.

[0102] In this way, there is a correlation between the thrust input data and the thrust output data. As described above, the learning data for machine learning of the thrust learning model M11 (thrust learning data) is generated based on data (big data) accumulated during past adjustments of the correspondence. That is, for example, thrust input data for each adjustment (rotor position, thrust play length, motor frame number, and rated frequency) and thrust output data corresponding to the thrust input data (voltage value of the composite signal (S24, S68) corresponding to the rotor position) are extracted from the big data. The extracted thrust input data and thrust output data are associated with each other to generate one thrust learning data.

[0103] In addition, there is a correlation between the radial input data and the radial output data, except for the rotor position. In this embodiment, the learning data (radial learning data) for machine learning of the radial learning model M12 is generated based on the above-mentioned big data. That is, for example, the radial input data (rotor position, motor frame number, and rated frequency) for each adjustment and the radial output data (voltage value of the composite signal (S13, S57) corresponding to the rotor position) corresponding to the radial input data are extracted from the big data. The extracted radial input data and radial output data are associated with each other to generate one radial learning data.

[0104] The thrust learning model M11 thus generated can output a voltage value of the composite signal (S24, S68) corresponding to the rotor position by inputting thrust input data (rotor position, thrust play length, motor frame number, and rated frequency) as shown in Fig. 10. That is, the thrust learning model M11 is machine-trained to output a voltage value of the composite signal (S24, S68) corresponding to the rotor position when the rotor position, thrust play length, motor frame number (rated current, rated voltage, number of turns), and rated frequency are input as input data. Similarly, the radial learning model M12 is machine-trained to output a voltage value of the composite signal (S13, S57) corresponding to the rotor position when the rotor position, motor frame number (rated current, rated voltage, number of turns), and rated frequency are input as input data.

[0105] In the present invention, the machine learning algorithm used for machine learning is not limited to a neural network. That is, for example, the machine learning algorithm may be a random forest, a decision tree, a support vector machine, or the like.

[0106] ● Operation of the motor bearing wear monitor Next, the operation of the pump 1 will be described below, focusing on the operation of the device 5 before shipment of the pump 1. In the following description, Figs. 1 to 10 will be referred to as appropriate.

[0107] FIG. 11 is a flowchart showing an example of the operation of the present device 5.

[0108] For example, the device 5 executes a thrust adjustment value estimation process (ST1), a radial adjustment value estimation process (ST2), and a judgment criterion setting process (ST3) before shipping the pump 1. The device 5 also executes a wear amount detection process (ST4) during operation of the pump 1. The thrust adjustment value estimation process (ST1) and the radial adjustment value estimation process (ST2) are examples of this estimation method.

[0109] As described above, before the pump 1 is shipped, the above-mentioned correspondence needs to be adjusted so that the voltage values ​​of the detection coils C1 to C8 indicate the amounts of wear of the bearings 32 and 33.

[0110] Thrust adjustment value estimation process FIG. 12 is a flowchart showing an example of the thrust adjustment value estimation process (ST1).

[0111] The "thrust adjustment value estimation process (ST1)" is a process in which the device 5 (control unit 53) estimates the voltage value (thrust adjustment value) of the composite signal (S24, S68) by using the thrust learning model M11.

[0112] First, the first acquisition unit 530 acquires thrust input data (rotor position, thrust play length, motor frame number, and rated frequency) of the pump 1 (ST11: acquisition step). The thrust input data of the pump 1 is acquired by the first acquisition unit 530, for example, by an adjuster of the pump 1 inputting the data to the device 5 using an input device (not shown).

[0113] Next, the estimation unit 531 inputs the thrust input data acquired by the first acquisition unit 530 to the thrust learning model M11, and estimates a voltage value of the composite signal (S24, S68) corresponding to the rotor position (ST12: estimation step). The estimated voltage value is associated with information indicating the rotor position and stored, for example, in the storage unit 54. Specifically, when the rotor position is the front position, the estimation unit 531 estimates a voltage value corresponding to the front position.

[0114] Next, the control unit 53 determines whether or not the voltage values ​​at all rotor positions have been estimated (ST13). When the voltage values ​​at all rotor positions have not been estimated, that is, when there is a rotor position at which the voltage value has not been estimated ("N" in ST13), the thrust adjustment value estimation process (ST1) returns to the process (ST11). On the other hand, when the voltage values ​​at all rotor positions have been estimated ("Y" in ST13), the thrust adjustment value estimation process (ST1) ends.

[0115] In this way, the device 5 estimates the thrust adjustment value by inputting thrust input data to the thrust learning model M11. Therefore, the device 5 does not require the operator to operate the machine or send liquid to obtain these voltage values, and the labor required is only to input the input data. Therefore, the device 5 can reduce the labor required for adjustment.

[0116] ●Radial adjustment value estimation process FIG. 13 is a flowchart showing an example of the radial adjustment value estimation process (ST2).

[0117] The "radial adjustment value estimation process (ST2)" is a process in which the device 5 (control unit 53) estimates the voltage value (radial adjustment value) of the composite signal (S13, S57) by using the radial learning model M12.

[0118] First, the first acquisition unit 530 acquires radial input data (rotor position, motor frame number, and rated frequency) of the pump 1 (ST21: acquisition step). The radial input data of the pump 1 is acquired by the first acquisition unit 530, for example, by an adjuster of the pump 1 inputting the data to the device 5 using an input device (not shown).

[0119] Next, the estimation unit 531 inputs the radial input data acquired by the first acquisition unit 530 to the radial learning model M12, and estimates a voltage value of the composite signal (S13, S57) corresponding to the rotor position (ST22: estimation step). The estimated voltage value is associated with information indicating the rotor position and stored in, for example, the storage unit 54. Specifically, when the rotor position is the rear position, the estimation unit 531 estimates a voltage value corresponding to the radial position at the rear position.

[0120] Next, the control unit 53 determines whether or not the voltage values ​​at all rotor positions have been estimated (ST23). When the voltage values ​​at all rotor positions have not been estimated, that is, when there is a rotor position at which the voltage value has not been estimated ("N" in ST23), the radial adjustment value estimation process (ST2) returns to the process (ST21). On the other hand, when the voltage values ​​at all rotor positions have been estimated ("Y" in ST23), the radial adjustment value estimation process (ST2) ends.

[0121] Adjusting the radial direction correspondence, like adjusting the thrust direction correspondence, requires multiple manual machine operations by an operator, resulting in a large number of man-hours. On the other hand, the present device 5 estimates these voltage values ​​(radial adjustment values) by inputting radial input data into the radial learning model M12. In other words, the present device 5 does not require machine operation or liquid transfer by an operator to obtain these voltage values, and the man-hours involved are limited to inputting the input data. Therefore, the present device 5 can reduce the man-hours required for adjustment.

[0122] ● Criteria setting process FIG. 14 is a flowchart showing an example of the judgment criterion setting process (ST3).

[0123] The "criterion setting process (ST3)" is a process for setting a thrust judgment criterion and a radial judgment criterion based on the estimated voltage value.

[0124] First, the setting unit 532 acquires the voltage value (thrust adjustment value) of the composite signal (S24, S68) estimated by the estimation unit 531 from the storage unit 54 (ST31).

[0125] Next, the setting unit 532 calculates a thrust determination criterion based on the acquired thrust adjustment value (ST32). Specifically, the setting unit 532 calculates a difference value of the voltage value corresponding to the intermediate position. Next, the setting unit 532 adds the difference value to the voltage value of the composite signal (S24) to calculate a difference value between the voltage value of the composite signal (S24) after the addition and the voltage value of the composite signal (S68). At this time, the difference value corresponding to the intermediate position is "0". Next, the setting unit 532 calculates "n" times each difference value as the thrust determination criterion.

[0126] Next, the setting unit 532 sets the calculated thrust determination criterion as the latest thrust determination criterion of the device 5 (ST33).

[0127] Next, the setting unit 532 acquires the voltage value (radial adjustment value) of the composite signal (S13, S57) estimated by the estimation unit 531 from the storage unit 54 (ST34).

[0128] Next, the setting unit 532 calculates a radial judgment criterion based on the acquired radial adjustment value (ST35). Specifically, the setting unit 532 compares the voltage value of the composite signal (S13) at a predetermined rotor position (e.g., the front position) with the voltage value of the composite signal (S57). Next, the setting unit 532 selects the larger voltage value from the voltage value of the composite signal (S13) and the voltage value of the composite signal (S57). Next, the setting unit 532 calculates "n" times the selected voltage value as the radial judgment criterion.

[0129] Next, the setting unit 532 sets the calculated radial judgment criterion as the latest radial judgment criterion of the device 5 (ST36).

[0130] ●Wear amount detection processing The "wear amount detection process (ST4)" is a process for detecting the amount of wear of the bearings 32, 33 based on each composite signal (S13, S57, S24, S68). Since the wear amount detection process (ST4) is a known process, a detailed description thereof will be omitted.

[0131] The detection coils C1 to C8 constantly output detection signals during rotation of the rotor 36. The second acquisition unit 533 acquires the composite signal (S13, S57) and the differential signal (Sd).

[0132] In the wear amount detection process (ST4), the wear amount detection unit 534 detects the amount of wear in the radial direction of the bearings 32, 33 based on the second correspondence information and the composite signal (S13, S57). Also, the wear amount detection unit 534 detects the amount of wear in the thrust direction of the bearings 32, 33 based on the first correspondence information and the difference signal (Sd).

[0133] Summary According to the embodiment described above, the device 5 includes a storage unit 54, a first acquisition unit 530, and an estimation unit 531. The storage unit 54 stores a thrust learning model M11. The thrust learning model M11 is machine-trained to output a thrust adjustment value when thrust input data is input. The thrust input data includes at least a rotor position, a thrust play length, a rated current value, and a number of turns. The rotor position is any one of a front position, a rear position, and a middle position. The thrust adjustment value is a voltage value of the composite signal (S24, S68) when the rotor 36 is located at the front position, the rear position, and the middle position, respectively. According to this configuration, manual machine operation for adjusting the correspondence (first correspondence information) is not required. As a result, in the pump 1, the man-hours for adjustment are significantly reduced.

[0134] Moreover, according to the embodiment described above, the thrust input data includes the rated voltage value and the rated frequency of the motor unit 3. According to this configuration, the estimation accuracy of the thrust adjustment value by the thrust learning model M11 is improved.

[0135] Furthermore, according to the embodiment described above, the thrust input data includes the motor frame number instead of the number of turns and the rated voltage value. This configuration reduces the amount of data required for machine learning. Also, it becomes easier to generate thrust learning data.

[0136] Furthermore, according to the embodiment described above, the memory unit 54 stores the radial learning model M12. The radial learning model M12 is machine-trained to output a radial adjustment value when radial input data is input. The radial input data includes at least the rated current value and the number of turns. The radial adjustment value is the voltage value of the composite signal (S13, S57) when the rotor 36 is located at the radial position. According to this configuration, liquid transfer for adjusting the correspondence (second correspondence information) is not required.

[0137] ●Estimation device● Next, a second embodiment of the present estimation device will be described below, taking as an example a case where the present estimation device is separate from the present pump. In the following description, the same elements as those in the first embodiment and elements having common functions are given the same reference numerals as those in the first embodiment for convenience of explanation, and the explanation thereof will be omitted. In the following description, Figures 1 to 5 will be referred to as appropriate.

[0138] Configuration of the estimation device FIG. 15 is a functional block diagram of the present estimation device, showing another embodiment (second embodiment) of the present estimation device.

[0139] The present estimation device 6 estimates the adjustment value of the present device 5. The present estimation device 6 includes a communication unit 60, an operation unit 61, a display unit 62, a control unit 63, and a storage unit 64. The present estimation device 6 is realized, for example, by a PC (Personal Computer). In the second embodiment, the present estimation device 6 estimates a thrust judgment criterion as the thrust adjustment value, and estimates a radial judgment criterion as the radial adjustment value. That is, the adjustment value includes the thrust judgment criterion and the radial judgment criterion.

[0140] The communication unit 60 is, for example, a communication module or a communication interface. The communication unit 60 is connected to the device 5, for example, via a telecommunication line.

[0141] The operation unit 61 is a device operated (for example, to input information such as input data) by a user (for example, an adjustment worker) of the present estimation device 6. The operation unit 61 is, for example, a keyboard, a mouse, or a touch panel.

[0142] The display unit 62 is a device that displays an input screen for information input by the operation unit 61 and information output by the control unit 63. The display unit 62 is, for example, a monitor or a display.

[0143] The control unit 63 controls the overall operation of the present estimation device 6. The control unit 63 is configured with, for example, a processor such as a CPU 63a, a volatile memory such as a RAM 63b that functions as a working area for the CPU 53a, and a non-volatile memory such as a ROM 63c that stores various information such as the present estimation program. The control unit 63 includes an acquisition unit 630 and an estimation unit 631.

[0144] The present estimation program runs in the control unit 63, and cooperates with the hardware resources of the present estimation device 6 to realize the present estimation method described below. By causing a processor (CPU 63a) included in the control unit 63 to execute the present estimation program, the present estimation program can cause the processor to function as an acquisition unit 630 and an estimation unit 631, and can cause the processor to execute the present estimation method. Furthermore, by causing a computer to execute the present estimation program, the present estimation program can cause the computer to function as the present estimation device 6.

[0145] In the present invention, the present estimation program may be stored in the storage unit 64. Also, the present estimation program may be stored in a non-transitory storage medium (e.g., a CD, a DVD, a USB memory, etc.) in an installable file format or an executable file format, and provided to the present estimation device 6 via a dedicated reading medium.

[0146] The acquisition unit 630 acquires the thrust input data and the radial input data. The operation of the acquisition unit 630 will be described in detail later.

[0147] The estimation unit 631 inputs the thrust input data acquired by the acquisition unit 630 to the thrust learning model M21 to estimate a thrust adjustment value (thrust judgment criterion). The estimation unit 631 also inputs the radial input data acquired by the acquisition unit 630 to the radial learning model M22 to estimate a radial adjustment value (radial judgment criterion). The operation of the estimation unit 631 will be described in detail later.

[0148] The storage unit 64 stores information (for example, the thrust learning model M21 and the radial learning model M22) necessary for the operation of the estimation device 6. The storage unit 64 is, for example, a non-volatile memory such as an EEPROM or a flash memory.

[0149] Learning model Next, the thrust learning model M21 and the radial learning model M22 will be described below. In the following description, FIG. 15 will be referred to as appropriate.

[0150] FIG. 16 is a schematic diagram showing an example of information (thrust learning model M21, radial learning model M22) stored in the storage unit 64. As shown in FIG.

[0151] The "thrust learning model M21" is a trained learning model that is trained to output a thrust judgment criterion when thrust input data is input. The thrust learning model M21 is generated in advance by, for example, a machine learning device and stored in the storage unit 64.

[0152] The "radial learning model M22" is a trained learning model that has been machine-learned to output a radial judgment criterion when radial input data is input. The radial learning model M22 is generated in advance by, for example, a machine learning device and stored in the storage unit 64.

[0153] The "thrust output data" is a thrust judgment criterion, and specifically, the difference between the voltage value of the composite signal (S24) after the offset processing at the front maximum position and the voltage value of the composite signal (S68) (i.e., the voltage value of the differential signal (Sd)) "V df ", and the difference value at the maximum rear position "V dr ” and the difference value at the intermediate position “V dc " In the first embodiment, these difference values ​​(thrust determination criteria) are calculated based on the voltage values ​​of the composite signals (S24, S68) at each rotor position. There is a correlation between these difference values ​​and the thrust input data. Therefore, there is also a correlation between the thrust determination criteria and the thrust input data.

[0154] In this way, there is a correlation between the thrust input data and the thrust output data. The learning data (thrust learning data) for machine learning of the thrust learning model M21 is generated based on the big data described above. That is, for example, thrust input data for each adjustment (rotor position, thrust play length, motor frame number, and rated frequency) and thrust output data (thrust judgment criterion) corresponding to the thrust input data are extracted from the big data. The extracted thrust input data and thrust output data are associated with each other to generate one piece of thrust learning data.

[0155] The "radial output data" is the radial judgment standard, specifically, the voltage value "V d " As described above, the radial judgment criterion is calculated based on the voltage values ​​of the composite signals (S13, S57) at the radial position. There is a correlation between these voltage values ​​and the radial input data. Therefore, there is also a correlation between the radial judgment criterion and the radial input data.

[0156] In addition, there is a correlation between the radial input data and the radial output data. The learning data (radial learning data) for machine learning of the radial learning model M22 is generated based on the above-mentioned big data. That is, for example, the radial input data (rotor position, motor frame number, and rated frequency) for each adjustment and the radial output data (radial judgment criterion) corresponding to the radial input data are extracted from the big data. The extracted radial input data and radial output data are associated with each other to generate one radial learning data.

[0157] The thrust learning model M21 thus generated is capable of outputting a thrust judgment criterion by inputting thrust input data (rotor position, thrust play length, motor frame number, and rated frequency) as shown in Fig. 16. That is, the thrust learning model M21 is machine-trained to output a thrust judgment criterion when the rotor position, thrust play length, motor frame number (rated current, rated voltage, number of turns), and rated frequency are input as input data. Similarly, the radial learning model M22 is machine-trained to output a radial judgment criterion when the rotor position, motor frame number (rated current, rated voltage, number of turns), and rated frequency are input as input data.

[0158] Operation of the estimation device Next, the operation of the present estimating device 6 will be described below.

[0159] FIG. 17 is a flowchart showing an example of the operation of the estimation device 6.

[0160] The estimation device 6 executes the thrust adjustment value estimation process (ST5) and the radial adjustment value estimation process (ST6) before, for example, shipping of the pump 1. The thrust adjustment value estimation process (ST5) and the radial adjustment value estimation process (ST6) are examples of the present method.

[0161] Thrust adjustment value estimation process FIG. 18 is a flowchart showing an example of the thrust adjustment value estimation process (ST5).

[0162] The "thrust adjustment value estimation process (ST5)" is a process in which the estimation device 6 (control unit 63) estimates a thrust judgment standard (thrust adjustment value) using the thrust learning model M21.

[0163] First, the acquisition unit 630 acquires thrust input data (rotor position, thrust play length, motor frame number, and rated frequency) of the pump 1 (ST51: acquisition step). The thrust input data of the pump 1 is acquired by the acquisition unit 630, for example, by an adjuster of the pump 1 inputting the data to the estimation device 6 using the operation unit 61.

[0164] Next, the estimation unit 631 inputs the thrust input data acquired by the acquisition unit 630 to the thrust learning model M21, and estimates a voltage value corresponding to the position of the thrust determination reference (front maximum position, rear maximum position, or intermediate position) (ST52: estimation step). The estimated voltage value is associated with information indicating the position of the thrust determination reference, and is stored, for example, in the storage unit 64. Specifically, when the rotor position is the front position, the estimation unit 631 estimates a voltage value corresponding to the front maximum position.

[0165] Next, the control unit 63 determines whether or not the voltage values ​​at all rotor positions have been estimated (ST53). When the voltage values ​​at all rotor positions have not been estimated ("N" in ST53), the thrust adjustment value estimation process (ST5) returns to the process (ST51). On the other hand, when the voltage values ​​at all rotor positions have been estimated ("Y" in ST53), the thrust adjustment value estimation process (ST5) ends. The estimated voltage value is set in the device 5 as the thrust determination standard.

[0166] ●Radial adjustment value estimation process FIG. 19 is a flowchart showing an example of the radial adjustment value estimation process (ST6).

[0167] The "radial adjustment value estimation process (ST6)" is a process in which the estimation device 6 (control unit 63) estimates the radial determination standard (radial adjustment value) by using the radial learning model M22.

[0168] First, the acquisition unit 630 acquires radial input data (rotor position, motor frame number, and rated frequency) of the pump 1 (ST61: acquisition step). The radial input data of the pump 1 is acquired by the acquisition unit 630, for example, by an adjuster of the pump 1 inputting the data to the estimation device 6 using the operation unit 61.

[0169] Next, the estimation unit 631 inputs the radial input data acquired by the acquisition unit 630 to the radial learning model M22 to estimate the voltage value at the radial maximum position (ST62: estimation step). The estimated voltage value is associated with information indicating the radial maximum position and is stored in, for example, the storage unit 64. The estimated voltage value is set in the device 5 as a radial judgment criterion.

[0170] Summary According to the embodiment described above, the present estimation device 6 includes a storage unit 64, an acquisition unit 630, and an estimation unit 631. The storage unit 64 stores a thrust learning model M21. The thrust learning model M21 is machine-trained to output a thrust adjustment value when thrust input data is input. The thrust input data includes at least a rotor position, a thrust play length, a rated current value, and a number of turns. The rotor position is any one of a front position, a rear position, and an intermediate position. The thrust adjustment value is a voltage value of a differential signal (Sd) when the rotor 36 is located at each of a front maximum position, a rear maximum position, and an intermediate position. According to this configuration, a human machine operation for adjusting the correspondence (first correspondence information) is not required. As a result, in the present pump 1, the man-hours for adjustment are significantly reduced.

[0171] Moreover, according to the embodiment described above, the thrust input data includes the rated voltage value and the rated frequency of the motor unit 3. According to this configuration, the estimation accuracy of the thrust adjustment value by the thrust learning model M21 is improved.

[0172] Furthermore, according to the embodiment described above, the thrust input data includes the motor frame number instead of the number of turns and the rated voltage value. This configuration reduces the amount of data required for machine learning. Also, it becomes easier to generate thrust learning data.

[0173] Furthermore, according to the embodiment described above, the storage unit 64 stores the radial learning model M22. The radial learning model M22 is machine-trained to output a radial adjustment value when radial input data is input. The radial input data includes at least the rated current value and the number of turns. The radial adjustment value is the larger voltage value among the voltage values ​​of the composite signal (S13, S57) when the rotor 36 is located at the radial maximum position. According to this configuration, liquid transfer for adjusting the correspondence (second correspondence information) is not required.

[0174] ●Other embodiments● In each embodiment, the thrust input data for machine learning may include at least the rated current value, thrust play length, number of turns, and rotor position of the motor unit 3, and may not include the rated voltage value and / or rated frequency. In this case, when the rated current value, thrust play length, number of turns, and rotor position are input, the thrust learning model M11 outputs the voltage value of the composite signal (S24, S68) corresponding to the rotor position as the thrust adjustment value. Also, when the rated current value, thrust play length, number of turns, and rotor position are input, the thrust learning model M21 outputs the difference value of the position corresponding to the rotor position as the thrust adjustment value. In this configuration, the estimation accuracy of the thrust adjustment value may be lower than that of each embodiment. However, the estimation accuracy is sufficient to monitor the wear state of the bearings 32 and 33 by the present device 5.

[0175] In each embodiment, the value of the composite signal (S13) at each rotor position is approximately the same, and the value of the composite signal (S57) at each rotor position is also approximately the same. Therefore, the radial input data only needs to include the rated current value and the number of turns of the motor unit 3 at at least one rotor position, and does not need to include the rotor position. In this case, when the rated current value and the number of turns are input, the radial learning model M12 outputs the voltage value of the composite signal (S13) or the composite signal (S57) as the radial adjustment value. Also, when the rated current value and the number of turns are input, the radial learning model M22 outputs the voltage value of the radial maximum position as the radial adjustment value. In this configuration, the estimation accuracy of the radial adjustment value may be lower than that of each embodiment. However, the estimation accuracy is sufficient to monitor the wear state of the bearings 32, 33 by the present device 5.

[0176] Furthermore, in the first embodiment, the storage unit 54 may store a thrust learning model M21. In this case, the estimation unit 531 estimates a difference value as the thrust adjustment value.

[0177] Furthermore, in the second embodiment, the storage unit 64 may store the thrust learning model M11. In this case, the estimation unit 631 estimates the voltage value of the composite signal (S24, S68) as the thrust adjustment value. The control unit 63 may function as the setting unit 532.

[0178] Furthermore, in the first embodiment, the storage unit 54 may store the radial learning model M22. In this case, the estimation unit 631 estimates the voltage value at the radial maximum position as the radial adjustment value.

[0179] Furthermore, in the second embodiment, the storage unit 64 may store the radial learning model M12. In this case, the estimation unit 631 estimates the voltage value of the composite signal (S13, S57) as the radial adjustment value. The control unit 63 may function as the setting unit 532.

[0180] Furthermore, in the second embodiment, the thrust learning model M21 may output not only the difference values ​​but also offset information as the thrust adjustment values. In this case, the thrust learning data of the thrust learning model M21 also includes the offset information.

[0181] Furthermore, in the first embodiment, the device 5 may execute processes (ST1 to ST3) to update the thrust judgment criterion and the radial judgment criterion when the drive frequency (rated frequency) is changed by inverter control. When the drive frequency is changed by the inverter, the voltage values ​​of the detection signals of the detection coils C1 to C8 change, causing technical problems such as erroneous detection due to a deviation in the correspondence relationship. Therefore, manual adjustment of the correspondence relationship is required every time the drive frequency is changed. In this configuration, even if the drive frequency is changed by the inverter, the device 5 can adjust the correspondence relationship without manual mechanical operation.

[0182] Furthermore, in the second embodiment, the device 5 does not necessarily have to include the first acquisition unit 530, the estimation unit 531, and the setting unit 532.

[0183] ●Embodiments of the present invention● Next, the embodiments of the present invention as understood from the above-described embodiments will be described below, using the terms and symbols described in the respective embodiments.

[0184] The first embodiment of the present invention estimates an adjustment value of a motor bearing wear monitoring device (e.g., motor bearing wear monitoring device 5) that monitors the wear state of a bearing (e.g., bearings 32, 33) supporting a rotating shaft (e.g., rotating shaft 31) of a rotor based on detection signals from a plurality of detection coils (e.g., detection coils C1 to C8) that detect magnetic flux changes corresponding to position changes of a rotor (e.g., rotor 36) relative to a stator (e.g., stator 37) of a motor (e.g., motor unit 3) of a canned motor pump (e.g., canned motor pump 1). An estimation device (e.g., a control unit 53, an estimation device 6), wherein each of the plurality of detection coils is attached to the stator and outputs the detection signal indicating the magnetic flux change, the plurality of detection coils include a plurality of thrust detection coils (e.g., detection coils C2, C4, C6, C8) that detect the magnetic flux change in a thrust direction of the rotating shaft, and the plurality of thrust detection coils include a pair of first thrust detection coils (e.g., detection coils C2, C4) and another pair of second thrust detection coils (e.g., detection coils C6,C8), in which the first thrust detection coil is disposed at an end of the stator on one side in the thrust direction, and the second thrust detection coil is disposed at an end of the stator on the other side in the thrust direction, and the adjustment value includes a thrust adjustment value in the thrust direction, and the thrust adjustment value includes a thrust determination criterion for the wear state in the thrust direction that can be calculated based on a voltage value of a first thrust resultant signal (e.g., a resultant signal (S24)) obtained by combining the detection signals output from the first thrust detection coils and a voltage value of a second thrust resultant signal (e.g., a resultant signal (S68)) obtained by combining the detection signals output from the second thrust detection coils, or the voltage value of the first thrust resultant signal and the voltage value of the second thrust resultant signal, when the rotor is located at a first position (e.g., a front position), a second position (e.g., a rear position), and a third position (e.g., an intermediate position) relative to the stator, respectively, and the second position is a position where the rotor has moved to the maximum in the one direction relative to the stator within a mechanical movable range of the rotating shaft relative to the stator, the second position is a position where the rotor has moved to the maximum in the other direction relative to the stator within the movable range, and the third position is an intermediate position between the first position and the second position, and a thrust input including a rated current value of the motor, a length of the movable range, a number of turns of the detection coil, and a position of the rotor relative to the stator in the thrust direction The estimation device includes a memory unit (e.g., memory units 54, 64) that stores a trained thrust learning model (e.g., thrust learning models M11, M21) that has been machine-learned to output the thrust adjustment value when data is input, an acquisition unit (e.g., a first acquisition unit 530, an acquisition unit 630) that acquires the thrust input data, and an estimation unit (e.g., estimation units 531, 631) that inputs the thrust input data acquired by the acquisition unit into the thrust learning model to estimate the thrust adjustment value. According to this configuration, the number of adjustment steps is significantly reduced.

[0185] A second embodiment of the present invention is an estimation device according to the first embodiment, wherein the thrust input data includes a rated voltage value of the motor and / or a rated frequency of the motor. According to this configuration, the estimation accuracy of the thrust adjustment value by the thrust learning model is improved.

[0186] A third embodiment of the present invention is an estimation device according to the first embodiment, wherein the thrust input data includes, instead of the number of turns, a motor frame number that defines a combination of the motor output, the motor size, and the number of turns. According to this configuration, the amount of data required for machine learning is reduced, making it easier to generate thrust training data.

[0187] A fourth embodiment of the present invention is the first embodiment, wherein the plurality of detection coils include a plurality of radial detection coils (e.g., detection coils C1, C3, C5, C7) that detect the magnetic flux change in the radial direction of the rotating shaft, and the plurality of radial detection coils include a set of first radial detection coils (e.g., detection coils C1, C3) and another set of second radial detection coils (e.g., detection coils C5, C7), and in the thrust direction, the first radial detection coil is disposed at an end of the stator on the one side, and the second radial detection coil is disposed at an end of the stator on the other side, the bearing is a sliding bearing lubricated by a handled fluid of the canned motor pump, the adjustment value includes a radial adjustment value in the radial direction, and the radial adjustment value is a first radial composite signal (e.g., a composite signal) obtained by combining the detection signals output from each of the first radial detection coils when the rotor relative to the stator is located at a fourth position (e.g., a radial position). the fourth position is a position at which the rotor has moved to the maximum extent in the radial direction relative to the stator within a mechanical movable range of the rotating shaft relative to the bearing in the radial direction; the memory unit stores a trained radial learning model (e.g., radial learning models M12, M22) that has been machine-trained to output the radial adjustment value when radial input data including the rated current value and the number of turns is input; the acquisition unit acquires the radial input data; and the estimation unit inputs the radial input data acquired by the acquisition unit into the radial learning model to estimate the radial adjustment value. According to this configuration, there is no need to send liquid for adjusting the correspondence (second correspondence information).

[0188] A fifth embodiment of the present invention is an estimation program (for example, this estimation program) that causes a computer to function as the estimation device according to the first embodiment. According to this configuration, the number of adjustment steps is significantly reduced.

[0189] A sixth embodiment of the present invention relates to an estimation device (e.g., control unit 53, estimation device 6) that estimates an adjustment value of a motor bearing wear monitoring device (e.g., motor bearing wear monitoring device 5) that monitors a wear state of a bearing (e.g., bearings 32, 33) supporting a rotating shaft (e.g., rotating shaft 31) of a rotor (e.g., motor unit 3) of a canned motor pump (e.g., canned motor pump 1) based on detection signals of each of a plurality of detection coils (e.g., detection coils C1 to C8) that detect a magnetic flux change corresponding to a position change of the rotor (e.g., rotor 36) relative to a stator (e.g., stator 37) of the motor of the canned motor pump. In the method for estimating the adjustment value (e.g., thrust adjustment value estimation process (ST1, ST5)) executed by the above-mentioned method, each of the plurality of detection coils is attached to the stator and outputs the detection signal indicating the magnetic flux change, the plurality of detection coils include a plurality of thrust detection coils (e.g., detection coils C2, C4, C6, C8) that detect the magnetic flux change in a thrust direction of the rotating shaft, and the plurality of thrust detection coils include a pair of first thrust detection coils (e.g., detection coils C2, C4) and another pair of second thrust detection coils (e.g., detection coils C6,C8), in which the first thrust detection coil is disposed at an end of the stator on one side in the thrust direction, and the second thrust detection coil is disposed at an end of the stator on the other side in the thrust direction, and the adjustment value includes a thrust adjustment value in the thrust direction, and the thrust adjustment value is a value obtained by calculating a thrust adjustment value output from each of the first thrust detection coils when the rotor is located at a first position (e.g., a front position), a second position (e.g., a rear position), and a third position (e.g., an intermediate position) relative to the stator. a thrust determination criterion for the wear state in the thrust direction, which is generated based on a voltage value of a first thrust resultant signal (e.g., a resultant signal (S24)) obtained by combining detection signals and a voltage value of a second thrust resultant signal (e.g., a resultant signal (S68)) obtained by combining the detection signals output from each of the second thrust detection coils, or based on the voltage value of the first thrust resultant signal and the voltage value of the second thrust resultant signal, and the first position is within a mechanical movable range of the rotating shaft relative to the bearing in the thrust direction. the first position is a position where the rotor has moved to the maximum in the one direction relative to the stator, the second position is a position where the rotor has moved to the maximum in the other direction relative to the stator within the movable range, and the third position is an intermediate position between the first position and the second position, and the estimation device outputs the thrust adjustment value when thrust input data including a rated current value of the motor, a length of the movable range, a number of turns of the detection coil, and a position of the rotor relative to the stator in the thrust direction is input. The estimation method includes a storage unit (e.g., storage units 54, 64) that stores a trained thrust learning model (e.g., thrust learning models M11, M21) that has been machine-learned to estimate the thrust adjustment value, and includes an acquisition step (e.g., acquisition step (ST11, ST51)) in which the estimation device acquires the thrust input data, and an estimation step (e.g., estimation step (ST12, ST52)) in which the estimation device inputs the thrust input data acquired by the acquisition step into the thrust learning model to estimate the thrust adjustment value. According to this configuration, the number of adjustment steps is significantly reduced.

[0190] A seventh embodiment of the present invention is a motor bearing wear monitoring device (e.g., motor bearing wear monitoring device 5) that monitors a wear state of a bearing (e.g., bearings 32, 33) supporting a rotating shaft (e.g., rotating shaft 31) of a canned motor pump (e.g., canned motor pump 1) based on detection signals of a plurality of detection coils (e.g., detection coils C1 to C8) that detect a magnetic flux change corresponding to a position change of a rotor (e.g., rotor 36) relative to a stator (e.g., stator 37) of the motor (e.g., motor unit 3). Each of the plurality of detection coils is attached to the stator and outputs the detection signal indicating the magnetic flux change. The plurality of detection coils include a plurality of thrust detection coils (e.g., detection coils C2, C4, C6, C8) that detect the magnetic flux change in the thrust direction of the rotating shaft, and the plurality of thrust detection coils include a set of first thrust detection coils (e.g., detection coils C2, C4) and another set of second thrust detection coils (e.g., detection coils C6,C8), in which, in the thrust direction, the first thrust detection coil is disposed at an end of the stator on one side, and the second thrust detection coil is disposed at an end of the stator on the other side, and the motor includes a storage unit (e.g., storage unit 54) that stores a trained thrust learning model (e.g., thrust learning model M11) that has been machine-learned to output a thrust adjustment value when thrust input data including a rated current value of the motor, a length of a mechanically movable range of the rotating shaft relative to the bearing in the thrust direction, a number of turns of the detection coil, and a position of the rotor relative to the stator in the thrust direction is input, an acquisition unit (e.g., first acquisition unit 530) that acquires the thrust input data, and an estimation unit (e.g., estimation unit 531) that inputs the thrust input data acquired by the acquisition unit into the thrust learning model to estimate the thrust adjustment value, and the thrust adjustment value is calculated based on the thrust adjustment value when the rotor is at a first position (e.g., The motor bearing wear monitoring device includes a voltage value of a first thrust composite signal (e.g., composite signal (S24)) obtained by combining the detection signals output from the first thrust detection coils, a voltage value of a second thrust composite signal (e.g., composite signal (S68)) obtained by combining the detection signals output from the second thrust detection coils, or a thrust judgment criterion for the wear state in the thrust direction that can be calculated based on the voltage value of the first thrust composite signal and the voltage value of the second thrust composite signal when the rotor is located at a first position (e.g., a front position), a second position (e.g., a rear position), and a third position (e.g., an intermediate position), respectively, the first position being a position where the rotor has moved maximally in the one direction relative to the stator within the movable range, the second position being a position where the rotor has moved maximally in the other direction relative to the stator within the movable range, and the third position being an intermediate position between the first position and the second position. According to this configuration, the number of adjustment steps is significantly reduced.

[0191] An eighth embodiment of the present invention is a canned motor pump (e.g., canned motor pump 1) comprising a rotor (e.g., rotor 36), a stator (e.g., stator 37) that rotates the rotor, a rotating shaft (e.g., rotating shaft 31) to which the rotation of the rotor is transmitted, a bearing (e.g., bearings 32, 33) that rotatably supports the rotating shaft, a plurality of detection coils (e.g., detection coils C1 to C8) attached to the stator and detecting magnetic flux changes corresponding to positional changes of the rotor relative to the stator, and a motor bearing wear monitoring device (e.g., motor bearing wear monitoring device 5) that monitors the wear state of the bearings based on output signals from the detection coils, wherein the motor bearing wear monitoring device is the motor bearing wear monitoring device described in the seventh embodiment. According to this configuration, the number of adjustment steps is significantly reduced. [Explanation of symbols]

[0192] 1 Canned motor pump 3 Motor section (motor) 5. Motor bearing wear monitoring device 53 Control unit (estimation device) 530 1st Acquisition Department (Acquisition Department) 531 Estimation Department 54 Memory section 6 Estimation device 630 Acquisition Department 631 Estimation Department 64 Memory section C1, C3 Detector coil (radial detector coil, first radial detector coil) C5, C7 Detector coils (radial detector coil, second radial detector coil) C2, C4 detection coil (thrust detection coil, first thrust detection coil) C6, C8 Detector coils (thrust detector coil, second thrust detector coil) M11 Thrust Learning Model M12 Radial Learning Model M21 Thrust Learning Model M22 Radial Learning Model

Claims

1. 1. An estimation device for estimating an adjustment value of a motor bearing wear monitoring device that monitors a wear state of a bearing supporting a rotating shaft of a rotor, based on detection signals from a plurality of detection coils that detect a magnetic flux change corresponding to a position change of a rotor relative to a stator of a motor of a canned motor pump, the estimation device comprising: Each of the plurality of detection coils is attached to the stator and outputs the detection signal indicative of the magnetic flux change, The plurality of detection coils include a plurality of thrust detection coils for detecting the change in the magnetic flux in the thrust direction of the rotating shaft; Including, The plurality of thrust detection coils include A pair of first thrust detection coils; Another pair of second thrust detection coils; Including, In the thrust direction, The first thrust detection coil is disposed at one end of the stator, the second thrust detection coil is disposed at the other end of the stator, The adjustment value is a thrust adjustment value in the thrust direction; Including, The thrust adjustment value is a voltage value of a first thrust resultant signal obtained by combining the detection signals output from the first thrust detection coils, and a voltage value of a second thrust resultant signal obtained by combining the detection signals output from the second thrust detection coils, when the rotor is located at a first position, a second position, and a third position relative to the stator, respectively; or a thrust determination criterion for the wear state in the thrust direction, the criterion being calculable based on the voltage value of the first thrust resultant signal and the voltage value of the second thrust resultant signal; Including, the first position is a position at which the rotor has moved maximally in the one direction relative to the stator within a mechanical movable range of the rotating shaft relative to the bearing in the thrust direction, the second position is a position where the rotor has moved to the maximum extent in the other direction relative to the stator within the movable range, the third position is an intermediate position between the first position and the second position, a memory unit that stores a trained thrust learning model that has been machine-learned to output the thrust adjustment value when thrust input data including a rated current value of the motor, a length of the movable range, a number of turns of the detection coil, and a position of the rotor relative to the stator in the thrust direction is input; and an acquisition unit that acquires the thrust input data; an estimation unit that inputs the thrust input data acquired by the acquisition unit into the thrust learning model to estimate the thrust adjustment value; It is made of Estimation device.

2. The thrust input data is the rated voltage value of the motor and / or the rated frequency of the motor; Including, The estimation device according to claim 1 .

3. The thrust input data is a motor frame number that defines a combination of the motor output, the motor size, and the number of turns, instead of the number of turns; Including, The estimation device according to claim 1 .

4. The plurality of detection coils include a plurality of radial detection coils for detecting the change in the magnetic flux in a radial direction of the rotating shaft; Including, The plurality of radial detection coils include a pair of first radial detection coils; Another pair of second radial detection coils; Including, In the thrust direction, The first radial detection coil is disposed at an end of the stator on the one side, the second radial detection coil is disposed at the end of the stator on the other side, the bearing is a sliding bearing lubricated by a pumped fluid of the canned motor pump, The adjustment value is A radial adjustment value in the radial direction; Including, The radial adjustment value is a voltage value of a first radial composite signal obtained by combining the detection signals output from the first radial detection coils, and a voltage value of a second radial composite signal obtained by combining the detection signals output from the second radial detection coils, when the rotor is located at a fourth position relative to the stator; or a radial determination criterion for the wear state in the radial direction, the radial determination criterion being generated based on the voltage value of the first radial resultant signal and the voltage value of the second radial resultant signal; Including, the fourth position is a position at which the rotor has moved to a maximum extent in the radial direction relative to the stator within a mechanical movable range of the rotating shaft relative to the bearing in the radial direction, The storage unit stores a trained radial learning model that has been machine-learned to output the radial adjustment value when radial input data including the rated current value and the number of turns is input, The acquisition unit acquires the radial input data, The estimation unit inputs the radial input data acquired by the acquisition unit into the radial learning model to estimate the radial adjustment value. The estimation device according to claim 1 .

5. A computer is caused to function as the estimation device according to claim 1. Estimation program.

6. 1. A method for estimating an adjustment value of a motor bearing wear monitoring device for monitoring a wear state of a bearing supporting a rotating shaft of a rotor, based on detection signals from a plurality of detection coils that detect a magnetic flux change corresponding to a position change of a rotor relative to a stator of a motor of a canned motor pump, the method being executed by an estimation device, the method comprising: Each of the plurality of detection coils is attached to the stator and outputs the detection signal indicative of the magnetic flux change, The plurality of detection coils include a plurality of thrust detection coils for detecting the change in the magnetic flux in the thrust direction of the rotating shaft; Including, The plurality of thrust detection coils include A pair of first thrust detection coils; Another pair of second thrust detection coils; Including, In the thrust direction, The first thrust detection coil is disposed at one end of the stator, the second thrust detection coil is disposed at the other end of the stator, The adjustment value is a thrust adjustment value in the thrust direction; Including, The thrust adjustment value is a voltage value of a first thrust resultant signal obtained by combining the detection signals output from the first thrust detection coils, and a voltage value of a second thrust resultant signal obtained by combining the detection signals output from the second thrust detection coils, when the rotor is located at a first position, a second position, and a third position relative to the stator, respectively; or a thrust determination criterion for the wear state in the thrust direction, the thrust determination criterion being generated based on the voltage value of the first thrust resultant signal and the voltage value of the second thrust resultant signal; Including, the first position is a position at which the rotor has moved maximally in the one direction relative to the stator within a mechanical movable range of the rotating shaft relative to the bearing in the thrust direction, the second position is a position where the rotor has moved to the maximum extent in the other direction relative to the stator within the movable range, the third position is an intermediate position between the first position and the second position, The estimation device includes: a memory unit that stores a trained thrust learning model that has been machine-learned to output the thrust adjustment value when thrust input data including a rated current value of the motor, a length of the movable range, a number of turns of the detection coil, and a position of the rotor with respect to the stator in the thrust direction is input; With an acquisition step in which the estimator acquires the thrust input data; an estimation step in which the estimation device inputs the thrust input data acquired in the acquisition step into the thrust learning model to estimate the thrust adjustment value; Including, Estimation method.

7. 1. A motor bearing wear monitoring device for monitoring a wear state of a bearing supporting a rotating shaft of a rotor of a canned motor pump, based on detection signals from a plurality of detection coils that detect a magnetic flux change corresponding to a position change of the rotor with respect to a stator of the motor, the device comprising: Each of the plurality of detection coils is attached to the stator and outputs the detection signal indicative of the magnetic flux change, The plurality of detection coils include a plurality of thrust detection coils for detecting the change in the magnetic flux in the thrust direction of the rotating shaft; Including, The plurality of thrust detection coils include A pair of first thrust detection coils; Another pair of second thrust detection coils; Including, In the thrust direction, The first thrust detection coil is disposed at one end of the stator, the second thrust detection coil is disposed at the other end of the stator, a memory unit that stores a trained thrust learning model that is machine-learned to output a thrust adjustment value when thrust input data including a rated current value of the motor, a length of a mechanically movable range of the rotating shaft relative to the bearing in the thrust direction, a number of turns of the detection coil, and a position of the rotor relative to the stator in the thrust direction is input; and an acquisition unit that acquires the thrust input data; an estimation unit that inputs the thrust input data acquired by the acquisition unit into the thrust learning model to estimate the thrust adjustment value; and The thrust adjustment value is a voltage value of a first thrust resultant signal obtained by combining the detection signals output from the first thrust detection coils, and a voltage value of a second thrust resultant signal obtained by combining the detection signals output from the second thrust detection coils, when the rotor is located at a first position, a second position, and a third position relative to the stator, respectively; or a thrust determination criterion for the wear state in the thrust direction, the thrust determination criterion being generated based on the voltage value of the first thrust resultant signal and the voltage value of the second thrust resultant signal; Including, the first position is a position where the rotor has moved to the maximum extent in the one direction relative to the stator within the movable range, the second position is a position where the rotor has moved to the maximum extent in the other direction relative to the stator within the movable range, The third position is an intermediate position between the first position and the second position. Motor bearing wear monitoring device.

8. A rotor; A stator that rotates the rotor; a rotating shaft to which the rotation of the rotor is transmitted; a bearing that rotatably supports the rotating shaft; a plurality of detection coils attached to the stator to detect magnetic flux changes corresponding to positional changes of the rotor relative to the stator; a motor bearing wear monitor that monitors a wear state of the bearing based on an output signal of the detection coil; and The motor bearing wear monitoring device is a motor bearing wear monitoring device according to claim 7. Canned motor pump.

Images